diff --git a/autoload.php b/autoload.php new file mode 100644 index 0000000..aeb5fcf --- /dev/null +++ b/autoload.php @@ -0,0 +1,97 @@ +setSafeMode(true); + +// HTML-Purifier +require_once ps(__DIR__ . $config["path"]["htmlpurifier"] . "/HTMLPurifier.auto.php"); +$purifier = new HTMLPurifier(HTMLPurifier_Config::createDefault()); + +// PHPMailer +use PHPMailer\PHPMailer\PHPMailer; +use PHPMailer\PHPMailer\Exception; + +require_once ps(__DIR__ . $config["path"]["phpmailer"] . "/Exception.php"); +require_once ps(__DIR__ . $config["path"]["phpmailer"] . "/PHPMailer.php"); +require_once ps(__DIR__ . $config["path"]["phpmailer"] . "/SMTP.php"); + +$mailer = new PHPMailer(true); + +// Smarty +require_once ps(__DIR__ . $config["path"]["smarty"] . "/Smarty.class.php"); +$smarty = new Smarty(); +$smarty->setTemplateDir(ps(__DIR__ . $config["smarty"]["template"] . "/" . $usertheme)); +$smarty->setConfigDir(ps(__DIR__ . $config["smarty"]["config"])); +$smarty->setCompileDir(ps(__DIR__ . $config["smarty"]["compile"])); +$smarty->setCacheDir(ps(__DIR__ . $config["smarty"]["cache"])); + +// Getting all plugins for the Theme +require ps(__DIR__ . $config["smarty"]["template"] . "/{$usertheme}/info.php"); +foreach ($theme["plugins"] as $reqPlugin) { + if (!file_exists(ps(__DIR__ . $config["path"]["plugins"] . "/enabled/" . $reqPlugin . ".php"))) + die("This theme requires following plugin to be enabled: " . $reqPlugin); + require_once ps(__DIR__ . $config["path"]["plugins"] . "/enabled/" . $reqPlugin . ".php"); +} + +// Plugins (Legacy) +// $plugins = glob(ps(__DIR__ . $config["path"]["plugins"] . "/enabled/*.php")); +// foreach ($plugins as $plugin) { +// require_once $plugin; +// } + +// And finally +$usertheme = getUserTheme($logged, $user["theme"] ?? ""); +$userlang = getUserLang($logged, $user["lang"] ?? ""); +$preflang = getPrefLang(); +require ps(__DIR__ . $config["smarty"]["template"] . "/{$usertheme}/info.php"); +require ps(__DIR__ . $config["path"]["langs"] . "/{$userlang}.php"); + +visit(); + +$smarty->assign("config", $config); +$smarty->assign("lang", $lang); +$smarty->assign("theme", $theme); +$smarty->assign("userlang", $userlang); +$smarty->assign("usertheme", $usertheme); +$smarty->assign("version", file_get_contents(ps(__DIR__ . "/version.txt"))); +$smarty->assign("logged", $logged); +$smarty->assign("user", $user); +$smarty->assign("preflang", $preflang); diff --git a/config.php b/config.php new file mode 100644 index 0000000..8288454 --- /dev/null +++ b/config.php @@ -0,0 +1,81 @@ + true, + "cache_lifetime" => null, + "timeout" => false, // deprecated! Set it to false! + "primary_key" => "id", + "search" => array( + "min_length" => 2, + "mode" => "or", + "score_key" => "scoreKey" + ), + "folder_permissions" => 0777 +); + +// MaxFileSize (in Bytes, visit https://www.gbmb.org/mb-to-bytes for help) +$config["mfs"]["cover"] = 5242880; // 5MB +$config["mfs"]["chapter"] = 52428800; // 50MB + +// Default-Variablen +$config["default"]["theme"] = "nucleus"; +$config["default"]["lang"] = "en"; +$config["default"]["avatar"] = "https://rav.h33t.moe/data/8c4f8647-4bec-420e-96e0-284125793baf.jpeg"; + +// Captcha +$config["captcha"]["enabled"] = false; +$config["captcha"]["type"] = "hcaptcha"; // "hcaptcha" +$config["captcha"]["hcaptcha"]["secret"] = ""; +$config["captcha"]["hcaptcha"]["sitekey"] = ""; + +// Themes and Languages +$config["themes"] = array( + "nucleus" => "Nucleus" +); +$config["langs"] = array( + "en" => "English", +); + +// Avatars +$config["avatars"] = array( + "https://rav.h33t.moe/data/8c4f8647-4bec-420e-96e0-284125793baf.jpeg", + "https://rav.h33t.moe/data/cf39f370-73f9-4428-bc65-136e1d509cc9.jpeg", + "https://rav.shishnet.org/af4cf8aadc45565bbeecb0ced4857ed5.jpeg", + "https://rav.shishnet.org/4f054d8a364b1cb658a458df687621c6.jpeg", + "https://rav.shishnet.org/21e78a09e342964a8c7ce20e410697d0.jpeg", + "https://rav.shishnet.org/436e8788f8ed655e9c74c54dc9947d00.jpeg", + "https://rav.shishnet.org/3737e6629146ba78fb4a84284357802a.gif", + "https://rav.shishnet.org/c6bbc472ba1ec7012620ac0c1b35491a.gif", +); + +// X elements per page for pagination +$config["perpage"]["titles"] = 25; +$config["perpage"]["chapters"] = 36; + +$config["path"]["sleek"] = "/software/SleekDB"; +$config["path"]["parsedown"] = "/software"; +$config["path"]["langs"] = "/library/langs"; +$config["path"]["htmlpurifier"] = "/software/HTMLPurifier"; +$config["path"]["smarty"] = "/software/Smarty"; +$config["path"]["plugins"] = "/library/plugins"; +$config["path"]["phpmailer"] = "/software/PHPMailer"; +$config["path"]["imagescrambler"] = "/software"; + +// Diese Software nutzt Smarty als Template-Engine. Dokumentation: https://smarty-php.github.io/smarty/ +$config["smarty"]["template"] = "/library/themes"; +$config["smarty"]["config"] = "/software/Smarty/config"; +$config["smarty"]["compile"] = "/software/Smarty/compile"; +$config["smarty"]["cache"] = "/software/Smarty/cache"; diff --git a/custom/format.json b/custom/format.json new file mode 100644 index 0000000..bb6705c --- /dev/null +++ b/custom/format.json @@ -0,0 +1,15 @@ +[ + "4-Koma", + "Adaption", + "Anthology", + "Award Winning", + "Doujinshi", + "Fan Colored", + "Fan Color", + "Full Color", + "Long Strip", + "Official Colored", + "Oneshot", + "User Created", + "Web Comic" +] diff --git a/custom/genre.json b/custom/genre.json new file mode 100644 index 0000000..e1c6421 --- /dev/null +++ b/custom/genre.json @@ -0,0 +1,27 @@ +[ + "Action", + "Adventure", + "Boys' Love", + "Comedy", + "Crime", + "Drama", + "Fantasy", + "Girls' Love", + "Historical", + "Horror", + "Isekai", + "Magical Girls", + "Mecha", + "Medical", + "Mystery", + "Philosophical", + "Psychological", + "Romance", + "Sci-Fi", + "Slice of Life", + "Sports", + "Superhero", + "Thriller", + "Tragedy", + "Wuxia" +] \ No newline at end of file diff --git a/custom/theme.json b/custom/theme.json new file mode 100644 index 0000000..e0ae5d9 --- /dev/null +++ b/custom/theme.json @@ -0,0 +1,39 @@ +[ + "Aliens", + "Animals", + "Cooking", + "Crossdressing", + "Delinquents", + "Demons", + "Genderswap", + "Ghosts", + "Gyaru", + "Harem", + "Incest", + "Loli", + "Mafia", + "Magic", + "Martial Arts", + "Military", + "Monster Girls", + "Monsters", + "Music", + "Ninja", + "Office Workers", + "Police", + "Post-Apocalyptic", + "Reincarnation", + "Reverse Harem", + "Samurai", + "School Life", + "Shota", + "Supernatural", + "Survival", + "Time Travel", + "Traditional Games", + "Vampires", + "Video Games", + "Villainess", + "Virtual Reality", + "Zombies" +] \ No newline at end of file diff --git a/custom/upload_langs.json b/custom/upload_langs.json new file mode 100644 index 0000000..436965c --- /dev/null +++ b/custom/upload_langs.json @@ -0,0 +1,22 @@ +[ + [ + "gb", + "English", + "๐Ÿ‡ฌ๐Ÿ‡ง" + ], + [ + "de", + "German", + "๐Ÿ‡ฉ๐Ÿ‡ช" + ], + [ + "pt", + "Portuguese", + "๐Ÿ‡ต๐Ÿ‡น" + ], + [ + "fr", + "French", + "๐Ÿ‡ซ๐Ÿ‡ท" + ] +] \ No newline at end of file diff --git a/custom/warnings.json b/custom/warnings.json new file mode 100644 index 0000000..7326b21 --- /dev/null +++ b/custom/warnings.json @@ -0,0 +1,5 @@ +[ + "Gore", + "Sexual Violence", + "Smut" +] \ No newline at end of file diff --git a/funky.php b/funky.php new file mode 100644 index 0000000..13ab425 --- /dev/null +++ b/funky.php @@ -0,0 +1,396 @@ + clean($action), + "success" => $success, + "value" => clean($value), + "user" => $user, + "ip" => clean($_SERVER["REMOTE_ADDR"]), + "timestamp" => now() + ); + $db->insert($data); + } + return true; +} + +function visit() +{ + require "config.php"; + require_once ps(__DIR__ . $config["path"]["sleek"] . "/Store.php"); + $db = new \SleekDB\Store("visitLogs", ps(__DIR__ . $config["db"]["sleek"]["dir"]), $config["db"]["sleek"]["config"]); // Logs + if (empty($db->findOneBy(["ip", "=", clean($_SERVER["REMOTE_ADDR"])]))) { + $data = array( + "ip" => clean($_SERVER["REMOTE_ADDR"]), + "timestamp" => now() + ); + $db->insert($data); + } +} + +function titleVisit($title) +{ + require "config.php"; + require_once ps(__DIR__ . $config["path"]["sleek"] . "/Store.php"); + $db = new \SleekDB\Store("titleViews", ps(__DIR__ . $config["db"]["sleek"]["dir"]), $config["db"]["sleek"]["config"]); // Logs + if (empty($db->findOneBy([["ip", "=", clean($_SERVER["REMOTE_ADDR"])], "AND", ["title.id", "=", $title["id"]]]))) { + $data = array( + "title" => $title, + "ip" => clean($_SERVER["REMOTE_ADDR"]), + "timestamp" => now() + ); + $db->insert($data); + } +} + +function chapterVisit($chapter) +{ + require "config.php"; + require_once ps(__DIR__ . $config["path"]["sleek"] . "/Store.php"); + $db = new \SleekDB\Store("chapterViews", ps(__DIR__ . $config["db"]["sleek"]["dir"]), $config["db"]["sleek"]["config"]); // Logs + if (empty($db->findOneBy([["ip", "=", clean($_SERVER["REMOTE_ADDR"])], "AND", ["chapter.id", "=", $chapter["id"]]]))) { + $data = array( + "chapter" => $chapter, + "ip" => clean($_SERVER["REMOTE_ADDR"]), + "timestamp" => now() + ); + $db->insert($data); + } +} + +function hCaptcha($response) +{ + require "config.php"; + $data = array( + "secret" => $config["captcha"]["hcaptcha"]["secret"], + "response" => $response + ); + $verify = curl_init(); + curl_setopt($verify, CURLOPT_URL, "https://hcaptcha.com/siteverify"); + curl_setopt($verify, CURLOPT_POST, true); + curl_setopt($verify, CURLOPT_POSTFIELDS, http_build_query($data)); + curl_setopt($verify, CURLOPT_RETURNTRANSFER, true); + $responseData = json_decode(curl_exec($verify)); + return $responseData->success ? true : false; +} + +function valCustom($file) +{ + require "config.php"; + require_once ps(__DIR__ . $config["path"]["sleek"] . "/Store.php"); + $db = new \SleekDB\Store("custom_" . $file, ps(__DIR__ . $config["db"]["sleek"]["dir"]), $config["db"]["sleek"]["config"]); + $file = file_exists(ps(__DIR__ . "/custom/{$file}.json")) ? file_get_contents(ps(__DIR__ . "/custom/{$file}.json")) : ""; + $data = jd($file); + $_data = $db->findAll(); + if (!empty($data)) { + sort($data); + foreach ($data as $dat) { + $dta = array( + "name" => $dat, + "timestamp" => now() + ); + if (empty($db->findOneBy(["name", "=", $dat]))) $db->insert($dta); + } + } + if (!empty($_data)) { + sort($_data); + foreach ($_data as $dat) { + if (!in_array($dat["name"], $data)) { + $db->deleteBy(["name", "=", $dat["name"]]); + } + } + return $_data; + } else { + return true; + } +} + +function valCLang($file) +{ + require "config.php"; + require_once ps(__DIR__ . $config["path"]["sleek"] . "/Store.php"); + $db = new \SleekDB\Store("custom_" . $file, ps(__DIR__ . $config["db"]["sleek"]["dir"]), $config["db"]["sleek"]["config"]); + $file = file_exists(ps(__DIR__ . "/custom/{$file}.json")) ? file_get_contents(ps(__DIR__ . "/custom/{$file}.json")) : ""; + $data = jd($file); + $_data = $db->findAll(); + if (!empty($_data)) { + sort($_data); + $langs = array_column($data, 0); + $langs = array_reverse($langs); + foreach ($_data as $dat) { + $found = false; + foreach ($langs as $l) { + if ($dat["code"] == $l) $found = true; + } + if (!$found) $db->deleteBy(["code", "=", $dat["code"]]); + } + } + if (!empty($data)) { + sort($data); + foreach ($data as $dat) { + $dta = array( + "code" => $dat[0], + "name" => $dat[1], + "flag" => $dat[2], + "timestamp" => now() + ); + if (empty($db->findOneBy(["code", "=", $dat[0]]))) $db->insert($dta); + } + } + return !empty($_data) ? $_data : true; +} + +function getTag($file, $id) +{ + $tags = valCustom($file); + foreach ($tags as $tg) { + if ($tg["id"] == $id) return $tg; + } + return null; +} + +function rmrf($dir) +{ + foreach (glob($dir) as $file) { + if (is_dir($file)) { + rmrf("$file/*"); + rmdir($file); + } else { + unlink($file); + } + } +} + +function valImage($location, $file) +{ + // Image? + $check = getimagesize($location); + if ($check == false) return "Fake image."; + // In array? + $filetypes = array("jpg", "jpeg", "png", "gif", "webp"); + if (!in_array(strtolower($file), $filetypes)) return "Invalid Image format."; + // Yes! + return true; +} + +function unzip($file, $tmp, $target) +{ + $zip = new ZipArchive; + $res = $zip->open($file); + if ($res !== true) die("Something!"); + + // extract it to the path we determined above + if (file_exists($tmp)) rmrf($tmp); + if (file_exists($target)) rmrf($target); + mkdir($tmp, 0755, true); + mkdir($target, 0755, true); + $zip->extractTo($tmp); + $files = glob("$tmp/*.{jpg,jpeg,webp,gif,png}", GLOB_BRACE); + if (empty($files)) return "No images in ZIP!"; + foreach ($files as $f) { + $check = getimagesize($f); + if ($check == false) { + return "An error occured."; + rmrf($tmp); + } + } + sort($files, SORT_STRING); + $c = 1; + foreach ($files as $_file) { + rename($_file, ps($target . "/{$c}." . strtolower(pathinfo($_file, PATHINFO_EXTENSION)))); + $c++; + } + $zip->close(); + rmrf($tmp); + unlink($file); + return "success"; +} + +function formatChapterTitle($volume, $chapter, $type = "short") +{ + switch ($type) { + case "full": + $type = "full"; + break; + case "short": + default: + $type = "short"; + } + $out = ""; + if (substr($chapter, -2) == ".00") { + $chapter = substr($chapter, 0, -3); + } elseif (substr($chapter, -1) == "0") { + $chapter = substr($chapter, 0, -1); + } + if ($type == "short") { + if (!empty($volume)) $out .= "Vol." . $volume . " "; + $out .= "Ch." . $chapter; + } + if ($type == "full") { + if (!empty($volume)) $out .= "Volume " . $volume . " "; + $out .= "Chapter " . $chapter; + } + return $out; +} + +function formatDate($date, $full = false) +{ + $date = clean($date); + + $s = $date; + $date = strtotime($s); + if ($full == false) { + return date('d. M Y', $date); + } else { + return date('d. M Y H:m:i', $date); + } +} + +function getUserLang($logged = false, $userlang = "") +{ + require "config.php"; + $userlang = $logged ? $userlang : cat($_COOKIE[cat($config["title"]) . "_lang"] ?? $config["default"]["lang"]); + if (!file_exists(ps(__DIR__ . $config["path"]["langs"] . "/{$userlang}.php"))) + $userlang = $config["default"]["lang"]; + return $userlang; +} + +function getUserTheme($logged = false, $usertheme = "") +{ + require "config.php"; + $usertheme = $logged ? $usertheme : cat($_COOKIE[cat($config["title"]) . "_theme"] ?? $config["default"]["theme"]); + if (!file_exists(ps(__DIR__ . $config["smarty"]["template"] . "/{$usertheme}/info.php"))) + $usertheme = $config["default"]["theme"]; + return $usertheme; +} + +function getPrefLang() +{ + require "config.php"; + return isset($_COOKIE[cat($config["title"]) . "_preflang"]) && !empty($_COOKIE[cat($config["title"]) . "_preflang"]) ? cat($_COOKIE[cat($config["title"]) . "_preflang"]) : $config["default"]["lang"]; +} + +function timeAgo($datetime, $full = false) +{ + // Thx - https://stackoverflow.com/questions/1416697/converting-timestamp-to-time-ago-in-php-e-g-1-day-ago-2-days-ago + $now = new DateTime; + $ago = new DateTime($datetime); + $diff = $now->diff($ago); + + $diff->w = floor($diff->d / 7); + $diff->d -= $diff->w * 7; + + $string = array( + 'y' => 'year', + 'm' => 'month', + 'w' => 'week', + 'd' => 'day', + 'h' => 'hour', + 'i' => 'min', + 's' => 'second', + ); + foreach ($string as $k => &$v) { + if ($diff->$k) { + $v = $diff->$k . ' ' . $v . ($diff->$k > 1 ? 's' : ''); + } else { + unset($string[$k]); + } + } + + if (!$full) $string = array_slice($string, 0, 1); + return $string ? implode(', ', $string) . ' ago' : 'just now'; +} + +// Only available in PHP 8.x which I don't like at all +if (!function_exists("str_contains")) { + function str_contains($haystack, $needle) + { + return $needle !== "" && mb_strpos($haystack, $needle) !== false; + } +} + +function shorten($text, $maxlength = 25) +{ + // This function is used, to display only a certain amount of characters + if (strlen($text) > $maxlength) + return substr($text, 0, $maxlength) . "..."; + return $text; +} diff --git a/library/langs/en.php b/library/langs/en.php new file mode 100644 index 0000000..70bfd7e --- /dev/null +++ b/library/langs/en.php @@ -0,0 +1,10 @@ + [ + "name" => "English", + "author" => "Saintly & S-VHS", + "website" => "https://h33t.moe", + "updated" => "30.03.2023" + ] +]; diff --git a/library/plugins/disabled/getRel.php b/library/plugins/disabled/getRel.php new file mode 100644 index 0000000..3c75bec --- /dev/null +++ b/library/plugins/disabled/getRel.php @@ -0,0 +1,14 @@ +assign("rel", clean($_GET["rel"])); diff --git a/library/plugins/disabled/keep.txt b/library/plugins/disabled/keep.txt new file mode 100644 index 0000000..ec3e524 --- /dev/null +++ b/library/plugins/disabled/keep.txt @@ -0,0 +1 @@ +Keep this, GitHub! \ No newline at end of file diff --git a/library/plugins/enabled/daisyTheme.php b/library/plugins/enabled/daisyTheme.php new file mode 100644 index 0000000..84e8c58 --- /dev/null +++ b/library/plugins/enabled/daisyTheme.php @@ -0,0 +1,17 @@ +assign("daisytheme", $daisytheme); + unset($daisytheme); +} diff --git a/library/plugins/enabled/logoImage.php b/library/plugins/enabled/logoImage.php new file mode 100644 index 0000000..ab0b085 --- /dev/null +++ b/library/plugins/enabled/logoImage.php @@ -0,0 +1,20 @@ +assign("logoImage", $logoImage); + unset($logoImage); + unset($usertheme); +} diff --git a/library/plugins/enabled/readChapters.php b/library/plugins/enabled/readChapters.php new file mode 100644 index 0000000..320934c --- /dev/null +++ b/library/plugins/enabled/readChapters.php @@ -0,0 +1,25 @@ +findBy(["user", "==", $user["id"]]); + $_readChapters = array(); + foreach ($readChapters as $key => $ch) { + array_push($_readChapters, $ch["chapter"]); + } + if (isset($smarty)) + $smarty->assign("readChapters", $_readChapters); + + unset($ch); + unset($_readChapters); + unset($readChapters); +} diff --git a/library/plugins/enabled/simpleAlert.php b/library/plugins/enabled/simpleAlert.php new file mode 100644 index 0000000..fbc04a5 --- /dev/null +++ b/library/plugins/enabled/simpleAlert.php @@ -0,0 +1,32 @@ + "info", // "", "info", "success", "warning", "error" + "content" => "Welcome to {$config["title"]}! To use all the functions such as commenting or Bookmarking, please create a free acount!", + "timestamp" => now() +); +// Database Insert +$db["alerts"]->insert($data); +*/ +$topAlert = $db["alerts"]->findAll(["id" => "DESC"], 1); +if (!empty($topAlert)) $topAlert = $topAlert[0]; +$readAlert = !empty($topAlert) ? ($logged ? (!empty($db["alertReads"]->findOneBy([["user", "=", $user["id"]], "AND", ["alert", "=", $topAlert["id"]]])) ? true : false) : false) : false; + +if (isset($smarty)) { + $smarty->assign("topAlert", $topAlert); + $smarty->assign("readAlert", $readAlert); + + unset($topAlert); + unset($readAlert); +} diff --git a/library/plugins/enabled/started.php b/library/plugins/enabled/started.php new file mode 100644 index 0000000..06164e6 --- /dev/null +++ b/library/plugins/enabled/started.php @@ -0,0 +1,4 @@ +assign("userlangs", $_userlangs); + unset($lang); + // unset($userlangs); + unset($_userlangs); +} diff --git a/library/secrets/README.txt b/library/secrets/README.txt new file mode 100644 index 0000000..5c70ec4 --- /dev/null +++ b/library/secrets/README.txt @@ -0,0 +1,6 @@ +DO NOT EDIT ANY OF THE SECRETS (pwease)! + +THIS WILL NOT ONLY BREAK THE SOFTWARE +BUT ALSO THE API - and I don't want that. + +- thanks, Saintly \ No newline at end of file diff --git a/library/themes/nucleus/info.php b/library/themes/nucleus/info.php new file mode 100644 index 0000000..d347c7e --- /dev/null +++ b/library/themes/nucleus/info.php @@ -0,0 +1,16 @@ + "Nucleus", + "author" => "Saintly2k, S-VHS and Kaligula", + "website" => "https://h33t.moe/", + "plugins" => [ + "daisyTheme", + "logoImage", + "readChapters", + "simpleAlert", + "started", + "userLangs" + ], + "version" => "2023-03-30" +]; diff --git a/library/themes/nucleus/pages/chapter.tpl b/library/themes/nucleus/pages/chapter.tpl new file mode 100644 index 0000000..f34a25f --- /dev/null +++ b/library/themes/nucleus/pages/chapter.tpl @@ -0,0 +1,3 @@ +{foreach from=$images item=item key=key name=name} + Page {$key + 1} +{/foreach} \ No newline at end of file diff --git a/library/themes/nucleus/pages/index.tpl b/library/themes/nucleus/pages/index.tpl new file mode 100644 index 0000000..0df581a --- /dev/null +++ b/library/themes/nucleus/pages/index.tpl @@ -0,0 +1,126 @@ +
+
+

+ + Recently Updated Titles + +

+
+ {if !empty($recentlyUpdated)} +
+ {foreach from=$recentlyUpdated item=item key=key name=name} +
+
+
+ + + +
+
+

+ {$item.title.title} +
+ {if $item.title.sstatus == 1}Planned{elseif $item.title.sstatus == 2}Ongoing{elseif $item.title.sstatus == 3}Hiatus{elseif $item.title.sstatus == 4}Completed{else}Cancelled{/if} +
+

+

{$item.title.alts}

+
+ {$item.title.summary2} +
+ +
+
+
+ {/foreach} +
+
+ {foreach from=$recentlyUpdated item=item key=key name=name} + {$key + 1} + {/foreach} +
+ {else} +

There are no Titles at the Moment!

+ {/if} +
+ + +
+

+ + Latest Releases + +

+ {if !empty($chapters)} +
+ {foreach from=$chapters item=item key=key name=name} +
+
+ + Cover + +
+
+

+ + + {shorten($item.title.title, 10)} + + + + + + + +

+
+

+ + {$item.language.2} + {formatChapterTitle($item.volume, $item.number)} + +

+

+ + + + {$item.user.username} + + +

+

+ {timeAgo($item.timestamp)} +

+
+
+
+ {/foreach} +
+ + More + +
+
+ {else} +

There are no Chapters on this page!

+ {/if} +
+ \ No newline at end of file diff --git a/library/themes/nucleus/pages/releases.tpl b/library/themes/nucleus/pages/releases.tpl new file mode 100644 index 0000000..1a4c59c --- /dev/null +++ b/library/themes/nucleus/pages/releases.tpl @@ -0,0 +1,86 @@ + +
+

+ Releases - Page {$page} +

+ {if !empty($chapters)} +
+ {foreach from=$chapters item=item key=key name=name} +
+
+ + Cover + +
+
+

+ + + {shorten($item.title.title, 10)} + + + + + + +

+
+

+ + {$item.language.2} + {formatChapterTitle($item.volume, $item.number)} + +

+

+ + + + {$item.user.username} + + +

+

+ {timeAgo($item.timestamp)} +

+
+
+
+ {/foreach} +
+ {else} +

There are no Chapters on this page!

+ {/if} + + {if !empty($pagis)} + +
+ {if $page > 1} + ยซ + โ€น + {/if} + {foreach from=$pagis item=item key=key name=name} + {if $page != $item} + {$item} + {else} + {$item} + {/if} + {/foreach} + {if $page < $totalPages} + โ€บ + ยป + {/if} +
+ + {/if} +
+ \ No newline at end of file diff --git a/library/themes/nucleus/pages/title.tpl b/library/themes/nucleus/pages/title.tpl new file mode 100644 index 0000000..c63facc --- /dev/null +++ b/library/themes/nucleus/pages/title.tpl @@ -0,0 +1,746 @@ + +
+
+

+ {$title.title} +
+ {if $title.sstatus == 1}Planned{elseif $title.sstatus == 2}Ongoing{elseif $title.sstatus == 3}Hiatus{elseif $title.sstatus == 4}Completed{else}Cancelled{/if} +
+ {if $logged && $user.level >= 75} + + {/if} +

+

{$title.alts}

+
+
+
+ + Cover + +
+
+ +
+

Details

+

+ Author/s: + {if !empty($title.authors)} + {foreach from=$title.authors item=item key=key name=name} + + + {trim($item)} + + + {/foreach} + {else} + Unknown + {/if} +

+

+ Artist/s: + {if !empty($title.artists)} + {foreach from=$title.artists item=item key=key name=name} + + + {trim($item)} + + + {/foreach} + {else} + Unknown + {/if} +

+

+ Release Year: + {if !empty($title.releaseYear)} + {$title.releaseYear} + {else} + Unknown + {/if} +

+

+ Completion Year: + {if !empty($title.completionYear)} + {$title.completionYear} + {else} + Unknown + {/if} +

+ +

Tags

+
+
+

Formats

+ {if !empty($title.tags.formats)} + {foreach from=$title.tags.formats item=item key=key name=name} + + + {trim($item.name)} + + + {/foreach} + {/if} +
+
+

Warnings

+ {if !empty($title.tags.warnings)} + {foreach from=$title.tags.warnings item=item key=key name=name} + + + {trim($item.name)} + + + {/foreach} + {/if} +
+
+

Themes

+ {if !empty($title.tags.themes)} + {foreach from=$title.tags.themes item=item key=key name=name} + + + {trim($item.name)} + + + {/foreach} + {/if} +
+
+

Genres

+ {if !empty($title.tags.genres)} + {foreach from=$title.tags.genres item=item key=key name=name} + + + {trim($item.name)} + + + {/foreach} + {/if} +
+
+
+
+ {if !empty($title.summary)} +
+

Summary

+
+ {$title.summary} +
+
+ {/if} +
+
+ + + +
+

+ Chapters + ({$chapterCount}) + {if $logged && $user.level >= 75} + + {/if} +

+ + {if !empty($chapterLangs.0.language.chapters)} +
+ {foreach from=$chapterLangs item=item key=key name=name} + {if count($chapterLangs) > 1} + + {/foreach} +
+ + +
+ {foreach from=$chapterLangs item=_lang key=lkey name=lname} + {if count($chapterLangs) > 1} +
+ {/if} + +
+ + + + + + + + + {if $logged && $user.level >= 75} + + {/if} + + + + {foreach from=$_lang.language.chapters item=item key=key name=name} + + + + + + + {if $logged && $user.level >= 75} + + {/if} + + {if $logged && $user.level >= 75} + +
+
+

Edit Chapter

+
+
+ + + + + + + + + + + + + + + +
+ + +
+
+ + {/if} + {/foreach} + +
+ ＃ + + + 𝕋 + + + @ + + + ⟲ + +
+ + + + + {formatChapterTitle($item.volume, $item.number, "short")} + + + + + + + {$item.name} + + + + + + + + + {formatDate($item.timestamp)} + + + +
+
+ + {if count($chapterLangs) > 1} +
+ {/if} + {/foreach} +
+ + {else} +

There are no chapters at the moment!

+ {/if} +
+ + + +
+

+ Comments + ({$commentsCount}) +

+ {if $logged && $user.level >= 50} + {*
+
+
+ + + + + + + +
+
+
+ +
+ +
+
+
*} + {/if} +
+ + + +{if $logged && $user.level >= 75} + +
+
+

Edit Title

+
+
+ + + Cover + + + + + + + + + + + + + + + + + + + + +
+
+

Select Tags

+
+
+

Format/s

+
+ {foreach from=$upl_format item=item key=key name=name} + + {/foreach} +
+
+
+

Warning/s

+
+ {foreach from=$upl_warnings item=item key=key name=name} + + {/foreach} +
+
+
+

Theme/s

+
+ {foreach from=$upl_theme item=item key=key name=name} + + {/foreach} +
+
+
+

Genre/s

+
+ {foreach from=$upl_genre item=item key=key name=name} + + {/foreach} +
+
+ +
+
+
+ + + + + + + +
+
+
+
+ +
+
+

Add Chapter

+
+
+ + + + + + + + + + + + + + +
+
+ +
+
+ + +{/if} \ No newline at end of file diff --git a/library/themes/nucleus/pages/titles.tpl b/library/themes/nucleus/pages/titles.tpl new file mode 100644 index 0000000..163393b --- /dev/null +++ b/library/themes/nucleus/pages/titles.tpl @@ -0,0 +1,235 @@ + +
+

+ Titles - Page {$page} + {if $logged && $user.level >= 75} + Add Title + {/if} +

+ {if !empty($titles)} +
+ {foreach from=$titles item=item key=key name=name} +
+
+
+ + Cover + +
+
+

+ + {$item.title} + +

+
+ + {if $item.sstatus == 1}Planned{elseif $item.sstatus == 2}Ongoing{elseif $item.sstatus == 3}Hiatus{elseif $item.sstatus == 4}Completed{else}Cancelled{/if} + +
+
+
+
+ {/foreach} +
+ {else} +

There are no Titles on this page!

+ {/if} + + {if !empty($pagis)} +
+ {if $page > 1} + ยซ + โ€น + {/if} + {foreach from=$pagis item=item key=key name=name} + {if $page != $item} + {$item} + {else} + {$item} + {/if} + {/foreach} + {if $page < $totalPages} + โ€บ + ยป + {/if} +
+ {/if} +
+ + +{if $logged && $user.level >= 75} + +
+
+

Add Title

+
+
+ + + + + + + + + + + + + + + + + + + + + + +
+
+

Select Tags

+
+
+

Format/s

+
+ {foreach from=$upl_format item=item key=key name=name} + + {/foreach} +
+
+
+

Warning/s

+
+ {foreach from=$upl_warnings item=item key=key name=name} + + {/foreach} +
+
+
+

Theme/s

+
+ {foreach from=$upl_theme item=item key=key name=name} + + {/foreach} +
+
+
+

Genre/s

+
+ {foreach from=$upl_genre item=item key=key name=name} + + {/foreach} +
+
+ +
+
+
+ + + + + + + +
+
+
+
+ + +{/if} \ No newline at end of file diff --git a/library/themes/nucleus/parts/alert.tpl b/library/themes/nucleus/parts/alert.tpl new file mode 100644 index 0000000..b987129 --- /dev/null +++ b/library/themes/nucleus/parts/alert.tpl @@ -0,0 +1,41 @@ +{if !empty($topAlert) && !$readAlert} +
+
+ + {if $topAlert.type == "info"} + + {elseif $topAlert.type == "success"} + + {elseif $topAlert.type == "warning"} + + {else} + + {/if} + + {ucfirst($topAlert.type)}: {$topAlert.content} +
+ {if $logged} +
+ +
+ {/if} +
+{/if} + +{if $logged && $user.level == 49} +
+
+ + + + Info: Activate your account through the Email we sent you to use all functions of {$config.title}! +
+
+{/if} \ No newline at end of file diff --git a/library/themes/nucleus/parts/footer.tpl b/library/themes/nucleus/parts/footer.tpl new file mode 100644 index 0000000..87f3a26 --- /dev/null +++ b/library/themes/nucleus/parts/footer.tpl @@ -0,0 +1,322 @@ + + + +{if (isset($rel) && $rel != 'tab') || !isset($rel)} + {if !$logged} + +
+
+

Login

+
+
+ + +
+
+ +
+ +
+ + +
+
+
+
+ + +
+
+

Signup

+
+
+ + + + + +
+
+ +
+ +
+ + +
+
+
+
+ {else} + +
+
+

User Settings

+
+
+ + +
+
+ +
+ +
+ +
+
+
+
+ {/if} + + + + + +
+
+

Change Design

+ {$daisyThemes = array("light", "dark", "cupcake", "bumblebee", "emerald", "corporate", "synthwave", "retro", "cyberpunk", "valentine", "halloween", "garden", "forest", "aqua", "lofi", "pastel", "fantasy", "wireframe", "black", "luxury", "dracula", "cmyk", "autumn", "business", "acid", "lemonade", "night", "coffee", "winter")} +
+ {foreach from=$daisyThemes item=item key=key name=name} +
+
+
+
+
+ {$item} +
+ + + + +
+
+
+
+ {/foreach} + +
+
+
+ + + + +
+
+

Change Language

+
+ {foreach from=$userlangs item=item key=key name=name} +
+

{$item.name}

+

+ by + {if !empty($item.website)} + + {/if} + {$item.author} + {if !empty($item.website)} + + {/if} +

+

Updated: {$item.updated}

+
+ {/foreach} + +
+
+
+ + + + + + + + + + + + + +{/if} \ No newline at end of file diff --git a/library/themes/nucleus/parts/header.tpl b/library/themes/nucleus/parts/header.tpl new file mode 100644 index 0000000..3390aee --- /dev/null +++ b/library/themes/nucleus/parts/header.tpl @@ -0,0 +1,42 @@ +{if (isset($rel) && $rel != 'tab') || !isset($rel)} + + + + + + + + {$pagetitle} + + + + + + + + + + + + + + {include file="../parts/menu.tpl"} +{/if} \ No newline at end of file diff --git a/library/themes/nucleus/parts/menu.tpl b/library/themes/nucleus/parts/menu.tpl new file mode 100644 index 0000000..67b9c1a --- /dev/null +++ b/library/themes/nucleus/parts/menu.tpl @@ -0,0 +1,65 @@ + + + +
+
+
+ + +
+ + {if !empty($logoImage)} + Logo + {else} + {$config.title} + {/if} + +
+ +
+
+ +
    + {if $logged} +
  • Profile
    • +
    • +
    • + {else} +
    • +
    • + {/if} +
+
+
+
+ + +
+{include file="../parts/alert.tpl"} \ No newline at end of file diff --git a/public/.htaccess b/public/.htaccess new file mode 100644 index 0000000..918fb45 --- /dev/null +++ b/public/.htaccess @@ -0,0 +1,10 @@ +Options +FollowSymLinks +RewriteEngine On +Options -Indexes + +# If yours are too low set by the server? the second should be larger than the first +# php_value post_max_size 500M +# php_value upload_max_filesize 510M + +ErrorDocument 404 /fsx/public/error.php +ErrorDocument 403 /fsx/public/error.php \ No newline at end of file diff --git a/public/activate.php b/public/activate.php new file mode 100644 index 0000000..201c435 --- /dev/null +++ b/public/activate.php @@ -0,0 +1,19 @@ += 50) header("Location: index.php") && die("Already activated."); +if (!isset($_GET["token"]) || empty($_GET["token"])) header("Location: index.php") && die("No token given."); + +$token = clean($_GET["token"] ?? ""); + +if (empty($token)) header("Location: index.php") && die("Empty token."); + +$check = $db["activation"]->findOneBy(["token", "==", $token]); +if (empty($check)) header("Location: index.php") && die("Invalid token."); +$data = array( + "level" => 50 +); +$db["users"]->updateById($user["id"], $data); +header("Location: index.php"); diff --git a/public/ajax/account/login.php b/public/ajax/account/login.php new file mode 100644 index 0000000..b50b620 --- /dev/null +++ b/public/ajax/account/login.php @@ -0,0 +1,38 @@ + 64) die("Password can only be 64 characters long!"); +if (strlen($username) < 3) die("Username needs to be at least 3 characters long!"); +if (strlen($username) > 20) die("Username can only be 20 characters long!"); + +$check = $db["users"]->findOneBy(["username", "=", $username]); +if (empty($check)) doLog("login", false, "user not found") && die("User not found!"); +if (!password_verify($password, $check["password"])) doLog("login", false, "invalid password") && die("Wrong Password!"); +if ($check["banned"]) doLog("login", false, "banned", $check["id"]) && die("Banned! Reason: " . $check["bannedReason"]); + +// Everything is right! +$token = genToken(); +$session = array( + "user" => $check["id"], + "token" => $token, + "ip" => $_SERVER["REMOTE_ADDR"] +); +$db["sessions"]->insert($session); +setcookie(cat($config["title"]) . "_session", $token, time() + 606024 * 9999, "/"); +doLog("login", true, null, $check["id"]); +die("success"); diff --git a/public/ajax/account/logout.php b/public/ajax/account/logout.php new file mode 100644 index 0000000..8a955cd --- /dev/null +++ b/public/ajax/account/logout.php @@ -0,0 +1,9 @@ +deleteById($session["id"]); +die("success"); diff --git a/public/ajax/account/settings.php b/public/ajax/account/settings.php new file mode 100644 index 0000000..d6a1ba1 --- /dev/null +++ b/public/ajax/account/settings.php @@ -0,0 +1,18 @@ + $avatar, + "theme" => $theme, +); +$db["users"]->updateById($user["id"], $data); +die("success"); diff --git a/public/ajax/account/signup.php b/public/ajax/account/signup.php new file mode 100644 index 0000000..dd60be0 --- /dev/null +++ b/public/ajax/account/signup.php @@ -0,0 +1,89 @@ + 20) die("Username can only be 20 characters long!"); +if (strlen($password) < 8 || strlen($password) > 64) die("Password needs to be at leats 8 characters long!"); +if ($password != $password2) die("Passwords don't match!"); +if (strlen($email) < 6 || strlen($email) > 320) die("Email needs to be between 6 and 320 characters!"); +if (strlen($email2) < 6 || strlen($email2) > 320) die("Email needs to be between 6 and 320 characters!"); +if ($email != $email2) die("Emails don't match!"); + +$check = $db["users"]->findOneBy(["email", "=", $email]); +if (!empty($check)) doLog("signup", false, "email already in use: " . $email) && die("Email already in use!"); +$check = $db["users"]->findOneBy(["username", "=", $username]); +if (!empty($check)) doLog("signup", false, "username already in use: " . $username) && die("Username already in use!"); +$password = password_hash($password, PASSWORD_BCRYPT); + +if ($config["activation"]) { + $token = genToken(); + $activationLink = $config["url"] . "activate.php?token=" . $token; + + try { + $mailer->setFrom($config["email"], $config["title"] . " Staff", 0); + $mailer->addAddress($email, $config["title"] . " Reader"); + $mailer->isHTML(true); + $mailer->Subject = "Activate your account at " . $config["title"]; + $mailer->Body = "Hello, {$username}
You just created an account on {$config["title"]}.
Please use the link below to activate it and gain access to all of the features:
{$activationLink}

Regards,
The {$config["title"]} Staff"; + $mailer->AltBody = "Hello {$username}, you just created an account on {$config["title"]}. Please activate it with this link to fully access our site: {$activationLink} - Best regards, the {$config["title"]} Staff."; + $mailer->send(); + } catch (Exception $e) { + die("Email died: {$mailer->ErrorInfo}"); + } + $data = array( + "token" => $token, + "user" => $check + ); + $db["activation"]->insert($data); + $level = 49; +} else { + $level = 50; +} + +if (empty($db["users"]->findAll(null, 1))) $level = 100; + +$data = array( + "username" => $username, + "password" => $password, + "email" => $email, + "avatar" => $config["default"]["avatar"], + "level" => $level, + "theme" => $usertheme, + "lang" => $userlang, + "banned" => false, + "bannedReason" => null, + "timestamp" => now() +); +$db["users"]->insert($data); +$token = genToken(); +$check = $db["users"]->findOneBy(["username", "=", $username]); +$session = array( + "user" => $check["id"], + "token" => $token, + "ip" => $_SERVER["REMOTE_ADDR"] +); +$db["sessions"]->insert($session); +setcookie(cat($config["title"]) . "_session", $token, time() + 606024 * 9999, "/"); + +doLog("signup", true, null, $check["id"]); +die("success"); diff --git a/public/ajax/account/updateLang.php b/public/ajax/account/updateLang.php new file mode 100644 index 0000000..505f49a --- /dev/null +++ b/public/ajax/account/updateLang.php @@ -0,0 +1,12 @@ + $newLang +); +$db["users"]->updateById($user["id"], $data); +die("success"); diff --git a/public/ajax/alerts/dismiss.php b/public/ajax/alerts/dismiss.php new file mode 100644 index 0000000..660021e --- /dev/null +++ b/public/ajax/alerts/dismiss.php @@ -0,0 +1,24 @@ +findAll(["id" => "DESC"], 1)[0]; +if (!empty($topAlert)) { + $readAlert = !empty($db["alerts"]->findOneBy([["user", "=", $user["id"]], "AND", ["alert", "=", $topAlert["id"]]])) ? true : false; + + if (!$readAlert) { + $data = array( + "user" => $user["id"], + "alert" => $topAlert["id"], + "timestamp" => now() + ); + $db["alertReads"]->insert($data); + die("success"); + } else { + die("Already dismissed!"); + } +} else { + die("No alert to dismiss!"); +} diff --git a/public/ajax/chapters/add.php b/public/ajax/chapters/add.php new file mode 100644 index 0000000..8185a04 --- /dev/null +++ b/public/ajax/chapters/add.php @@ -0,0 +1,51 @@ +findById($id); + +if (empty($title)) die("Title does not exist!"); + +$number = cat($_POST["number"] ?? 1); +$volume = cat($_POST["volume"] ?? null); +$name = clean($_POST["title"] ?? ""); +$language = clean($_POST["language"] ?? ""); + +if (!isset($_FILES["zip"]) || empty($_FILES["zip"]["tmp_name"])) die("Missing ZIP file!"); +if (empty($number)) die("Invalid or empty chapter number!"); +if (empty($language)) die("Invalid Language!"); +$language = explode(",", $language); +if (empty($language[0]) || empty($language[1])) die("Invalid Language!"); + +$mime = mime_content_type($_FILES["zip"]["tmp_name"]); +$type = strtolower(pathinfo($_FILES["zip"]["name"], PATHINFO_EXTENSION)); + +if (empty($_FILES["zip"]["tmp_name"])) die("Invalid File!"); +if ($mime != "application/zip" || $type != "zip") die("Only ZIP is supported!"); +if ($_FILES["zip"]["size"] > $config["mfs"]["chapter"]) die(je(["s" => false, "msg" => "ZIP too large. Cannot exceed " . formatBytes($config["mfs"]["chapter"]) . "!"])); + +$cid = $db["chapters"]->getLastInsertedId() + 1; + +if (file_exists(ps(__DIR__ . "/../../data/chapters/{$cid}"))) rmrf(ps(__DIR__ . "/../../data/chapters/{$cid}")); +$result = unzip($_FILES["zip"]["tmp_name"], ps(__DIR__ . "/../../data/tmp/{$cid}"), ps(__DIR__ . "/../../data/chapters/{$cid}")); +if ($result !== "success") die($result); + +$data = array( + "number" => namba($number), + "volume" => namba($volume), + "name" => $name, + "language" => $language, + "title" => $title, + "user" => $user, + "lastEdited" => now(), + "timestamp" => now() +); +$db["chapters"]->insert($data); +die("success"); diff --git a/public/ajax/chapters/edit.php b/public/ajax/chapters/edit.php new file mode 100644 index 0000000..1cd136a --- /dev/null +++ b/public/ajax/chapters/edit.php @@ -0,0 +1,56 @@ +findById($id); + +if (empty($title)) die("Title does not exist!"); + +$number = cat($_POST["number"] ?? 1); +$volume = cat($_POST["volume"] ?? null); +$name = clean($_POST["title"] ?? ""); +$language = clean($_POST["language"] ?? ""); + +if (empty($number)) die("Invalid or empty chapter number!"); +if (empty($language)) die("Invalid Language!"); +$language = explode(",", $language); +if (empty($language[0]) || empty($language[1])) die("Invalid Language!"); + +$zip = false; +if (!isset($_FILES["zip"]) && !empty($_FILES["zip"]["tmp_name"])) { + $zip = true; + $mime = mime_content_type($_FILES["zip"]["tmp_name"]); + $type = strtolower(pathinfo($_FILES["zip"]["name"], PATHINFO_EXTENSION)); + + if (empty($_FILES["zip"]["tmp_name"])) die("Invalid File!"); + if ($mime != "application/zip" || $type != "zip") die("Only ZIP is supported!"); + if ($_FILES["zip"]["size"] > $config["mfs"]["chapter"]) die(je(["s" => false, "msg" => "ZIP too large. Cannot exceed " . formatBytes($config["mfs"]["chapter"]) . "!"])); +} + +if ($zip) { + $result = unzip($_FILES["zip"]["tmp_name"], ps(__DIR__ . "/../../data/tmp/{$cid}"), ps(__DIR__ . "/../../data/chapters/{$cid}")); + if ($result !== "success") die($result); +} + +$data = array( + "number" => namba($number), + "volume" => namba($volume), + "name" => $name, + "language" => $language, + "title" => $title, + "user" => $user, + "lastEdited" => now(), + "timestamp" => now() +); + +$db["chapters"]->updateById($cid, $data); +die("success"); diff --git a/public/ajax/chapters/read.php b/public/ajax/chapters/read.php new file mode 100644 index 0000000..2fdc575 --- /dev/null +++ b/public/ajax/chapters/read.php @@ -0,0 +1,26 @@ +findOneBy(["chapter", "==", $cid]); +if (empty($check)) { + $data = array( + "user" => $uid, + "chapter" => $cid, + "timestamp" => now() + ); + $db["readChapters"]->insert($data); +} else { + $db["readChapters"]->deleteById($check["id"]); +} + +die("success"); diff --git a/public/ajax/images/tmp.php b/public/ajax/images/tmp.php new file mode 100644 index 0000000..762c648 --- /dev/null +++ b/public/ajax/images/tmp.php @@ -0,0 +1,28 @@ + false, "msg" => "No image to upload!"])); + +// Upload image on select +if (!file_exists("../../data/tmp")) mkdir("../../data/tmp", 0777, true); // Create TMP folder if not exists +$string = genUuid(); +$target_file = "../../data/tmp/" . $string . "-" . basename($_FILES["cover"]["name"]); +$imageFileType = strtolower(pathinfo($target_file, PATHINFO_EXTENSION)); +$target_file = "../../data/tmp/" . $string . "." . $imageFileType; +$output_file = $string . "." . $imageFileType; + +// Check if image file is a actual image or fake image +$check = getimagesize($_FILES["cover"]["tmp_name"]); +if ($check == false) die(je(["s" => false, "msg" => "Invalid Image!"])); + +// Check file size +if ($_FILES["cover"]["size"] > $config["mfs"]["cover"]) die(je(["s" => false, "msg" => "Cover too large. Cannot exceed " . formatBytes($config["mfs"]["cover"]) . "!"])); + +// Allow certain file formats +if ($imageFileType != "jpg" && $imageFileType != "png" && $imageFileType != "jpeg" && $imageFileType != "webp") die(je(["s" => false, "msg" => "Invalid Image! Please use JPEG, PNG or WEBP."])); + +if (!move_uploaded_file($_FILES["cover"]["tmp_name"], $target_file)) die(je(["s" => false, "msg" => "Something went wrong..."])); +die(je(["s" => true, "msg" => $output_file])); diff --git a/public/ajax/titles/add.php b/public/ajax/titles/add.php new file mode 100644 index 0000000..17cf5ff --- /dev/null +++ b/public/ajax/titles/add.php @@ -0,0 +1,129 @@ + false, "msg" => "Cover is required!"])); +if (empty($title)) die(je(["s" => false, "msg" => "Title is required!"])); +switch ($ostatus) { + case 1: + break; + case 3: + break; + case 4: + break; + case 5: + break; + case 2: + default: + $ostatus = 2; +} +switch ($sstatus) { + case 1: + break; + case 3: + break; + case 4: + break; + case 5: + break; + case 2: + default: + $sstatus = 2; +} +if (empty($olang)) die(je(["s" => false, "msg" => "You need to enter an original language."])); +if (!empty($release)) { + if (!is_numeric($release)) die(je(["s" => false, "msg" => "You messed with the Release Year!"])); + if (strlen($release) != 4) die(je(["s" => false, "msg" => "Release years tend to be four digits long."])); +} +if (!empty($completion)) { + if (!is_numeric($completion)) die(je(["s" => false, "msg" => "You messed with the Completion Year!"])); + if (strlen($completion) != 4) die(je(["s" => false, "msg" => "Completion years tend to be four digits long."])); +} + +if (!is_array($formats)) die(je(["s" => false, "msg" => "Formats should be an array."])); +if (!is_array($warnings)) die(je(["s" => false, "msg" => "Warnings should be an array."])); +if (!is_array($themes)) die(je(["s" => false, "msg" => "Themes should be an array."])); +if (!is_array($genres)) die(je(["s" => false, "msg" => "Genres should be an array."])); + +if (!empty($formats)) { + $_formats = array(); + foreach ($formats as $format) { + if (!empty($format)) array_push($_formats, trim(cat($format))); + } + $formats = $_formats; +} +if (!empty($warnings)) { + $_warnings = array(); + foreach ($warnings as $warning) { + if (!empty($warning)) array_push($_warnings, trim(cat($warning))); + } + $warnings = $_warnings; +} +if (!empty($themes)) { + $_themes = array(); + foreach ($themes as $theme) { + if (!empty($theme)) array_push($_themes, trim(cat($theme))); + } + $themes = $_themes; +} +if (!empty($genres)) { + $_genres = array(); + foreach ($genres as $genre) { + if (!empty($genre)) array_push($_genres, trim(cat($genre))); + } + $genres = $_genres; +} + +// So far, everything is correct +if (!empty($db["titles"]->findOneBy(["title", "=", $title]))) die(je(["s" => false, "msg" => "Title already exists!"])); + +//die(je(["s" => false, "msg" => $cover])); +if (!file_exists("../../data/covers")) mkdir("../../data/covers", 0777, true); +if (file_exists("../../data/tmp/" . $cover)) rename("../../data/tmp/" . $cover, "../../data/covers/" . ($db["titles"]->getLastInsertedId() + 1) . ".png"); + +$data = array( + "title" => $title, + "alts" => $alts, + "authors" => $authors, + "artists" => $artists, + "lang" => $olang, + "status" => $ostatus, + "sstatus" => $sstatus, + "releaseYear" => $release, + "completionYear" => $completion, + "summary" => $summary, + "tags" => array( + "formats" => $formats, + "warnings" => $warnings, + "themes" => $themes, + "genres" => $genres + ), + "creator" => $user, + "lastEdited" => now(), + "timestamp" => now() +); +$db["titles"]->insert($data); +$title = $db["titles"]->findOneBy(["title", "=", $title]); + +// Everything is right, return true and title ID +die(je(["s" => true, "msg" => $title["id"]])); diff --git a/public/ajax/titles/edit.php b/public/ajax/titles/edit.php new file mode 100644 index 0000000..8c0b6cd --- /dev/null +++ b/public/ajax/titles/edit.php @@ -0,0 +1,133 @@ +findById($id); +if (empty($title)) die(je(["s" => false, "msg" => "Title not found!"])); + +$cover = clean($_POST["cover"] ?? ""); +$name = clean($_POST["title"] ?? ""); +$alts = clean($_POST["alts"] ?? ""); +$authors = clean($_POST["authors"] ?? ""); +$artists = clean($_POST["artists"] ?? ""); +$olang = clean($_POST["olang"] ?? ""); +$ostatus = clean($_POST["ostatus"] ?? ""); +$sstatus = clean($_POST["sstatus"] ?? ""); +$release = clean($_POST["release"] ?? ""); +$completion = clean($_POST["completion"] ?? ""); +$summary = clean($_POST["summary"] ?? ""); + +$formats = $_POST["format"] ?? array(); +$warnings = $_POST["warning"] ?? array(); +$themes = $_POST["theme"] ?? array(); +$genres = $_POST["genre"] ?? array(); + +if (empty($cover)) die(je(["s" => false, "msg" => "Cover is required!"])); +if (empty($name)) die(je(["s" => false, "msg" => "Title is required!"])); +switch ($ostatus) { + case 1: + break; + case 3: + break; + case 4: + break; + case 5: + break; + case 2: + default: + $ostatus = 2; +} +switch ($sstatus) { + case 1: + break; + case 3: + break; + case 4: + break; + case 5: + break; + case 2: + default: + $sstatus = 2; +} +if (empty($olang)) die(je(["s" => false, "msg" => "You need to enter an original language."])); +if (!empty($release)) { + if (!is_numeric($release)) die(je(["s" => false, "msg" => "You messed with the Release Year!"])); + if (strlen($release) != 4) die(je(["s" => false, "msg" => "Release years tend to be four digits long."])); +} +if (!empty($completion)) { + if (!is_numeric($completion)) die(je(["s" => false, "msg" => "You messed with the Completion Year!"])); + if (strlen($completion) != 4) die(je(["s" => false, "msg" => "Completion years tend to be four digits long."])); +} + +if (!is_array($formats)) die(je(["s" => false, "msg" => "Formats should be an array."])); +if (!is_array($warnings)) die(je(["s" => false, "msg" => "Warnings should be an array."])); +if (!is_array($themes)) die(je(["s" => false, "msg" => "Themes should be an array."])); +if (!is_array($genres)) die(je(["s" => false, "msg" => "Genres should be an array."])); + +if (!empty($formats)) { + $_formats = array(); + foreach ($formats as $format) { + if (!empty($format)) array_push($_formats, trim(cat($format))); + } + $formats = $_formats; +} +if (!empty($warnings)) { + $_warnings = array(); + foreach ($warnings as $warning) { + if (!empty($warning)) array_push($_warnings, trim(cat($warning))); + } + $warnings = $_warnings; +} +if (!empty($themes)) { + $_themes = array(); + foreach ($themes as $theme) { + if (!empty($theme)) array_push($_themes, trim(cat($theme))); + } + $themes = $_themes; +} +if (!empty($genres)) { + $_genres = array(); + foreach ($genres as $genre) { + if (!empty($genre)) array_push($_genres, trim(cat($genre))); + } + $genres = $_genres; +} + +// So far, everything is correct +if ($title != $title["title"]) + if (!empty($db["titles"]->findOneBy(["title", "=", $title]))) die(je(["s" => false, "msg" => "Title already exists!"])); + +if (!file_exists("../../data/covers")) mkdir("../../data/covers", 0777, true); +if (file_exists("../../data/tmp/" . $cover)) rename("../../data/tmp/" . $cover, "../../data/covers/" . $title["id"] . ".png"); + +$data = array( + "title" => $name, + "alts" => $alts, + "authors" => $authors, + "artists" => $artists, + "lang" => $olang, + "status" => $ostatus, + "sstatus" => $sstatus, + "releaseYear" => $release, + "completionYear" => $completion, + "summary" => $summary, + "tags" => array( + "formats" => $formats, + "warnings" => $warnings, + "themes" => $themes, + "genres" => $genres + ), + "lastEdited" => now() +); +$db["titles"]->updateById($title["id"], $data); + +// Everything is right, return true and title ID +die(je(["s" => true, "msg" => $title["id"]])); diff --git a/public/api.php b/public/api.php new file mode 100644 index 0000000..1480bc8 --- /dev/null +++ b/public/api.php @@ -0,0 +1,88 @@ + 503, "message" => "Analytics are disabled."])); + if (!isset($_GET["key"]) || empty($_GET["key"])) die(je(["code" => 401, "message" => "Key not supplied."])); + $key = clean($_GET["key"]); + if ($key != file_get_contents(ps(__DIR__ . "/../library/secrets/key.txt"))) die(je(["code" => 498, "message" => "Invalid key."])); + $data = array( + "code" => 201, + "version" => file_get_contents(ps(__DIR__ . "/../version.txt")), + "config" => array( + "title" => $config["title"], + "divider" => $config["divider"], + "slogan" => $config["slogan"], + "logs" => $config["logs"], + "debug" => $config["debug"], + "activation" => $config["activation"], + "url" => $config["url"], + "db" => array( + "type" => $config["db"]["type"], + "sleek" => array( + "dir" => $config["db"]["sleek"]["dir"], + "config" => $config["db"]["sleek"]["config"] + ) + ), + "mfs" => array( + "cover" => $config["mfs"]["cover"], + "chapter" => $config["mfs"]["chapter"] + ), + "default" => array( + "theme" => $config["default"]["theme"], + "lang" => $config["default"]["lang"], + "avatar" => $config["default"]["avatar"] + ), + "captcha" => array( + "enabled" => $config["captcha"]["enabled"], + "type" => $config["captcha"]["type"] + ), + "themes" => $config["themes"], + "langs" => $config["langs"], + "avatars" => $config["avatars"], + "perpage" => array( + "titles" => $config["perpage"]["titles"], + "chapters" => $config["perpage"]["chapters"], + ) + ), + "statistics" => array( + "users" => $db["users"]->count(), + "titles" => $db["titles"]->count(), + "comments" => array( + "chapters" => $db["chapterComments"]->count(), + "titles" => $db["titleComments"]->count(), + "profiles" => $db["profileComments"]->count(), + "total" => ($db["chapterComments"]->count() + $db["titleComments"]->count() + $db["profileComments"]->count()) + ), + "views" => array( + "chapters" => $db["chapterViews"]->count(), + "titles" => $db["titleViews"]->count(), + "profiles" => $db["profileViews"]->count(), + "total" => ($db["chapterViews"]->count() + $db["titleViews"]->count() + $db["profileViews"]->count()), + "visits" => $db["visitLogs"]->count() + ), + ), + "website" => array( + "onlineSince" => $started ?? "file deleted or plugin disabled", + "checks" => [ + now() => $started ?? "file deleted or plugin disabled" + ] + ), + "server" => array( + "self" => $_SERVER["PHP_SELF"], + "server" => $_SERVER["SERVER_NAME"], + "host" => $_SERVER["HTTP_HOST"], + "agent" => $_SERVER["HTTP_USER_AGENT"], + "script" => $_SERVER["SCRIPT_NAME"], + "gateway" => $_SERVER["GATEWAY_INTERFACE"], + "software" => $_SERVER["SERVER_SOFTWARE"], + "protocol" => $_SERVER["SERVER_PROTOCOL"], + "time" => $_SERVER["REQUEST_TIME"] + ), + "timestamp" => now() + ); + die(je($data)); +} diff --git a/public/assets/favicon/about.txt b/public/assets/favicon/about.txt new file mode 100644 index 0000000..3479a66 --- /dev/null +++ b/public/assets/favicon/about.txt @@ -0,0 +1,6 @@ +This favicon was generated using the following font: + +- Font Title: ABeeZee +- Font Author: Copyright 2011 The ABeeZee Project Authors (https://github.com/googlefonts/abeezee) with Reserved Font Name ABeeZee +- Font Source: http://fonts.gstatic.com/s/abeezee/v22/esDR31xSG-6AGleN6tKukbcHCpE.ttf +- Font License: SIL Open Font License, 1.1 (http://scripts.sil.org/OFL)) diff --git a/public/assets/favicon/android-chrome-192x192.png b/public/assets/favicon/android-chrome-192x192.png new file mode 100644 index 0000000..586764b Binary files /dev/null and b/public/assets/favicon/android-chrome-192x192.png differ diff --git a/public/assets/favicon/android-chrome-512x512.png b/public/assets/favicon/android-chrome-512x512.png new file mode 100644 index 0000000..115def3 Binary files /dev/null and b/public/assets/favicon/android-chrome-512x512.png differ diff --git a/public/assets/favicon/apple-touch-icon.png b/public/assets/favicon/apple-touch-icon.png new file mode 100644 index 0000000..76de9ea Binary files /dev/null and b/public/assets/favicon/apple-touch-icon.png differ diff --git a/public/assets/favicon/favicon-16x16.png b/public/assets/favicon/favicon-16x16.png new file mode 100644 index 0000000..d1378a2 Binary files /dev/null and b/public/assets/favicon/favicon-16x16.png differ diff --git a/public/assets/favicon/favicon-32x32.png b/public/assets/favicon/favicon-32x32.png new file mode 100644 index 0000000..5d970bb Binary files /dev/null and b/public/assets/favicon/favicon-32x32.png differ diff --git a/public/assets/favicon/favicon.ico b/public/assets/favicon/favicon.ico new file mode 100644 index 0000000..8934d90 Binary files /dev/null and b/public/assets/favicon/favicon.ico differ diff --git a/public/assets/favicon/site.webmanifest b/public/assets/favicon/site.webmanifest new file mode 100644 index 0000000..45dc8a2 --- /dev/null +++ b/public/assets/favicon/site.webmanifest @@ -0,0 +1 @@ +{"name":"","short_name":"","icons":[{"src":"/android-chrome-192x192.png","sizes":"192x192","type":"image/png"},{"src":"/android-chrome-512x512.png","sizes":"512x512","type":"image/png"}],"theme_color":"#ffffff","background_color":"#ffffff","display":"standalone"} \ No newline at end of file diff --git a/public/assets/js.cookie.js b/public/assets/js.cookie.js new file mode 100644 index 0000000..d36c82b --- /dev/null +++ b/public/assets/js.cookie.js @@ -0,0 +1,147 @@ +/*! js-cookie v3.0.1 | MIT */ +; +(function (global, factory) { + typeof exports === 'object' && typeof module !== 'undefined' ? module.exports = factory() : + typeof define === 'function' && define.amd ? define(factory) : + (global = global || self, (function () { + var current = global.Cookies; + var exports = global.Cookies = factory(); + exports.noConflict = function () { global.Cookies = current; return exports; }; + }())); +}(this, (function () { 'use strict'; + + /* eslint-disable no-var */ + function assign (target) { + for (var i = 1; i < arguments.length; i++) { + var source = arguments[i]; + for (var key in source) { + target[key] = source[key]; + } + } + return target + } + /* eslint-enable no-var */ + + /* eslint-disable no-var */ + var defaultConverter = { + read: function (value) { + if (value[0] === '"') { + value = value.slice(1, -1); + } + return value.replace(/(%[\dA-F]{2})+/gi, decodeURIComponent) + }, + write: function (value) { + return encodeURIComponent(value).replace( + /%(2[346BF]|3[AC-F]|40|5[BDE]|60|7[BCD])/g, + decodeURIComponent + ) + } + }; + /* eslint-enable no-var */ + + /* eslint-disable no-var */ + + function init (converter, defaultAttributes) { + function set (key, value, attributes) { + if (typeof document === 'undefined') { + return + } + + attributes = assign({}, defaultAttributes, attributes); + + if (typeof attributes.expires === 'number') { + attributes.expires = new Date(Date.now() + attributes.expires * 864e5); + } + if (attributes.expires) { + attributes.expires = attributes.expires.toUTCString(); + } + + key = encodeURIComponent(key) + .replace(/%(2[346B]|5E|60|7C)/g, decodeURIComponent) + .replace(/[()]/g, escape); + + var stringifiedAttributes = ''; + for (var attributeName in attributes) { + if (!attributes[attributeName]) { + continue + } + + stringifiedAttributes += '; ' + attributeName; + + if (attributes[attributeName] === true) { + continue + } + + // Considers RFC 6265 section 5.2: + // ... + // 3. If the remaining unparsed-attributes contains a %x3B (";") + // character: + // Consume the characters of the unparsed-attributes up to, + // not including, the first %x3B (";") character. + // ... + stringifiedAttributes += '=' + attributes[attributeName].split(';')[0]; + } + + return (document.cookie = + key + '=' + converter.write(value, key) + stringifiedAttributes) + } + + function get (key) { + if (typeof document === 'undefined' || (arguments.length && !key)) { + return + } + + // To prevent the for loop in the first place assign an empty array + // in case there are no cookies at all. + var cookies = document.cookie ? document.cookie.split('; ') : []; + var jar = {}; + for (var i = 0; i < cookies.length; i++) { + var parts = cookies[i].split('='); + var value = parts.slice(1).join('='); + + try { + var foundKey = decodeURIComponent(parts[0]); + jar[foundKey] = converter.read(value, foundKey); + + if (key === foundKey) { + break + } + } catch (e) {} + } + + return key ? jar[key] : jar + } + + return Object.create( + { + set: set, + get: get, + remove: function (key, attributes) { + set( + key, + '', + assign({}, attributes, { + expires: -1 + }) + ); + }, + withAttributes: function (attributes) { + return init(this.converter, assign({}, this.attributes, attributes)) + }, + withConverter: function (converter) { + return init(assign({}, this.converter, converter), this.attributes) + } + }, + { + attributes: { value: Object.freeze(defaultAttributes) }, + converter: { value: Object.freeze(converter) } + } + ) + } + + var api = init(defaultConverter, { path: '/' }); + /* eslint-enable no-var */ + + return api; + +}))); diff --git a/public/assets/miku_cursor/CREDITS.txt b/public/assets/miku_cursor/CREDITS.txt new file mode 100644 index 0000000..3a9a5cc --- /dev/null +++ b/public/assets/miku_cursor/CREDITS.txt @@ -0,0 +1,2 @@ +By: MIMI DESTINO +Source: https://www.rw-designer.com/cursor-set/miku-hatsune-md \ No newline at end of file diff --git a/public/assets/miku_cursor/busy.png b/public/assets/miku_cursor/busy.png new file mode 100644 index 0000000..f35e82e Binary files /dev/null and b/public/assets/miku_cursor/busy.png differ diff --git a/public/assets/miku_cursor/diagonal-1.png b/public/assets/miku_cursor/diagonal-1.png new file mode 100644 index 0000000..b464eb3 Binary files /dev/null and b/public/assets/miku_cursor/diagonal-1.png differ diff --git a/public/assets/miku_cursor/diagonal-2.png b/public/assets/miku_cursor/diagonal-2.png new file mode 100644 index 0000000..7774482 Binary files /dev/null and b/public/assets/miku_cursor/diagonal-2.png differ diff --git a/public/assets/miku_cursor/handwriting.png b/public/assets/miku_cursor/handwriting.png new file mode 100644 index 0000000..0d3dedf Binary files /dev/null and b/public/assets/miku_cursor/handwriting.png differ diff --git a/public/assets/miku_cursor/help.png b/public/assets/miku_cursor/help.png new file mode 100644 index 0000000..ce80c6a Binary files /dev/null and b/public/assets/miku_cursor/help.png differ diff --git a/public/assets/miku_cursor/link.png b/public/assets/miku_cursor/link.png new file mode 100644 index 0000000..10c62b4 Binary files /dev/null and b/public/assets/miku_cursor/link.png differ diff --git a/public/assets/miku_cursor/move.png b/public/assets/miku_cursor/move.png new file mode 100644 index 0000000..8a01621 Binary files /dev/null and b/public/assets/miku_cursor/move.png differ diff --git a/public/assets/miku_cursor/pos-select.png b/public/assets/miku_cursor/pos-select.png new file mode 100644 index 0000000..5f3b44b Binary files /dev/null and b/public/assets/miku_cursor/pos-select.png differ diff --git a/public/assets/miku_cursor/resize-h.png b/public/assets/miku_cursor/resize-h.png new file mode 100644 index 0000000..d588436 Binary files /dev/null and b/public/assets/miku_cursor/resize-h.png differ diff --git a/public/assets/miku_cursor/resize-v.png b/public/assets/miku_cursor/resize-v.png new file mode 100644 index 0000000..9b60e55 Binary files /dev/null and b/public/assets/miku_cursor/resize-v.png differ diff --git a/public/assets/miku_cursor/select-alt.png b/public/assets/miku_cursor/select-alt.png new file mode 100644 index 0000000..876a65e Binary files /dev/null and b/public/assets/miku_cursor/select-alt.png differ diff --git a/public/assets/miku_cursor/select-alt2.png b/public/assets/miku_cursor/select-alt2.png new file mode 100644 index 0000000..23d04cb Binary files /dev/null and b/public/assets/miku_cursor/select-alt2.png differ diff --git a/public/assets/miku_cursor/select.png b/public/assets/miku_cursor/select.png new file mode 100644 index 0000000..62cdb8a Binary files /dev/null and b/public/assets/miku_cursor/select.png differ diff --git a/public/assets/miku_cursor/text.png b/public/assets/miku_cursor/text.png new file mode 100644 index 0000000..066d4c6 Binary files /dev/null and b/public/assets/miku_cursor/text.png differ diff --git a/public/assets/miku_cursor/unavailable.png b/public/assets/miku_cursor/unavailable.png new file mode 100644 index 0000000..aa0e58d Binary files /dev/null and b/public/assets/miku_cursor/unavailable.png differ diff --git a/public/assets/miku_cursor/working.png b/public/assets/miku_cursor/working.png new file mode 100644 index 0000000..b859591 Binary files /dev/null and b/public/assets/miku_cursor/working.png differ diff --git a/public/assets/nucleus/autotheme.js b/public/assets/nucleus/autotheme.js new file mode 100644 index 0000000..355c8c4 --- /dev/null +++ b/public/assets/nucleus/autotheme.js @@ -0,0 +1,4 @@ +function assignTheme(prefix) { + let theme = Cookies.get(prefix + "daisytheme"); + document.body.setAttribute("data-theme", theme); +} \ No newline at end of file diff --git a/public/assets/nucleus/carousel.js b/public/assets/nucleus/carousel.js new file mode 100644 index 0000000..dfe6b5c --- /dev/null +++ b/public/assets/nucleus/carousel.js @@ -0,0 +1,8 @@ +function switchCarLink(evt,) { + let carlinks, i; + carlinks = document.getElementsByClassName("carlink"); + for (i = 0; i < carlinks.length; i++) { + carlinks[i].classList.remove("btn-active"); + } + evt.currentTarget.classList.add("btn-active"); +} \ No newline at end of file diff --git a/public/assets/nucleus/logo.png b/public/assets/nucleus/logo.png new file mode 100644 index 0000000..c064f11 Binary files /dev/null and b/public/assets/nucleus/logo.png differ diff --git a/public/assets/nucleus/tabs.js b/public/assets/nucleus/tabs.js new file mode 100644 index 0000000..3cb3794 --- /dev/null +++ b/public/assets/nucleus/tabs.js @@ -0,0 +1,14 @@ +function switchTab(evt, tab) { + let i, tabcontent, tablinks; + tabcontent = document.getElementsByClassName("tabcontent"); + for (i = 0; i < tabcontent.length; i++) { + tabcontent[i].classList.add("hidden"); + } + tablinks = document.getElementsByClassName("tablink"); + for (i = 0; i < tablinks.length; i++) { + tablinks[i].classList.remove("tab-active"); + } + document.getElementById(tab).classList.remove("hidden"); + document.getElementById(tab).classList.add("block"); + evt.currentTarget.classList.add("tab-active"); +} \ No newline at end of file diff --git a/public/assets/nucleus/tags.js b/public/assets/nucleus/tags.js new file mode 100644 index 0000000..c5851cf --- /dev/null +++ b/public/assets/nucleus/tags.js @@ -0,0 +1,55 @@ +function insertTag(id, toInsert, toInsertAfter, cursorWhere) { + let target = document.getElementById(id); + if (target.setRangeText) { + target.setRangeText(toInsert + toInsertAfter); + target.focus(); + setCaretToPos(target, Number(doGetCaretPosition(target) - cursorWhere)); + } else { + target.focus(); + document.execCommand("insertText", false /*no UI*/, toInsert + toInsertAfter); + target.focus(); + } +} + +function setSelectionRange(input, selectionStart, selectionEnd) { + if (input.setSelectionRange) { + input.focus(); + input.setSelectionRange(selectionStart, selectionEnd); + } + else if (input.createTextRange) { + let range = input.createTextRange(); + range.collapse(true); + range.moveEnd('character', selectionEnd); + range.moveStart('character', selectionStart); + range.select(); + } +} + +function setCaretToPos(input, pos) { + setSelectionRange(input, pos, pos); +} + +/* +** Returns the caret (cursor) position of the specified text field (oField). +** Return value range is 0-oField.value.length. +*/ +function doGetCaretPosition(oField) { + // Initialize + let iCaretPos = 0; + // IE Support + if (document.selection) { + // Set focus on the element + oField.focus(); + // To get cursor position, get empty selection range + let oSel = document.selection.createRange(); + // Move selection start to 0 position + oSel.moveStart('character', -oField.value.length); + // The caret position is selection length + iCaretPos = oSel.text.length; + } + // Firefox support + else if (oField.selectionStart || oField.selectionStart == '0') + iCaretPos = oField.selectionDirection == 'backward' ? oField.selectionStart : oField.selectionEnd; + // Return results + return iCaretPos; +} \ No newline at end of file diff --git a/public/assets/other/kofi_button_blue.png b/public/assets/other/kofi_button_blue.png new file mode 100644 index 0000000..aad3c07 Binary files /dev/null and b/public/assets/other/kofi_button_blue.png differ diff --git a/public/assets/other/kofi_s_tag_white.png b/public/assets/other/kofi_s_tag_white.png new file mode 100644 index 0000000..308c5fe Binary files /dev/null and b/public/assets/other/kofi_s_tag_white.png differ diff --git a/public/assets/other/paypal-donate-button.png b/public/assets/other/paypal-donate-button.png new file mode 100644 index 0000000..cbd225f Binary files /dev/null and b/public/assets/other/paypal-donate-button.png differ diff --git a/public/assets/page.js b/public/assets/page.js new file mode 100644 index 0000000..c2239d9 --- /dev/null +++ b/public/assets/page.js @@ -0,0 +1,24 @@ +$(function () { + $("a[rel='tab']").click(function (e) { + let pageurl = $(this).attr('href'); + $.ajax({ + url: pageurl + '?rel=tab', success: function (data) { + $('#content').html(data); + } + }); + if (pageurl != window.location) { + window.history.pushState({ path: pageurl }, '', pageurl); + } + document.title = $(this).attr("ttl") + " " + $("#siteDivider").val() + " " + $("#siteName").val(); $('html, body') + .animate({ scrollTop: 0 }, 'fast'); + return false; + }); +}); + +$(window).bind('popstate', function () { + $.ajax({ + url: location.pathname + '?rel=tab', success: function (data) { + $('#content').html(data); + } + }); +}); \ No newline at end of file diff --git a/public/chapter.php b/public/chapter.php new file mode 100644 index 0000000..4a0b59a --- /dev/null +++ b/public/chapter.php @@ -0,0 +1,28 @@ +findById($id); +$title = $db["titles"]->findById($chapter["title"]["id"]); +if (empty($title)) header("Location: titles.php") && die("Title not found."); +if (empty($chapter)) header("Location: title.php?id={$title["id"]}") && die("Chapter not found."); + +$images = glob(ps(__DIR__ . "/data/chapters/{$id}/*.{jpg,png,jpeg,webp,gif}"), GLOB_BRACE); +natsort($images); + +$comments = $db["chapterComments"]->findBy(["chapter.id", "=", $title["id"]], ["id" => "DESC"]); + +chapterVisit($chapter); + +$smarty->assign("commentsCount", count($comments)); +$smarty->assign("title", $title); +$smarty->assign("chapter", $chapter); +$smarty->assign("images", $images); +$smarty->assign("pagetitle", "Read " . $title["title"] . " " . formatChapterTitle($chapter["volume"], $chapter["number"]) . " (Chapter) " . $config["divider"] . " " . $config["title"]); + +$smarty->display("parts/header.tpl"); +$smarty->display("pages/chapter.tpl"); +$smarty->display("parts/footer.tpl"); diff --git a/public/data/chapters/1/1.jpg b/public/data/chapters/1/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/1/1.jpg differ diff --git a/public/data/chapters/1/2.jpg b/public/data/chapters/1/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/1/2.jpg differ diff --git a/public/data/chapters/1/3.jpg b/public/data/chapters/1/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/1/3.jpg differ diff --git a/public/data/chapters/1/4.jpg b/public/data/chapters/1/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/1/4.jpg differ diff --git a/public/data/chapters/1/5.jpg b/public/data/chapters/1/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/1/5.jpg differ diff --git a/public/data/chapters/1/6.png b/public/data/chapters/1/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/1/6.png differ diff --git a/public/data/chapters/1/7.jpg b/public/data/chapters/1/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/1/7.jpg differ diff --git a/public/data/chapters/1/8.png b/public/data/chapters/1/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/1/8.png differ diff --git a/public/data/chapters/1/9.png b/public/data/chapters/1/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/1/9.png differ diff --git a/public/data/chapters/10/1.jpg b/public/data/chapters/10/1.jpg new file mode 100644 index 0000000..d962821 Binary files /dev/null and b/public/data/chapters/10/1.jpg differ diff --git a/public/data/chapters/10/10.jpg b/public/data/chapters/10/10.jpg new file mode 100644 index 0000000..0c12733 Binary files /dev/null and b/public/data/chapters/10/10.jpg differ diff --git a/public/data/chapters/10/11.jpg b/public/data/chapters/10/11.jpg new file mode 100644 index 0000000..c03a9f7 Binary files /dev/null and b/public/data/chapters/10/11.jpg differ diff --git a/public/data/chapters/10/12.jpg b/public/data/chapters/10/12.jpg new file mode 100644 index 0000000..e118bf4 Binary files /dev/null and b/public/data/chapters/10/12.jpg differ diff --git a/public/data/chapters/10/13.jpg b/public/data/chapters/10/13.jpg new file mode 100644 index 0000000..4234563 Binary files /dev/null and b/public/data/chapters/10/13.jpg differ diff --git a/public/data/chapters/10/14.jpg b/public/data/chapters/10/14.jpg new file mode 100644 index 0000000..1aa9062 Binary files /dev/null and b/public/data/chapters/10/14.jpg differ diff --git a/public/data/chapters/10/15.jpg b/public/data/chapters/10/15.jpg new file mode 100644 index 0000000..e37f53b Binary files /dev/null and b/public/data/chapters/10/15.jpg differ diff --git a/public/data/chapters/10/16.jpg b/public/data/chapters/10/16.jpg new file mode 100644 index 0000000..12aeba0 Binary files /dev/null and b/public/data/chapters/10/16.jpg differ diff --git a/public/data/chapters/10/17.jpg b/public/data/chapters/10/17.jpg new file mode 100644 index 0000000..0a858b0 Binary files /dev/null and b/public/data/chapters/10/17.jpg differ diff --git a/public/data/chapters/10/18.jpg b/public/data/chapters/10/18.jpg new file mode 100644 index 0000000..70f97b6 Binary files /dev/null and b/public/data/chapters/10/18.jpg differ diff --git a/public/data/chapters/10/19.jpg b/public/data/chapters/10/19.jpg new file mode 100644 index 0000000..34026f3 Binary files /dev/null and b/public/data/chapters/10/19.jpg differ diff --git a/public/data/chapters/10/2.jpg b/public/data/chapters/10/2.jpg new file mode 100644 index 0000000..60dba48 Binary files /dev/null and b/public/data/chapters/10/2.jpg differ diff --git a/public/data/chapters/10/20.jpg b/public/data/chapters/10/20.jpg new file mode 100644 index 0000000..fb5706c Binary files /dev/null and b/public/data/chapters/10/20.jpg differ diff --git a/public/data/chapters/10/21.jpg b/public/data/chapters/10/21.jpg new file mode 100644 index 0000000..167d59c Binary files /dev/null and b/public/data/chapters/10/21.jpg differ diff --git a/public/data/chapters/10/22.jpg b/public/data/chapters/10/22.jpg new file mode 100644 index 0000000..6906eea Binary files /dev/null and b/public/data/chapters/10/22.jpg differ diff --git a/public/data/chapters/10/23.jpg b/public/data/chapters/10/23.jpg new file mode 100644 index 0000000..26438bf Binary files /dev/null and b/public/data/chapters/10/23.jpg differ diff --git a/public/data/chapters/10/24.jpg b/public/data/chapters/10/24.jpg new file mode 100644 index 0000000..46d9e59 Binary files /dev/null and b/public/data/chapters/10/24.jpg differ diff --git a/public/data/chapters/10/25.jpg b/public/data/chapters/10/25.jpg new file mode 100644 index 0000000..abe6882 Binary files /dev/null and b/public/data/chapters/10/25.jpg differ diff --git a/public/data/chapters/10/26.jpg b/public/data/chapters/10/26.jpg new file mode 100644 index 0000000..f2e7968 Binary files /dev/null and b/public/data/chapters/10/26.jpg differ diff --git a/public/data/chapters/10/27.jpg b/public/data/chapters/10/27.jpg new file mode 100644 index 0000000..698d2bc Binary files /dev/null and b/public/data/chapters/10/27.jpg differ diff --git a/public/data/chapters/10/28.jpg b/public/data/chapters/10/28.jpg new file mode 100644 index 0000000..6175da3 Binary files /dev/null and b/public/data/chapters/10/28.jpg differ diff --git a/public/data/chapters/10/29.jpg b/public/data/chapters/10/29.jpg new file mode 100644 index 0000000..1876f09 Binary files /dev/null and b/public/data/chapters/10/29.jpg differ diff --git a/public/data/chapters/10/3.jpg b/public/data/chapters/10/3.jpg new file mode 100644 index 0000000..4d3d5c8 Binary files /dev/null and b/public/data/chapters/10/3.jpg differ diff --git a/public/data/chapters/10/30.jpg b/public/data/chapters/10/30.jpg new file mode 100644 index 0000000..7da5365 Binary files /dev/null and b/public/data/chapters/10/30.jpg differ diff --git a/public/data/chapters/10/31.jpg b/public/data/chapters/10/31.jpg new file mode 100644 index 0000000..c81e508 Binary files /dev/null and b/public/data/chapters/10/31.jpg differ diff --git a/public/data/chapters/10/32.jpg b/public/data/chapters/10/32.jpg new file mode 100644 index 0000000..79784c6 Binary files /dev/null and b/public/data/chapters/10/32.jpg differ diff --git a/public/data/chapters/10/33.jpg b/public/data/chapters/10/33.jpg new file mode 100644 index 0000000..f42f418 Binary files /dev/null and b/public/data/chapters/10/33.jpg differ diff --git a/public/data/chapters/10/34.jpg b/public/data/chapters/10/34.jpg new file mode 100644 index 0000000..9ddb8a5 Binary files /dev/null and b/public/data/chapters/10/34.jpg differ diff --git a/public/data/chapters/10/35.jpg b/public/data/chapters/10/35.jpg new file mode 100644 index 0000000..80abdcd Binary files /dev/null and b/public/data/chapters/10/35.jpg differ diff --git a/public/data/chapters/10/36.jpg b/public/data/chapters/10/36.jpg new file mode 100644 index 0000000..1b72c16 Binary files /dev/null and b/public/data/chapters/10/36.jpg differ diff --git a/public/data/chapters/10/37.jpg b/public/data/chapters/10/37.jpg new file mode 100644 index 0000000..1e4f41a Binary files /dev/null and b/public/data/chapters/10/37.jpg differ diff --git a/public/data/chapters/10/38.jpg b/public/data/chapters/10/38.jpg new file mode 100644 index 0000000..ec7844a Binary files /dev/null and b/public/data/chapters/10/38.jpg differ diff --git a/public/data/chapters/10/39.jpg b/public/data/chapters/10/39.jpg new file mode 100644 index 0000000..63f3164 Binary files /dev/null and b/public/data/chapters/10/39.jpg differ diff --git a/public/data/chapters/10/4.jpg b/public/data/chapters/10/4.jpg new file mode 100644 index 0000000..4142ab8 Binary files /dev/null and b/public/data/chapters/10/4.jpg differ diff --git a/public/data/chapters/10/5.jpg b/public/data/chapters/10/5.jpg new file mode 100644 index 0000000..03db99b Binary files /dev/null and b/public/data/chapters/10/5.jpg differ diff --git a/public/data/chapters/10/6.jpg b/public/data/chapters/10/6.jpg new file mode 100644 index 0000000..555ab3c Binary files /dev/null and b/public/data/chapters/10/6.jpg differ diff --git a/public/data/chapters/10/7.jpg b/public/data/chapters/10/7.jpg new file mode 100644 index 0000000..7dc4f3c Binary files /dev/null and b/public/data/chapters/10/7.jpg differ diff --git a/public/data/chapters/10/8.jpg b/public/data/chapters/10/8.jpg new file mode 100644 index 0000000..daaf5a7 Binary files /dev/null and b/public/data/chapters/10/8.jpg differ diff --git a/public/data/chapters/10/9.jpg b/public/data/chapters/10/9.jpg new file mode 100644 index 0000000..d5abacc Binary files /dev/null and b/public/data/chapters/10/9.jpg differ diff --git a/public/data/chapters/2/1.jpg b/public/data/chapters/2/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/2/1.jpg differ diff --git a/public/data/chapters/2/2.jpg b/public/data/chapters/2/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/2/2.jpg differ diff --git a/public/data/chapters/2/3.jpg b/public/data/chapters/2/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/2/3.jpg differ diff --git a/public/data/chapters/2/4.jpg b/public/data/chapters/2/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/2/4.jpg differ diff --git a/public/data/chapters/2/5.jpg b/public/data/chapters/2/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/2/5.jpg differ diff --git a/public/data/chapters/2/6.png b/public/data/chapters/2/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/2/6.png differ diff --git a/public/data/chapters/2/7.jpg b/public/data/chapters/2/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/2/7.jpg differ diff --git a/public/data/chapters/2/8.png b/public/data/chapters/2/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/2/8.png differ diff --git a/public/data/chapters/2/9.png b/public/data/chapters/2/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/2/9.png differ diff --git a/public/data/chapters/3/1.jpg b/public/data/chapters/3/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/3/1.jpg differ diff --git a/public/data/chapters/3/2.jpg b/public/data/chapters/3/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/3/2.jpg differ diff --git a/public/data/chapters/3/3.jpg b/public/data/chapters/3/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/3/3.jpg differ diff --git a/public/data/chapters/3/4.jpg b/public/data/chapters/3/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/3/4.jpg differ diff --git a/public/data/chapters/3/5.jpg b/public/data/chapters/3/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/3/5.jpg differ diff --git a/public/data/chapters/3/6.png b/public/data/chapters/3/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/3/6.png differ diff --git a/public/data/chapters/3/7.jpg b/public/data/chapters/3/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/3/7.jpg differ diff --git a/public/data/chapters/3/8.png b/public/data/chapters/3/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/3/8.png differ diff --git a/public/data/chapters/3/9.png b/public/data/chapters/3/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/3/9.png differ diff --git a/public/data/chapters/4/1.jpg b/public/data/chapters/4/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/4/1.jpg differ diff --git a/public/data/chapters/4/2.jpg b/public/data/chapters/4/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/4/2.jpg differ diff --git a/public/data/chapters/4/3.jpg b/public/data/chapters/4/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/4/3.jpg differ diff --git a/public/data/chapters/4/4.jpg b/public/data/chapters/4/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/4/4.jpg differ diff --git a/public/data/chapters/4/5.jpg b/public/data/chapters/4/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/4/5.jpg differ diff --git a/public/data/chapters/4/6.png b/public/data/chapters/4/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/4/6.png differ diff --git a/public/data/chapters/4/7.jpg b/public/data/chapters/4/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/4/7.jpg differ diff --git a/public/data/chapters/4/8.png b/public/data/chapters/4/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/4/8.png differ diff --git a/public/data/chapters/4/9.png b/public/data/chapters/4/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/4/9.png differ diff --git a/public/data/chapters/5/1.jpg b/public/data/chapters/5/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/5/1.jpg differ diff --git a/public/data/chapters/5/2.jpg b/public/data/chapters/5/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/5/2.jpg differ diff --git a/public/data/chapters/5/3.jpg b/public/data/chapters/5/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/5/3.jpg differ diff --git a/public/data/chapters/5/4.jpg b/public/data/chapters/5/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/5/4.jpg differ diff --git a/public/data/chapters/5/5.jpg b/public/data/chapters/5/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/5/5.jpg differ diff --git a/public/data/chapters/5/6.png b/public/data/chapters/5/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/5/6.png differ diff --git a/public/data/chapters/5/7.jpg b/public/data/chapters/5/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/5/7.jpg differ diff --git a/public/data/chapters/5/8.png b/public/data/chapters/5/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/5/8.png differ diff --git a/public/data/chapters/5/9.png b/public/data/chapters/5/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/5/9.png differ diff --git a/public/data/chapters/6/1.jpg b/public/data/chapters/6/1.jpg new file mode 100644 index 0000000..22b4d34 Binary files /dev/null and b/public/data/chapters/6/1.jpg differ diff --git a/public/data/chapters/6/2.jpg b/public/data/chapters/6/2.jpg new file mode 100644 index 0000000..4e81b69 Binary files /dev/null and b/public/data/chapters/6/2.jpg differ diff --git a/public/data/chapters/6/3.jpg b/public/data/chapters/6/3.jpg new file mode 100644 index 0000000..ac0d5a0 Binary files /dev/null and b/public/data/chapters/6/3.jpg differ diff --git a/public/data/chapters/6/4.jpg b/public/data/chapters/6/4.jpg new file mode 100644 index 0000000..bfbac17 Binary files /dev/null and b/public/data/chapters/6/4.jpg differ diff --git a/public/data/chapters/6/5.jpg b/public/data/chapters/6/5.jpg new file mode 100644 index 0000000..615e63a Binary files /dev/null and b/public/data/chapters/6/5.jpg differ diff --git a/public/data/chapters/6/6.png b/public/data/chapters/6/6.png new file mode 100644 index 0000000..b448768 Binary files /dev/null and b/public/data/chapters/6/6.png differ diff --git a/public/data/chapters/6/7.jpg b/public/data/chapters/6/7.jpg new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/chapters/6/7.jpg differ diff --git a/public/data/chapters/6/8.png b/public/data/chapters/6/8.png new file mode 100644 index 0000000..c063509 Binary files /dev/null and b/public/data/chapters/6/8.png differ diff --git a/public/data/chapters/6/9.png b/public/data/chapters/6/9.png new file mode 100644 index 0000000..81dd07c Binary files /dev/null and b/public/data/chapters/6/9.png differ diff --git a/public/data/chapters/7/1.jpg b/public/data/chapters/7/1.jpg new file mode 100644 index 0000000..d962821 Binary files /dev/null and b/public/data/chapters/7/1.jpg differ diff --git a/public/data/chapters/7/10.jpg b/public/data/chapters/7/10.jpg new file mode 100644 index 0000000..0c12733 Binary files /dev/null and b/public/data/chapters/7/10.jpg differ diff --git a/public/data/chapters/7/11.jpg b/public/data/chapters/7/11.jpg new file mode 100644 index 0000000..c03a9f7 Binary files /dev/null and b/public/data/chapters/7/11.jpg differ diff --git a/public/data/chapters/7/12.jpg b/public/data/chapters/7/12.jpg new file mode 100644 index 0000000..e118bf4 Binary files /dev/null and b/public/data/chapters/7/12.jpg differ diff --git a/public/data/chapters/7/13.jpg b/public/data/chapters/7/13.jpg new file mode 100644 index 0000000..4234563 Binary files /dev/null and b/public/data/chapters/7/13.jpg differ diff --git a/public/data/chapters/7/14.jpg b/public/data/chapters/7/14.jpg new file mode 100644 index 0000000..1aa9062 Binary files /dev/null and b/public/data/chapters/7/14.jpg differ diff --git a/public/data/chapters/7/15.jpg b/public/data/chapters/7/15.jpg new file mode 100644 index 0000000..e37f53b Binary files /dev/null and b/public/data/chapters/7/15.jpg differ diff --git a/public/data/chapters/7/16.jpg b/public/data/chapters/7/16.jpg new file mode 100644 index 0000000..12aeba0 Binary files /dev/null and b/public/data/chapters/7/16.jpg differ diff --git a/public/data/chapters/7/17.jpg b/public/data/chapters/7/17.jpg new file mode 100644 index 0000000..0a858b0 Binary files /dev/null and b/public/data/chapters/7/17.jpg differ diff --git a/public/data/chapters/7/18.jpg b/public/data/chapters/7/18.jpg new file mode 100644 index 0000000..70f97b6 Binary files /dev/null and b/public/data/chapters/7/18.jpg differ diff --git a/public/data/chapters/7/19.jpg b/public/data/chapters/7/19.jpg new file mode 100644 index 0000000..34026f3 Binary files /dev/null and b/public/data/chapters/7/19.jpg differ diff --git a/public/data/chapters/7/2.jpg b/public/data/chapters/7/2.jpg new file mode 100644 index 0000000..60dba48 Binary files /dev/null and b/public/data/chapters/7/2.jpg differ diff --git a/public/data/chapters/7/20.jpg b/public/data/chapters/7/20.jpg new file mode 100644 index 0000000..fb5706c Binary files /dev/null and b/public/data/chapters/7/20.jpg differ diff --git a/public/data/chapters/7/21.jpg b/public/data/chapters/7/21.jpg new file mode 100644 index 0000000..167d59c Binary files /dev/null and b/public/data/chapters/7/21.jpg differ diff --git a/public/data/chapters/7/22.jpg b/public/data/chapters/7/22.jpg new file mode 100644 index 0000000..6906eea Binary files /dev/null and b/public/data/chapters/7/22.jpg differ diff --git a/public/data/chapters/7/23.jpg b/public/data/chapters/7/23.jpg new file mode 100644 index 0000000..26438bf Binary files /dev/null and b/public/data/chapters/7/23.jpg differ diff --git a/public/data/chapters/7/24.jpg b/public/data/chapters/7/24.jpg new file mode 100644 index 0000000..46d9e59 Binary files /dev/null and b/public/data/chapters/7/24.jpg differ diff --git a/public/data/chapters/7/25.jpg b/public/data/chapters/7/25.jpg new file mode 100644 index 0000000..abe6882 Binary files /dev/null and b/public/data/chapters/7/25.jpg differ diff --git a/public/data/chapters/7/26.jpg b/public/data/chapters/7/26.jpg new file mode 100644 index 0000000..f2e7968 Binary files /dev/null and b/public/data/chapters/7/26.jpg differ diff --git a/public/data/chapters/7/27.jpg b/public/data/chapters/7/27.jpg new file mode 100644 index 0000000..698d2bc Binary files /dev/null and b/public/data/chapters/7/27.jpg differ diff --git a/public/data/chapters/7/28.jpg b/public/data/chapters/7/28.jpg new file mode 100644 index 0000000..6175da3 Binary files /dev/null and b/public/data/chapters/7/28.jpg differ diff --git a/public/data/chapters/7/29.jpg b/public/data/chapters/7/29.jpg new file mode 100644 index 0000000..1876f09 Binary files /dev/null and b/public/data/chapters/7/29.jpg differ diff --git a/public/data/chapters/7/3.jpg b/public/data/chapters/7/3.jpg new file mode 100644 index 0000000..4d3d5c8 Binary files /dev/null and b/public/data/chapters/7/3.jpg differ diff --git a/public/data/chapters/7/30.jpg b/public/data/chapters/7/30.jpg new file mode 100644 index 0000000..7da5365 Binary files /dev/null and b/public/data/chapters/7/30.jpg differ diff --git a/public/data/chapters/7/31.jpg b/public/data/chapters/7/31.jpg new file mode 100644 index 0000000..c81e508 Binary files /dev/null and b/public/data/chapters/7/31.jpg differ diff --git a/public/data/chapters/7/32.jpg b/public/data/chapters/7/32.jpg new file mode 100644 index 0000000..79784c6 Binary files /dev/null and b/public/data/chapters/7/32.jpg differ diff --git a/public/data/chapters/7/33.jpg b/public/data/chapters/7/33.jpg new file mode 100644 index 0000000..f42f418 Binary files /dev/null and b/public/data/chapters/7/33.jpg differ diff --git a/public/data/chapters/7/34.jpg b/public/data/chapters/7/34.jpg new file mode 100644 index 0000000..9ddb8a5 Binary files /dev/null and b/public/data/chapters/7/34.jpg differ diff --git a/public/data/chapters/7/35.jpg b/public/data/chapters/7/35.jpg new file mode 100644 index 0000000..80abdcd Binary files /dev/null and b/public/data/chapters/7/35.jpg differ diff --git a/public/data/chapters/7/36.jpg b/public/data/chapters/7/36.jpg new file mode 100644 index 0000000..1b72c16 Binary files /dev/null and b/public/data/chapters/7/36.jpg differ diff --git a/public/data/chapters/7/37.jpg b/public/data/chapters/7/37.jpg new file mode 100644 index 0000000..1e4f41a Binary files /dev/null and b/public/data/chapters/7/37.jpg differ diff --git a/public/data/chapters/7/38.jpg b/public/data/chapters/7/38.jpg new file mode 100644 index 0000000..ec7844a Binary files /dev/null and b/public/data/chapters/7/38.jpg differ diff --git a/public/data/chapters/7/39.jpg b/public/data/chapters/7/39.jpg new file mode 100644 index 0000000..63f3164 Binary files /dev/null and b/public/data/chapters/7/39.jpg differ diff --git a/public/data/chapters/7/4.jpg b/public/data/chapters/7/4.jpg new file mode 100644 index 0000000..4142ab8 Binary files /dev/null and b/public/data/chapters/7/4.jpg differ diff --git a/public/data/chapters/7/5.jpg b/public/data/chapters/7/5.jpg new file mode 100644 index 0000000..03db99b Binary files /dev/null and b/public/data/chapters/7/5.jpg differ diff --git a/public/data/chapters/7/6.jpg b/public/data/chapters/7/6.jpg new file mode 100644 index 0000000..555ab3c Binary files /dev/null and b/public/data/chapters/7/6.jpg differ diff --git a/public/data/chapters/7/7.jpg b/public/data/chapters/7/7.jpg new file mode 100644 index 0000000..7dc4f3c Binary files /dev/null and b/public/data/chapters/7/7.jpg differ diff --git a/public/data/chapters/7/8.jpg b/public/data/chapters/7/8.jpg new file mode 100644 index 0000000..daaf5a7 Binary files /dev/null and b/public/data/chapters/7/8.jpg differ diff --git a/public/data/chapters/7/9.jpg b/public/data/chapters/7/9.jpg new file mode 100644 index 0000000..d5abacc Binary files /dev/null and b/public/data/chapters/7/9.jpg differ diff --git a/public/data/chapters/8/1.jpg b/public/data/chapters/8/1.jpg new file mode 100644 index 0000000..d962821 Binary files /dev/null and b/public/data/chapters/8/1.jpg differ diff --git a/public/data/chapters/8/10.jpg b/public/data/chapters/8/10.jpg new file mode 100644 index 0000000..0c12733 Binary files /dev/null and b/public/data/chapters/8/10.jpg differ diff --git a/public/data/chapters/8/11.jpg b/public/data/chapters/8/11.jpg new file mode 100644 index 0000000..c03a9f7 Binary files /dev/null and b/public/data/chapters/8/11.jpg differ diff --git a/public/data/chapters/8/12.jpg b/public/data/chapters/8/12.jpg new file mode 100644 index 0000000..e118bf4 Binary files /dev/null and b/public/data/chapters/8/12.jpg differ diff --git a/public/data/chapters/8/13.jpg b/public/data/chapters/8/13.jpg new file mode 100644 index 0000000..4234563 Binary files /dev/null and b/public/data/chapters/8/13.jpg differ diff --git a/public/data/chapters/8/14.jpg b/public/data/chapters/8/14.jpg new file mode 100644 index 0000000..1aa9062 Binary files /dev/null and b/public/data/chapters/8/14.jpg differ diff --git a/public/data/chapters/8/15.jpg b/public/data/chapters/8/15.jpg new file mode 100644 index 0000000..e37f53b Binary files /dev/null and b/public/data/chapters/8/15.jpg differ diff --git a/public/data/chapters/8/16.jpg b/public/data/chapters/8/16.jpg new file mode 100644 index 0000000..12aeba0 Binary files /dev/null and b/public/data/chapters/8/16.jpg differ diff --git a/public/data/chapters/8/17.jpg b/public/data/chapters/8/17.jpg new file mode 100644 index 0000000..0a858b0 Binary files /dev/null and b/public/data/chapters/8/17.jpg differ diff --git a/public/data/chapters/8/18.jpg b/public/data/chapters/8/18.jpg new file mode 100644 index 0000000..70f97b6 Binary files /dev/null and b/public/data/chapters/8/18.jpg differ diff --git a/public/data/chapters/8/19.jpg b/public/data/chapters/8/19.jpg new file mode 100644 index 0000000..34026f3 Binary files /dev/null and b/public/data/chapters/8/19.jpg differ diff --git a/public/data/chapters/8/2.jpg b/public/data/chapters/8/2.jpg new file mode 100644 index 0000000..60dba48 Binary files /dev/null and b/public/data/chapters/8/2.jpg differ diff --git a/public/data/chapters/8/20.jpg b/public/data/chapters/8/20.jpg new file mode 100644 index 0000000..fb5706c Binary files /dev/null and b/public/data/chapters/8/20.jpg differ diff --git a/public/data/chapters/8/21.jpg b/public/data/chapters/8/21.jpg new file mode 100644 index 0000000..167d59c Binary files /dev/null and b/public/data/chapters/8/21.jpg differ diff --git a/public/data/chapters/8/22.jpg b/public/data/chapters/8/22.jpg new file mode 100644 index 0000000..6906eea Binary files /dev/null and b/public/data/chapters/8/22.jpg differ diff --git a/public/data/chapters/8/23.jpg b/public/data/chapters/8/23.jpg new file mode 100644 index 0000000..26438bf Binary files /dev/null and b/public/data/chapters/8/23.jpg differ diff --git a/public/data/chapters/8/24.jpg b/public/data/chapters/8/24.jpg new file mode 100644 index 0000000..46d9e59 Binary files /dev/null and b/public/data/chapters/8/24.jpg differ diff --git a/public/data/chapters/8/25.jpg b/public/data/chapters/8/25.jpg new file mode 100644 index 0000000..abe6882 Binary files /dev/null and b/public/data/chapters/8/25.jpg differ diff --git a/public/data/chapters/8/26.jpg b/public/data/chapters/8/26.jpg new file mode 100644 index 0000000..f2e7968 Binary files /dev/null and b/public/data/chapters/8/26.jpg differ diff --git a/public/data/chapters/8/27.jpg b/public/data/chapters/8/27.jpg new file mode 100644 index 0000000..698d2bc Binary files /dev/null and b/public/data/chapters/8/27.jpg differ diff --git a/public/data/chapters/8/28.jpg b/public/data/chapters/8/28.jpg new file mode 100644 index 0000000..6175da3 Binary files /dev/null and b/public/data/chapters/8/28.jpg differ diff --git a/public/data/chapters/8/29.jpg b/public/data/chapters/8/29.jpg new file mode 100644 index 0000000..1876f09 Binary files /dev/null and b/public/data/chapters/8/29.jpg differ diff --git a/public/data/chapters/8/3.jpg b/public/data/chapters/8/3.jpg new file mode 100644 index 0000000..4d3d5c8 Binary files /dev/null and b/public/data/chapters/8/3.jpg differ diff --git a/public/data/chapters/8/30.jpg b/public/data/chapters/8/30.jpg new file mode 100644 index 0000000..7da5365 Binary files /dev/null and b/public/data/chapters/8/30.jpg differ diff --git a/public/data/chapters/8/31.jpg b/public/data/chapters/8/31.jpg new file mode 100644 index 0000000..c81e508 Binary files /dev/null and b/public/data/chapters/8/31.jpg differ diff --git a/public/data/chapters/8/32.jpg b/public/data/chapters/8/32.jpg new file mode 100644 index 0000000..79784c6 Binary files /dev/null and b/public/data/chapters/8/32.jpg differ diff --git a/public/data/chapters/8/33.jpg b/public/data/chapters/8/33.jpg new file mode 100644 index 0000000..f42f418 Binary files /dev/null and b/public/data/chapters/8/33.jpg differ diff --git a/public/data/chapters/8/34.jpg b/public/data/chapters/8/34.jpg new file mode 100644 index 0000000..9ddb8a5 Binary files /dev/null and b/public/data/chapters/8/34.jpg differ diff --git a/public/data/chapters/8/35.jpg b/public/data/chapters/8/35.jpg new file mode 100644 index 0000000..80abdcd Binary files /dev/null and b/public/data/chapters/8/35.jpg differ diff --git a/public/data/chapters/8/36.jpg b/public/data/chapters/8/36.jpg new file mode 100644 index 0000000..1b72c16 Binary files /dev/null and b/public/data/chapters/8/36.jpg differ diff --git a/public/data/chapters/8/37.jpg b/public/data/chapters/8/37.jpg new file mode 100644 index 0000000..1e4f41a Binary files /dev/null and b/public/data/chapters/8/37.jpg differ diff --git a/public/data/chapters/8/38.jpg b/public/data/chapters/8/38.jpg new file mode 100644 index 0000000..ec7844a Binary files /dev/null and b/public/data/chapters/8/38.jpg differ diff --git a/public/data/chapters/8/39.jpg b/public/data/chapters/8/39.jpg new file mode 100644 index 0000000..63f3164 Binary files /dev/null and b/public/data/chapters/8/39.jpg differ diff --git a/public/data/chapters/8/4.jpg b/public/data/chapters/8/4.jpg new file mode 100644 index 0000000..4142ab8 Binary files /dev/null and b/public/data/chapters/8/4.jpg differ diff --git a/public/data/chapters/8/5.jpg b/public/data/chapters/8/5.jpg new file mode 100644 index 0000000..03db99b Binary files /dev/null and b/public/data/chapters/8/5.jpg differ diff --git a/public/data/chapters/8/6.jpg b/public/data/chapters/8/6.jpg new file mode 100644 index 0000000..555ab3c Binary files /dev/null and b/public/data/chapters/8/6.jpg differ diff --git a/public/data/chapters/8/7.jpg b/public/data/chapters/8/7.jpg new file mode 100644 index 0000000..7dc4f3c Binary files /dev/null and b/public/data/chapters/8/7.jpg differ diff --git a/public/data/chapters/8/8.jpg b/public/data/chapters/8/8.jpg new file mode 100644 index 0000000..daaf5a7 Binary files /dev/null and b/public/data/chapters/8/8.jpg differ diff --git a/public/data/chapters/8/9.jpg b/public/data/chapters/8/9.jpg new file mode 100644 index 0000000..d5abacc Binary files /dev/null and b/public/data/chapters/8/9.jpg differ diff --git a/public/data/chapters/9/1.jpg b/public/data/chapters/9/1.jpg new file mode 100644 index 0000000..d962821 Binary files /dev/null and b/public/data/chapters/9/1.jpg differ diff --git a/public/data/chapters/9/10.jpg b/public/data/chapters/9/10.jpg new file mode 100644 index 0000000..0c12733 Binary files /dev/null and b/public/data/chapters/9/10.jpg differ diff --git a/public/data/chapters/9/11.jpg b/public/data/chapters/9/11.jpg new file mode 100644 index 0000000..c03a9f7 Binary files /dev/null and b/public/data/chapters/9/11.jpg differ diff --git a/public/data/chapters/9/12.jpg b/public/data/chapters/9/12.jpg new file mode 100644 index 0000000..e118bf4 Binary files /dev/null and b/public/data/chapters/9/12.jpg differ diff --git a/public/data/chapters/9/13.jpg b/public/data/chapters/9/13.jpg new file mode 100644 index 0000000..4234563 Binary files /dev/null and b/public/data/chapters/9/13.jpg differ diff --git a/public/data/chapters/9/14.jpg b/public/data/chapters/9/14.jpg new file mode 100644 index 0000000..1aa9062 Binary files /dev/null and b/public/data/chapters/9/14.jpg differ diff --git a/public/data/chapters/9/15.jpg b/public/data/chapters/9/15.jpg new file mode 100644 index 0000000..e37f53b Binary files /dev/null and b/public/data/chapters/9/15.jpg differ diff --git a/public/data/chapters/9/16.jpg b/public/data/chapters/9/16.jpg new file mode 100644 index 0000000..12aeba0 Binary files /dev/null and b/public/data/chapters/9/16.jpg differ diff --git a/public/data/chapters/9/17.jpg b/public/data/chapters/9/17.jpg new file mode 100644 index 0000000..0a858b0 Binary files /dev/null and b/public/data/chapters/9/17.jpg differ diff --git a/public/data/chapters/9/18.jpg b/public/data/chapters/9/18.jpg new file mode 100644 index 0000000..70f97b6 Binary files /dev/null and b/public/data/chapters/9/18.jpg differ diff --git a/public/data/chapters/9/19.jpg b/public/data/chapters/9/19.jpg new file mode 100644 index 0000000..34026f3 Binary files /dev/null and b/public/data/chapters/9/19.jpg differ diff --git a/public/data/chapters/9/2.jpg b/public/data/chapters/9/2.jpg new file mode 100644 index 0000000..60dba48 Binary files /dev/null and b/public/data/chapters/9/2.jpg differ diff --git a/public/data/chapters/9/20.jpg b/public/data/chapters/9/20.jpg new file mode 100644 index 0000000..fb5706c Binary files /dev/null and b/public/data/chapters/9/20.jpg differ diff --git a/public/data/chapters/9/21.jpg b/public/data/chapters/9/21.jpg new file mode 100644 index 0000000..167d59c Binary files /dev/null and b/public/data/chapters/9/21.jpg differ diff --git a/public/data/chapters/9/22.jpg b/public/data/chapters/9/22.jpg new file mode 100644 index 0000000..6906eea Binary files /dev/null and b/public/data/chapters/9/22.jpg differ diff --git a/public/data/chapters/9/23.jpg b/public/data/chapters/9/23.jpg new file mode 100644 index 0000000..26438bf Binary files /dev/null and b/public/data/chapters/9/23.jpg differ diff --git a/public/data/chapters/9/24.jpg b/public/data/chapters/9/24.jpg new file mode 100644 index 0000000..46d9e59 Binary files /dev/null and b/public/data/chapters/9/24.jpg differ diff --git a/public/data/chapters/9/25.jpg b/public/data/chapters/9/25.jpg new file mode 100644 index 0000000..abe6882 Binary files /dev/null and b/public/data/chapters/9/25.jpg differ diff --git a/public/data/chapters/9/26.jpg b/public/data/chapters/9/26.jpg new file mode 100644 index 0000000..f2e7968 Binary files /dev/null and b/public/data/chapters/9/26.jpg differ diff --git a/public/data/chapters/9/27.jpg b/public/data/chapters/9/27.jpg new file mode 100644 index 0000000..698d2bc Binary files /dev/null and b/public/data/chapters/9/27.jpg differ diff --git a/public/data/chapters/9/28.jpg b/public/data/chapters/9/28.jpg new file mode 100644 index 0000000..6175da3 Binary files /dev/null and b/public/data/chapters/9/28.jpg differ diff --git a/public/data/chapters/9/29.jpg b/public/data/chapters/9/29.jpg new file mode 100644 index 0000000..1876f09 Binary files /dev/null and b/public/data/chapters/9/29.jpg differ diff --git a/public/data/chapters/9/3.jpg b/public/data/chapters/9/3.jpg new file mode 100644 index 0000000..4d3d5c8 Binary files /dev/null and b/public/data/chapters/9/3.jpg differ diff --git a/public/data/chapters/9/30.jpg b/public/data/chapters/9/30.jpg new file mode 100644 index 0000000..7da5365 Binary files /dev/null and b/public/data/chapters/9/30.jpg differ diff --git a/public/data/chapters/9/31.jpg b/public/data/chapters/9/31.jpg new file mode 100644 index 0000000..c81e508 Binary files /dev/null and b/public/data/chapters/9/31.jpg differ diff --git a/public/data/chapters/9/32.jpg b/public/data/chapters/9/32.jpg new file mode 100644 index 0000000..79784c6 Binary files /dev/null and b/public/data/chapters/9/32.jpg differ diff --git a/public/data/chapters/9/33.jpg b/public/data/chapters/9/33.jpg new file mode 100644 index 0000000..f42f418 Binary files /dev/null and b/public/data/chapters/9/33.jpg differ diff --git a/public/data/chapters/9/34.jpg b/public/data/chapters/9/34.jpg new file mode 100644 index 0000000..9ddb8a5 Binary files /dev/null and b/public/data/chapters/9/34.jpg differ diff --git a/public/data/chapters/9/35.jpg b/public/data/chapters/9/35.jpg new file mode 100644 index 0000000..80abdcd Binary files /dev/null and b/public/data/chapters/9/35.jpg differ diff --git a/public/data/chapters/9/36.jpg b/public/data/chapters/9/36.jpg new file mode 100644 index 0000000..1b72c16 Binary files /dev/null and b/public/data/chapters/9/36.jpg differ diff --git a/public/data/chapters/9/37.jpg b/public/data/chapters/9/37.jpg new file mode 100644 index 0000000..1e4f41a Binary files /dev/null and b/public/data/chapters/9/37.jpg differ diff --git a/public/data/chapters/9/38.jpg b/public/data/chapters/9/38.jpg new file mode 100644 index 0000000..ec7844a Binary files /dev/null and b/public/data/chapters/9/38.jpg differ diff --git a/public/data/chapters/9/39.jpg b/public/data/chapters/9/39.jpg new file mode 100644 index 0000000..63f3164 Binary files /dev/null and b/public/data/chapters/9/39.jpg differ diff --git a/public/data/chapters/9/4.jpg b/public/data/chapters/9/4.jpg new file mode 100644 index 0000000..4142ab8 Binary files /dev/null and b/public/data/chapters/9/4.jpg differ diff --git a/public/data/chapters/9/5.jpg b/public/data/chapters/9/5.jpg new file mode 100644 index 0000000..03db99b Binary files /dev/null and b/public/data/chapters/9/5.jpg differ diff --git a/public/data/chapters/9/6.jpg b/public/data/chapters/9/6.jpg new file mode 100644 index 0000000..555ab3c Binary files /dev/null and b/public/data/chapters/9/6.jpg differ diff --git a/public/data/chapters/9/7.jpg b/public/data/chapters/9/7.jpg new file mode 100644 index 0000000..7dc4f3c Binary files /dev/null and b/public/data/chapters/9/7.jpg differ diff --git a/public/data/chapters/9/8.jpg b/public/data/chapters/9/8.jpg new file mode 100644 index 0000000..daaf5a7 Binary files /dev/null and b/public/data/chapters/9/8.jpg differ diff --git a/public/data/chapters/9/9.jpg b/public/data/chapters/9/9.jpg new file mode 100644 index 0000000..d5abacc Binary files /dev/null and b/public/data/chapters/9/9.jpg differ diff --git a/public/data/covers/1.png b/public/data/covers/1.png new file mode 100644 index 0000000..e452931 Binary files /dev/null and b/public/data/covers/1.png differ diff --git a/public/data/covers/2.png b/public/data/covers/2.png new file mode 100644 index 0000000..b6cefad Binary files /dev/null and b/public/data/covers/2.png differ diff --git a/public/data/covers/3.png b/public/data/covers/3.png new file mode 100644 index 0000000..226ef95 Binary files /dev/null and b/public/data/covers/3.png differ diff --git a/public/data/covers/4.png b/public/data/covers/4.png new file mode 100644 index 0000000..ef09be9 Binary files /dev/null and b/public/data/covers/4.png differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/01.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/01.jpg new file mode 100644 index 0000000..d962821 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/01.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/02.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/02.jpg new file mode 100644 index 0000000..60dba48 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/02.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/03.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/03.jpg new file mode 100644 index 0000000..4d3d5c8 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/03.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/04.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/04.jpg new file mode 100644 index 0000000..4142ab8 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/04.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/05.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/05.jpg new file mode 100644 index 0000000..03db99b Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/05.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/06.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/06.jpg new file mode 100644 index 0000000..555ab3c Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/06.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/07.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/07.jpg new file mode 100644 index 0000000..7dc4f3c Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/07.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/08.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/08.jpg new file mode 100644 index 0000000..daaf5a7 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/08.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/09.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/09.jpg new file mode 100644 index 0000000..d5abacc Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/09.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/10.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/10.jpg new file mode 100644 index 0000000..0c12733 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/10.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/11.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/11.jpg new file mode 100644 index 0000000..c03a9f7 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/11.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/12.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/12.jpg new file mode 100644 index 0000000..e118bf4 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/12.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/13.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/13.jpg new file mode 100644 index 0000000..4234563 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/13.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/14.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/14.jpg new file mode 100644 index 0000000..1aa9062 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/14.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/15.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/15.jpg new file mode 100644 index 0000000..e37f53b Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/15.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/16.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/16.jpg new file mode 100644 index 0000000..12aeba0 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/16.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/17.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/17.jpg new file mode 100644 index 0000000..0a858b0 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/17.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/18.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/18.jpg new file mode 100644 index 0000000..70f97b6 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/18.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/19.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/19.jpg new file mode 100644 index 0000000..34026f3 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/19.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/20.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/20.jpg new file mode 100644 index 0000000..fb5706c Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/20.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/21.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/21.jpg new file mode 100644 index 0000000..167d59c Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/21.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/22.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/22.jpg new file mode 100644 index 0000000..6906eea Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/22.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/23.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/23.jpg new file mode 100644 index 0000000..26438bf Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/23.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/24.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/24.jpg new file mode 100644 index 0000000..46d9e59 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/24.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/25.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/25.jpg new file mode 100644 index 0000000..abe6882 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/25.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/26.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/26.jpg new file mode 100644 index 0000000..f2e7968 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/26.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/27.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/27.jpg new file mode 100644 index 0000000..698d2bc Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/27.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/28.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/28.jpg new file mode 100644 index 0000000..6175da3 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/28.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/29.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/29.jpg new file mode 100644 index 0000000..1876f09 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/29.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/30.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/30.jpg new file mode 100644 index 0000000..7da5365 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/30.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/31.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/31.jpg new file mode 100644 index 0000000..c81e508 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/31.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/32.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/32.jpg new file mode 100644 index 0000000..79784c6 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/32.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/33.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/33.jpg new file mode 100644 index 0000000..f42f418 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/33.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/34.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/34.jpg new file mode 100644 index 0000000..9ddb8a5 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/34.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/35.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/35.jpg new file mode 100644 index 0000000..80abdcd Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/35.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/36.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/36.jpg new file mode 100644 index 0000000..1b72c16 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/36.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/37.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/37.jpg new file mode 100644 index 0000000..1e4f41a Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/37.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/38.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/38.jpg new file mode 100644 index 0000000..ec7844a Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/38.jpg differ diff --git a/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/39.jpg b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/39.jpg new file mode 100644 index 0000000..63f3164 Binary files /dev/null and b/public/data/tmp/7/Oneshot (en) [No Group Scanlation]/39.jpg differ diff --git a/public/index.php b/public/index.php new file mode 100644 index 0000000..195eab9 --- /dev/null +++ b/public/index.php @@ -0,0 +1,66 @@ +createQueryBuilder() +// ->getQuery() +// ->fetch(); +// $titleCount = 0; +// $titleCountArray = array(); +// foreach ($_popularTitles as $key => $pop) { +// // 10 is the amount of max titles +// $ago = timeAgo($pop["timestamp"]); +// if (str_contains($ago, "second") || str_contains($ago, "min") || str_contains($ago, "hour") || str_contains($ago, "day")) { +// $views[$pop["title"]["id"]]["views"] = 0; +// $views[$pop["title"]["id"]]["title"] = array(); +// $popularTitles[$pop["title"]["id"]] = array(); +// if ($titleCount <= 4 && !in_array($pop["title"]["id"], $titleCountArray)) { +// $titleCount++; +// array_push($titleCountArray, $pop["title"]["id"]); +// } +// } +// } +// foreach ($_popularTitles as $key => $pop) { +// $ago = timeAgo($pop["timestamp"]); +// if (str_contains($ago, "second") || str_contains($ago, "min") || str_contains($ago, "hour") || str_contains($ago, "day")) { +// $views[$pop["title"]["id"]]["views"]++; +// if (empty($views[$pop["title"]["id"]]["title"])) { +// $views[$pop["title"]["id"]]["title"] = $db["titles"]->findById($pop["title"]["id"]); +// $views[$pop["title"]["id"]]["title"]["summary1"] = shorten($parsedown->text($purifier->purify($views[$pop["title"]["id"]]["title"]["summary"])), 200); +// $views[$pop["title"]["id"]]["title"]["summary2"] = shorten($parsedown->text($purifier->purify($views[$pop["title"]["id"]]["title"]["summary"])), 200); +// } +// } +// } +// sort($views); +// $views = array_reverse($views); +// /Popular Titles +// $smarty->assign("popularTitles", $views); + +// Recently Updated Titles +$recentlyUpdated = $db["chapters"]->createQueryBuilder() + ->orderBy(["id" => "DESC"]) + ->distinct(["title.id"]) + ->getQuery() + ->fetch(); + +foreach ($recentlyUpdated as $key => $rec) { + $title = $db["titles"]->findById($rec["title"]["id"]); + $recentlyUpdated[$key]["title"]["summary1"] = shorten($parsedown->text($purifier->purify($title["summary"])), 400); + $recentlyUpdated[$key]["title"]["summary2"] = shorten($parsedown->text($purifier->purify($title["summary"])), 100); +} + +$chapters = $db["chapters"]->createQueryBuilder() + ->orderBy(["id" => "DESC"]) + ->limit($config["perpage"]["chapters"]) + ->getQuery() + ->fetch(); + +$smarty->assign("chapters", $chapters); +$smarty->assign("recentlyUpdated", $recentlyUpdated); +$smarty->assign("pagetitle", $config["title"] . " " . $config["divider"] . " " . $config["slogan"]); + +$smarty->display("parts/header.tpl"); +$smarty->display("pages/index.tpl"); +$smarty->display("parts/footer.tpl"); diff --git a/public/install.php b/public/install.php new file mode 100644 index 0000000..c365488 --- /dev/null +++ b/public/install.php @@ -0,0 +1,328 @@ + "http://api.h33t.moe/api.php?action=fsx_installation&key={$key}&domain={$actualLink}", + CURLOPT_RETURNTRANSFER => true, + CURLOPT_ENCODING => "", + CURLOPT_MAXREDIRS => 10, + CURLOPT_TIMEOUT => 0, + CURLOPT_FOLLOWLOCATION => true, + CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1, + CURLOPT_CUSTOMREQUEST => "POST", + )); + $response = curl_exec($curl); + // print_r($response); + + unlink("install.php"); + header("Refresh: 2; url=index.php"); +} + +?> + + + + + + + + + + FoOlSlideX Installation + + + + + + + + + + + + + + + + +
+ + + FoOlSlideX Logo + +

+ Developed by + Saintly2k and + The + Gang. +

+ +
+ +
+
    +
  • = 1 ? "step-primary" : "step-info" ?>">Requirements
    • +
  • = 1 ? ($_GET["step"] == 1 ? "step-primary step-info" : "step-primary") : "" ?>">Credits
    • + +
  • = 3 ? ($_GET["step"] == 3 ? "step-primary step-info" : "step-primary") : "" ?>">Installation
    • +
  • = 4 ? ($_GET["step"] == 4 ? "step-primary step-success" : "step-primary") : "" ?>">Finish
    • +
+
+ + +

Requirements

+
+
+

+ Before you start, please make sure that you edited the config.php file in the root directory properly. If you did not, you can use this installer just fine but it will fail to initiate some things, so please do it. +

+

+ If you have some questions, join the Discord and ask in #foolslidex for help. We'll try to answer as soon as possible. +

+
+ + Continue + +
+ + + +

Credits

+
+
+

+ FoOlSlideX is an open-source software for sharing and reading comics of all kinds. +

+

+ It has been developed by the following people: +

+ +

+ It makes use of the following technologies and softwares: +

+ +
+ + Continue + +
+ +
+

+ To support the lead developers, Saintly2k, Kaligula and S-VHS, please consider donating: +

+
+
+ + Donate through Ko-fi + +
+
+ + Donate through PayPal + +
+
+
+ + + + + +

Installation

+
+
+

There's nothing here to customize yet. Maybe we'll implement something here later on in newer versions.

+ +
+
+ + + +

Installation

+
+

You're almost done! To finalize your installation, hit the button below.

+ + Finalize + +
+ + + +

Finishing

+
+

+ If everything worked, you should be redirected in two seconds... +

+
+ + +
+ +

+ Installing FoOlSlideX + +
+ by Saintly2k and + The + Gang. + +
+ or + +

+ +
+ + + +
+
+

Change Design

+ +
+ +
+
+
+
+
+ +
+ + + + +
+
+
+
+ + +
+
+
+ + + + +
+
+

Change Language

+
+ +
');updateUserLang('');"> +

+

+ by + + " target="_blank" class="link"> + + + + + +

+

Updated:

+
+ + +
+
+
+ + + + + + + \ No newline at end of file diff --git a/public/releases.php b/public/releases.php new file mode 100644 index 0000000..fd5dc96 --- /dev/null +++ b/public/releases.php @@ -0,0 +1,31 @@ +createQueryBuilder() + ->orderBy(["id" => "DESC"]) + ->limit($limit) + ->skip($skip) + ->getQuery() + ->fetch(); + +$pagis = array(); +$totalPages = $db["chapters"]->count() / $config["perpage"]["chapters"]; +for ($i = 0; $i < $totalPages; $i++) { + array_push($pagis, $i + 1); +} + +$smarty->assign("pagetitle", "Releases - Page " . $page . " " . $config["divider"] . " " . $config["title"]); +$smarty->assign("page", $page); +$smarty->assign("chapters", $chapters); +$smarty->assign("pagis", $pagis); +$smarty->assign("totalPages", $totalPages); + +$smarty->display("parts/header.tpl"); +$smarty->display("pages/releases.tpl"); +$smarty->display("parts/footer.tpl"); diff --git a/public/title.php b/public/title.php new file mode 100644 index 0000000..fc527e8 --- /dev/null +++ b/public/title.php @@ -0,0 +1,137 @@ +findById($id); +if (empty($title)) header("Location: titles.php") && die("Title not found."); + +$title["authors2"] = $title["authors"]; +$title["artists2"] = $title["artists"]; +if (!empty($title["authors"])) $title["authors"] = explode(",", $title["authors"]); +if (!empty($title["artists"])) $title["artists"] = explode(",", $title["artists"]); + +if (!empty($title["tags"]["formats"])) { + $_array = array(); + foreach ($title["tags"]["formats"] as $item) { + if (!empty($item) && is_numeric($item)) { + $call = getTag("format", $item); + if (!empty($call)) array_push($_array, $call); + } + } + $title["tags"]["_formats"] = $title["tags"]["formats"]; + $title["tags"]["formats"] = $_array; +} else { + $title["tags"]["_formats"] = array(); +} +if (!empty($title["tags"]["warnings"])) { + $_array = array(); + foreach ($title["tags"]["warnings"] as $item) { + if (!empty($item) && is_numeric($item)) { + $call = getTag("warnings", $item); + if (!empty($call)) array_push($_array, $call); + } + } + $title["tags"]["_warnings"] = $title["tags"]["warnings"]; + $title["tags"]["warnings"] = $_array; +} else { + $title["tags"]["_warnings"] = array(); +} +if (!empty($title["tags"]["themes"])) { + $_array = array(); + foreach ($title["tags"]["themes"] as $item) { + if (!empty($item) && is_numeric($item)) { + $call = getTag("theme", $item); + if (!empty($call)) array_push($_array, $call); + } + } + $title["tags"]["_themes"] = $title["tags"]["themes"]; + $title["tags"]["themes"] = $_array; +} else { + $title["tags"]["_themes"] = array(); +} +if (!empty($title["tags"]["genres"])) { + $_array = array(); + foreach ($title["tags"]["genres"] as $item) { + if (!empty($item) && is_numeric($item)) { + $call = getTag("genre", $item); + if (!empty($call)) array_push($_array, $call); + } + } + $title["tags"]["_genres"] = $title["tags"]["genres"]; + $title["tags"]["genres"] = $_array; +} else { + $title["tags"]["_genres"] = array(); +} + +if ($logged && $user["level"] >= 75) { + // Gotta implement a function here that makes it for all files inside /custom/ + $upl["theme"] = valCustom("theme"); + $upl["genre"] = valCustom("genre"); + $upl["warnings"] = valCustom("warnings"); + $upl["format"] = valCustom("format"); + $upl["langs"] = valCLang("upload_langs"); + + $smarty->assign("upl_theme", $upl["theme"]); + $smarty->assign("upl_genre", $upl["genre"]); + $smarty->assign("upl_warnings", $upl["warnings"]); + $smarty->assign("upl_format", $upl["format"]); + $smarty->assign("upl_langs", $upl["langs"]); +} + +if (!empty($title["summary"])) { + $title["summary2"] = $title["summary"]; + $title["summary"] = $parsedown->text($purifier->purify($title["summary"])); +} else { + $title["summary2"] = ""; +} + +$chapters = array(); +$chapterLangs = array(); +$chapterCount = 0; +if (!empty($db["chapters"]->findOneBy(["title.id", "=", $title["id"]]))) { + // Chapter Languages + $chapterLangs = $db["chapters"]->createQueryBuilder() + ->select(["language"]) + ->where(["title.id", "=", $title["id"]]) + ->distinct("language.0") + ->getQuery() + ->fetch(); + sort($chapterLangs); + // Preferred Language + if (!in_array($preflang, array_column(array_column($chapterLangs, "language"), 1))) $smarty->assign("preflang", $chapterLangs[0]["language"][1]); + // Actual Chapters + foreach ($chapterLangs as $key => $chLang) { + $_chapters = $db["chapters"]->createQueryBuilder() + ->where([["title.id", "=", $title["id"]], "AND", ["language.1", "=", $chLang["language"][1]]]) + ->orderBy(["volume" => "DESC"]) + ->orderBy(["number" => "DESC"]) + ->getQuery() + ->fetch(); + if (!empty($_chapters)) { + $chapterLangs[$key]["language"]["chapters"] = array(); + $chapterLangs[$key]["language"]["count"] = count($_chapters); + foreach ($_chapters as $_chapter) { + // array_push($chapterLangs[$chLang[]], $_chapter); + array_push($chapterLangs[$key]["language"]["chapters"], $_chapter); + $chapterCount++; + } + } + } +} + +$comments = $db["titleComments"]->findBy(["title.id", "=", $title["id"]], ["id" => "DESC"]); + +titleVisit($title); + +$smarty->assign("commentsCount", count($comments)); +$smarty->assign("chapterLangs", $chapterLangs); +$smarty->assign("chapterCount", $chapterCount); +$smarty->assign("pagetitle", $title["title"] . " (Title) " . $config["divider"] . " " . $config["title"]); +$smarty->assign("title", $title); + +$smarty->display("parts/header.tpl"); +$smarty->display("pages/title.tpl"); +$smarty->display("parts/footer.tpl"); diff --git a/public/titles.php b/public/titles.php new file mode 100644 index 0000000..54eab30 --- /dev/null +++ b/public/titles.php @@ -0,0 +1,45 @@ +createQueryBuilder() + ->orderBy(["title" => "ASC"]) + ->limit($limit) + ->skip($skip) + ->getQuery() + ->fetch(); + +$pagis = array(); +$totalPages = $db["titles"]->count() / $config["perpage"]["titles"]; +for ($i = 0; $i < $totalPages; $i++) { + array_push($pagis, $i + 1); +} + +if($logged && $user["level"] >= 75) { + // Gotta implement a function here that makes it for all files inside /custom/ + $upl["theme"] = valCustom("theme"); + $upl["genre"] = valCustom("genre"); + $upl["warnings"] = valCustom("warnings"); + $upl["format"] = valCustom("format"); + //valCLang("upload_langs"); + + $smarty->assign("upl_theme", $upl["theme"]); + $smarty->assign("upl_genre", $upl["genre"]); + $smarty->assign("upl_warnings", $upl["warnings"]); + $smarty->assign("upl_format", $upl["format"]); +} + +$smarty->assign("pagetitle", "Titles - Page " . $page . " " . $config["divider"] . " " . $config["title"]); +$smarty->assign("page", $page); +$smarty->assign("titles", $titles); +$smarty->assign("pagis", $pagis); +$smarty->assign("totalPages", $totalPages); + +$smarty->display("parts/header.tpl"); +$smarty->display("pages/titles.tpl"); +$smarty->display("parts/footer.tpl"); diff --git a/session.php b/session.php new file mode 100644 index 0000000..f3b401a --- /dev/null +++ b/session.php @@ -0,0 +1,15 @@ +findOneBy(["token", "=", $token]); + if (!empty($session)) { + unset($user); + $user = $db["users"]->findOneBy(["id", "=", $session["user"]]); + if (!empty($user)) { + $logged = true; + } + } +} diff --git a/software/HTMLPurifier/HTMLPurifier.auto.php b/software/HTMLPurifier/HTMLPurifier.auto.php new file mode 100644 index 0000000..1960c39 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier.auto.php @@ -0,0 +1,11 @@ +purify($html, $config); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier.includes.php b/software/HTMLPurifier/HTMLPurifier.includes.php new file mode 100644 index 0000000..47ee013 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier.includes.php @@ -0,0 +1,235 @@ + $attributes) { + $allowed_elements[$element] = true; + foreach ($attributes as $attribute => $x) { + $allowed_attributes["$element.$attribute"] = true; + } + } + $config->set('HTML.AllowedElements', $allowed_elements); + $config->set('HTML.AllowedAttributes', $allowed_attributes); + if ($allowed_protocols !== null) { + $config->set('URI.AllowedSchemes', $allowed_protocols); + } + $purifier = new HTMLPurifier($config); + return $purifier->purify($string); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier.path.php b/software/HTMLPurifier/HTMLPurifier.path.php new file mode 100644 index 0000000..39b1b65 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier.path.php @@ -0,0 +1,11 @@ +config = HTMLPurifier_Config::create($config); + $this->strategy = new HTMLPurifier_Strategy_Core(); + } + + /** + * Adds a filter to process the output. First come first serve + * + * @param HTMLPurifier_Filter $filter HTMLPurifier_Filter object + */ + public function addFilter($filter) + { + trigger_error( + 'HTMLPurifier->addFilter() is deprecated, use configuration directives' . + ' in the Filter namespace or Filter.Custom', + E_USER_WARNING + ); + $this->filters[] = $filter; + } + + /** + * Filters an HTML snippet/document to be XSS-free and standards-compliant. + * + * @param string $html String of HTML to purify + * @param HTMLPurifier_Config $config Config object for this operation, + * if omitted, defaults to the config object specified during this + * object's construction. The parameter can also be any type + * that HTMLPurifier_Config::create() supports. + * + * @return string Purified HTML + */ + public function purify($html, $config = null) + { + // :TODO: make the config merge in, instead of replace + $config = $config ? HTMLPurifier_Config::create($config) : $this->config; + + // implementation is partially environment dependant, partially + // configuration dependant + $lexer = HTMLPurifier_Lexer::create($config); + + $context = new HTMLPurifier_Context(); + + // setup HTML generator + $this->generator = new HTMLPurifier_Generator($config, $context); + $context->register('Generator', $this->generator); + + // set up global context variables + if ($config->get('Core.CollectErrors')) { + // may get moved out if other facilities use it + $language_factory = HTMLPurifier_LanguageFactory::instance(); + $language = $language_factory->create($config, $context); + $context->register('Locale', $language); + + $error_collector = new HTMLPurifier_ErrorCollector($context); + $context->register('ErrorCollector', $error_collector); + } + + // setup id_accumulator context, necessary due to the fact that + // AttrValidator can be called from many places + $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context); + $context->register('IDAccumulator', $id_accumulator); + + $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context); + + // setup filters + $filter_flags = $config->getBatch('Filter'); + $custom_filters = $filter_flags['Custom']; + unset($filter_flags['Custom']); + $filters = array(); + foreach ($filter_flags as $filter => $flag) { + if (!$flag) { + continue; + } + if (strpos($filter, '.') !== false) { + continue; + } + $class = "HTMLPurifier_Filter_$filter"; + $filters[] = new $class; + } + foreach ($custom_filters as $filter) { + // maybe "HTMLPurifier_Filter_$filter", but be consistent with AutoFormat + $filters[] = $filter; + } + $filters = array_merge($filters, $this->filters); + // maybe prepare(), but later + + for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) { + $html = $filters[$i]->preFilter($html, $config, $context); + } + + // purified HTML + $html = + $this->generator->generateFromTokens( + // list of tokens + $this->strategy->execute( + // list of un-purified tokens + $lexer->tokenizeHTML( + // un-purified HTML + $html, + $config, + $context + ), + $config, + $context + ) + ); + + for ($i = $filter_size - 1; $i >= 0; $i--) { + $html = $filters[$i]->postFilter($html, $config, $context); + } + + $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context); + $this->context =& $context; + return $html; + } + + /** + * Filters an array of HTML snippets + * + * @param string[] $array_of_html Array of html snippets + * @param HTMLPurifier_Config $config Optional config object for this operation. + * See HTMLPurifier::purify() for more details. + * + * @return string[] Array of purified HTML + */ + public function purifyArray($array_of_html, $config = null) + { + $context_array = array(); + $array = array(); + foreach($array_of_html as $key=>$value){ + if (is_array($value)) { + $array[$key] = $this->purifyArray($value, $config); + } else { + $array[$key] = $this->purify($value, $config); + } + $context_array[$key] = $this->context; + } + $this->context = $context_array; + return $array; + } + + /** + * Singleton for enforcing just one HTML Purifier in your system + * + * @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype + * HTMLPurifier instance to overload singleton with, + * or HTMLPurifier_Config instance to configure the + * generated version with. + * + * @return HTMLPurifier + */ + public static function instance($prototype = null) + { + if (!self::$instance || $prototype) { + if ($prototype instanceof HTMLPurifier) { + self::$instance = $prototype; + } elseif ($prototype) { + self::$instance = new HTMLPurifier($prototype); + } else { + self::$instance = new HTMLPurifier(); + } + } + return self::$instance; + } + + /** + * Singleton for enforcing just one HTML Purifier in your system + * + * @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype + * HTMLPurifier instance to overload singleton with, + * or HTMLPurifier_Config instance to configure the + * generated version with. + * + * @return HTMLPurifier + * @note Backwards compatibility, see instance() + */ + public static function getInstance($prototype = null) + { + return HTMLPurifier::instance($prototype); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier.safe-includes.php b/software/HTMLPurifier/HTMLPurifier.safe-includes.php new file mode 100644 index 0000000..94543f5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier.safe-includes.php @@ -0,0 +1,229 @@ +getHTMLDefinition(); + $parent = new HTMLPurifier_Token_Start($definition->info_parent); + $stack = array($parent->toNode()); + foreach ($tokens as $token) { + $token->skip = null; // [MUT] + $token->carryover = null; // [MUT] + if ($token instanceof HTMLPurifier_Token_End) { + $token->start = null; // [MUT] + $r = array_pop($stack); + //assert($r->name === $token->name); + //assert(empty($token->attr)); + $r->endCol = $token->col; + $r->endLine = $token->line; + $r->endArmor = $token->armor; + continue; + } + $node = $token->toNode(); + $stack[count($stack)-1]->children[] = $node; + if ($token instanceof HTMLPurifier_Token_Start) { + $stack[] = $node; + } + } + //assert(count($stack) == 1); + return $stack[0]; + } + + public static function flatten($node, $config, $context) { + $level = 0; + $nodes = array($level => new HTMLPurifier_Queue(array($node))); + $closingTokens = array(); + $tokens = array(); + do { + while (!$nodes[$level]->isEmpty()) { + $node = $nodes[$level]->shift(); // FIFO + list($start, $end) = $node->toTokenPair(); + if ($level > 0) { + $tokens[] = $start; + } + if ($end !== NULL) { + $closingTokens[$level][] = $end; + } + if ($node instanceof HTMLPurifier_Node_Element) { + $level++; + $nodes[$level] = new HTMLPurifier_Queue(); + foreach ($node->children as $childNode) { + $nodes[$level]->push($childNode); + } + } + } + $level--; + if ($level && isset($closingTokens[$level])) { + while ($token = array_pop($closingTokens[$level])) { + $tokens[] = $token; + } + } + } while ($level > 0); + return $tokens; + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/AttrCollections.php b/software/HTMLPurifier/HTMLPurifier/AttrCollections.php new file mode 100644 index 0000000..c7b17cf --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrCollections.php @@ -0,0 +1,148 @@ +doConstruct($attr_types, $modules); + } + + public function doConstruct($attr_types, $modules) + { + // load extensions from the modules + foreach ($modules as $module) { + foreach ($module->attr_collections as $coll_i => $coll) { + if (!isset($this->info[$coll_i])) { + $this->info[$coll_i] = array(); + } + foreach ($coll as $attr_i => $attr) { + if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) { + // merge in includes + $this->info[$coll_i][$attr_i] = array_merge( + $this->info[$coll_i][$attr_i], + $attr + ); + continue; + } + $this->info[$coll_i][$attr_i] = $attr; + } + } + } + // perform internal expansions and inclusions + foreach ($this->info as $name => $attr) { + // merge attribute collections that include others + $this->performInclusions($this->info[$name]); + // replace string identifiers with actual attribute objects + $this->expandIdentifiers($this->info[$name], $attr_types); + } + } + + /** + * Takes a reference to an attribute associative array and performs + * all inclusions specified by the zero index. + * @param array &$attr Reference to attribute array + */ + public function performInclusions(&$attr) + { + if (!isset($attr[0])) { + return; + } + $merge = $attr[0]; + $seen = array(); // recursion guard + // loop through all the inclusions + for ($i = 0; isset($merge[$i]); $i++) { + if (isset($seen[$merge[$i]])) { + continue; + } + $seen[$merge[$i]] = true; + // foreach attribute of the inclusion, copy it over + if (!isset($this->info[$merge[$i]])) { + continue; + } + foreach ($this->info[$merge[$i]] as $key => $value) { + if (isset($attr[$key])) { + continue; + } // also catches more inclusions + $attr[$key] = $value; + } + if (isset($this->info[$merge[$i]][0])) { + // recursion + $merge = array_merge($merge, $this->info[$merge[$i]][0]); + } + } + unset($attr[0]); + } + + /** + * Expands all string identifiers in an attribute array by replacing + * them with the appropriate values inside HTMLPurifier_AttrTypes + * @param array &$attr Reference to attribute array + * @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance + */ + public function expandIdentifiers(&$attr, $attr_types) + { + // because foreach will process new elements we add, make sure we + // skip duplicates + $processed = array(); + + foreach ($attr as $def_i => $def) { + // skip inclusions + if ($def_i === 0) { + continue; + } + + if (isset($processed[$def_i])) { + continue; + } + + // determine whether or not attribute is required + if ($required = (strpos($def_i, '*') !== false)) { + // rename the definition + unset($attr[$def_i]); + $def_i = trim($def_i, '*'); + $attr[$def_i] = $def; + } + + $processed[$def_i] = true; + + // if we've already got a literal object, move on + if (is_object($def)) { + // preserve previous required + $attr[$def_i]->required = ($required || $attr[$def_i]->required); + continue; + } + + if ($def === false) { + unset($attr[$def_i]); + continue; + } + + if ($t = $attr_types->get($def)) { + $attr[$def_i] = $t; + $attr[$def_i]->required = $required; + } else { + unset($attr[$def_i]); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef.php b/software/HTMLPurifier/HTMLPurifier/AttrDef.php new file mode 100644 index 0000000..739646f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef.php @@ -0,0 +1,144 @@ + by removing + * leading and trailing whitespace, ignoring line feeds, and replacing + * carriage returns and tabs with spaces. While most useful for HTML + * attributes specified as CDATA, it can also be applied to most CSS + * values. + * + * @note This method is not entirely standards compliant, as trim() removes + * more types of whitespace than specified in the spec. In practice, + * this is rarely a problem, as those extra characters usually have + * already been removed by HTMLPurifier_Encoder. + * + * @warning This processing is inconsistent with XML's whitespace handling + * as specified by section 3.3.3 and referenced XHTML 1.0 section + * 4.7. However, note that we are NOT necessarily + * parsing XML, thus, this behavior may still be correct. We + * assume that newlines have been normalized. + */ + public function parseCDATA($string) + { + $string = trim($string); + $string = str_replace(array("\n", "\t", "\r"), ' ', $string); + return $string; + } + + /** + * Factory method for creating this class from a string. + * @param string $string String construction info + * @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string + */ + public function make($string) + { + // default implementation, return a flyweight of this object. + // If $string has an effect on the returned object (i.e. you + // need to overload this method), it is best + // to clone or instantiate new copies. (Instantiation is safer.) + return $this; + } + + /** + * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work + * properly. THIS IS A HACK! + * @param string $string a CSS colour definition + * @return string + */ + protected function mungeRgb($string) + { + $p = '\s*(\d+(\.\d+)?([%]?))\s*'; + + if (preg_match('/(rgba|hsla)\(/', $string)) { + return preg_replace('/(rgba|hsla)\('.$p.','.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8,\11)', $string); + } + + return preg_replace('/(rgb|hsl)\('.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8)', $string); + } + + /** + * Parses a possibly escaped CSS string and returns the "pure" + * version of it. + */ + protected function expandCSSEscape($string) + { + // flexibly parse it + $ret = ''; + for ($i = 0, $c = strlen($string); $i < $c; $i++) { + if ($string[$i] === '\\') { + $i++; + if ($i >= $c) { + $ret .= '\\'; + break; + } + if (ctype_xdigit($string[$i])) { + $code = $string[$i]; + for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) { + if (!ctype_xdigit($string[$i])) { + break; + } + $code .= $string[$i]; + } + // We have to be extremely careful when adding + // new characters, to make sure we're not breaking + // the encoding. + $char = HTMLPurifier_Encoder::unichr(hexdec($code)); + if (HTMLPurifier_Encoder::cleanUTF8($char) === '') { + continue; + } + $ret .= $char; + if ($i < $c && trim($string[$i]) !== '') { + $i--; + } + continue; + } + if ($string[$i] === "\n") { + continue; + } + } + $ret .= $string[$i]; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php new file mode 100644 index 0000000..ad2cb90 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php @@ -0,0 +1,136 @@ +parseCDATA($css); + + $definition = $config->getCSSDefinition(); + $allow_duplicates = $config->get("CSS.AllowDuplicates"); + + + // According to the CSS2.1 spec, the places where a + // non-delimiting semicolon can appear are in strings + // escape sequences. So here is some dumb hack to + // handle quotes. + $len = strlen($css); + $accum = ""; + $declarations = array(); + $quoted = false; + for ($i = 0; $i < $len; $i++) { + $c = strcspn($css, ";'\"", $i); + $accum .= substr($css, $i, $c); + $i += $c; + if ($i == $len) break; + $d = $css[$i]; + if ($quoted) { + $accum .= $d; + if ($d == $quoted) { + $quoted = false; + } + } else { + if ($d == ";") { + $declarations[] = $accum; + $accum = ""; + } else { + $accum .= $d; + $quoted = $d; + } + } + } + if ($accum != "") $declarations[] = $accum; + + $propvalues = array(); + $new_declarations = ''; + + /** + * Name of the current CSS property being validated. + */ + $property = false; + $context->register('CurrentCSSProperty', $property); + + foreach ($declarations as $declaration) { + if (!$declaration) { + continue; + } + if (!strpos($declaration, ':')) { + continue; + } + list($property, $value) = explode(':', $declaration, 2); + $property = trim($property); + $value = trim($value); + $ok = false; + do { + if (isset($definition->info[$property])) { + $ok = true; + break; + } + if (ctype_lower($property)) { + break; + } + $property = strtolower($property); + if (isset($definition->info[$property])) { + $ok = true; + break; + } + } while (0); + if (!$ok) { + continue; + } + // inefficient call, since the validator will do this again + if (strtolower(trim($value)) !== 'inherit') { + // inherit works for everything (but only on the base property) + $result = $definition->info[$property]->validate( + $value, + $config, + $context + ); + } else { + $result = 'inherit'; + } + if ($result === false) { + continue; + } + if ($allow_duplicates) { + $new_declarations .= "$property:$result;"; + } else { + $propvalues[$property] = $result; + } + } + + $context->destroy('CurrentCSSProperty'); + + // procedure does not write the new CSS simultaneously, so it's + // slightly inefficient, but it's the only way of getting rid of + // duplicates. Perhaps config to optimize it, but not now. + + foreach ($propvalues as $prop => $value) { + $new_declarations .= "$prop:$value;"; + } + + return $new_declarations ? $new_declarations : false; + + } + +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php new file mode 100644 index 0000000..af2b83d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php @@ -0,0 +1,34 @@ + 1.0) { + $result = '1'; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php new file mode 100644 index 0000000..28c4988 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php @@ -0,0 +1,113 @@ +getCSSDefinition(); + $this->info['background-color'] = $def->info['background-color']; + $this->info['background-image'] = $def->info['background-image']; + $this->info['background-repeat'] = $def->info['background-repeat']; + $this->info['background-attachment'] = $def->info['background-attachment']; + $this->info['background-position'] = $def->info['background-position']; + $this->info['background-size'] = $def->info['background-size']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // munge rgb() decl if necessary + $string = $this->mungeRgb($string); + + // assumes URI doesn't have spaces in it + $bits = explode(' ', $string); // bits to process + + $caught = array(); + $caught['color'] = false; + $caught['image'] = false; + $caught['repeat'] = false; + $caught['attachment'] = false; + $caught['position'] = false; + $caught['size'] = false; + + $i = 0; // number of catches + + foreach ($bits as $bit) { + if ($bit === '') { + continue; + } + foreach ($caught as $key => $status) { + if ($key != 'position') { + if ($status !== false) { + continue; + } + $r = $this->info['background-' . $key]->validate($bit, $config, $context); + } else { + $r = $bit; + } + if ($r === false) { + continue; + } + if ($key == 'position') { + if ($caught[$key] === false) { + $caught[$key] = ''; + } + $caught[$key] .= $r . ' '; + } else { + $caught[$key] = $r; + } + $i++; + break; + } + } + + if (!$i) { + return false; + } + if ($caught['position'] !== false) { + $caught['position'] = $this->info['background-position']-> + validate($caught['position'], $config, $context); + } + + $ret = array(); + foreach ($caught as $value) { + if ($value === false) { + continue; + } + $ret[] = $value; + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php new file mode 100644 index 0000000..4580ef5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php @@ -0,0 +1,157 @@ + | | left | center | right + ] + [ + | | top | center | bottom + ]? + ] | + [ // this signifies that the vertical and horizontal adjectives + // can be arbitrarily ordered, however, there can only be two, + // one of each, or none at all + [ + left | center | right + ] || + [ + top | center | bottom + ] + ] + top, left = 0% + center, (none) = 50% + bottom, right = 100% +*/ + +/* QuirksMode says: + keyword + length/percentage must be ordered correctly, as per W3C + + Internet Explorer and Opera, however, support arbitrary ordering. We + should fix it up. + + Minor issue though, not strictly necessary. +*/ + +// control freaks may appreciate the ability to convert these to +// percentages or something, but it's not necessary + +/** + * Validates the value of background-position. + */ +class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef +{ + + /** + * @type HTMLPurifier_AttrDef_CSS_Length + */ + protected $length; + + /** + * @type HTMLPurifier_AttrDef_CSS_Percentage + */ + protected $percentage; + + public function __construct() + { + $this->length = new HTMLPurifier_AttrDef_CSS_Length(); + $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage(); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + $bits = explode(' ', $string); + + $keywords = array(); + $keywords['h'] = false; // left, right + $keywords['v'] = false; // top, bottom + $keywords['ch'] = false; // center (first word) + $keywords['cv'] = false; // center (second word) + $measures = array(); + + $i = 0; + + $lookup = array( + 'top' => 'v', + 'bottom' => 'v', + 'left' => 'h', + 'right' => 'h', + 'center' => 'c' + ); + + foreach ($bits as $bit) { + if ($bit === '') { + continue; + } + + // test for keyword + $lbit = ctype_lower($bit) ? $bit : strtolower($bit); + if (isset($lookup[$lbit])) { + $status = $lookup[$lbit]; + if ($status == 'c') { + if ($i == 0) { + $status = 'ch'; + } else { + $status = 'cv'; + } + } + $keywords[$status] = $lbit; + $i++; + } + + // test for length + $r = $this->length->validate($bit, $config, $context); + if ($r !== false) { + $measures[] = $r; + $i++; + } + + // test for percentage + $r = $this->percentage->validate($bit, $config, $context); + if ($r !== false) { + $measures[] = $r; + $i++; + } + } + + if (!$i) { + return false; + } // no valid values were caught + + $ret = array(); + + // first keyword + if ($keywords['h']) { + $ret[] = $keywords['h']; + } elseif ($keywords['ch']) { + $ret[] = $keywords['ch']; + $keywords['cv'] = false; // prevent re-use: center = center center + } elseif (count($measures)) { + $ret[] = array_shift($measures); + } + + if ($keywords['v']) { + $ret[] = $keywords['v']; + } elseif ($keywords['cv']) { + $ret[] = $keywords['cv']; + } elseif (count($measures)) { + $ret[] = array_shift($measures); + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php new file mode 100644 index 0000000..16243ba --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php @@ -0,0 +1,56 @@ +getCSSDefinition(); + $this->info['border-width'] = $def->info['border-width']; + $this->info['border-style'] = $def->info['border-style']; + $this->info['border-top-color'] = $def->info['border-top-color']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + $string = $this->mungeRgb($string); + $bits = explode(' ', $string); + $done = array(); // segments we've finished + $ret = ''; // return value + foreach ($bits as $bit) { + foreach ($this->info as $propname => $validator) { + if (isset($done[$propname])) { + continue; + } + $r = $validator->validate($bit, $config, $context); + if ($r !== false) { + $ret .= $r . ' '; + $done[$propname] = true; + break; + } + } + } + return rtrim($ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php new file mode 100644 index 0000000..d7287a0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php @@ -0,0 +1,161 @@ +alpha = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + } + + /** + * @param string $color + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($color, $config, $context) + { + static $colors = null; + if ($colors === null) { + $colors = $config->get('Core.ColorKeywords'); + } + + $color = trim($color); + if ($color === '') { + return false; + } + + $lower = strtolower($color); + if (isset($colors[$lower])) { + return $colors[$lower]; + } + + if (preg_match('#(rgb|rgba|hsl|hsla)\(#', $color, $matches) === 1) { + $length = strlen($color); + if (strpos($color, ')') !== $length - 1) { + return false; + } + + // get used function : rgb, rgba, hsl or hsla + $function = $matches[1]; + + $parameters_size = 3; + $alpha_channel = false; + if (substr($function, -1) === 'a') { + $parameters_size = 4; + $alpha_channel = true; + } + + /* + * Allowed types for values : + * parameter_position => [type => max_value] + */ + $allowed_types = array( + 1 => array('percentage' => 100, 'integer' => 255), + 2 => array('percentage' => 100, 'integer' => 255), + 3 => array('percentage' => 100, 'integer' => 255), + ); + $allow_different_types = false; + + if (strpos($function, 'hsl') !== false) { + $allowed_types = array( + 1 => array('integer' => 360), + 2 => array('percentage' => 100), + 3 => array('percentage' => 100), + ); + $allow_different_types = true; + } + + $values = trim(str_replace($function, '', $color), ' ()'); + + $parts = explode(',', $values); + if (count($parts) !== $parameters_size) { + return false; + } + + $type = false; + $new_parts = array(); + $i = 0; + + foreach ($parts as $part) { + $i++; + $part = trim($part); + + if ($part === '') { + return false; + } + + // different check for alpha channel + if ($alpha_channel === true && $i === count($parts)) { + $result = $this->alpha->validate($part, $config, $context); + + if ($result === false) { + return false; + } + + $new_parts[] = (string)$result; + continue; + } + + if (substr($part, -1) === '%') { + $current_type = 'percentage'; + } else { + $current_type = 'integer'; + } + + if (!array_key_exists($current_type, $allowed_types[$i])) { + return false; + } + + if (!$type) { + $type = $current_type; + } + + if ($allow_different_types === false && $type != $current_type) { + return false; + } + + $max_value = $allowed_types[$i][$current_type]; + + if ($current_type == 'integer') { + // Return value between range 0 -> $max_value + $new_parts[] = (int)max(min($part, $max_value), 0); + } elseif ($current_type == 'percentage') { + $new_parts[] = (float)max(min(rtrim($part, '%'), $max_value), 0) . '%'; + } + } + + $new_values = implode(',', $new_parts); + + $color = $function . '(' . $new_values . ')'; + } else { + // hexadecimal handling + if ($color[0] === '#') { + $hex = substr($color, 1); + } else { + $hex = $color; + $color = '#' . $color; + } + $length = strlen($hex); + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } + } + return $color; + } + +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php new file mode 100644 index 0000000..9c17505 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php @@ -0,0 +1,48 @@ +defs = $defs; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + foreach ($this->defs as $i => $def) { + $result = $this->defs[$i]->validate($string, $config, $context); + if ($result !== false) { + return $result; + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php new file mode 100644 index 0000000..9d77cc9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php @@ -0,0 +1,44 @@ +def = $def; + $this->element = $element; + } + + /** + * Checks if CurrentToken is set and equal to $this->element + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $token = $context->get('CurrentToken', true); + if ($token && $token->name == $this->element) { + return false; + } + return $this->def->validate($string, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php new file mode 100644 index 0000000..bde4c33 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php @@ -0,0 +1,77 @@ +intValidator = new HTMLPurifier_AttrDef_Integer(); + } + + /** + * @param string $value + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($value, $config, $context) + { + $value = $this->parseCDATA($value); + if ($value === 'none') { + return $value; + } + // if we looped this we could support multiple filters + $function_length = strcspn($value, '('); + $function = trim(substr($value, 0, $function_length)); + if ($function !== 'alpha' && + $function !== 'Alpha' && + $function !== 'progid:DXImageTransform.Microsoft.Alpha' + ) { + return false; + } + $cursor = $function_length + 1; + $parameters_length = strcspn($value, ')', $cursor); + $parameters = substr($value, $cursor, $parameters_length); + $params = explode(',', $parameters); + $ret_params = array(); + $lookup = array(); + foreach ($params as $param) { + list($key, $value) = explode('=', $param); + $key = trim($key); + $value = trim($value); + if (isset($lookup[$key])) { + continue; + } + if ($key !== 'opacity') { + continue; + } + $value = $this->intValidator->validate($value, $config, $context); + if ($value === false) { + continue; + } + $int = (int)$value; + if ($int > 100) { + $value = '100'; + } + if ($int < 0) { + $value = '0'; + } + $ret_params[] = "$key=$value"; + $lookup[$key] = true; + } + $ret_parameters = implode(',', $ret_params); + $ret_function = "$function($ret_parameters)"; + return $ret_function; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php new file mode 100644 index 0000000..579b97e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php @@ -0,0 +1,176 @@ +getCSSDefinition(); + $this->info['font-style'] = $def->info['font-style']; + $this->info['font-variant'] = $def->info['font-variant']; + $this->info['font-weight'] = $def->info['font-weight']; + $this->info['font-size'] = $def->info['font-size']; + $this->info['line-height'] = $def->info['line-height']; + $this->info['font-family'] = $def->info['font-family']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + static $system_fonts = array( + 'caption' => true, + 'icon' => true, + 'menu' => true, + 'message-box' => true, + 'small-caption' => true, + 'status-bar' => true + ); + + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // check if it's one of the keywords + $lowercase_string = strtolower($string); + if (isset($system_fonts[$lowercase_string])) { + return $lowercase_string; + } + + $bits = explode(' ', $string); // bits to process + $stage = 0; // this indicates what we're looking for + $caught = array(); // which stage 0 properties have we caught? + $stage_1 = array('font-style', 'font-variant', 'font-weight'); + $final = ''; // output + + for ($i = 0, $size = count($bits); $i < $size; $i++) { + if ($bits[$i] === '') { + continue; + } + switch ($stage) { + case 0: // attempting to catch font-style, font-variant or font-weight + foreach ($stage_1 as $validator_name) { + if (isset($caught[$validator_name])) { + continue; + } + $r = $this->info[$validator_name]->validate( + $bits[$i], + $config, + $context + ); + if ($r !== false) { + $final .= $r . ' '; + $caught[$validator_name] = true; + break; + } + } + // all three caught, continue on + if (count($caught) >= 3) { + $stage = 1; + } + if ($r !== false) { + break; + } + case 1: // attempting to catch font-size and perhaps line-height + $found_slash = false; + if (strpos($bits[$i], '/') !== false) { + list($font_size, $line_height) = + explode('/', $bits[$i]); + if ($line_height === '') { + // ooh, there's a space after the slash! + $line_height = false; + $found_slash = true; + } + } else { + $font_size = $bits[$i]; + $line_height = false; + } + $r = $this->info['font-size']->validate( + $font_size, + $config, + $context + ); + if ($r !== false) { + $final .= $r; + // attempt to catch line-height + if ($line_height === false) { + // we need to scroll forward + for ($j = $i + 1; $j < $size; $j++) { + if ($bits[$j] === '') { + continue; + } + if ($bits[$j] === '/') { + if ($found_slash) { + return false; + } else { + $found_slash = true; + continue; + } + } + $line_height = $bits[$j]; + break; + } + } else { + // slash already found + $found_slash = true; + $j = $i; + } + if ($found_slash) { + $i = $j; + $r = $this->info['line-height']->validate( + $line_height, + $config, + $context + ); + if ($r !== false) { + $final .= '/' . $r; + } + } + $final .= ' '; + $stage = 2; + break; + } + return false; + case 2: // attempting to catch font-family + $font_family = + implode(' ', array_slice($bits, $i, $size - $i)); + $r = $this->info['font-family']->validate( + $font_family, + $config, + $context + ); + if ($r !== false) { + $final .= $r . ' '; + // processing completed successfully + return rtrim($final); + } + return false; + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php new file mode 100644 index 0000000..74e24c8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php @@ -0,0 +1,219 @@ +mask = '_- '; + for ($c = 'a'; $c <= 'z'; $c++) { + $this->mask .= $c; + } + for ($c = 'A'; $c <= 'Z'; $c++) { + $this->mask .= $c; + } + for ($c = '0'; $c <= '9'; $c++) { + $this->mask .= $c; + } // cast-y, but should be fine + // special bytes used by UTF-8 + for ($i = 0x80; $i <= 0xFF; $i++) { + // We don't bother excluding invalid bytes in this range, + // because the our restriction of well-formed UTF-8 will + // prevent these from ever occurring. + $this->mask .= chr($i); + } + + /* + PHP's internal strcspn implementation is + O(length of string * length of mask), making it inefficient + for large masks. However, it's still faster than + preg_match 8) + for (p = s1;;) { + spanp = s2; + do { + if (*spanp == c || p == s1_end) { + return p - s1; + } + } while (spanp++ < (s2_end - 1)); + c = *++p; + } + */ + // possible optimization: invert the mask. + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + static $generic_names = array( + 'serif' => true, + 'sans-serif' => true, + 'monospace' => true, + 'fantasy' => true, + 'cursive' => true + ); + $allowed_fonts = $config->get('CSS.AllowedFonts'); + + // assume that no font names contain commas in them + $fonts = explode(',', $string); + $final = ''; + foreach ($fonts as $font) { + $font = trim($font); + if ($font === '') { + continue; + } + // match a generic name + if (isset($generic_names[$font])) { + if ($allowed_fonts === null || isset($allowed_fonts[$font])) { + $final .= $font . ', '; + } + continue; + } + // match a quoted name + if ($font[0] === '"' || $font[0] === "'") { + $length = strlen($font); + if ($length <= 2) { + continue; + } + $quote = $font[0]; + if ($font[$length - 1] !== $quote) { + continue; + } + $font = substr($font, 1, $length - 2); + } + + $font = $this->expandCSSEscape($font); + + // $font is a pure representation of the font name + + if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) { + continue; + } + + if (ctype_alnum($font) && $font !== '') { + // very simple font, allow it in unharmed + $final .= $font . ', '; + continue; + } + + // bugger out on whitespace. form feed (0C) really + // shouldn't show up regardless + $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font); + + // Here, there are various classes of characters which need + // to be treated differently: + // - Alphanumeric characters are essentially safe. We + // handled these above. + // - Spaces require quoting, though most parsers will do + // the right thing if there aren't any characters that + // can be misinterpreted + // - Dashes rarely occur, but they fairly unproblematic + // for parsing/rendering purposes. + // The above characters cover the majority of Western font + // names. + // - Arbitrary Unicode characters not in ASCII. Because + // most parsers give little thought to Unicode, treatment + // of these codepoints is basically uniform, even for + // punctuation-like codepoints. These characters can + // show up in non-Western pages and are supported by most + // major browsers, for example: "๏ผญ๏ผณ ๆ˜Žๆœ" is a + // legitimate font-name + // . See + // the CSS3 spec for more examples: + // + // You can see live samples of these on the Internet: + // + // However, most of these fonts have ASCII equivalents: + // for example, 'MS Mincho', and it's considered + // professional to use ASCII font names instead of + // Unicode font names. Thanks Takeshi Terada for + // providing this information. + // The following characters, to my knowledge, have not been + // used to name font names. + // - Single quote. While theoretically you might find a + // font name that has a single quote in its name (serving + // as an apostrophe, e.g. Dave's Scribble), I haven't + // been able to find any actual examples of this. + // Internet Explorer's cssText translation (which I + // believe is invoked by innerHTML) normalizes any + // quoting to single quotes, and fails to escape single + // quotes. (Note that this is not IE's behavior for all + // CSS properties, just some sort of special casing for + // font-family). So a single quote *cannot* be used + // safely in the font-family context if there will be an + // innerHTML/cssText translation. Note that Firefox 3.x + // does this too. + // - Double quote. In IE, these get normalized to + // single-quotes, no matter what the encoding. (Fun + // fact, in IE8, the 'content' CSS property gained + // support, where they special cased to preserve encoded + // double quotes, but still translate unadorned double + // quotes into single quotes.) So, because their + // fixpoint behavior is identical to single quotes, they + // cannot be allowed either. Firefox 3.x displays + // single-quote style behavior. + // - Backslashes are reduced by one (so \\ -> \) every + // iteration, so they cannot be used safely. This shows + // up in IE7, IE8 and FF3 + // - Semicolons, commas and backticks are handled properly. + // - The rest of the ASCII punctuation is handled properly. + // We haven't checked what browsers do to unadorned + // versions, but this is not important as long as the + // browser doesn't /remove/ surrounding quotes (as IE does + // for HTML). + // + // With these results in hand, we conclude that there are + // various levels of safety: + // - Paranoid: alphanumeric, spaces and dashes(?) + // - International: Paranoid + non-ASCII Unicode + // - Edgy: Everything except quotes, backslashes + // - NoJS: Standards compliance, e.g. sod IE. Note that + // with some judicious character escaping (since certain + // types of escaping doesn't work) this is theoretically + // OK as long as innerHTML/cssText is not called. + // We believe that international is a reasonable default + // (that we will implement now), and once we do more + // extensive research, we may feel comfortable with dropping + // it down to edgy. + + // Edgy: alphanumeric, spaces, dashes, underscores and Unicode. Use of + // str(c)spn assumes that the string was already well formed + // Unicode (which of course it is). + if (strspn($font, $this->mask) !== strlen($font)) { + continue; + } + + // Historical: + // In the absence of innerHTML/cssText, these ugly + // transforms don't pose a security risk (as \\ and \" + // might--these escapes are not supported by most browsers). + // We could try to be clever and use single-quote wrapping + // when there is a double quote present, but I have choosen + // not to implement that. (NOTE: you can reduce the amount + // of escapes by one depending on what quoting style you use) + // $font = str_replace('\\', '\\5C ', $font); + // $font = str_replace('"', '\\22 ', $font); + // $font = str_replace("'", '\\27 ', $font); + + // font possibly with spaces, requires quoting + $final .= "'$font', "; + } + $final = rtrim($final, ', '); + if ($final === '') { + return false; + } + return $final; + } + +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php new file mode 100644 index 0000000..973002c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php @@ -0,0 +1,32 @@ +def = $def; + $this->allow = $allow; + } + + /** + * Intercepts and removes !important if necessary + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // test for ! and important tokens + $string = trim($string); + $is_important = false; + // :TODO: optimization: test directly for !important and ! important + if (strlen($string) >= 9 && substr($string, -9) === 'important') { + $temp = rtrim(substr($string, 0, -9)); + // use a temp, because we might want to restore important + if (strlen($temp) >= 1 && substr($temp, -1) === '!') { + $string = rtrim(substr($temp, 0, -1)); + $is_important = true; + } + } + $string = $this->def->validate($string, $config, $context); + if ($this->allow && $is_important) { + $string .= ' !important'; + } + return $string; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php new file mode 100644 index 0000000..f12453a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php @@ -0,0 +1,77 @@ +min = $min !== null ? HTMLPurifier_Length::make($min) : null; + $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + + // Optimizations + if ($string === '') { + return false; + } + if ($string === '0') { + return '0'; + } + if (strlen($string) === 1) { + return false; + } + + $length = HTMLPurifier_Length::make($string); + if (!$length->isValid()) { + return false; + } + + if ($this->min) { + $c = $length->compareTo($this->min); + if ($c === false) { + return false; + } + if ($c < 0) { + return false; + } + } + if ($this->max) { + $c = $length->compareTo($this->max); + if ($c === false) { + return false; + } + if ($c > 0) { + return false; + } + } + return $length->toString(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php new file mode 100644 index 0000000..e74d426 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php @@ -0,0 +1,112 @@ +getCSSDefinition(); + $this->info['list-style-type'] = $def->info['list-style-type']; + $this->info['list-style-position'] = $def->info['list-style-position']; + $this->info['list-style-image'] = $def->info['list-style-image']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // assumes URI doesn't have spaces in it + $bits = explode(' ', strtolower($string)); // bits to process + + $caught = array(); + $caught['type'] = false; + $caught['position'] = false; + $caught['image'] = false; + + $i = 0; // number of catches + $none = false; + + foreach ($bits as $bit) { + if ($i >= 3) { + return; + } // optimization bit + if ($bit === '') { + continue; + } + foreach ($caught as $key => $status) { + if ($status !== false) { + continue; + } + $r = $this->info['list-style-' . $key]->validate($bit, $config, $context); + if ($r === false) { + continue; + } + if ($r === 'none') { + if ($none) { + continue; + } else { + $none = true; + } + if ($key == 'image') { + continue; + } + } + $caught[$key] = $r; + $i++; + break; + } + } + + if (!$i) { + return false; + } + + $ret = array(); + + // construct type + if ($caught['type']) { + $ret[] = $caught['type']; + } + + // construct image + if ($caught['image']) { + $ret[] = $caught['image']; + } + + // construct position + if ($caught['position']) { + $ret[] = $caught['position']; + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php new file mode 100644 index 0000000..e707f87 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php @@ -0,0 +1,71 @@ +single = $single; + $this->max = $max; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->mungeRgb($this->parseCDATA($string)); + if ($string === '') { + return false; + } + $parts = explode(' ', $string); // parseCDATA replaced \r, \t and \n + $length = count($parts); + $final = ''; + for ($i = 0, $num = 0; $i < $length && $num < $this->max; $i++) { + if (ctype_space($parts[$i])) { + continue; + } + $result = $this->single->validate($parts[$i], $config, $context); + if ($result !== false) { + $final .= $result . ' '; + $num++; + } + } + if ($final === '') { + return false; + } + return rtrim($final); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php new file mode 100644 index 0000000..ef49d20 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php @@ -0,0 +1,90 @@ +non_negative = $non_negative; + } + + /** + * @param string $number + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string|bool + * @warning Some contexts do not pass $config, $context. These + * variables should not be used without checking HTMLPurifier_Length + */ + public function validate($number, $config, $context) + { + $number = $this->parseCDATA($number); + + if ($number === '') { + return false; + } + if ($number === '0') { + return '0'; + } + + $sign = ''; + switch ($number[0]) { + case '-': + if ($this->non_negative) { + return false; + } + $sign = '-'; + case '+': + $number = substr($number, 1); + } + + if (ctype_digit($number)) { + $number = ltrim($number, '0'); + return $number ? $sign . $number : '0'; + } + + // Period is the only non-numeric character allowed + if (strpos($number, '.') === false) { + return false; + } + + list($left, $right) = explode('.', $number, 2); + + if ($left === '' && $right === '') { + return false; + } + if ($left !== '' && !ctype_digit($left)) { + return false; + } + + // Remove leading zeros until positive number or a zero stays left + if (ltrim($left, '0') != '') { + $left = ltrim($left, '0'); + } else { + $left = '0'; + } + + $right = rtrim($right, '0'); + + if ($right === '') { + return $left ? $sign . $left : '0'; + } elseif (!ctype_digit($right)) { + return false; + } + return $sign . $left . '.' . $right; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php new file mode 100644 index 0000000..f0f25c5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php @@ -0,0 +1,54 @@ +number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + + if ($string === '') { + return false; + } + $length = strlen($string); + if ($length === 1) { + return false; + } + if ($string[$length - 1] !== '%') { + return false; + } + + $number = substr($string, 0, $length - 1); + $number = $this->number_def->validate($number, $config, $context); + + if ($number === false) { + return false; + } + return "$number%"; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php new file mode 100644 index 0000000..5fd4b7f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php @@ -0,0 +1,46 @@ + true, + 'overline' => true, + 'underline' => true, + ); + + $string = strtolower($this->parseCDATA($string)); + + if ($string === 'none') { + return $string; + } + + $parts = explode(' ', $string); + $final = ''; + foreach ($parts as $part) { + if (isset($allowed_values[$part])) { + $final .= $part . ' '; + } + } + $final = rtrim($final); + if ($final === '') { + return false; + } + return $final; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php new file mode 100644 index 0000000..6617aca --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php @@ -0,0 +1,77 @@ +parseCDATA($uri_string); + if (strpos($uri_string, 'url(') !== 0) { + return false; + } + $uri_string = substr($uri_string, 4); + if (strlen($uri_string) == 0) { + return false; + } + $new_length = strlen($uri_string) - 1; + if ($uri_string[$new_length] != ')') { + return false; + } + $uri = trim(substr($uri_string, 0, $new_length)); + + if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) { + $quote = $uri[0]; + $new_length = strlen($uri) - 1; + if ($uri[$new_length] !== $quote) { + return false; + } + $uri = substr($uri, 1, $new_length - 1); + } + + $uri = $this->expandCSSEscape($uri); + + $result = parent::validate($uri, $config, $context); + + if ($result === false) { + return false; + } + + // extra sanity check; should have been done by URI + $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result); + + // suspicious characters are ()'; we're going to percent encode + // them for safety. + $result = str_replace(array('(', ')', "'"), array('%28', '%29', '%27'), $result); + + // there's an extra bug where ampersands lose their escaping on + // an innerHTML cycle, so a very unlucky query parameter could + // then change the meaning of the URL. Unfortunately, there's + // not much we can do about that... + return "url(\"$result\")"; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php new file mode 100644 index 0000000..6698a00 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php @@ -0,0 +1,44 @@ +clone = $clone; + } + + /** + * @param string $v + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($v, $config, $context) + { + return $this->clone->validate($v, $config, $context); + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + return clone $this->clone; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php new file mode 100644 index 0000000..8abda7f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php @@ -0,0 +1,73 @@ +valid_values = array_flip($valid_values); + $this->case_sensitive = $case_sensitive; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = trim($string); + if (!$this->case_sensitive) { + // we may want to do full case-insensitive libraries + $string = ctype_lower($string) ? $string : strtolower($string); + } + $result = isset($this->valid_values[$string]); + + return $result ? $string : false; + } + + /** + * @param string $string In form of comma-delimited list of case-insensitive + * valid values. Example: "foo,bar,baz". Prepend "s:" to make + * case sensitive + * @return HTMLPurifier_AttrDef_Enum + */ + public function make($string) + { + if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') { + $string = substr($string, 2); + $sensitive = true; + } else { + $sensitive = false; + } + $values = explode(',', $string); + return new HTMLPurifier_AttrDef_Enum($values, $sensitive); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php new file mode 100644 index 0000000..be3bbc8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php @@ -0,0 +1,48 @@ +name = $name; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + return $this->name; + } + + /** + * @param string $string Name of attribute + * @return HTMLPurifier_AttrDef_HTML_Bool + */ + public function make($string) + { + return new HTMLPurifier_AttrDef_HTML_Bool($string); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php new file mode 100644 index 0000000..d501348 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php @@ -0,0 +1,48 @@ +getDefinition('HTML')->doctype->name; + if ($name == "XHTML 1.1" || $name == "XHTML 2.0") { + return parent::split($string, $config, $context); + } else { + return preg_split('/\s+/', $string); + } + } + + /** + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function filter($tokens, $config, $context) + { + $allowed = $config->get('Attr.AllowedClasses'); + $forbidden = $config->get('Attr.ForbiddenClasses'); + $ret = array(); + foreach ($tokens as $token) { + if (($allowed === null || isset($allowed[$token])) && + !isset($forbidden[$token]) && + // We need this O(n) check because of PHP's array + // implementation that casts -0 to 0. + !in_array($token, $ret, true) + ) { + $ret[] = $token; + } + } + return $ret; + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php new file mode 100644 index 0000000..946ebb7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php @@ -0,0 +1,51 @@ +get('Core.ColorKeywords'); + } + + $string = trim($string); + + if (empty($string)) { + return false; + } + $lower = strtolower($string); + if (isset($colors[$lower])) { + return $colors[$lower]; + } + if ($string[0] === '#') { + $hex = substr($string, 1); + } else { + $hex = $string; + } + + $length = strlen($hex); + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } + if ($length === 3) { + $hex = $hex[0] . $hex[0] . $hex[1] . $hex[1] . $hex[2] . $hex[2]; + } + return "#$hex"; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ContentEditable.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ContentEditable.php new file mode 100644 index 0000000..5b03d3e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ContentEditable.php @@ -0,0 +1,16 @@ +get('HTML.Trusted')) { + $allowed = array('', 'true', 'false'); + } + + $enum = new HTMLPurifier_AttrDef_Enum($allowed); + + return $enum->validate($string, $config, $context); + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php new file mode 100644 index 0000000..d79ba12 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php @@ -0,0 +1,38 @@ +valid_values === false) { + $this->valid_values = $config->get('Attr.AllowedFrameTargets'); + } + return parent::validate($string, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php new file mode 100644 index 0000000..4ba4561 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php @@ -0,0 +1,113 @@ +selector = $selector; + } + + /** + * @param string $id + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($id, $config, $context) + { + if (!$this->selector && !$config->get('Attr.EnableID')) { + return false; + } + + $id = trim($id); // trim it first + + if ($id === '') { + return false; + } + + $prefix = $config->get('Attr.IDPrefix'); + if ($prefix !== '') { + $prefix .= $config->get('Attr.IDPrefixLocal'); + // prevent re-appending the prefix + if (strpos($id, $prefix) !== 0) { + $id = $prefix . $id; + } + } elseif ($config->get('Attr.IDPrefixLocal') !== '') { + trigger_error( + '%Attr.IDPrefixLocal cannot be used unless ' . + '%Attr.IDPrefix is set', + E_USER_WARNING + ); + } + + if (!$this->selector) { + $id_accumulator =& $context->get('IDAccumulator'); + if (isset($id_accumulator->ids[$id])) { + return false; + } + } + + // we purposely avoid using regex, hopefully this is faster + + if ($config->get('Attr.ID.HTML5') === true) { + if (preg_match('/[\t\n\x0b\x0c ]/', $id)) { + return false; + } + } else { + if (ctype_alpha($id)) { + // OK + } else { + if (!ctype_alpha(@$id[0])) { + return false; + } + // primitive style of regexps, I suppose + $trim = trim( + $id, + 'A..Za..z0..9:-._' + ); + if ($trim !== '') { + return false; + } + } + } + + $regexp = $config->get('Attr.IDBlacklistRegexp'); + if ($regexp && preg_match($regexp, $id)) { + return false; + } + + if (!$this->selector) { + $id_accumulator->add($id); + } + + // if no change was made to the ID, return the result + // else, return the new id if stripping whitespace made it + // valid, or return false. + return $id; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php new file mode 100644 index 0000000..1c4006f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php @@ -0,0 +1,56 @@ + 100) { + return '100%'; + } + return ((string)$points) . '%'; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php new file mode 100644 index 0000000..63fa04c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php @@ -0,0 +1,72 @@ + 'AllowedRel', + 'rev' => 'AllowedRev' + ); + if (!isset($configLookup[$name])) { + trigger_error( + 'Unrecognized attribute name for link ' . + 'relationship.', + E_USER_ERROR + ); + return; + } + $this->name = $configLookup[$name]; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $allowed = $config->get('Attr.' . $this->name); + if (empty($allowed)) { + return false; + } + + $string = $this->parseCDATA($string); + $parts = explode(' ', $string); + + // lookup to prevent duplicates + $ret_lookup = array(); + foreach ($parts as $part) { + $part = strtolower(trim($part)); + if (!isset($allowed[$part])) { + continue; + } + $ret_lookup[$part] = true; + } + + if (empty($ret_lookup)) { + return false; + } + $string = implode(' ', array_keys($ret_lookup)); + return $string; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php new file mode 100644 index 0000000..bbb20f2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php @@ -0,0 +1,60 @@ +split($string, $config, $context); + $tokens = $this->filter($tokens, $config, $context); + if (empty($tokens)) { + return false; + } + return implode(' ', $tokens); + } + + /** + * Splits a space separated list of tokens into its constituent parts. + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function split($string, $config, $context) + { + // OPTIMIZABLE! + // do the preg_match, capture all subpatterns for reformulation + + // we don't support U+00A1 and up codepoints or + // escaping because I don't know how to do that with regexps + // and plus it would complicate optimization efforts (you never + // see that anyway). + $pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start + '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' . + '(?:(?=\s)|\z)/'; // look ahead for space or string end + preg_match_all($pattern, $string, $matches); + return $matches[1]; + } + + /** + * Template method for removing certain tokens based on arbitrary criteria. + * @note If we wanted to be really functional, we'd do an array_filter + * with a callback. But... we're not. + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function filter($tokens, $config, $context) + { + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php new file mode 100644 index 0000000..a1d019e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php @@ -0,0 +1,76 @@ +max = $max; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = trim($string); + if ($string === '0') { + return $string; + } + if ($string === '') { + return false; + } + $length = strlen($string); + if (substr($string, $length - 2) == 'px') { + $string = substr($string, 0, $length - 2); + } + if (!is_numeric($string)) { + return false; + } + $int = (int)$string; + + if ($int < 0) { + return '0'; + } + + // upper-bound value, extremely high values can + // crash operating systems, see + // WARNING, above link WILL crash you if you're using Windows + + if ($this->max !== null && $int > $this->max) { + return (string)$this->max; + } + return (string)$int; + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + if ($string === '') { + $max = null; + } else { + $max = (int)$string; + } + $class = get_class($this); + return new $class($max); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php new file mode 100644 index 0000000..400e707 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php @@ -0,0 +1,91 @@ +negative = $negative; + $this->zero = $zero; + $this->positive = $positive; + } + + /** + * @param string $integer + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($integer, $config, $context) + { + $integer = $this->parseCDATA($integer); + if ($integer === '') { + return false; + } + + // we could possibly simply typecast it to integer, but there are + // certain fringe cases that must not return an integer. + + // clip leading sign + if ($this->negative && $integer[0] === '-') { + $digits = substr($integer, 1); + if ($digits === '0') { + $integer = '0'; + } // rm minus sign for zero + } elseif ($this->positive && $integer[0] === '+') { + $digits = $integer = substr($integer, 1); // rm unnecessary plus + } else { + $digits = $integer; + } + + // test if it's numeric + if (!ctype_digit($digits)) { + return false; + } + + // perform scope tests + if (!$this->zero && $integer == 0) { + return false; + } + if (!$this->positive && $integer > 0) { + return false; + } + if (!$this->negative && $integer < 0) { + return false; + } + + return $integer; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php new file mode 100644 index 0000000..2a55cea --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php @@ -0,0 +1,86 @@ + 8 || !ctype_alnum($subtags[1])) { + return $new_string; + } + if (!ctype_lower($subtags[1])) { + $subtags[1] = strtolower($subtags[1]); + } + + $new_string .= '-' . $subtags[1]; + if ($num_subtags == 2) { + return $new_string; + } + + // process all other subtags, index 2 and up + for ($i = 2; $i < $num_subtags; $i++) { + $length = strlen($subtags[$i]); + if ($length == 0 || $length > 8 || !ctype_alnum($subtags[$i])) { + return $new_string; + } + if (!ctype_lower($subtags[$i])) { + $subtags[$i] = strtolower($subtags[$i]); + } + $new_string .= '-' . $subtags[$i]; + } + return $new_string; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php new file mode 100644 index 0000000..c7eb319 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php @@ -0,0 +1,53 @@ +tag = $tag; + $this->withTag = $with_tag; + $this->withoutTag = $without_tag; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $token = $context->get('CurrentToken', true); + if (!$token || $token->name !== $this->tag) { + return $this->withoutTag->validate($string, $config, $context); + } else { + return $this->withTag->validate($string, $config, $context); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/Text.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/Text.php new file mode 100644 index 0000000..4553a4e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/Text.php @@ -0,0 +1,21 @@ +parseCDATA($string); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/URI.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI.php new file mode 100644 index 0000000..c1cd897 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI.php @@ -0,0 +1,111 @@ +parser = new HTMLPurifier_URIParser(); + $this->embedsResource = (bool)$embeds_resource; + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef_URI + */ + public function make($string) + { + $embeds = ($string === 'embedded'); + return new HTMLPurifier_AttrDef_URI($embeds); + } + + /** + * @param string $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($uri, $config, $context) + { + if ($config->get('URI.Disable')) { + return false; + } + + $uri = $this->parseCDATA($uri); + + // parse the URI + $uri = $this->parser->parse($uri); + if ($uri === false) { + return false; + } + + // add embedded flag to context for validators + $context->register('EmbeddedURI', $this->embedsResource); + + $ok = false; + do { + + // generic validation + $result = $uri->validate($config, $context); + if (!$result) { + break; + } + + // chained filtering + $uri_def = $config->getDefinition('URI'); + $result = $uri_def->filter($uri, $config, $context); + if (!$result) { + break; + } + + // scheme-specific validation + $scheme_obj = $uri->getSchemeObj($config, $context); + if (!$scheme_obj) { + break; + } + if ($this->embedsResource && !$scheme_obj->browsable) { + break; + } + $result = $scheme_obj->validate($uri, $config, $context); + if (!$result) { + break; + } + + // Post chained filtering + $result = $uri_def->postFilter($uri, $config, $context); + if (!$result) { + break; + } + + // survived gauntlet + $ok = true; + + } while (false); + + $context->destroy('EmbeddedURI'); + if (!$ok) { + return false; + } + // back to string + return $uri->toString(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php new file mode 100644 index 0000000..daf32b7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php @@ -0,0 +1,20 @@ +" + // that needs more percent encoding to be done + if ($string == '') { + return false; + } + $string = trim($string); + $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); + return $result ? $string : false; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php new file mode 100644 index 0000000..1beeaa5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php @@ -0,0 +1,142 @@ +ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); + $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $length = strlen($string); + // empty hostname is OK; it's usually semantically equivalent: + // the default host as defined by a URI scheme is used: + // + // If the URI scheme defines a default for host, then that + // default applies when the host subcomponent is undefined + // or when the registered name is empty (zero length). + if ($string === '') { + return ''; + } + if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') { + //IPv6 + $ip = substr($string, 1, $length - 2); + $valid = $this->ipv6->validate($ip, $config, $context); + if ($valid === false) { + return false; + } + return '[' . $valid . ']'; + } + + // need to do checks on unusual encodings too + $ipv4 = $this->ipv4->validate($string, $config, $context); + if ($ipv4 !== false) { + return $ipv4; + } + + // A regular domain name. + + // This doesn't match I18N domain names, but we don't have proper IRI support, + // so force users to insert Punycode. + + // There is not a good sense in which underscores should be + // allowed, since it's technically not! (And if you go as + // far to allow everything as specified by the DNS spec... + // well, that's literally everything, modulo some space limits + // for the components and the overall name (which, by the way, + // we are NOT checking!). So we (arbitrarily) decide this: + // let's allow underscores wherever we would have allowed + // hyphens, if they are enabled. This is a pretty good match + // for browser behavior, for example, a large number of browsers + // cannot handle foo_.example.com, but foo_bar.example.com is + // fairly well supported. + $underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : ''; + + // Based off of RFC 1738, but amended so that + // as per RFC 3696, the top label need only not be all numeric. + // The productions describing this are: + $a = '[a-z]'; // alpha + $an = '[a-z0-9]'; // alphanum + $and = "[a-z0-9-$underscore]"; // alphanum | "-" + // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum + $domainlabel = "$an(?:$and*$an)?"; + // AMENDED as per RFC 3696 + // toplabel = alphanum | alphanum *( alphanum | "-" ) alphanum + // side condition: not all numeric + $toplabel = "$an(?:$and*$an)?"; + // hostname = *( domainlabel "." ) toplabel [ "." ] + if (preg_match("/^(?:$domainlabel\.)*($toplabel)\.?$/i", $string, $matches)) { + if (!ctype_digit($matches[1])) { + return $string; + } + } + + // PHP 5.3 and later support this functionality natively + if (function_exists('idn_to_ascii')) { + if (defined('IDNA_NONTRANSITIONAL_TO_ASCII') && defined('INTL_IDNA_VARIANT_UTS46')) { + $string = idn_to_ascii($string, IDNA_NONTRANSITIONAL_TO_ASCII, INTL_IDNA_VARIANT_UTS46); + } else { + $string = idn_to_ascii($string); + } + + // If we have Net_IDNA2 support, we can support IRIs by + // punycoding them. (This is the most portable thing to do, + // since otherwise we have to assume browsers support + } elseif ($config->get('Core.EnableIDNA')) { + $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); + // we need to encode each period separately + $parts = explode('.', $string); + try { + $new_parts = array(); + foreach ($parts as $part) { + $encodable = false; + for ($i = 0, $c = strlen($part); $i < $c; $i++) { + if (ord($part[$i]) > 0x7a) { + $encodable = true; + break; + } + } + if (!$encodable) { + $new_parts[] = $part; + } else { + $new_parts[] = $idna->encode($part); + } + } + $string = implode('.', $new_parts); + } catch (Exception $e) { + // XXX error reporting + } + } + // Try again + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php new file mode 100644 index 0000000..30ac16c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php @@ -0,0 +1,45 @@ +ip4) { + $this->_loadRegex(); + } + + if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) { + return $aIP; + } + return false; + } + + /** + * Lazy load function to prevent regex from being stuffed in + * cache. + */ + protected function _loadRegex() + { + $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 + $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php new file mode 100644 index 0000000..f243793 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php @@ -0,0 +1,89 @@ +ip4) { + $this->_loadRegex(); + } + + $original = $aIP; + + $hex = '[0-9a-fA-F]'; + $blk = '(?:' . $hex . '{1,4})'; + $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 + + // prefix check + if (strpos($aIP, '/') !== false) { + if (preg_match('#' . $pre . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + unset($find); + } else { + return false; + } + } + + // IPv4-compatiblity check + if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + $ip = explode('.', $find[0]); + $ip = array_map('dechex', $ip); + $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; + unset($find, $ip); + } + + // compression check + $aIP = explode('::', $aIP); + $c = count($aIP); + if ($c > 2) { + return false; + } elseif ($c == 2) { + list($first, $second) = $aIP; + $first = explode(':', $first); + $second = explode(':', $second); + + if (count($first) + count($second) > 8) { + return false; + } + + while (count($first) < 8) { + array_push($first, '0'); + } + + array_splice($first, 8 - count($second), 8, $second); + $aIP = $first; + unset($first, $second); + } else { + $aIP = explode(':', $aIP[0]); + } + $c = count($aIP); + + if ($c != 8) { + return false; + } + + // All the pieces should be 16-bit hex strings. Are they? + foreach ($aIP as $piece) { + if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) { + return false; + } + } + return $original; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform.php new file mode 100644 index 0000000..b428331 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform.php @@ -0,0 +1,60 @@ +confiscateAttr($attr, 'background'); + // some validation should happen here + + $this->prependCSS($attr, "background-image:url($background);"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php new file mode 100644 index 0000000..d66c04a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php @@ -0,0 +1,27 @@ +get('Attr.DefaultTextDir'); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php new file mode 100644 index 0000000..0f51fd2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php @@ -0,0 +1,28 @@ +confiscateAttr($attr, 'bgcolor'); + // some validation should happen here + + $this->prependCSS($attr, "background-color:$bgcolor;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php new file mode 100644 index 0000000..f25cd01 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php @@ -0,0 +1,47 @@ +attr = $attr; + $this->css = $css; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + unset($attr[$this->attr]); + $this->prependCSS($attr, $this->css); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php new file mode 100644 index 0000000..057dc01 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php @@ -0,0 +1,26 @@ +confiscateAttr($attr, 'border'); + // some validation should happen here + $this->prependCSS($attr, "border:{$border_width}px solid;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php new file mode 100644 index 0000000..7ccd0e3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php @@ -0,0 +1,68 @@ +attr = $attr; + $this->enumToCSS = $enum_to_css; + $this->caseSensitive = (bool)$case_sensitive; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + + $value = trim($attr[$this->attr]); + unset($attr[$this->attr]); + + if (!$this->caseSensitive) { + $value = strtolower($value); + } + + if (!isset($this->enumToCSS[$value])) { + return $attr; + } + $this->prependCSS($attr, $this->enumToCSS[$value]); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php new file mode 100644 index 0000000..235ebb3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php @@ -0,0 +1,47 @@ +get('Core.RemoveInvalidImg')) { + return $attr; + } + $attr['src'] = $config->get('Attr.DefaultInvalidImage'); + $src = false; + } + + if (!isset($attr['alt'])) { + if ($src) { + $alt = $config->get('Attr.DefaultImageAlt'); + if ($alt === null) { + $attr['alt'] = basename($attr['src']); + } else { + $attr['alt'] = $alt; + } + } else { + $attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt'); + } + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php new file mode 100644 index 0000000..350b335 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php @@ -0,0 +1,61 @@ + array('left', 'right'), + 'vspace' => array('top', 'bottom') + ); + + /** + * @param string $attr + */ + public function __construct($attr) + { + $this->attr = $attr; + if (!isset($this->css[$attr])) { + trigger_error(htmlspecialchars($attr) . ' is not valid space attribute'); + } + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + + $width = $this->confiscateAttr($attr, $this->attr); + // some validation could happen here + + if (!isset($this->css[$this->attr])) { + return $attr; + } + + $style = ''; + foreach ($this->css[$this->attr] as $suffix) { + $property = "margin-$suffix"; + $style .= "$property:{$width}px;"; + } + $this->prependCSS($attr, $style); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php new file mode 100644 index 0000000..3ab47ed --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php @@ -0,0 +1,56 @@ +pixels = new HTMLPurifier_AttrDef_HTML_Pixels(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $t = 'text'; + } else { + $t = strtolower($attr['type']); + } + if (isset($attr['checked']) && $t !== 'radio' && $t !== 'checkbox') { + unset($attr['checked']); + } + if (isset($attr['maxlength']) && $t !== 'text' && $t !== 'password') { + unset($attr['maxlength']); + } + if (isset($attr['size']) && $t !== 'text' && $t !== 'password') { + $result = $this->pixels->validate($attr['size'], $config, $context); + if ($result === false) { + unset($attr['size']); + } else { + $attr['size'] = $result; + } + } + if (isset($attr['src']) && $t !== 'image') { + unset($attr['src']); + } + if (!isset($attr['value']) && ($t === 'radio' || $t === 'checkbox')) { + $attr['value'] = ''; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php new file mode 100644 index 0000000..5b0aff0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php @@ -0,0 +1,31 @@ +name = $name; + $this->cssName = $css_name ? $css_name : $name; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->name])) { + return $attr; + } + $length = $this->confiscateAttr($attr, $this->name); + if (ctype_digit($length)) { + $length .= 'px'; + } + $this->prependCSS($attr, $this->cssName . ":$length;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php new file mode 100644 index 0000000..63cce68 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php @@ -0,0 +1,33 @@ +get('HTML.Attr.Name.UseCDATA')) { + return $attr; + } + if (!isset($attr['name'])) { + return $attr; + } + $id = $this->confiscateAttr($attr, 'name'); + if (isset($attr['id'])) { + return $attr; + } + $attr['id'] = $id; + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php new file mode 100644 index 0000000..5a1fdbb --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php @@ -0,0 +1,46 @@ +idDef = new HTMLPurifier_AttrDef_HTML_ID(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['name'])) { + return $attr; + } + $name = $attr['name']; + if (isset($attr['id']) && $attr['id'] === $name) { + return $attr; + } + $result = $this->idDef->validate($name, $config, $context); + if ($result === false) { + unset($attr['name']); + } else { + $attr['name'] = $result; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php new file mode 100644 index 0000000..1057ebe --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php @@ -0,0 +1,52 @@ +parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isLocal($config, $context)) { + if (isset($attr['rel'])) { + $rels = explode(' ', $attr['rel']); + if (!in_array('nofollow', $rels)) { + $rels[] = 'nofollow'; + } + $attr['rel'] = implode(' ', $rels); + } else { + $attr['rel'] = 'nofollow'; + } + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php new file mode 100644 index 0000000..231c81a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php @@ -0,0 +1,25 @@ +uri = new HTMLPurifier_AttrDef_URI(true); // embedded + $this->wmode = new HTMLPurifier_AttrDef_Enum(array('window', 'opaque', 'transparent')); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + // If we add support for other objects, we'll need to alter the + // transforms. + switch ($attr['name']) { + // application/x-shockwave-flash + // Keep this synchronized with Injector/SafeObject.php + case 'allowScriptAccess': + $attr['value'] = 'never'; + break; + case 'allowNetworking': + $attr['value'] = 'internal'; + break; + case 'allowFullScreen': + if ($config->get('HTML.FlashAllowFullScreen')) { + $attr['value'] = ($attr['value'] == 'true') ? 'true' : 'false'; + } else { + $attr['value'] = 'false'; + } + break; + case 'wmode': + $attr['value'] = $this->wmode->validate($attr['value'], $config, $context); + break; + case 'movie': + case 'src': + $attr['name'] = "movie"; + $attr['value'] = $this->uri->validate($attr['value'], $config, $context); + break; + case 'flashvars': + // we're going to allow arbitrary inputs to the SWF, on + // the reasoning that it could only hack the SWF, not us. + break; + // add other cases to support other param name/value pairs + default: + $attr['name'] = $attr['value'] = null; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php new file mode 100644 index 0000000..b7057bb --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php @@ -0,0 +1,23 @@ + + */ +class HTMLPurifier_AttrTransform_ScriptRequired extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $attr['type'] = 'text/javascript'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php new file mode 100644 index 0000000..dd63ea8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php @@ -0,0 +1,45 @@ +parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isBenign($config, $context)) { + $attr['target'] = '_blank'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetNoopener.php b/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetNoopener.php new file mode 100644 index 0000000..1db3c6c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTransform/TargetNoopener.php @@ -0,0 +1,37 @@ + + */ +class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + // Calculated from Firefox + if (!isset($attr['cols'])) { + $attr['cols'] = '22'; + } + if (!isset($attr['rows'])) { + $attr['rows'] = '3'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrTypes.php b/software/HTMLPurifier/HTMLPurifier/AttrTypes.php new file mode 100644 index 0000000..e4429e8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrTypes.php @@ -0,0 +1,97 @@ +info['Enum'] = new HTMLPurifier_AttrDef_Enum(); + $this->info['Bool'] = new HTMLPurifier_AttrDef_HTML_Bool(); + + $this->info['CDATA'] = new HTMLPurifier_AttrDef_Text(); + $this->info['ID'] = new HTMLPurifier_AttrDef_HTML_ID(); + $this->info['Length'] = new HTMLPurifier_AttrDef_HTML_Length(); + $this->info['MultiLength'] = new HTMLPurifier_AttrDef_HTML_MultiLength(); + $this->info['NMTOKENS'] = new HTMLPurifier_AttrDef_HTML_Nmtokens(); + $this->info['Pixels'] = new HTMLPurifier_AttrDef_HTML_Pixels(); + $this->info['Text'] = new HTMLPurifier_AttrDef_Text(); + $this->info['URI'] = new HTMLPurifier_AttrDef_URI(); + $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang(); + $this->info['Color'] = new HTMLPurifier_AttrDef_HTML_Color(); + $this->info['IAlign'] = self::makeEnum('top,middle,bottom,left,right'); + $this->info['LAlign'] = self::makeEnum('top,bottom,left,right'); + $this->info['FrameTarget'] = new HTMLPurifier_AttrDef_HTML_FrameTarget(); + $this->info['ContentEditable'] = new HTMLPurifier_AttrDef_HTML_ContentEditable(); + + // unimplemented aliases + $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text(); + $this->info['ContentTypes'] = new HTMLPurifier_AttrDef_Text(); + $this->info['Charsets'] = new HTMLPurifier_AttrDef_Text(); + $this->info['Character'] = new HTMLPurifier_AttrDef_Text(); + + // "proprietary" types + $this->info['Class'] = new HTMLPurifier_AttrDef_HTML_Class(); + + // number is really a positive integer (one or more digits) + // FIXME: ^^ not always, see start and value of list items + $this->info['Number'] = new HTMLPurifier_AttrDef_Integer(false, false, true); + } + + private static function makeEnum($in) + { + return new HTMLPurifier_AttrDef_Clone(new HTMLPurifier_AttrDef_Enum(explode(',', $in))); + } + + /** + * Retrieves a type + * @param string $type String type name + * @return HTMLPurifier_AttrDef Object AttrDef for type + */ + public function get($type) + { + // determine if there is any extra info tacked on + if (strpos($type, '#') !== false) { + list($type, $string) = explode('#', $type, 2); + } else { + $string = ''; + } + + if (!isset($this->info[$type])) { + trigger_error('Cannot retrieve undefined attribute type ' . $type, E_USER_ERROR); + return; + } + return $this->info[$type]->make($string); + } + + /** + * Sets a new implementation for a type + * @param string $type String type name + * @param HTMLPurifier_AttrDef $impl Object AttrDef for type + */ + public function set($type, $impl) + { + $this->info[$type] = $impl; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/AttrValidator.php b/software/HTMLPurifier/HTMLPurifier/AttrValidator.php new file mode 100644 index 0000000..f97dc93 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/AttrValidator.php @@ -0,0 +1,178 @@ +getHTMLDefinition(); + $e =& $context->get('ErrorCollector', true); + + // initialize IDAccumulator if necessary + $ok =& $context->get('IDAccumulator', true); + if (!$ok) { + $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context); + $context->register('IDAccumulator', $id_accumulator); + } + + // initialize CurrentToken if necessary + $current_token =& $context->get('CurrentToken', true); + if (!$current_token) { + $context->register('CurrentToken', $token); + } + + if (!$token instanceof HTMLPurifier_Token_Start && + !$token instanceof HTMLPurifier_Token_Empty + ) { + return; + } + + // create alias to global definition array, see also $defs + // DEFINITION CALL + $d_defs = $definition->info_global_attr; + + // don't update token until the very end, to ensure an atomic update + $attr = $token->attr; + + // do global transformations (pre) + // nothing currently utilizes this + foreach ($definition->info_attr_transform_pre as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // do local transformations only applicable to this element (pre) + // ex.

to

+ foreach ($definition->info[$token->name]->attr_transform_pre as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // create alias to this element's attribute definition array, see + // also $d_defs (global attribute definition array) + // DEFINITION CALL + $defs = $definition->info[$token->name]->attr; + + $attr_key = false; + $context->register('CurrentAttr', $attr_key); + + // iterate through all the attribute keypairs + // Watch out for name collisions: $key has previously been used + foreach ($attr as $attr_key => $value) { + + // call the definition + if (isset($defs[$attr_key])) { + // there is a local definition defined + if ($defs[$attr_key] === false) { + // We've explicitly been told not to allow this element. + // This is usually when there's a global definition + // that must be overridden. + // Theoretically speaking, we could have a + // AttrDef_DenyAll, but this is faster! + $result = false; + } else { + // validate according to the element's definition + $result = $defs[$attr_key]->validate( + $value, + $config, + $context + ); + } + } elseif (isset($d_defs[$attr_key])) { + // there is a global definition defined, validate according + // to the global definition + $result = $d_defs[$attr_key]->validate( + $value, + $config, + $context + ); + } else { + // system never heard of the attribute? DELETE! + $result = false; + } + + // put the results into effect + if ($result === false || $result === null) { + // this is a generic error message that should replaced + // with more specific ones when possible + if ($e) { + $e->send(E_ERROR, 'AttrValidator: Attribute removed'); + } + + // remove the attribute + unset($attr[$attr_key]); + } elseif (is_string($result)) { + // generally, if a substitution is happening, there + // was some sort of implicit correction going on. We'll + // delegate it to the attribute classes to say exactly what. + + // simple substitution + $attr[$attr_key] = $result; + } else { + // nothing happens + } + + // we'd also want slightly more complicated substitution + // involving an array as the return value, + // although we're not sure how colliding attributes would + // resolve (certain ones would be completely overriden, + // others would prepend themselves). + } + + $context->destroy('CurrentAttr'); + + // post transforms + + // global (error reporting untested) + foreach ($definition->info_attr_transform_post as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // local (error reporting untested) + foreach ($definition->info[$token->name]->attr_transform_post as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + $token->attr = $attr; + + // destroy CurrentToken if we made it ourselves + if (!$current_token) { + $context->destroy('CurrentToken'); + } + + } + + +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Bootstrap.php b/software/HTMLPurifier/HTMLPurifier/Bootstrap.php new file mode 100644 index 0000000..707122b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Bootstrap.php @@ -0,0 +1,124 @@ + +if (!defined('PHP_EOL')) { + switch (strtoupper(substr(PHP_OS, 0, 3))) { + case 'WIN': + define('PHP_EOL', "\r\n"); + break; + case 'DAR': + define('PHP_EOL', "\r"); + break; + default: + define('PHP_EOL', "\n"); + } +} + +/** + * Bootstrap class that contains meta-functionality for HTML Purifier such as + * the autoload function. + * + * @note + * This class may be used without any other files from HTML Purifier. + */ +class HTMLPurifier_Bootstrap +{ + + /** + * Autoload function for HTML Purifier + * @param string $class Class to load + * @return bool + */ + public static function autoload($class) + { + $file = HTMLPurifier_Bootstrap::getPath($class); + if (!$file) { + return false; + } + // Technically speaking, it should be ok and more efficient to + // just do 'require', but Antonio Parraga reports that with + // Zend extensions such as Zend debugger and APC, this invariant + // may be broken. Since we have efficient alternatives, pay + // the cost here and avoid the bug. + require_once HTMLPURIFIER_PREFIX . '/' . $file; + return true; + } + + /** + * Returns the path for a specific class. + * @param string $class Class path to get + * @return string + */ + public static function getPath($class) + { + if (strncmp('HTMLPurifier', $class, 12) !== 0) { + return false; + } + // Custom implementations + if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) { + $code = str_replace('_', '-', substr($class, 22)); + $file = 'HTMLPurifier/Language/classes/' . $code . '.php'; + } else { + $file = str_replace('_', '/', $class) . '.php'; + } + if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) { + return false; + } + return $file; + } + + /** + * "Pre-registers" our autoloader on the SPL stack. + */ + public static function registerAutoload() + { + $autoload = array('HTMLPurifier_Bootstrap', 'autoload'); + if (($funcs = spl_autoload_functions()) === false) { + spl_autoload_register($autoload); + } elseif (function_exists('spl_autoload_unregister')) { + if (version_compare(PHP_VERSION, '5.3.0', '>=')) { + // prepend flag exists, no need for shenanigans + spl_autoload_register($autoload, true, true); + } else { + $buggy = version_compare(PHP_VERSION, '5.2.11', '<'); + $compat = version_compare(PHP_VERSION, '5.1.2', '<=') && + version_compare(PHP_VERSION, '5.1.0', '>='); + foreach ($funcs as $func) { + if ($buggy && is_array($func)) { + // :TRICKY: There are some compatibility issues and some + // places where we need to error out + $reflector = new ReflectionMethod($func[0], $func[1]); + if (!$reflector->isStatic()) { + throw new Exception( + 'HTML Purifier autoloader registrar is not compatible + with non-static object methods due to PHP Bug #44144; + Please do not use HTMLPurifier.autoload.php (or any + file that includes this file); instead, place the code: + spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\')) + after your own autoloaders.' + ); + } + // Suprisingly, spl_autoload_register supports the + // Class::staticMethod callback format, although call_user_func doesn't + if ($compat) { + $func = implode('::', $func); + } + } + spl_autoload_unregister($func); + } + spl_autoload_register($autoload); + foreach ($funcs as $func) { + spl_autoload_register($func); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/CSSDefinition.php b/software/HTMLPurifier/HTMLPurifier/CSSDefinition.php new file mode 100644 index 0000000..3f08b81 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/CSSDefinition.php @@ -0,0 +1,549 @@ +info['text-align'] = new HTMLPurifier_AttrDef_Enum( + array('left', 'right', 'center', 'justify'), + false + ); + + $border_style = + $this->info['border-bottom-style'] = + $this->info['border-right-style'] = + $this->info['border-left-style'] = + $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum( + array( + 'none', + 'hidden', + 'dotted', + 'dashed', + 'solid', + 'double', + 'groove', + 'ridge', + 'inset', + 'outset' + ), + false + ); + + $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style); + + $this->info['clear'] = new HTMLPurifier_AttrDef_Enum( + array('none', 'left', 'right', 'both'), + false + ); + $this->info['float'] = new HTMLPurifier_AttrDef_Enum( + array('none', 'left', 'right'), + false + ); + $this->info['font-style'] = new HTMLPurifier_AttrDef_Enum( + array('normal', 'italic', 'oblique'), + false + ); + $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum( + array('normal', 'small-caps'), + false + ); + + $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('none')), + new HTMLPurifier_AttrDef_CSS_URI() + ) + ); + + $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum( + array('inside', 'outside'), + false + ); + $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum( + array( + 'disc', + 'circle', + 'square', + 'decimal', + 'lower-roman', + 'upper-roman', + 'lower-alpha', + 'upper-alpha', + 'none' + ), + false + ); + $this->info['list-style-image'] = $uri_or_none; + + $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config); + + $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum( + array('capitalize', 'uppercase', 'lowercase', 'none'), + false + ); + $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color(); + + $this->info['background-image'] = $uri_or_none; + $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum( + array('repeat', 'repeat-x', 'repeat-y', 'no-repeat') + ); + $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum( + array('scroll', 'fixed') + ); + $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition(); + + $this->info['background-size'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'auto', + 'cover', + 'contain', + 'initial', + 'inherit', + ) + ), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $border_color = + $this->info['border-top-color'] = + $this->info['border-bottom-color'] = + $this->info['border-left-color'] = + $this->info['border-right-color'] = + $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('transparent')), + new HTMLPurifier_AttrDef_CSS_Color() + ) + ); + + $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config); + + $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color); + + $border_width = + $this->info['border-top-width'] = + $this->info['border-bottom-width'] = + $this->info['border-left-width'] = + $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')), + new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative + ) + ); + + $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width); + + $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'xx-small', + 'x-small', + 'small', + 'medium', + 'large', + 'x-large', + 'xx-large', + 'larger', + 'smaller' + ) + ), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); + + $margin = + $this->info['margin-top'] = + $this->info['margin-bottom'] = + $this->info['margin-left'] = + $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ); + + $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin); + + // non-negative + $padding = + $this->info['padding-top'] = + $this->info['padding-bottom'] = + $this->info['padding-left'] = + $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); + + $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding); + + $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); + + $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true), + new HTMLPurifier_AttrDef_Enum(array('auto', 'initial', 'inherit')) + ) + ); + $trusted_min_wh = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true), + new HTMLPurifier_AttrDef_Enum(array('initial', 'inherit')) + ) + ); + $trusted_max_wh = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true), + new HTMLPurifier_AttrDef_Enum(array('none', 'initial', 'inherit')) + ) + ); + $max = $config->get('CSS.MaxImgLength'); + + $this->info['width'] = + $this->info['height'] = + $max === null ? + $trusted_wh : + new HTMLPurifier_AttrDef_Switch( + 'img', + // For img tags: + new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0', $max), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ), + // For everyone else: + $trusted_wh + ); + $this->info['min-width'] = + $this->info['min-height'] = + $max === null ? + $trusted_min_wh : + new HTMLPurifier_AttrDef_Switch( + 'img', + // For img tags: + new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0', $max), + new HTMLPurifier_AttrDef_Enum(array('initial', 'inherit')) + ) + ), + // For everyone else: + $trusted_min_wh + ); + $this->info['max-width'] = + $this->info['max-height'] = + $max === null ? + $trusted_max_wh : + new HTMLPurifier_AttrDef_Switch( + 'img', + // For img tags: + new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0', $max), + new HTMLPurifier_AttrDef_Enum(array('none', 'initial', 'inherit')) + ) + ), + // For everyone else: + $trusted_max_wh + ); + + $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration(); + + $this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily(); + + // this could use specialized code + $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum( + array( + 'normal', + 'bold', + 'bolder', + 'lighter', + '100', + '200', + '300', + '400', + '500', + '600', + '700', + '800', + '900' + ), + false + ); + + // MUST be called after other font properties, as it references + // a CSSDefinition object + $this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config); + + // same here + $this->info['border'] = + $this->info['border-bottom'] = + $this->info['border-top'] = + $this->info['border-left'] = + $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config); + + $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum( + array('collapse', 'separate') + ); + + $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum( + array('top', 'bottom') + ); + + $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum( + array('auto', 'fixed') + ); + + $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'baseline', + 'sub', + 'super', + 'top', + 'text-top', + 'middle', + 'bottom', + 'text-bottom' + ) + ), + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); + + $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2); + + // These CSS properties don't work on many browsers, but we live + // in THE FUTURE! + $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum( + array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line') + ); + + if ($config->get('CSS.Proprietary')) { + $this->doSetupProprietary($config); + } + + if ($config->get('CSS.AllowTricky')) { + $this->doSetupTricky($config); + } + + if ($config->get('CSS.Trusted')) { + $this->doSetupTrusted($config); + } + + $allow_important = $config->get('CSS.AllowImportant'); + // wrap all attr-defs with decorator that handles !important + foreach ($this->info as $k => $v) { + $this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important); + } + + $this->setupConfigStuff($config); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupProprietary($config) + { + // Internet Explorer only scrollbar colors + $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + + // vendor specific prefixes of opacity + $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + + // only opacity, for now + $this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter(); + + // more CSS3 + $this->info['page-break-after'] = + $this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum( + array( + 'auto', + 'always', + 'avoid', + 'left', + 'right' + ) + ); + $this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto', 'avoid')); + + $border_radius = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Percentage(true), // disallow negative + new HTMLPurifier_AttrDef_CSS_Length('0') // disallow negative + )); + + $this->info['border-top-left-radius'] = + $this->info['border-top-right-radius'] = + $this->info['border-bottom-right-radius'] = + $this->info['border-bottom-left-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 2); + // TODO: support SLASH syntax + $this->info['border-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 4); + + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTricky($config) + { + $this->info['display'] = new HTMLPurifier_AttrDef_Enum( + array( + 'inline', + 'block', + 'list-item', + 'run-in', + 'compact', + 'marker', + 'table', + 'inline-block', + 'inline-table', + 'table-row-group', + 'table-header-group', + 'table-footer-group', + 'table-row', + 'table-column-group', + 'table-column', + 'table-cell', + 'table-caption', + 'none' + ) + ); + $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum( + array('visible', 'hidden', 'collapse') + ); + $this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll')); + $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTrusted($config) + { + $this->info['position'] = new HTMLPurifier_AttrDef_Enum( + array('static', 'relative', 'absolute', 'fixed') + ); + $this->info['top'] = + $this->info['left'] = + $this->info['right'] = + $this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + $this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Integer(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + } + + /** + * Performs extra config-based processing. Based off of + * HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_Config $config + * @todo Refactor duplicate elements into common class (probably using + * composition, not inheritance). + */ + protected function setupConfigStuff($config) + { + // setup allowed elements + $support = "(for information on implementing this, see the " . + "support forums) "; + $allowed_properties = $config->get('CSS.AllowedProperties'); + if ($allowed_properties !== null) { + foreach ($this->info as $name => $d) { + if (!isset($allowed_properties[$name])) { + unset($this->info[$name]); + } + unset($allowed_properties[$name]); + } + // emit errors + foreach ($allowed_properties as $name => $d) { + // :TODO: Is this htmlspecialchars() call really necessary? + $name = htmlspecialchars($name); + trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING); + } + } + + $forbidden_properties = $config->get('CSS.ForbiddenProperties'); + if ($forbidden_properties !== null) { + foreach ($this->info as $name => $d) { + if (isset($forbidden_properties[$name])) { + unset($this->info[$name]); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef.php b/software/HTMLPurifier/HTMLPurifier/ChildDef.php new file mode 100644 index 0000000..8eb17b8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef.php @@ -0,0 +1,52 @@ +elements; + } + + /** + * Validates nodes according to definition and returns modification. + * + * @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node + * @param HTMLPurifier_Config $config HTMLPurifier_Config object + * @param HTMLPurifier_Context $context HTMLPurifier_Context object + * @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children + */ + abstract public function validateChildren($children, $config, $context); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php new file mode 100644 index 0000000..7439be2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php @@ -0,0 +1,67 @@ +inline = new HTMLPurifier_ChildDef_Optional($inline); + $this->block = new HTMLPurifier_ChildDef_Optional($block); + $this->elements = $this->block->elements; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + if ($context->get('IsInline') === false) { + return $this->block->validateChildren( + $children, + $config, + $context + ); + } else { + return $this->inline->validateChildren( + $children, + $config, + $context + ); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php new file mode 100644 index 0000000..f515888 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php @@ -0,0 +1,102 @@ +dtd_regex = $dtd_regex; + $this->_compileRegex(); + } + + /** + * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex) + */ + protected function _compileRegex() + { + $raw = str_replace(' ', '', $this->dtd_regex); + if ($raw[0] != '(') { + $raw = "($raw)"; + } + $el = '[#a-zA-Z0-9_.-]+'; + $reg = $raw; + + // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M + // DOING! Seriously: if there's problems, please report them. + + // collect all elements into the $elements array + preg_match_all("/$el/", $reg, $matches); + foreach ($matches[0] as $match) { + $this->elements[$match] = true; + } + + // setup all elements as parentheticals with leading commas + $reg = preg_replace("/$el/", '(,\\0)', $reg); + + // remove commas when they were not solicited + $reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg); + + // remove all non-paranthetical commas: they are handled by first regex + $reg = preg_replace("/,\(/", '(', $reg); + + $this->_pcre_regex = $reg; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + $list_of_children = ''; + $nesting = 0; // depth into the nest + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + continue; + } + $list_of_children .= $node->name . ','; + } + // add leading comma to deal with stray comma declarations + $list_of_children = ',' . rtrim($list_of_children, ','); + $okay = + preg_match( + '/^,?' . $this->_pcre_regex . '$/', + $list_of_children + ); + return (bool)$okay; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php new file mode 100644 index 0000000..a8a6cbd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php @@ -0,0 +1,38 @@ + true, 'ul' => true, 'ol' => true); + + public $whitespace; + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // if li is not allowed, delete parent node + if (!isset($config->getHTMLDefinition()->info['li'])) { + trigger_error("Cannot allow ul/ol without allowing li", E_USER_WARNING); + return false; + } + + // the new set of children + $result = array(); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $current_li = null; + + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if ($node->name === 'li') { + // good + $current_li = $node; + $result[] = $node; + } else { + // we want to tuck this into the previous li + // Invariant: we expect the node to be ol/ul + // ToDo: Make this more robust in the case of not ol/ul + // by distinguishing between existing li and li created + // to handle non-list elements; non-list elements should + // not be appended to an existing li; only li created + // for non-list. This distinction is not currently made. + if ($current_li === null) { + $current_li = new HTMLPurifier_Node_Element('li'); + $result[] = $current_li; + } + $current_li->children[] = $node; + $current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo + } + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php new file mode 100644 index 0000000..b946806 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php @@ -0,0 +1,45 @@ +whitespace) { + return $children; + } else { + return array(); + } + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Required.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Required.php new file mode 100644 index 0000000..0d1c8f5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Required.php @@ -0,0 +1,118 @@ + $x) { + $elements[$i] = true; + if (empty($i)) { + unset($elements[$i]); + } // remove blank + } + } + $this->elements = $elements; + } + + /** + * @type bool + */ + public $allow_empty = false; + + /** + * @type string + */ + public $type = 'required'; + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // the new set of children + $result = array(); + + // whether or not parsed character data is allowed + // this controls whether or not we silently drop a tag + // or generate escaped HTML from it + $pcdata_allowed = isset($this->elements['#PCDATA']); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $stack = array_reverse($children); + while (!empty($stack)) { + $node = array_pop($stack); + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if (!isset($this->elements[$node->name])) { + // special case text + // XXX One of these ought to be redundant or something + if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) { + $result[] = $node; + continue; + } + // spill the child contents in + // ToDo: Make configurable + if ($node instanceof HTMLPurifier_Node_Element) { + for ($i = count($node->children) - 1; $i >= 0; $i--) { + $stack[] = $node->children[$i]; + } + continue; + } + continue; + } + $result[] = $node; + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + $this->whitespace = true; + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php new file mode 100644 index 0000000..3270a46 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php @@ -0,0 +1,110 @@ +init($config); + return $this->fake_elements; + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + $this->init($config); + + // trick the parent class into thinking it allows more + $this->elements = $this->fake_elements; + $result = parent::validateChildren($children, $config, $context); + $this->elements = $this->real_elements; + + if ($result === false) { + return array(); + } + if ($result === true) { + $result = $children; + } + + $def = $config->getHTMLDefinition(); + $block_wrap_name = $def->info_block_wrapper; + $block_wrap = false; + $ret = array(); + + foreach ($result as $node) { + if ($block_wrap === false) { + if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) || + ($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) { + $block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper); + $ret[] = $block_wrap; + } + } else { + if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) { + $block_wrap = false; + + } + } + if ($block_wrap) { + $block_wrap->children[] = $node; + } else { + $ret[] = $node; + } + } + return $ret; + } + + /** + * @param HTMLPurifier_Config $config + */ + private function init($config) + { + if (!$this->init) { + $def = $config->getHTMLDefinition(); + // allow all inline elements + $this->real_elements = $this->elements; + $this->fake_elements = $def->info_content_sets['Flow']; + $this->fake_elements['#PCDATA'] = true; + $this->init = true; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ChildDef/Table.php b/software/HTMLPurifier/HTMLPurifier/ChildDef/Table.php new file mode 100644 index 0000000..67c7e95 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ChildDef/Table.php @@ -0,0 +1,224 @@ + true, + 'tbody' => true, + 'thead' => true, + 'tfoot' => true, + 'caption' => true, + 'colgroup' => true, + 'col' => true + ); + + public function __construct() + { + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + if (empty($children)) { + return false; + } + + // only one of these elements is allowed in a table + $caption = false; + $thead = false; + $tfoot = false; + + // whitespace + $initial_ws = array(); + $after_caption_ws = array(); + $after_thead_ws = array(); + $after_tfoot_ws = array(); + + // as many of these as you want + $cols = array(); + $content = array(); + + $tbody_mode = false; // if true, then we need to wrap any stray + // s with a . + + $ws_accum =& $initial_ws; + + foreach ($children as $node) { + if ($node instanceof HTMLPurifier_Node_Comment) { + $ws_accum[] = $node; + continue; + } + switch ($node->name) { + case 'tbody': + $tbody_mode = true; + // fall through + case 'tr': + $content[] = $node; + $ws_accum =& $content; + break; + case 'caption': + // there can only be one caption! + if ($caption !== false) break; + $caption = $node; + $ws_accum =& $after_caption_ws; + break; + case 'thead': + $tbody_mode = true; + // XXX This breaks rendering properties with + // Firefox, which never floats a to + // the top. Ever. (Our scheme will float the + // first to the top.) So maybe + // s that are not first should be + // turned into ? Very tricky, indeed. + if ($thead === false) { + $thead = $node; + $ws_accum =& $after_thead_ws; + } else { + // Oops, there's a second one! What + // should we do? Current behavior is to + // transmutate the first and last entries into + // tbody tags, and then put into content. + // Maybe a better idea is to *attach + // it* to the existing thead or tfoot? + // We don't do this, because Firefox + // doesn't float an extra tfoot to the + // bottom like it does for the first one. + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; + } + break; + case 'tfoot': + // see above for some aveats + $tbody_mode = true; + if ($tfoot === false) { + $tfoot = $node; + $ws_accum =& $after_tfoot_ws; + } else { + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; + } + break; + case 'colgroup': + case 'col': + $cols[] = $node; + $ws_accum =& $cols; + break; + case '#PCDATA': + // How is whitespace handled? We treat is as sticky to + // the *end* of the previous element. So all of the + // nonsense we have worked on is to keep things + // together. + if (!empty($node->is_whitespace)) { + $ws_accum[] = $node; + } + break; + } + } + + if (empty($content) && $thead === false && $tfoot === false) { + return false; + } + + $ret = $initial_ws; + if ($caption !== false) { + $ret[] = $caption; + $ret = array_merge($ret, $after_caption_ws); + } + if ($cols !== false) { + $ret = array_merge($ret, $cols); + } + if ($thead !== false) { + $ret[] = $thead; + $ret = array_merge($ret, $after_thead_ws); + } + if ($tfoot !== false) { + $ret[] = $tfoot; + $ret = array_merge($ret, $after_tfoot_ws); + } + + if ($tbody_mode) { + // we have to shuffle tr into tbody + $current_tr_tbody = null; + + foreach($content as $node) { + switch ($node->name) { + case 'tbody': + $current_tr_tbody = null; + $ret[] = $node; + break; + case 'tr': + if ($current_tr_tbody === null) { + $current_tr_tbody = new HTMLPurifier_Node_Element('tbody'); + $ret[] = $current_tr_tbody; + } + $current_tr_tbody->children[] = $node; + break; + case '#PCDATA': + //assert($node->is_whitespace); + if ($current_tr_tbody === null) { + $ret[] = $node; + } else { + $current_tr_tbody->children[] = $node; + } + break; + } + } + } else { + $ret = array_merge($ret, $content); + } + + return $ret; + + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Config.php b/software/HTMLPurifier/HTMLPurifier/Config.php new file mode 100644 index 0000000..797d268 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Config.php @@ -0,0 +1,920 @@ +defaultPlist; + $this->plist = new HTMLPurifier_PropertyList($parent); + $this->def = $definition; // keep a copy around for checking + $this->parser = new HTMLPurifier_VarParser_Flexible(); + } + + /** + * Convenience constructor that creates a config object based on a mixed var + * @param mixed $config Variable that defines the state of the config + * object. Can be: a HTMLPurifier_Config() object, + * an array of directives based on loadArray(), + * or a string filename of an ini file. + * @param HTMLPurifier_ConfigSchema $schema Schema object + * @return HTMLPurifier_Config Configured object + */ + public static function create($config, $schema = null) + { + if ($config instanceof HTMLPurifier_Config) { + // pass-through + return $config; + } + if (!$schema) { + $ret = HTMLPurifier_Config::createDefault(); + } else { + $ret = new HTMLPurifier_Config($schema); + } + if (is_string($config)) { + $ret->loadIni($config); + } elseif (is_array($config)) $ret->loadArray($config); + return $ret; + } + + /** + * Creates a new config object that inherits from a previous one. + * @param HTMLPurifier_Config $config Configuration object to inherit from. + * @return HTMLPurifier_Config object with $config as its parent. + */ + public static function inherit(HTMLPurifier_Config $config) + { + return new HTMLPurifier_Config($config->def, $config->plist); + } + + /** + * Convenience constructor that creates a default configuration object. + * @return HTMLPurifier_Config default object. + */ + public static function createDefault() + { + $definition = HTMLPurifier_ConfigSchema::instance(); + $config = new HTMLPurifier_Config($definition); + return $config; + } + + /** + * Retrieves a value from the configuration. + * + * @param string $key String key + * @param mixed $a + * + * @return mixed + */ + public function get($key, $a = null) + { + if ($a !== null) { + $this->triggerError( + "Using deprecated API: use \$config->get('$key.$a') instead", + E_USER_WARNING + ); + $key = "$key.$a"; + } + if (!$this->finalized) { + $this->autoFinalize(); + } + if (!isset($this->def->info[$key])) { + // can't add % due to SimpleTest bug + $this->triggerError( + 'Cannot retrieve value of undefined directive ' . htmlspecialchars($key), + E_USER_WARNING + ); + return; + } + if (isset($this->def->info[$key]->isAlias)) { + $d = $this->def->info[$key]; + $this->triggerError( + 'Cannot get value from aliased directive, use real name ' . $d->key, + E_USER_ERROR + ); + return; + } + if ($this->lock) { + list($ns) = explode('.', $key); + if ($ns !== $this->lock) { + $this->triggerError( + 'Cannot get value of namespace ' . $ns . ' when lock for ' . + $this->lock . + ' is active, this probably indicates a Definition setup method ' . + 'is accessing directives that are not within its namespace', + E_USER_ERROR + ); + return; + } + } + return $this->plist->get($key); + } + + /** + * Retrieves an array of directives to values from a given namespace + * + * @param string $namespace String namespace + * + * @return array + */ + public function getBatch($namespace) + { + if (!$this->finalized) { + $this->autoFinalize(); + } + $full = $this->getAll(); + if (!isset($full[$namespace])) { + $this->triggerError( + 'Cannot retrieve undefined namespace ' . + htmlspecialchars($namespace), + E_USER_WARNING + ); + return; + } + return $full[$namespace]; + } + + /** + * Returns a SHA-1 signature of a segment of the configuration object + * that uniquely identifies that particular configuration + * + * @param string $namespace Namespace to get serial for + * + * @return string + * @note Revision is handled specially and is removed from the batch + * before processing! + */ + public function getBatchSerial($namespace) + { + if (empty($this->serials[$namespace])) { + $batch = $this->getBatch($namespace); + unset($batch['DefinitionRev']); + $this->serials[$namespace] = sha1(serialize($batch)); + } + return $this->serials[$namespace]; + } + + /** + * Returns a SHA-1 signature for the entire configuration object + * that uniquely identifies that particular configuration + * + * @return string + */ + public function getSerial() + { + if (empty($this->serial)) { + $this->serial = sha1(serialize($this->getAll())); + } + return $this->serial; + } + + /** + * Retrieves all directives, organized by namespace + * + * @warning This is a pretty inefficient function, avoid if you can + */ + public function getAll() + { + if (!$this->finalized) { + $this->autoFinalize(); + } + $ret = array(); + foreach ($this->plist->squash() as $name => $value) { + list($ns, $key) = explode('.', $name, 2); + $ret[$ns][$key] = $value; + } + return $ret; + } + + /** + * Sets a value to configuration. + * + * @param string $key key + * @param mixed $value value + * @param mixed $a + */ + public function set($key, $value, $a = null) + { + if (strpos($key, '.') === false) { + $namespace = $key; + $directive = $value; + $value = $a; + $key = "$key.$directive"; + $this->triggerError("Using deprecated API: use \$config->set('$key', ...) instead", E_USER_NOTICE); + } else { + list($namespace) = explode('.', $key); + } + if ($this->isFinalized('Cannot set directive after finalization')) { + return; + } + if (!isset($this->def->info[$key])) { + $this->triggerError( + 'Cannot set undefined directive ' . htmlspecialchars($key) . ' to value', + E_USER_WARNING + ); + return; + } + $def = $this->def->info[$key]; + + if (isset($def->isAlias)) { + if ($this->aliasMode) { + $this->triggerError( + 'Double-aliases not allowed, please fix '. + 'ConfigSchema bug with' . $key, + E_USER_ERROR + ); + return; + } + $this->aliasMode = true; + $this->set($def->key, $value); + $this->aliasMode = false; + $this->triggerError("$key is an alias, preferred directive name is {$def->key}", E_USER_NOTICE); + return; + } + + // Raw type might be negative when using the fully optimized form + // of stdClass, which indicates allow_null == true + $rtype = is_int($def) ? $def : $def->type; + if ($rtype < 0) { + $type = -$rtype; + $allow_null = true; + } else { + $type = $rtype; + $allow_null = isset($def->allow_null); + } + + try { + $value = $this->parser->parse($value, $type, $allow_null); + } catch (HTMLPurifier_VarParserException $e) { + $this->triggerError( + 'Value for ' . $key . ' is of invalid type, should be ' . + HTMLPurifier_VarParser::getTypeName($type), + E_USER_WARNING + ); + return; + } + if (is_string($value) && is_object($def)) { + // resolve value alias if defined + if (isset($def->aliases[$value])) { + $value = $def->aliases[$value]; + } + // check to see if the value is allowed + if (isset($def->allowed) && !isset($def->allowed[$value])) { + $this->triggerError( + 'Value not supported, valid values are: ' . + $this->_listify($def->allowed), + E_USER_WARNING + ); + return; + } + } + $this->plist->set($key, $value); + + // reset definitions if the directives they depend on changed + // this is a very costly process, so it's discouraged + // with finalization + if ($namespace == 'HTML' || $namespace == 'CSS' || $namespace == 'URI') { + $this->definitions[$namespace] = null; + } + + $this->serials[$namespace] = false; + } + + /** + * Convenience function for error reporting + * + * @param array $lookup + * + * @return string + */ + private function _listify($lookup) + { + $list = array(); + foreach ($lookup as $name => $b) { + $list[] = $name; + } + return implode(', ', $list); + } + + /** + * Retrieves object reference to the HTML definition. + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawHTMLDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_HTMLDefinition|null + */ + public function getHTMLDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('HTML', $raw, $optimized); + } + + /** + * Retrieves object reference to the CSS definition + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawCSSDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_CSSDefinition|null + */ + public function getCSSDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('CSS', $raw, $optimized); + } + + /** + * Retrieves object reference to the URI definition + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawURIDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_URIDefinition|null + */ + public function getURIDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('URI', $raw, $optimized); + } + + /** + * Retrieves a definition + * + * @param string $type Type of definition: HTML, CSS, etc + * @param bool $raw Whether or not definition should be returned raw + * @param bool $optimized Only has an effect when $raw is true. Whether + * or not to return null if the result is already present in + * the cache. This is off by default for backwards + * compatibility reasons, but you need to do things this + * way in order to ensure that caching is done properly. + * Check out enduser-customize.html for more details. + * We probably won't ever change this default, as much as the + * maybe semantics is the "right thing to do." + * + * @throws HTMLPurifier_Exception + * @return HTMLPurifier_Definition|null + */ + public function getDefinition($type, $raw = false, $optimized = false) + { + if ($optimized && !$raw) { + throw new HTMLPurifier_Exception("Cannot set optimized = true when raw = false"); + } + if (!$this->finalized) { + $this->autoFinalize(); + } + // temporarily suspend locks, so we can handle recursive definition calls + $lock = $this->lock; + $this->lock = null; + $factory = HTMLPurifier_DefinitionCacheFactory::instance(); + $cache = $factory->create($type, $this); + $this->lock = $lock; + if (!$raw) { + // full definition + // --------------- + // check if definition is in memory + if (!empty($this->definitions[$type])) { + $def = $this->definitions[$type]; + // check if the definition is setup + if ($def->setup) { + return $def; + } else { + $def->setup($this); + if ($def->optimized) { + $cache->add($def, $this); + } + return $def; + } + } + // check if definition is in cache + $def = $cache->get($this); + if ($def) { + // definition in cache, save to memory and return it + $this->definitions[$type] = $def; + return $def; + } + // initialize it + $def = $this->initDefinition($type); + // set it up + $this->lock = $type; + $def->setup($this); + $this->lock = null; + // save in cache + $cache->add($def, $this); + // return it + return $def; + } else { + // raw definition + // -------------- + // check preconditions + $def = null; + if ($optimized) { + if (is_null($this->get($type . '.DefinitionID'))) { + // fatally error out if definition ID not set + throw new HTMLPurifier_Exception( + "Cannot retrieve raw version without specifying %$type.DefinitionID" + ); + } + } + if (!empty($this->definitions[$type])) { + $def = $this->definitions[$type]; + if ($def->setup && !$optimized) { + $extra = $this->chatty ? + " (try moving this code block earlier in your initialization)" : + ""; + throw new HTMLPurifier_Exception( + "Cannot retrieve raw definition after it has already been setup" . + $extra + ); + } + if ($def->optimized === null) { + $extra = $this->chatty ? " (try flushing your cache)" : ""; + throw new HTMLPurifier_Exception( + "Optimization status of definition is unknown" . $extra + ); + } + if ($def->optimized !== $optimized) { + $msg = $optimized ? "optimized" : "unoptimized"; + $extra = $this->chatty ? + " (this backtrace is for the first inconsistent call, which was for a $msg raw definition)" + : ""; + throw new HTMLPurifier_Exception( + "Inconsistent use of optimized and unoptimized raw definition retrievals" . $extra + ); + } + } + // check if definition was in memory + if ($def) { + if ($def->setup) { + // invariant: $optimized === true (checked above) + return null; + } else { + return $def; + } + } + // if optimized, check if definition was in cache + // (because we do the memory check first, this formulation + // is prone to cache slamming, but I think + // guaranteeing that either /all/ of the raw + // setup code or /none/ of it is run is more important.) + if ($optimized) { + // This code path only gets run once; once we put + // something in $definitions (which is guaranteed by the + // trailing code), we always short-circuit above. + $def = $cache->get($this); + if ($def) { + // save the full definition for later, but don't + // return it yet + $this->definitions[$type] = $def; + return null; + } + } + // check invariants for creation + if (!$optimized) { + if (!is_null($this->get($type . '.DefinitionID'))) { + if ($this->chatty) { + $this->triggerError( + 'Due to a documentation error in previous version of HTML Purifier, your ' . + 'definitions are not being cached. If this is OK, you can remove the ' . + '%$type.DefinitionRev and %$type.DefinitionID declaration. Otherwise, ' . + 'modify your code to use maybeGetRawDefinition, and test if the returned ' . + 'value is null before making any edits (if it is null, that means that a ' . + 'cached version is available, and no raw operations are necessary). See ' . + '' . + 'Customize for more details', + E_USER_WARNING + ); + } else { + $this->triggerError( + "Useless DefinitionID declaration", + E_USER_WARNING + ); + } + } + } + // initialize it + $def = $this->initDefinition($type); + $def->optimized = $optimized; + return $def; + } + throw new HTMLPurifier_Exception("The impossible happened!"); + } + + /** + * Initialise definition + * + * @param string $type What type of definition to create + * + * @return HTMLPurifier_CSSDefinition|HTMLPurifier_HTMLDefinition|HTMLPurifier_URIDefinition + * @throws HTMLPurifier_Exception + */ + private function initDefinition($type) + { + // quick checks failed, let's create the object + if ($type == 'HTML') { + $def = new HTMLPurifier_HTMLDefinition(); + } elseif ($type == 'CSS') { + $def = new HTMLPurifier_CSSDefinition(); + } elseif ($type == 'URI') { + $def = new HTMLPurifier_URIDefinition(); + } else { + throw new HTMLPurifier_Exception( + "Definition of $type type not supported" + ); + } + $this->definitions[$type] = $def; + return $def; + } + + public function maybeGetRawDefinition($name) + { + return $this->getDefinition($name, true, true); + } + + /** + * @return HTMLPurifier_HTMLDefinition|null + */ + public function maybeGetRawHTMLDefinition() + { + return $this->getDefinition('HTML', true, true); + } + + /** + * @return HTMLPurifier_CSSDefinition|null + */ + public function maybeGetRawCSSDefinition() + { + return $this->getDefinition('CSS', true, true); + } + + /** + * @return HTMLPurifier_URIDefinition|null + */ + public function maybeGetRawURIDefinition() + { + return $this->getDefinition('URI', true, true); + } + + /** + * Loads configuration values from an array with the following structure: + * Namespace.Directive => Value + * + * @param array $config_array Configuration associative array + */ + public function loadArray($config_array) + { + if ($this->isFinalized('Cannot load directives after finalization')) { + return; + } + foreach ($config_array as $key => $value) { + $key = str_replace('_', '.', $key); + if (strpos($key, '.') !== false) { + $this->set($key, $value); + } else { + $namespace = $key; + $namespace_values = $value; + foreach ($namespace_values as $directive => $value2) { + $this->set($namespace .'.'. $directive, $value2); + } + } + } + } + + /** + * Returns a list of array(namespace, directive) for all directives + * that are allowed in a web-form context as per an allowed + * namespaces/directives list. + * + * @param array $allowed List of allowed namespaces/directives + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function getAllowedDirectivesForForm($allowed, $schema = null) + { + if (!$schema) { + $schema = HTMLPurifier_ConfigSchema::instance(); + } + if ($allowed !== true) { + if (is_string($allowed)) { + $allowed = array($allowed); + } + $allowed_ns = array(); + $allowed_directives = array(); + $blacklisted_directives = array(); + foreach ($allowed as $ns_or_directive) { + if (strpos($ns_or_directive, '.') !== false) { + // directive + if ($ns_or_directive[0] == '-') { + $blacklisted_directives[substr($ns_or_directive, 1)] = true; + } else { + $allowed_directives[$ns_or_directive] = true; + } + } else { + // namespace + $allowed_ns[$ns_or_directive] = true; + } + } + } + $ret = array(); + foreach ($schema->info as $key => $def) { + list($ns, $directive) = explode('.', $key, 2); + if ($allowed !== true) { + if (isset($blacklisted_directives["$ns.$directive"])) { + continue; + } + if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) { + continue; + } + } + if (isset($def->isAlias)) { + continue; + } + if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') { + continue; + } + $ret[] = array($ns, $directive); + } + return $ret; + } + + /** + * Loads configuration values from $_GET/$_POST that were posted + * via ConfigForm + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return mixed + */ + public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) + { + $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $schema); + $config = HTMLPurifier_Config::create($ret, $schema); + return $config; + } + + /** + * Merges in configuration values from $_GET/$_POST to object. NOT STATIC. + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + */ + public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true) + { + $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $this->def); + $this->loadArray($ret); + } + + /** + * Prepares an array from a form into something usable for the more + * strict parts of HTMLPurifier_Config + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) + { + if ($index !== false) { + $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array(); + } + $mq = $mq_fix && version_compare(PHP_VERSION, '7.4.0', '<') && function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc(); + + $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $schema); + $ret = array(); + foreach ($allowed as $key) { + list($ns, $directive) = $key; + $skey = "$ns.$directive"; + if (!empty($array["Null_$skey"])) { + $ret[$ns][$directive] = null; + continue; + } + if (!isset($array[$skey])) { + continue; + } + $value = $mq ? stripslashes($array[$skey]) : $array[$skey]; + $ret[$ns][$directive] = $value; + } + return $ret; + } + + /** + * Loads configuration values from an ini file + * + * @param string $filename Name of ini file + */ + public function loadIni($filename) + { + if ($this->isFinalized('Cannot load directives after finalization')) { + return; + } + $array = parse_ini_file($filename, true); + $this->loadArray($array); + } + + /** + * Checks whether or not the configuration object is finalized. + * + * @param string|bool $error String error message, or false for no error + * + * @return bool + */ + public function isFinalized($error = false) + { + if ($this->finalized && $error) { + $this->triggerError($error, E_USER_ERROR); + } + return $this->finalized; + } + + /** + * Finalizes configuration only if auto finalize is on and not + * already finalized + */ + public function autoFinalize() + { + if ($this->autoFinalize) { + $this->finalize(); + } else { + $this->plist->squash(true); + } + } + + /** + * Finalizes a configuration object, prohibiting further change + */ + public function finalize() + { + $this->finalized = true; + $this->parser = null; + } + + /** + * Produces a nicely formatted error message by supplying the + * stack frame information OUTSIDE of HTMLPurifier_Config. + * + * @param string $msg An error message + * @param int $no An error number + */ + protected function triggerError($msg, $no) + { + // determine previous stack frame + $extra = ''; + if ($this->chatty) { + $trace = debug_backtrace(); + // zip(tail(trace), trace) -- but PHP is not Haskell har har + for ($i = 0, $c = count($trace); $i < $c - 1; $i++) { + // XXX this is not correct on some versions of HTML Purifier + if (isset($trace[$i + 1]['class']) && $trace[$i + 1]['class'] === 'HTMLPurifier_Config') { + continue; + } + $frame = $trace[$i]; + $extra = " invoked on line {$frame['line']} in file {$frame['file']}"; + break; + } + } + trigger_error($msg . $extra, $no); + } + + /** + * Returns a serialized form of the configuration object that can + * be reconstituted. + * + * @return string + */ + public function serialize() + { + $this->getDefinition('HTML'); + $this->getDefinition('CSS'); + $this->getDefinition('URI'); + return serialize($this); + } + +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema.php new file mode 100644 index 0000000..c3fe8cd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema.php @@ -0,0 +1,176 @@ + array( + * 'Directive' => new stdClass(), + * ) + * ) + * + * The stdClass may have the following properties: + * + * - If isAlias isn't set: + * - type: Integer type of directive, see HTMLPurifier_VarParser for definitions + * - allow_null: If set, this directive allows null values + * - aliases: If set, an associative array of value aliases to real values + * - allowed: If set, a lookup array of allowed (string) values + * - If isAlias is set: + * - namespace: Namespace this directive aliases to + * - name: Directive name this directive aliases to + * + * In certain degenerate cases, stdClass will actually be an integer. In + * that case, the value is equivalent to an stdClass with the type + * property set to the integer. If the integer is negative, type is + * equal to the absolute value of integer, and allow_null is true. + * + * This class is friendly with HTMLPurifier_Config. If you need introspection + * about the schema, you're better of using the ConfigSchema_Interchange, + * which uses more memory but has much richer information. + * @type array + */ + public $info = array(); + + /** + * Application-wide singleton + * @type HTMLPurifier_ConfigSchema + */ + protected static $singleton; + + public function __construct() + { + $this->defaultPlist = new HTMLPurifier_PropertyList(); + } + + /** + * Unserializes the default ConfigSchema. + * @return HTMLPurifier_ConfigSchema + */ + public static function makeFromSerial() + { + $contents = file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser'); + $r = unserialize($contents); + if (!$r) { + $hash = sha1($contents); + trigger_error("Unserialization of configuration schema failed, sha1 of file was $hash", E_USER_ERROR); + } + return $r; + } + + /** + * Retrieves an instance of the application-wide configuration definition. + * @param HTMLPurifier_ConfigSchema $prototype + * @return HTMLPurifier_ConfigSchema + */ + public static function instance($prototype = null) + { + if ($prototype !== null) { + HTMLPurifier_ConfigSchema::$singleton = $prototype; + } elseif (HTMLPurifier_ConfigSchema::$singleton === null || $prototype === true) { + HTMLPurifier_ConfigSchema::$singleton = HTMLPurifier_ConfigSchema::makeFromSerial(); + } + return HTMLPurifier_ConfigSchema::$singleton; + } + + /** + * Defines a directive for configuration + * @warning Will fail of directive's namespace is defined. + * @warning This method's signature is slightly different from the legacy + * define() static method! Beware! + * @param string $key Name of directive + * @param mixed $default Default value of directive + * @param string $type Allowed type of the directive. See + * HTMLPurifier_VarParser::$types for allowed values + * @param bool $allow_null Whether or not to allow null values + */ + public function add($key, $default, $type, $allow_null) + { + $obj = new stdClass(); + $obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type]; + if ($allow_null) { + $obj->allow_null = true; + } + $this->info[$key] = $obj; + $this->defaults[$key] = $default; + $this->defaultPlist->set($key, $default); + } + + /** + * Defines a directive value alias. + * + * Directive value aliases are convenient for developers because it lets + * them set a directive to several values and get the same result. + * @param string $key Name of Directive + * @param array $aliases Hash of aliased values to the real alias + */ + public function addValueAliases($key, $aliases) + { + if (!isset($this->info[$key]->aliases)) { + $this->info[$key]->aliases = array(); + } + foreach ($aliases as $alias => $real) { + $this->info[$key]->aliases[$alias] = $real; + } + } + + /** + * Defines a set of allowed values for a directive. + * @warning This is slightly different from the corresponding static + * method definition. + * @param string $key Name of directive + * @param array $allowed Lookup array of allowed values + */ + public function addAllowedValues($key, $allowed) + { + $this->info[$key]->allowed = $allowed; + } + + /** + * Defines a directive alias for backwards compatibility + * @param string $key Directive that will be aliased + * @param string $new_key Directive that the alias will be to + */ + public function addAlias($key, $new_key) + { + $obj = new stdClass; + $obj->key = $new_key; + $obj->isAlias = true; + $this->info[$key] = $obj; + } + + /** + * Replaces any stdClass that only has the type property with type integer. + */ + public function postProcess() + { + foreach ($this->info as $key => $v) { + if (count((array) $v) == 1) { + $this->info[$key] = $v->type; + } elseif (count((array) $v) == 2 && isset($v->allow_null)) { + $this->info[$key] = -$v->type; + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php new file mode 100644 index 0000000..d5906cd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php @@ -0,0 +1,48 @@ +directives as $d) { + $schema->add( + $d->id->key, + $d->default, + $d->type, + $d->typeAllowsNull + ); + if ($d->allowed !== null) { + $schema->addAllowedValues( + $d->id->key, + $d->allowed + ); + } + foreach ($d->aliases as $alias) { + $schema->addAlias( + $alias->key, + $d->id->key + ); + } + if ($d->valueAliases !== null) { + $schema->addValueAliases( + $d->id->key, + $d->valueAliases + ); + } + } + $schema->postProcess(); + return $schema; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php new file mode 100644 index 0000000..5fa56f7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php @@ -0,0 +1,144 @@ +startElement('div'); + + $purifier = HTMLPurifier::getInstance(); + $html = $purifier->purify($html); + $this->writeAttribute('xmlns', 'http://www.w3.org/1999/xhtml'); + $this->writeRaw($html); + + $this->endElement(); // div + } + + /** + * @param mixed $var + * @return string + */ + protected function export($var) + { + if ($var === array()) { + return 'array()'; + } + return var_export($var, true); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + */ + public function build($interchange) + { + // global access, only use as last resort + $this->interchange = $interchange; + + $this->setIndent(true); + $this->startDocument('1.0', 'UTF-8'); + $this->startElement('configdoc'); + $this->writeElement('title', $interchange->name); + + foreach ($interchange->directives as $directive) { + $this->buildDirective($directive); + } + + if ($this->namespace) { + $this->endElement(); + } // namespace + + $this->endElement(); // configdoc + $this->flush(); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + */ + public function buildDirective($directive) + { + // Kludge, although I suppose having a notion of a "root namespace" + // certainly makes things look nicer when documentation is built. + // Depends on things being sorted. + if (!$this->namespace || $this->namespace !== $directive->id->getRootNamespace()) { + if ($this->namespace) { + $this->endElement(); + } // namespace + $this->namespace = $directive->id->getRootNamespace(); + $this->startElement('namespace'); + $this->writeAttribute('id', $this->namespace); + $this->writeElement('name', $this->namespace); + } + + $this->startElement('directive'); + $this->writeAttribute('id', $directive->id->toString()); + + $this->writeElement('name', $directive->id->getDirective()); + + $this->startElement('aliases'); + foreach ($directive->aliases as $alias) { + $this->writeElement('alias', $alias->toString()); + } + $this->endElement(); // aliases + + $this->startElement('constraints'); + if ($directive->version) { + $this->writeElement('version', $directive->version); + } + $this->startElement('type'); + if ($directive->typeAllowsNull) { + $this->writeAttribute('allow-null', 'yes'); + } + $this->text($directive->type); + $this->endElement(); // type + if ($directive->allowed) { + $this->startElement('allowed'); + foreach ($directive->allowed as $value => $x) { + $this->writeElement('value', $value); + } + $this->endElement(); // allowed + } + $this->writeElement('default', $this->export($directive->default)); + $this->writeAttribute('xml:space', 'preserve'); + if ($directive->external) { + $this->startElement('external'); + foreach ($directive->external as $project) { + $this->writeElement('project', $project); + } + $this->endElement(); + } + $this->endElement(); // constraints + + if ($directive->deprecatedVersion) { + $this->startElement('deprecated'); + $this->writeElement('version', $directive->deprecatedVersion); + $this->writeElement('use', $directive->deprecatedUse->toString()); + $this->endElement(); // deprecated + } + + $this->startElement('description'); + $this->writeHTMLDiv($directive->description); + $this->endElement(); // description + + $this->endElement(); // directive + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php new file mode 100644 index 0000000..2671516 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php @@ -0,0 +1,11 @@ + array(directive info) + * @type HTMLPurifier_ConfigSchema_Interchange_Directive[] + */ + public $directives = array(); + + /** + * Adds a directive array to $directives + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function addDirective($directive) + { + if (isset($this->directives[$i = $directive->id->toString()])) { + throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine directive '$i'"); + } + $this->directives[$i] = $directive; + } + + /** + * Convenience function to perform standard validation. Throws exception + * on failed validation. + */ + public function validate() + { + $validator = new HTMLPurifier_ConfigSchema_Validator(); + return $validator->validate($this); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php new file mode 100644 index 0000000..127a39a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php @@ -0,0 +1,89 @@ + true). + * Null if all values are allowed. + * @type array + */ + public $allowed; + + /** + * List of aliases for the directive. + * e.g. array(new HTMLPurifier_ConfigSchema_Interchange_Id('Ns', 'Dir'))). + * @type HTMLPurifier_ConfigSchema_Interchange_Id[] + */ + public $aliases = array(); + + /** + * Hash of value aliases, e.g. array('alt' => 'real'). Null if value + * aliasing is disabled (necessary for non-scalar types). + * @type array + */ + public $valueAliases; + + /** + * Version of HTML Purifier the directive was introduced, e.g. '1.3.1'. + * Null if the directive has always existed. + * @type string + */ + public $version; + + /** + * ID of directive that supercedes this old directive. + * Null if not deprecated. + * @type HTMLPurifier_ConfigSchema_Interchange_Id + */ + public $deprecatedUse; + + /** + * Version of HTML Purifier this directive was deprecated. Null if not + * deprecated. + * @type string + */ + public $deprecatedVersion; + + /** + * List of external projects this directive depends on, e.g. array('CSSTidy'). + * @type array + */ + public $external = array(); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php new file mode 100644 index 0000000..126f09d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php @@ -0,0 +1,58 @@ +key = $key; + } + + /** + * @return string + * @warning This is NOT magic, to ensure that people don't abuse SPL and + * cause problems for PHP 5.0 support. + */ + public function toString() + { + return $this->key; + } + + /** + * @return string + */ + public function getRootNamespace() + { + return substr($this->key, 0, strpos($this->key, ".")); + } + + /** + * @return string + */ + public function getDirective() + { + return substr($this->key, strpos($this->key, ".") + 1); + } + + /** + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id + */ + public static function make($id) + { + return new HTMLPurifier_ConfigSchema_Interchange_Id($id); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php new file mode 100644 index 0000000..655e6dd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php @@ -0,0 +1,226 @@ +varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native(); + } + + /** + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public static function buildFromDirectory($dir = null) + { + $builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder(); + $interchange = new HTMLPurifier_ConfigSchema_Interchange(); + return $builder->buildDir($interchange, $dir); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public function buildDir($interchange, $dir = null) + { + if (!$dir) { + $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema'; + } + if (file_exists($dir . '/info.ini')) { + $info = parse_ini_file($dir . '/info.ini'); + $interchange->name = $info['name']; + } + + $files = array(); + $dh = opendir($dir); + while (false !== ($file = readdir($dh))) { + if (!$file || $file[0] == '.' || strrchr($file, '.') !== '.txt') { + continue; + } + $files[] = $file; + } + closedir($dh); + + sort($files); + foreach ($files as $file) { + $this->buildFile($interchange, $dir . '/' . $file); + } + return $interchange; + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $file + */ + public function buildFile($interchange, $file) + { + $parser = new HTMLPurifier_StringHashParser(); + $this->build( + $interchange, + new HTMLPurifier_StringHash($parser->parseFile($file)) + ); + } + + /** + * Builds an interchange object based on a hash. + * @param HTMLPurifier_ConfigSchema_Interchange $interchange HTMLPurifier_ConfigSchema_Interchange object to build + * @param HTMLPurifier_StringHash $hash source data + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function build($interchange, $hash) + { + if (!$hash instanceof HTMLPurifier_StringHash) { + $hash = new HTMLPurifier_StringHash($hash); + } + if (!isset($hash['ID'])) { + throw new HTMLPurifier_ConfigSchema_Exception('Hash does not have any ID'); + } + if (strpos($hash['ID'], '.') === false) { + if (count($hash) == 2 && isset($hash['DESCRIPTION'])) { + $hash->offsetGet('DESCRIPTION'); // prevent complaining + } else { + throw new HTMLPurifier_ConfigSchema_Exception('All directives must have a namespace'); + } + } else { + $this->buildDirective($interchange, $hash); + } + $this->_findUnused($hash); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param HTMLPurifier_StringHash $hash + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function buildDirective($interchange, $hash) + { + $directive = new HTMLPurifier_ConfigSchema_Interchange_Directive(); + + // These are required elements: + $directive->id = $this->id($hash->offsetGet('ID')); + $id = $directive->id->toString(); // convenience + + if (isset($hash['TYPE'])) { + $type = explode('/', $hash->offsetGet('TYPE')); + if (isset($type[1])) { + $directive->typeAllowsNull = true; + } + $directive->type = $type[0]; + } else { + throw new HTMLPurifier_ConfigSchema_Exception("TYPE in directive hash '$id' not defined"); + } + + if (isset($hash['DEFAULT'])) { + try { + $directive->default = $this->varParser->parse( + $hash->offsetGet('DEFAULT'), + $directive->type, + $directive->typeAllowsNull + ); + } catch (HTMLPurifier_VarParserException $e) { + throw new HTMLPurifier_ConfigSchema_Exception($e->getMessage() . " in DEFAULT in directive hash '$id'"); + } + } + + if (isset($hash['DESCRIPTION'])) { + $directive->description = $hash->offsetGet('DESCRIPTION'); + } + + if (isset($hash['ALLOWED'])) { + $directive->allowed = $this->lookup($this->evalArray($hash->offsetGet('ALLOWED'))); + } + + if (isset($hash['VALUE-ALIASES'])) { + $directive->valueAliases = $this->evalArray($hash->offsetGet('VALUE-ALIASES')); + } + + if (isset($hash['ALIASES'])) { + $raw_aliases = trim($hash->offsetGet('ALIASES')); + $aliases = preg_split('/\s*,\s*/', $raw_aliases); + foreach ($aliases as $alias) { + $directive->aliases[] = $this->id($alias); + } + } + + if (isset($hash['VERSION'])) { + $directive->version = $hash->offsetGet('VERSION'); + } + + if (isset($hash['DEPRECATED-USE'])) { + $directive->deprecatedUse = $this->id($hash->offsetGet('DEPRECATED-USE')); + } + + if (isset($hash['DEPRECATED-VERSION'])) { + $directive->deprecatedVersion = $hash->offsetGet('DEPRECATED-VERSION'); + } + + if (isset($hash['EXTERNAL'])) { + $directive->external = preg_split('/\s*,\s*/', trim($hash->offsetGet('EXTERNAL'))); + } + + $interchange->addDirective($directive); + } + + /** + * Evaluates an array PHP code string without array() wrapper + * @param string $contents + */ + protected function evalArray($contents) + { + return eval('return array(' . $contents . ');'); + } + + /** + * Converts an array list into a lookup array. + * @param array $array + * @return array + */ + protected function lookup($array) + { + $ret = array(); + foreach ($array as $val) { + $ret[$val] = true; + } + return $ret; + } + + /** + * Convenience function that creates an HTMLPurifier_ConfigSchema_Interchange_Id + * object based on a string Id. + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id + */ + protected function id($id) + { + return HTMLPurifier_ConfigSchema_Interchange_Id::make($id); + } + + /** + * Triggers errors for any unused keys passed in the hash; such keys + * may indicate typos, missing values, etc. + * @param HTMLPurifier_StringHash $hash Hash to check. + */ + protected function _findUnused($hash) + { + $accessed = $hash->getAccessed(); + foreach ($hash as $k => $v) { + if (!isset($accessed[$k])) { + trigger_error("String hash key '$k' not used by builder", E_USER_NOTICE); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php new file mode 100644 index 0000000..fb31277 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php @@ -0,0 +1,248 @@ +parser = new HTMLPurifier_VarParser(); + } + + /** + * Validates a fully-formed interchange object. + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @return bool + */ + public function validate($interchange) + { + $this->interchange = $interchange; + $this->aliases = array(); + // PHP is a bit lax with integer <=> string conversions in + // arrays, so we don't use the identical !== comparison + foreach ($interchange->directives as $i => $directive) { + $id = $directive->id->toString(); + if ($i != $id) { + $this->error(false, "Integrity violation: key '$i' does not match internal id '$id'"); + } + $this->validateDirective($directive); + } + return true; + } + + /** + * Validates a HTMLPurifier_ConfigSchema_Interchange_Id object. + * @param HTMLPurifier_ConfigSchema_Interchange_Id $id + */ + public function validateId($id) + { + $id_string = $id->toString(); + $this->context[] = "id '$id_string'"; + if (!$id instanceof HTMLPurifier_ConfigSchema_Interchange_Id) { + // handled by InterchangeBuilder + $this->error(false, 'is not an instance of HTMLPurifier_ConfigSchema_Interchange_Id'); + } + // keys are now unconstrained (we might want to narrow down to A-Za-z0-9.) + // we probably should check that it has at least one namespace + $this->with($id, 'key') + ->assertNotEmpty() + ->assertIsString(); // implicit assertIsString handled by InterchangeBuilder + array_pop($this->context); + } + + /** + * Validates a HTMLPurifier_ConfigSchema_Interchange_Directive object. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirective($d) + { + $id = $d->id->toString(); + $this->context[] = "directive '$id'"; + $this->validateId($d->id); + + $this->with($d, 'description') + ->assertNotEmpty(); + + // BEGIN - handled by InterchangeBuilder + $this->with($d, 'type') + ->assertNotEmpty(); + $this->with($d, 'typeAllowsNull') + ->assertIsBool(); + try { + // This also tests validity of $d->type + $this->parser->parse($d->default, $d->type, $d->typeAllowsNull); + } catch (HTMLPurifier_VarParserException $e) { + $this->error('default', 'had error: ' . $e->getMessage()); + } + // END - handled by InterchangeBuilder + + if (!is_null($d->allowed) || !empty($d->valueAliases)) { + // allowed and valueAliases require that we be dealing with + // strings, so check for that early. + $d_int = HTMLPurifier_VarParser::$types[$d->type]; + if (!isset(HTMLPurifier_VarParser::$stringTypes[$d_int])) { + $this->error('type', 'must be a string type when used with allowed or value aliases'); + } + } + + $this->validateDirectiveAllowed($d); + $this->validateDirectiveValueAliases($d); + $this->validateDirectiveAliases($d); + + array_pop($this->context); + } + + /** + * Extra validation if $allowed member variable of + * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveAllowed($d) + { + if (is_null($d->allowed)) { + return; + } + $this->with($d, 'allowed') + ->assertNotEmpty() + ->assertIsLookup(); // handled by InterchangeBuilder + if (is_string($d->default) && !isset($d->allowed[$d->default])) { + $this->error('default', 'must be an allowed value'); + } + $this->context[] = 'allowed'; + foreach ($d->allowed as $val => $x) { + if (!is_string($val)) { + $this->error("value $val", 'must be a string'); + } + } + array_pop($this->context); + } + + /** + * Extra validation if $valueAliases member variable of + * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveValueAliases($d) + { + if (is_null($d->valueAliases)) { + return; + } + $this->with($d, 'valueAliases') + ->assertIsArray(); // handled by InterchangeBuilder + $this->context[] = 'valueAliases'; + foreach ($d->valueAliases as $alias => $real) { + if (!is_string($alias)) { + $this->error("alias $alias", 'must be a string'); + } + if (!is_string($real)) { + $this->error("alias target $real from alias '$alias'", 'must be a string'); + } + if ($alias === $real) { + $this->error("alias '$alias'", "must not be an alias to itself"); + } + } + if (!is_null($d->allowed)) { + foreach ($d->valueAliases as $alias => $real) { + if (isset($d->allowed[$alias])) { + $this->error("alias '$alias'", 'must not be an allowed value'); + } elseif (!isset($d->allowed[$real])) { + $this->error("alias '$alias'", 'must be an alias to an allowed value'); + } + } + } + array_pop($this->context); + } + + /** + * Extra validation if $aliases member variable of + * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveAliases($d) + { + $this->with($d, 'aliases') + ->assertIsArray(); // handled by InterchangeBuilder + $this->context[] = 'aliases'; + foreach ($d->aliases as $alias) { + $this->validateId($alias); + $s = $alias->toString(); + if (isset($this->interchange->directives[$s])) { + $this->error("alias '$s'", 'collides with another directive'); + } + if (isset($this->aliases[$s])) { + $other_directive = $this->aliases[$s]; + $this->error("alias '$s'", "collides with alias for directive '$other_directive'"); + } + $this->aliases[$s] = $d->id->toString(); + } + array_pop($this->context); + } + + // protected helper functions + + /** + * Convenience function for generating HTMLPurifier_ConfigSchema_ValidatorAtom + * for validating simple member variables of objects. + * @param $obj + * @param $member + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + protected function with($obj, $member) + { + return new HTMLPurifier_ConfigSchema_ValidatorAtom($this->getFormattedContext(), $obj, $member); + } + + /** + * Emits an error, providing helpful context. + * @throws HTMLPurifier_ConfigSchema_Exception + */ + protected function error($target, $msg) + { + if ($target !== false) { + $prefix = ucfirst($target) . ' in ' . $this->getFormattedContext(); + } else { + $prefix = ucfirst($this->getFormattedContext()); + } + throw new HTMLPurifier_ConfigSchema_Exception(trim($prefix . ' ' . $msg)); + } + + /** + * Returns a formatted context string. + * @return string + */ + protected function getFormattedContext() + { + return implode(' in ', array_reverse($this->context)); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php new file mode 100644 index 0000000..c9aa364 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php @@ -0,0 +1,130 @@ +context = $context; + $this->obj = $obj; + $this->member = $member; + $this->contents =& $obj->$member; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsString() + { + if (!is_string($this->contents)) { + $this->error('must be a string'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsBool() + { + if (!is_bool($this->contents)) { + $this->error('must be a boolean'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsArray() + { + if (!is_array($this->contents)) { + $this->error('must be an array'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotNull() + { + if ($this->contents === null) { + $this->error('must not be null'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertAlnum() + { + $this->assertIsString(); + if (!ctype_alnum($this->contents)) { + $this->error('must be alphanumeric'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotEmpty() + { + if (empty($this->contents)) { + $this->error('must not be empty'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsLookup() + { + $this->assertIsArray(); + foreach ($this->contents as $v) { + if ($v !== true) { + $this->error('must be a lookup array'); + } + } + return $this; + } + + /** + * @param string $msg + * @throws HTMLPurifier_ConfigSchema_Exception + */ + protected function error($msg) + { + throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser new file mode 100644 index 0000000..a5426c7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser @@ -0,0 +1 @@ +O:25:"HTMLPurifier_ConfigSchema":3:{s:8:"defaults";a:127:{s:19:"Attr.AllowedClasses";N;s:24:"Attr.AllowedFrameTargets";a:0:{}s:15:"Attr.AllowedRel";a:0:{}s:15:"Attr.AllowedRev";a:0:{}s:18:"Attr.ClassUseCDATA";N;s:20:"Attr.DefaultImageAlt";N;s:24:"Attr.DefaultInvalidImage";s:0:"";s:27:"Attr.DefaultInvalidImageAlt";s:13:"Invalid image";s:19:"Attr.DefaultTextDir";s:3:"ltr";s:13:"Attr.EnableID";b:0;s:21:"Attr.ForbiddenClasses";a:0:{}s:13:"Attr.ID.HTML5";N;s:16:"Attr.IDBlacklist";a:0:{}s:22:"Attr.IDBlacklistRegexp";N;s:13:"Attr.IDPrefix";s:0:"";s:18:"Attr.IDPrefixLocal";s:0:"";s:24:"AutoFormat.AutoParagraph";b:0;s:17:"AutoFormat.Custom";a:0:{}s:25:"AutoFormat.DisplayLinkURI";b:0;s:18:"AutoFormat.Linkify";b:0;s:33:"AutoFormat.PurifierLinkify.DocURL";s:3:"#%s";s:26:"AutoFormat.PurifierLinkify";b:0;s:32:"AutoFormat.RemoveEmpty.Predicate";a:4:{s:8:"colgroup";a:0:{}s:2:"th";a:0:{}s:2:"td";a:0:{}s:6:"iframe";a:1:{i:0;s:3:"src";}}s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";a:2:{s:2:"td";b:1;s:2:"th";b:1;}s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";b:0;s:22:"AutoFormat.RemoveEmpty";b:0;s:39:"AutoFormat.RemoveSpansWithoutAttributes";b:0;s:19:"CSS.AllowDuplicates";b:0;s:18:"CSS.AllowImportant";b:0;s:15:"CSS.AllowTricky";b:0;s:16:"CSS.AllowedFonts";N;s:21:"CSS.AllowedProperties";N;s:17:"CSS.DefinitionRev";i:1;s:23:"CSS.ForbiddenProperties";a:0:{}s:16:"CSS.MaxImgLength";s:6:"1200px";s:15:"CSS.Proprietary";b:0;s:11:"CSS.Trusted";b:0;s:20:"Cache.DefinitionImpl";s:10:"Serializer";s:20:"Cache.SerializerPath";N;s:27:"Cache.SerializerPermissions";i:493;s:22:"Core.AggressivelyFixLt";b:1;s:29:"Core.AggressivelyRemoveScript";b:1;s:28:"Core.AllowHostnameUnderscore";b:0;s:23:"Core.AllowParseManyTags";b:0;s:18:"Core.CollectErrors";b:0;s:18:"Core.ColorKeywords";a:148:{s:9:"aliceblue";s:7:"#F0F8FF";s:12:"antiquewhite";s:7:"#FAEBD7";s:4:"aqua";s:7:"#00FFFF";s:10:"aquamarine";s:7:"#7FFFD4";s:5:"azure";s:7:"#F0FFFF";s:5:"beige";s:7:"#F5F5DC";s:6:"bisque";s:7:"#FFE4C4";s:5:"black";s:7:"#000000";s:14:"blanchedalmond";s:7:"#FFEBCD";s:4:"blue";s:7:"#0000FF";s:10:"blueviolet";s:7:"#8A2BE2";s:5:"brown";s:7:"#A52A2A";s:9:"burlywood";s:7:"#DEB887";s:9:"cadetblue";s:7:"#5F9EA0";s:10:"chartreuse";s:7:"#7FFF00";s:9:"chocolate";s:7:"#D2691E";s:5:"coral";s:7:"#FF7F50";s:14:"cornflowerblue";s:7:"#6495ED";s:8:"cornsilk";s:7:"#FFF8DC";s:7:"crimson";s:7:"#DC143C";s:4:"cyan";s:7:"#00FFFF";s:8:"darkblue";s:7:"#00008B";s:8:"darkcyan";s:7:"#008B8B";s:13:"darkgoldenrod";s:7:"#B8860B";s:8:"darkgray";s:7:"#A9A9A9";s:8:"darkgrey";s:7:"#A9A9A9";s:9:"darkgreen";s:7:"#006400";s:9:"darkkhaki";s:7:"#BDB76B";s:11:"darkmagenta";s:7:"#8B008B";s:14:"darkolivegreen";s:7:"#556B2F";s:10:"darkorange";s:7:"#FF8C00";s:10:"darkorchid";s:7:"#9932CC";s:7:"darkred";s:7:"#8B0000";s:10:"darksalmon";s:7:"#E9967A";s:12:"darkseagreen";s:7:"#8FBC8F";s:13:"darkslateblue";s:7:"#483D8B";s:13:"darkslategray";s:7:"#2F4F4F";s:13:"darkslategrey";s:7:"#2F4F4F";s:13:"darkturquoise";s:7:"#00CED1";s:10:"darkviolet";s:7:"#9400D3";s:8:"deeppink";s:7:"#FF1493";s:11:"deepskyblue";s:7:"#00BFFF";s:7:"dimgray";s:7:"#696969";s:7:"dimgrey";s:7:"#696969";s:10:"dodgerblue";s:7:"#1E90FF";s:9:"firebrick";s:7:"#B22222";s:11:"floralwhite";s:7:"#FFFAF0";s:11:"forestgreen";s:7:"#228B22";s:7:"fuchsia";s:7:"#FF00FF";s:9:"gainsboro";s:7:"#DCDCDC";s:10:"ghostwhite";s:7:"#F8F8FF";s:4:"gold";s:7:"#FFD700";s:9:"goldenrod";s:7:"#DAA520";s:4:"gray";s:7:"#808080";s:4:"grey";s:7:"#808080";s:5:"green";s:7:"#008000";s:11:"greenyellow";s:7:"#ADFF2F";s:8:"honeydew";s:7:"#F0FFF0";s:7:"hotpink";s:7:"#FF69B4";s:9:"indianred";s:7:"#CD5C5C";s:6:"indigo";s:7:"#4B0082";s:5:"ivory";s:7:"#FFFFF0";s:5:"khaki";s:7:"#F0E68C";s:8:"lavender";s:7:"#E6E6FA";s:13:"lavenderblush";s:7:"#FFF0F5";s:9:"lawngreen";s:7:"#7CFC00";s:12:"lemonchiffon";s:7:"#FFFACD";s:9:"lightblue";s:7:"#ADD8E6";s:10:"lightcoral";s:7:"#F08080";s:9:"lightcyan";s:7:"#E0FFFF";s:20:"lightgoldenrodyellow";s:7:"#FAFAD2";s:9:"lightgray";s:7:"#D3D3D3";s:9:"lightgrey";s:7:"#D3D3D3";s:10:"lightgreen";s:7:"#90EE90";s:9:"lightpink";s:7:"#FFB6C1";s:11:"lightsalmon";s:7:"#FFA07A";s:13:"lightseagreen";s:7:"#20B2AA";s:12:"lightskyblue";s:7:"#87CEFA";s:14:"lightslategray";s:7:"#778899";s:14:"lightslategrey";s:7:"#778899";s:14:"lightsteelblue";s:7:"#B0C4DE";s:11:"lightyellow";s:7:"#FFFFE0";s:4:"lime";s:7:"#00FF00";s:9:"limegreen";s:7:"#32CD32";s:5:"linen";s:7:"#FAF0E6";s:7:"magenta";s:7:"#FF00FF";s:6:"maroon";s:7:"#800000";s:16:"mediumaquamarine";s:7:"#66CDAA";s:10:"mediumblue";s:7:"#0000CD";s:12:"mediumorchid";s:7:"#BA55D3";s:12:"mediumpurple";s:7:"#9370DB";s:14:"mediumseagreen";s:7:"#3CB371";s:15:"mediumslateblue";s:7:"#7B68EE";s:17:"mediumspringgreen";s:7:"#00FA9A";s:15:"mediumturquoise";s:7:"#48D1CC";s:15:"mediumvioletred";s:7:"#C71585";s:12:"midnightblue";s:7:"#191970";s:9:"mintcream";s:7:"#F5FFFA";s:9:"mistyrose";s:7:"#FFE4E1";s:8:"moccasin";s:7:"#FFE4B5";s:11:"navajowhite";s:7:"#FFDEAD";s:4:"navy";s:7:"#000080";s:7:"oldlace";s:7:"#FDF5E6";s:5:"olive";s:7:"#808000";s:9:"olivedrab";s:7:"#6B8E23";s:6:"orange";s:7:"#FFA500";s:9:"orangered";s:7:"#FF4500";s:6:"orchid";s:7:"#DA70D6";s:13:"palegoldenrod";s:7:"#EEE8AA";s:9:"palegreen";s:7:"#98FB98";s:13:"paleturquoise";s:7:"#AFEEEE";s:13:"palevioletred";s:7:"#DB7093";s:10:"papayawhip";s:7:"#FFEFD5";s:9:"peachpuff";s:7:"#FFDAB9";s:4:"peru";s:7:"#CD853F";s:4:"pink";s:7:"#FFC0CB";s:4:"plum";s:7:"#DDA0DD";s:10:"powderblue";s:7:"#B0E0E6";s:6:"purple";s:7:"#800080";s:13:"rebeccapurple";s:7:"#663399";s:3:"red";s:7:"#FF0000";s:9:"rosybrown";s:7:"#BC8F8F";s:9:"royalblue";s:7:"#4169E1";s:11:"saddlebrown";s:7:"#8B4513";s:6:"salmon";s:7:"#FA8072";s:10:"sandybrown";s:7:"#F4A460";s:8:"seagreen";s:7:"#2E8B57";s:8:"seashell";s:7:"#FFF5EE";s:6:"sienna";s:7:"#A0522D";s:6:"silver";s:7:"#C0C0C0";s:7:"skyblue";s:7:"#87CEEB";s:9:"slateblue";s:7:"#6A5ACD";s:9:"slategray";s:7:"#708090";s:9:"slategrey";s:7:"#708090";s:4:"snow";s:7:"#FFFAFA";s:11:"springgreen";s:7:"#00FF7F";s:9:"steelblue";s:7:"#4682B4";s:3:"tan";s:7:"#D2B48C";s:4:"teal";s:7:"#008080";s:7:"thistle";s:7:"#D8BFD8";s:6:"tomato";s:7:"#FF6347";s:9:"turquoise";s:7:"#40E0D0";s:6:"violet";s:7:"#EE82EE";s:5:"wheat";s:7:"#F5DEB3";s:5:"white";s:7:"#FFFFFF";s:10:"whitesmoke";s:7:"#F5F5F5";s:6:"yellow";s:7:"#FFFF00";s:11:"yellowgreen";s:7:"#9ACD32";}s:30:"Core.ConvertDocumentToFragment";b:1;s:36:"Core.DirectLexLineNumberSyncInterval";i:0;s:20:"Core.DisableExcludes";b:0;s:15:"Core.EnableIDNA";b:0;s:13:"Core.Encoding";s:5:"utf-8";s:26:"Core.EscapeInvalidChildren";b:0;s:22:"Core.EscapeInvalidTags";b:0;s:29:"Core.EscapeNonASCIICharacters";b:0;s:19:"Core.HiddenElements";a:2:{s:6:"script";b:1;s:5:"style";b:1;}s:13:"Core.Language";s:2:"en";s:24:"Core.LegacyEntityDecoder";b:0;s:14:"Core.LexerImpl";N;s:24:"Core.MaintainLineNumbers";N;s:22:"Core.NormalizeNewlines";b:1;s:21:"Core.RemoveInvalidImg";b:1;s:33:"Core.RemoveProcessingInstructions";b:0;s:25:"Core.RemoveScriptContents";N;s:13:"Filter.Custom";a:0:{}s:34:"Filter.ExtractStyleBlocks.Escaping";b:1;s:31:"Filter.ExtractStyleBlocks.Scope";N;s:34:"Filter.ExtractStyleBlocks.TidyImpl";N;s:25:"Filter.ExtractStyleBlocks";b:0;s:14:"Filter.YouTube";b:0;s:12:"HTML.Allowed";N;s:22:"HTML.AllowedAttributes";N;s:20:"HTML.AllowedComments";a:0:{}s:26:"HTML.AllowedCommentsRegexp";N;s:20:"HTML.AllowedElements";N;s:19:"HTML.AllowedModules";N;s:23:"HTML.Attr.Name.UseCDATA";b:0;s:17:"HTML.BlockWrapper";s:1:"p";s:16:"HTML.CoreModules";a:7:{s:9:"Structure";b:1;s:4:"Text";b:1;s:9:"Hypertext";b:1;s:4:"List";b:1;s:22:"NonXMLCommonAttributes";b:1;s:19:"XMLCommonAttributes";b:1;s:16:"CommonAttributes";b:1;}s:18:"HTML.CustomDoctype";N;s:17:"HTML.DefinitionID";N;s:18:"HTML.DefinitionRev";i:1;s:12:"HTML.Doctype";N;s:25:"HTML.FlashAllowFullScreen";b:0;s:24:"HTML.ForbiddenAttributes";a:0:{}s:22:"HTML.ForbiddenElements";a:0:{}s:10:"HTML.Forms";b:0;s:17:"HTML.MaxImgLength";i:1200;s:13:"HTML.Nofollow";b:0;s:11:"HTML.Parent";s:3:"div";s:16:"HTML.Proprietary";b:0;s:14:"HTML.SafeEmbed";b:0;s:15:"HTML.SafeIframe";b:0;s:15:"HTML.SafeObject";b:0;s:18:"HTML.SafeScripting";a:0:{}s:11:"HTML.Strict";b:0;s:16:"HTML.TargetBlank";b:0;s:19:"HTML.TargetNoopener";b:1;s:21:"HTML.TargetNoreferrer";b:1;s:12:"HTML.TidyAdd";a:0:{}s:14:"HTML.TidyLevel";s:6:"medium";s:15:"HTML.TidyRemove";a:0:{}s:12:"HTML.Trusted";b:0;s:10:"HTML.XHTML";b:1;s:28:"Output.CommentScriptContents";b:1;s:19:"Output.FixInnerHTML";b:1;s:18:"Output.FlashCompat";b:0;s:14:"Output.Newline";N;s:15:"Output.SortAttr";b:0;s:17:"Output.TidyFormat";b:0;s:17:"Test.ForceNoIconv";b:0;s:18:"URI.AllowedSchemes";a:7:{s:4:"http";b:1;s:5:"https";b:1;s:6:"mailto";b:1;s:3:"ftp";b:1;s:4:"nntp";b:1;s:4:"news";b:1;s:3:"tel";b:1;}s:8:"URI.Base";N;s:17:"URI.DefaultScheme";s:4:"http";s:16:"URI.DefinitionID";N;s:17:"URI.DefinitionRev";i:1;s:11:"URI.Disable";b:0;s:19:"URI.DisableExternal";b:0;s:28:"URI.DisableExternalResources";b:0;s:20:"URI.DisableResources";b:0;s:8:"URI.Host";N;s:17:"URI.HostBlacklist";a:0:{}s:16:"URI.MakeAbsolute";b:0;s:9:"URI.Munge";N;s:18:"URI.MungeResources";b:0;s:18:"URI.MungeSecretKey";N;s:26:"URI.OverrideAllowedSchemes";b:1;s:20:"URI.SafeIframeRegexp";N;}s:12:"defaultPlist";O:25:"HTMLPurifier_PropertyList":3:{s:7:"*data";a:127:{s:19:"Attr.AllowedClasses";N;s:24:"Attr.AllowedFrameTargets";a:0:{}s:15:"Attr.AllowedRel";a:0:{}s:15:"Attr.AllowedRev";a:0:{}s:18:"Attr.ClassUseCDATA";N;s:20:"Attr.DefaultImageAlt";N;s:24:"Attr.DefaultInvalidImage";s:0:"";s:27:"Attr.DefaultInvalidImageAlt";s:13:"Invalid image";s:19:"Attr.DefaultTextDir";s:3:"ltr";s:13:"Attr.EnableID";b:0;s:21:"Attr.ForbiddenClasses";a:0:{}s:13:"Attr.ID.HTML5";N;s:16:"Attr.IDBlacklist";a:0:{}s:22:"Attr.IDBlacklistRegexp";N;s:13:"Attr.IDPrefix";s:0:"";s:18:"Attr.IDPrefixLocal";s:0:"";s:24:"AutoFormat.AutoParagraph";b:0;s:17:"AutoFormat.Custom";a:0:{}s:25:"AutoFormat.DisplayLinkURI";b:0;s:18:"AutoFormat.Linkify";b:0;s:33:"AutoFormat.PurifierLinkify.DocURL";s:3:"#%s";s:26:"AutoFormat.PurifierLinkify";b:0;s:32:"AutoFormat.RemoveEmpty.Predicate";a:4:{s:8:"colgroup";a:0:{}s:2:"th";a:0:{}s:2:"td";a:0:{}s:6:"iframe";a:1:{i:0;s:3:"src";}}s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";a:2:{s:2:"td";b:1;s:2:"th";b:1;}s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";b:0;s:22:"AutoFormat.RemoveEmpty";b:0;s:39:"AutoFormat.RemoveSpansWithoutAttributes";b:0;s:19:"CSS.AllowDuplicates";b:0;s:18:"CSS.AllowImportant";b:0;s:15:"CSS.AllowTricky";b:0;s:16:"CSS.AllowedFonts";N;s:21:"CSS.AllowedProperties";N;s:17:"CSS.DefinitionRev";i:1;s:23:"CSS.ForbiddenProperties";a:0:{}s:16:"CSS.MaxImgLength";s:6:"1200px";s:15:"CSS.Proprietary";b:0;s:11:"CSS.Trusted";b:0;s:20:"Cache.DefinitionImpl";s:10:"Serializer";s:20:"Cache.SerializerPath";N;s:27:"Cache.SerializerPermissions";i:493;s:22:"Core.AggressivelyFixLt";b:1;s:29:"Core.AggressivelyRemoveScript";b:1;s:28:"Core.AllowHostnameUnderscore";b:0;s:23:"Core.AllowParseManyTags";b:0;s:18:"Core.CollectErrors";b:0;s:18:"Core.ColorKeywords";a:148:{s:9:"aliceblue";s:7:"#F0F8FF";s:12:"antiquewhite";s:7:"#FAEBD7";s:4:"aqua";s:7:"#00FFFF";s:10:"aquamarine";s:7:"#7FFFD4";s:5:"azure";s:7:"#F0FFFF";s:5:"beige";s:7:"#F5F5DC";s:6:"bisque";s:7:"#FFE4C4";s:5:"black";s:7:"#000000";s:14:"blanchedalmond";s:7:"#FFEBCD";s:4:"blue";s:7:"#0000FF";s:10:"blueviolet";s:7:"#8A2BE2";s:5:"brown";s:7:"#A52A2A";s:9:"burlywood";s:7:"#DEB887";s:9:"cadetblue";s:7:"#5F9EA0";s:10:"chartreuse";s:7:"#7FFF00";s:9:"chocolate";s:7:"#D2691E";s:5:"coral";s:7:"#FF7F50";s:14:"cornflowerblue";s:7:"#6495ED";s:8:"cornsilk";s:7:"#FFF8DC";s:7:"crimson";s:7:"#DC143C";s:4:"cyan";s:7:"#00FFFF";s:8:"darkblue";s:7:"#00008B";s:8:"darkcyan";s:7:"#008B8B";s:13:"darkgoldenrod";s:7:"#B8860B";s:8:"darkgray";s:7:"#A9A9A9";s:8:"darkgrey";s:7:"#A9A9A9";s:9:"darkgreen";s:7:"#006400";s:9:"darkkhaki";s:7:"#BDB76B";s:11:"darkmagenta";s:7:"#8B008B";s:14:"darkolivegreen";s:7:"#556B2F";s:10:"darkorange";s:7:"#FF8C00";s:10:"darkorchid";s:7:"#9932CC";s:7:"darkred";s:7:"#8B0000";s:10:"darksalmon";s:7:"#E9967A";s:12:"darkseagreen";s:7:"#8FBC8F";s:13:"darkslateblue";s:7:"#483D8B";s:13:"darkslategray";s:7:"#2F4F4F";s:13:"darkslategrey";s:7:"#2F4F4F";s:13:"darkturquoise";s:7:"#00CED1";s:10:"darkviolet";s:7:"#9400D3";s:8:"deeppink";s:7:"#FF1493";s:11:"deepskyblue";s:7:"#00BFFF";s:7:"dimgray";s:7:"#696969";s:7:"dimgrey";s:7:"#696969";s:10:"dodgerblue";s:7:"#1E90FF";s:9:"firebrick";s:7:"#B22222";s:11:"floralwhite";s:7:"#FFFAF0";s:11:"forestgreen";s:7:"#228B22";s:7:"fuchsia";s:7:"#FF00FF";s:9:"gainsboro";s:7:"#DCDCDC";s:10:"ghostwhite";s:7:"#F8F8FF";s:4:"gold";s:7:"#FFD700";s:9:"goldenrod";s:7:"#DAA520";s:4:"gray";s:7:"#808080";s:4:"grey";s:7:"#808080";s:5:"green";s:7:"#008000";s:11:"greenyellow";s:7:"#ADFF2F";s:8:"honeydew";s:7:"#F0FFF0";s:7:"hotpink";s:7:"#FF69B4";s:9:"indianred";s:7:"#CD5C5C";s:6:"indigo";s:7:"#4B0082";s:5:"ivory";s:7:"#FFFFF0";s:5:"khaki";s:7:"#F0E68C";s:8:"lavender";s:7:"#E6E6FA";s:13:"lavenderblush";s:7:"#FFF0F5";s:9:"lawngreen";s:7:"#7CFC00";s:12:"lemonchiffon";s:7:"#FFFACD";s:9:"lightblue";s:7:"#ADD8E6";s:10:"lightcoral";s:7:"#F08080";s:9:"lightcyan";s:7:"#E0FFFF";s:20:"lightgoldenrodyellow";s:7:"#FAFAD2";s:9:"lightgray";s:7:"#D3D3D3";s:9:"lightgrey";s:7:"#D3D3D3";s:10:"lightgreen";s:7:"#90EE90";s:9:"lightpink";s:7:"#FFB6C1";s:11:"lightsalmon";s:7:"#FFA07A";s:13:"lightseagreen";s:7:"#20B2AA";s:12:"lightskyblue";s:7:"#87CEFA";s:14:"lightslategray";s:7:"#778899";s:14:"lightslategrey";s:7:"#778899";s:14:"lightsteelblue";s:7:"#B0C4DE";s:11:"lightyellow";s:7:"#FFFFE0";s:4:"lime";s:7:"#00FF00";s:9:"limegreen";s:7:"#32CD32";s:5:"linen";s:7:"#FAF0E6";s:7:"magenta";s:7:"#FF00FF";s:6:"maroon";s:7:"#800000";s:16:"mediumaquamarine";s:7:"#66CDAA";s:10:"mediumblue";s:7:"#0000CD";s:12:"mediumorchid";s:7:"#BA55D3";s:12:"mediumpurple";s:7:"#9370DB";s:14:"mediumseagreen";s:7:"#3CB371";s:15:"mediumslateblue";s:7:"#7B68EE";s:17:"mediumspringgreen";s:7:"#00FA9A";s:15:"mediumturquoise";s:7:"#48D1CC";s:15:"mediumvioletred";s:7:"#C71585";s:12:"midnightblue";s:7:"#191970";s:9:"mintcream";s:7:"#F5FFFA";s:9:"mistyrose";s:7:"#FFE4E1";s:8:"moccasin";s:7:"#FFE4B5";s:11:"navajowhite";s:7:"#FFDEAD";s:4:"navy";s:7:"#000080";s:7:"oldlace";s:7:"#FDF5E6";s:5:"olive";s:7:"#808000";s:9:"olivedrab";s:7:"#6B8E23";s:6:"orange";s:7:"#FFA500";s:9:"orangered";s:7:"#FF4500";s:6:"orchid";s:7:"#DA70D6";s:13:"palegoldenrod";s:7:"#EEE8AA";s:9:"palegreen";s:7:"#98FB98";s:13:"paleturquoise";s:7:"#AFEEEE";s:13:"palevioletred";s:7:"#DB7093";s:10:"papayawhip";s:7:"#FFEFD5";s:9:"peachpuff";s:7:"#FFDAB9";s:4:"peru";s:7:"#CD853F";s:4:"pink";s:7:"#FFC0CB";s:4:"plum";s:7:"#DDA0DD";s:10:"powderblue";s:7:"#B0E0E6";s:6:"purple";s:7:"#800080";s:13:"rebeccapurple";s:7:"#663399";s:3:"red";s:7:"#FF0000";s:9:"rosybrown";s:7:"#BC8F8F";s:9:"royalblue";s:7:"#4169E1";s:11:"saddlebrown";s:7:"#8B4513";s:6:"salmon";s:7:"#FA8072";s:10:"sandybrown";s:7:"#F4A460";s:8:"seagreen";s:7:"#2E8B57";s:8:"seashell";s:7:"#FFF5EE";s:6:"sienna";s:7:"#A0522D";s:6:"silver";s:7:"#C0C0C0";s:7:"skyblue";s:7:"#87CEEB";s:9:"slateblue";s:7:"#6A5ACD";s:9:"slategray";s:7:"#708090";s:9:"slategrey";s:7:"#708090";s:4:"snow";s:7:"#FFFAFA";s:11:"springgreen";s:7:"#00FF7F";s:9:"steelblue";s:7:"#4682B4";s:3:"tan";s:7:"#D2B48C";s:4:"teal";s:7:"#008080";s:7:"thistle";s:7:"#D8BFD8";s:6:"tomato";s:7:"#FF6347";s:9:"turquoise";s:7:"#40E0D0";s:6:"violet";s:7:"#EE82EE";s:5:"wheat";s:7:"#F5DEB3";s:5:"white";s:7:"#FFFFFF";s:10:"whitesmoke";s:7:"#F5F5F5";s:6:"yellow";s:7:"#FFFF00";s:11:"yellowgreen";s:7:"#9ACD32";}s:30:"Core.ConvertDocumentToFragment";b:1;s:36:"Core.DirectLexLineNumberSyncInterval";i:0;s:20:"Core.DisableExcludes";b:0;s:15:"Core.EnableIDNA";b:0;s:13:"Core.Encoding";s:5:"utf-8";s:26:"Core.EscapeInvalidChildren";b:0;s:22:"Core.EscapeInvalidTags";b:0;s:29:"Core.EscapeNonASCIICharacters";b:0;s:19:"Core.HiddenElements";a:2:{s:6:"script";b:1;s:5:"style";b:1;}s:13:"Core.Language";s:2:"en";s:24:"Core.LegacyEntityDecoder";b:0;s:14:"Core.LexerImpl";N;s:24:"Core.MaintainLineNumbers";N;s:22:"Core.NormalizeNewlines";b:1;s:21:"Core.RemoveInvalidImg";b:1;s:33:"Core.RemoveProcessingInstructions";b:0;s:25:"Core.RemoveScriptContents";N;s:13:"Filter.Custom";a:0:{}s:34:"Filter.ExtractStyleBlocks.Escaping";b:1;s:31:"Filter.ExtractStyleBlocks.Scope";N;s:34:"Filter.ExtractStyleBlocks.TidyImpl";N;s:25:"Filter.ExtractStyleBlocks";b:0;s:14:"Filter.YouTube";b:0;s:12:"HTML.Allowed";N;s:22:"HTML.AllowedAttributes";N;s:20:"HTML.AllowedComments";a:0:{}s:26:"HTML.AllowedCommentsRegexp";N;s:20:"HTML.AllowedElements";N;s:19:"HTML.AllowedModules";N;s:23:"HTML.Attr.Name.UseCDATA";b:0;s:17:"HTML.BlockWrapper";s:1:"p";s:16:"HTML.CoreModules";a:7:{s:9:"Structure";b:1;s:4:"Text";b:1;s:9:"Hypertext";b:1;s:4:"List";b:1;s:22:"NonXMLCommonAttributes";b:1;s:19:"XMLCommonAttributes";b:1;s:16:"CommonAttributes";b:1;}s:18:"HTML.CustomDoctype";N;s:17:"HTML.DefinitionID";N;s:18:"HTML.DefinitionRev";i:1;s:12:"HTML.Doctype";N;s:25:"HTML.FlashAllowFullScreen";b:0;s:24:"HTML.ForbiddenAttributes";a:0:{}s:22:"HTML.ForbiddenElements";a:0:{}s:10:"HTML.Forms";b:0;s:17:"HTML.MaxImgLength";i:1200;s:13:"HTML.Nofollow";b:0;s:11:"HTML.Parent";s:3:"div";s:16:"HTML.Proprietary";b:0;s:14:"HTML.SafeEmbed";b:0;s:15:"HTML.SafeIframe";b:0;s:15:"HTML.SafeObject";b:0;s:18:"HTML.SafeScripting";a:0:{}s:11:"HTML.Strict";b:0;s:16:"HTML.TargetBlank";b:0;s:19:"HTML.TargetNoopener";b:1;s:21:"HTML.TargetNoreferrer";b:1;s:12:"HTML.TidyAdd";a:0:{}s:14:"HTML.TidyLevel";s:6:"medium";s:15:"HTML.TidyRemove";a:0:{}s:12:"HTML.Trusted";b:0;s:10:"HTML.XHTML";b:1;s:28:"Output.CommentScriptContents";b:1;s:19:"Output.FixInnerHTML";b:1;s:18:"Output.FlashCompat";b:0;s:14:"Output.Newline";N;s:15:"Output.SortAttr";b:0;s:17:"Output.TidyFormat";b:0;s:17:"Test.ForceNoIconv";b:0;s:18:"URI.AllowedSchemes";a:7:{s:4:"http";b:1;s:5:"https";b:1;s:6:"mailto";b:1;s:3:"ftp";b:1;s:4:"nntp";b:1;s:4:"news";b:1;s:3:"tel";b:1;}s:8:"URI.Base";N;s:17:"URI.DefaultScheme";s:4:"http";s:16:"URI.DefinitionID";N;s:17:"URI.DefinitionRev";i:1;s:11:"URI.Disable";b:0;s:19:"URI.DisableExternal";b:0;s:28:"URI.DisableExternalResources";b:0;s:20:"URI.DisableResources";b:0;s:8:"URI.Host";N;s:17:"URI.HostBlacklist";a:0:{}s:16:"URI.MakeAbsolute";b:0;s:9:"URI.Munge";N;s:18:"URI.MungeResources";b:0;s:18:"URI.MungeSecretKey";N;s:26:"URI.OverrideAllowedSchemes";b:1;s:20:"URI.SafeIframeRegexp";N;}s:9:"*parent";N;s:8:"*cache";N;}s:4:"info";a:140:{s:19:"Attr.AllowedClasses";i:-8;s:24:"Attr.AllowedFrameTargets";i:8;s:15:"Attr.AllowedRel";i:8;s:15:"Attr.AllowedRev";i:8;s:18:"Attr.ClassUseCDATA";i:-7;s:20:"Attr.DefaultImageAlt";i:-1;s:24:"Attr.DefaultInvalidImage";i:1;s:27:"Attr.DefaultInvalidImageAlt";i:1;s:19:"Attr.DefaultTextDir";O:8:"stdClass":2:{s:4:"type";i:1;s:7:"allowed";a:2:{s:3:"ltr";b:1;s:3:"rtl";b:1;}}s:13:"Attr.EnableID";i:7;s:17:"HTML.EnableAttrID";O:8:"stdClass":2:{s:3:"key";s:13:"Attr.EnableID";s:7:"isAlias";b:1;}s:21:"Attr.ForbiddenClasses";i:8;s:13:"Attr.ID.HTML5";i:-7;s:16:"Attr.IDBlacklist";i:9;s:22:"Attr.IDBlacklistRegexp";i:-1;s:13:"Attr.IDPrefix";i:1;s:18:"Attr.IDPrefixLocal";i:1;s:24:"AutoFormat.AutoParagraph";i:7;s:17:"AutoFormat.Custom";i:9;s:25:"AutoFormat.DisplayLinkURI";i:7;s:18:"AutoFormat.Linkify";i:7;s:33:"AutoFormat.PurifierLinkify.DocURL";i:1;s:37:"AutoFormatParam.PurifierLinkifyDocURL";O:8:"stdClass":2:{s:3:"key";s:33:"AutoFormat.PurifierLinkify.DocURL";s:7:"isAlias";b:1;}s:26:"AutoFormat.PurifierLinkify";i:7;s:32:"AutoFormat.RemoveEmpty.Predicate";i:10;s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";i:8;s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";i:7;s:22:"AutoFormat.RemoveEmpty";i:7;s:39:"AutoFormat.RemoveSpansWithoutAttributes";i:7;s:19:"CSS.AllowDuplicates";i:7;s:18:"CSS.AllowImportant";i:7;s:15:"CSS.AllowTricky";i:7;s:16:"CSS.AllowedFonts";i:-8;s:21:"CSS.AllowedProperties";i:-8;s:17:"CSS.DefinitionRev";i:5;s:23:"CSS.ForbiddenProperties";i:8;s:16:"CSS.MaxImgLength";i:-1;s:15:"CSS.Proprietary";i:7;s:11:"CSS.Trusted";i:7;s:20:"Cache.DefinitionImpl";i:-1;s:20:"Core.DefinitionCache";O:8:"stdClass":2:{s:3:"key";s:20:"Cache.DefinitionImpl";s:7:"isAlias";b:1;}s:20:"Cache.SerializerPath";i:-1;s:27:"Cache.SerializerPermissions";i:-5;s:22:"Core.AggressivelyFixLt";i:7;s:29:"Core.AggressivelyRemoveScript";i:7;s:28:"Core.AllowHostnameUnderscore";i:7;s:23:"Core.AllowParseManyTags";i:7;s:18:"Core.CollectErrors";i:7;s:18:"Core.ColorKeywords";i:10;s:30:"Core.ConvertDocumentToFragment";i:7;s:24:"Core.AcceptFullDocuments";O:8:"stdClass":2:{s:3:"key";s:30:"Core.ConvertDocumentToFragment";s:7:"isAlias";b:1;}s:36:"Core.DirectLexLineNumberSyncInterval";i:5;s:20:"Core.DisableExcludes";i:7;s:15:"Core.EnableIDNA";i:7;s:13:"Core.Encoding";i:2;s:26:"Core.EscapeInvalidChildren";i:7;s:22:"Core.EscapeInvalidTags";i:7;s:29:"Core.EscapeNonASCIICharacters";i:7;s:19:"Core.HiddenElements";i:8;s:13:"Core.Language";i:1;s:24:"Core.LegacyEntityDecoder";i:7;s:14:"Core.LexerImpl";i:-11;s:24:"Core.MaintainLineNumbers";i:-7;s:22:"Core.NormalizeNewlines";i:7;s:21:"Core.RemoveInvalidImg";i:7;s:33:"Core.RemoveProcessingInstructions";i:7;s:25:"Core.RemoveScriptContents";i:-7;s:13:"Filter.Custom";i:9;s:34:"Filter.ExtractStyleBlocks.Escaping";i:7;s:33:"Filter.ExtractStyleBlocksEscaping";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.Escaping";s:7:"isAlias";b:1;}s:38:"FilterParam.ExtractStyleBlocksEscaping";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.Escaping";s:7:"isAlias";b:1;}s:31:"Filter.ExtractStyleBlocks.Scope";i:-1;s:30:"Filter.ExtractStyleBlocksScope";O:8:"stdClass":2:{s:3:"key";s:31:"Filter.ExtractStyleBlocks.Scope";s:7:"isAlias";b:1;}s:35:"FilterParam.ExtractStyleBlocksScope";O:8:"stdClass":2:{s:3:"key";s:31:"Filter.ExtractStyleBlocks.Scope";s:7:"isAlias";b:1;}s:34:"Filter.ExtractStyleBlocks.TidyImpl";i:-11;s:38:"FilterParam.ExtractStyleBlocksTidyImpl";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.TidyImpl";s:7:"isAlias";b:1;}s:25:"Filter.ExtractStyleBlocks";i:7;s:14:"Filter.YouTube";i:7;s:12:"HTML.Allowed";i:-4;s:22:"HTML.AllowedAttributes";i:-8;s:20:"HTML.AllowedComments";i:8;s:26:"HTML.AllowedCommentsRegexp";i:-1;s:20:"HTML.AllowedElements";i:-8;s:19:"HTML.AllowedModules";i:-8;s:23:"HTML.Attr.Name.UseCDATA";i:7;s:17:"HTML.BlockWrapper";i:1;s:16:"HTML.CoreModules";i:8;s:18:"HTML.CustomDoctype";i:-1;s:17:"HTML.DefinitionID";i:-1;s:18:"HTML.DefinitionRev";i:5;s:12:"HTML.Doctype";O:8:"stdClass":3:{s:4:"type";i:1;s:10:"allow_null";b:1;s:7:"allowed";a:5:{s:22:"HTML 4.01 Transitional";b:1;s:16:"HTML 4.01 Strict";b:1;s:22:"XHTML 1.0 Transitional";b:1;s:16:"XHTML 1.0 Strict";b:1;s:9:"XHTML 1.1";b:1;}}s:25:"HTML.FlashAllowFullScreen";i:7;s:24:"HTML.ForbiddenAttributes";i:8;s:22:"HTML.ForbiddenElements";i:8;s:10:"HTML.Forms";i:7;s:17:"HTML.MaxImgLength";i:-5;s:13:"HTML.Nofollow";i:7;s:11:"HTML.Parent";i:1;s:16:"HTML.Proprietary";i:7;s:14:"HTML.SafeEmbed";i:7;s:15:"HTML.SafeIframe";i:7;s:15:"HTML.SafeObject";i:7;s:18:"HTML.SafeScripting";i:8;s:11:"HTML.Strict";i:7;s:16:"HTML.TargetBlank";i:7;s:19:"HTML.TargetNoopener";i:7;s:21:"HTML.TargetNoreferrer";i:7;s:12:"HTML.TidyAdd";i:8;s:14:"HTML.TidyLevel";O:8:"stdClass":2:{s:4:"type";i:1;s:7:"allowed";a:4:{s:4:"none";b:1;s:5:"light";b:1;s:6:"medium";b:1;s:5:"heavy";b:1;}}s:15:"HTML.TidyRemove";i:8;s:12:"HTML.Trusted";i:7;s:10:"HTML.XHTML";i:7;s:10:"Core.XHTML";O:8:"stdClass":2:{s:3:"key";s:10:"HTML.XHTML";s:7:"isAlias";b:1;}s:28:"Output.CommentScriptContents";i:7;s:26:"Core.CommentScriptContents";O:8:"stdClass":2:{s:3:"key";s:28:"Output.CommentScriptContents";s:7:"isAlias";b:1;}s:19:"Output.FixInnerHTML";i:7;s:18:"Output.FlashCompat";i:7;s:14:"Output.Newline";i:-1;s:15:"Output.SortAttr";i:7;s:17:"Output.TidyFormat";i:7;s:15:"Core.TidyFormat";O:8:"stdClass":2:{s:3:"key";s:17:"Output.TidyFormat";s:7:"isAlias";b:1;}s:17:"Test.ForceNoIconv";i:7;s:18:"URI.AllowedSchemes";i:8;s:8:"URI.Base";i:-1;s:17:"URI.DefaultScheme";i:-1;s:16:"URI.DefinitionID";i:-1;s:17:"URI.DefinitionRev";i:5;s:11:"URI.Disable";i:7;s:15:"Attr.DisableURI";O:8:"stdClass":2:{s:3:"key";s:11:"URI.Disable";s:7:"isAlias";b:1;}s:19:"URI.DisableExternal";i:7;s:28:"URI.DisableExternalResources";i:7;s:20:"URI.DisableResources";i:7;s:8:"URI.Host";i:-1;s:17:"URI.HostBlacklist";i:9;s:16:"URI.MakeAbsolute";i:7;s:9:"URI.Munge";i:-1;s:18:"URI.MungeResources";i:7;s:18:"URI.MungeSecretKey";i:-1;s:26:"URI.OverrideAllowedSchemes";i:7;s:20:"URI.SafeIframeRegexp";i:-1;}} \ No newline at end of file diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt new file mode 100644 index 0000000..0517fed --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt @@ -0,0 +1,8 @@ +Attr.AllowedClasses +TYPE: lookup/null +VERSION: 4.0.0 +DEFAULT: null +--DESCRIPTION-- +List of allowed class values in the class attribute. By default, this is null, +which means all classes are allowed. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt new file mode 100644 index 0000000..249edd6 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt @@ -0,0 +1,12 @@ +Attr.AllowedFrameTargets +TYPE: lookup +DEFAULT: array() +--DESCRIPTION-- +Lookup table of all allowed link frame targets. Some commonly used link +targets include _blank, _self, _parent and _top. Values should be +lowercase, as validation will be done in a case-sensitive manner despite +W3C's recommendation. XHTML 1.0 Strict does not permit the target attribute +so this directive will have no effect in that doctype. XHTML 1.1 does not +enable the Target module by default, you will have to manually enable it +(see the module documentation for more details.) +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt new file mode 100644 index 0000000..9a8fa6a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt @@ -0,0 +1,9 @@ +Attr.AllowedRel +TYPE: lookup +VERSION: 1.6.0 +DEFAULT: array() +--DESCRIPTION-- +List of allowed forward document relationships in the rel attribute. Common +values may be nofollow or print. By default, this is empty, meaning that no +document relationships are allowed. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt new file mode 100644 index 0000000..b017883 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt @@ -0,0 +1,9 @@ +Attr.AllowedRev +TYPE: lookup +VERSION: 1.6.0 +DEFAULT: array() +--DESCRIPTION-- +List of allowed reverse document relationships in the rev attribute. This +attribute is a bit of an edge-case; if you don't know what it is for, stay +away. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt new file mode 100644 index 0000000..e774b82 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt @@ -0,0 +1,19 @@ +Attr.ClassUseCDATA +TYPE: bool/null +DEFAULT: null +VERSION: 4.0.0 +--DESCRIPTION-- +If null, class will auto-detect the doctype and, if matching XHTML 1.1 or +XHTML 2.0, will use the restrictive NMTOKENS specification of class. Otherwise, +it will use a relaxed CDATA definition. If true, the relaxed CDATA definition +is forced; if false, the NMTOKENS definition is forced. To get behavior +of HTML Purifier prior to 4.0.0, set this directive to false. + +Some rational behind the auto-detection: +in previous versions of HTML Purifier, it was assumed that the form of +class was NMTOKENS, as specified by the XHTML Modularization (representing +XHTML 1.1 and XHTML 2.0). The DTDs for HTML 4.01 and XHTML 1.0, however +specify class as CDATA. HTML 5 effectively defines it as CDATA, but +with the additional constraint that each name should be unique (this is not +explicitly outlined in previous specifications). +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt new file mode 100644 index 0000000..533165e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt @@ -0,0 +1,11 @@ +Attr.DefaultImageAlt +TYPE: string/null +DEFAULT: null +VERSION: 3.2.0 +--DESCRIPTION-- +This is the content of the alt tag of an image if the user had not +previously specified an alt attribute. This applies to all images without +a valid alt attribute, as opposed to %Attr.DefaultInvalidImageAlt, which +only applies to invalid images, and overrides in the case of an invalid image. +Default behavior with null is to use the basename of the src tag for the alt. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt new file mode 100644 index 0000000..9eb7e38 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt @@ -0,0 +1,9 @@ +Attr.DefaultInvalidImage +TYPE: string +DEFAULT: '' +--DESCRIPTION-- +This is the default image an img tag will be pointed to if it does not have +a valid src attribute. In future versions, we may allow the image tag to +be removed completely, but due to design issues, this is not possible right +now. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt new file mode 100644 index 0000000..2f17bf4 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt @@ -0,0 +1,8 @@ +Attr.DefaultInvalidImageAlt +TYPE: string +DEFAULT: 'Invalid image' +--DESCRIPTION-- +This is the content of the alt tag of an invalid image if the user had not +previously specified an alt attribute. It has no effect when the image is +valid but there was no alt attribute present. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt new file mode 100644 index 0000000..52654b5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt @@ -0,0 +1,10 @@ +Attr.DefaultTextDir +TYPE: string +DEFAULT: 'ltr' +--DESCRIPTION-- +Defines the default text direction (ltr or rtl) of the document being +parsed. This generally is the same as the value of the dir attribute in +HTML, or ltr if that is not specified. +--ALLOWED-- +'ltr', 'rtl' +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt new file mode 100644 index 0000000..6440d21 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt @@ -0,0 +1,16 @@ +Attr.EnableID +TYPE: bool +DEFAULT: false +VERSION: 1.2.0 +--DESCRIPTION-- +Allows the ID attribute in HTML. This is disabled by default due to the +fact that without proper configuration user input can easily break the +validation of a webpage by specifying an ID that is already on the +surrounding HTML. If you don't mind throwing caution to the wind, enable +this directive, but I strongly recommend you also consider blacklisting IDs +you use (%Attr.IDBlacklist) or prefixing all user supplied IDs +(%Attr.IDPrefix). When set to true HTML Purifier reverts to the behavior of +pre-1.2.0 versions. +--ALIASES-- +HTML.EnableAttrID +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt new file mode 100644 index 0000000..f31d226 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt @@ -0,0 +1,8 @@ +Attr.ForbiddenClasses +TYPE: lookup +VERSION: 4.0.0 +DEFAULT: array() +--DESCRIPTION-- +List of forbidden class values in the class attribute. By default, this is +empty, which means that no classes are forbidden. See also %Attr.AllowedClasses. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txt new file mode 100644 index 0000000..735d4b7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txt @@ -0,0 +1,10 @@ +Attr.ID.HTML5 +TYPE: bool/null +DEFAULT: null +VERSION: 4.8.0 +--DESCRIPTION-- +In HTML5, restrictions on the format of the id attribute have been significantly +relaxed, such that any string is valid so long as it contains no spaces and +is at least one character. In lieu of a general HTML5 compatibility flag, +set this configuration directive to true to use the relaxed rules. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt new file mode 100644 index 0000000..5f2b5e3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt @@ -0,0 +1,5 @@ +Attr.IDBlacklist +TYPE: list +DEFAULT: array() +DESCRIPTION: Array of IDs not allowed in the document. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt new file mode 100644 index 0000000..6f58245 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt @@ -0,0 +1,9 @@ +Attr.IDBlacklistRegexp +TYPE: string/null +VERSION: 1.6.0 +DEFAULT: NULL +--DESCRIPTION-- +PCRE regular expression to be matched against all IDs. If the expression is +matches, the ID is rejected. Use this with care: may cause significant +degradation. ID matching is done after all other validation. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt new file mode 100644 index 0000000..cc49d43 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt @@ -0,0 +1,12 @@ +Attr.IDPrefix +TYPE: string +VERSION: 1.2.0 +DEFAULT: '' +--DESCRIPTION-- +String to prefix to IDs. If you have no idea what IDs your pages may use, +you may opt to simply add a prefix to all user-submitted ID attributes so +that they are still usable, but will not conflict with core page IDs. +Example: setting the directive to 'user_' will result in a user submitted +'foo' to become 'user_foo' Be sure to set %HTML.EnableAttrID to true +before using this. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt new file mode 100644 index 0000000..2c5924a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt @@ -0,0 +1,14 @@ +Attr.IDPrefixLocal +TYPE: string +VERSION: 1.2.0 +DEFAULT: '' +--DESCRIPTION-- +Temporary prefix for IDs used in conjunction with %Attr.IDPrefix. If you +need to allow multiple sets of user content on web page, you may need to +have a seperate prefix that changes with each iteration. This way, +seperately submitted user content displayed on the same page doesn't +clobber each other. Ideal values are unique identifiers for the content it +represents (i.e. the id of the row in the database). Be sure to add a +seperator (like an underscore) at the end. Warning: this directive will +not work unless %Attr.IDPrefix is set to a non-empty value! +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt new file mode 100644 index 0000000..d5caa1b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt @@ -0,0 +1,31 @@ +AutoFormat.AutoParagraph +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ This directive turns on auto-paragraphing, where double newlines are + converted in to paragraphs whenever possible. Auto-paragraphing: +

+
    +
  • Always applies to inline elements or text in the root node,
    • +
  • Applies to inline elements or text with double newlines in nodes + that allow paragraph tags,
    • +
  • Applies to double newlines in paragraph tags
    • +
+

+ p tags must be allowed for this directive to take effect. + We do not use br tags for paragraphing, as that is + semantically incorrect. +

+

+ To prevent auto-paragraphing as a content-producer, refrain from using + double-newlines except to specify a new paragraph or in contexts where + it has special meaning (whitespace usually has no meaning except in + tags like pre, so this should not be difficult.) To prevent + the paragraphing of inline text adjacent to block elements, wrap them + in div tags (the behavior is slightly different outside of + the root node.) +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt new file mode 100644 index 0000000..2a47648 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt @@ -0,0 +1,12 @@ +AutoFormat.Custom +TYPE: list +VERSION: 2.0.1 +DEFAULT: array() +--DESCRIPTION-- + +

+ This directive can be used to add custom auto-format injectors. + Specify an array of injector names (class name minus the prefix) + or concrete implementations. Injector class must exist. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt new file mode 100644 index 0000000..663064a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt @@ -0,0 +1,11 @@ +AutoFormat.DisplayLinkURI +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ This directive turns on the in-text display of URIs in <a> tags, and disables + those links. For example, example becomes + example (http://example.com). +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt new file mode 100644 index 0000000..3a48ba9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt @@ -0,0 +1,12 @@ +AutoFormat.Linkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ This directive turns on linkification, auto-linking http, ftp and + https URLs. a tags with the href attribute + must be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt new file mode 100644 index 0000000..db58b13 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt @@ -0,0 +1,12 @@ +AutoFormat.PurifierLinkify.DocURL +TYPE: string +VERSION: 2.0.1 +DEFAULT: '#%s' +ALIASES: AutoFormatParam.PurifierLinkifyDocURL +--DESCRIPTION-- +

+ Location of configuration documentation to link to, let %s substitute + into the configuration's namespace and directive names sans the percent + sign. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt new file mode 100644 index 0000000..7996488 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt @@ -0,0 +1,12 @@ +AutoFormat.PurifierLinkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ Internal auto-formatter that converts configuration directives in + syntax %Namespace.Directive to links. a tags + with the href attribute must be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt new file mode 100644 index 0000000..6367fe2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt @@ -0,0 +1,14 @@ +AutoFormat.RemoveEmpty.Predicate +TYPE: hash +VERSION: 4.7.0 +DEFAULT: array('colgroup' => array(), 'th' => array(), 'td' => array(), 'iframe' => array('src')) +--DESCRIPTION-- +

+ Given that an element has no contents, it will be removed by default, unless + this predicate dictates otherwise. The predicate can either be an associative + map from tag name to list of attributes that must be present for the element + to be considered preserved: thus, the default always preserves colgroup, + th and td, and also iframe if it + has a src. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt new file mode 100644 index 0000000..35c393b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt @@ -0,0 +1,11 @@ +AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions +TYPE: lookup +VERSION: 4.0.0 +DEFAULT: array('td' => true, 'th' => true) +--DESCRIPTION-- +

+ When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp + are enabled, this directive defines what HTML elements should not be + removede if they have only a non-breaking space in them. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt new file mode 100644 index 0000000..9228dee --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt @@ -0,0 +1,15 @@ +AutoFormat.RemoveEmpty.RemoveNbsp +TYPE: bool +VERSION: 4.0.0 +DEFAULT: false +--DESCRIPTION-- +

+ When enabled, HTML Purifier will treat any elements that contain only + non-breaking spaces as well as regular whitespace as empty, and remove + them when %AutoFormat.RemoveEmpty is enabled. +

+

+ See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements + that don't have this behavior applied to them. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt new file mode 100644 index 0000000..34657ba --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt @@ -0,0 +1,46 @@ +AutoFormat.RemoveEmpty +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ When enabled, HTML Purifier will attempt to remove empty elements that + contribute no semantic information to the document. The following types + of nodes will be removed: +

+
  • + Tags with no attributes and no content, and that are not empty + elements (remove <a></a> but not + <br />), and +
    • +
  • + Tags with no content, except for:
      +
    • The colgroup element, or
      • +
    • + Elements with the id or name attribute, + when those attributes are permitted on those elements. +
      • +
    • +
+

+ Please be very careful when using this functionality; while it may not + seem that empty elements contain useful information, they can alter the + layout of a document given appropriate styling. This directive is most + useful when you are processing machine-generated HTML, please avoid using + it on regular user HTML. +

+

+ Elements that contain only whitespace will be treated as empty. Non-breaking + spaces, however, do not count as whitespace. See + %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior. +

+

+ This algorithm is not perfect; you may still notice some empty tags, + particularly if a node had elements, but those elements were later removed + because they were not permitted in that context, or tags that, after + being auto-closed by another tag, where empty. This is for safety reasons + to prevent clever code from breaking validation. The general rule of thumb: + if a tag looked empty on the way in, it will get removed; if HTML Purifier + made it empty, it will stay. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt new file mode 100644 index 0000000..dde990a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt @@ -0,0 +1,11 @@ +AutoFormat.RemoveSpansWithoutAttributes +TYPE: bool +VERSION: 4.0.1 +DEFAULT: false +--DESCRIPTION-- +

+ This directive causes span tags without any attributes + to be removed. It will also remove spans that had all attributes + removed during processing. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowDuplicates.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowDuplicates.txt new file mode 100644 index 0000000..4d054b1 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowDuplicates.txt @@ -0,0 +1,11 @@ +CSS.AllowDuplicates +TYPE: bool +DEFAULT: false +VERSION: 4.8.0 +--DESCRIPTION-- +

+ By default, HTML Purifier removes duplicate CSS properties, + like color:red; color:blue. If this is set to + true, duplicate properties are allowed. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt new file mode 100644 index 0000000..b324608 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt @@ -0,0 +1,8 @@ +CSS.AllowImportant +TYPE: bool +DEFAULT: false +VERSION: 3.1.0 +--DESCRIPTION-- +This parameter determines whether or not !important cascade modifiers should +be allowed in user CSS. If false, !important will stripped. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt new file mode 100644 index 0000000..748be0e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt @@ -0,0 +1,11 @@ +CSS.AllowTricky +TYPE: bool +DEFAULT: false +VERSION: 3.1.0 +--DESCRIPTION-- +This parameter determines whether or not to allow "tricky" CSS properties and +values. Tricky CSS properties/values can drastically modify page layout or +be used for deceptive practices but do not directly constitute a security risk. +For example, display:none; is considered a tricky property that +will only be allowed if this directive is set to true. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt new file mode 100644 index 0000000..3fd4654 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt @@ -0,0 +1,12 @@ +CSS.AllowedFonts +TYPE: lookup/null +VERSION: 4.3.0 +DEFAULT: NULL +--DESCRIPTION-- +

+ Allows you to manually specify a set of allowed fonts. If + NULL, all fonts are allowed. This directive + affects generic names (serif, sans-serif, monospace, cursive, + fantasy) as well as specific font families. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt new file mode 100644 index 0000000..460112e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt @@ -0,0 +1,18 @@ +CSS.AllowedProperties +TYPE: lookup/null +VERSION: 3.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ If HTML Purifier's style attributes set is unsatisfactory for your needs, + you can overload it with your own list of tags to allow. Note that this + method is subtractive: it does its job by taking away from HTML Purifier + usual feature set, so you cannot add an attribute that HTML Purifier never + supported in the first place. +

+

+ Warning: If another directive conflicts with the + elements here, that directive will win and override. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt new file mode 100644 index 0000000..5cb7dda --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt @@ -0,0 +1,11 @@ +CSS.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt new file mode 100644 index 0000000..f1f5c5f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt @@ -0,0 +1,13 @@ +CSS.ForbiddenProperties +TYPE: lookup +VERSION: 4.2.0 +DEFAULT: array() +--DESCRIPTION-- +

+ This is the logical inverse of %CSS.AllowedProperties, and it will + override that directive or any other directive. If possible, + %CSS.AllowedProperties is recommended over this directive, + because it can sometimes be difficult to tell whether or not you've + forbidden all of the CSS properties you truly would like to disallow. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt new file mode 100644 index 0000000..7a32914 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt @@ -0,0 +1,16 @@ +CSS.MaxImgLength +TYPE: string/null +DEFAULT: '1200px' +VERSION: 3.1.1 +--DESCRIPTION-- +

+ This parameter sets the maximum allowed length on img tags, + effectively the width and height properties. + Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is + in place to prevent imagecrash attacks, disable with null at your own risk. + This directive is similar to %HTML.MaxImgLength, and both should be + concurrently edited, although there are + subtle differences in the input format (the CSS max is a number with + a unit). +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt new file mode 100644 index 0000000..148eedb --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt @@ -0,0 +1,10 @@ +CSS.Proprietary +TYPE: bool +VERSION: 3.0.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Whether or not to allow safe, proprietary CSS values. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt new file mode 100644 index 0000000..e733a61 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt @@ -0,0 +1,9 @@ +CSS.Trusted +TYPE: bool +VERSION: 4.2.1 +DEFAULT: false +--DESCRIPTION-- +Indicates whether or not the user's CSS input is trusted or not. If the +input is trusted, a more expansive set of allowed properties. See +also %HTML.Trusted. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt new file mode 100644 index 0000000..c486724 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt @@ -0,0 +1,14 @@ +Cache.DefinitionImpl +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: 'Serializer' +--DESCRIPTION-- + +This directive defines which method to use when caching definitions, +the complex data-type that makes HTML Purifier tick. Set to null +to disable caching (not recommended, as you will see a definite +performance degradation). + +--ALIASES-- +Core.DefinitionCache +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt new file mode 100644 index 0000000..5403650 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt @@ -0,0 +1,13 @@ +Cache.SerializerPath +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Absolute path with no trailing slash to store serialized definitions in. + Default is within the + HTML Purifier library inside DefinitionCache/Serializer. This + path must be writable by the webserver. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt new file mode 100644 index 0000000..2e0cc81 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt @@ -0,0 +1,16 @@ +Cache.SerializerPermissions +TYPE: int/null +VERSION: 4.3.0 +DEFAULT: 0755 +--DESCRIPTION-- + +

+ Directory permissions of the files and directories created inside + the DefinitionCache/Serializer or other custom serializer path. +

+

+ In HTML Purifier 4.8.0, this also supports NULL, + which means that no chmod'ing or directory creation shall + occur. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt new file mode 100644 index 0000000..568cbf3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt @@ -0,0 +1,18 @@ +Core.AggressivelyFixLt +TYPE: bool +VERSION: 2.1.0 +DEFAULT: true +--DESCRIPTION-- +

+ This directive enables aggressive pre-filter fixes HTML Purifier can + perform in order to ensure that open angled-brackets do not get killed + during parsing stage. Enabling this will result in two preg_replace_callback + calls and at least two preg_replace calls for every HTML document parsed; + if your users make very well-formed HTML, you can set this directive false. + This has no effect when DirectLex is used. +

+

+ Notice: This directive's default turned from false to true + in HTML Purifier 3.2.0. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt new file mode 100644 index 0000000..b2b6ab1 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt @@ -0,0 +1,16 @@ +Core.AggressivelyRemoveScript +TYPE: bool +VERSION: 4.9.0 +DEFAULT: true +--DESCRIPTION-- +

+ This directive enables aggressive pre-filter removal of + script tags. This is not necessary for security, + but it can help work around a bug in libxml where embedded + HTML elements inside script sections cause the parser to + choke. To revert to pre-4.9.0 behavior, set this to false. + This directive has no effect if %Core.Trusted is true, + %Core.RemoveScriptContents is false, or %Core.HiddenElements + does not contain script. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt new file mode 100644 index 0000000..2c910cc --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt @@ -0,0 +1,16 @@ +Core.AllowHostnameUnderscore +TYPE: bool +VERSION: 4.6.0 +DEFAULT: false +--DESCRIPTION-- +

+ By RFC 1123, underscores are not permitted in host names. + (This is in contrast to the specification for DNS, RFC + 2181, which allows underscores.) + However, most browsers do the right thing when faced with + an underscore in the host name, and so some poorly written + websites are written with the expectation this should work. + Setting this parameter to true relaxes our allowed character + check so that underscores are permitted. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowParseManyTags.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowParseManyTags.txt new file mode 100644 index 0000000..06278f8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowParseManyTags.txt @@ -0,0 +1,12 @@ +Core.AllowParseManyTags +TYPE: bool +DEFAULT: false +VERSION: 4.10.1 +--DESCRIPTION-- +

+ This directive allows parsing of many nested tags. + If you set true, relaxes any hardcoded limit from the parser. + However, in that case it may cause a Dos attack. + Be careful when enabling it. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt new file mode 100644 index 0000000..d731791 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt @@ -0,0 +1,12 @@ +Core.CollectErrors +TYPE: bool +VERSION: 2.0.0 +DEFAULT: false +--DESCRIPTION-- + +Whether or not to collect errors found while filtering the document. This +is a useful way to give feedback to your users. Warning: +Currently this feature is very patchy and experimental, with lots of +possible error messages not yet implemented. It will not cause any +problems, but it may not help your users either. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt new file mode 100644 index 0000000..a75844c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt @@ -0,0 +1,160 @@ +Core.ColorKeywords +TYPE: hash +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'aliceblue' => '#F0F8FF', + 'antiquewhite' => '#FAEBD7', + 'aqua' => '#00FFFF', + 'aquamarine' => '#7FFFD4', + 'azure' => '#F0FFFF', + 'beige' => '#F5F5DC', + 'bisque' => '#FFE4C4', + 'black' => '#000000', + 'blanchedalmond' => '#FFEBCD', + 'blue' => '#0000FF', + 'blueviolet' => '#8A2BE2', + 'brown' => '#A52A2A', + 'burlywood' => '#DEB887', + 'cadetblue' => '#5F9EA0', + 'chartreuse' => '#7FFF00', + 'chocolate' => '#D2691E', + 'coral' => '#FF7F50', + 'cornflowerblue' => '#6495ED', + 'cornsilk' => '#FFF8DC', + 'crimson' => '#DC143C', + 'cyan' => '#00FFFF', + 'darkblue' => '#00008B', + 'darkcyan' => '#008B8B', + 'darkgoldenrod' => '#B8860B', + 'darkgray' => '#A9A9A9', + 'darkgrey' => '#A9A9A9', + 'darkgreen' => '#006400', + 'darkkhaki' => '#BDB76B', + 'darkmagenta' => '#8B008B', + 'darkolivegreen' => '#556B2F', + 'darkorange' => '#FF8C00', + 'darkorchid' => '#9932CC', + 'darkred' => '#8B0000', + 'darksalmon' => '#E9967A', + 'darkseagreen' => '#8FBC8F', + 'darkslateblue' => '#483D8B', + 'darkslategray' => '#2F4F4F', + 'darkslategrey' => '#2F4F4F', + 'darkturquoise' => '#00CED1', + 'darkviolet' => '#9400D3', + 'deeppink' => '#FF1493', + 'deepskyblue' => '#00BFFF', + 'dimgray' => '#696969', + 'dimgrey' => '#696969', + 'dodgerblue' => '#1E90FF', + 'firebrick' => '#B22222', + 'floralwhite' => '#FFFAF0', + 'forestgreen' => '#228B22', + 'fuchsia' => '#FF00FF', + 'gainsboro' => '#DCDCDC', + 'ghostwhite' => '#F8F8FF', + 'gold' => '#FFD700', + 'goldenrod' => '#DAA520', + 'gray' => '#808080', + 'grey' => '#808080', + 'green' => '#008000', + 'greenyellow' => '#ADFF2F', + 'honeydew' => '#F0FFF0', + 'hotpink' => '#FF69B4', + 'indianred' => '#CD5C5C', + 'indigo' => '#4B0082', + 'ivory' => '#FFFFF0', + 'khaki' => '#F0E68C', + 'lavender' => '#E6E6FA', + 'lavenderblush' => '#FFF0F5', + 'lawngreen' => '#7CFC00', + 'lemonchiffon' => '#FFFACD', + 'lightblue' => '#ADD8E6', + 'lightcoral' => '#F08080', + 'lightcyan' => '#E0FFFF', + 'lightgoldenrodyellow' => '#FAFAD2', + 'lightgray' => '#D3D3D3', + 'lightgrey' => '#D3D3D3', + 'lightgreen' => '#90EE90', + 'lightpink' => '#FFB6C1', + 'lightsalmon' => '#FFA07A', + 'lightseagreen' => '#20B2AA', + 'lightskyblue' => '#87CEFA', + 'lightslategray' => '#778899', + 'lightslategrey' => '#778899', + 'lightsteelblue' => '#B0C4DE', + 'lightyellow' => '#FFFFE0', + 'lime' => '#00FF00', + 'limegreen' => '#32CD32', + 'linen' => '#FAF0E6', + 'magenta' => '#FF00FF', + 'maroon' => '#800000', + 'mediumaquamarine' => '#66CDAA', + 'mediumblue' => '#0000CD', + 'mediumorchid' => '#BA55D3', + 'mediumpurple' => '#9370DB', + 'mediumseagreen' => '#3CB371', + 'mediumslateblue' => '#7B68EE', + 'mediumspringgreen' => '#00FA9A', + 'mediumturquoise' => '#48D1CC', + 'mediumvioletred' => '#C71585', + 'midnightblue' => '#191970', + 'mintcream' => '#F5FFFA', + 'mistyrose' => '#FFE4E1', + 'moccasin' => '#FFE4B5', + 'navajowhite' => '#FFDEAD', + 'navy' => '#000080', + 'oldlace' => '#FDF5E6', + 'olive' => '#808000', + 'olivedrab' => '#6B8E23', + 'orange' => '#FFA500', + 'orangered' => '#FF4500', + 'orchid' => '#DA70D6', + 'palegoldenrod' => '#EEE8AA', + 'palegreen' => '#98FB98', + 'paleturquoise' => '#AFEEEE', + 'palevioletred' => '#DB7093', + 'papayawhip' => '#FFEFD5', + 'peachpuff' => '#FFDAB9', + 'peru' => '#CD853F', + 'pink' => '#FFC0CB', + 'plum' => '#DDA0DD', + 'powderblue' => '#B0E0E6', + 'purple' => '#800080', + 'rebeccapurple' => '#663399', + 'red' => '#FF0000', + 'rosybrown' => '#BC8F8F', + 'royalblue' => '#4169E1', + 'saddlebrown' => '#8B4513', + 'salmon' => '#FA8072', + 'sandybrown' => '#F4A460', + 'seagreen' => '#2E8B57', + 'seashell' => '#FFF5EE', + 'sienna' => '#A0522D', + 'silver' => '#C0C0C0', + 'skyblue' => '#87CEEB', + 'slateblue' => '#6A5ACD', + 'slategray' => '#708090', + 'slategrey' => '#708090', + 'snow' => '#FFFAFA', + 'springgreen' => '#00FF7F', + 'steelblue' => '#4682B4', + 'tan' => '#D2B48C', + 'teal' => '#008080', + 'thistle' => '#D8BFD8', + 'tomato' => '#FF6347', + 'turquoise' => '#40E0D0', + 'violet' => '#EE82EE', + 'wheat' => '#F5DEB3', + 'white' => '#FFFFFF', + 'whitesmoke' => '#F5F5F5', + 'yellow' => '#FFFF00', + 'yellowgreen' => '#9ACD32' +) +--DESCRIPTION-- + +Lookup array of color names to six digit hexadecimal number corresponding +to color, with preceding hash mark. Used when parsing colors. The lookup +is done in a case-insensitive manner. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt new file mode 100644 index 0000000..64b114f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt @@ -0,0 +1,14 @@ +Core.ConvertDocumentToFragment +TYPE: bool +DEFAULT: true +--DESCRIPTION-- + +This parameter determines whether or not the filter should convert +input that is a full document with html and body tags to a fragment +of just the contents of a body tag. This parameter is simply something +HTML Purifier can do during an edge-case: for most inputs, this +processing is not necessary. + +--ALIASES-- +Core.AcceptFullDocuments +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt new file mode 100644 index 0000000..36f16e0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt @@ -0,0 +1,17 @@ +Core.DirectLexLineNumberSyncInterval +TYPE: int +VERSION: 2.0.0 +DEFAULT: 0 +--DESCRIPTION-- + +

+ Specifies the number of tokens the DirectLex line number tracking + implementations should process before attempting to resyncronize the + current line count by manually counting all previous new-lines. When + at 0, this functionality is disabled. Lower values will decrease + performance, and this is only strictly necessary if the counting + algorithm is buggy (in which case you should report it as a bug). + This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is + not being used. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt new file mode 100644 index 0000000..1cd4c2c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt @@ -0,0 +1,14 @@ +Core.DisableExcludes +TYPE: bool +DEFAULT: false +VERSION: 4.5.0 +--DESCRIPTION-- +

+ This directive disables SGML-style exclusions, e.g. the exclusion of + <object> in any descendant of a + <pre> tag. Disabling excludes will allow some + invalid documents to pass through HTML Purifier, but HTML Purifier + will also be less likely to accidentally remove large documents during + processing. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt new file mode 100644 index 0000000..ce243c3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt @@ -0,0 +1,9 @@ +Core.EnableIDNA +TYPE: bool +DEFAULT: false +VERSION: 4.4.0 +--DESCRIPTION-- +Allows international domain names in URLs. This configuration option +requires the PEAR Net_IDNA2 module to be installed. It operates by +punycoding any internationalized host names for maximum portability. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt new file mode 100644 index 0000000..8bfb47c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt @@ -0,0 +1,15 @@ +Core.Encoding +TYPE: istring +DEFAULT: 'utf-8' +--DESCRIPTION-- +If for some reason you are unable to convert all webpages to UTF-8, you can +use this directive as a stop-gap compatibility change to let HTML Purifier +deal with non UTF-8 input. This technique has notable deficiencies: +absolutely no characters outside of the selected character encoding will be +preserved, not even the ones that have been ampersand escaped (this is due +to a UTF-8 specific feature that automatically resolves all +entities), making it pretty useless for anything except the most I18N-blind +applications, although %Core.EscapeNonASCIICharacters offers fixes this +trouble with another tradeoff. This directive only accepts ISO-8859-1 if +iconv is not enabled. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt new file mode 100644 index 0000000..a3881be --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt @@ -0,0 +1,12 @@ +Core.EscapeInvalidChildren +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +

Warning: this configuration option is no longer does anything as of 4.6.0.

+ +

When true, a child is found that is not allowed in the context of the +parent element will be transformed into text as if it were ASCII. When +false, that element and all internal tags will be dropped, though text will +be preserved. There is no option for dropping the element but preserving +child nodes.

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt new file mode 100644 index 0000000..a7a5b24 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt @@ -0,0 +1,7 @@ +Core.EscapeInvalidTags +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When true, invalid tags will be written back to the document as plain text. +Otherwise, they are silently dropped. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt new file mode 100644 index 0000000..abb4999 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt @@ -0,0 +1,13 @@ +Core.EscapeNonASCIICharacters +TYPE: bool +VERSION: 1.4.0 +DEFAULT: false +--DESCRIPTION-- +This directive overcomes a deficiency in %Core.Encoding by blindly +converting all non-ASCII characters into decimal numeric entities before +converting it to its native encoding. This means that even characters that +can be expressed in the non-UTF-8 encoding will be entity-ized, which can +be a real downer for encodings like Big5. It also assumes that the ASCII +repetoire is available, although this is the case for almost all encodings. +Anyway, use UTF-8! +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt new file mode 100644 index 0000000..915391e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt @@ -0,0 +1,19 @@ +Core.HiddenElements +TYPE: lookup +--DEFAULT-- +array ( + 'script' => true, + 'style' => true, +) +--DESCRIPTION-- + +

+ This directive is a lookup array of elements which should have their + contents removed when they are not allowed by the HTML definition. + For example, the contents of a script tag are not + normally shown in a document, so if script tags are to be removed, + their contents should be removed to. This is opposed to a b + tag, which defines some presentational changes but does not hide its + contents. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Language.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Language.txt new file mode 100644 index 0000000..233fca1 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Language.txt @@ -0,0 +1,10 @@ +Core.Language +TYPE: string +VERSION: 2.0.0 +DEFAULT: 'en' +--DESCRIPTION-- + +ISO 639 language code for localizable things in HTML Purifier to use, +which is mainly error reporting. There is currently only an English (en) +translation, so this directive is currently useless. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LegacyEntityDecoder.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LegacyEntityDecoder.txt new file mode 100644 index 0000000..392b436 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LegacyEntityDecoder.txt @@ -0,0 +1,36 @@ +Core.LegacyEntityDecoder +TYPE: bool +VERSION: 4.9.0 +DEFAULT: false +--DESCRIPTION-- +

+ Prior to HTML Purifier 4.9.0, entities were decoded by performing + a global search replace for all entities whose decoded versions + did not have special meanings under HTML, and replaced them with + their decoded versions. We would match all entities, even if they did + not have a trailing semicolon, but only if there weren't any trailing + alphanumeric characters. +

+ + + + + + +
OriginalTextAttribute
&yen;¥¥
&yen¥¥
&yena&yena&yena
&yen=¥=¥=
+

+ In HTML Purifier 4.9.0, we changed the behavior of entity parsing + to match entities that had missing trailing semicolons in less + cases, to more closely match HTML5 parsing behavior: +

+ + + + + + +
OriginalTextAttribute
&yen;¥¥
&yen¥¥
&yena¥a&yena
&yen=¥=&yen=
+

+ This flag reverts back to pre-HTML Purifier 4.9.0 behavior. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt new file mode 100644 index 0000000..8983e2c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt @@ -0,0 +1,34 @@ +Core.LexerImpl +TYPE: mixed/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ This parameter determines what lexer implementation can be used. The + valid values are: +

+
+
null
+
+ Recommended, the lexer implementation will be auto-detected based on + your PHP-version and configuration. +
+
string lexer identifier
+
+ This is a slim way of manually overridding the implementation. + Currently recognized values are: DOMLex (the default PHP5 +implementation) + and DirectLex (the default PHP4 implementation). Only use this if + you know what you are doing: usually, the auto-detection will + manage things for cases you aren't even aware of. +
+
object lexer instance
+
+ Super-advanced: you can specify your own, custom, implementation that + implements the interface defined by HTMLPurifier_Lexer. + I may remove this option simply because I don't expect anyone + to use it. +
+
+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt new file mode 100644 index 0000000..eb841a7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt @@ -0,0 +1,16 @@ +Core.MaintainLineNumbers +TYPE: bool/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ If true, HTML Purifier will add line number information to all tokens. + This is useful when error reporting is turned on, but can result in + significant performance degradation and should not be used when + unnecessary. This directive must be used with the DirectLex lexer, + as the DOMLex lexer does not (yet) support this functionality. + If the value is null, an appropriate value will be selected based + on other configuration. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt new file mode 100644 index 0000000..d77f536 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt @@ -0,0 +1,11 @@ +Core.NormalizeNewlines +TYPE: bool +VERSION: 4.2.0 +DEFAULT: true +--DESCRIPTION-- +

+ Whether or not to normalize newlines to the operating + system default. When false, HTML Purifier + will attempt to preserve mixed newline files. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt new file mode 100644 index 0000000..4070c2a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt @@ -0,0 +1,12 @@ +Core.RemoveInvalidImg +TYPE: bool +DEFAULT: true +VERSION: 1.3.0 +--DESCRIPTION-- + +

+ This directive enables pre-emptive URI checking in img + tags, as the attribute validation strategy is not authorized to + remove elements from the document. Revert to pre-1.3.0 behavior by setting to false. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt new file mode 100644 index 0000000..3397d9f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt @@ -0,0 +1,11 @@ +Core.RemoveProcessingInstructions +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +Instead of escaping processing instructions in the form <? ... +?>, remove it out-right. This may be useful if the HTML +you are validating contains XML processing instruction gunk, however, +it can also be user-unfriendly for people attempting to post PHP +snippets. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt new file mode 100644 index 0000000..a4cd966 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt @@ -0,0 +1,12 @@ +Core.RemoveScriptContents +TYPE: bool/null +DEFAULT: NULL +VERSION: 2.0.0 +DEPRECATED-VERSION: 2.1.0 +DEPRECATED-USE: Core.HiddenElements +--DESCRIPTION-- +

+ This directive enables HTML Purifier to remove not only script tags + but all of their contents. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt new file mode 100644 index 0000000..3db50ef --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt @@ -0,0 +1,11 @@ +Filter.Custom +TYPE: list +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ This directive can be used to add custom filters; it is nearly the + equivalent of the now deprecated HTMLPurifier->addFilter() + method. Specify an array of concrete implementations. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt new file mode 100644 index 0000000..16829bc --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt @@ -0,0 +1,14 @@ +Filter.ExtractStyleBlocks.Escaping +TYPE: bool +VERSION: 3.0.0 +DEFAULT: true +ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping +--DESCRIPTION-- + +

+ Whether or not to escape the dangerous characters <, > and & + as \3C, \3E and \26, respectively. This is can be safely set to false + if the contents of StyleBlocks will be placed in an external stylesheet, + where there is no risk of it being interpreted as HTML. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt new file mode 100644 index 0000000..7f95f54 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt @@ -0,0 +1,29 @@ +Filter.ExtractStyleBlocks.Scope +TYPE: string/null +VERSION: 3.0.0 +DEFAULT: NULL +ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope +--DESCRIPTION-- + +

+ If you would like users to be able to define external stylesheets, but + only allow them to specify CSS declarations for a specific node and + prevent them from fiddling with other elements, use this directive. + It accepts any valid CSS selector, and will prepend this to any + CSS declaration extracted from the document. For example, if this + directive is set to #user-content and a user uses the + selector a:hover, the final selector will be + #user-content a:hover. +

+

+ The comma shorthand may be used; consider the above example, with + #user-content, #user-content2, the final selector will + be #user-content a:hover, #user-content2 a:hover. +

+

+ Warning: It is possible for users to bypass this measure + using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML + Purifier, and I am working to get it fixed. Until then, HTML Purifier + performs a basic check to prevent this. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt new file mode 100644 index 0000000..6c231b2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt @@ -0,0 +1,16 @@ +Filter.ExtractStyleBlocks.TidyImpl +TYPE: mixed/null +VERSION: 3.1.0 +DEFAULT: NULL +ALIASES: FilterParam.ExtractStyleBlocksTidyImpl +--DESCRIPTION-- +

+ If left NULL, HTML Purifier will attempt to instantiate a csstidy + class to use for internal cleaning. This will usually be good enough. +

+

+ However, for trusted user input, you can set this to false to + disable cleaning. In addition, you can supply your own concrete implementation + of Tidy's interface to use, although I don't know why you'd want to do that. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt new file mode 100644 index 0000000..078d087 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt @@ -0,0 +1,74 @@ +Filter.ExtractStyleBlocks +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +EXTERNAL: CSSTidy +--DESCRIPTION-- +

+ This directive turns on the style block extraction filter, which removes + style blocks from input HTML, cleans them up with CSSTidy, + and places them in the StyleBlocks context variable, for further + use by you, usually to be placed in an external stylesheet, or a + style block in the head of your document. +

+

+ Sample usage: +

+
';
+?>
+
+
+
+  Filter.ExtractStyleBlocks
+body {color:#F00;} Some text';
+
+    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Filter', 'ExtractStyleBlocks', true);
+    $purifier = new HTMLPurifier($config);
+
+    $html = $purifier->purify($dirty);
+
+    // This implementation writes the stylesheets to the styles/ directory.
+    // You can also echo the styles inside the document, but it's a bit
+    // more difficult to make sure they get interpreted properly by
+    // browsers; try the usual CSS armoring techniques.
+    $styles = $purifier->context->get('StyleBlocks');
+    $dir = 'styles/';
+    if (!is_dir($dir)) mkdir($dir);
+    $hash = sha1($_GET['html']);
+    foreach ($styles as $i => $style) {
+        file_put_contents($name = $dir . $hash . "_$i");
+        echo '';
+    }
+?>
+
+
+  

+    
+  

+
+
+]]>
+

+ Warning: It is possible for a user to mount an + imagecrash attack using this CSS. Counter-measures are difficult; + it is not simply enough to limit the range of CSS lengths (using + relative lengths with many nesting levels allows for large values + to be attained without actually specifying them in the stylesheet), + and the flexible nature of selectors makes it difficult to selectively + disable lengths on image tags (HTML Purifier, however, does disable + CSS width and height in inline styling). There are probably two effective + counter measures: an explicit width and height set to auto in all + images in your document (unlikely) or the disabling of width and + height (somewhat reasonable). Whether or not these measures should be + used is left to the reader. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt new file mode 100644 index 0000000..321eaa2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt @@ -0,0 +1,16 @@ +Filter.YouTube +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ Warning: Deprecated in favor of %HTML.SafeObject and + %Output.FlashCompat (turn both on to allow YouTube videos and other + Flash content). +

+

+ This directive enables YouTube video embedding in HTML Purifier. Check + this document + on embedding videos for more information on what this filter does. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt new file mode 100644 index 0000000..0b2c106 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -0,0 +1,25 @@ +HTML.Allowed +TYPE: itext/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ This is a preferred convenience directive that combines + %HTML.AllowedElements and %HTML.AllowedAttributes. + Specify elements and attributes that are allowed using: + element1[attr1|attr2],element2.... For example, + if you would like to only allow paragraphs and links, specify + a[href],p. You can specify attributes that apply + to all elements using an asterisk, e.g. *[lang]. + You can also use newlines instead of commas to separate elements. +

+

+ Warning: + All of the constraints on the component directives are still enforced. + The syntax is a subset of TinyMCE's valid_elements + whitelist: directly copy-pasting it here will probably result in + broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes + are set, this directive has no effect. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt new file mode 100644 index 0000000..fcf093f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt @@ -0,0 +1,19 @@ +HTML.AllowedAttributes +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ If HTML Purifier's attribute set is unsatisfactory, overload it! + The syntax is "tag.attr" or "*.attr" for the global attributes + (style, id, class, dir, lang, xml:lang). +

+

+ Warning: If another directive conflicts with the + elements here, that directive will win and override. For + example, %HTML.EnableAttrID will take precedence over *.id in this + directive. You must set that directive to true before you can use + IDs at all. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt new file mode 100644 index 0000000..140e214 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt @@ -0,0 +1,10 @@ +HTML.AllowedComments +TYPE: lookup +VERSION: 4.4.0 +DEFAULT: array() +--DESCRIPTION-- +A whitelist which indicates what explicit comment bodies should be +allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp +(these directives are union'ed together, so a comment is considered +valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt new file mode 100644 index 0000000..f22e977 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt @@ -0,0 +1,15 @@ +HTML.AllowedCommentsRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +A regexp, which if it matches the body of a comment, indicates that +it should be allowed. Trailing and leading spaces are removed prior +to running this regular expression. +Warning: Make sure you specify +correct anchor metacharacters ^regex$, otherwise you may accept +comments that you did not mean to! In particular, the regex /foo|bar/ +is probably not sufficiently strict, since it also allows foobar. +See also %HTML.AllowedComments (these directives are union'ed together, +so a comment is considered valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt new file mode 100644 index 0000000..1d3fa79 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt @@ -0,0 +1,23 @@ +HTML.AllowedElements +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- +

+ If HTML Purifier's tag set is unsatisfactory for your needs, you can + overload it with your own list of tags to allow. If you change + this, you probably also want to change %HTML.AllowedAttributes; see + also %HTML.Allowed which lets you set allowed elements and + attributes at the same time. +

+

+ If you attempt to allow an element that HTML Purifier does not know + about, HTML Purifier will raise an error. You will need to manually + tell HTML Purifier about this element by using the + advanced customization features. +

+

+ Warning: If another directive conflicts with the + elements here, that directive will win and override. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt new file mode 100644 index 0000000..5a59a55 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt @@ -0,0 +1,20 @@ +HTML.AllowedModules +TYPE: lookup/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ A doctype comes with a set of usual modules to use. Without having + to mucking about with the doctypes, you can quickly activate or + disable these modules by specifying which modules you wish to allow + with this directive. This is most useful for unit testing specific + modules, although end users may find it useful for their own ends. +

+

+ If you specify a module that does not exist, the manager will silently + fail to use it, so be careful! User-defined modules are not affected + by this directive. Modules defined in %HTML.CoreModules are not + affected by this directive. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt new file mode 100644 index 0000000..151fb7b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt @@ -0,0 +1,11 @@ +HTML.Attr.Name.UseCDATA +TYPE: bool +DEFAULT: false +VERSION: 4.0.0 +--DESCRIPTION-- +The W3C specification DTD defines the name attribute to be CDATA, not ID, due +to limitations of DTD. In certain documents, this relaxed behavior is desired, +whether it is to specify duplicate names, or to specify names that would be +illegal IDs (for example, names that begin with a digit.) Set this configuration +directive to true to use the relaxed parsing rules. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt new file mode 100644 index 0000000..45ae469 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt @@ -0,0 +1,18 @@ +HTML.BlockWrapper +TYPE: string +VERSION: 1.3.0 +DEFAULT: 'p' +--DESCRIPTION-- + +

+ String name of element to wrap inline elements that are inside a block + context. This only occurs in the children of blockquote in strict mode. +

+

+ Example: by default value, + <blockquote>Foo</blockquote> would become + <blockquote><p>Foo</p></blockquote>. + The <p> tags can be replaced with whatever you desire, + as long as it is a block level element. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt new file mode 100644 index 0000000..5246188 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt @@ -0,0 +1,23 @@ +HTML.CoreModules +TYPE: lookup +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'Structure' => true, + 'Text' => true, + 'Hypertext' => true, + 'List' => true, + 'NonXMLCommonAttributes' => true, + 'XMLCommonAttributes' => true, + 'CommonAttributes' => true, +) +--DESCRIPTION-- + +

+ Certain modularized doctypes (XHTML, namely), have certain modules + that must be included for the doctype to be an conforming document + type: put those modules here. By default, XHTML's core modules + are used. You can set this to a blank array to disable core module + protection, but this is not recommended. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt new file mode 100644 index 0000000..6ed70b5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt @@ -0,0 +1,9 @@ +HTML.CustomDoctype +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +A custom doctype for power-users who defined their own document +type. This directive only applies when %HTML.Doctype is blank. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt new file mode 100644 index 0000000..103db75 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt @@ -0,0 +1,33 @@ +HTML.DefinitionID +TYPE: string/null +DEFAULT: NULL +VERSION: 2.0.0 +--DESCRIPTION-- + +

+ Unique identifier for a custom-built HTML definition. If you edit + the raw version of the HTMLDefinition, introducing changes that the + configuration object does not reflect, you must specify this variable. + If you change your custom edits, you should change this directive, or + clear your cache. Example: +

+
+$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', '1');
+$def = $config->getHTMLDefinition();
+$def->addAttribute('a', 'tabindex', 'Number');
+
+

+ In the above example, the configuration is still at the defaults, but + using the advanced API, an extra attribute has been added. The + configuration object normally has no way of knowing that this change + has taken place, so it needs an extra directive: %HTML.DefinitionID. + If someone else attempts to use the default configuration, these two + pieces of code will not clobber each other in the cache, since one has + an extra directive attached to it. +

+

+ You must specify a value to this directive to use the + advanced API features. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt new file mode 100644 index 0000000..229ae02 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt @@ -0,0 +1,16 @@ +HTML.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition specified in + %HTML.DefinitionID. This serves the same purpose: uniquely identifying + your custom definition, but this one does so in a chronological + context: revision 3 is more up-to-date then revision 2. Thus, when + this gets incremented, the cache handling is smart enough to clean + up any older revisions of your definition as well as flush the + cache. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt new file mode 100644 index 0000000..9dab497 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt @@ -0,0 +1,11 @@ +HTML.Doctype +TYPE: string/null +DEFAULT: NULL +--DESCRIPTION-- +Doctype to use during filtering. Technically speaking this is not actually +a doctype (as it does not identify a corresponding DTD), but we are using +this name for sake of simplicity. When non-blank, this will override any +older directives like %HTML.XHTML or %HTML.Strict. +--ALLOWED-- +'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1' +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt new file mode 100644 index 0000000..7878dc0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt @@ -0,0 +1,11 @@ +HTML.FlashAllowFullScreen +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit embedded Flash content from + %HTML.SafeObject to expand to the full screen. Corresponds to + the allowFullScreen parameter. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt new file mode 100644 index 0000000..57358f9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt @@ -0,0 +1,21 @@ +HTML.ForbiddenAttributes +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ While this directive is similar to %HTML.AllowedAttributes, for + forwards-compatibility with XML, this attribute has a different syntax. Instead of + tag.attr, use tag@attr. To disallow href + attributes in a tags, set this directive to + a@href. You can also disallow an attribute globally with + attr or *@attr (either syntax is fine; the latter + is provided for consistency with %HTML.AllowedAttributes). +

+

+ Warning: This directive complements %HTML.ForbiddenElements, + accordingly, check + out that directive for a discussion of why you + should think twice before using this directive. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt new file mode 100644 index 0000000..93a53e1 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt @@ -0,0 +1,20 @@ +HTML.ForbiddenElements +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ This was, perhaps, the most requested feature ever in HTML + Purifier. Please don't abuse it! This is the logical inverse of + %HTML.AllowedElements, and it will override that directive, or any + other directive. +

+

+ If possible, %HTML.Allowed is recommended over this directive, because it + can sometimes be difficult to tell whether or not you've forbidden all of + the behavior you would like to disallow. If you forbid img + with the expectation of preventing images on your site, you'll be in for + a nasty surprise when people start using the background-image + CSS property. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Forms.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Forms.txt new file mode 100644 index 0000000..4a432d8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Forms.txt @@ -0,0 +1,11 @@ +HTML.Forms +TYPE: bool +VERSION: 4.13.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit form elements in the user input, regardless of + %HTML.Trusted value. Please be very careful when using this functionality, as + enabling forms in untrusted documents may allow for phishing attacks. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt new file mode 100644 index 0000000..e424c38 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt @@ -0,0 +1,14 @@ +HTML.MaxImgLength +TYPE: int/null +DEFAULT: 1200 +VERSION: 3.1.1 +--DESCRIPTION-- +

+ This directive controls the maximum number of pixels in the width and + height attributes in img tags. This is + in place to prevent imagecrash attacks, disable with null at your own risk. + This directive is similar to %CSS.MaxImgLength, and both should be + concurrently edited, although there are + subtle differences in the input format (the HTML max is an integer). +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt new file mode 100644 index 0000000..700b309 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt @@ -0,0 +1,7 @@ +HTML.Nofollow +TYPE: bool +VERSION: 4.3.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, nofollow rel attributes are added to all outgoing links. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt new file mode 100644 index 0000000..62e8e16 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt @@ -0,0 +1,12 @@ +HTML.Parent +TYPE: string +VERSION: 1.3.0 +DEFAULT: 'div' +--DESCRIPTION-- + +

+ String name of element that HTML fragment passed to library will be + inserted in. An interesting variation would be using span as the + parent element, meaning that only inline tags would be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt new file mode 100644 index 0000000..dfb7204 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt @@ -0,0 +1,12 @@ +HTML.Proprietary +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to allow proprietary elements and attributes in your + documents, as per HTMLPurifier_HTMLModule_Proprietary. + Warning: This can cause your documents to stop + validating! +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt new file mode 100644 index 0000000..cdda09a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt @@ -0,0 +1,13 @@ +HTML.SafeEmbed +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit embed tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to embed tags. Embed is a proprietary + element and will cause your website to stop validating; you should + see if you can use %Output.FlashCompat with %HTML.SafeObject instead + first.

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt new file mode 100644 index 0000000..5eb6ec2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt @@ -0,0 +1,13 @@ +HTML.SafeIframe +TYPE: bool +VERSION: 4.4.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit iframe tags in untrusted documents. This + directive must be accompanied by a whitelist of permitted iframes, + such as %URI.SafeIframeRegexp, otherwise it will fatally error. + This directive has no effect on strict doctypes, as iframes are not + valid. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt new file mode 100644 index 0000000..ceb342e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt @@ -0,0 +1,13 @@ +HTML.SafeObject +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit object tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to object tags. You should also enable + %Output.FlashCompat in order to generate Internet Explorer + compatibility code for your object tags. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt new file mode 100644 index 0000000..5ebc7a1 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt @@ -0,0 +1,10 @@ +HTML.SafeScripting +TYPE: lookup +VERSION: 4.5.0 +DEFAULT: array() +--DESCRIPTION-- +

+ Whether or not to permit script tags to external scripts in documents. + Inline scripting is not allowed, and the script must match an explicit whitelist. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt new file mode 100644 index 0000000..a8b1de5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt @@ -0,0 +1,9 @@ +HTML.Strict +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +DEPRECATED-VERSION: 1.7.0 +DEPRECATED-USE: HTML.Doctype +--DESCRIPTION-- +Determines whether or not to use Transitional (loose) or Strict rulesets. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt new file mode 100644 index 0000000..587a167 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt @@ -0,0 +1,8 @@ +HTML.TargetBlank +TYPE: bool +VERSION: 4.4.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, target=blank attributes are added to all outgoing links. +(This includes links from an HTTPS version of a page to an HTTP version.) +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt new file mode 100644 index 0000000..dd514c0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt @@ -0,0 +1,10 @@ +--# vim: et sw=4 sts=4 +HTML.TargetNoopener +TYPE: bool +VERSION: 4.8.0 +DEFAULT: TRUE +--DESCRIPTION-- +If enabled, noopener rel attributes are added to links which have +a target attribute associated with them. This prevents malicious +destinations from overwriting the original window. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt new file mode 100644 index 0000000..cb5a0b0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt @@ -0,0 +1,9 @@ +HTML.TargetNoreferrer +TYPE: bool +VERSION: 4.8.0 +DEFAULT: TRUE +--DESCRIPTION-- +If enabled, noreferrer rel attributes are added to links which have +a target attribute associated with them. This prevents malicious +destinations from overwriting the original window. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt new file mode 100644 index 0000000..b4c271b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt @@ -0,0 +1,8 @@ +HTML.TidyAdd +TYPE: lookup +VERSION: 2.0.0 +DEFAULT: array() +--DESCRIPTION-- + +Fixes to add to the default set of Tidy fixes as per your level. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt new file mode 100644 index 0000000..4186ccd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt @@ -0,0 +1,24 @@ +HTML.TidyLevel +TYPE: string +VERSION: 2.0.0 +DEFAULT: 'medium' +--DESCRIPTION-- + +

General level of cleanliness the Tidy module should enforce. +There are four allowed values:

+
+
none
+
No extra tidying should be done
+
light
+
Only fix elements that would be discarded otherwise due to + lack of support in doctype
+
medium
+
Enforce best practices
+
heavy
+
Transform all deprecated elements and attributes to standards + compliant equivalents
+
+ +--ALLOWED-- +'none', 'light', 'medium', 'heavy' +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt new file mode 100644 index 0000000..996762b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt @@ -0,0 +1,8 @@ +HTML.TidyRemove +TYPE: lookup +VERSION: 2.0.0 +DEFAULT: array() +--DESCRIPTION-- + +Fixes to remove from the default set of Tidy fixes as per your level. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt new file mode 100644 index 0000000..1db9237 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt @@ -0,0 +1,9 @@ +HTML.Trusted +TYPE: bool +VERSION: 2.0.0 +DEFAULT: false +--DESCRIPTION-- +Indicates whether or not the user input is trusted or not. If the input is +trusted, a more expansive set of allowed tags and attributes will be used. +See also %CSS.Trusted. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt new file mode 100644 index 0000000..2a47e38 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt @@ -0,0 +1,11 @@ +HTML.XHTML +TYPE: bool +DEFAULT: true +VERSION: 1.1.0 +DEPRECATED-VERSION: 1.7.0 +DEPRECATED-USE: HTML.Doctype +--DESCRIPTION-- +Determines whether or not output is XHTML 1.0 or HTML 4.01 flavor. +--ALIASES-- +Core.XHTML +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt new file mode 100644 index 0000000..08921fd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt @@ -0,0 +1,10 @@ +Output.CommentScriptContents +TYPE: bool +VERSION: 2.0.0 +DEFAULT: true +--DESCRIPTION-- +Determines whether or not HTML Purifier should attempt to fix up the +contents of script tags for legacy browsers with comments. +--ALIASES-- +Core.CommentScriptContents +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt new file mode 100644 index 0000000..d6f0d9f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt @@ -0,0 +1,15 @@ +Output.FixInnerHTML +TYPE: bool +VERSION: 4.3.0 +DEFAULT: true +--DESCRIPTION-- +

+ If true, HTML Purifier will protect against Internet Explorer's + mishandling of the innerHTML attribute by appending + a space to any attribute that does not contain angled brackets, spaces + or quotes, but contains a backtick. This slightly changes the + semantics of any given attribute, so if this is unacceptable and + you do not use innerHTML on any of your pages, you can + turn this directive off. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt new file mode 100644 index 0000000..93398e8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt @@ -0,0 +1,11 @@ +Output.FlashCompat +TYPE: bool +VERSION: 4.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ If true, HTML Purifier will generate Internet Explorer compatibility + code for all object code. This is highly recommended if you enable + %HTML.SafeObject. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt new file mode 100644 index 0000000..79f8ad8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt @@ -0,0 +1,13 @@ +Output.Newline +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Newline string to format final output with. If left null, HTML Purifier + will auto-detect the default newline type of the system and use that; + you can manually override it here. Remember, \r\n is Windows, \r + is Mac, and \n is Unix. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt new file mode 100644 index 0000000..232b023 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt @@ -0,0 +1,14 @@ +Output.SortAttr +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ If true, HTML Purifier will sort attributes by name before writing them back + to the document, converting a tag like: <el b="" a="" c="" /> + to <el a="" b="" c="" />. This is a workaround for + a bug in FCKeditor which causes it to swap attributes order, adding noise + to text diffs. If you're not seeing this bug, chances are, you don't need + this directive. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt new file mode 100644 index 0000000..06bab00 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt @@ -0,0 +1,25 @@ +Output.TidyFormat +TYPE: bool +VERSION: 1.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Determines whether or not to run Tidy on the final output for pretty + formatting reasons, such as indentation and wrap. +

+

+ This can greatly improve readability for editors who are hand-editing + the HTML, but is by no means necessary as HTML Purifier has already + fixed all major errors the HTML may have had. Tidy is a non-default + extension, and this directive will silently fail if Tidy is not + available. +

+

+ If you are looking to make the overall look of your page's source + better, I recommend running Tidy on the entire page rather than just + user-content (after all, the indentation relative to the containing + blocks will be incorrect). +

+--ALIASES-- +Core.TidyFormat +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt new file mode 100644 index 0000000..071bc02 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt @@ -0,0 +1,7 @@ +Test.ForceNoIconv +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When set to true, HTMLPurifier_Encoder will act as if iconv does not exist +and use only pure PHP implementations. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt new file mode 100644 index 0000000..eb97307 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt @@ -0,0 +1,18 @@ +URI.AllowedSchemes +TYPE: lookup +--DEFAULT-- +array ( + 'http' => true, + 'https' => true, + 'mailto' => true, + 'ftp' => true, + 'nntp' => true, + 'news' => true, + 'tel' => true, +) +--DESCRIPTION-- +Whitelist that defines the schemes that a URI is allowed to have. This +prevents XSS attacks from using pseudo-schemes like javascript or mocha. +There is also support for the data and file +URI schemes, but they are not enabled by default. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt new file mode 100644 index 0000000..876f068 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt @@ -0,0 +1,17 @@ +URI.Base +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ The base URI is the URI of the document this purified HTML will be + inserted into. This information is important if HTML Purifier needs + to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute + is on. You may use a non-absolute URI for this value, but behavior + may vary (%URI.MakeAbsolute deals nicely with both absolute and + relative paths, but forwards-compatibility is not guaranteed). + Warning: If set, the scheme on this URI + overrides the one specified by %URI.DefaultScheme. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt new file mode 100644 index 0000000..834bc08 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt @@ -0,0 +1,15 @@ +URI.DefaultScheme +TYPE: string/null +DEFAULT: 'http' +--DESCRIPTION-- + +

+ Defines through what scheme the output will be served, in order to + select the proper object validator when no scheme information is present. +

+ +

+ Starting with HTML Purifier 4.9.0, the default scheme can be null, in + which case we reject all URIs which do not have explicit schemes. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt new file mode 100644 index 0000000..f05312b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt @@ -0,0 +1,11 @@ +URI.DefinitionID +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Unique identifier for a custom-built URI definition. If you want + to add custom URIFilters, you must specify this value. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt new file mode 100644 index 0000000..80cfea9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt @@ -0,0 +1,11 @@ +URI.DefinitionRev +TYPE: int +VERSION: 2.1.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt new file mode 100644 index 0000000..71ce025 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt @@ -0,0 +1,14 @@ +URI.Disable +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Disables all URIs in all forms. Not sure why you'd want to do that + (after all, the Internet's founded on the notion of a hyperlink). +

+ +--ALIASES-- +Attr.DisableURI +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt new file mode 100644 index 0000000..13c122c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt @@ -0,0 +1,11 @@ +URI.DisableExternal +TYPE: bool +VERSION: 1.2.0 +DEFAULT: false +--DESCRIPTION-- +Disables links to external websites. This is a highly effective anti-spam +and anti-pagerank-leech measure, but comes at a hefty price: nolinks or +images outside of your domain will be allowed. Non-linkified URIs will +still be preserved. If you want to be able to link to subdomains or use +absolute URIs, specify %URI.Host for your website. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt new file mode 100644 index 0000000..abcc1ef --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt @@ -0,0 +1,13 @@ +URI.DisableExternalResources +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- +Disables the embedding of external resources, preventing users from +embedding things like images from other hosts. This prevents access +tracking (good for email viewers), bandwidth leeching, cross-site request +forging, goatse.cx posting, and other nasties, but also results in a loss +of end-user functionality (they can't directly post a pic they posted from +Flickr anymore). Use it if you don't have a robust user-content moderation +team. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt new file mode 100644 index 0000000..f891de4 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt @@ -0,0 +1,15 @@ +URI.DisableResources +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ Disables embedding resources, essentially meaning no pictures. You can + still link to them though. See %URI.DisableExternalResources for why + this might be a good idea. +

+

+ Note: While this directive has been available since 1.3.0, + it didn't actually start doing anything until 4.2.0. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt new file mode 100644 index 0000000..ee83b12 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt @@ -0,0 +1,19 @@ +URI.Host +TYPE: string/null +VERSION: 1.2.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Defines the domain name of the server, so we can determine whether or + an absolute URI is from your website or not. Not strictly necessary, + as users should be using relative URIs to reference resources on your + website. It will, however, let you use absolute URIs to link to + subdomains of the domain you post here: i.e. example.com will allow + sub.example.com. However, higher up domains will still be excluded: + if you set %URI.Host to sub.example.com, example.com will be blocked. + Note: This directive overrides %URI.Base because + a given page may be on a sub-domain, but you wish HTML Purifier to be + more relaxed and allow some of the parent domains too. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt new file mode 100644 index 0000000..0b6df76 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt @@ -0,0 +1,9 @@ +URI.HostBlacklist +TYPE: list +VERSION: 1.3.0 +DEFAULT: array() +--DESCRIPTION-- +List of strings that are forbidden in the host of any URI. Use it to kill +domain names of spam, etc. Note that it will catch anything in the domain, +so moo.com will catch moo.com.example.com. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt new file mode 100644 index 0000000..4214900 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt @@ -0,0 +1,13 @@ +URI.MakeAbsolute +TYPE: bool +VERSION: 2.1.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Converts all URIs into absolute forms. This is useful when the HTML + being filtered assumes a specific base path, but will actually be + viewed in a different context (and setting an alternate base URI is + not possible). %URI.Base must be set for this directive to work. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt new file mode 100644 index 0000000..58c81dc --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt @@ -0,0 +1,83 @@ +URI.Munge +TYPE: string/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Munges all browsable (usually http, https and ftp) + absolute URIs into another URI, usually a URI redirection service. + This directive accepts a URI, formatted with a %s where + the url-encoded original URI should be inserted (sample: + http://www.google.com/url?q=%s). +

+

+ Uses for this directive: +

+
    +
  • + Prevent PageRank leaks, while being fairly transparent + to users (you may also want to add some client side JavaScript to + override the text in the statusbar). Notice: + Many security experts believe that this form of protection does not deter spam-bots. +
    • +
  • + Redirect users to a splash page telling them they are leaving your + website. While this is poor usability practice, it is often mandated + in corporate environments. +
    • +
+

+ Prior to HTML Purifier 3.1.1, this directive also enabled the munging + of browsable external resources, which could break things if your redirection + script was a splash page or used meta tags. To revert to + previous behavior, please use %URI.MungeResources. +

+

+ You may want to also use %URI.MungeSecretKey along with this directive + in order to enforce what URIs your redirector script allows. Open + redirector scripts can be a security risk and negatively affect the + reputation of your domain name. +

+

+ Starting with HTML Purifier 3.1.1, there is also these substitutions: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
KeyDescriptionExample <a href="">
%r1 - The URI embeds a resource
(blank) - The URI is merely a link
%nThe name of the tag this URI came froma
%mThe name of the attribute this URI came fromhref
%pThe name of the CSS property this URI came from, or blank if irrelevant
+

+ Admittedly, these letters are somewhat arbitrary; the only stipulation + was that they couldn't be a through f. r is for resource (I would have preferred + e, but you take what you can get), n is for name, m + was picked because it came after n (and I couldn't use a), p is for + property. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt new file mode 100644 index 0000000..6fce0fd --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt @@ -0,0 +1,17 @@ +URI.MungeResources +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ If true, any URI munging directives like %URI.Munge + will also apply to embedded resources, such as <img src="">. + Be careful enabling this directive if you have a redirector script + that does not use the Location HTTP header; all of your images + and other embedded resources will break. +

+

+ Warning: It is strongly advised you use this in conjunction + %URI.MungeSecretKey to mitigate the security risk of an open redirector. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt new file mode 100644 index 0000000..1e17c1d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt @@ -0,0 +1,30 @@ +URI.MungeSecretKey +TYPE: string/null +VERSION: 3.1.1 +DEFAULT: NULL +--DESCRIPTION-- +

+ This directive enables secure checksum generation along with %URI.Munge. + It should be set to a secure key that is not shared with anyone else. + The checksum can be placed in the URI using %t. Use of this checksum + affords an additional level of protection by allowing a redirector + to check if a URI has passed through HTML Purifier with this line: +

+ +
$checksum === hash_hmac("sha256", $url, $secret_key)
+ +

+ If the output is TRUE, the redirector script should accept the URI. +

+ +

+ Please note that it would still be possible for an attacker to procure + secure hashes en-mass by abusing your website's Preview feature or the + like, but this service affords an additional level of protection + that should be combined with website blacklisting. +

+ +

+ Remember this has no effect if %URI.Munge is not on. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt new file mode 100644 index 0000000..23331a4 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt @@ -0,0 +1,9 @@ +URI.OverrideAllowedSchemes +TYPE: bool +DEFAULT: true +--DESCRIPTION-- +If this is set to true (which it is by default), you can override +%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the +registry. If false, you will also have to update that directive in order +to add more schemes. +--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt new file mode 100644 index 0000000..7908483 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt @@ -0,0 +1,22 @@ +URI.SafeIframeRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +

+ A PCRE regular expression that will be matched against an iframe URI. This is + a relatively inflexible scheme, but works well enough for the most common + use-case of iframes: embedded video. This directive only has an effect if + %HTML.SafeIframe is enabled. Here are some example values: +

+
    +
  • %^http://www.youtube.com/embed/% - Allow YouTube videos
    • +
  • %^http://player.vimeo.com/video/% - Allow Vimeo videos
    • +
  • %^http://(www.youtube.com/embed/|player.vimeo.com/video/)% - Allow both
    • +
+

+ Note that this directive does not give you enough granularity to, say, disable + all autoplay videos. Pipe up on the HTML Purifier forums if this + is a capability you want. +

+--# vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini new file mode 100644 index 0000000..5de4505 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini @@ -0,0 +1,3 @@ +name = "HTML Purifier" + +; vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ContentSets.php b/software/HTMLPurifier/HTMLPurifier/ContentSets.php new file mode 100644 index 0000000..543e3f8 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ContentSets.php @@ -0,0 +1,170 @@ + true) indexed by name. + * @type array + * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets + */ + public $lookup = array(); + + /** + * Synchronized list of defined content sets (keys of info). + * @type array + */ + protected $keys = array(); + /** + * Synchronized list of defined content values (values of info). + * @type array + */ + protected $values = array(); + + /** + * Merges in module's content sets, expands identifiers in the content + * sets and populates the keys, values and lookup member variables. + * @param HTMLPurifier_HTMLModule[] $modules List of HTMLPurifier_HTMLModule + */ + public function __construct($modules) + { + if (!is_array($modules)) { + $modules = array($modules); + } + // populate content_sets based on module hints + // sorry, no way of overloading + foreach ($modules as $module) { + foreach ($module->content_sets as $key => $value) { + $temp = $this->convertToLookup($value); + if (isset($this->lookup[$key])) { + // add it into the existing content set + $this->lookup[$key] = array_merge($this->lookup[$key], $temp); + } else { + $this->lookup[$key] = $temp; + } + } + } + $old_lookup = false; + while ($old_lookup !== $this->lookup) { + $old_lookup = $this->lookup; + foreach ($this->lookup as $i => $set) { + $add = array(); + foreach ($set as $element => $x) { + if (isset($this->lookup[$element])) { + $add += $this->lookup[$element]; + unset($this->lookup[$i][$element]); + } + } + $this->lookup[$i] += $add; + } + } + + foreach ($this->lookup as $key => $lookup) { + $this->info[$key] = implode(' | ', array_keys($lookup)); + } + $this->keys = array_keys($this->info); + $this->values = array_values($this->info); + } + + /** + * Accepts a definition; generates and assigns a ChildDef for it + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef reference + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + */ + public function generateChildDef(&$def, $module) + { + if (!empty($def->child)) { // already done! + return; + } + $content_model = $def->content_model; + if (is_string($content_model)) { + // Assume that $this->keys is alphanumeric + $def->content_model = preg_replace_callback( + '/\b(' . implode('|', $this->keys) . ')\b/', + array($this, 'generateChildDefCallback'), + $content_model + ); + //$def->content_model = str_replace( + // $this->keys, $this->values, $content_model); + } + $def->child = $this->getChildDef($def, $module); + } + + public function generateChildDefCallback($matches) + { + return $this->info[$matches[0]]; + } + + /** + * Instantiates a ChildDef based on content_model and content_model_type + * member variables in HTMLPurifier_ElementDef + * @note This will also defer to modules for custom HTMLPurifier_ChildDef + * subclasses that need content set expansion + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef to have ChildDef extracted + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + * @return HTMLPurifier_ChildDef corresponding to ElementDef + */ + public function getChildDef($def, $module) + { + $value = $def->content_model; + if (is_object($value)) { + trigger_error( + 'Literal object child definitions should be stored in '. + 'ElementDef->child not ElementDef->content_model', + E_USER_NOTICE + ); + return $value; + } + switch ($def->content_model_type) { + case 'required': + return new HTMLPurifier_ChildDef_Required($value); + case 'optional': + return new HTMLPurifier_ChildDef_Optional($value); + case 'empty': + return new HTMLPurifier_ChildDef_Empty(); + case 'custom': + return new HTMLPurifier_ChildDef_Custom($value); + } + // defer to its module + $return = false; + if ($module->defines_child_def) { // save a func call + $return = $module->getChildDef($def); + } + if ($return !== false) { + return $return; + } + // error-out + trigger_error( + 'Could not determine which ChildDef class to instantiate', + E_USER_ERROR + ); + return false; + } + + /** + * Converts a string list of elements separated by pipes into + * a lookup array. + * @param string $string List of elements + * @return array Lookup array of elements + */ + protected function convertToLookup($string) + { + $array = explode('|', str_replace(' ', '', $string)); + $ret = array(); + foreach ($array as $k) { + $ret[$k] = true; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Context.php b/software/HTMLPurifier/HTMLPurifier/Context.php new file mode 100644 index 0000000..00e509c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Context.php @@ -0,0 +1,95 @@ +_storage)) { + trigger_error( + "Name $name produces collision, cannot re-register", + E_USER_ERROR + ); + return; + } + $this->_storage[$name] =& $ref; + } + + /** + * Retrieves a variable reference from the context. + * @param string $name String name + * @param bool $ignore_error Boolean whether or not to ignore error + * @return mixed + */ + public function &get($name, $ignore_error = false) + { + if (!array_key_exists($name, $this->_storage)) { + if (!$ignore_error) { + trigger_error( + "Attempted to retrieve non-existent variable $name", + E_USER_ERROR + ); + } + $var = null; // so we can return by reference + return $var; + } + return $this->_storage[$name]; + } + + /** + * Destroys a variable in the context. + * @param string $name String name + */ + public function destroy($name) + { + if (!array_key_exists($name, $this->_storage)) { + trigger_error( + "Attempted to destroy non-existent variable $name", + E_USER_ERROR + ); + return; + } + unset($this->_storage[$name]); + } + + /** + * Checks whether or not the variable exists. + * @param string $name String name + * @return bool + */ + public function exists($name) + { + return array_key_exists($name, $this->_storage); + } + + /** + * Loads a series of variables from an associative array + * @param array $context_array Assoc array of variables to load + */ + public function loadArray($context_array) + { + foreach ($context_array as $key => $discard) { + $this->register($key, $context_array[$key]); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Definition.php b/software/HTMLPurifier/HTMLPurifier/Definition.php new file mode 100644 index 0000000..bc6d433 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Definition.php @@ -0,0 +1,55 @@ +setup) { + return; + } + $this->setup = true; + $this->doSetup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache.php b/software/HTMLPurifier/HTMLPurifier/DefinitionCache.php new file mode 100644 index 0000000..9aa8ff3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCache.php @@ -0,0 +1,129 @@ +type = $type; + } + + /** + * Generates a unique identifier for a particular configuration + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @return string + */ + public function generateKey($config) + { + return $config->version . ',' . // possibly replace with function calls + $config->getBatchSerial($this->type) . ',' . + $config->get($this->type . '.DefinitionRev'); + } + + /** + * Tests whether or not a key is old with respect to the configuration's + * version and revision number. + * @param string $key Key to test + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config to test against + * @return bool + */ + public function isOld($key, $config) + { + if (substr_count($key, ',') < 2) { + return true; + } + list($version, $hash, $revision) = explode(',', $key, 3); + $compare = version_compare($version, $config->version); + // version mismatch, is always old + if ($compare != 0) { + return true; + } + // versions match, ids match, check revision number + if ($hash == $config->getBatchSerial($this->type) && + $revision < $config->get($this->type . '.DefinitionRev')) { + return true; + } + return false; + } + + /** + * Checks if a definition's type jives with the cache's type + * @note Throws an error on failure + * @param HTMLPurifier_Definition $def Definition object to check + * @return bool true if good, false if not + */ + public function checkDefType($def) + { + if ($def->type !== $this->type) { + trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}"); + return false; + } + return true; + } + + /** + * Adds a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function add($def, $config); + + /** + * Unconditionally saves a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function set($def, $config); + + /** + * Replace an object in the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function replace($def, $config); + + /** + * Retrieves a definition object from the cache + * @param HTMLPurifier_Config $config + */ + abstract public function get($config); + + /** + * Removes a definition object to the cache + * @param HTMLPurifier_Config $config + */ + abstract public function remove($config); + + /** + * Clears all objects from cache + * @param HTMLPurifier_Config $config + */ + abstract public function flush($config); + + /** + * Clears all expired (older version or revision) objects from cache + * @note Be careful implementing this method as flush. Flush must + * not interfere with other Definition types, and cleanup() + * should not be repeatedly called by userland code. + * @param HTMLPurifier_Config $config + */ + abstract public function cleanup($config); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php new file mode 100644 index 0000000..b57a51b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php @@ -0,0 +1,112 @@ +copy(); + // reference is necessary for mocks in PHP 4 + $decorator->cache =& $cache; + $decorator->type = $cache->type; + return $decorator; + } + + /** + * Cross-compatible clone substitute + * @return HTMLPurifier_DefinitionCache_Decorator + */ + public function copy() + { + return new HTMLPurifier_DefinitionCache_Decorator(); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { + return $this->cache->add($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + return $this->cache->set($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + return $this->cache->replace($def, $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + return $this->cache->get($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function remove($config) + { + return $this->cache->remove($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function flush($config) + { + return $this->cache->flush($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function cleanup($config) + { + return $this->cache->cleanup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php new file mode 100644 index 0000000..4991777 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php @@ -0,0 +1,78 @@ +definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + $status = parent::set($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + $status = parent::replace($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + $key = $this->generateKey($config); + if (isset($this->definitions[$key])) { + return $this->definitions[$key]; + } + $this->definitions[$key] = parent::get($config); + return $this->definitions[$key]; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in new file mode 100644 index 0000000..b1fec8d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in @@ -0,0 +1,82 @@ +checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function set($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function replace($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool|HTMLPurifier_Config + */ + public function get($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unserialize(file_get_contents($file)); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function remove($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unlink($file); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function flush($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + // Apparently, on some versions of PHP, readdir will return + // an empty string if you pass an invalid argument to readdir. + // So you need this test. See #49. + if (false === $dh) { + return false; + } + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + unlink($dir . '/' . $filename); + } + closedir($dh); + return true; + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function cleanup($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + // See #49 (and above). + if (false === $dh) { + return false; + } + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + $key = substr($filename, 0, strlen($filename) - 4); + if ($this->isOld($key, $config)) { + unlink($dir . '/' . $filename); + } + } + closedir($dh); + return true; + } + + /** + * Generates the file path to the serial file corresponding to + * the configuration and definition name + * @param HTMLPurifier_Config $config + * @return string + * @todo Make protected + */ + public function generateFilePath($config) + { + $key = $this->generateKey($config); + return $this->generateDirectoryPath($config) . '/' . $key . '.ser'; + } + + /** + * Generates the path to the directory contain this cache's serial files + * @param HTMLPurifier_Config $config + * @return string + * @note No trailing slash + * @todo Make protected + */ + public function generateDirectoryPath($config) + { + $base = $this->generateBaseDirectoryPath($config); + return $base . '/' . $this->type; + } + + /** + * Generates path to base directory that contains all definition type + * serials + * @param HTMLPurifier_Config $config + * @return mixed|string + * @todo Make protected + */ + public function generateBaseDirectoryPath($config) + { + $base = $config->get('Cache.SerializerPath'); + $base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base; + return $base; + } + + /** + * Convenience wrapper function for file_put_contents + * @param string $file File name to write to + * @param string $data Data to write into file + * @param HTMLPurifier_Config $config + * @return int|bool Number of bytes written if success, or false if failure. + */ + private function _write($file, $data, $config) + { + $result = file_put_contents($file, $data); + if ($result !== false) { + // set permissions of the new file (no execute) + $chmod = $config->get('Cache.SerializerPermissions'); + if ($chmod !== null) { + chmod($file, $chmod & 0666); + } + } + return $result; + } + + /** + * Prepares the directory that this type stores the serials in + * @param HTMLPurifier_Config $config + * @return bool True if successful + */ + private function _prepareDir($config) + { + $directory = $this->generateDirectoryPath($config); + $chmod = $config->get('Cache.SerializerPermissions'); + if ($chmod === null) { + if (!@mkdir($directory) && !is_dir($directory)) { + trigger_error( + 'Could not create directory ' . $directory . '', + E_USER_WARNING + ); + return false; + } + return true; + } + if (!is_dir($directory)) { + $base = $this->generateBaseDirectoryPath($config); + if (!is_dir($base)) { + trigger_error( + 'Base directory ' . $base . ' does not exist, + please create or change using %Cache.SerializerPath', + E_USER_WARNING + ); + return false; + } elseif (!$this->_testPermissions($base, $chmod)) { + return false; + } + if (!@mkdir($directory, $chmod) && !is_dir($directory)) { + trigger_error( + 'Could not create directory ' . $directory . '', + E_USER_WARNING + ); + return false; + } + if (!$this->_testPermissions($directory, $chmod)) { + return false; + } + } elseif (!$this->_testPermissions($directory, $chmod)) { + return false; + } + return true; + } + + /** + * Tests permissions on a directory and throws out friendly + * error messages and attempts to chmod it itself if possible + * @param string $dir Directory path + * @param int $chmod Permissions + * @return bool True if directory is writable + */ + private function _testPermissions($dir, $chmod) + { + // early abort, if it is writable, everything is hunky-dory + if (is_writable($dir)) { + return true; + } + if (!is_dir($dir)) { + // generally, you'll want to handle this beforehand + // so a more specific error message can be given + trigger_error( + 'Directory ' . $dir . ' does not exist', + E_USER_WARNING + ); + return false; + } + if (function_exists('posix_getuid') && $chmod !== null) { + // POSIX system, we can give more specific advice + if (fileowner($dir) === posix_getuid()) { + // we can chmod it ourselves + $chmod = $chmod | 0700; + if (chmod($dir, $chmod)) { + return true; + } + } elseif (filegroup($dir) === posix_getgid()) { + $chmod = $chmod | 0070; + } else { + // PHP's probably running as nobody, so we'll + // need to give global permissions + $chmod = $chmod | 0777; + } + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please chmod to ' . decoct($chmod), + E_USER_WARNING + ); + } else { + // generic error message + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please alter file permissions', + E_USER_WARNING + ); + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.15.0,f474c0a322b208e83d22d3aef33ecb184bc71d31,1.ser b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.15.0,f474c0a322b208e83d22d3aef33ecb184bc71d31,1.ser new file mode 100644 index 0000000..931f16a Binary files /dev/null and b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.15.0,f474c0a322b208e83d22d3aef33ecb184bc71d31,1.ser differ diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README new file mode 100644 index 0000000..2e35c1c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README @@ -0,0 +1,3 @@ +This is a dummy file to prevent Git from ignoring this empty directory. + + vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php b/software/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php new file mode 100644 index 0000000..fd1cc9b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php @@ -0,0 +1,106 @@ + array()); + + /** + * @type array + */ + protected $implementations = array(); + + /** + * @type HTMLPurifier_DefinitionCache_Decorator[] + */ + protected $decorators = array(); + + /** + * Initialize default decorators + */ + public function setup() + { + $this->addDecorator('Cleanup'); + } + + /** + * Retrieves an instance of global definition cache factory. + * @param HTMLPurifier_DefinitionCacheFactory $prototype + * @return HTMLPurifier_DefinitionCacheFactory + */ + public static function instance($prototype = null) + { + static $instance; + if ($prototype !== null) { + $instance = $prototype; + } elseif ($instance === null || $prototype === true) { + $instance = new HTMLPurifier_DefinitionCacheFactory(); + $instance->setup(); + } + return $instance; + } + + /** + * Registers a new definition cache object + * @param string $short Short name of cache object, for reference + * @param string $long Full class name of cache object, for construction + */ + public function register($short, $long) + { + $this->implementations[$short] = $long; + } + + /** + * Factory method that creates a cache object based on configuration + * @param string $type Name of definitions handled by cache + * @param HTMLPurifier_Config $config Config instance + * @return mixed + */ + public function create($type, $config) + { + $method = $config->get('Cache.DefinitionImpl'); + if ($method === null) { + return new HTMLPurifier_DefinitionCache_Null($type); + } + if (!empty($this->caches[$method][$type])) { + return $this->caches[$method][$type]; + } + if (isset($this->implementations[$method]) && + class_exists($class = $this->implementations[$method], false)) { + $cache = new $class($type); + } else { + if ($method != 'Serializer') { + trigger_error("Unrecognized DefinitionCache $method, using Serializer instead", E_USER_WARNING); + } + $cache = new HTMLPurifier_DefinitionCache_Serializer($type); + } + foreach ($this->decorators as $decorator) { + $new_cache = $decorator->decorate($cache); + // prevent infinite recursion in PHP 4 + unset($cache); + $cache = $new_cache; + } + $this->caches[$method][$type] = $cache; + return $this->caches[$method][$type]; + } + + /** + * Registers a decorator to add to all new cache objects + * @param HTMLPurifier_DefinitionCache_Decorator|string $decorator An instance or the name of a decorator + */ + public function addDecorator($decorator) + { + if (is_string($decorator)) { + $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator"; + $decorator = new $class; + } + $this->decorators[$decorator->name] = $decorator; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Doctype.php b/software/HTMLPurifier/HTMLPurifier/Doctype.php new file mode 100644 index 0000000..4acd06e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Doctype.php @@ -0,0 +1,73 @@ +renderDoctype. + * If structure changes, please update that function. + */ +class HTMLPurifier_Doctype +{ + /** + * Full name of doctype + * @type string + */ + public $name; + + /** + * List of standard modules (string identifiers or literal objects) + * that this doctype uses + * @type array + */ + public $modules = array(); + + /** + * List of modules to use for tidying up code + * @type array + */ + public $tidyModules = array(); + + /** + * Is the language derived from XML (i.e. XHTML)? + * @type bool + */ + public $xml = true; + + /** + * List of aliases for this doctype + * @type array + */ + public $aliases = array(); + + /** + * Public DTD identifier + * @type string + */ + public $dtdPublic; + + /** + * System DTD identifier + * @type string + */ + public $dtdSystem; + + public function __construct( + $name = null, + $xml = true, + $modules = array(), + $tidyModules = array(), + $aliases = array(), + $dtd_public = null, + $dtd_system = null + ) { + $this->name = $name; + $this->xml = $xml; + $this->modules = $modules; + $this->tidyModules = $tidyModules; + $this->aliases = $aliases; + $this->dtdPublic = $dtd_public; + $this->dtdSystem = $dtd_system; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php b/software/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php new file mode 100644 index 0000000..acc1d64 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php @@ -0,0 +1,142 @@ +doctypes[$doctype->name] = $doctype; + $name = $doctype->name; + // hookup aliases + foreach ($doctype->aliases as $alias) { + if (isset($this->doctypes[$alias])) { + continue; + } + $this->aliases[$alias] = $name; + } + // remove old aliases + if (isset($this->aliases[$name])) { + unset($this->aliases[$name]); + } + return $doctype; + } + + /** + * Retrieves reference to a doctype of a certain name + * @note This function resolves aliases + * @note When possible, use the more fully-featured make() + * @param string $doctype Name of doctype + * @return HTMLPurifier_Doctype Editable doctype object + */ + public function get($doctype) + { + if (isset($this->aliases[$doctype])) { + $doctype = $this->aliases[$doctype]; + } + if (!isset($this->doctypes[$doctype])) { + trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist', E_USER_ERROR); + $anon = new HTMLPurifier_Doctype($doctype); + return $anon; + } + return $this->doctypes[$doctype]; + } + + /** + * Creates a doctype based on a configuration object, + * will perform initialization on the doctype + * @note Use this function to get a copy of doctype that config + * can hold on to (this is necessary in order to tell + * Generator whether or not the current document is XML + * based or not). + * @param HTMLPurifier_Config $config + * @return HTMLPurifier_Doctype + */ + public function make($config) + { + return clone $this->get($this->getDoctypeFromConfig($config)); + } + + /** + * Retrieves the doctype from the configuration object + * @param HTMLPurifier_Config $config + * @return string + */ + public function getDoctypeFromConfig($config) + { + // recommended test + $doctype = $config->get('HTML.Doctype'); + if (!empty($doctype)) { + return $doctype; + } + $doctype = $config->get('HTML.CustomDoctype'); + if (!empty($doctype)) { + return $doctype; + } + // backwards-compatibility + if ($config->get('HTML.XHTML')) { + $doctype = 'XHTML 1.0'; + } else { + $doctype = 'HTML 4.01'; + } + if ($config->get('HTML.Strict')) { + $doctype .= ' Strict'; + } else { + $doctype .= ' Transitional'; + } + return $doctype; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ElementDef.php b/software/HTMLPurifier/HTMLPurifier/ElementDef.php new file mode 100644 index 0000000..57cfd2b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ElementDef.php @@ -0,0 +1,216 @@ +setup(), this array may also + * contain an array at index 0 that indicates which attribute + * collections to load into the full array. It may also + * contain string indentifiers in lieu of HTMLPurifier_AttrDef, + * see HTMLPurifier_AttrTypes on how they are expanded during + * HTMLPurifier_HTMLDefinition->setup() processing. + */ + public $attr = array(); + + // XXX: Design note: currently, it's not possible to override + // previously defined AttrTransforms without messing around with + // the final generated config. This is by design; a previous version + // used an associated list of attr_transform, but it was extremely + // easy to accidentally override other attribute transforms by + // forgetting to specify an index (and just using 0.) While we + // could check this by checking the index number and complaining, + // there is a second problem which is that it is not at all easy to + // tell when something is getting overridden. Combine this with a + // codebase where this isn't really being used, and it's perfect for + // nuking. + + /** + * List of tags HTMLPurifier_AttrTransform to be done before validation. + * @type array + */ + public $attr_transform_pre = array(); + + /** + * List of tags HTMLPurifier_AttrTransform to be done after validation. + * @type array + */ + public $attr_transform_post = array(); + + /** + * HTMLPurifier_ChildDef of this tag. + * @type HTMLPurifier_ChildDef + */ + public $child; + + /** + * Abstract string representation of internal ChildDef rules. + * @see HTMLPurifier_ContentSets for how this is parsed and then transformed + * into an HTMLPurifier_ChildDef. + * @warning This is a temporary variable that is not available after + * being processed by HTMLDefinition + * @type string + */ + public $content_model; + + /** + * Value of $child->type, used to determine which ChildDef to use, + * used in combination with $content_model. + * @warning This must be lowercase + * @warning This is a temporary variable that is not available after + * being processed by HTMLDefinition + * @type string + */ + public $content_model_type; + + /** + * Does the element have a content model (#PCDATA | Inline)*? This + * is important for chameleon ins and del processing in + * HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't + * have to worry about this one. + * @type bool + */ + public $descendants_are_inline = false; + + /** + * List of the names of required attributes this element has. + * Dynamically populated by HTMLPurifier_HTMLDefinition::getElement() + * @type array + */ + public $required_attr = array(); + + /** + * Lookup table of tags excluded from all descendants of this tag. + * @type array + * @note SGML permits exclusions for all descendants, but this is + * not possible with DTDs or XML Schemas. W3C has elected to + * use complicated compositions of content_models to simulate + * exclusion for children, but we go the simpler, SGML-style + * route of flat-out exclusions, which correctly apply to + * all descendants and not just children. Note that the XHTML + * Modularization Abstract Modules are blithely unaware of such + * distinctions. + */ + public $excludes = array(); + + /** + * This tag is explicitly auto-closed by the following tags. + * @type array + */ + public $autoclose = array(); + + /** + * If a foreign element is found in this element, test if it is + * allowed by this sub-element; if it is, instead of closing the + * current element, place it inside this element. + * @type string + */ + public $wrap; + + /** + * Whether or not this is a formatting element affected by the + * "Active Formatting Elements" algorithm. + * @type bool + */ + public $formatting; + + /** + * Low-level factory constructor for creating new standalone element defs + */ + public static function create($content_model, $content_model_type, $attr) + { + $def = new HTMLPurifier_ElementDef(); + $def->content_model = $content_model; + $def->content_model_type = $content_model_type; + $def->attr = $attr; + return $def; + } + + /** + * Merges the values of another element definition into this one. + * Values from the new element def take precedence if a value is + * not mergeable. + * @param HTMLPurifier_ElementDef $def + */ + public function mergeIn($def) + { + // later keys takes precedence + foreach ($def->attr as $k => $v) { + if ($k === 0) { + // merge in the includes + // sorry, no way to override an include + foreach ($v as $v2) { + $this->attr[0][] = $v2; + } + continue; + } + if ($v === false) { + if (isset($this->attr[$k])) { + unset($this->attr[$k]); + } + continue; + } + $this->attr[$k] = $v; + } + $this->_mergeAssocArray($this->excludes, $def->excludes); + $this->attr_transform_pre = array_merge($this->attr_transform_pre, $def->attr_transform_pre); + $this->attr_transform_post = array_merge($this->attr_transform_post, $def->attr_transform_post); + + if (!empty($def->content_model)) { + $this->content_model = + str_replace("#SUPER", (string)$this->content_model, $def->content_model); + $this->child = false; + } + if (!empty($def->content_model_type)) { + $this->content_model_type = $def->content_model_type; + $this->child = false; + } + if (!is_null($def->child)) { + $this->child = $def->child; + } + if (!is_null($def->formatting)) { + $this->formatting = $def->formatting; + } + if ($def->descendants_are_inline) { + $this->descendants_are_inline = $def->descendants_are_inline; + } + } + + /** + * Merges one array into another, removes values which equal false + * @param $a1 Array by reference that is merged into + * @param $a2 Array that merges into $a1 + */ + private function _mergeAssocArray(&$a1, $a2) + { + foreach ($a2 as $k => $v) { + if ($v === false) { + if (isset($a1[$k])) { + unset($a1[$k]); + } + continue; + } + $a1[$k] = $v; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Encoder.php b/software/HTMLPurifier/HTMLPurifier/Encoder.php new file mode 100644 index 0000000..d4791cc --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Encoder.php @@ -0,0 +1,617 @@ += $c) { + $r .= self::unsafeIconv($in, $out, substr($text, $i)); + break; + } + // wibble the boundary + if (0x80 != (0xC0 & ord($text[$i + $max_chunk_size]))) { + $chunk_size = $max_chunk_size; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 1]))) { + $chunk_size = $max_chunk_size - 1; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 2]))) { + $chunk_size = $max_chunk_size - 2; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 3]))) { + $chunk_size = $max_chunk_size - 3; + } else { + return false; // rather confusing UTF-8... + } + $chunk = substr($text, $i, $chunk_size); // substr doesn't mind overlong lengths + $r .= self::unsafeIconv($in, $out, $chunk); + $i += $chunk_size; + } + return $r; + } else { + return false; + } + } else { + return false; + } + } + + /** + * Cleans a UTF-8 string for well-formedness and SGML validity + * + * It will parse according to UTF-8 and return a valid UTF8 string, with + * non-SGML codepoints excluded. + * + * Specifically, it will permit: + * \x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF} + * Source: https://www.w3.org/TR/REC-xml/#NT-Char + * Arguably this function should be modernized to the HTML5 set + * of allowed characters: + * https://www.w3.org/TR/html5/syntax.html#preprocessing-the-input-stream + * which simultaneously expand and restrict the set of allowed characters. + * + * @param string $str The string to clean + * @param bool $force_php + * @return string + * + * @note Just for reference, the non-SGML code points are 0 to 31 and + * 127 to 159, inclusive. However, we allow code points 9, 10 + * and 13, which are the tab, line feed and carriage return + * respectively. 128 and above the code points map to multibyte + * UTF-8 representations. + * + * @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and + * hsivonen@iki.fi at under the + * LGPL license. Notes on what changed are inside, but in general, + * the original code transformed UTF-8 text into an array of integer + * Unicode codepoints. Understandably, transforming that back to + * a string would be somewhat expensive, so the function was modded to + * directly operate on the string. However, this discourages code + * reuse, and the logic enumerated here would be useful for any + * function that needs to be able to understand UTF-8 characters. + * As of right now, only smart lossless character encoding converters + * would need that, and I'm probably not going to implement them. + */ + public static function cleanUTF8($str, $force_php = false) + { + // UTF-8 validity is checked since PHP 4.3.5 + // This is an optimization: if the string is already valid UTF-8, no + // need to do PHP stuff. 99% of the time, this will be the case. + if (preg_match( + '/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', + $str + )) { + return $str; + } + + $mState = 0; // cached expected number of octets after the current octet + // until the beginning of the next UTF8 character sequence + $mUcs4 = 0; // cached Unicode character + $mBytes = 1; // cached expected number of octets in the current sequence + + // original code involved an $out that was an array of Unicode + // codepoints. Instead of having to convert back into UTF-8, we've + // decided to directly append valid UTF-8 characters onto a string + // $out once they're done. $char accumulates raw bytes, while $mUcs4 + // turns into the Unicode code point, so there's some redundancy. + + $out = ''; + $char = ''; + + $len = strlen($str); + for ($i = 0; $i < $len; $i++) { + $in = ord($str[$i]); + $char .= $str[$i]; // append byte to char + if (0 == $mState) { + // When mState is zero we expect either a US-ASCII character + // or a multi-octet sequence. + if (0 == (0x80 & ($in))) { + // US-ASCII, pass straight through. + if (($in <= 31 || $in == 127) && + !($in == 9 || $in == 13 || $in == 10) // save \r\t\n + ) { + // control characters, remove + } else { + $out .= $char; + } + // reset + $char = ''; + $mBytes = 1; + } elseif (0xC0 == (0xE0 & ($in))) { + // First octet of 2 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x1F) << 6; + $mState = 1; + $mBytes = 2; + } elseif (0xE0 == (0xF0 & ($in))) { + // First octet of 3 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x0F) << 12; + $mState = 2; + $mBytes = 3; + } elseif (0xF0 == (0xF8 & ($in))) { + // First octet of 4 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x07) << 18; + $mState = 3; + $mBytes = 4; + } elseif (0xF8 == (0xFC & ($in))) { + // First octet of 5 octet sequence. + // + // This is illegal because the encoded codepoint must be + // either: + // (a) not the shortest form or + // (b) outside the Unicode range of 0-0x10FFFF. + // Rather than trying to resynchronize, we will carry on + // until the end of the sequence and let the later error + // handling code catch it. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x03) << 24; + $mState = 4; + $mBytes = 5; + } elseif (0xFC == (0xFE & ($in))) { + // First octet of 6 octet sequence, see comments for 5 + // octet sequence. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 1) << 30; + $mState = 5; + $mBytes = 6; + } else { + // Current octet is neither in the US-ASCII range nor a + // legal first octet of a multi-octet sequence. + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char = ''; + } + } else { + // When mState is non-zero, we expect a continuation of the + // multi-octet sequence + if (0x80 == (0xC0 & ($in))) { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + if (0 == --$mState) { + // End of the multi-octet sequence. mUcs4 now contains + // the final Unicode codepoint to be output + + // Check for illegal sequences and codepoints. + + // From Unicode 3.1, non-shortest form is illegal + if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || + ((3 == $mBytes) && ($mUcs4 < 0x0800)) || + ((4 == $mBytes) && ($mUcs4 < 0x10000)) || + (4 < $mBytes) || + // From Unicode 3.2, surrogate characters = illegal + (($mUcs4 & 0xFFFFF800) == 0xD800) || + // Codepoints outside the Unicode range are illegal + ($mUcs4 > 0x10FFFF) + ) { + + } elseif (0xFEFF != $mUcs4 && // omit BOM + // check for valid Char unicode codepoints + ( + 0x9 == $mUcs4 || + 0xA == $mUcs4 || + 0xD == $mUcs4 || + (0x20 <= $mUcs4 && 0x7E >= $mUcs4) || + // 7F-9F is not strictly prohibited by XML, + // but it is non-SGML, and thus we don't allow it + (0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) || + (0xE000 <= $mUcs4 && 0xFFFD >= $mUcs4) || + (0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4) + ) + ) { + $out .= $char; + } + // initialize UTF8 cache (reset) + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char = ''; + } + } else { + // ((0xC0 & (*in) != 0x80) && (mState != 0)) + // Incomplete multi-octet sequence. + // used to result in complete fail, but we'll reset + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char =''; + } + } + } + return $out; + } + + /** + * Translates a Unicode codepoint into its corresponding UTF-8 character. + * @note Based on Feyd's function at + * , + * which is in public domain. + * @note While we're going to do code point parsing anyway, a good + * optimization would be to refuse to translate code points that + * are non-SGML characters. However, this could lead to duplication. + * @note This is very similar to the unichr function in + * maintenance/generate-entity-file.php (although this is superior, + * due to its sanity checks). + */ + + // +----------+----------+----------+----------+ + // | 33222222 | 22221111 | 111111 | | + // | 10987654 | 32109876 | 54321098 | 76543210 | bit + // +----------+----------+----------+----------+ + // | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F + // | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF + // | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF + // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF + // +----------+----------+----------+----------+ + // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF) + // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes + // +----------+----------+----------+----------+ + + public static function unichr($code) + { + if ($code > 1114111 or $code < 0 or + ($code >= 55296 and $code <= 57343) ) { + // bits are set outside the "valid" range as defined + // by UNICODE 4.1.0 + return ''; + } + + $x = $y = $z = $w = 0; + if ($code < 128) { + // regular ASCII character + $x = $code; + } else { + // set up bits for UTF-8 + $x = ($code & 63) | 128; + if ($code < 2048) { + $y = (($code & 2047) >> 6) | 192; + } else { + $y = (($code & 4032) >> 6) | 128; + if ($code < 65536) { + $z = (($code >> 12) & 15) | 224; + } else { + $z = (($code >> 12) & 63) | 128; + $w = (($code >> 18) & 7) | 240; + } + } + } + // set up the actual character + $ret = ''; + if ($w) { + $ret .= chr($w); + } + if ($z) { + $ret .= chr($z); + } + if ($y) { + $ret .= chr($y); + } + $ret .= chr($x); + + return $ret; + } + + /** + * @return bool + */ + public static function iconvAvailable() + { + static $iconv = null; + if ($iconv === null) { + $iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE; + } + return $iconv; + } + + /** + * Convert a string to UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public static function convertToUTF8($str, $config, $context) + { + $encoding = $config->get('Core.Encoding'); + if ($encoding === 'utf-8') { + return $str; + } + static $iconv = null; + if ($iconv === null) { + $iconv = self::iconvAvailable(); + } + if ($iconv && !$config->get('Test.ForceNoIconv')) { + // unaffected by bugs, since UTF-8 support all characters + $str = self::unsafeIconv($encoding, 'utf-8//IGNORE', $str); + if ($str === false) { + // $encoding is not a valid encoding + trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR); + return ''; + } + // If the string is bjorked by Shift_JIS or a similar encoding + // that doesn't support all of ASCII, convert the naughty + // characters to their true byte-wise ASCII/UTF-8 equivalents. + $str = strtr($str, self::testEncodingSupportsASCII($encoding)); + return $str; + } elseif ($encoding === 'iso-8859-1' && function_exists('mb_convert_encoding')) { + $str = mb_convert_encoding($str, 'UTF-8', 'ISO-8859-1'); + return $str; + } + $bug = HTMLPurifier_Encoder::testIconvTruncateBug(); + if ($bug == self::ICONV_OK) { + trigger_error('Encoding not supported, please install iconv', E_USER_ERROR); + } else { + trigger_error( + 'You have a buggy version of iconv, see https://bugs.php.net/bug.php?id=48147 ' . + 'and http://sourceware.org/bugzilla/show_bug.cgi?id=13541', + E_USER_ERROR + ); + } + } + + /** + * Converts a string from UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + * @note Currently, this is a lossy conversion, with unexpressable + * characters being omitted. + */ + public static function convertFromUTF8($str, $config, $context) + { + $encoding = $config->get('Core.Encoding'); + if ($escape = $config->get('Core.EscapeNonASCIICharacters')) { + $str = self::convertToASCIIDumbLossless($str); + } + if ($encoding === 'utf-8') { + return $str; + } + static $iconv = null; + if ($iconv === null) { + $iconv = self::iconvAvailable(); + } + if ($iconv && !$config->get('Test.ForceNoIconv')) { + // Undo our previous fix in convertToUTF8, otherwise iconv will barf + $ascii_fix = self::testEncodingSupportsASCII($encoding); + if (!$escape && !empty($ascii_fix)) { + $clear_fix = array(); + foreach ($ascii_fix as $utf8 => $native) { + $clear_fix[$utf8] = ''; + } + $str = strtr($str, $clear_fix); + } + $str = strtr($str, array_flip($ascii_fix)); + // Normal stuff + $str = self::iconv('utf-8', $encoding . '//IGNORE', $str); + return $str; + } elseif ($encoding === 'iso-8859-1' && function_exists('mb_convert_encoding')) { + $str = mb_convert_encoding($str, 'ISO-8859-1', 'UTF-8'); + return $str; + } + trigger_error('Encoding not supported', E_USER_ERROR); + // You might be tempted to assume that the ASCII representation + // might be OK, however, this is *not* universally true over all + // encodings. So we take the conservative route here, rather + // than forcibly turn on %Core.EscapeNonASCIICharacters + } + + /** + * Lossless (character-wise) conversion of HTML to ASCII + * @param string $str UTF-8 string to be converted to ASCII + * @return string ASCII encoded string with non-ASCII character entity-ized + * @warning Adapted from MediaWiki, claiming fair use: this is a common + * algorithm. If you disagree with this license fudgery, + * implement it yourself. + * @note Uses decimal numeric entities since they are best supported. + * @note This is a DUMB function: it has no concept of keeping + * character entities that the projected character encoding + * can allow. We could possibly implement a smart version + * but that would require it to also know which Unicode + * codepoints the charset supported (not an easy task). + * @note Sort of with cleanUTF8() but it assumes that $str is + * well-formed UTF-8 + */ + public static function convertToASCIIDumbLossless($str) + { + $bytesleft = 0; + $result = ''; + $working = 0; + $len = strlen($str); + for ($i = 0; $i < $len; $i++) { + $bytevalue = ord($str[$i]); + if ($bytevalue <= 0x7F) { //0xxx xxxx + $result .= chr($bytevalue); + $bytesleft = 0; + } elseif ($bytevalue <= 0xBF) { //10xx xxxx + $working = $working << 6; + $working += ($bytevalue & 0x3F); + $bytesleft--; + if ($bytesleft <= 0) { + $result .= "&#" . $working . ";"; + } + } elseif ($bytevalue <= 0xDF) { //110x xxxx + $working = $bytevalue & 0x1F; + $bytesleft = 1; + } elseif ($bytevalue <= 0xEF) { //1110 xxxx + $working = $bytevalue & 0x0F; + $bytesleft = 2; + } else { //1111 0xxx + $working = $bytevalue & 0x07; + $bytesleft = 3; + } + } + return $result; + } + + /** No bugs detected in iconv. */ + const ICONV_OK = 0; + + /** Iconv truncates output if converting from UTF-8 to another + * character set with //IGNORE, and a non-encodable character is found */ + const ICONV_TRUNCATES = 1; + + /** Iconv does not support //IGNORE, making it unusable for + * transcoding purposes */ + const ICONV_UNUSABLE = 2; + + /** + * glibc iconv has a known bug where it doesn't handle the magic + * //IGNORE stanza correctly. In particular, rather than ignore + * characters, it will return an EILSEQ after consuming some number + * of characters, and expect you to restart iconv as if it were + * an E2BIG. Old versions of PHP did not respect the errno, and + * returned the fragment, so as a result you would see iconv + * mysteriously truncating output. We can work around this by + * manually chopping our input into segments of about 8000 + * characters, as long as PHP ignores the error code. If PHP starts + * paying attention to the error code, iconv becomes unusable. + * + * @return int Error code indicating severity of bug. + */ + public static function testIconvTruncateBug() + { + static $code = null; + if ($code === null) { + // better not use iconv, otherwise infinite loop! + $r = self::unsafeIconv('utf-8', 'ascii//IGNORE', "\xCE\xB1" . str_repeat('a', 9000)); + if ($r === false) { + $code = self::ICONV_UNUSABLE; + } elseif (($c = strlen($r)) < 9000) { + $code = self::ICONV_TRUNCATES; + } elseif ($c > 9000) { + trigger_error( + 'Your copy of iconv is extremely buggy. Please notify HTML Purifier maintainers: ' . + 'include your iconv version as per phpversion()', + E_USER_ERROR + ); + } else { + $code = self::ICONV_OK; + } + } + return $code; + } + + /** + * This expensive function tests whether or not a given character + * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will + * fail this test, and require special processing. Variable width + * encodings shouldn't ever fail. + * + * @param string $encoding Encoding name to test, as per iconv format + * @param bool $bypass Whether or not to bypass the precompiled arrays. + * @return Array of UTF-8 characters to their corresponding ASCII, + * which can be used to "undo" any overzealous iconv action. + */ + public static function testEncodingSupportsASCII($encoding, $bypass = false) + { + // All calls to iconv here are unsafe, proof by case analysis: + // If ICONV_OK, no difference. + // If ICONV_TRUNCATE, all calls involve one character inputs, + // so bug is not triggered. + // If ICONV_UNUSABLE, this call is irrelevant + static $encodings = array(); + if (!$bypass) { + if (isset($encodings[$encoding])) { + return $encodings[$encoding]; + } + $lenc = strtolower($encoding); + switch ($lenc) { + case 'shift_jis': + return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~'); + case 'johab': + return array("\xE2\x82\xA9" => '\\'); + } + if (strpos($lenc, 'iso-8859-') === 0) { + return array(); + } + } + $ret = array(); + if (self::unsafeIconv('UTF-8', $encoding, 'a') === false) { + return false; + } + for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars + $c = chr($i); // UTF-8 char + $r = self::unsafeIconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion + if ($r === '' || + // This line is needed for iconv implementations that do not + // omit characters that do not exist in the target character set + ($r === $c && self::unsafeIconv($encoding, 'UTF-8//IGNORE', $r) !== $c) + ) { + // Reverse engineer: what's the UTF-8 equiv of this byte + // sequence? This assumes that there's no variable width + // encoding that doesn't support ASCII. + $ret[self::unsafeIconv($encoding, 'UTF-8//IGNORE', $c)] = $c; + } + } + $encodings[$encoding] = $ret; + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/EntityLookup.php b/software/HTMLPurifier/HTMLPurifier/EntityLookup.php new file mode 100644 index 0000000..f12ff13 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/EntityLookup.php @@ -0,0 +1,48 @@ +table = unserialize(file_get_contents($file)); + } + + /** + * Retrieves sole instance of the object. + * @param bool|HTMLPurifier_EntityLookup $prototype Optional prototype of custom lookup table to overload with. + * @return HTMLPurifier_EntityLookup + */ + public static function instance($prototype = false) + { + // no references, since PHP doesn't copy unless modified + static $instance = null; + if ($prototype) { + $instance = $prototype; + } elseif (!$instance) { + $instance = new HTMLPurifier_EntityLookup(); + $instance->setup(); + } + return $instance; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser b/software/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser new file mode 100644 index 0000000..e8b0812 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser @@ -0,0 +1 @@ +a:253:{s:4:"fnof";s:2:"ฦ’";s:5:"Alpha";s:2:"ฮ‘";s:4:"Beta";s:2:"ฮ’";s:5:"Gamma";s:2:"ฮ“";s:5:"Delta";s:2:"ฮ”";s:7:"Epsilon";s:2:"ฮ•";s:4:"Zeta";s:2:"ฮ–";s:3:"Eta";s:2:"ฮ—";s:5:"Theta";s:2:"ฮ˜";s:4:"Iota";s:2:"ฮ™";s:5:"Kappa";s:2:"ฮš";s:6:"Lambda";s:2:"ฮ›";s:2:"Mu";s:2:"ฮœ";s:2:"Nu";s:2:"ฮ";s:2:"Xi";s:2:"ฮž";s:7:"Omicron";s:2:"ฮŸ";s:2:"Pi";s:2:"ฮ ";s:3:"Rho";s:2:"ฮก";s:5:"Sigma";s:2:"ฮฃ";s:3:"Tau";s:2:"ฮค";s:7:"Upsilon";s:2:"ฮฅ";s:3:"Phi";s:2:"ฮฆ";s:3:"Chi";s:2:"ฮง";s:3:"Psi";s:2:"ฮจ";s:5:"Omega";s:2:"ฮฉ";s:5:"alpha";s:2:"ฮฑ";s:4:"beta";s:2:"ฮฒ";s:5:"gamma";s:2:"ฮณ";s:5:"delta";s:2:"ฮด";s:7:"epsilon";s:2:"ฮต";s:4:"zeta";s:2:"ฮถ";s:3:"eta";s:2:"ฮท";s:5:"theta";s:2:"ฮธ";s:4:"iota";s:2:"ฮน";s:5:"kappa";s:2:"ฮบ";s:6:"lambda";s:2:"ฮป";s:2:"mu";s:2:"ฮผ";s:2:"nu";s:2:"ฮฝ";s:2:"xi";s:2:"ฮพ";s:7:"omicron";s:2:"ฮฟ";s:2:"pi";s:2:"ฯ€";s:3:"rho";s:2:"ฯ";s:6:"sigmaf";s:2:"ฯ‚";s:5:"sigma";s:2:"ฯƒ";s:3:"tau";s:2:"ฯ„";s:7:"upsilon";s:2:"ฯ…";s:3:"phi";s:2:"ฯ†";s:3:"chi";s:2:"ฯ‡";s:3:"psi";s:2:"ฯˆ";s:5:"omega";s:2:"ฯ‰";s:8:"thetasym";s:2:"ฯ‘";s:5:"upsih";s:2:"ฯ’";s:3:"piv";s:2:"ฯ–";s:4:"bull";s:3:"โ€ข";s:6:"hellip";s:3:"โ€ฆ";s:5:"prime";s:3:"โ€ฒ";s:5:"Prime";s:3:"โ€ณ";s:5:"oline";s:3:"โ€พ";s:5:"frasl";s:3:"โ„";s:6:"weierp";s:3:"โ„˜";s:5:"image";s:3:"โ„‘";s:4:"real";s:3:"โ„œ";s:5:"trade";s:3:"โ„ข";s:7:"alefsym";s:3:"โ„ต";s:4:"larr";s:3:"โ†";s:4:"uarr";s:3:"โ†‘";s:4:"rarr";s:3:"โ†’";s:4:"darr";s:3:"โ†“";s:4:"harr";s:3:"โ†”";s:5:"crarr";s:3:"โ†ต";s:4:"lArr";s:3:"โ‡";s:4:"uArr";s:3:"โ‡‘";s:4:"rArr";s:3:"โ‡’";s:4:"dArr";s:3:"โ‡“";s:4:"hArr";s:3:"โ‡”";s:6:"forall";s:3:"โˆ€";s:4:"part";s:3:"โˆ‚";s:5:"exist";s:3:"โˆƒ";s:5:"empty";s:3:"โˆ…";s:5:"nabla";s:3:"โˆ‡";s:4:"isin";s:3:"โˆˆ";s:5:"notin";s:3:"โˆ‰";s:2:"ni";s:3:"โˆ‹";s:4:"prod";s:3:"โˆ";s:3:"sum";s:3:"โˆ‘";s:5:"minus";s:3:"โˆ’";s:6:"lowast";s:3:"โˆ—";s:5:"radic";s:3:"โˆš";s:4:"prop";s:3:"โˆ";s:5:"infin";s:3:"โˆž";s:3:"ang";s:3:"โˆ ";s:3:"and";s:3:"โˆง";s:2:"or";s:3:"โˆจ";s:3:"cap";s:3:"โˆฉ";s:3:"cup";s:3:"โˆช";s:3:"int";s:3:"โˆซ";s:6:"there4";s:3:"โˆด";s:3:"sim";s:3:"โˆผ";s:4:"cong";s:3:"โ‰…";s:5:"asymp";s:3:"โ‰ˆ";s:2:"ne";s:3:"โ‰ ";s:5:"equiv";s:3:"โ‰ก";s:2:"le";s:3:"โ‰ค";s:2:"ge";s:3:"โ‰ฅ";s:3:"sub";s:3:"โŠ‚";s:3:"sup";s:3:"โŠƒ";s:4:"nsub";s:3:"โŠ„";s:4:"sube";s:3:"โŠ†";s:4:"supe";s:3:"โŠ‡";s:5:"oplus";s:3:"โŠ•";s:6:"otimes";s:3:"โŠ—";s:4:"perp";s:3:"โŠฅ";s:4:"sdot";s:3:"โ‹…";s:5:"lceil";s:3:"โŒˆ";s:5:"rceil";s:3:"โŒ‰";s:6:"lfloor";s:3:"โŒŠ";s:6:"rfloor";s:3:"โŒ‹";s:4:"lang";s:3:"โŒฉ";s:4:"rang";s:3:"โŒช";s:3:"loz";s:3:"โ—Š";s:6:"spades";s:3:"โ™ ";s:5:"clubs";s:3:"โ™ฃ";s:6:"hearts";s:3:"โ™ฅ";s:5:"diams";s:3:"โ™ฆ";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"ล’";s:5:"oelig";s:2:"ล“";s:6:"Scaron";s:2:"ล ";s:6:"scaron";s:2:"ลก";s:4:"Yuml";s:2:"ลธ";s:4:"circ";s:2:"ห†";s:5:"tilde";s:2:"หœ";s:4:"ensp";s:3:"โ€‚";s:4:"emsp";s:3:"โ€ƒ";s:6:"thinsp";s:3:"โ€‰";s:4:"zwnj";s:3:"โ€Œ";s:3:"zwj";s:3:"โ€";s:3:"lrm";s:3:"โ€Ž";s:3:"rlm";s:3:"โ€";s:5:"ndash";s:3:"โ€“";s:5:"mdash";s:3:"โ€”";s:5:"lsquo";s:3:"โ€˜";s:5:"rsquo";s:3:"โ€™";s:5:"sbquo";s:3:"โ€š";s:5:"ldquo";s:3:"โ€œ";s:5:"rdquo";s:3:"โ€";s:5:"bdquo";s:3:"โ€ž";s:6:"dagger";s:3:"โ€ ";s:6:"Dagger";s:3:"โ€ก";s:6:"permil";s:3:"โ€ฐ";s:6:"lsaquo";s:3:"โ€น";s:6:"rsaquo";s:3:"โ€บ";s:4:"euro";s:3:"โ‚ฌ";s:4:"nbsp";s:2:"ย ";s:5:"iexcl";s:2:"ยก";s:4:"cent";s:2:"ยข";s:5:"pound";s:2:"ยฃ";s:6:"curren";s:2:"ยค";s:3:"yen";s:2:"ยฅ";s:6:"brvbar";s:2:"ยฆ";s:4:"sect";s:2:"ยง";s:3:"uml";s:2:"ยจ";s:4:"copy";s:2:"ยฉ";s:4:"ordf";s:2:"ยช";s:5:"laquo";s:2:"ยซ";s:3:"not";s:2:"ยฌ";s:3:"shy";s:2:"ยญ";s:3:"reg";s:2:"ยฎ";s:4:"macr";s:2:"ยฏ";s:3:"deg";s:2:"ยฐ";s:6:"plusmn";s:2:"ยฑ";s:4:"sup2";s:2:"ยฒ";s:4:"sup3";s:2:"ยณ";s:5:"acute";s:2:"ยด";s:5:"micro";s:2:"ยต";s:4:"para";s:2:"ยถ";s:6:"middot";s:2:"ยท";s:5:"cedil";s:2:"ยธ";s:4:"sup1";s:2:"ยน";s:4:"ordm";s:2:"ยบ";s:5:"raquo";s:2:"ยป";s:6:"frac14";s:2:"ยผ";s:6:"frac12";s:2:"ยฝ";s:6:"frac34";s:2:"ยพ";s:6:"iquest";s:2:"ยฟ";s:6:"Agrave";s:2:"ร€";s:6:"Aacute";s:2:"ร";s:5:"Acirc";s:2:"ร‚";s:6:"Atilde";s:2:"รƒ";s:4:"Auml";s:2:"ร„";s:5:"Aring";s:2:"ร…";s:5:"AElig";s:2:"ร†";s:6:"Ccedil";s:2:"ร‡";s:6:"Egrave";s:2:"รˆ";s:6:"Eacute";s:2:"ร‰";s:5:"Ecirc";s:2:"รŠ";s:4:"Euml";s:2:"ร‹";s:6:"Igrave";s:2:"รŒ";s:6:"Iacute";s:2:"ร";s:5:"Icirc";s:2:"รŽ";s:4:"Iuml";s:2:"ร";s:3:"ETH";s:2:"ร";s:6:"Ntilde";s:2:"ร‘";s:6:"Ograve";s:2:"ร’";s:6:"Oacute";s:2:"ร“";s:5:"Ocirc";s:2:"ร”";s:6:"Otilde";s:2:"ร•";s:4:"Ouml";s:2:"ร–";s:5:"times";s:2:"ร—";s:6:"Oslash";s:2:"ร˜";s:6:"Ugrave";s:2:"ร™";s:6:"Uacute";s:2:"รš";s:5:"Ucirc";s:2:"ร›";s:4:"Uuml";s:2:"รœ";s:6:"Yacute";s:2:"ร";s:5:"THORN";s:2:"รž";s:5:"szlig";s:2:"รŸ";s:6:"agrave";s:2:"ร ";s:6:"aacute";s:2:"รก";s:5:"acirc";s:2:"รข";s:6:"atilde";s:2:"รฃ";s:4:"auml";s:2:"รค";s:5:"aring";s:2:"รฅ";s:5:"aelig";s:2:"รฆ";s:6:"ccedil";s:2:"รง";s:6:"egrave";s:2:"รจ";s:6:"eacute";s:2:"รฉ";s:5:"ecirc";s:2:"รช";s:4:"euml";s:2:"รซ";s:6:"igrave";s:2:"รฌ";s:6:"iacute";s:2:"รญ";s:5:"icirc";s:2:"รฎ";s:4:"iuml";s:2:"รฏ";s:3:"eth";s:2:"รฐ";s:6:"ntilde";s:2:"รฑ";s:6:"ograve";s:2:"รฒ";s:6:"oacute";s:2:"รณ";s:5:"ocirc";s:2:"รด";s:6:"otilde";s:2:"รต";s:4:"ouml";s:2:"รถ";s:6:"divide";s:2:"รท";s:6:"oslash";s:2:"รธ";s:6:"ugrave";s:2:"รน";s:6:"uacute";s:2:"รบ";s:5:"ucirc";s:2:"รป";s:4:"uuml";s:2:"รผ";s:6:"yacute";s:2:"รฝ";s:5:"thorn";s:2:"รพ";s:4:"yuml";s:2:"รฟ";} \ No newline at end of file diff --git a/software/HTMLPurifier/HTMLPurifier/EntityParser.php b/software/HTMLPurifier/HTMLPurifier/EntityParser.php new file mode 100644 index 0000000..3ef2d09 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/EntityParser.php @@ -0,0 +1,285 @@ +_semiOptionalPrefixRegex = "/&()()()($semi_optional)/"; + + $this->_textEntitiesRegex = + '/&(?:'. + // hex + '[#]x([a-fA-F0-9]+);?|'. + // dec + '[#]0*(\d+);?|'. + // string (mandatory semicolon) + // NB: order matters: match semicolon preferentially + '([A-Za-z_:][A-Za-z0-9.\-_:]*);|'. + // string (optional semicolon) + "($semi_optional)". + ')/'; + + $this->_attrEntitiesRegex = + '/&(?:'. + // hex + '[#]x([a-fA-F0-9]+);?|'. + // dec + '[#]0*(\d+);?|'. + // string (mandatory semicolon) + // NB: order matters: match semicolon preferentially + '([A-Za-z_:][A-Za-z0-9.\-_:]*);|'. + // string (optional semicolon) + // don't match if trailing is equals or alphanumeric (URL + // like) + "($semi_optional)(?![=;A-Za-z0-9])". + ')/'; + + } + + /** + * Substitute entities with the parsed equivalents. Use this on + * textual data in an HTML document (as opposed to attributes.) + * + * @param string $string String to have entities parsed. + * @return string Parsed string. + */ + public function substituteTextEntities($string) + { + return preg_replace_callback( + $this->_textEntitiesRegex, + array($this, 'entityCallback'), + $string + ); + } + + /** + * Substitute entities with the parsed equivalents. Use this on + * attribute contents in documents. + * + * @param string $string String to have entities parsed. + * @return string Parsed string. + */ + public function substituteAttrEntities($string) + { + return preg_replace_callback( + $this->_attrEntitiesRegex, + array($this, 'entityCallback'), + $string + ); + } + + /** + * Callback function for substituteNonSpecialEntities() that does the work. + * + * @param array $matches PCRE matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + + protected function entityCallback($matches) + { + $entity = $matches[0]; + $hex_part = @$matches[1]; + $dec_part = @$matches[2]; + $named_part = empty($matches[3]) ? (empty($matches[4]) ? "" : $matches[4]) : $matches[3]; + if ($hex_part !== NULL && $hex_part !== "") { + return HTMLPurifier_Encoder::unichr(hexdec($hex_part)); + } elseif ($dec_part !== NULL && $dec_part !== "") { + return HTMLPurifier_Encoder::unichr((int) $dec_part); + } else { + if (!$this->_entity_lookup) { + $this->_entity_lookup = HTMLPurifier_EntityLookup::instance(); + } + if (isset($this->_entity_lookup->table[$named_part])) { + return $this->_entity_lookup->table[$named_part]; + } else { + // exact match didn't match anything, so test if + // any of the semicolon optional match the prefix. + // Test that this is an EXACT match is important to + // prevent infinite loop + if (!empty($matches[3])) { + return preg_replace_callback( + $this->_semiOptionalPrefixRegex, + array($this, 'entityCallback'), + $entity + ); + } + return $entity; + } + } + } + + // LEGACY CODE BELOW + + /** + * Callback regex string for parsing entities. + * @type string + */ + protected $_substituteEntitiesRegex = + '/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/'; + // 1. hex 2. dec 3. string (XML style) + + /** + * Decimal to parsed string conversion table for special entities. + * @type array + */ + protected $_special_dec2str = + array( + 34 => '"', + 38 => '&', + 39 => "'", + 60 => '<', + 62 => '>' + ); + + /** + * Stripped entity names to decimal conversion table for special entities. + * @type array + */ + protected $_special_ent2dec = + array( + 'quot' => 34, + 'amp' => 38, + 'lt' => 60, + 'gt' => 62 + ); + + /** + * Substitutes non-special entities with their parsed equivalents. Since + * running this whenever you have parsed character is t3h 5uck, we run + * it before everything else. + * + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteNonSpecialEntities($string) + { + // it will try to detect missing semicolons, but don't rely on it + return preg_replace_callback( + $this->_substituteEntitiesRegex, + array($this, 'nonSpecialEntityCallback'), + $string + ); + } + + /** + * Callback function for substituteNonSpecialEntities() that does the work. + * + * @param array $matches PCRE matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + + protected function nonSpecialEntityCallback($matches) + { + // replaces all but big five + $entity = $matches[0]; + $is_num = (@$matches[0][1] === '#'); + if ($is_num) { + $is_hex = (@$entity[2] === 'x'); + $code = $is_hex ? hexdec($matches[1]) : (int) $matches[2]; + // abort for special characters + if (isset($this->_special_dec2str[$code])) { + return $entity; + } + return HTMLPurifier_Encoder::unichr($code); + } else { + if (isset($this->_special_ent2dec[$matches[3]])) { + return $entity; + } + if (!$this->_entity_lookup) { + $this->_entity_lookup = HTMLPurifier_EntityLookup::instance(); + } + if (isset($this->_entity_lookup->table[$matches[3]])) { + return $this->_entity_lookup->table[$matches[3]]; + } else { + return $entity; + } + } + } + + /** + * Substitutes only special entities with their parsed equivalents. + * + * @notice We try to avoid calling this function because otherwise, it + * would have to be called a lot (for every parsed section). + * + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteSpecialEntities($string) + { + return preg_replace_callback( + $this->_substituteEntitiesRegex, + array($this, 'specialEntityCallback'), + $string + ); + } + + /** + * Callback function for substituteSpecialEntities() that does the work. + * + * This callback has same syntax as nonSpecialEntityCallback(). + * + * @param array $matches PCRE-style matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + protected function specialEntityCallback($matches) + { + $entity = $matches[0]; + $is_num = (@$matches[0][1] === '#'); + if ($is_num) { + $is_hex = (@$entity[2] === 'x'); + $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2]; + return isset($this->_special_dec2str[$int]) ? + $this->_special_dec2str[$int] : + $entity; + } else { + return isset($this->_special_ent2dec[$matches[3]]) ? + $this->_special_dec2str[$this->_special_ent2dec[$matches[3]]] : + $entity; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ErrorCollector.php b/software/HTMLPurifier/HTMLPurifier/ErrorCollector.php new file mode 100644 index 0000000..d47e3f2 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ErrorCollector.php @@ -0,0 +1,244 @@ +locale =& $context->get('Locale'); + $this->context = $context; + $this->_current =& $this->_stacks[0]; + $this->errors =& $this->_stacks[0]; + } + + /** + * Sends an error message to the collector for later use + * @param int $severity Error severity, PHP error style (don't use E_USER_) + * @param string $msg Error message text + */ + public function send($severity, $msg) + { + $args = array(); + if (func_num_args() > 2) { + $args = func_get_args(); + array_shift($args); + unset($args[0]); + } + + $token = $this->context->get('CurrentToken', true); + $line = $token ? $token->line : $this->context->get('CurrentLine', true); + $col = $token ? $token->col : $this->context->get('CurrentCol', true); + $attr = $this->context->get('CurrentAttr', true); + + // perform special substitutions, also add custom parameters + $subst = array(); + if (!is_null($token)) { + $args['CurrentToken'] = $token; + } + if (!is_null($attr)) { + $subst['$CurrentAttr.Name'] = $attr; + if (isset($token->attr[$attr])) { + $subst['$CurrentAttr.Value'] = $token->attr[$attr]; + } + } + + if (empty($args)) { + $msg = $this->locale->getMessage($msg); + } else { + $msg = $this->locale->formatMessage($msg, $args); + } + + if (!empty($subst)) { + $msg = strtr($msg, $subst); + } + + // (numerically indexed) + $error = array( + self::LINENO => $line, + self::SEVERITY => $severity, + self::MESSAGE => $msg, + self::CHILDREN => array() + ); + $this->_current[] = $error; + + // NEW CODE BELOW ... + // Top-level errors are either: + // TOKEN type, if $value is set appropriately, or + // "syntax" type, if $value is null + $new_struct = new HTMLPurifier_ErrorStruct(); + $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN; + if ($token) { + $new_struct->value = clone $token; + } + if (is_int($line) && is_int($col)) { + if (isset($this->lines[$line][$col])) { + $struct = $this->lines[$line][$col]; + } else { + $struct = $this->lines[$line][$col] = $new_struct; + } + // These ksorts may present a performance problem + ksort($this->lines[$line], SORT_NUMERIC); + } else { + if (isset($this->lines[-1])) { + $struct = $this->lines[-1]; + } else { + $struct = $this->lines[-1] = $new_struct; + } + } + ksort($this->lines, SORT_NUMERIC); + + // Now, check if we need to operate on a lower structure + if (!empty($attr)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr); + if (!$struct->value) { + $struct->value = array($attr, 'PUT VALUE HERE'); + } + } + if (!empty($cssprop)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop); + if (!$struct->value) { + // if we tokenize CSS this might be a little more difficult to do + $struct->value = array($cssprop, 'PUT VALUE HERE'); + } + } + + // Ok, structs are all setup, now time to register the error + $struct->addError($severity, $msg); + } + + /** + * Retrieves raw error data for custom formatter to use + */ + public function getRaw() + { + return $this->errors; + } + + /** + * Default HTML formatting implementation for error messages + * @param HTMLPurifier_Config $config Configuration, vital for HTML output nature + * @param array $errors Errors array to display; used for recursion. + * @return string + */ + public function getHTMLFormatted($config, $errors = null) + { + $ret = array(); + + $this->generator = new HTMLPurifier_Generator($config, $this->context); + if ($errors === null) { + $errors = $this->errors; + } + + // 'At line' message needs to be removed + + // generation code for new structure goes here. It needs to be recursive. + foreach ($this->lines as $line => $col_array) { + if ($line == -1) { + continue; + } + foreach ($col_array as $col => $struct) { + $this->_renderStruct($ret, $struct, $line, $col); + } + } + if (isset($this->lines[-1])) { + $this->_renderStruct($ret, $this->lines[-1]); + } + + if (empty($errors)) { + return '

' . $this->locale->getMessage('ErrorCollector: No errors') . '

'; + } else { + return '
  • ' . implode('
  • ', $ret) . '
'; + } + + } + + private function _renderStruct(&$ret, $struct, $line = null, $col = null) + { + $stack = array($struct); + $context_stack = array(array()); + while ($current = array_pop($stack)) { + $context = array_pop($context_stack); + foreach ($current->errors as $error) { + list($severity, $msg) = $error; + $string = ''; + $string .= '
'; + // W3C uses an icon to indicate the severity of the error. + $error = $this->locale->getErrorName($severity); + $string .= "$error "; + if (!is_null($line) && !is_null($col)) { + $string .= "Line $line, Column $col: "; + } else { + $string .= 'End of Document: '; + } + $string .= '' . $this->generator->escape($msg) . ' '; + $string .= '
'; + // Here, have a marker for the character on the column appropriate. + // Be sure to clip extremely long lines. + //$string .= '
';
+                //$string .= '';
+                //$string .= '
'; + $ret[] = $string; + } + foreach ($current->children as $array) { + $context[] = $current; + $stack = array_merge($stack, array_reverse($array, true)); + for ($i = count($array); $i > 0; $i--) { + $context_stack[] = $context; + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/ErrorStruct.php b/software/HTMLPurifier/HTMLPurifier/ErrorStruct.php new file mode 100644 index 0000000..cf869d3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/ErrorStruct.php @@ -0,0 +1,74 @@ +children[$type][$id])) { + $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); + $this->children[$type][$id]->type = $type; + } + return $this->children[$type][$id]; + } + + /** + * @param int $severity + * @param string $message + */ + public function addError($severity, $message) + { + $this->errors[] = array($severity, $message); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Exception.php b/software/HTMLPurifier/HTMLPurifier/Exception.php new file mode 100644 index 0000000..be85b4c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Exception.php @@ -0,0 +1,12 @@ +preFilter, + * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter, + * 1->postFilter. + * + * @note Methods are not declared abstract as it is perfectly legitimate + * for an implementation not to want anything to happen on a step + */ + +class HTMLPurifier_Filter +{ + + /** + * Name of the filter for identification purposes. + * @type string + */ + public $name; + + /** + * Pre-processor function, handles HTML before HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function preFilter($html, $config, $context) + { + return $html; + } + + /** + * Post-processor function, handles HTML after HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + return $html; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php b/software/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php new file mode 100644 index 0000000..66f70b0 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php @@ -0,0 +1,341 @@ + blocks from input HTML, cleans them up + * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') + * so they can be used elsewhere in the document. + * + * @note + * See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for + * sample usage. + * + * @note + * This filter can also be used on stylesheets not included in the + * document--something purists would probably prefer. Just directly + * call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS() + */ +class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter +{ + /** + * @type string + */ + public $name = 'ExtractStyleBlocks'; + + /** + * @type array + */ + private $_styleMatches = array(); + + /** + * @type csstidy + */ + private $_tidy; + + /** + * @type HTMLPurifier_AttrDef_HTML_ID + */ + private $_id_attrdef; + + /** + * @type HTMLPurifier_AttrDef_CSS_Ident + */ + private $_class_attrdef; + + /** + * @type HTMLPurifier_AttrDef_Enum + */ + private $_enum_attrdef; + + public function __construct() + { + $this->_tidy = new csstidy(); + $this->_tidy->set_cfg('lowercase_s', false); + $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); + $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); + $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( + array( + 'first-child', + 'link', + 'visited', + 'active', + 'hover', + 'focus' + ) + ); + } + + /** + * Save the contents of CSS blocks to style matches + * @param array $matches preg_replace style $matches array + */ + protected function styleCallback($matches) + { + $this->_styleMatches[] = $matches[1]; + } + + /** + * Removes inline + // we must not grab foo in a font-family prop). + if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { + $css = str_replace( + array('<', '>', '&'), + array('\3C ', '\3E ', '\26 '), + $css + ); + } + return $css; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Filter/YouTube.php b/software/HTMLPurifier/HTMLPurifier/Filter/YouTube.php new file mode 100644 index 0000000..276d836 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Filter/YouTube.php @@ -0,0 +1,65 @@ +]+>.+?' . + '(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?#s'; + $pre_replace = '\1'; + return preg_replace($pre_regex, $pre_replace, $html); + } + + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + $post_regex = '#((?:v|cp)/[A-Za-z0-9\-_=]+)#'; + return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); + } + + /** + * @param $url + * @return string + */ + protected function armorUrl($url) + { + return str_replace('--', '--', $url); + } + + /** + * @param array $matches + * @return string + */ + protected function postFilterCallback($matches) + { + $url = $this->armorUrl($matches[1]); + return '' . + '' . + '' . + ''; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Generator.php b/software/HTMLPurifier/HTMLPurifier/Generator.php new file mode 100644 index 0000000..eb56e2d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Generator.php @@ -0,0 +1,286 @@ + tags. + * @type bool + */ + private $_scriptFix = false; + + /** + * Cache of HTMLDefinition during HTML output to determine whether or + * not attributes should be minimized. + * @type HTMLPurifier_HTMLDefinition + */ + private $_def; + + /** + * Cache of %Output.SortAttr. + * @type bool + */ + private $_sortAttr; + + /** + * Cache of %Output.FlashCompat. + * @type bool + */ + private $_flashCompat; + + /** + * Cache of %Output.FixInnerHTML. + * @type bool + */ + private $_innerHTMLFix; + + /** + * Stack for keeping track of object information when outputting IE + * compatibility code. + * @type array + */ + private $_flashStack = array(); + + /** + * Configuration for the generator + * @type HTMLPurifier_Config + */ + protected $config; + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + public function __construct($config, $context) + { + $this->config = $config; + $this->_scriptFix = $config->get('Output.CommentScriptContents'); + $this->_innerHTMLFix = $config->get('Output.FixInnerHTML'); + $this->_sortAttr = $config->get('Output.SortAttr'); + $this->_flashCompat = $config->get('Output.FlashCompat'); + $this->_def = $config->getHTMLDefinition(); + $this->_xhtml = $this->_def->doctype->xml; + } + + /** + * Generates HTML from an array of tokens. + * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token + * @return string Generated HTML + */ + public function generateFromTokens($tokens) + { + if (!$tokens) { + return ''; + } + + // Basic algorithm + $html = ''; + for ($i = 0, $size = count($tokens); $i < $size; $i++) { + if ($this->_scriptFix && $tokens[$i]->name === 'script' + && $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) { + // script special case + // the contents of the script block must be ONE token + // for this to work. + $html .= $this->generateFromToken($tokens[$i++]); + $html .= $this->generateScriptFromToken($tokens[$i++]); + } + $html .= $this->generateFromToken($tokens[$i]); + } + + // Tidy cleanup + if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) { + $tidy = new Tidy; + $tidy->parseString( + $html, + array( + 'indent'=> true, + 'output-xhtml' => $this->_xhtml, + 'show-body-only' => true, + 'indent-spaces' => 2, + 'wrap' => 68, + ), + 'utf8' + ); + $tidy->cleanRepair(); + $html = (string) $tidy; // explicit cast necessary + } + + // Normalize newlines to system defined value + if ($this->config->get('Core.NormalizeNewlines')) { + $nl = $this->config->get('Output.Newline'); + if ($nl === null) { + $nl = PHP_EOL; + } + if ($nl !== "\n") { + $html = str_replace("\n", $nl, $html); + } + } + return $html; + } + + /** + * Generates HTML from a single token. + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string Generated HTML + */ + public function generateFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token) { + trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING); + return ''; + + } elseif ($token instanceof HTMLPurifier_Token_Start) { + $attr = $this->generateAttributes($token->attr, $token->name); + if ($this->_flashCompat) { + if ($token->name == "object") { + $flash = new stdClass(); + $flash->attr = $token->attr; + $flash->param = array(); + $this->_flashStack[] = $flash; + } + } + return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_End) { + $_extra = ''; + if ($this->_flashCompat) { + if ($token->name == "object" && !empty($this->_flashStack)) { + // doesn't do anything for now + } + } + return $_extra . 'name . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + if ($this->_flashCompat && $token->name == "param" && !empty($this->_flashStack)) { + $this->_flashStack[count($this->_flashStack)-1]->param[$token->attr['name']] = $token->attr['value']; + } + $attr = $this->generateAttributes($token->attr, $token->name); + return '<' . $token->name . ($attr ? ' ' : '') . $attr . + ( $this->_xhtml ? ' /': '' ) //
v.
+ . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Text) { + return $this->escape($token->data, ENT_NOQUOTES); + + } elseif ($token instanceof HTMLPurifier_Token_Comment) { + return ''; + } else { + return ''; + + } + } + + /** + * Special case processor for the contents of script tags + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string + * @warning This runs into problems if there's already a literal + * --> somewhere inside the script contents. + */ + public function generateScriptFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token_Text) { + return $this->generateFromToken($token); + } + // Thanks + $data = preg_replace('#//\s*$#', '', $token->data); + return ''; + } + + /** + * Generates attribute declarations from attribute array. + * @note This does not include the leading or trailing space. + * @param array $assoc_array_of_attributes Attribute array + * @param string $element Name of element attributes are for, used to check + * attribute minimization. + * @return string Generated HTML fragment for insertion. + */ + public function generateAttributes($assoc_array_of_attributes, $element = '') + { + $html = ''; + if ($this->_sortAttr) { + ksort($assoc_array_of_attributes); + } + foreach ($assoc_array_of_attributes as $key => $value) { + if (!$this->_xhtml) { + // Remove namespaced attributes + if (strpos($key, ':') !== false) { + continue; + } + // Check if we should minimize the attribute: val="val" -> val + if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) { + $html .= $key . ' '; + continue; + } + } + // Workaround for Internet Explorer innerHTML bug. + // Essentially, Internet Explorer, when calculating + // innerHTML, omits quotes if there are no instances of + // angled brackets, quotes or spaces. However, when parsing + // HTML (for example, when you assign to innerHTML), it + // treats backticks as quotes. Thus, + // `` + // becomes + // `` + // becomes + // + // Fortunately, all we need to do is trigger an appropriate + // quoting style, which we do by adding an extra space. + // This also is consistent with the W3C spec, which states + // that user agents may ignore leading or trailing + // whitespace (in fact, most don't, at least for attributes + // like alt, but an extra space at the end is barely + // noticeable). Still, we have a configuration knob for + // this, since this transformation is not necesary if you + // don't process user input with innerHTML or you don't plan + // on supporting Internet Explorer. + if ($this->_innerHTMLFix) { + if (strpos($value, '`') !== false) { + // check if correct quoting style would not already be + // triggered + if (strcspn($value, '"\' <>') === strlen($value)) { + // protect! + $value .= ' '; + } + } + } + $html .= $key.'="'.$this->escape($value).'" '; + } + return rtrim($html); + } + + /** + * Escapes raw text data. + * @todo This really ought to be protected, but until we have a facility + * for properly generating HTML here w/o using tokens, it stays + * public. + * @param string $string String data to escape for HTML. + * @param int $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is + * permissible for non-attribute output. + * @return string escaped data. + */ + public function escape($string, $quote = null) + { + // Workaround for APC bug on Mac Leopard reported by sidepodcast + // http://htmlpurifier.org/phorum/read.php?3,4823,4846 + if ($quote === null) { + $quote = ENT_COMPAT; + } + return htmlspecialchars($string, $quote, 'UTF-8'); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLDefinition.php b/software/HTMLPurifier/HTMLPurifier/HTMLDefinition.php new file mode 100644 index 0000000..9b7b334 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLDefinition.php @@ -0,0 +1,493 @@ +getAnonymousModule(); + if (!isset($module->info[$element_name])) { + $element = $module->addBlankElement($element_name); + } else { + $element = $module->info[$element_name]; + } + $element->attr[$attr_name] = $def; + } + + /** + * Adds a custom element to your HTML definition + * @see HTMLPurifier_HTMLModule::addElement() for detailed + * parameter and return value descriptions. + */ + public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array()) + { + $module = $this->getAnonymousModule(); + // assume that if the user is calling this, the element + // is safe. This may not be a good idea + $element = $module->addElement($element_name, $type, $contents, $attr_collections, $attributes); + return $element; + } + + /** + * Adds a blank element to your HTML definition, for overriding + * existing behavior + * @param string $element_name + * @return HTMLPurifier_ElementDef + * @see HTMLPurifier_HTMLModule::addBlankElement() for detailed + * parameter and return value descriptions. + */ + public function addBlankElement($element_name) + { + $module = $this->getAnonymousModule(); + $element = $module->addBlankElement($element_name); + return $element; + } + + /** + * Retrieves a reference to the anonymous module, so you can + * bust out advanced features without having to make your own + * module. + * @return HTMLPurifier_HTMLModule + */ + public function getAnonymousModule() + { + if (!$this->_anonModule) { + $this->_anonModule = new HTMLPurifier_HTMLModule(); + $this->_anonModule->name = 'Anonymous'; + } + return $this->_anonModule; + } + + private $_anonModule = null; + + // PUBLIC BUT INTERNAL VARIABLES -------------------------------------- + + /** + * @type string + */ + public $type = 'HTML'; + + /** + * @type HTMLPurifier_HTMLModuleManager + */ + public $manager; + + /** + * Performs low-cost, preliminary initialization. + */ + public function __construct() + { + $this->manager = new HTMLPurifier_HTMLModuleManager(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetup($config) + { + $this->processModules($config); + $this->setupConfigStuff($config); + unset($this->manager); + + // cleanup some of the element definitions + foreach ($this->info as $k => $v) { + unset($this->info[$k]->content_model); + unset($this->info[$k]->content_model_type); + } + } + + /** + * Extract out the information from the manager + * @param HTMLPurifier_Config $config + */ + protected function processModules($config) + { + if ($this->_anonModule) { + // for user specific changes + // this is late-loaded so we don't have to deal with PHP4 + // reference wonky-ness + $this->manager->addModule($this->_anonModule); + unset($this->_anonModule); + } + + $this->manager->setup($config); + $this->doctype = $this->manager->doctype; + + foreach ($this->manager->modules as $module) { + foreach ($module->info_tag_transform as $k => $v) { + if ($v === false) { + unset($this->info_tag_transform[$k]); + } else { + $this->info_tag_transform[$k] = $v; + } + } + foreach ($module->info_attr_transform_pre as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_pre[$k]); + } else { + $this->info_attr_transform_pre[$k] = $v; + } + } + foreach ($module->info_attr_transform_post as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_post[$k]); + } else { + $this->info_attr_transform_post[$k] = $v; + } + } + foreach ($module->info_injector as $k => $v) { + if ($v === false) { + unset($this->info_injector[$k]); + } else { + $this->info_injector[$k] = $v; + } + } + } + $this->info = $this->manager->getElements(); + $this->info_content_sets = $this->manager->contentSets->lookup; + } + + /** + * Sets up stuff based on config. We need a better way of doing this. + * @param HTMLPurifier_Config $config + */ + protected function setupConfigStuff($config) + { + $block_wrapper = $config->get('HTML.BlockWrapper'); + if (isset($this->info_content_sets['Block'][$block_wrapper])) { + $this->info_block_wrapper = $block_wrapper; + } else { + trigger_error( + 'Cannot use non-block element as block wrapper', + E_USER_ERROR + ); + } + + $parent = $config->get('HTML.Parent'); + $def = $this->manager->getElement($parent, true); + if ($def) { + $this->info_parent = $parent; + $this->info_parent_def = $def; + } else { + trigger_error( + 'Cannot use unrecognized element as parent', + E_USER_ERROR + ); + $this->info_parent_def = $this->manager->getElement($this->info_parent, true); + } + + // support template text + $support = "(for information on implementing this, see the support forums) "; + + // setup allowed elements ----------------------------------------- + + $allowed_elements = $config->get('HTML.AllowedElements'); + $allowed_attributes = $config->get('HTML.AllowedAttributes'); // retrieve early + + if (!is_array($allowed_elements) && !is_array($allowed_attributes)) { + $allowed = $config->get('HTML.Allowed'); + if (is_string($allowed)) { + list($allowed_elements, $allowed_attributes) = $this->parseTinyMCEAllowedList($allowed); + } + } + + if (is_array($allowed_elements)) { + foreach ($this->info as $name => $d) { + if (!isset($allowed_elements[$name])) { + unset($this->info[$name]); + } + unset($allowed_elements[$name]); + } + // emit errors + foreach ($allowed_elements as $element => $d) { + $element = htmlspecialchars($element); // PHP doesn't escape errors, be careful! + trigger_error("Element '$element' is not supported $support", E_USER_WARNING); + } + } + + // setup allowed attributes --------------------------------------- + + $allowed_attributes_mutable = $allowed_attributes; // by copy! + if (is_array($allowed_attributes)) { + // This actually doesn't do anything, since we went away from + // global attributes. It's possible that userland code uses + // it, but HTMLModuleManager doesn't! + foreach ($this->info_global_attr as $attr => $x) { + $keys = array($attr, "*@$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + unset($this->info_global_attr[$attr]); + } + } + + foreach ($this->info as $tag => $info) { + foreach ($info->attr as $attr => $x) { + $keys = array("$tag@$attr", $attr, "*@$attr", "$tag.$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + if ($this->info[$tag]->attr[$attr]->required) { + trigger_error( + "Required attribute '$attr' in element '$tag' " . + "was not allowed, which means '$tag' will not be allowed either", + E_USER_WARNING + ); + } + unset($this->info[$tag]->attr[$attr]); + } + } + } + // emit errors + foreach ($allowed_attributes_mutable as $elattr => $d) { + $bits = preg_split('/[.@]/', $elattr, 2); + $c = count($bits); + switch ($c) { + case 2: + if ($bits[0] !== '*') { + $element = htmlspecialchars($bits[0]); + $attribute = htmlspecialchars($bits[1]); + if (!isset($this->info[$element])) { + trigger_error( + "Cannot allow attribute '$attribute' if element " . + "'$element' is not allowed/supported $support" + ); + } else { + trigger_error( + "Attribute '$attribute' in element '$element' not supported $support", + E_USER_WARNING + ); + } + break; + } + // otherwise fall through + case 1: + $attribute = htmlspecialchars($bits[0]); + trigger_error( + "Global attribute '$attribute' is not ". + "supported in any elements $support", + E_USER_WARNING + ); + break; + } + } + } + + // setup forbidden elements --------------------------------------- + + $forbidden_elements = $config->get('HTML.ForbiddenElements'); + $forbidden_attributes = $config->get('HTML.ForbiddenAttributes'); + + foreach ($this->info as $tag => $info) { + if (isset($forbidden_elements[$tag])) { + unset($this->info[$tag]); + continue; + } + foreach ($info->attr as $attr => $x) { + if (isset($forbidden_attributes["$tag@$attr"]) || + isset($forbidden_attributes["*@$attr"]) || + isset($forbidden_attributes[$attr]) + ) { + unset($this->info[$tag]->attr[$attr]); + continue; + } elseif (isset($forbidden_attributes["$tag.$attr"])) { // this segment might get removed eventually + // $tag.$attr are not user supplied, so no worries! + trigger_error( + "Error with $tag.$attr: tag.attr syntax not supported for " . + "HTML.ForbiddenAttributes; use tag@attr instead", + E_USER_WARNING + ); + } + } + } + foreach ($forbidden_attributes as $key => $v) { + if (strlen($key) < 2) { + continue; + } + if ($key[0] != '*') { + continue; + } + if ($key[1] == '.') { + trigger_error( + "Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead", + E_USER_WARNING + ); + } + } + + // setup injectors ----------------------------------------------------- + foreach ($this->info_injector as $i => $injector) { + if ($injector->checkNeeded($config) !== false) { + // remove injector that does not have it's required + // elements/attributes present, and is thus not needed. + unset($this->info_injector[$i]); + } + } + } + + /** + * Parses a TinyMCE-flavored Allowed Elements and Attributes list into + * separate lists for processing. Format is element[attr1|attr2],element2... + * @warning Although it's largely drawn from TinyMCE's implementation, + * it is different, and you'll probably have to modify your lists + * @param array $list String list to parse + * @return array + * @todo Give this its own class, probably static interface + */ + public function parseTinyMCEAllowedList($list) + { + $list = str_replace(array(' ', "\t"), '', $list); + + $elements = array(); + $attributes = array(); + + $chunks = preg_split('/(,|[\n\r]+)/', $list); + foreach ($chunks as $chunk) { + if (empty($chunk)) { + continue; + } + // remove TinyMCE element control characters + if (!strpos($chunk, '[')) { + $element = $chunk; + $attr = false; + } else { + list($element, $attr) = explode('[', $chunk); + } + if ($element !== '*') { + $elements[$element] = true; + } + if (!$attr) { + continue; + } + $attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ] + $attr = explode('|', $attr); + foreach ($attr as $key) { + $attributes["$element.$key"] = true; + } + } + return array($elements, $attributes); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule.php new file mode 100644 index 0000000..9dbb987 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule.php @@ -0,0 +1,285 @@ +info, since the object's data is only info, + * with extra behavior associated with it. + * @type array + */ + public $attr_collections = array(); + + /** + * Associative array of deprecated tag name to HTMLPurifier_TagTransform. + * @type array + */ + public $info_tag_transform = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed before validation. + * @type array + */ + public $info_attr_transform_pre = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed after validation. + * @type array + */ + public $info_attr_transform_post = array(); + + /** + * List of HTMLPurifier_Injector to be performed during well-formedness fixing. + * An injector will only be invoked if all of it's pre-requisites are met; + * if an injector fails setup, there will be no error; it will simply be + * silently disabled. + * @type array + */ + public $info_injector = array(); + + /** + * Boolean flag that indicates whether or not getChildDef is implemented. + * For optimization reasons: may save a call to a function. Be sure + * to set it if you do implement getChildDef(), otherwise it will have + * no effect! + * @type bool + */ + public $defines_child_def = false; + + /** + * Boolean flag whether or not this module is safe. If it is not safe, all + * of its members are unsafe. Modules are safe by default (this might be + * slightly dangerous, but it doesn't make much sense to force HTML Purifier, + * which is based off of safe HTML, to explicitly say, "This is safe," even + * though there are modules which are "unsafe") + * + * @type bool + * @note Previously, safety could be applied at an element level granularity. + * We've removed this ability, so in order to add "unsafe" elements + * or attributes, a dedicated module with this property set to false + * must be used. + */ + public $safe = true; + + /** + * Retrieves a proper HTMLPurifier_ChildDef subclass based on + * content_model and content_model_type member variables of + * the HTMLPurifier_ElementDef class. There is a similar function + * in HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef subclass + */ + public function getChildDef($def) + { + return false; + } + + // -- Convenience ----------------------------------------------------- + + /** + * Convenience function that sets up a new element + * @param string $element Name of element to add + * @param string|bool $type What content set should element be registered to? + * Set as false to skip this step. + * @param string|HTMLPurifier_ChildDef $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @param array|string $attr_includes What attribute collections to register to + * element? + * @param array $attr What unique attributes does the element define? + * @see HTMLPurifier_ElementDef:: for in-depth descriptions of these parameters. + * @return HTMLPurifier_ElementDef Created element definition object, so you + * can set advanced parameters + */ + public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array()) + { + $this->elements[] = $element; + // parse content_model + list($content_model_type, $content_model) = $this->parseContents($contents); + // merge in attribute inclusions + $this->mergeInAttrIncludes($attr, $attr_includes); + // add element to content sets + if ($type) { + $this->addElementToContentSet($element, $type); + } + // create element + $this->info[$element] = HTMLPurifier_ElementDef::create( + $content_model, + $content_model_type, + $attr + ); + // literal object $contents means direct child manipulation + if (!is_string($contents)) { + $this->info[$element]->child = $contents; + } + return $this->info[$element]; + } + + /** + * Convenience function that creates a totally blank, non-standalone + * element. + * @param string $element Name of element to create + * @return HTMLPurifier_ElementDef Created element + */ + public function addBlankElement($element) + { + if (!isset($this->info[$element])) { + $this->elements[] = $element; + $this->info[$element] = new HTMLPurifier_ElementDef(); + $this->info[$element]->standalone = false; + } else { + trigger_error("Definition for $element already exists in module, cannot redefine"); + } + return $this->info[$element]; + } + + /** + * Convenience function that registers an element to a content set + * @param string $element Element to register + * @param string $type Name content set (warning: case sensitive, usually upper-case + * first letter) + */ + public function addElementToContentSet($element, $type) + { + if (!isset($this->content_sets[$type])) { + $this->content_sets[$type] = ''; + } else { + $this->content_sets[$type] .= ' | '; + } + $this->content_sets[$type] .= $element; + } + + /** + * Convenience function that transforms single-string contents + * into separate content model and content model type + * @param string $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @return array + * @note If contents is an object, an array of two nulls will be + * returned, and the callee needs to take the original $contents + * and use it directly. + */ + public function parseContents($contents) + { + if (!is_string($contents)) { + return array(null, null); + } // defer + switch ($contents) { + // check for shorthand content model forms + case 'Empty': + return array('empty', ''); + case 'Inline': + return array('optional', 'Inline | #PCDATA'); + case 'Flow': + return array('optional', 'Flow | #PCDATA'); + } + list($content_model_type, $content_model) = explode(':', $contents); + $content_model_type = strtolower(trim($content_model_type)); + $content_model = trim($content_model); + return array($content_model_type, $content_model); + } + + /** + * Convenience function that merges a list of attribute includes into + * an attribute array. + * @param array $attr Reference to attr array to modify + * @param array $attr_includes Array of includes / string include to merge in + */ + public function mergeInAttrIncludes(&$attr, $attr_includes) + { + if (!is_array($attr_includes)) { + if (empty($attr_includes)) { + $attr_includes = array(); + } else { + $attr_includes = array($attr_includes); + } + } + $attr[0] = $attr_includes; + } + + /** + * Convenience function that generates a lookup table with boolean + * true as value. + * @param string $list List of values to turn into a lookup + * @note You can also pass an arbitrary number of arguments in + * place of the regular argument + * @return array array equivalent of list + */ + public function makeLookup($list) + { + $args = func_get_args(); + if (is_string($list)) { + $list = $args; + } + $ret = array(); + foreach ($list as $value) { + if (is_null($value)) { + continue; + } + $ret[$value] = true; + } + return $ret; + } + + /** + * Lazy load construction of the module after determining whether + * or not it's needed, and also when a finalized configuration object + * is available. + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php new file mode 100644 index 0000000..1e67c79 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php @@ -0,0 +1,44 @@ + array('dir' => false) + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $bdo = $this->addElement( + 'bdo', + 'Inline', + 'Inline', + array('Core', 'Lang'), + array( + 'dir' => 'Enum#ltr,rtl', // required + // The Abstract Module specification has the attribute + // inclusions wrong for bdo: bdo allows Lang + ) + ); + $bdo->attr_transform_post[] = new HTMLPurifier_AttrTransform_BdoDir(); + + $this->attr_collections['I18N']['dir'] = 'Enum#ltr,rtl'; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php new file mode 100644 index 0000000..7220c14 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php @@ -0,0 +1,32 @@ + array( + 0 => array('Style'), + // 'xml:space' => false, + 'class' => 'Class', + 'id' => 'ID', + 'title' => 'CDATA', + 'contenteditable' => 'ContentEditable', + ), + 'Lang' => array(), + 'I18N' => array( + 0 => array('Lang'), // proprietary, for xml:lang/lang + ), + 'Common' => array( + 0 => array('Core', 'I18N') + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php new file mode 100644 index 0000000..a9042a3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php @@ -0,0 +1,55 @@ + 'URI', + // 'datetime' => 'Datetime', // not implemented + ); + $this->addElement('del', 'Inline', $contents, 'Common', $attr); + $this->addElement('ins', 'Inline', $contents, 'Common', $attr); + } + + // HTML 4.01 specifies that ins/del must not contain block + // elements when used in an inline context, chameleon is + // a complicated workaround to acheive this effect + + // Inline context ! Block context (exclamation mark is + // separator, see getChildDef for parsing) + + /** + * @type bool + */ + public $defines_child_def = true; + + /** + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef_Chameleon + */ + public function getChildDef($def) + { + if ($def->content_model_type != 'chameleon') { + return false; + } + $value = explode('!', $def->content_model); + return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php new file mode 100644 index 0000000..eb0edcf --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php @@ -0,0 +1,194 @@ + 'Form', + 'Inline' => 'Formctrl', + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + if ($config->get('HTML.Forms')) { + $this->safe = true; + } + + $form = $this->addElement( + 'form', + 'Form', + 'Required: Heading | List | Block | fieldset', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accept-charset' => 'Charsets', + 'action*' => 'URI', + 'method' => 'Enum#get,post', + // really ContentType, but these two are the only ones used today + 'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data', + ) + ); + $form->excludes = array('form' => true); + + $input = $this->addElement( + 'input', + 'Formctrl', + 'Empty', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accesskey' => 'Character', + 'alt' => 'Text', + 'checked' => 'Bool#checked', + 'disabled' => 'Bool#disabled', + 'maxlength' => 'Number', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'size' => 'Number', + 'src' => 'URI#embedded', + 'tabindex' => 'Number', + 'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image', + 'value' => 'CDATA', + ) + ); + $input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input(); + + $this->addElement( + 'select', + 'Formctrl', + 'Required: optgroup | option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'multiple' => 'Bool#multiple', + 'name' => 'CDATA', + 'size' => 'Number', + 'tabindex' => 'Number', + ) + ); + + $this->addElement( + 'option', + false, + 'Optional: #PCDATA', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label' => 'Text', + 'selected' => 'Bool#selected', + 'value' => 'CDATA', + ) + ); + // It's illegal for there to be more than one selected, but not + // be multiple. Also, no selected means undefined behavior. This might + // be difficult to implement; perhaps an injector, or a context variable. + + $textarea = $this->addElement( + 'textarea', + 'Formctrl', + 'Optional: #PCDATA', + 'Common', + array( + 'accesskey' => 'Character', + 'cols*' => 'Number', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'rows*' => 'Number', + 'tabindex' => 'Number', + ) + ); + $textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea(); + + $button = $this->addElement( + 'button', + 'Formctrl', + 'Optional: #PCDATA | Heading | List | Block | Inline', + 'Common', + array( + 'accesskey' => 'Character', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'tabindex' => 'Number', + 'type' => 'Enum#button,submit,reset', + 'value' => 'CDATA', + ) + ); + + // For exclusions, ideally we'd specify content sets, not literal elements + $button->excludes = $this->makeLookup( + 'form', + 'fieldset', // Form + 'input', + 'select', + 'textarea', + 'label', + 'button', // Formctrl + 'a', // as per HTML 4.01 spec, this is omitted by modularization + 'isindex', + 'iframe' // legacy items + ); + + // Extra exclusion: img usemap="" is not permitted within this element. + // We'll omit this for now, since we don't have any good way of + // indicating it yet. + + // This is HIGHLY user-unfriendly; we need a custom child-def for this + $this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common'); + + $label = $this->addElement( + 'label', + 'Formctrl', + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + // 'for' => 'IDREF', // IDREF not implemented, cannot allow + ) + ); + $label->excludes = array('label' => true); + + $this->addElement( + 'legend', + false, + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + ) + ); + + $this->addElement( + 'optgroup', + false, + 'Required: option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label*' => 'Text', + ) + ); + // Don't forget an injector for . This one's a little complex + // because it maps to multiple elements. + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php new file mode 100644 index 0000000..72d7a31 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php @@ -0,0 +1,40 @@ +addElement( + 'a', + 'Inline', + 'Inline', + 'Common', + array( + // 'accesskey' => 'Character', + // 'charset' => 'Charset', + 'href' => 'URI', + // 'hreflang' => 'LanguageCode', + 'rel' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rel'), + 'rev' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rev'), + // 'tabindex' => 'Number', + // 'type' => 'ContentType', + ) + ); + $a->formatting = true; + $a->excludes = array('a' => true); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php new file mode 100644 index 0000000..f7e7c91 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php @@ -0,0 +1,51 @@ +get('HTML.SafeIframe')) { + $this->safe = true; + } + $this->addElement( + 'iframe', + 'Inline', + 'Flow', + 'Common', + array( + 'src' => 'URI#embedded', + 'width' => 'Length', + 'height' => 'Length', + 'name' => 'ID', + 'scrolling' => 'Enum#yes,no,auto', + 'frameborder' => 'Enum#0,1', + 'longdesc' => 'URI', + 'marginheight' => 'Pixels', + 'marginwidth' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php new file mode 100644 index 0000000..0f5fdb3 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php @@ -0,0 +1,49 @@ +get('HTML.MaxImgLength'); + $img = $this->addElement( + 'img', + 'Inline', + 'Empty', + 'Common', + array( + 'alt*' => 'Text', + // According to the spec, it's Length, but percents can + // be abused, so we allow only Pixels. + 'height' => 'Pixels#' . $max, + 'width' => 'Pixels#' . $max, + 'longdesc' => 'URI', + 'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded + ) + ); + if ($max === null || $config->get('HTML.Trusted')) { + $img->attr['height'] = + $img->attr['width'] = 'Length'; + } + + // kind of strange, but splitting things up would be inefficient + $img->attr_transform_pre[] = + $img->attr_transform_post[] = + new HTMLPurifier_AttrTransform_ImgRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php new file mode 100644 index 0000000..86b5299 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php @@ -0,0 +1,186 @@ +addElement( + 'basefont', + 'Inline', + 'Empty', + null, + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + 'id' => 'ID' + ) + ); + $this->addElement('center', 'Block', 'Flow', 'Common'); + $this->addElement( + 'dir', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + $this->addElement( + 'font', + 'Inline', + 'Inline', + array('Core', 'I18N'), + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + ) + ); + $this->addElement( + 'menu', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + + $s = $this->addElement('s', 'Inline', 'Inline', 'Common'); + $s->formatting = true; + + $strike = $this->addElement('strike', 'Inline', 'Inline', 'Common'); + $strike->formatting = true; + + $u = $this->addElement('u', 'Inline', 'Inline', 'Common'); + $u->formatting = true; + + // setup modifications to old elements + + $align = 'Enum#left,right,center,justify'; + + $address = $this->addBlankElement('address'); + $address->content_model = 'Inline | #PCDATA | p'; + $address->content_model_type = 'optional'; + $address->child = false; + + $blockquote = $this->addBlankElement('blockquote'); + $blockquote->content_model = 'Flow | #PCDATA'; + $blockquote->content_model_type = 'optional'; + $blockquote->child = false; + + $br = $this->addBlankElement('br'); + $br->attr['clear'] = 'Enum#left,all,right,none'; + + $caption = $this->addBlankElement('caption'); + $caption->attr['align'] = 'Enum#top,bottom,left,right'; + + $div = $this->addBlankElement('div'); + $div->attr['align'] = $align; + + $dl = $this->addBlankElement('dl'); + $dl->attr['compact'] = 'Bool#compact'; + + for ($i = 1; $i <= 6; $i++) { + $h = $this->addBlankElement("h$i"); + $h->attr['align'] = $align; + } + + $hr = $this->addBlankElement('hr'); + $hr->attr['align'] = $align; + $hr->attr['noshade'] = 'Bool#noshade'; + $hr->attr['size'] = 'Pixels'; + $hr->attr['width'] = 'Length'; + + $img = $this->addBlankElement('img'); + $img->attr['align'] = 'IAlign'; + $img->attr['border'] = 'Pixels'; + $img->attr['hspace'] = 'Pixels'; + $img->attr['vspace'] = 'Pixels'; + + // figure out this integer business + + $li = $this->addBlankElement('li'); + $li->attr['value'] = new HTMLPurifier_AttrDef_Integer(); + $li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle'; + + $ol = $this->addBlankElement('ol'); + $ol->attr['compact'] = 'Bool#compact'; + $ol->attr['start'] = new HTMLPurifier_AttrDef_Integer(); + $ol->attr['type'] = 'Enum#s:1,i,I,a,A'; + + $p = $this->addBlankElement('p'); + $p->attr['align'] = $align; + + $pre = $this->addBlankElement('pre'); + $pre->attr['width'] = 'Number'; + + // script omitted + + $table = $this->addBlankElement('table'); + $table->attr['align'] = 'Enum#left,center,right'; + $table->attr['bgcolor'] = 'Color'; + + $tr = $this->addBlankElement('tr'); + $tr->attr['bgcolor'] = 'Color'; + + $th = $this->addBlankElement('th'); + $th->attr['bgcolor'] = 'Color'; + $th->attr['height'] = 'Length'; + $th->attr['nowrap'] = 'Bool#nowrap'; + $th->attr['width'] = 'Length'; + + $td = $this->addBlankElement('td'); + $td->attr['bgcolor'] = 'Color'; + $td->attr['height'] = 'Length'; + $td->attr['nowrap'] = 'Bool#nowrap'; + $td->attr['width'] = 'Length'; + + $ul = $this->addBlankElement('ul'); + $ul->attr['compact'] = 'Bool#compact'; + $ul->attr['type'] = 'Enum#square,disc,circle'; + + // "safe" modifications to "unsafe" elements + // WARNING: If you want to add support for an unsafe, legacy + // attribute, make a new TrustedLegacy module with the trusted + // bit set appropriately + + $form = $this->addBlankElement('form'); + $form->content_model = 'Flow | #PCDATA'; + $form->content_model_type = 'optional'; + $form->attr['target'] = 'FrameTarget'; + + $input = $this->addBlankElement('input'); + $input->attr['align'] = 'IAlign'; + + $legend = $this->addBlankElement('legend'); + $legend->attr['align'] = 'LAlign'; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/List.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/List.php new file mode 100644 index 0000000..7a20ff7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/List.php @@ -0,0 +1,51 @@ + 'List'); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $ol = $this->addElement('ol', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + $ul = $this->addElement('ul', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + // XXX The wrap attribute is handled by MakeWellFormed. This is all + // quite unsatisfactory, because we generated this + // *specifically* for lists, and now a big chunk of the handling + // is done properly by the List ChildDef. So actually, we just + // want enough information to make autoclosing work properly, + // and then hand off the tricky stuff to the ChildDef. + $ol->wrap = 'li'; + $ul->wrap = 'li'; + $this->addElement('dl', 'List', 'Required: dt | dd', 'Common'); + + $this->addElement('li', false, 'Flow', 'Common'); + + $this->addElement('dd', false, 'Flow', 'Common'); + $this->addElement('dt', false, 'Inline', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php new file mode 100644 index 0000000..60c0545 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php @@ -0,0 +1,26 @@ +addBlankElement($name); + $element->attr['name'] = 'CDATA'; + if (!$config->get('HTML.Attr.Name.UseCDATA')) { + $element->attr_transform_post[] = new HTMLPurifier_AttrTransform_NameSync(); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php new file mode 100644 index 0000000..dc9410a --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php @@ -0,0 +1,25 @@ +addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php new file mode 100644 index 0000000..da72225 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php @@ -0,0 +1,20 @@ + array( + 'lang' => 'LanguageCode', + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php new file mode 100644 index 0000000..2f9efc5 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php @@ -0,0 +1,62 @@ + to cater to legacy browsers: this + * module does not allow this sort of behavior + */ +class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule +{ + /** + * @type string + */ + public $name = 'Object'; + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'object', + 'Inline', + 'Optional: #PCDATA | Flow | param', + 'Common', + array( + 'archive' => 'URI', + 'classid' => 'URI', + 'codebase' => 'URI', + 'codetype' => 'Text', + 'data' => 'URI', + 'declare' => 'Bool#declare', + 'height' => 'Length', + 'name' => 'CDATA', + 'standby' => 'Text', + 'tabindex' => 'Number', + 'type' => 'ContentType', + 'width' => 'Length' + ) + ); + + $this->addElement( + 'param', + false, + 'Empty', + null, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'type' => 'Text', + 'value' => 'Text', + 'valuetype' => 'Enum#data,ref,object' + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php new file mode 100644 index 0000000..6458ce9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php @@ -0,0 +1,42 @@ +addElement('hr', 'Block', 'Empty', 'Common'); + $this->addElement('sub', 'Inline', 'Inline', 'Common'); + $this->addElement('sup', 'Inline', 'Inline', 'Common'); + $b = $this->addElement('b', 'Inline', 'Inline', 'Common'); + $b->formatting = true; + $big = $this->addElement('big', 'Inline', 'Inline', 'Common'); + $big->formatting = true; + $i = $this->addElement('i', 'Inline', 'Inline', 'Common'); + $i->formatting = true; + $small = $this->addElement('small', 'Inline', 'Inline', 'Common'); + $small->formatting = true; + $tt = $this->addElement('tt', 'Inline', 'Inline', 'Common'); + $tt->formatting = true; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php new file mode 100644 index 0000000..5ee3c8e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php @@ -0,0 +1,40 @@ +addElement( + 'marquee', + 'Inline', + 'Flow', + 'Common', + array( + 'direction' => 'Enum#left,right,up,down', + 'behavior' => 'Enum#alternate', + 'width' => 'Length', + 'height' => 'Length', + 'scrolldelay' => 'Number', + 'scrollamount' => 'Number', + 'loop' => 'Number', + 'bgcolor' => 'Color', + 'hspace' => 'Pixels', + 'vspace' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php new file mode 100644 index 0000000..a0d4892 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php @@ -0,0 +1,36 @@ +addElement( + 'ruby', + 'Inline', + 'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))', + 'Common' + ); + $this->addElement('rbc', false, 'Required: rb', 'Common'); + $this->addElement('rtc', false, 'Required: rt', 'Common'); + $rb = $this->addElement('rb', false, 'Inline', 'Common'); + $rb->excludes = array('ruby' => true); + $rt = $this->addElement('rt', false, 'Inline', 'Common', array('rbspan' => 'Number')); + $rt->excludes = array('ruby' => true); + $this->addElement('rp', false, 'Optional: #PCDATA', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php new file mode 100644 index 0000000..04e6689 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php @@ -0,0 +1,40 @@ +get('HTML.MaxImgLength'); + $embed = $this->addElement( + 'embed', + 'Inline', + 'Empty', + 'Common', + array( + 'src*' => 'URI#embedded', + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'allowscriptaccess' => 'Enum#never', + 'allownetworking' => 'Enum#internal', + 'flashvars' => 'Text', + 'wmode' => 'Enum#window,transparent,opaque', + 'name' => 'ID', + ) + ); + $embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php new file mode 100644 index 0000000..1297f80 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php @@ -0,0 +1,62 @@ +get('HTML.MaxImgLength'); + $object = $this->addElement( + 'object', + 'Inline', + 'Optional: param | Flow | #PCDATA', + 'Common', + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'data' => 'URI#embedded', + 'codebase' => new HTMLPurifier_AttrDef_Enum( + array( + 'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0' + ) + ), + ) + ); + $object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject(); + + $param = $this->addElement( + 'param', + false, + 'Empty', + false, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'value' => 'Text' + ) + ); + $param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam(); + $this->info_injector[] = 'SafeObject'; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php new file mode 100644 index 0000000..aea7584 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php @@ -0,0 +1,40 @@ +get('HTML.SafeScripting'); + $script = $this->addElement( + 'script', + 'Inline', + 'Optional:', // Not `Empty` to not allow to autoclose the #i', '', $html); + } + + return $html; + } + + /** + * Takes a string of HTML (fragment or document) and returns the content + * @todo Consider making protected + */ + public function extractBody($html) + { + $matches = array(); + $result = preg_match('|(.*?)]*>(.*)|is', $html, $matches); + if ($result) { + // Make sure it's not in a comment + $comment_start = strrpos($matches[1], ''); + if ($comment_start === false || + ($comment_end !== false && $comment_end > $comment_start)) { + return $matches[2]; + } + } + return $html; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Lexer/DOMLex.php b/software/HTMLPurifier/HTMLPurifier/Lexer/DOMLex.php new file mode 100644 index 0000000..ca5f25b --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Lexer/DOMLex.php @@ -0,0 +1,338 @@ +factory = new HTMLPurifier_TokenFactory(); + } + + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + */ + public function tokenizeHTML($html, $config, $context) + { + $html = $this->normalize($html, $config, $context); + + // attempt to armor stray angled brackets that cannot possibly + // form tags and thus are probably being used as emoticons + if ($config->get('Core.AggressivelyFixLt')) { + $char = '[^a-z!\/]'; + $comment = "/|\z)/is"; + $html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html); + do { + $old = $html; + $html = preg_replace("/<($char)/i", '<\\1', $html); + } while ($html !== $old); + $html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments + } + + // preprocess html, essential for UTF-8 + $html = $this->wrapHTML($html, $config, $context); + + $doc = new DOMDocument(); + $doc->encoding = 'UTF-8'; // theoretically, the above has this covered + + $options = 0; + if ($config->get('Core.AllowParseManyTags') && defined('LIBXML_PARSEHUGE')) { + $options |= LIBXML_PARSEHUGE; + } + + set_error_handler(array($this, 'muteErrorHandler')); + // loadHTML() fails on PHP 5.3 when second parameter is given + if ($options) { + $doc->loadHTML($html, $options); + } else { + $doc->loadHTML($html); + } + restore_error_handler(); + + $body = $doc->getElementsByTagName('html')->item(0)-> // + getElementsByTagName('body')->item(0); // + + $div = $body->getElementsByTagName('div')->item(0); //
+ $tokens = array(); + $this->tokenizeDOM($div, $tokens, $config); + // If the div has a sibling, that means we tripped across + // a premature
tag. So remove the div we parsed, + // and then tokenize the rest of body. We can't tokenize + // the sibling directly as we'll lose the tags in that case. + if ($div->nextSibling) { + $body->removeChild($div); + $this->tokenizeDOM($body, $tokens, $config); + } + return $tokens; + } + + /** + * Iterative function that tokenizes a node, putting it into an accumulator. + * To iterate is human, to recurse divine - L. Peter Deutsch + * @param DOMNode $node DOMNode to be tokenized. + * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. + * @return HTMLPurifier_Token of node appended to previously passed tokens. + */ + protected function tokenizeDOM($node, &$tokens, $config) + { + $level = 0; + $nodes = array($level => new HTMLPurifier_Queue(array($node))); + $closingNodes = array(); + do { + while (!$nodes[$level]->isEmpty()) { + $node = $nodes[$level]->shift(); // FIFO + $collect = $level > 0 ? true : false; + $needEndingTag = $this->createStartNode($node, $tokens, $collect, $config); + if ($needEndingTag) { + $closingNodes[$level][] = $node; + } + if ($node->childNodes && $node->childNodes->length) { + $level++; + $nodes[$level] = new HTMLPurifier_Queue(); + foreach ($node->childNodes as $childNode) { + $nodes[$level]->push($childNode); + } + } + } + $level--; + if ($level && isset($closingNodes[$level])) { + while ($node = array_pop($closingNodes[$level])) { + $this->createEndNode($node, $tokens); + } + } + } while ($level > 0); + } + + /** + * Portably retrieve the tag name of a node; deals with older versions + * of libxml like 2.7.6 + * @param DOMNode $node + */ + protected function getTagName($node) + { + if (isset($node->tagName)) { + return $node->tagName; + } else if (isset($node->nodeName)) { + return $node->nodeName; + } else if (isset($node->localName)) { + return $node->localName; + } + return null; + } + + /** + * Portably retrieve the data of a node; deals with older versions + * of libxml like 2.7.6 + * @param DOMNode $node + */ + protected function getData($node) + { + if (isset($node->data)) { + return $node->data; + } else if (isset($node->nodeValue)) { + return $node->nodeValue; + } else if (isset($node->textContent)) { + return $node->textContent; + } + return null; + } + + + /** + * @param DOMNode $node DOMNode to be tokenized. + * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. + * @param bool $collect Says whether or start and close are collected, set to + * false at first recursion because it's the implicit DIV + * tag you're dealing with. + * @return bool if the token needs an endtoken + * @todo data and tagName properties don't seem to exist in DOMNode? + */ + protected function createStartNode($node, &$tokens, $collect, $config) + { + // intercept non element nodes. WE MUST catch all of them, + // but we're not getting the character reference nodes because + // those should have been preprocessed + if ($node->nodeType === XML_TEXT_NODE) { + $data = $this->getData($node); // Handle variable data property + if ($data !== null) { + $tokens[] = $this->factory->createText($data); + } + return false; + } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { + // undo libxml's special treatment of )#si', + array($this, 'scriptCallback'), + $html + ); + } + + $html = $this->normalize($html, $config, $context); + + $cursor = 0; // our location in the text + $inside_tag = false; // whether or not we're parsing the inside of a tag + $array = array(); // result array + + // This is also treated to mean maintain *column* numbers too + $maintain_line_numbers = $config->get('Core.MaintainLineNumbers'); + + if ($maintain_line_numbers === null) { + // automatically determine line numbering by checking + // if error collection is on + $maintain_line_numbers = $config->get('Core.CollectErrors'); + } + + if ($maintain_line_numbers) { + $current_line = 1; + $current_col = 0; + $length = strlen($html); + } else { + $current_line = false; + $current_col = false; + $length = false; + } + $context->register('CurrentLine', $current_line); + $context->register('CurrentCol', $current_col); + $nl = "\n"; + // how often to manually recalculate. This will ALWAYS be right, + // but it's pretty wasteful. Set to 0 to turn off + $synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval'); + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + // for testing synchronization + $loops = 0; + + while (++$loops) { + // $cursor is either at the start of a token, or inside of + // a tag (i.e. there was a < immediately before it), as indicated + // by $inside_tag + + if ($maintain_line_numbers) { + // $rcursor, however, is always at the start of a token. + $rcursor = $cursor - (int)$inside_tag; + + // Column number is cheap, so we calculate it every round. + // We're interested at the *end* of the newline string, so + // we need to add strlen($nl) == 1 to $nl_pos before subtracting it + // from our "rcursor" position. + $nl_pos = strrpos($html, $nl, $rcursor - $length); + $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1); + + // recalculate lines + if ($synchronize_interval && // synchronization is on + $cursor > 0 && // cursor is further than zero + $loops % $synchronize_interval === 0) { // time to synchronize! + $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor); + } + } + + $position_next_lt = strpos($html, '<', $cursor); + $position_next_gt = strpos($html, '>', $cursor); + + // triggers on "asdf" but not "asdf " + // special case to set up context + if ($position_next_lt === $cursor) { + $inside_tag = true; + $cursor++; + } + + if (!$inside_tag && $position_next_lt !== false) { + // We are not inside tag and there still is another tag to parse + $token = new + HTMLPurifier_Token_Text( + $this->parseText( + substr( + $html, + $cursor, + $position_next_lt - $cursor + ), $config + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor); + } + $array[] = $token; + $cursor = $position_next_lt + 1; + $inside_tag = true; + continue; + } elseif (!$inside_tag) { + // We are not inside tag but there are no more tags + // If we're already at the end, break + if ($cursor === strlen($html)) { + break; + } + // Create Text of rest of string + $token = new + HTMLPurifier_Token_Text( + $this->parseText( + substr( + $html, + $cursor + ), $config + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } + $array[] = $token; + break; + } elseif ($inside_tag && $position_next_gt !== false) { + // We are in tag and it is well formed + // Grab the internals of the tag + $strlen_segment = $position_next_gt - $cursor; + + if ($strlen_segment < 1) { + // there's nothing to process! + $token = new HTMLPurifier_Token_Text('<'); + $cursor++; + continue; + } + + $segment = substr($html, $cursor, $strlen_segment); + + if ($segment === false) { + // somehow, we attempted to access beyond the end of + // the string, defense-in-depth, reported by Nate Abele + break; + } + + // Check if it's a comment + if (substr($segment, 0, 3) === '!--') { + // re-determine segment length, looking for --> + $position_comment_end = strpos($html, '-->', $cursor); + if ($position_comment_end === false) { + // uh oh, we have a comment that extends to + // infinity. Can't be helped: set comment + // end position to end of string + if ($e) { + $e->send(E_WARNING, 'Lexer: Unclosed comment'); + } + $position_comment_end = strlen($html); + $end = true; + } else { + $end = false; + } + $strlen_segment = $position_comment_end - $cursor; + $segment = substr($html, $cursor, $strlen_segment); + $token = new + HTMLPurifier_Token_Comment( + substr( + $segment, + 3, + $strlen_segment - 3 + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment); + } + $array[] = $token; + $cursor = $end ? $position_comment_end : $position_comment_end + 3; + $inside_tag = false; + continue; + } + + // Check if it's an end tag + $is_end_tag = (strpos($segment, '/') === 0); + if ($is_end_tag) { + $type = substr($segment, 1); + $token = new HTMLPurifier_Token_End($type); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + $cursor = $position_next_gt + 1; + continue; + } + + // Check leading character is alnum, if not, we may + // have accidently grabbed an emoticon. Translate into + // text and go our merry way + if (!ctype_alpha($segment[0])) { + // XML: $segment[0] !== '_' && $segment[0] !== ':' + if ($e) { + $e->send(E_NOTICE, 'Lexer: Unescaped lt'); + } + $token = new HTMLPurifier_Token_Text('<'); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + continue; + } + + // Check if it is explicitly self closing, if so, remove + // trailing slash. Remember, we could have a tag like
, so + // any later token processing scripts must convert improperly + // classified EmptyTags from StartTags. + $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1); + if ($is_self_closing) { + $strlen_segment--; + $segment = substr($segment, 0, $strlen_segment); + } + + // Check if there are any attributes + $position_first_space = strcspn($segment, $this->_whitespace); + + if ($position_first_space >= $strlen_segment) { + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($segment); + } else { + $token = new HTMLPurifier_Token_Start($segment); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + $cursor = $position_next_gt + 1; + continue; + } + + // Grab out all the data + $type = substr($segment, 0, $position_first_space); + $attribute_string = + trim( + substr( + $segment, + $position_first_space + ) + ); + if ($attribute_string) { + $attr = $this->parseAttributeString( + $attribute_string, + $config, + $context + ); + } else { + $attr = array(); + } + + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($type, $attr); + } else { + $token = new HTMLPurifier_Token_Start($type, $attr); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $cursor = $position_next_gt + 1; + $inside_tag = false; + continue; + } else { + // inside tag, but there's no ending > sign + if ($e) { + $e->send(E_WARNING, 'Lexer: Missing gt'); + } + $token = new + HTMLPurifier_Token_Text( + '<' . + $this->parseText( + substr($html, $cursor), $config + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } + // no cursor scroll? Hmm... + $array[] = $token; + break; + } + break; + } + + $context->destroy('CurrentLine'); + $context->destroy('CurrentCol'); + return $array; + } + + /** + * PHP 5.0.x compatible substr_count that implements offset and length + * @param string $haystack + * @param string $needle + * @param int $offset + * @param int $length + * @return int + */ + protected function substrCount($haystack, $needle, $offset, $length) + { + static $oldVersion; + if ($oldVersion === null) { + $oldVersion = version_compare(PHP_VERSION, '5.1', '<'); + } + if ($oldVersion) { + $haystack = substr($haystack, $offset, $length); + return substr_count($haystack, $needle); + } else { + return substr_count($haystack, $needle, $offset, $length); + } + } + + /** + * Takes the inside of an HTML tag and makes an assoc array of attributes. + * + * @param string $string Inside of tag excluding name. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array Assoc array of attributes. + */ + public function parseAttributeString($string, $config, $context) + { + $string = (string)$string; // quick typecast + + if ($string == '') { + return array(); + } // no attributes + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + // let's see if we can abort as quickly as possible + // one equal sign, no spaces => one attribute + $num_equal = substr_count($string, '='); + $has_space = strpos($string, ' '); + if ($num_equal === 0 && !$has_space) { + // bool attribute + return array($string => $string); + } elseif ($num_equal === 1 && !$has_space) { + // only one attribute + list($key, $quoted_value) = explode('=', $string); + $quoted_value = trim($quoted_value); + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + return array(); + } + if (!$quoted_value) { + return array($key => ''); + } + $first_char = @$quoted_value[0]; + $last_char = @$quoted_value[strlen($quoted_value) - 1]; + + $same_quote = ($first_char == $last_char); + $open_quote = ($first_char == '"' || $first_char == "'"); + + if ($same_quote && $open_quote) { + // well behaved + $value = substr($quoted_value, 1, strlen($quoted_value) - 2); + } else { + // not well behaved + if ($open_quote) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing end quote'); + } + $value = substr($quoted_value, 1); + } else { + $value = $quoted_value; + } + } + if ($value === false) { + $value = ''; + } + return array($key => $this->parseAttr($value, $config)); + } + + // setup loop environment + $array = array(); // return assoc array of attributes + $cursor = 0; // current position in string (moves forward) + $size = strlen($string); // size of the string (stays the same) + + // if we have unquoted attributes, the parser expects a terminating + // space, so let's guarantee that there's always a terminating space. + $string .= ' '; + + $old_cursor = -1; + while ($cursor < $size) { + if ($old_cursor >= $cursor) { + throw new Exception("Infinite loop detected"); + } + $old_cursor = $cursor; + + $cursor += ($value = strspn($string, $this->_whitespace, $cursor)); + // grab the key + + $key_begin = $cursor; //we're currently at the start of the key + + // scroll past all characters that are the key (not whitespace or =) + $cursor += strcspn($string, $this->_whitespace . '=', $cursor); + + $key_end = $cursor; // now at the end of the key + + $key = substr($string, $key_begin, $key_end - $key_begin); + + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop + continue; // empty key + } + + // scroll past all whitespace + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor >= $size) { + $array[$key] = $key; + break; + } + + // if the next character is an equal sign, we've got a regular + // pair, otherwise, it's a bool attribute + $first_char = @$string[$cursor]; + + if ($first_char == '=') { + // key="value" + + $cursor++; + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor === false) { + $array[$key] = ''; + break; + } + + // we might be in front of a quote right now + + $char = @$string[$cursor]; + + if ($char == '"' || $char == "'") { + // it's quoted, end bound is $char + $cursor++; + $value_begin = $cursor; + $cursor = strpos($string, $char, $cursor); + $value_end = $cursor; + } else { + // it's not quoted, end bound is whitespace + $value_begin = $cursor; + $cursor += strcspn($string, $this->_whitespace, $cursor); + $value_end = $cursor; + } + + // we reached a premature end + if ($cursor === false) { + $cursor = $size; + $value_end = $cursor; + } + + $value = substr($string, $value_begin, $value_end - $value_begin); + if ($value === false) { + $value = ''; + } + $array[$key] = $this->parseAttr($value, $config); + $cursor++; + } else { + // boolattr + if ($key !== '') { + $array[$key] = $key; + } else { + // purely theoretical + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + } + } + } + return $array; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php b/software/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php new file mode 100644 index 0000000..1564f28 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php @@ -0,0 +1,4788 @@ +normalize($html, $config, $context); + $new_html = $this->wrapHTML($new_html, $config, $context, false /* no div */); + try { + $parser = new HTML5($new_html); + $doc = $parser->save(); + } catch (DOMException $e) { + // Uh oh, it failed. Punt to DirectLex. + $lexer = new HTMLPurifier_Lexer_DirectLex(); + $context->register('PH5PError', $e); // save the error, so we can detect it + return $lexer->tokenizeHTML($html, $config, $context); // use original HTML + } + $tokens = array(); + $this->tokenizeDOM( + $doc->getElementsByTagName('html')->item(0)-> // + getElementsByTagName('body')->item(0) // + , + $tokens, $config + ); + return $tokens; + } +} + +/* + +Copyright 2007 Jeroen van der Meer + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +*/ + +class HTML5 +{ + private $data; + private $char; + private $EOF; + private $state; + private $tree; + private $token; + private $content_model; + private $escape = false; + private $entities = array( + 'AElig;', + 'AElig', + 'AMP;', + 'AMP', + 'Aacute;', + 'Aacute', + 'Acirc;', + 'Acirc', + 'Agrave;', + 'Agrave', + 'Alpha;', + 'Aring;', + 'Aring', + 'Atilde;', + 'Atilde', + 'Auml;', + 'Auml', + 'Beta;', + 'COPY;', + 'COPY', + 'Ccedil;', + 'Ccedil', + 'Chi;', + 'Dagger;', + 'Delta;', + 'ETH;', + 'ETH', + 'Eacute;', + 'Eacute', + 'Ecirc;', + 'Ecirc', + 'Egrave;', + 'Egrave', + 'Epsilon;', + 'Eta;', + 'Euml;', + 'Euml', + 'GT;', + 'GT', + 'Gamma;', + 'Iacute;', + 'Iacute', + 'Icirc;', + 'Icirc', + 'Igrave;', + 'Igrave', + 'Iota;', + 'Iuml;', + 'Iuml', + 'Kappa;', + 'LT;', + 'LT', + 'Lambda;', + 'Mu;', + 'Ntilde;', + 'Ntilde', + 'Nu;', + 'OElig;', + 'Oacute;', + 'Oacute', + 'Ocirc;', + 'Ocirc', + 'Ograve;', + 'Ograve', + 'Omega;', + 'Omicron;', + 'Oslash;', + 'Oslash', + 'Otilde;', + 'Otilde', + 'Ouml;', + 'Ouml', + 'Phi;', + 'Pi;', + 'Prime;', + 'Psi;', + 'QUOT;', + 'QUOT', + 'REG;', + 'REG', + 'Rho;', + 'Scaron;', + 'Sigma;', + 'THORN;', + 'THORN', + 'TRADE;', + 'Tau;', + 'Theta;', + 'Uacute;', + 'Uacute', + 'Ucirc;', + 'Ucirc', + 'Ugrave;', + 'Ugrave', + 'Upsilon;', + 'Uuml;', + 'Uuml', + 'Xi;', + 'Yacute;', + 'Yacute', + 'Yuml;', + 'Zeta;', + 'aacute;', + 'aacute', + 'acirc;', + 'acirc', + 'acute;', + 'acute', + 'aelig;', + 'aelig', + 'agrave;', + 'agrave', + 'alefsym;', + 'alpha;', + 'amp;', + 'amp', + 'and;', + 'ang;', + 'apos;', + 'aring;', + 'aring', + 'asymp;', + 'atilde;', + 'atilde', + 'auml;', + 'auml', + 'bdquo;', + 'beta;', + 'brvbar;', + 'brvbar', + 'bull;', + 'cap;', + 'ccedil;', + 'ccedil', + 'cedil;', + 'cedil', + 'cent;', + 'cent', + 'chi;', + 'circ;', + 'clubs;', + 'cong;', + 'copy;', + 'copy', + 'crarr;', + 'cup;', + 'curren;', + 'curren', + 'dArr;', + 'dagger;', + 'darr;', + 'deg;', + 'deg', + 'delta;', + 'diams;', + 'divide;', + 'divide', + 'eacute;', + 'eacute', + 'ecirc;', + 'ecirc', + 'egrave;', + 'egrave', + 'empty;', + 'emsp;', + 'ensp;', + 'epsilon;', + 'equiv;', + 'eta;', + 'eth;', + 'eth', + 'euml;', + 'euml', + 'euro;', + 'exist;', + 'fnof;', + 'forall;', + 'frac12;', + 'frac12', + 'frac14;', + 'frac14', + 'frac34;', + 'frac34', + 'frasl;', + 'gamma;', + 'ge;', + 'gt;', + 'gt', + 'hArr;', + 'harr;', + 'hearts;', + 'hellip;', + 'iacute;', + 'iacute', + 'icirc;', + 'icirc', + 'iexcl;', + 'iexcl', + 'igrave;', + 'igrave', + 'image;', + 'infin;', + 'int;', + 'iota;', + 'iquest;', + 'iquest', + 'isin;', + 'iuml;', + 'iuml', + 'kappa;', + 'lArr;', + 'lambda;', + 'lang;', + 'laquo;', + 'laquo', + 'larr;', + 'lceil;', + 'ldquo;', + 'le;', + 'lfloor;', + 'lowast;', + 'loz;', + 'lrm;', + 'lsaquo;', + 'lsquo;', + 'lt;', + 'lt', + 'macr;', + 'macr', + 'mdash;', + 'micro;', + 'micro', + 'middot;', + 'middot', + 'minus;', + 'mu;', + 'nabla;', + 'nbsp;', + 'nbsp', + 'ndash;', + 'ne;', + 'ni;', + 'not;', + 'not', + 'notin;', + 'nsub;', + 'ntilde;', + 'ntilde', + 'nu;', + 'oacute;', + 'oacute', + 'ocirc;', + 'ocirc', + 'oelig;', + 'ograve;', + 'ograve', + 'oline;', + 'omega;', + 'omicron;', + 'oplus;', + 'or;', + 'ordf;', + 'ordf', + 'ordm;', + 'ordm', + 'oslash;', + 'oslash', + 'otilde;', + 'otilde', + 'otimes;', + 'ouml;', + 'ouml', + 'para;', + 'para', + 'part;', + 'permil;', + 'perp;', + 'phi;', + 'pi;', + 'piv;', + 'plusmn;', + 'plusmn', + 'pound;', + 'pound', + 'prime;', + 'prod;', + 'prop;', + 'psi;', + 'quot;', + 'quot', + 'rArr;', + 'radic;', + 'rang;', + 'raquo;', + 'raquo', + 'rarr;', + 'rceil;', + 'rdquo;', + 'real;', + 'reg;', + 'reg', + 'rfloor;', + 'rho;', + 'rlm;', + 'rsaquo;', + 'rsquo;', + 'sbquo;', + 'scaron;', + 'sdot;', + 'sect;', + 'sect', + 'shy;', + 'shy', + 'sigma;', + 'sigmaf;', + 'sim;', + 'spades;', + 'sub;', + 'sube;', + 'sum;', + 'sup1;', + 'sup1', + 'sup2;', + 'sup2', + 'sup3;', + 'sup3', + 'sup;', + 'supe;', + 'szlig;', + 'szlig', + 'tau;', + 'there4;', + 'theta;', + 'thetasym;', + 'thinsp;', + 'thorn;', + 'thorn', + 'tilde;', + 'times;', + 'times', + 'trade;', + 'uArr;', + 'uacute;', + 'uacute', + 'uarr;', + 'ucirc;', + 'ucirc', + 'ugrave;', + 'ugrave', + 'uml;', + 'uml', + 'upsih;', + 'upsilon;', + 'uuml;', + 'uuml', + 'weierp;', + 'xi;', + 'yacute;', + 'yacute', + 'yen;', + 'yen', + 'yuml;', + 'yuml', + 'zeta;', + 'zwj;', + 'zwnj;' + ); + + const PCDATA = 0; + const RCDATA = 1; + const CDATA = 2; + const PLAINTEXT = 3; + + const DOCTYPE = 0; + const STARTTAG = 1; + const ENDTAG = 2; + const COMMENT = 3; + const CHARACTR = 4; + const EOF = 5; + + public function __construct($data) + { + $this->data = $data; + $this->char = -1; + $this->EOF = strlen($data); + $this->tree = new HTML5TreeConstructer; + $this->content_model = self::PCDATA; + + $this->state = 'data'; + + while ($this->state !== null) { + $this->{$this->state . 'State'}(); + } + } + + public function save() + { + return $this->tree->save(); + } + + private function char() + { + return ($this->char < $this->EOF) + ? $this->data[$this->char] + : false; + } + + private function character($s, $l = 0) + { + if ($s + $l < $this->EOF) { + if ($l === 0) { + return $this->data[$s]; + } else { + return substr($this->data, $s, $l); + } + } + } + + private function characters($char_class, $start) + { + return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start)); + } + + private function dataState() + { + // Consume the next input character + $this->char++; + $char = $this->char(); + + if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { + /* U+0026 AMPERSAND (&) + When the content model flag is set to one of the PCDATA or RCDATA + states: switch to the entity data state. Otherwise: treat it as per + the "anything else" entry below. */ + $this->state = 'entityData'; + + } elseif ($char === '-') { + /* If the content model flag is set to either the RCDATA state or + the CDATA state, and the escape flag is false, and there are at + least three characters before this one in the input stream, and the + last four characters in the input stream, including this one, are + U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS, + and U+002D HYPHEN-MINUS (""), + set the escape flag to false. */ + if (($this->content_model === self::RCDATA || + $this->content_model === self::CDATA) && $this->escape === true && + $this->character($this->char, 3) === '-->' + ) { + $this->escape = false; + } + + /* In any case, emit the input character as a character token. + Stay in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + } elseif ($this->char === $this->EOF) { + /* EOF + Emit an end-of-file token. */ + $this->EOF(); + + } elseif ($this->content_model === self::PLAINTEXT) { + /* When the content model flag is set to the PLAINTEXT state + THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of + the text and emit it as a character token. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => substr($this->data, $this->char) + ) + ); + + $this->EOF(); + + } else { + /* Anything else + THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that + otherwise would also be treated as a character token and emit it + as a single character token. Stay in the data state. */ + $len = strcspn($this->data, '<&', $this->char); + $char = substr($this->data, $this->char, $len); + $this->char += $len - 1; + + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + $this->state = 'data'; + } + } + + private function entityDataState() + { + // Attempt to consume an entity. + $entity = $this->entity(); + + // If nothing is returned, emit a U+0026 AMPERSAND character token. + // Otherwise, emit the character token that was returned. + $char = (!$entity) ? '&' : $entity; + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + // Finally, switch to the data state. + $this->state = 'data'; + } + + private function tagOpenState() + { + switch ($this->content_model) { + case self::RCDATA: + case self::CDATA: + /* If the next input character is a U+002F SOLIDUS (/) character, + consume it and switch to the close tag open state. If the next + input character is not a U+002F SOLIDUS (/) character, emit a + U+003C LESS-THAN SIGN character token and switch to the data + state to process the next input character. */ + if ($this->character($this->char + 1) === '/') { + $this->char++; + $this->state = 'closeTagOpen'; + + } else { + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); + + $this->state = 'data'; + } + break; + + case self::PCDATA: + // If the content model flag is set to the PCDATA state + // Consume the next input character: + $this->char++; + $char = $this->char(); + + if ($char === '!') { + /* U+0021 EXCLAMATION MARK (!) + Switch to the markup declaration open state. */ + $this->state = 'markupDeclarationOpen'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Switch to the close tag open state. */ + $this->state = 'closeTagOpen'; + + } elseif (preg_match('/^[A-Za-z]$/', $char)) { + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z + Create a new start tag token, set its tag name to the lowercase + version of the input character (add 0x0020 to the character's code + point), then switch to the tag name state. (Don't emit the token + yet; further details will be filled in before it is emitted.) */ + $this->token = array( + 'name' => strtolower($char), + 'type' => self::STARTTAG, + 'attr' => array() + ); + + $this->state = 'tagName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Parse error. Emit a U+003C LESS-THAN SIGN character token and a + U+003E GREATER-THAN SIGN character token. Switch to the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<>' + ) + ); + + $this->state = 'data'; + + } elseif ($char === '?') { + /* U+003F QUESTION MARK (?) + Parse error. Switch to the bogus comment state. */ + $this->state = 'bogusComment'; + + } else { + /* Anything else + Parse error. Emit a U+003C LESS-THAN SIGN character token and + reconsume the current input character in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); + + $this->char--; + $this->state = 'data'; + } + break; + } + } + + private function closeTagOpenState() + { + $next_node = strtolower($this->characters('A-Za-z', $this->char + 1)); + $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName; + + if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && + (!$the_same || ($the_same && (!preg_match( + '/[\t\n\x0b\x0c >\/]/', + $this->character($this->char + 1 + strlen($next_node)) + ) || $this->EOF === $this->char))) + ) { + /* If the content model flag is set to the RCDATA or CDATA states then + examine the next few characters. If they do not match the tag name of + the last start tag token emitted (case insensitively), or if they do but + they are not immediately followed by one of the following characters: + * U+0009 CHARACTER TABULATION + * U+000A LINE FEED (LF) + * U+000B LINE TABULATION + * U+000C FORM FEED (FF) + * U+0020 SPACE + * U+003E GREATER-THAN SIGN (>) + * U+002F SOLIDUS (/) + * EOF + ...then there is a parse error. Emit a U+003C LESS-THAN SIGN character + token, a U+002F SOLIDUS character token, and switch to the data state + to process the next input character. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => 'state = 'data'; + + } else { + /* Otherwise, if the content model flag is set to the PCDATA state, + or if the next few characters do match that tag name, consume the + next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[A-Za-z]$/', $char)) { + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z + Create a new end tag token, set its tag name to the lowercase version + of the input character (add 0x0020 to the character's code point), then + switch to the tag name state. (Don't emit the token yet; further details + will be filled in before it is emitted.) */ + $this->token = array( + 'name' => strtolower($char), + 'type' => self::ENDTAG + ); + + $this->state = 'tagName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Parse error. Switch to the data state. */ + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F + SOLIDUS character token. Reconsume the EOF character in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => 'char--; + $this->state = 'data'; + + } else { + /* Parse error. Switch to the bogus comment state. */ + $this->state = 'bogusComment'; + } + } + } + + private function tagNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } else { + /* Anything else + Append the current input character to the current tag token's tag name. + Stay in the tag name state. */ + $this->token['name'] .= strtolower($char); + $this->state = 'tagName'; + } + } + + private function beforeAttributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Stay in the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Start a new attribute in the current tag token. Set that attribute's + name to the current input character, and its value to the empty string. + Switch to the attribute name state. */ + $this->token['attr'][] = array( + 'name' => strtolower($char), + 'value' => null + ); + + $this->state = 'attributeName'; + } + } + + private function attributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute name state. */ + $this->state = 'afterAttributeName'; + + } elseif ($char === '=') { + /* U+003D EQUALS SIGN (=) + Switch to the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's name. + Stay in the attribute name state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['name'] .= strtolower($char); + + $this->state = 'attributeName'; + } + } + + private function afterAttributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the after attribute name state. */ + $this->state = 'afterAttributeName'; + + } elseif ($char === '=') { + /* U+003D EQUALS SIGN (=) + Switch to the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the + before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Start a new attribute in the current tag token. Set that attribute's + name to the current input character, and its value to the empty string. + Switch to the attribute name state. */ + $this->token['attr'][] = array( + 'name' => strtolower($char), + 'value' => null + ); + + $this->state = 'attributeName'; + } + } + + private function beforeAttributeValueState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '"') { + /* U+0022 QUOTATION MARK (") + Switch to the attribute value (double-quoted) state. */ + $this->state = 'attributeValueDoubleQuoted'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the attribute value (unquoted) state and reconsume + this input character. */ + $this->char--; + $this->state = 'attributeValueUnquoted'; + + } elseif ($char === '\'') { + /* U+0027 APOSTROPHE (') + Switch to the attribute value (single-quoted) state. */ + $this->state = 'attributeValueSingleQuoted'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Switch to the attribute value (unquoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueUnquoted'; + } + } + + private function attributeValueDoubleQuotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if ($char === '"') { + /* U+0022 QUOTATION MARK (") + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState('double'); + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the character + in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (double-quoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueDoubleQuoted'; + } + } + + private function attributeValueSingleQuotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if ($char === '\'') { + /* U+0022 QUOTATION MARK (') + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState('single'); + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the character + in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (single-quoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueSingleQuoted'; + } + } + + private function attributeValueUnquotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState(); + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (unquoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueUnquoted'; + } + } + + private function entityInAttributeValueState() + { + // Attempt to consume an entity. + $entity = $this->entity(); + + // If nothing is returned, append a U+0026 AMPERSAND character to the + // current attribute's value. Otherwise, emit the character token that + // was returned. + $char = (!$entity) + ? '&' + : $entity; + + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + } + + private function bogusCommentState() + { + /* Consume every character up to the first U+003E GREATER-THAN SIGN + character (>) or the end of the file (EOF), whichever comes first. Emit + a comment token whose data is the concatenation of all the characters + starting from and including the character that caused the state machine + to switch into the bogus comment state, up to and including the last + consumed character before the U+003E character, if any, or up to the + end of the file otherwise. (If the comment was started by the end of + the file (EOF), the token is empty.) */ + $data = $this->characters('^>', $this->char); + $this->emitToken( + array( + 'data' => $data, + 'type' => self::COMMENT + ) + ); + + $this->char += strlen($data); + + /* Switch to the data state. */ + $this->state = 'data'; + + /* If the end of the file was reached, reconsume the EOF character. */ + if ($this->char === $this->EOF) { + $this->char = $this->EOF - 1; + } + } + + private function markupDeclarationOpenState() + { + /* If the next two characters are both U+002D HYPHEN-MINUS (-) + characters, consume those two characters, create a comment token whose + data is the empty string, and switch to the comment state. */ + if ($this->character($this->char + 1, 2) === '--') { + $this->char += 2; + $this->state = 'comment'; + $this->token = array( + 'data' => null, + 'type' => self::COMMENT + ); + + /* Otherwise if the next seven chacacters are a case-insensitive match + for the word "DOCTYPE", then consume those characters and switch to the + DOCTYPE state. */ + } elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') { + $this->char += 7; + $this->state = 'doctype'; + + /* Otherwise, is is a parse error. Switch to the bogus comment state. + The next character that is consumed, if any, is the first character + that will be in the comment. */ + } else { + $this->char++; + $this->state = 'bogusComment'; + } + } + + private function commentState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + /* U+002D HYPHEN-MINUS (-) */ + if ($char === '-') { + /* Switch to the comment dash state */ + $this->state = 'commentDash'; + + /* EOF */ + } elseif ($this->char === $this->EOF) { + /* Parse error. Emit the comment token. Reconsume the EOF character + in the data state. */ + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + /* Anything else */ + } else { + /* Append the input character to the comment token's data. Stay in + the comment state. */ + $this->token['data'] .= $char; + } + } + + private function commentDashState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + /* U+002D HYPHEN-MINUS (-) */ + if ($char === '-') { + /* Switch to the comment end state */ + $this->state = 'commentEnd'; + + /* EOF */ + } elseif ($this->char === $this->EOF) { + /* Parse error. Emit the comment token. Reconsume the EOF character + in the data state. */ + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + /* Anything else */ + } else { + /* Append a U+002D HYPHEN-MINUS (-) character and the input + character to the comment token's data. Switch to the comment state. */ + $this->token['data'] .= '-' . $char; + $this->state = 'comment'; + } + } + + private function commentEndState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '-') { + $this->token['data'] .= '-'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['data'] .= '--' . $char; + $this->state = 'comment'; + } + } + + private function doctypeState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + $this->state = 'beforeDoctypeName'; + + } else { + $this->char--; + $this->state = 'beforeDoctypeName'; + } + } + + private function beforeDoctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + // Stay in the before DOCTYPE name state. + + } elseif (preg_match('/^[a-z]$/', $char)) { + $this->token = array( + 'name' => strtoupper($char), + 'type' => self::DOCTYPE, + 'error' => true + ); + + $this->state = 'doctypeName'; + + } elseif ($char === '>') { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); + + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); + + $this->char--; + $this->state = 'data'; + + } else { + $this->token = array( + 'name' => $char, + 'type' => self::DOCTYPE, + 'error' => true + ); + + $this->state = 'doctypeName'; + } + } + + private function doctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + $this->state = 'AfterDoctypeName'; + + } elseif ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif (preg_match('/^[a-z]$/', $char)) { + $this->token['name'] .= strtoupper($char); + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['name'] .= $char; + } + + $this->token['error'] = ($this->token['name'] === 'HTML') + ? false + : true; + } + + private function afterDoctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + // Stay in the DOCTYPE name state. + + } elseif ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['error'] = true; + $this->state = 'bogusDoctype'; + } + } + + private function bogusDoctypeState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + // Stay in the bogus DOCTYPE state. + } + } + + private function entity() + { + $start = $this->char; + + // This section defines how to consume an entity. This definition is + // used when parsing entities in text and in attributes. + + // The behaviour depends on the identity of the next character (the + // one immediately after the U+0026 AMPERSAND character): + + switch ($this->character($this->char + 1)) { + // U+0023 NUMBER SIGN (#) + case '#': + + // The behaviour further depends on the character after the + // U+0023 NUMBER SIGN: + switch ($this->character($this->char + 1)) { + // U+0078 LATIN SMALL LETTER X + // U+0058 LATIN CAPITAL LETTER X + case 'x': + case 'X': + // Follow the steps below, but using the range of + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT + // NINE, U+0061 LATIN SMALL LETTER A through to U+0066 + // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER + // A, through to U+0046 LATIN CAPITAL LETTER F (in other + // words, 0-9, A-F, a-f). + $char = 1; + $char_class = '0-9A-Fa-f'; + break; + + // Anything else + default: + // Follow the steps below, but using the range of + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT + // NINE (i.e. just 0-9). + $char = 0; + $char_class = '0-9'; + break; + } + + // Consume as many characters as match the range of characters + // given above. + $this->char++; + $e_name = $this->characters($char_class, $this->char + $char + 1); + $entity = $this->character($start, $this->char); + $cond = strlen($e_name) > 0; + + // The rest of the parsing happens below. + break; + + // Anything else + default: + // Consume the maximum number of characters possible, with the + // consumed characters case-sensitively matching one of the + // identifiers in the first column of the entities table. + + $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); + $len = strlen($e_name); + + for ($c = 1; $c <= $len; $c++) { + $id = substr($e_name, 0, $c); + $this->char++; + + if (in_array($id, $this->entities)) { + if ($e_name[$c - 1] !== ';') { + if ($c < $len && $e_name[$c] == ';') { + $this->char++; // consume extra semicolon + } + } + $entity = $id; + break; + } + } + + $cond = isset($entity); + // The rest of the parsing happens below. + break; + } + + if (!$cond) { + // If no match can be made, then this is a parse error. No + // characters are consumed, and nothing is returned. + $this->char = $start; + return false; + } + + // Return a character token for the character corresponding to the + // entity name (as given by the second column of the entities table). + return html_entity_decode('&' . rtrim($entity, ';') . ';', ENT_QUOTES, 'UTF-8'); + } + + private function emitToken($token) + { + $emit = $this->tree->emitToken($token); + + if (is_int($emit)) { + $this->content_model = $emit; + + } elseif ($token['type'] === self::ENDTAG) { + $this->content_model = self::PCDATA; + } + } + + private function EOF() + { + $this->state = null; + $this->tree->emitToken( + array( + 'type' => self::EOF + ) + ); + } +} + +class HTML5TreeConstructer +{ + public $stack = array(); + + private $phase; + private $mode; + private $dom; + private $foster_parent = null; + private $a_formatting = array(); + + private $head_pointer = null; + private $form_pointer = null; + + private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th'); + private $formatting = array( + 'a', + 'b', + 'big', + 'em', + 'font', + 'i', + 'nobr', + 's', + 'small', + 'strike', + 'strong', + 'tt', + 'u' + ); + private $special = array( + 'address', + 'area', + 'base', + 'basefont', + 'bgsound', + 'blockquote', + 'body', + 'br', + 'center', + 'col', + 'colgroup', + 'dd', + 'dir', + 'div', + 'dl', + 'dt', + 'embed', + 'fieldset', + 'form', + 'frame', + 'frameset', + 'h1', + 'h2', + 'h3', + 'h4', + 'h5', + 'h6', + 'head', + 'hr', + 'iframe', + 'image', + 'img', + 'input', + 'isindex', + 'li', + 'link', + 'listing', + 'menu', + 'meta', + 'noembed', + 'noframes', + 'noscript', + 'ol', + 'optgroup', + 'option', + 'p', + 'param', + 'plaintext', + 'pre', + 'script', + 'select', + 'spacer', + 'style', + 'tbody', + 'textarea', + 'tfoot', + 'thead', + 'title', + 'tr', + 'ul', + 'wbr' + ); + + // The different phases. + const INIT_PHASE = 0; + const ROOT_PHASE = 1; + const MAIN_PHASE = 2; + const END_PHASE = 3; + + // The different insertion modes for the main phase. + const BEFOR_HEAD = 0; + const IN_HEAD = 1; + const AFTER_HEAD = 2; + const IN_BODY = 3; + const IN_TABLE = 4; + const IN_CAPTION = 5; + const IN_CGROUP = 6; + const IN_TBODY = 7; + const IN_ROW = 8; + const IN_CELL = 9; + const IN_SELECT = 10; + const AFTER_BODY = 11; + const IN_FRAME = 12; + const AFTR_FRAME = 13; + + // The different types of elements. + const SPECIAL = 0; + const SCOPING = 1; + const FORMATTING = 2; + const PHRASING = 3; + + const MARKER = 0; + + public function __construct() + { + $this->phase = self::INIT_PHASE; + $this->mode = self::BEFOR_HEAD; + $this->dom = new DOMDocument; + + $this->dom->encoding = 'UTF-8'; + $this->dom->preserveWhiteSpace = true; + $this->dom->substituteEntities = true; + $this->dom->strictErrorChecking = false; + } + + // Process tag tokens + public function emitToken($token) + { + switch ($this->phase) { + case self::INIT_PHASE: + return $this->initPhase($token); + break; + case self::ROOT_PHASE: + return $this->rootElementPhase($token); + break; + case self::MAIN_PHASE: + return $this->mainPhase($token); + break; + case self::END_PHASE : + return $this->trailingEndPhase($token); + break; + } + } + + private function initPhase($token) + { + /* Initially, the tree construction stage must handle each token + emitted from the tokenisation stage as follows: */ + + /* A DOCTYPE token that is marked as being in error + A comment token + A start tag token + An end tag token + A character token that is not one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE + An end-of-file token */ + if ((isset($token['error']) && $token['error']) || + $token['type'] === HTML5::COMMENT || + $token['type'] === HTML5::STARTTAG || + $token['type'] === HTML5::ENDTAG || + $token['type'] === HTML5::EOF || + ($token['type'] === HTML5::CHARACTR && isset($token['data']) && + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) + ) { + /* This specification does not define how to handle this case. In + particular, user agents may ignore the entirety of this specification + altogether for such documents, and instead invoke special parse modes + with a greater emphasis on backwards compatibility. */ + + $this->phase = self::ROOT_PHASE; + return $this->rootElementPhase($token); + + /* A DOCTYPE token marked as being correct */ + } elseif (isset($token['error']) && !$token['error']) { + /* Append a DocumentType node to the Document node, with the name + attribute set to the name given in the DOCTYPE token (which will be + "HTML"), and the other attributes specific to DocumentType objects + set to null, empty lists, or the empty string as appropriate. */ + $doctype = new DOMDocumentType(null, null, 'HTML'); + + /* Then, switch to the root element phase of the tree construction + stage. */ + $this->phase = self::ROOT_PHASE; + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif (isset($token['data']) && preg_match( + '/^[\t\n\x0b\x0c ]+$/', + $token['data'] + ) + ) { + /* Append that character to the Document node. */ + $text = $this->dom->createTextNode($token['data']); + $this->dom->appendChild($text); + } + } + + private function rootElementPhase($token) + { + /* After the initial phase, as each token is emitted from the tokenisation + stage, it must be processed as described in this section. */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the Document object with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->dom->appendChild($comment); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append that character to the Document node. */ + $text = $this->dom->createTextNode($token['data']); + $this->dom->appendChild($text); + + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED + (FF), or U+0020 SPACE + A start tag token + An end tag token + An end-of-file token */ + } elseif (($token['type'] === HTML5::CHARACTR && + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || + $token['type'] === HTML5::STARTTAG || + $token['type'] === HTML5::ENDTAG || + $token['type'] === HTML5::EOF + ) { + /* Create an HTMLElement node with the tag name html, in the HTML + namespace. Append it to the Document object. Switch to the main + phase and reprocess the current token. */ + $html = $this->dom->createElement('html'); + $this->dom->appendChild($html); + $this->stack[] = $html; + + $this->phase = self::MAIN_PHASE; + return $this->mainPhase($token); + } + } + + private function mainPhase($token) + { + /* Tokens in the main phase must be handled as follows: */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A start tag token with the tag name "html" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { + /* If this start tag token was not the first start tag token, then + it is a parse error. */ + + /* For each attribute on the token, check to see if the attribute + is already present on the top element of the stack of open elements. + If it is not, add the attribute and its corresponding value to that + element. */ + foreach ($token['attr'] as $attr) { + if (!$this->stack[0]->hasAttribute($attr['name'])) { + $this->stack[0]->setAttribute($attr['name'], $attr['value']); + } + } + + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Anything else. */ + } else { + /* Depends on the insertion mode: */ + switch ($this->mode) { + case self::BEFOR_HEAD: + return $this->beforeHead($token); + break; + case self::IN_HEAD: + return $this->inHead($token); + break; + case self::AFTER_HEAD: + return $this->afterHead($token); + break; + case self::IN_BODY: + return $this->inBody($token); + break; + case self::IN_TABLE: + return $this->inTable($token); + break; + case self::IN_CAPTION: + return $this->inCaption($token); + break; + case self::IN_CGROUP: + return $this->inColumnGroup($token); + break; + case self::IN_TBODY: + return $this->inTableBody($token); + break; + case self::IN_ROW: + return $this->inRow($token); + break; + case self::IN_CELL: + return $this->inCell($token); + break; + case self::IN_SELECT: + return $this->inSelect($token); + break; + case self::AFTER_BODY: + return $this->afterBody($token); + break; + case self::IN_FRAME: + return $this->inFrameset($token); + break; + case self::AFTR_FRAME: + return $this->afterFrameset($token); + break; + case self::END_PHASE: + return $this->trailingEndPhase($token); + break; + } + } + } + + private function beforeHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token with the tag name "head" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { + /* Create an element for the token, append the new element to the + current node and push it onto the stack of open elements. */ + $element = $this->insertElement($token); + + /* Set the head element pointer to this new element node. */ + $this->head_pointer = $element; + + /* Change the insertion mode to "in head". */ + $this->mode = self::IN_HEAD; + + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title". Or an end tag with the tag name "html". + Or a character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or any other start tag token */ + } elseif ($token['type'] === HTML5::STARTTAG || + ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') || + ($token['type'] === HTML5::CHARACTR && !preg_match( + '/^[\t\n\x0b\x0c ]$/', + $token['data'] + )) + ) { + /* Act as if a start tag token with the tag name "head" and no + attributes had been seen, then reprocess the current token. */ + $this->beforeHead( + array( + 'name' => 'head', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inHead($token); + + /* Any other end tag */ + } elseif ($token['type'] === HTML5::ENDTAG) { + /* Parse error. Ignore the token. */ + } + } + + private function inHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. + + THIS DIFFERS FROM THE SPEC: If the current node is either a title, style + or script element, append the character to the current node regardless + of its content. */ + if (($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || ( + $token['type'] === HTML5::CHARACTR && in_array( + end($this->stack)->nodeName, + array('title', 'style', 'script') + )) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('title', 'style', 'script')) + ) { + array_pop($this->stack); + return HTML5::PCDATA; + + /* A start tag with the tag name "title" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + } else { + $element = $this->insertElement($token); + } + + /* Switch the tokeniser's content model flag to the RCDATA state. */ + return HTML5::RCDATA; + + /* A start tag with the tag name "style" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + } else { + $this->insertElement($token); + } + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + + /* A start tag with the tag name "script" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { + /* Create an element for the token. */ + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + + /* A start tag with the tag name "base", "link", or "meta" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('base', 'link', 'meta') + ) + ) { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + array_pop($this->stack); + + } else { + $this->insertElement($token); + } + + /* An end tag with the tag name "head" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { + /* If the current node is a head element, pop the current node off + the stack of open elements. */ + if ($this->head_pointer->isSameNode(end($this->stack))) { + array_pop($this->stack); + + /* Otherwise, this is a parse error. */ + } else { + // k + } + + /* Change the insertion mode to "after head". */ + $this->mode = self::AFTER_HEAD; + + /* A start tag with the tag name "head" or an end tag except "html". */ + } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || + ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html') + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* If the current node is a head element, act as if an end tag + token with the tag name "head" had been seen. */ + if ($this->head_pointer->isSameNode(end($this->stack))) { + $this->inHead( + array( + 'name' => 'head', + 'type' => HTML5::ENDTAG + ) + ); + + /* Otherwise, change the insertion mode to "after head". */ + } else { + $this->mode = self::AFTER_HEAD; + } + + /* Then, reprocess the current token. */ + return $this->afterHead($token); + } + } + + private function afterHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token with the tag name "body" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { + /* Insert a body element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in body". */ + $this->mode = self::IN_BODY; + + /* A start tag token with the tag name "frameset" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { + /* Insert a frameset element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in frameset". */ + $this->mode = self::IN_FRAME; + + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('base', 'link', 'meta', 'script', 'style', 'title') + ) + ) { + /* Parse error. Switch the insertion mode back to "in head" and + reprocess the token. */ + $this->mode = self::IN_HEAD; + return $this->inHead($token); + + /* Anything else */ + } else { + /* Act as if a start tag token with the tag name "body" and no + attributes had been seen, and then reprocess the current token. */ + $this->afterHead( + array( + 'name' => 'body', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inBody($token); + } + } + + private function inBody($token) + { + /* Handle the token as follows: */ + + switch ($token['type']) { + /* A character token */ + case HTML5::CHARACTR: + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Append the token's character to the current node. */ + $this->insertText($token['data']); + break; + + /* A comment token */ + case HTML5::COMMENT: + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + break; + + case HTML5::STARTTAG: + switch ($token['name']) { + /* A start tag token whose tag name is one of: "script", + "style" */ + case 'script': + case 'style': + /* Process the token as if the insertion mode had been "in + head". */ + return $this->inHead($token); + break; + + /* A start tag token whose tag name is one of: "base", "link", + "meta", "title" */ + case 'base': + case 'link': + case 'meta': + case 'title': + /* Parse error. Process the token as if the insertion mode + had been "in head". */ + return $this->inHead($token); + break; + + /* A start tag token with the tag name "body" */ + case 'body': + /* Parse error. If the second element on the stack of open + elements is not a body element, or, if the stack of open + elements has only one node on it, then ignore the token. + (innerHTML case) */ + if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { + // Ignore + + /* Otherwise, for each attribute on the token, check to see + if the attribute is already present on the body element (the + second element) on the stack of open elements. If it is not, + add the attribute and its corresponding value to that + element. */ + } else { + foreach ($token['attr'] as $attr) { + if (!$this->stack[1]->hasAttribute($attr['name'])) { + $this->stack[1]->setAttribute($attr['name'], $attr['value']); + } + } + } + break; + + /* A start tag whose tag name is one of: "address", + "blockquote", "center", "dir", "div", "dl", "fieldset", + "listing", "menu", "ol", "p", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'p': + case 'ul': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + break; + + /* A start tag whose tag name is "form" */ + case 'form': + /* If the form element pointer is not null, ignore the + token with a parse error. */ + if ($this->form_pointer !== null) { + // Ignore. + + /* Otherwise: */ + } else { + /* If the stack of open elements has a p element in + scope, then act as if an end tag with the tag name p + had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token, and set the + form element pointer to point to the element created. */ + $element = $this->insertElement($token); + $this->form_pointer = $element; + } + break; + + /* A start tag whose tag name is "li", "dd" or "dt" */ + case 'li': + case 'dd': + case 'dt': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + $stack_length = count($this->stack) - 1; + + for ($n = $stack_length; 0 <= $n; $n--) { + /* 1. Initialise node to be the current node (the + bottommost node of the stack). */ + $stop = false; + $node = $this->stack[$n]; + $cat = $this->getElementCategory($node->tagName); + + /* 2. If node is an li, dd or dt element, then pop all + the nodes from the current node up to node, including + node, then stop this algorithm. */ + if ($token['name'] === $node->tagName || ($token['name'] !== 'li' + && ($node->tagName === 'dd' || $node->tagName === 'dt')) + ) { + for ($x = $stack_length; $x >= $n; $x--) { + array_pop($this->stack); + } + + break; + } + + /* 3. If node is not in the formatting category, and is + not in the phrasing category, and is not an address or + div element, then stop this algorithm. */ + if ($cat !== self::FORMATTING && $cat !== self::PHRASING && + $node->tagName !== 'address' && $node->tagName !== 'div' + ) { + break; + } + } + + /* Finally, insert an HTML element with the same tag + name as the token's. */ + $this->insertElement($token); + break; + + /* A start tag token whose tag name is "plaintext" */ + case 'plaintext': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + return HTML5::PLAINTEXT; + break; + + /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4", + "h5", "h6" */ + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the stack of open elements has in scope an element whose + tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then + this is a parse error; pop elements from the stack until an + element with one of those tag names has been popped from the + stack. */ + while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { + array_pop($this->stack); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + break; + + /* A start tag whose tag name is "a" */ + case 'a': + /* If the list of active formatting elements contains + an element whose tag name is "a" between the end of the + list and the last marker on the list (or the start of + the list if there is no marker on the list), then this + is a parse error; act as if an end tag with the tag name + "a" had been seen, then remove that element from the list + of active formatting elements and the stack of open + elements if the end tag didn't already remove it (it + might not have if the element is not in table scope). */ + $leng = count($this->a_formatting); + + for ($n = $leng - 1; $n >= 0; $n--) { + if ($this->a_formatting[$n] === self::MARKER) { + break; + + } elseif ($this->a_formatting[$n]->nodeName === 'a') { + $this->emitToken( + array( + 'name' => 'a', + 'type' => HTML5::ENDTAG + ) + ); + break; + } + } + + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $el = $this->insertElement($token); + + /* Add that element to the list of active formatting + elements. */ + $this->a_formatting[] = $el; + break; + + /* A start tag whose tag name is one of: "b", "big", "em", "font", + "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ + case 'b': + case 'big': + case 'em': + case 'font': + case 'i': + case 'nobr': + case 's': + case 'small': + case 'strike': + case 'strong': + case 'tt': + case 'u': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $el = $this->insertElement($token); + + /* Add that element to the list of active formatting + elements. */ + $this->a_formatting[] = $el; + break; + + /* A start tag token whose tag name is "button" */ + case 'button': + /* If the stack of open elements has a button element in scope, + then this is a parse error; act as if an end tag with the tag + name "button" had been seen, then reprocess the token. (We don't + do that. Unnecessary.) */ + if ($this->elementInScope('button')) { + $this->inBody( + array( + 'name' => 'button', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + break; + + /* A start tag token whose tag name is one of: "marquee", "object" */ + case 'marquee': + case 'object': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + break; + + /* A start tag token whose tag name is "xmp" */ + case 'xmp': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Switch the content model flag to the CDATA state. */ + return HTML5::CDATA; + break; + + /* A start tag whose tag name is "table" */ + case 'table': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in table". */ + $this->mode = self::IN_TABLE; + break; + + /* A start tag whose tag name is one of: "area", "basefont", + "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */ + case 'area': + case 'basefont': + case 'bgsound': + case 'br': + case 'embed': + case 'img': + case 'param': + case 'spacer': + case 'wbr': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "hr" */ + case 'hr': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "image" */ + case 'image': + /* Parse error. Change the token's tag name to "img" and + reprocess it. (Don't ask.) */ + $token['name'] = 'img'; + return $this->inBody($token); + break; + + /* A start tag whose tag name is "input" */ + case 'input': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an input element for the token. */ + $element = $this->insertElement($token, false); + + /* If the form element pointer is not null, then associate the + input element with the form element pointed to by the form + element pointer. */ + $this->form_pointer !== null + ? $this->form_pointer->appendChild($element) + : end($this->stack)->appendChild($element); + + /* Pop that input element off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "isindex" */ + case 'isindex': + /* Parse error. */ + // w/e + + /* If the form element pointer is not null, + then ignore the token. */ + if ($this->form_pointer === null) { + /* Act as if a start tag token with the tag name "form" had + been seen. */ + $this->inBody( + array( + 'name' => 'body', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "hr" had + been seen. */ + $this->inBody( + array( + 'name' => 'hr', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "p" had + been seen. */ + $this->inBody( + array( + 'name' => 'p', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "label" + had been seen. */ + $this->inBody( + array( + 'name' => 'label', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a stream of character tokens had been seen. */ + $this->insertText( + 'This is a searchable index. ' . + 'Insert your search keywords here: ' + ); + + /* Act as if a start tag token with the tag name "input" + had been seen, with all the attributes from the "isindex" + token, except with the "name" attribute set to the value + "isindex" (ignoring any explicit "name" attribute). */ + $attr = $token['attr']; + $attr[] = array('name' => 'name', 'value' => 'isindex'); + + $this->inBody( + array( + 'name' => 'input', + 'type' => HTML5::STARTTAG, + 'attr' => $attr + ) + ); + + /* Act as if a stream of character tokens had been seen + (see below for what they should say). */ + $this->insertText( + 'This is a searchable index. ' . + 'Insert your search keywords here: ' + ); + + /* Act as if an end tag token with the tag name "label" + had been seen. */ + $this->inBody( + array( + 'name' => 'label', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if an end tag token with the tag name "p" had + been seen. */ + $this->inBody( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if a start tag token with the tag name "hr" had + been seen. */ + $this->inBody( + array( + 'name' => 'hr', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if an end tag token with the tag name "form" had + been seen. */ + $this->inBody( + array( + 'name' => 'form', + 'type' => HTML5::ENDTAG + ) + ); + } + break; + + /* A start tag whose tag name is "textarea" */ + case 'textarea': + $this->insertElement($token); + + /* Switch the tokeniser's content model flag to the + RCDATA state. */ + return HTML5::RCDATA; + break; + + /* A start tag whose tag name is one of: "iframe", "noembed", + "noframes" */ + case 'iframe': + case 'noembed': + case 'noframes': + $this->insertElement($token); + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + break; + + /* A start tag whose tag name is "select" */ + case 'select': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in select". */ + $this->mode = self::IN_SELECT; + break; + + /* A start or end tag whose tag name is one of: "caption", "col", + "colgroup", "frame", "frameset", "head", "option", "optgroup", + "tbody", "td", "tfoot", "th", "thead", "tr". */ + case 'caption': + case 'col': + case 'colgroup': + case 'frame': + case 'frameset': + case 'head': + case 'option': + case 'optgroup': + case 'tbody': + case 'td': + case 'tfoot': + case 'th': + case 'thead': + case 'tr': + // Parse error. Ignore the token. + break; + + /* A start or end tag whose tag name is one of: "event-source", + "section", "nav", "article", "aside", "header", "footer", + "datagrid", "command" */ + case 'event-source': + case 'section': + case 'nav': + case 'article': + case 'aside': + case 'header': + case 'footer': + case 'datagrid': + case 'command': + // Work in progress! + break; + + /* A start tag token not covered by the previous entries */ + default: + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + $this->insertElement($token, true, true); + break; + } + break; + + case HTML5::ENDTAG: + switch ($token['name']) { + /* An end tag with the tag name "body" */ + case 'body': + /* If the second element in the stack of open elements is + not a body element, this is a parse error. Ignore the token. + (innerHTML case) */ + if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { + // Ignore. + + /* If the current node is not the body element, then this + is a parse error. */ + } elseif (end($this->stack)->nodeName !== 'body') { + // Parse error. + } + + /* Change the insertion mode to "after body". */ + $this->mode = self::AFTER_BODY; + break; + + /* An end tag with the tag name "html" */ + case 'html': + /* Act as if an end tag with tag name "body" had been seen, + then, if that token wasn't ignored, reprocess the current + token. */ + $this->inBody( + array( + 'name' => 'body', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->afterBody($token); + break; + + /* An end tag whose tag name is one of: "address", "blockquote", + "center", "dir", "div", "dl", "fieldset", "listing", "menu", + "ol", "pre", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'pre': + case 'ul': + /* If the stack of open elements has an element in scope + with the same tag name as that of the token, then generate + implied end tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with + the same tag name as that of the token, then this + is a parse error. */ + // w/e + + /* If the stack of open elements has an element in + scope with the same tag name as that of the token, + then pop elements from this stack until an element + with that tag name has been popped from the stack. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is "form" */ + case 'form': + /* If the stack of open elements has an element in scope + with the same tag name as that of the token, then generate + implied end tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + } + + if (end($this->stack)->nodeName !== $token['name']) { + /* Now, if the current node is not an element with the + same tag name as that of the token, then this is a parse + error. */ + // w/e + + } else { + /* Otherwise, if the current node is an element with + the same tag name as that of the token pop that element + from the stack. */ + array_pop($this->stack); + } + + /* In any case, set the form element pointer to null. */ + $this->form_pointer = null; + break; + + /* An end tag whose tag name is "p" */ + case 'p': + /* If the stack of open elements has a p element in scope, + then generate implied end tags, except for p elements. */ + if ($this->elementInScope('p')) { + $this->generateImpliedEndTags(array('p')); + + /* If the current node is not a p element, then this is + a parse error. */ + // k + + /* If the stack of open elements has a p element in + scope, then pop elements from this stack until the stack + no longer has a p element in scope. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->elementInScope('p')) { + array_pop($this->stack); + + } else { + break; + } + } + } + break; + + /* An end tag whose tag name is "dd", "dt", or "li" */ + case 'dd': + case 'dt': + case 'li': + /* If the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then + generate implied end tags, except for elements with the + same tag name as the token. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(array($token['name'])); + + /* If the current node is not an element with the same + tag name as the token, then this is a parse error. */ + // w/e + + /* If the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then + pop elements from this stack until an element with that + tag name has been popped from the stack. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4", + "h5", "h6" */ + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'); + + /* If the stack of open elements has in scope an element whose + tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then + generate implied end tags. */ + if ($this->elementInScope($elements)) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with the same + tag name as that of the token, then this is a parse error. */ + // w/e + + /* If the stack of open elements has in scope an element + whose tag name is one of "h1", "h2", "h3", "h4", "h5", or + "h6", then pop elements from the stack until an element + with one of those tag names has been popped from the stack. */ + while ($this->elementInScope($elements)) { + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is one of: "a", "b", "big", "em", + "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ + case 'a': + case 'b': + case 'big': + case 'em': + case 'font': + case 'i': + case 'nobr': + case 's': + case 'small': + case 'strike': + case 'strong': + case 'tt': + case 'u': + /* 1. Let the formatting element be the last element in + the list of active formatting elements that: + * is between the end of the list and the last scope + marker in the list, if any, or the start of the list + otherwise, and + * has the same tag name as the token. + */ + while (true) { + for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) { + if ($this->a_formatting[$a] === self::MARKER) { + break; + + } elseif ($this->a_formatting[$a]->tagName === $token['name']) { + $formatting_element = $this->a_formatting[$a]; + $in_stack = in_array($formatting_element, $this->stack, true); + $fe_af_pos = $a; + break; + } + } + + /* If there is no such node, or, if that node is + also in the stack of open elements but the element + is not in scope, then this is a parse error. Abort + these steps. The token is ignored. */ + if (!isset($formatting_element) || ($in_stack && + !$this->elementInScope($token['name'])) + ) { + break; + + /* Otherwise, if there is such a node, but that node + is not in the stack of open elements, then this is a + parse error; remove the element from the list, and + abort these steps. */ + } elseif (isset($formatting_element) && !$in_stack) { + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + break; + } + + /* 2. Let the furthest block be the topmost node in the + stack of open elements that is lower in the stack + than the formatting element, and is not an element in + the phrasing or formatting categories. There might + not be one. */ + $fe_s_pos = array_search($formatting_element, $this->stack, true); + $length = count($this->stack); + + for ($s = $fe_s_pos + 1; $s < $length; $s++) { + $category = $this->getElementCategory($this->stack[$s]->nodeName); + + if ($category !== self::PHRASING && $category !== self::FORMATTING) { + $furthest_block = $this->stack[$s]; + } + } + + /* 3. If there is no furthest block, then the UA must + skip the subsequent steps and instead just pop all + the nodes from the bottom of the stack of open + elements, from the current node up to the formatting + element, and remove the formatting element from the + list of active formatting elements. */ + if (!isset($furthest_block)) { + for ($n = $length - 1; $n >= $fe_s_pos; $n--) { + array_pop($this->stack); + } + + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + break; + } + + /* 4. Let the common ancestor be the element + immediately above the formatting element in the stack + of open elements. */ + $common_ancestor = $this->stack[$fe_s_pos - 1]; + + /* 5. If the furthest block has a parent node, then + remove the furthest block from its parent node. */ + if ($furthest_block->parentNode !== null) { + $furthest_block->parentNode->removeChild($furthest_block); + } + + /* 6. Let a bookmark note the position of the + formatting element in the list of active formatting + elements relative to the elements on either side + of it in the list. */ + $bookmark = $fe_af_pos; + + /* 7. Let node and last node be the furthest block. + Follow these steps: */ + $node = $furthest_block; + $last_node = $furthest_block; + + while (true) { + for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { + /* 7.1 Let node be the element immediately + prior to node in the stack of open elements. */ + $node = $this->stack[$n]; + + /* 7.2 If node is not in the list of active + formatting elements, then remove node from + the stack of open elements and then go back + to step 1. */ + if (!in_array($node, $this->a_formatting, true)) { + unset($this->stack[$n]); + $this->stack = array_merge($this->stack); + + } else { + break; + } + } + + /* 7.3 Otherwise, if node is the formatting + element, then go to the next step in the overall + algorithm. */ + if ($node === $formatting_element) { + break; + + /* 7.4 Otherwise, if last node is the furthest + block, then move the aforementioned bookmark to + be immediately after the node in the list of + active formatting elements. */ + } elseif ($last_node === $furthest_block) { + $bookmark = array_search($node, $this->a_formatting, true) + 1; + } + + /* 7.5 If node has any children, perform a + shallow clone of node, replace the entry for + node in the list of active formatting elements + with an entry for the clone, replace the entry + for node in the stack of open elements with an + entry for the clone, and let node be the clone. */ + if ($node->hasChildNodes()) { + $clone = $node->cloneNode(); + $s_pos = array_search($node, $this->stack, true); + $a_pos = array_search($node, $this->a_formatting, true); + + $this->stack[$s_pos] = $clone; + $this->a_formatting[$a_pos] = $clone; + $node = $clone; + } + + /* 7.6 Insert last node into node, first removing + it from its previous parent node if any. */ + if ($last_node->parentNode !== null) { + $last_node->parentNode->removeChild($last_node); + } + + $node->appendChild($last_node); + + /* 7.7 Let last node be node. */ + $last_node = $node; + } + + /* 8. Insert whatever last node ended up being in + the previous step into the common ancestor node, + first removing it from its previous parent node if + any. */ + if ($last_node->parentNode !== null) { + $last_node->parentNode->removeChild($last_node); + } + + $common_ancestor->appendChild($last_node); + + /* 9. Perform a shallow clone of the formatting + element. */ + $clone = $formatting_element->cloneNode(); + + /* 10. Take all of the child nodes of the furthest + block and append them to the clone created in the + last step. */ + while ($furthest_block->hasChildNodes()) { + $child = $furthest_block->firstChild; + $furthest_block->removeChild($child); + $clone->appendChild($child); + } + + /* 11. Append that clone to the furthest block. */ + $furthest_block->appendChild($clone); + + /* 12. Remove the formatting element from the list + of active formatting elements, and insert the clone + into the list of active formatting elements at the + position of the aforementioned bookmark. */ + $fe_af_pos = array_search($formatting_element, $this->a_formatting, true); + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + + $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1); + $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting)); + $this->a_formatting = array_merge($af_part1, array($clone), $af_part2); + + /* 13. Remove the formatting element from the stack + of open elements, and insert the clone into the stack + of open elements immediately after (i.e. in a more + deeply nested position than) the position of the + furthest block in that stack. */ + $fe_s_pos = array_search($formatting_element, $this->stack, true); + $fb_s_pos = array_search($furthest_block, $this->stack, true); + unset($this->stack[$fe_s_pos]); + + $s_part1 = array_slice($this->stack, 0, $fb_s_pos); + $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack)); + $this->stack = array_merge($s_part1, array($clone), $s_part2); + + /* 14. Jump back to step 1 in this series of steps. */ + unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block); + } + break; + + /* An end tag token whose tag name is one of: "button", + "marquee", "object" */ + case 'button': + case 'marquee': + case 'object': + /* If the stack of open elements has an element in scope whose + tag name matches the tag name of the token, then generate implied + tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with the same + tag name as the token, then this is a parse error. */ + // k + + /* Now, if the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then pop + elements from the stack until that element has been popped from + the stack, and clear the list of active formatting elements up + to the last marker. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + + $marker = end(array_keys($this->a_formatting, self::MARKER, true)); + + for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) { + array_pop($this->a_formatting); + } + } + break; + + /* Or an end tag whose tag name is one of: "area", "basefont", + "bgsound", "br", "embed", "hr", "iframe", "image", "img", + "input", "isindex", "noembed", "noframes", "param", "select", + "spacer", "table", "textarea", "wbr" */ + case 'area': + case 'basefont': + case 'bgsound': + case 'br': + case 'embed': + case 'hr': + case 'iframe': + case 'image': + case 'img': + case 'input': + case 'isindex': + case 'noembed': + case 'noframes': + case 'param': + case 'select': + case 'spacer': + case 'table': + case 'textarea': + case 'wbr': + // Parse error. Ignore the token. + break; + + /* An end tag token not covered by the previous entries */ + default: + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + /* Initialise node to be the current node (the bottommost + node of the stack). */ + $node = end($this->stack); + + /* If node has the same tag name as the end tag token, + then: */ + if ($token['name'] === $node->nodeName) { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* If the tag name of the end tag token does not + match the tag name of the current node, this is a + parse error. */ + // k + + /* Pop all the nodes from the current node up to + node, including node, then stop this algorithm. */ + for ($x = count($this->stack) - $n; $x >= $n; $x--) { + array_pop($this->stack); + } + + } else { + $category = $this->getElementCategory($node); + + if ($category !== self::SPECIAL && $category !== self::SCOPING) { + /* Otherwise, if node is in neither the formatting + category nor the phrasing category, then this is a + parse error. Stop this algorithm. The end tag token + is ignored. */ + return false; + } + } + } + break; + } + break; + } + } + + private function inTable($token) + { + $clear = array('html', 'table'); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $text = $this->dom->createTextNode($token['data']); + end($this->stack)->appendChild($text); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + end($this->stack)->appendChild($comment); + + /* A start tag whose tag name is "caption" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'caption' + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + + /* Insert an HTML element for the token, then switch the + insertion mode to "in caption". */ + $this->insertElement($token); + $this->mode = self::IN_CAPTION; + + /* A start tag whose tag name is "colgroup" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'colgroup' + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the + insertion mode to "in column group". */ + $this->insertElement($token); + $this->mode = self::IN_CGROUP; + + /* A start tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'col' + ) { + $this->inTable( + array( + 'name' => 'colgroup', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + $this->inColumnGroup($token); + + /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('tbody', 'tfoot', 'thead') + ) + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the insertion + mode to "in table body". */ + $this->insertElement($token); + $this->mode = self::IN_TBODY; + + /* A start tag whose tag name is one of: "td", "th", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && + in_array($token['name'], array('td', 'th', 'tr')) + ) { + /* Act as if a start tag token with the tag name "tbody" had been + seen, then reprocess the current token. */ + $this->inTable( + array( + 'name' => 'tbody', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inTableBody($token); + + /* A start tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'table' + ) { + /* Parse error. Act as if an end tag token with the tag name "table" + had been seen, then, if that token wasn't ignored, reprocess the + current token. */ + $this->inTable( + array( + 'name' => 'table', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->mainPhase($token); + + /* An end tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'table' + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + return false; + + /* Otherwise: */ + } else { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Now, if the current node is not a table element, then this + is a parse error. */ + // w/e + + /* Pop elements from this stack until a table element has been + popped from the stack. */ + while (true) { + $current = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($current === 'table') { + break; + } + } + + /* Reset the insertion mode appropriately. */ + $this->resetInsertionMode(); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array( + 'body', + 'caption', + 'col', + 'colgroup', + 'html', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* Parse error. Process the token as if the insertion mode was "in + body", with the following exception: */ + + /* If the current node is a table, tbody, tfoot, thead, or tr + element, then, whenever a node would be inserted into the current + node, it must instead be inserted into the foster parent element. */ + if (in_array( + end($this->stack)->nodeName, + array('table', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* The foster parent element is the parent element of the last + table element in the stack of open elements, if there is a + table element and it has such a parent element. If there is no + table element in the stack of open elements (innerHTML case), + then the foster parent element is the first element in the + stack of open elements (the html element). Otherwise, if there + is a table element in the stack of open elements, but the last + table element in the stack of open elements has no parent, or + its parent node is not an element, then the foster parent + element is the element before the last table element in the + stack of open elements. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === 'table') { + $table = $this->stack[$n]; + break; + } + } + + if (isset($table) && $table->parentNode !== null) { + $this->foster_parent = $table->parentNode; + + } elseif (!isset($table)) { + $this->foster_parent = $this->stack[0]; + + } elseif (isset($table) && ($table->parentNode === null || + $table->parentNode->nodeType !== XML_ELEMENT_NODE) + ) { + $this->foster_parent = $this->stack[$n - 1]; + } + } + + $this->inBody($token); + } + } + + private function inCaption($token) + { + /* An end tag whose tag name is "caption" */ + if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore + + /* Otherwise: */ + } else { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Now, if the current node is not a caption element, then this + is a parse error. */ + // w/e + + /* Pop elements from this stack until a caption element has + been popped from the stack. */ + while (true) { + $node = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($node === 'caption') { + break; + } + } + + /* Clear the list of active formatting elements up to the last + marker. */ + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); + + /* Switch the insertion mode to "in table". */ + $this->mode = self::IN_TABLE; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag + name is "table" */ + } elseif (($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + )) || ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'table') + ) { + /* Parse error. Act as if an end tag with the tag name "caption" + had been seen, then, if that token wasn't ignored, reprocess the + current token. */ + $this->inCaption( + array( + 'name' => 'caption', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inTable($token); + + /* An end tag whose tag name is one of: "body", "col", "colgroup", + "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array( + 'body', + 'col', + 'colgroup', + 'html', + 'tbody', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in body". */ + $this->inBody($token); + } + } + + private function inColumnGroup($token) + { + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $text = $this->dom->createTextNode($token['data']); + end($this->stack)->appendChild($text); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + end($this->stack)->appendChild($comment); + + /* A start tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { + /* Insert a col element for the token. Immediately pop the current + node off the stack of open elements. */ + $this->insertElement($token); + array_pop($this->stack); + + /* An end tag whose tag name is "colgroup" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'colgroup' + ) { + /* If the current node is the root html element, then this is a + parse error, ignore the token. (innerHTML case) */ + if (end($this->stack)->nodeName === 'html') { + // Ignore + + /* Otherwise, pop the current node (which will be a colgroup + element) from the stack of open elements. Switch the insertion + mode to "in table". */ + } else { + array_pop($this->stack); + $this->mode = self::IN_TABLE; + } + + /* An end tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Act as if an end tag with the tag name "colgroup" had been seen, + and then, if that token wasn't ignored, reprocess the current token. */ + $this->inColumnGroup( + array( + 'name' => 'colgroup', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inTable($token); + } + } + + private function inTableBody($token) + { + $clear = array('tbody', 'tfoot', 'thead', 'html'); + + /* A start tag whose tag name is "tr" */ + if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Insert a tr element for the token, then switch the insertion + mode to "in row". */ + $this->insertElement($token); + $this->mode = self::IN_ROW; + + /* A start tag whose tag name is one of: "th", "td" */ + } elseif ($token['type'] === HTML5::STARTTAG && + ($token['name'] === 'th' || $token['name'] === 'td') + ) { + /* Parse error. Act as if a start tag with the tag name "tr" had + been seen, then reprocess the current token. */ + $this->inTableBody( + array( + 'name' => 'tr', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inRow($token); + + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('tbody', 'tfoot', 'thead')) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore + + /* Otherwise: */ + } else { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Pop the current node from the stack of open elements. Switch + the insertion mode to "in table". */ + array_pop($this->stack); + $this->mode = self::IN_TABLE; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ + } elseif (($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead') + )) || + ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table') + ) { + /* If the stack of open elements does not have a tbody, thead, or + tfoot element in table scope, this is a parse error. Ignore the + token. (innerHTML case) */ + if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Act as if an end tag with the same tag name as the current + node ("tbody", "tfoot", or "thead") had been seen, then + reprocess the current token. */ + $this->inTableBody( + array( + 'name' => end($this->stack)->nodeName, + 'type' => HTML5::ENDTAG + ) + ); + + return $this->mainPhase($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "td", "th", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr') + ) + ) { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in table". */ + $this->inTable($token); + } + } + + private function inRow($token) + { + $clear = array('tr', 'html'); + + /* A start tag whose tag name is one of: "th", "td" */ + if ($token['type'] === HTML5::STARTTAG && + ($token['name'] === 'th' || $token['name'] === 'td') + ) { + /* Clear the stack back to a table row context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the insertion + mode to "in cell". */ + $this->insertElement($token); + $this->mode = self::IN_CELL; + + /* Insert a marker at the end of the list of active formatting + elements. */ + $this->a_formatting[] = self::MARKER; + + /* An end tag whose tag name is "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Clear the stack back to a table row context. */ + $this->clearStackToTableContext($clear); + + /* Pop the current node (which will be a tr element) from the + stack of open elements. Switch the insertion mode to "in table + body". */ + array_pop($this->stack); + $this->mode = self::IN_TBODY; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* Act as if an end tag with the tag name "tr" had been seen, then, + if that token wasn't ignored, reprocess the current token. */ + $this->inRow( + array( + 'name' => 'tr', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inCell($token); + + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('tbody', 'tfoot', 'thead')) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Otherwise, act as if an end tag with the tag name "tr" had + been seen, then reprocess the current token. */ + $this->inRow( + array( + 'name' => 'tr', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inCell($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "td", "th" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr') + ) + ) { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in table". */ + $this->inTable($token); + } + } + + private function inCell($token) + { + /* An end tag whose tag name is one of: "td", "th" */ + if ($token['type'] === HTML5::ENDTAG && + ($token['name'] === 'td' || $token['name'] === 'th') + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as that of the token, then this is a + parse error and the token must be ignored. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Generate implied end tags, except for elements with the same + tag name as the token. */ + $this->generateImpliedEndTags(array($token['name'])); + + /* Now, if the current node is not an element with the same tag + name as the token, then this is a parse error. */ + // k + + /* Pop elements from this stack until an element with the same + tag name as the token has been popped from the stack. */ + while (true) { + $node = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($node === $token['name']) { + break; + } + } + + /* Clear the list of active formatting elements up to the last + marker. */ + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); + + /* Switch the insertion mode to "in row". (The current node + will be a tr element at this point.) */ + $this->mode = self::IN_ROW; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + /* If the stack of open elements does not have a td or th element + in table scope, then this is a parse error; ignore the token. + (innerHTML case) */ + if (!$this->elementInScope(array('td', 'th'), true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + /* If the stack of open elements does not have a td or th element + in table scope, then this is a parse error; ignore the token. + (innerHTML case) */ + if (!$this->elementInScope(array('td', 'th'), true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html') + ) + ) { + /* Parse error. Ignore the token. */ + + /* An end tag whose tag name is one of: "table", "tbody", "tfoot", + "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('table', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as that of the token (which can only + happen for "tbody", "tfoot" and "thead", or, in the innerHTML case), + then this is a parse error and the token must be ignored. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in body". */ + $this->inBody($token); + } + } + + private function inSelect($token) + { + /* Handle the token as follows: */ + + /* A character token */ + if ($token['type'] === HTML5::CHARACTR) { + /* Append the token's character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token whose tag name is "option" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'option' + ) { + /* If the current node is an option element, act as if an end tag + with the tag name "option" had been seen. */ + if (end($this->stack)->nodeName === 'option') { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* A start tag token whose tag name is "optgroup" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'optgroup' + ) { + /* If the current node is an option element, act as if an end tag + with the tag name "option" had been seen. */ + if (end($this->stack)->nodeName === 'option') { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the current node is an optgroup element, act as if an end tag + with the tag name "optgroup" had been seen. */ + if (end($this->stack)->nodeName === 'optgroup') { + $this->inSelect( + array( + 'name' => 'optgroup', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* An end tag token whose tag name is "optgroup" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'optgroup' + ) { + /* First, if the current node is an option element, and the node + immediately before it in the stack of open elements is an optgroup + element, then act as if an end tag with the tag name "option" had + been seen. */ + $elements_in_stack = count($this->stack); + + if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' && + $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup' + ) { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the current node is an optgroup element, then pop that node + from the stack of open elements. Otherwise, this is a parse error, + ignore the token. */ + if ($this->stack[$elements_in_stack - 1] === 'optgroup') { + array_pop($this->stack); + } + + /* An end tag token whose tag name is "option" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'option' + ) { + /* If the current node is an option element, then pop that node + from the stack of open elements. Otherwise, this is a parse error, + ignore the token. */ + if (end($this->stack)->nodeName === 'option') { + array_pop($this->stack); + } + + /* An end tag whose tag name is "select" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'select' + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // w/e + + /* Otherwise: */ + } else { + /* Pop elements from the stack of open elements until a select + element has been popped from the stack. */ + while (true) { + $current = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($current === 'select') { + break; + } + } + + /* Reset the insertion mode appropriately. */ + $this->resetInsertionMode(); + } + + /* A start tag whose tag name is "select" */ + } elseif ($token['name'] === 'select' && + $token['type'] === HTML5::STARTTAG + ) { + /* Parse error. Act as if the token had been an end tag with the + tag name "select" instead. */ + $this->inSelect( + array( + 'name' => 'select', + 'type' => HTML5::ENDTAG + ) + ); + + /* An end tag whose tag name is one of: "caption", "table", "tbody", + "tfoot", "thead", "tr", "td", "th" */ + } elseif (in_array( + $token['name'], + array( + 'caption', + 'table', + 'tbody', + 'tfoot', + 'thead', + 'tr', + 'td', + 'th' + ) + ) && $token['type'] === HTML5::ENDTAG + ) { + /* Parse error. */ + // w/e + + /* If the stack of open elements has an element in table scope with + the same tag name as that of the token, then act as if an end tag + with the tag name "select" had been seen, and reprocess the token. + Otherwise, ignore the token. */ + if ($this->elementInScope($token['name'], true)) { + $this->inSelect( + array( + 'name' => 'select', + 'type' => HTML5::ENDTAG + ) + ); + + $this->mainPhase($token); + } + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function afterBody($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Process the token as it would be processed if the insertion mode + was "in body". */ + $this->inBody($token); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the first element in the stack of open + elements (the html element), with the data attribute set to the + data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->stack[0]->appendChild($comment); + + /* An end tag with the tag name "html" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { + /* If the parser was originally created in order to handle the + setting of an element's innerHTML attribute, this is a parse error; + ignore the token. (The element will be an html element in this + case.) (innerHTML case) */ + + /* Otherwise, switch to the trailing end phase. */ + $this->phase = self::END_PHASE; + + /* Anything else */ + } else { + /* Parse error. Set the insertion mode to "in body" and reprocess + the token. */ + $this->mode = self::IN_BODY; + return $this->inBody($token); + } + } + + private function inFrameset($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag with the tag name "frameset" */ + } elseif ($token['name'] === 'frameset' && + $token['type'] === HTML5::STARTTAG + ) { + $this->insertElement($token); + + /* An end tag with the tag name "frameset" */ + } elseif ($token['name'] === 'frameset' && + $token['type'] === HTML5::ENDTAG + ) { + /* If the current node is the root html element, then this is a + parse error; ignore the token. (innerHTML case) */ + if (end($this->stack)->nodeName === 'html') { + // Ignore + + } else { + /* Otherwise, pop the current node from the stack of open + elements. */ + array_pop($this->stack); + + /* If the parser was not originally created in order to handle + the setting of an element's innerHTML attribute (innerHTML case), + and the current node is no longer a frameset element, then change + the insertion mode to "after frameset". */ + $this->mode = self::AFTR_FRAME; + } + + /* A start tag with the tag name "frame" */ + } elseif ($token['name'] === 'frame' && + $token['type'] === HTML5::STARTTAG + ) { + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { + /* Process the token as if the insertion mode had been "in body". */ + $this->inBody($token); + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function afterFrameset($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* An end tag with the tag name "html" */ + } elseif ($token['name'] === 'html' && + $token['type'] === HTML5::ENDTAG + ) { + /* Switch to the trailing end phase. */ + $this->phase = self::END_PHASE; + + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { + /* Process the token as if the insertion mode had been "in body". */ + $this->inBody($token); + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function trailingEndPhase($token) + { + /* After the main phase, as each token is emitted from the tokenisation + stage, it must be processed as described in this section. */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the Document object with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->dom->appendChild($comment); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Process the token as it would be processed in the main phase. */ + $this->mainPhase($token); + + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or a start tag token. Or an end tag token. */ + } elseif (($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || + $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG + ) { + /* Parse error. Switch back to the main phase and reprocess the + token. */ + $this->phase = self::MAIN_PHASE; + return $this->mainPhase($token); + + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { + /* OMG DONE!! */ + } + } + + private function insertElement($token, $append = true, $check = false) + { + // Proprietary workaround for libxml2's limitations with tag names + if ($check) { + // Slightly modified HTML5 tag-name modification, + // removing anything that's not an ASCII letter, digit, or hyphen + $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']); + // Remove leading hyphens and numbers + $token['name'] = ltrim($token['name'], '-0..9'); + // In theory, this should ever be needed, but just in case + if ($token['name'] === '') { + $token['name'] = 'span'; + } // arbitrary generic choice + } + + $el = $this->dom->createElement($token['name']); + + foreach ($token['attr'] as $attr) { + if (!$el->hasAttribute($attr['name'])) { + $el->setAttribute($attr['name'], (string)$attr['value']); + } + } + + $this->appendToRealParent($el); + $this->stack[] = $el; + + return $el; + } + + private function insertText($data) + { + $text = $this->dom->createTextNode($data); + $this->appendToRealParent($text); + } + + private function insertComment($data) + { + $comment = $this->dom->createComment($data); + $this->appendToRealParent($comment); + } + + private function appendToRealParent($node) + { + if ($this->foster_parent === null) { + end($this->stack)->appendChild($node); + + } elseif ($this->foster_parent !== null) { + /* If the foster parent element is the parent element of the + last table element in the stack of open elements, then the new + node must be inserted immediately before the last table element + in the stack of open elements in the foster parent element; + otherwise, the new node must be appended to the foster parent + element. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === 'table' && + $this->stack[$n]->parentNode !== null + ) { + $table = $this->stack[$n]; + break; + } + } + + if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) { + $this->foster_parent->insertBefore($node, $table); + } else { + $this->foster_parent->appendChild($node); + } + + $this->foster_parent = null; + } + } + + private function elementInScope($el, $table = false) + { + if (is_array($el)) { + foreach ($el as $element) { + if ($this->elementInScope($element, $table)) { + return true; + } + } + + return false; + } + + $leng = count($this->stack); + + for ($n = 0; $n < $leng; $n++) { + /* 1. Initialise node to be the current node (the bottommost node of + the stack). */ + $node = $this->stack[$leng - 1 - $n]; + + if ($node->tagName === $el) { + /* 2. If node is the target node, terminate in a match state. */ + return true; + + } elseif ($node->tagName === 'table') { + /* 3. Otherwise, if node is a table element, terminate in a failure + state. */ + return false; + + } elseif ($table === true && in_array( + $node->tagName, + array( + 'caption', + 'td', + 'th', + 'button', + 'marquee', + 'object' + ) + ) + ) { + /* 4. Otherwise, if the algorithm is the "has an element in scope" + variant (rather than the "has an element in table scope" variant), + and node is one of the following, terminate in a failure state. */ + return false; + + } elseif ($node === $node->ownerDocument->documentElement) { + /* 5. Otherwise, if node is an html element (root element), terminate + in a failure state. (This can only happen if the node is the topmost + node of the stack of open elements, and prevents the next step from + being invoked if there are no more elements in the stack.) */ + return false; + } + + /* Otherwise, set node to the previous entry in the stack of open + elements and return to step 2. (This will never fail, since the loop + will always terminate in the previous step if the top of the stack + is reached.) */ + } + } + + private function reconstructActiveFormattingElements() + { + /* 1. If there are no entries in the list of active formatting elements, + then there is nothing to reconstruct; stop this algorithm. */ + $formatting_elements = count($this->a_formatting); + + if ($formatting_elements === 0) { + return false; + } + + /* 3. Let entry be the last (most recently added) element in the list + of active formatting elements. */ + $entry = end($this->a_formatting); + + /* 2. If the last (most recently added) entry in the list of active + formatting elements is a marker, or if it is an element that is in the + stack of open elements, then there is nothing to reconstruct; stop this + algorithm. */ + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { + return false; + } + + for ($a = $formatting_elements - 1; $a >= 0; true) { + /* 4. If there are no entries before entry in the list of active + formatting elements, then jump to step 8. */ + if ($a === 0) { + $step_seven = false; + break; + } + + /* 5. Let entry be the entry one earlier than entry in the list of + active formatting elements. */ + $a--; + $entry = $this->a_formatting[$a]; + + /* 6. If entry is neither a marker nor an element that is also in + thetack of open elements, go to step 4. */ + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { + break; + } + } + + while (true) { + /* 7. Let entry be the element one later than entry in the list of + active formatting elements. */ + if (isset($step_seven) && $step_seven === true) { + $a++; + $entry = $this->a_formatting[$a]; + } + + /* 8. Perform a shallow clone of the element entry to obtain clone. */ + $clone = $entry->cloneNode(); + + /* 9. Append clone to the current node and push it onto the stack + of open elements so that it is the new current node. */ + end($this->stack)->appendChild($clone); + $this->stack[] = $clone; + + /* 10. Replace the entry for entry in the list with an entry for + clone. */ + $this->a_formatting[$a] = $clone; + + /* 11. If the entry for clone in the list of active formatting + elements is not the last entry in the list, return to step 7. */ + if (end($this->a_formatting) !== $clone) { + $step_seven = true; + } else { + break; + } + } + } + + private function clearTheActiveFormattingElementsUpToTheLastMarker() + { + /* When the steps below require the UA to clear the list of active + formatting elements up to the last marker, the UA must perform the + following steps: */ + + while (true) { + /* 1. Let entry be the last (most recently added) entry in the list + of active formatting elements. */ + $entry = end($this->a_formatting); + + /* 2. Remove entry from the list of active formatting elements. */ + array_pop($this->a_formatting); + + /* 3. If entry was a marker, then stop the algorithm at this point. + The list has been cleared up to the last marker. */ + if ($entry === self::MARKER) { + break; + } + } + } + + private function generateImpliedEndTags($exclude = array()) + { + /* When the steps below require the UA to generate implied end tags, + then, if the current node is a dd element, a dt element, an li element, + a p element, a td element, a th element, or a tr element, the UA must + act as if an end tag with the respective tag name had been seen and + then generate implied end tags again. */ + $node = end($this->stack); + $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); + + while (in_array(end($this->stack)->nodeName, $elements)) { + array_pop($this->stack); + } + } + + private function getElementCategory($node) + { + $name = $node->tagName; + if (in_array($name, $this->special)) { + return self::SPECIAL; + } elseif (in_array($name, $this->scoping)) { + return self::SCOPING; + } elseif (in_array($name, $this->formatting)) { + return self::FORMATTING; + } else { + return self::PHRASING; + } + } + + private function clearStackToTableContext($elements) + { + /* When the steps above require the UA to clear the stack back to a + table context, it means that the UA must, while the current node is not + a table element or an html element, pop elements from the stack of open + elements. If this causes any elements to be popped from the stack, then + this is a parse error. */ + while (true) { + $node = end($this->stack)->nodeName; + + if (in_array($node, $elements)) { + break; + } else { + array_pop($this->stack); + } + } + } + + private function resetInsertionMode() + { + /* 1. Let last be false. */ + $last = false; + $leng = count($this->stack); + + for ($n = $leng - 1; $n >= 0; $n--) { + /* 2. Let node be the last node in the stack of open elements. */ + $node = $this->stack[$n]; + + /* 3. If node is the first node in the stack of open elements, then + set last to true. If the element whose innerHTML attribute is being + set is neither a td element nor a th element, then set node to the + element whose innerHTML attribute is being set. (innerHTML case) */ + if ($this->stack[0]->isSameNode($node)) { + $last = true; + } + + /* 4. If node is a select element, then switch the insertion mode to + "in select" and abort these steps. (innerHTML case) */ + if ($node->nodeName === 'select') { + $this->mode = self::IN_SELECT; + break; + + /* 5. If node is a td or th element, then switch the insertion mode + to "in cell" and abort these steps. */ + } elseif ($node->nodeName === 'td' || $node->nodeName === 'th') { + $this->mode = self::IN_CELL; + break; + + /* 6. If node is a tr element, then switch the insertion mode to + "in row" and abort these steps. */ + } elseif ($node->nodeName === 'tr') { + $this->mode = self::IN_ROW; + break; + + /* 7. If node is a tbody, thead, or tfoot element, then switch the + insertion mode to "in table body" and abort these steps. */ + } elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { + $this->mode = self::IN_TBODY; + break; + + /* 8. If node is a caption element, then switch the insertion mode + to "in caption" and abort these steps. */ + } elseif ($node->nodeName === 'caption') { + $this->mode = self::IN_CAPTION; + break; + + /* 9. If node is a colgroup element, then switch the insertion mode + to "in column group" and abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'colgroup') { + $this->mode = self::IN_CGROUP; + break; + + /* 10. If node is a table element, then switch the insertion mode + to "in table" and abort these steps. */ + } elseif ($node->nodeName === 'table') { + $this->mode = self::IN_TABLE; + break; + + /* 11. If node is a head element, then switch the insertion mode + to "in body" ("in body"! not "in head"!) and abort these steps. + (innerHTML case) */ + } elseif ($node->nodeName === 'head') { + $this->mode = self::IN_BODY; + break; + + /* 12. If node is a body element, then switch the insertion mode to + "in body" and abort these steps. */ + } elseif ($node->nodeName === 'body') { + $this->mode = self::IN_BODY; + break; + + /* 13. If node is a frameset element, then switch the insertion + mode to "in frameset" and abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'frameset') { + $this->mode = self::IN_FRAME; + break; + + /* 14. If node is an html element, then: if the head element + pointer is null, switch the insertion mode to "before head", + otherwise, switch the insertion mode to "after head". In either + case, abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'html') { + $this->mode = ($this->head_pointer === null) + ? self::BEFOR_HEAD + : self::AFTER_HEAD; + + break; + + /* 15. If last is true, then set the insertion mode to "in body" + and abort these steps. (innerHTML case) */ + } elseif ($last) { + $this->mode = self::IN_BODY; + break; + } + } + } + + private function closeCell() + { + /* If the stack of open elements has a td or th element in table scope, + then act as if an end tag token with that tag name had been seen. */ + foreach (array('td', 'th') as $cell) { + if ($this->elementInScope($cell, true)) { + $this->inCell( + array( + 'name' => $cell, + 'type' => HTML5::ENDTAG + ) + ); + + break; + } + } + } + + public function save() + { + return $this->dom; + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/Node.php b/software/HTMLPurifier/HTMLPurifier/Node.php new file mode 100644 index 0000000..3995fec --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Node.php @@ -0,0 +1,49 @@ +data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Comment($this->data, $this->line, $this->col), null); + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/Node/Element.php b/software/HTMLPurifier/HTMLPurifier/Node/Element.php new file mode 100644 index 0000000..6cbf56d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Node/Element.php @@ -0,0 +1,59 @@ + form or the form, i.e. + * is it a pair of start/end tokens or an empty token. + * @bool + */ + public $empty = false; + + public $endCol = null, $endLine = null, $endArmor = array(); + + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) { + $this->name = $name; + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toTokenPair() { + // XXX inefficiency here, normalization is not necessary + if ($this->empty) { + return array(new HTMLPurifier_Token_Empty($this->name, $this->attr, $this->line, $this->col, $this->armor), null); + } else { + $start = new HTMLPurifier_Token_Start($this->name, $this->attr, $this->line, $this->col, $this->armor); + $end = new HTMLPurifier_Token_End($this->name, array(), $this->endLine, $this->endCol, $this->endArmor); + //$end->start = $start; + return array($start, $end); + } + } +} + diff --git a/software/HTMLPurifier/HTMLPurifier/Node/Text.php b/software/HTMLPurifier/HTMLPurifier/Node/Text.php new file mode 100644 index 0000000..aec9166 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Node/Text.php @@ -0,0 +1,54 @@ +data = $data; + $this->is_whitespace = $is_whitespace; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Text($this->data, $this->line, $this->col), null); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/PercentEncoder.php b/software/HTMLPurifier/HTMLPurifier/PercentEncoder.php new file mode 100644 index 0000000..18c8bbb --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/PercentEncoder.php @@ -0,0 +1,111 @@ +preserve[$i] = true; + } + for ($i = 65; $i <= 90; $i++) { // upper-case + $this->preserve[$i] = true; + } + for ($i = 97; $i <= 122; $i++) { // lower-case + $this->preserve[$i] = true; + } + $this->preserve[45] = true; // Dash - + $this->preserve[46] = true; // Period . + $this->preserve[95] = true; // Underscore _ + $this->preserve[126]= true; // Tilde ~ + + // extra letters not to escape + if ($preserve !== false) { + for ($i = 0, $c = strlen($preserve); $i < $c; $i++) { + $this->preserve[ord($preserve[$i])] = true; + } + } + } + + /** + * Our replacement for urlencode, it encodes all non-reserved characters, + * as well as any extra characters that were instructed to be preserved. + * @note + * Assumes that the string has already been normalized, making any + * and all percent escape sequences valid. Percents will not be + * re-escaped, regardless of their status in $preserve + * @param string $string String to be encoded + * @return string Encoded string. + */ + public function encode($string) + { + $ret = ''; + for ($i = 0, $c = strlen($string); $i < $c; $i++) { + if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])])) { + $ret .= '%' . sprintf('%02X', $int); + } else { + $ret .= $string[$i]; + } + } + return $ret; + } + + /** + * Fix up percent-encoding by decoding unreserved characters and normalizing. + * @warning This function is affected by $preserve, even though the + * usual desired behavior is for this not to preserve those + * characters. Be careful when reusing instances of PercentEncoder! + * @param string $string String to normalize + * @return string + */ + public function normalize($string) + { + if ($string == '') { + return ''; + } + $parts = explode('%', $string); + $ret = array_shift($parts); + foreach ($parts as $part) { + $length = strlen($part); + if ($length < 2) { + $ret .= '%25' . $part; + continue; + } + $encoding = substr($part, 0, 2); + $text = substr($part, 2); + if (!ctype_xdigit($encoding)) { + $ret .= '%25' . $part; + continue; + } + $int = hexdec($encoding); + if (isset($this->preserve[$int])) { + $ret .= chr($int) . $text; + continue; + } + $encoding = strtoupper($encoding); + $ret .= '%' . $encoding . $text; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Printer.php b/software/HTMLPurifier/HTMLPurifier/Printer.php new file mode 100644 index 0000000..549e4ce --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer.php @@ -0,0 +1,218 @@ +getAll(); + $context = new HTMLPurifier_Context(); + $this->generator = new HTMLPurifier_Generator($config, $context); + } + + /** + * Main function that renders object or aspect of that object + * @note Parameters vary depending on printer + */ + // function render() {} + + /** + * Returns a start tag + * @param string $tag Tag name + * @param array $attr Attribute array + * @return string + */ + protected function start($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) + ); + } + + /** + * Returns an end tag + * @param string $tag Tag name + * @return string + */ + protected function end($tag) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_End($tag) + ); + } + + /** + * Prints a complete element with content inside + * @param string $tag Tag name + * @param string $contents Element contents + * @param array $attr Tag attributes + * @param bool $escape whether or not to escape contents + * @return string + */ + protected function element($tag, $contents, $attr = array(), $escape = true) + { + return $this->start($tag, $attr) . + ($escape ? $this->escape($contents) : $contents) . + $this->end($tag); + } + + /** + * @param string $tag + * @param array $attr + * @return string + */ + protected function elementEmpty($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Empty($tag, $attr) + ); + } + + /** + * @param string $text + * @return string + */ + protected function text($text) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Text($text) + ); + } + + /** + * Prints a simple key/value row in a table. + * @param string $name Key + * @param mixed $value Value + * @return string + */ + protected function row($name, $value) + { + if (is_bool($value)) { + $value = $value ? 'On' : 'Off'; + } + return + $this->start('tr') . "\n" . + $this->element('th', $name) . "\n" . + $this->element('td', $value) . "\n" . + $this->end('tr'); + } + + /** + * Escapes a string for HTML output. + * @param string $string String to escape + * @return string + */ + protected function escape($string) + { + $string = HTMLPurifier_Encoder::cleanUTF8($string); + $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8'); + return $string; + } + + /** + * Takes a list of strings and turns them into a single list + * @param string[] $array List of strings + * @param bool $polite Bool whether or not to add an end before the last + * @return string + */ + protected function listify($array, $polite = false) + { + if (empty($array)) { + return 'None'; + } + $ret = ''; + $i = count($array); + foreach ($array as $value) { + $i--; + $ret .= $value; + if ($i > 0 && !($polite && $i == 1)) { + $ret .= ', '; + } + if ($polite && $i == 1) { + $ret .= 'and '; + } + } + return $ret; + } + + /** + * Retrieves the class of an object without prefixes, as well as metadata + * @param object $obj Object to determine class of + * @param string $sec_prefix Further prefix to remove + * @return string + */ + protected function getClass($obj, $sec_prefix = '') + { + static $five = null; + if ($five === null) { + $five = version_compare(PHP_VERSION, '5', '>='); + } + $prefix = 'HTMLPurifier_' . $sec_prefix; + if (!$five) { + $prefix = strtolower($prefix); + } + $class = str_replace($prefix, '', get_class($obj)); + $lclass = strtolower($class); + $class .= '('; + switch ($lclass) { + case 'enum': + $values = array(); + foreach ($obj->valid_values as $value => $bool) { + $values[] = $value; + } + $class .= implode(', ', $values); + break; + case 'css_composite': + $values = array(); + foreach ($obj->defs as $def) { + $values[] = $this->getClass($def, $sec_prefix); + } + $class .= implode(', ', $values); + break; + case 'css_multiple': + $class .= $this->getClass($obj->single, $sec_prefix) . ', '; + $class .= $obj->max; + break; + case 'css_denyelementdecorator': + $class .= $this->getClass($obj->def, $sec_prefix) . ', '; + $class .= $obj->element; + break; + case 'css_importantdecorator': + $class .= $this->getClass($obj->def, $sec_prefix); + if ($obj->allow) { + $class .= ', !important'; + } + break; + } + $class .= ')'; + return $class; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php b/software/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php new file mode 100644 index 0000000..29505fe --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php @@ -0,0 +1,44 @@ +def = $config->getCSSDefinition(); + $ret = ''; + + $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer')); + $ret .= $this->start('table'); + + $ret .= $this->element('caption', 'Properties ($info)'); + + $ret .= $this->start('thead'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Property', array('class' => 'heavy')); + $ret .= $this->element('th', 'Definition', array('class' => 'heavy', 'style' => 'width:auto;')); + $ret .= $this->end('tr'); + $ret .= $this->end('thead'); + + ksort($this->def->info); + foreach ($this->def->info as $property => $obj) { + $name = $this->getClass($obj, 'AttrDef_'); + $ret .= $this->row($property, $name); + } + + $ret .= $this->end('table'); + $ret .= $this->end('div'); + + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.css b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.css new file mode 100644 index 0000000..3ff1a88 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.css @@ -0,0 +1,10 @@ + +.hp-config {} + +.hp-config tbody th {text-align:right; padding-right:0.5em;} +.hp-config thead, .hp-config .namespace {background:#3C578C; color:#FFF;} +.hp-config .namespace th {text-align:center;} +.hp-config .verbose {display:none;} +.hp-config .controls {text-align:center;} + +/* vim: et sw=4 sts=4 */ diff --git a/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.js b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.js new file mode 100644 index 0000000..cba00c9 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.js @@ -0,0 +1,5 @@ +function toggleWriteability(id_of_patient, checked) { + document.getElementById(id_of_patient).disabled = checked; +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php new file mode 100644 index 0000000..33ae113 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php @@ -0,0 +1,451 @@ +docURL = $doc_url; + $this->name = $name; + $this->compress = $compress; + // initialize sub-printers + $this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default(); + $this->fields[HTMLPurifier_VarParser::C_BOOL] = new HTMLPurifier_Printer_ConfigForm_bool(); + } + + /** + * Sets default column and row size for textareas in sub-printers + * @param $cols Integer columns of textarea, null to use default + * @param $rows Integer rows of textarea, null to use default + */ + public function setTextareaDimensions($cols = null, $rows = null) + { + if ($cols) { + $this->fields['default']->cols = $cols; + } + if ($rows) { + $this->fields['default']->rows = $rows; + } + } + + /** + * Retrieves styling, in case it is not accessible by webserver + */ + public static function getCSS() + { + return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css'); + } + + /** + * Retrieves JavaScript, in case it is not accessible by webserver + */ + public static function getJavaScript() + { + return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js'); + } + + /** + * Returns HTML output for a configuration form + * @param HTMLPurifier_Config|array $config Configuration object of current form state, or an array + * where [0] has an HTML namespace and [1] is being rendered. + * @param array|bool $allowed Optional namespace(s) and directives to restrict form to. + * @param bool $render_controls + * @return string + */ + public function render($config, $allowed = true, $render_controls = true) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + + $this->config = $config; + $this->genConfig = $gen_config; + $this->prepareGenerator($gen_config); + + $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $config->def); + $all = array(); + foreach ($allowed as $key) { + list($ns, $directive) = $key; + $all[$ns][$directive] = $config->get($ns . '.' . $directive); + } + + $ret = ''; + $ret .= $this->start('table', array('class' => 'hp-config')); + $ret .= $this->start('thead'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Directive', array('class' => 'hp-directive')); + $ret .= $this->element('th', 'Value', array('class' => 'hp-value')); + $ret .= $this->end('tr'); + $ret .= $this->end('thead'); + foreach ($all as $ns => $directives) { + $ret .= $this->renderNamespace($ns, $directives); + } + if ($render_controls) { + $ret .= $this->start('tbody'); + $ret .= $this->start('tr'); + $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls')); + $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit')); + $ret .= '[Reset]'; + $ret .= $this->end('td'); + $ret .= $this->end('tr'); + $ret .= $this->end('tbody'); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders a single namespace + * @param $ns String namespace name + * @param array $directives array of directives to values + * @return string + */ + protected function renderNamespace($ns, $directives) + { + $ret = ''; + $ret .= $this->start('tbody', array('class' => 'namespace')); + $ret .= $this->start('tr'); + $ret .= $this->element('th', $ns, array('colspan' => 2)); + $ret .= $this->end('tr'); + $ret .= $this->end('tbody'); + $ret .= $this->start('tbody'); + foreach ($directives as $directive => $value) { + $ret .= $this->start('tr'); + $ret .= $this->start('th'); + if ($this->docURL) { + $url = str_replace('%s', urlencode("$ns.$directive"), $this->docURL); + $ret .= $this->start('a', array('href' => $url)); + } + $attr = array('for' => "{$this->name}:$ns.$directive"); + + // crop directive name if it's too long + if (!$this->compress || (strlen($directive) < $this->compress)) { + $directive_disp = $directive; + } else { + $directive_disp = substr($directive, 0, $this->compress - 2) . '...'; + $attr['title'] = $directive; + } + + $ret .= $this->element( + 'label', + $directive_disp, + // component printers must create an element with this id + $attr + ); + if ($this->docURL) { + $ret .= $this->end('a'); + } + $ret .= $this->end('th'); + + $ret .= $this->start('td'); + $def = $this->config->def->info["$ns.$directive"]; + if (is_int($def)) { + $allow_null = $def < 0; + $type = abs($def); + } else { + $type = $def->type; + $allow_null = isset($def->allow_null); + } + if (!isset($this->fields[$type])) { + $type = 0; + } // default + $type_obj = $this->fields[$type]; + if ($allow_null) { + $type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj); + } + $ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config)); + $ret .= $this->end('td'); + $ret .= $this->end('tr'); + } + $ret .= $this->end('tbody'); + return $ret; + } + +} + +/** + * Printer decorator for directives that accept null + */ +class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer +{ + /** + * Printer being decorated + * @type HTMLPurifier_Printer + */ + protected $obj; + + /** + * @param HTMLPurifier_Printer $obj Printer to decorate + */ + public function __construct($obj) + { + parent::__construct(); + $this->obj = $obj; + } + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + + $ret = ''; + $ret .= $this->start('label', array('for' => "$name:Null_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' Null/Disabled'); + $ret .= $this->end('label'); + $attr = array( + 'type' => 'checkbox', + 'value' => '1', + 'class' => 'null-toggle', + 'name' => "$name" . "[Null_$ns.$directive]", + 'id' => "$name:Null_$ns.$directive", + 'onclick' => "toggleWriteability('$name:$ns.$directive',checked)" // INLINE JAVASCRIPT!!!! + ); + if ($this->obj instanceof HTMLPurifier_Printer_ConfigForm_bool) { + // modify inline javascript slightly + $attr['onclick'] = + "toggleWriteability('$name:Yes_$ns.$directive',checked);" . + "toggleWriteability('$name:No_$ns.$directive',checked)"; + } + if ($value === null) { + $attr['checked'] = 'checked'; + } + $ret .= $this->elementEmpty('input', $attr); + $ret .= $this->text(' or '); + $ret .= $this->elementEmpty('br'); + $ret .= $this->obj->render($ns, $directive, $value, $name, array($gen_config, $config)); + return $ret; + } +} + +/** + * Swiss-army knife configuration form field printer + */ +class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer +{ + /** + * @type int + */ + public $cols = 18; + + /** + * @type int + */ + public $rows = 5; + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + // this should probably be split up a little + $ret = ''; + $def = $config->def->info["$ns.$directive"]; + if (is_int($def)) { + $type = abs($def); + } else { + $type = $def->type; + } + if (is_array($value)) { + switch ($type) { + case HTMLPurifier_VarParser::LOOKUP: + $array = $value; + $value = array(); + foreach ($array as $val => $b) { + $value[] = $val; + } + //TODO does this need a break? + case HTMLPurifier_VarParser::ALIST: + $value = implode(PHP_EOL, $value); + break; + case HTMLPurifier_VarParser::HASH: + $nvalue = ''; + foreach ($value as $i => $v) { + if (is_array($v)) { + // HACK + $v = implode(";", $v); + } + $nvalue .= "$i:$v" . PHP_EOL; + } + $value = $nvalue; + break; + default: + $value = ''; + } + } + if ($type === HTMLPurifier_VarParser::C_MIXED) { + return 'Not supported'; + $value = serialize($value); + } + $attr = array( + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:$ns.$directive" + ); + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + if (isset($def->allowed)) { + $ret .= $this->start('select', $attr); + foreach ($def->allowed as $val => $b) { + $attr = array(); + if ($value == $val) { + $attr['selected'] = 'selected'; + } + $ret .= $this->element('option', $val, $attr); + } + $ret .= $this->end('select'); + } elseif ($type === HTMLPurifier_VarParser::TEXT || + $type === HTMLPurifier_VarParser::ITEXT || + $type === HTMLPurifier_VarParser::ALIST || + $type === HTMLPurifier_VarParser::HASH || + $type === HTMLPurifier_VarParser::LOOKUP) { + $attr['cols'] = $this->cols; + $attr['rows'] = $this->rows; + $ret .= $this->start('textarea', $attr); + $ret .= $this->text($value); + $ret .= $this->end('textarea'); + } else { + $attr['value'] = $value; + $attr['type'] = 'text'; + $ret .= $this->elementEmpty('input', $attr); + } + return $ret; + } +} + +/** + * Bool form field printer + */ +class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer +{ + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + $ret = ''; + $ret .= $this->start('div', array('id' => "$name:$ns.$directive")); + + $ret .= $this->start('label', array('for' => "$name:Yes_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' Yes'); + $ret .= $this->end('label'); + + $attr = array( + 'type' => 'radio', + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:Yes_$ns.$directive", + 'value' => '1' + ); + if ($value === true) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + $ret .= $this->elementEmpty('input', $attr); + + $ret .= $this->start('label', array('for' => "$name:No_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' No'); + $ret .= $this->end('label'); + + $attr = array( + 'type' => 'radio', + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:No_$ns.$directive", + 'value' => '0' + ); + if ($value === false) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + $ret .= $this->elementEmpty('input', $attr); + + $ret .= $this->end('div'); + + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php b/software/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php new file mode 100644 index 0000000..ae86391 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php @@ -0,0 +1,324 @@ +config =& $config; + + $this->def = $config->getHTMLDefinition(); + + $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer')); + + $ret .= $this->renderDoctype(); + $ret .= $this->renderEnvironment(); + $ret .= $this->renderContentSets(); + $ret .= $this->renderInfo(); + + $ret .= $this->end('div'); + + return $ret; + } + + /** + * Renders the Doctype table + * @return string + */ + protected function renderDoctype() + { + $doctype = $this->def->doctype; + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Doctype'); + $ret .= $this->row('Name', $doctype->name); + $ret .= $this->row('XML', $doctype->xml ? 'Yes' : 'No'); + $ret .= $this->row('Default Modules', implode(', ', $doctype->modules)); + $ret .= $this->row('Default Tidy Modules', implode(', ', $doctype->tidyModules)); + $ret .= $this->end('table'); + return $ret; + } + + + /** + * Renders environment table, which is miscellaneous info + * @return string + */ + protected function renderEnvironment() + { + $def = $this->def; + + $ret = ''; + + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Environment'); + + $ret .= $this->row('Parent of fragment', $def->info_parent); + $ret .= $this->renderChildren($def->info_parent_def->child); + $ret .= $this->row('Block wrap name', $def->info_block_wrapper); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Global attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr), null, 0); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Tag transforms'); + $list = array(); + foreach ($def->info_tag_transform as $old => $new) { + $new = $this->getClass($new, 'TagTransform_'); + $list[] = "<$old> with $new"; + } + $ret .= $this->element('td', $this->listify($list)); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre)); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post)); + $ret .= $this->end('tr'); + + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders the Content Sets table + * @return string + */ + protected function renderContentSets() + { + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Content Sets'); + foreach ($this->def->info_content_sets as $name => $lookup) { + $ret .= $this->heavyHeader($name); + $ret .= $this->start('tr'); + $ret .= $this->element('td', $this->listifyTagLookup($lookup)); + $ret .= $this->end('tr'); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders the Elements ($info) table + * @return string + */ + protected function renderInfo() + { + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Elements ($info)'); + ksort($this->def->info); + $ret .= $this->heavyHeader('Allowed tags', 2); + $ret .= $this->start('tr'); + $ret .= $this->element('td', $this->listifyTagLookup($this->def->info), array('colspan' => 2)); + $ret .= $this->end('tr'); + foreach ($this->def->info as $name => $def) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', "<$name>", array('class' => 'heavy', 'colspan' => 2)); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Inline content'); + $ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No'); + $ret .= $this->end('tr'); + if (!empty($def->excludes)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Excludes'); + $ret .= $this->element('td', $this->listifyTagLookup($def->excludes)); + $ret .= $this->end('tr'); + } + if (!empty($def->attr_transform_pre)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre)); + $ret .= $this->end('tr'); + } + if (!empty($def->attr_transform_post)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post)); + $ret .= $this->end('tr'); + } + if (!empty($def->auto_close)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Auto closed by'); + $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close)); + $ret .= $this->end('tr'); + } + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Allowed attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->attr), array(), 0); + $ret .= $this->end('tr'); + + if (!empty($def->required_attr)) { + $ret .= $this->row('Required attributes', $this->listify($def->required_attr)); + } + + $ret .= $this->renderChildren($def->child); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders a row describing the allowed children of an element + * @param HTMLPurifier_ChildDef $def HTMLPurifier_ChildDef of pertinent element + * @return string + */ + protected function renderChildren($def) + { + $context = new HTMLPurifier_Context(); + $ret = ''; + $ret .= $this->start('tr'); + $elements = array(); + $attr = array(); + if (isset($def->elements)) { + if ($def->type == 'strictblockquote') { + $def->validateChildren(array(), $this->config, $context); + } + $elements = $def->elements; + } + if ($def->type == 'chameleon') { + $attr['rowspan'] = 2; + } elseif ($def->type == 'empty') { + $elements = array(); + } elseif ($def->type == 'table') { + $elements = array_flip( + array( + 'col', + 'caption', + 'colgroup', + 'thead', + 'tfoot', + 'tbody', + 'tr' + ) + ); + } + $ret .= $this->element('th', 'Allowed children', $attr); + + if ($def->type == 'chameleon') { + + $ret .= $this->element( + 'td', + 'Block: ' . + $this->escape($this->listifyTagLookup($def->block->elements)), + null, + 0 + ); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element( + 'td', + 'Inline: ' . + $this->escape($this->listifyTagLookup($def->inline->elements)), + null, + 0 + ); + + } elseif ($def->type == 'custom') { + + $ret .= $this->element( + 'td', + '' . ucfirst($def->type) . ': ' . + $def->dtd_regex + ); + + } else { + $ret .= $this->element( + 'td', + '' . ucfirst($def->type) . ': ' . + $this->escape($this->listifyTagLookup($elements)), + null, + 0 + ); + } + $ret .= $this->end('tr'); + return $ret; + } + + /** + * Listifies a tag lookup table. + * @param array $array Tag lookup array in form of array('tagname' => true) + * @return string + */ + protected function listifyTagLookup($array) + { + ksort($array); + $list = array(); + foreach ($array as $name => $discard) { + if ($name !== '#PCDATA' && !isset($this->def->info[$name])) { + continue; + } + $list[] = $name; + } + return $this->listify($list); + } + + /** + * Listifies a list of objects by retrieving class names and internal state + * @param array $array List of objects + * @return string + * @todo Also add information about internal state + */ + protected function listifyObjectList($array) + { + ksort($array); + $list = array(); + foreach ($array as $obj) { + $list[] = $this->getClass($obj, 'AttrTransform_'); + } + return $this->listify($list); + } + + /** + * Listifies a hash of attributes to AttrDef classes + * @param array $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef) + * @return string + */ + protected function listifyAttr($array) + { + ksort($array); + $list = array(); + foreach ($array as $name => $obj) { + if ($obj === false) { + continue; + } + $list[] = "$name = " . $this->getClass($obj, 'AttrDef_') . ''; + } + return $this->listify($list); + } + + /** + * Creates a heavy header row + * @param string $text + * @param int $num + * @return string + */ + protected function heavyHeader($text, $num = 1) + { + $ret = ''; + $ret .= $this->start('tr'); + $ret .= $this->element('th', $text, array('colspan' => $num, 'class' => 'heavy')); + $ret .= $this->end('tr'); + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/PropertyList.php b/software/HTMLPurifier/HTMLPurifier/PropertyList.php new file mode 100644 index 0000000..189348f --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/PropertyList.php @@ -0,0 +1,122 @@ +parent = $parent; + } + + /** + * Recursively retrieves the value for a key + * @param string $name + * @throws HTMLPurifier_Exception + */ + public function get($name) + { + if ($this->has($name)) { + return $this->data[$name]; + } + // possible performance bottleneck, convert to iterative if necessary + if ($this->parent) { + return $this->parent->get($name); + } + throw new HTMLPurifier_Exception("Key '$name' not found"); + } + + /** + * Sets the value of a key, for this plist + * @param string $name + * @param mixed $value + */ + public function set($name, $value) + { + $this->data[$name] = $value; + } + + /** + * Returns true if a given key exists + * @param string $name + * @return bool + */ + public function has($name) + { + return array_key_exists($name, $this->data); + } + + /** + * Resets a value to the value of it's parent, usually the default. If + * no value is specified, the entire plist is reset. + * @param string $name + */ + public function reset($name = null) + { + if ($name == null) { + $this->data = array(); + } else { + unset($this->data[$name]); + } + } + + /** + * Squashes this property list and all of its property lists into a single + * array, and returns the array. This value is cached by default. + * @param bool $force If true, ignores the cache and regenerates the array. + * @return array + */ + public function squash($force = false) + { + if ($this->cache !== null && !$force) { + return $this->cache; + } + if ($this->parent) { + return $this->cache = array_merge($this->parent->squash($force), $this->data); + } else { + return $this->cache = $this->data; + } + } + + /** + * Returns the parent plist. + * @return HTMLPurifier_PropertyList + */ + public function getParent() + { + return $this->parent; + } + + /** + * Sets the parent plist. + * @param HTMLPurifier_PropertyList $plist Parent plist + */ + public function setParent($plist) + { + $this->parent = $plist; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/PropertyListIterator.php b/software/HTMLPurifier/HTMLPurifier/PropertyListIterator.php new file mode 100644 index 0000000..f68fc8c --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/PropertyListIterator.php @@ -0,0 +1,43 @@ +l = strlen($filter); + $this->filter = $filter; + } + + /** + * @return bool + */ + #[\ReturnTypeWillChange] + public function accept() + { + $key = $this->getInnerIterator()->key(); + if (strncmp($key, $this->filter, $this->l) !== 0) { + return false; + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Queue.php b/software/HTMLPurifier/HTMLPurifier/Queue.php new file mode 100644 index 0000000..f58db90 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Queue.php @@ -0,0 +1,56 @@ +input = $input; + $this->output = array(); + } + + /** + * Shifts an element off the front of the queue. + */ + public function shift() { + if (empty($this->output)) { + $this->output = array_reverse($this->input); + $this->input = array(); + } + if (empty($this->output)) { + return NULL; + } + return array_pop($this->output); + } + + /** + * Pushes an element onto the front of the queue. + */ + public function push($x) { + array_push($this->input, $x); + } + + /** + * Checks if it's empty. + */ + public function isEmpty() { + return empty($this->input) && empty($this->output); + } +} diff --git a/software/HTMLPurifier/HTMLPurifier/Strategy.php b/software/HTMLPurifier/HTMLPurifier/Strategy.php new file mode 100644 index 0000000..e1ff3b7 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Strategy.php @@ -0,0 +1,26 @@ +strategies as $strategy) { + $tokens = $strategy->execute($tokens, $config, $context); + } + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Strategy/Core.php b/software/HTMLPurifier/HTMLPurifier/Strategy/Core.php new file mode 100644 index 0000000..4414c17 --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Strategy/Core.php @@ -0,0 +1,17 @@ +strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements(); + $this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed(); + $this->strategies[] = new HTMLPurifier_Strategy_FixNesting(); + $this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes(); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php b/software/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php new file mode 100644 index 0000000..6fa673d --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php @@ -0,0 +1,181 @@ +getHTMLDefinition(); + + $excludes_enabled = !$config->get('Core.DisableExcludes'); + + // setup the context variable 'IsInline', for chameleon processing + // is 'false' when we are not inline, 'true' when it must always + // be inline, and an integer when it is inline for a certain + // branch of the document tree + $is_inline = $definition->info_parent_def->descendants_are_inline; + $context->register('IsInline', $is_inline); + + // setup error collector + $e =& $context->get('ErrorCollector', true); + + //####################################################################// + // Loop initialization + + // stack that contains all elements that are excluded + // it is organized by parent elements, similar to $stack, + // but it is only populated when an element with exclusions is + // processed, i.e. there won't be empty exclusions. + $exclude_stack = array($definition->info_parent_def->excludes); + + // variable that contains the start token while we are processing + // nodes. This enables error reporting to do its job + $node = $top_node; + // dummy token + list($token, $d) = $node->toTokenPair(); + $context->register('CurrentNode', $node); + $context->register('CurrentToken', $token); + + //####################################################################// + // Loop + + // We need to implement a post-order traversal iteratively, to + // avoid running into stack space limits. This is pretty tricky + // to reason about, so we just manually stack-ify the recursive + // variant: + // + // function f($node) { + // foreach ($node->children as $child) { + // f($child); + // } + // validate($node); + // } + // + // Thus, we will represent a stack frame as array($node, + // $is_inline, stack of children) + // e.g. array_reverse($node->children) - already processed + // children. + + $parent_def = $definition->info_parent_def; + $stack = array( + array($top_node, + $parent_def->descendants_are_inline, + $parent_def->excludes, // exclusions + 0) + ); + + while (!empty($stack)) { + list($node, $is_inline, $excludes, $ix) = array_pop($stack); + // recursive call + $go = false; + $def = empty($stack) ? $definition->info_parent_def : $definition->info[$node->name]; + while (isset($node->children[$ix])) { + $child = $node->children[$ix++]; + if ($child instanceof HTMLPurifier_Node_Element) { + $go = true; + $stack[] = array($node, $is_inline, $excludes, $ix); + $stack[] = array($child, + // ToDo: I don't think it matters if it's def or + // child_def, but double check this... + $is_inline || $def->descendants_are_inline, + empty($def->excludes) ? $excludes + : array_merge($excludes, $def->excludes), + 0); + break; + } + }; + if ($go) continue; + list($token, $d) = $node->toTokenPair(); + // base case + if ($excludes_enabled && isset($excludes[$node->name])) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded'); + } else { + // XXX I suppose it would be slightly more efficient to + // avoid the allocation here and have children + // strategies handle it + $children = array(); + foreach ($node->children as $child) { + if (!$child->dead) $children[] = $child; + } + $result = $def->child->validateChildren($children, $config, $context); + if ($result === true) { + // nop + $node->children = $children; + } elseif ($result === false) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node removed'); + } else { + $node->children = $result; + if ($e) { + // XXX This will miss mutations of internal nodes. Perhaps defer to the child validators + if (empty($result) && !empty($children)) { + $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed'); + } else if ($result != $children) { + $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized'); + } + } + } + } + } + + //####################################################################// + // Post-processing + + // remove context variables + $context->destroy('IsInline'); + $context->destroy('CurrentNode'); + $context->destroy('CurrentToken'); + + //####################################################################// + // Return + + return HTMLPurifier_Arborize::flatten($node, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/software/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php b/software/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php new file mode 100644 index 0000000..a6eb09e --- /dev/null +++ b/software/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php @@ -0,0 +1,659 @@ +getHTMLDefinition(); + + // local variables + $generator = new HTMLPurifier_Generator($config, $context); + $escape_invalid_tags = $config->get('Core.EscapeInvalidTags'); + // used for autoclose early abortion + $global_parent_allowed_elements = $definition->info_parent_def->child->getAllowedElements($config); + $e = $context->get('ErrorCollector', true); + $i = false; // injector index + list($zipper, $token) = HTMLPurifier_Zipper::fromArray($tokens); + if ($token === NULL) { + return array(); + } + $reprocess = false; // whether or not to reprocess the same token + $stack = array(); + + // member variables + $this->stack =& $stack; + $this->tokens =& $tokens; + $this->token =& $token; + $this->zipper =& $zipper; + $this->config = $config; + $this->context = $context; + + // context variables + $context->register('CurrentNesting', $stack); + $context->register('InputZipper', $zipper); + $context->register('CurrentToken', $token); + + // -- begin INJECTOR -- + + $this->injectors = array(); + + $injectors = $config->getBatch('AutoFormat'); + $def_injectors = $definition->info_injector; + $custom_injectors = $injectors['Custom']; + unset($injectors['Custom']); // special case + foreach ($injectors as $injector => $b) { + // XXX: Fix with a legitimate lookup table of enabled filters + if (strpos($injector, '.') !== false) { + continue; + } + $injector = "HTMLPurifier_Injector_$injector"; + if (!$b) { + continue; + } + $this->injectors[] = new $injector; + } + foreach ($def_injectors as $injector) { + // assumed to be objects + $this->injectors[] = $injector; + } + foreach ($custom_injectors as $injector) { + if (!$injector) { + continue; + } + if (is_string($injector)) { + $injector = "HTMLPurifier_Injector_$injector"; + $injector = new $injector; + } + $this->injectors[] = $injector; + } + + // give the injectors references to the definition and context + // variables for performance reasons + foreach ($this->injectors as $ix => $injector) { + $error = $injector->prepare($config, $context); + if (!$error) { + continue; + } + array_splice($this->injectors, $ix, 1); // rm the injector + trigger_error("Cannot enable {$injector->name} injector because $error is not allowed", E_USER_WARNING); + } + + // -- end INJECTOR -- + + // a note on reprocessing: + // In order to reduce code duplication, whenever some code needs + // to make HTML changes in order to make things "correct", the + // new HTML gets sent through the purifier, regardless of its + // status. This means that if we add a start token, because it + // was totally necessary, we don't have to update nesting; we just + // punt ($reprocess = true; continue;) and it does that for us. + + // isset is in loop because $tokens size changes during loop exec + for (;; + // only increment if we don't need to reprocess + $reprocess ? $reprocess = false : $token = $zipper->next($token)) { + + // check for a rewind + if (is_int($i)) { + // possibility: disable rewinding if the current token has a + // rewind set on it already. This would offer protection from + // infinite loop, but might hinder some advanced rewinding. + $rewind_offset = $this->injectors[$i]->getRewindOffset(); + if (is_int($rewind_offset)) { + for ($j = 0; $j < $rewind_offset; $j++) { + if (empty($zipper->front)) break; + $token = $zipper->prev($token); + // indicate that other injectors should not process this token, + // but we need to reprocess it. See Note [Injector skips] + unset($token->skip[$i]); + $token->rewind = $i; + if ($token instanceof HTMLPurifier_Token_Start) { + array_pop($this->stack); + } elseif ($token instanceof HTMLPurifier_Token_End) { + $this->stack[] = $token->start; + } + } + } + $i = false; + } + + // handle case of document end + if ($token === NULL) { + // kill processing if stack is empty + if (empty($this->stack)) { + break; + } + + // peek + $top_nesting = array_pop($this->stack); + $this->stack[] = $top_nesting; + + // send error [TagClosedSuppress] + if ($e && !isset($top_nesting->armor['MakeWellFormed_TagClosedError'])) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $top_nesting); + } + + // append, don't splice, since this is the end + $token = new HTMLPurifier_Token_End($top_nesting->name); + + // punt! + $reprocess = true; + continue; + } + + //echo '
'; printZipper($zipper, $token);//printTokens($this->stack); + //flush(); + + // quick-check: if it's not a tag, no need to process + if (empty($token->is_tag)) { + if ($token instanceof HTMLPurifier_Token_Text) { + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + // See Note [Injector skips] + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + // XXX fuckup + $r = $token; + $injector->handleText($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + } + // another possibility is a comment + continue; + } + + if (isset($definition->info[$token->name])) { + $type = $definition->info[$token->name]->child->type; + } else { + $type = false; // Type is unknown, treat accordingly + } + + // quick tag checks: anything that's *not* an end tag + $ok = false; + if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) { + // claims to be a start tag but is empty + $token = new HTMLPurifier_Token_Empty( + $token->name, + $token->attr, + $token->line, + $token->col, + $token->armor + ); + $ok = true; + } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) { + // claims to be empty but really is a start tag + // NB: this assignment is required + $old_token = $token; + $token = new HTMLPurifier_Token_End($token->name); + $token = $this->insertBefore( + new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor) + ); + // punt (since we had to modify the input stream in a non-trivial way) + $reprocess = true; + continue; + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + // real empty token + $ok = true; + } elseif ($token instanceof HTMLPurifier_Token_Start) { + // start tag + + // ...unless they also have to close their parent + if (!empty($this->stack)) { + + // Performance note: you might think that it's rather + // inefficient, recalculating the autoclose information + // for every tag that a token closes (since when we + // do an autoclose, we push a new token into the + // stream and then /process/ that, before + // re-processing this token.) But this is + // necessary, because an injector can make an + // arbitrary transformations to the autoclosing + // tokens we introduce, so things may have changed + // in the meantime. Also, doing the inefficient thing is + // "easy" to reason about (for certain perverse definitions + // of "easy") + + $parent = array_pop($this->stack); + $this->stack[] = $parent; + + $parent_def = null; + $parent_elements = null; + $autoclose = false; + if (isset($definition->info[$parent->name])) { + $parent_def = $definition->info[$parent->name]; + $parent_elements = $parent_def->child->getAllowedElements($config); + $autoclose = !isset($parent_elements[$token->name]); + } + + if ($autoclose && $definition->info[$token->name]->wrap) { + // Check if an element can be wrapped by another + // element to make it valid in a context (for + // example,