function postDoReplaceText($s, $parentTag, $parentMask) { global $postNoSmilies, $postPoster, $smiliesReplaceOrig, $smiliesReplaceNew; if ($postPoster) { $s = preg_replace("'/me '", "<b>* " . htmlspecialchars($postPoster) . "</b> ", $s); } // silly filters //$s = preg_replace_callback('@\._+\.@', 'funhax', $s); //$s = str_replace(':3', ':3 '.rainbowify('ALL THE INSULTS I JUST SAID NOW BECOME LITTLE COLOURFUL FLOWERS'), $s); //Smilies if (!$postNoSmilies) { if (!isset($smiliesReplaceOrig)) { LoadSmilies(); } $s = preg_replace($smiliesReplaceOrig, $smiliesReplaceNew, $s); } //Automatic links // does it really have to be that complex?! we're not phpBB //$s = preg_replace_callback('((?:(?:view-source:)?(?:[Hh]t|[Ff])tps?://(?:(?:[^:&@/]*:[^:@/]*)@)?|\bwww\.)[a-zA-Z0-9\-]+(?:\.[a-zA-Z0-9\-]+)*(?::[0-9]+)?(?:/(?:->(?=\S)|&|[\w\-/%?=+#~:\'@*^$!]|[.,;\'|](?=\S)|(?:(\()|(\[)|\{)(?:->(?=\S)|[\w\-/%&?=+;#~:\'@*^$!.,;]|(?:(\()|(\[)|\{)(?:->(?=\S)|l[\w\-/%&?=+;#~:\'@*^$!.,;])*(?(3)\)|(?(4)\]|\})))*(?(1)\)|(?(2)\]|\})))*)?)', 'bbcodeURLAuto', $s); if (!($parentMask & TAG_NOAUTOLINK)) { $s = preg_replace_callback('@(?:(?:http|ftp)s?://|\\bwww\\.)[\\w\\-/%&?=+#~\'\\@*^$\\.,;!:]+[\\w\\-/%&?=+#~\'\\@*^$]@i', 'bbcodeURLAuto', $s); } //Plugin bucket for allowing plugins to add replacements. $bucket = "postMangler"; include __DIR__ . "/pluginloader.php"; return $s; }
function ShowSmilesInComments() { global $CommentsData; if (!empty($CommentsData)) { for ($i = 0; $i < count($CommentsData); $i++) { //replace comment text with Smilies function $CommentsData[$i]["text"] = LoadSmilies($CommentsData[$i]["text"]); } return array($CommentsData); } }
/** * Performs the actual parsing of the document. */ public function parse() { global $user; // Current state $state = 'data'; // This is used to avoid having to have look-behind in the data state. $lastFourChars = ''; /** * Escape flag as specified by the HTML5 specification: "used to * control the behavior of the tokeniser. It is either true or * false, and initially must be set to the false state." */ $escape = false; //echo "\n\n"; while ($state !== null) { /*echo $state . ' '; switch ($this->content_model) { case self::PCDATA: echo 'PCDATA'; break; case self::RCDATA: echo 'RCDATA'; break; case self::CDATA: echo 'CDATA'; break; case self::PLAINTEXT: echo 'PLAINTEXT'; break; } if ($escape) echo " escape"; echo "\n";*/ switch ($state) { case 'data': /* Consume the next input character */ $char = $this->stream->char(); $lastFourChars .= $char; if (strlen($lastFourChars) > 4) { $lastFourChars = substr($lastFourChars, -4); } $tag_begin_position = $this->stream->char; // see below for meaning $hyp_cond = !$escape && ($this->content_model === self::RCDATA || $this->content_model === self::CDATA); $amp_cond = !$escape && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA); $lt_cond = $this->content_model === self::PCDATA || ($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && !$escape; $gt_cond = $escape && ($this->content_model === self::RCDATA || $this->content_model === self::CDATA); if ($char === '&' && $amp_cond) { /* U+0026 AMPERSAND (&) When the content model flag is set to one of the PCDATA or RCDATA states and the escape flag is false: switch to the character reference data state. Otherwise: treat it as per the "anything else" entry below. */ $state = 'character reference data'; } elseif ($char === '-' && $hyp_cond && $lastFourChars === '<!--') { /* U+002D HYPHEN-MINUS (-) 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 ("<!--"), then set the escape flag to true. */ $escape = true; /* In any case, emit the input character as a character token. Stay in the data state. */ $this->emitToken(array('type' => self::CHARACTER, 'data' => '-')); // We do the "any case" part as part of "anything else". /* U+003C LESS-THAN SIGN (<) */ } elseif ($char === '<' && $lt_cond) { /* When the content model flag is set to the PCDATA state: switch to the tag open state. When the content model flag is set to either the RCDATA state or the CDATA state and the escape flag is false: switch to the tag open state. Otherwise: treat it as per the "anything else" entry below. */ $state = 'tag open'; } elseif ($char === '[' && $this->content_model === self::PCDATA) { $state = 'bbcode tag open'; /* U+003E GREATER-THAN SIGN (>) */ } elseif ($char === '>' && $gt_cond && substr($lastFourChars, 1) === '-->') { /* If the content model flag is set to either the RCDATA state or the CDATA state, and the escape flag is true, and the last three characters in the input stream including this one are U+002D HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"), set the escape flag to false. */ $escape = false; /* In any case, emit the input character as a character token. Stay in the data state. */ $this->emitToken(array('type' => self::CHARACTER, 'data' => '>')); // We do the "any case" part as part of "anything else". } elseif ($char === false) { /* EOF Emit an end-of-file token. */ $state = null; $this->tree->emitToken(array('type' => self::EOF)); } elseif ($char === "/") { if ($this->stream->chars(3) === "me ") { $this->stream->char += 2; $this->tree->emitToken(array('type' => self::STARTTAG, 'name' => 'b')); $this->tree->emitToken(array('type' => self::CHARACTER, 'data' => "* {$this->userName}")); $this->tree->emitToken(array('type' => self::ENDTAG, 'name' => 'b')); } else { $this->tree->emitToken(array('type' => self::CHARACTER, 'data' => '/')); } } elseif ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { if ($char === "\n" || $char === "\f") { $this->emitNewLine(); } $this->stream->charsWhile(" \t"); // Directly after emitting a token you switch back to the "data // state". At that point spaceCharacters are important so they are // emitted separately. $this->emitToken(array('type' => self::SPACECHARACTER, 'data' => $char)); } else { global $postNoSmilies, $smiliesReplaceOrig, $smiliesReplaceNew; $result = ""; if ($this->content_model === self::PCDATA) { $endChars = "<&[\n\f"; } else { $endChars = "<\n\f"; } while (strpos($endChars, $char) === FALSE && $char !== FALSE) { $result .= $char; if ($this->content_model === self::PCDATA && !$postNoSmilies) { if (!isset($smiliesReplaceOrig)) { LoadSmilies(); } if (isset($smiliesReplaceOrig[$char])) { foreach ($smiliesReplaceOrig[$char] as $i => $regexp) { if (preg_match($regexp, $this->stream->data, $matches, 0, $this->stream->char - 1)) { $this->stream->char += strlen($matches[0]) - 1; $this->emitToken(array('type' => self::CHARACTER, 'data' => substr($result, 0, -1))); $this->emitToken(array('type' => self::STARTTAG, 'name' => 'img', 'attr' => array(array('name' => 'class', 'value' => 'smiley'), array('name' => 'src', 'value' => $smiliesReplaceNew[$char][$i])))); break 3; } } } } // Link RegExp $nonsense = '(\\G(?:(?:view-source:)?(?:[Hh]t|[Ff])tps?://(?:(?:[^:&@/]*:[^:@/]*)@)?|\\bwww\\.)[a-zA-Z0-9\\-]+(?:\\.[a-zA-Z0-9\\-]+)*(?::[0-9]+)?(?:/(?:->(?=\\S)|&|[\\w\\-/%?=+#~:\'@*^$!]|[.,;\'|](?=\\S)|(?:(\\()|(\\{))(?:->(?=\\S)|[\\w\\-/%&?=+;#~:\'@*^$!.,;]|(?:(\\()|(\\{))(?:->(?=\\S)|[\\w\\-/%&?=+;#~:\'@*^$!.,;])*(?(3)\\)|\\}))*(?(1)\\)|\\}))*)?)s'; if ($this->content_model === self::PCDATA && preg_match($nonsense, $this->stream->data, $matches, 0, $this->stream->char - 1)) { $this->stream->char += strlen($matches[0]) - 1; $this->emitToken(array('type' => self::CHARACTER, 'data' => substr($result, 0, -1))); $this->emitToken(array('type' => self::URL, 'data' => $matches[0])); break 2; } $char = $this->stream->char(); } $this->stream->unget(); $this->emitToken(array('type' => self::CHARACTER, 'data' => $result)); $lastFourChars .= $chars; if (strlen($lastFourChars) > 4) { $lastFourChars = substr($lastFourChars, -4); } $state = 'data'; } break; case 'character reference data': /* (This cannot happen if the content model flag is set to the CDATA state.) */ /* Attempt to consume a character reference, with no additional allowed character. */ $entity = $this->consumeCharacterReference(); /* If nothing is returned, emit a U+0026 AMPERSAND character token. Otherwise, emit the character token that was returned. */ // This is all done when consuming the character reference. $this->emitToken(array('type' => self::CHARACTER, 'data' => $entity)); /* Finally, switch to the data state. */ $state = 'data'; break; case 'tag open': $char = $this->stream->char(); switch ($this->content_model) { case self::RCDATA: case self::CDATA: /* Consume the next input character. If it is a U+002F SOLIDUS (/) character, switch to the close tag open state. Otherwise, emit a U+003C LESS-THAN SIGN character token and reconsume the current input character in the data state. */ // We consumed above. if ($char === '/') { $state = 'close tag open'; } else { $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $this->stream->unget(); $state = 'data'; } break; case self::PCDATA: /* If the content model flag is set to the PCDATA state Consume the next input character: */ // We consumed above. if ($char === '!') { /* U+0021 EXCLAMATION MARK (!) Switch to the markup declaration open state. */ $state = 'markup declaration open'; } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the close tag open state. */ $state = 'close tag open'; } elseif ('A' <= $char && $char <= 'Z') { /* 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()); $state = 'tag name'; } elseif ('a' <= $char && $char <= 'z') { /* U+0061 LATIN SMALL LETTER A through to U+007A LATIN SMALL LETTER Z Create a new start tag token, set its tag name to the input character, 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' => $char, 'type' => self::STARTTAG, 'attr' => array()); $state = 'tag name'; } elseif ($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::PARSEERROR, 'data' => 'expected-tag-name-but-got-right-bracket')); $this->emitToken(array('type' => self::CHARACTER, 'data' => '<>')); $state = 'data'; } elseif ($char === '?') { /* U+003F QUESTION MARK (?) Parse error. Switch to the bogus comment state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-tag-name-but-got-question-mark')); $this->token = array('data' => '?', 'type' => self::COMMENT); $state = 'bogus comment'; } 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::PARSEERROR, 'data' => 'expected-tag-name')); $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $state = 'data'; $this->stream->unget(); } break; } break; case 'close tag open': if ($this->content_model === self::RCDATA || $this->content_model === self::CDATA) { /* If the content model flag is set to the RCDATA or CDATA states... */ $name = strtolower($this->stream->charsWhile(self::ALPHA)); $following = $this->stream->char(); $this->stream->unget(); if (!$this->token || $this->token['name'] !== $name || $this->token['name'] === $name && !in_array($following, array("\t", "\n", "\f", " ", ">", "/", false))) { /* if no start tag token has ever been emitted by this instance of the tokenizer (fragment case), or, if the next few characters do not match the tag name of the last start tag token emitted (compared in an ASCII case-insensitive manner), 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+000C FORM FEED (FF) * U+0020 SPACE * U+003E GREATER-THAN SIGN (>) * U+002F SOLIDUS (/) * EOF ...then 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. */ // XXX: Probably ought to replace in_array with $following === x ||... // We also need to emit $name now we've consumed that, as we // know it'll just be emitted as a character token. $this->emitToken(array('type' => self::CHARACTER, 'data' => '</' . $name)); $state = 'data'; } else { // This matches what would happen if we actually did the // otherwise below (but we can't because we've consumed too // much). // Start the end tag token with the name we already have. $this->token = array('name' => $name, 'type' => self::ENDTAG); // Change to tag name state. $state = 'tag name'; } } elseif ($this->content_model === self::PCDATA) { /* Otherwise, if the content model flag is set to the PCDATA state [...]: */ $char = $this->stream->char(); if ('A' <= $char && $char <= 'Z') { /* 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); $state = 'tag name'; } elseif ('a' <= $char && $char <= 'z') { /* U+0061 LATIN SMALL LETTER A through to U+007A LATIN SMALL LETTER Z Create a new end tag token, set its tag name to the input character, 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' => $char, 'type' => self::ENDTAG); $state = 'tag name'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-closing-tag-but-got-right-bracket')); $state = 'data'; } elseif ($char === false) { /* 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::PARSEERROR, 'data' => 'expected-closing-tag-but-got-eof')); $this->emitToken(array('type' => self::CHARACTER, 'data' => '</')); $this->stream->unget(); $state = 'data'; } else { /* Parse error. Switch to the bogus comment state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-closing-tag-but-got-char')); $this->token = array('data' => $char, 'type' => self::COMMENT); $state = 'bogus comment'; } } break; case 'tag name': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { if (!isset($this->allowed_tags[$this->token['name']])) { $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $this->stream->char = $tag_begin_position; $state = 'data'; break; } /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the before attribute name state. */ $state = 'before attribute name'; } elseif ($char === '/') { if (!isset($this->allowed_tags[$this->token['name']])) { $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $this->stream->char = $tag_begin_position; $state = 'data'; break; } /* U+002F SOLIDUS (/) Switch to the self-closing start tag state. */ $state = 'self-closing start tag'; } elseif ($char === '>') { if (!isset($this->allowed_tags[$this->token['name']])) { $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $this->stream->char = $tag_begin_position; $state = 'data'; break; } /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Append the lowercase version of the current input character (add 0x0020 to the character's code point) to the current tag token's tag name. Stay in the tag name state. */ $chars = $this->stream->charsWhile(self::UPPER_ALPHA); $this->token['name'] .= strtolower($char . $chars); $state = 'tag name'; } elseif ($char === false) { if (!isset($this->allowed_tags[$this->token['name']])) { $this->emitToken(array('type' => self::CHARACTER, 'data' => '<')); $this->stream->char = $tag_begin_position; $state = 'data'; break; } /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-tag-name')); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current tag token's tag name. Stay in the tag name state. */ $chars = $this->stream->charsUntil("\t\n\f />" . self::UPPER_ALPHA); $this->token['name'] .= $char . $chars; $state = 'tag name'; } break; case 'before attribute name': /* Consume the next input character: */ $char = $this->stream->char(); // this conditional is optimized, check bottom if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the before attribute name state. */ $state = 'before attribute name'; } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the self-closing start tag state. */ $state = 'self-closing start tag'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Start a new attribute in the current tag token. Set that attribute's name to the lowercase version of the current input character (add 0x0020 to the character's code point), and its value to the empty string. Switch to the attribute name state.*/ $this->token['attr'][] = array('name' => strtolower($char), 'value' => ''); $state = 'attribute name'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-attribute-name-but-got-eof')); $this->stream->unget(); $state = 'data'; } else { /* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE (') U+003C LESS-THAN SIGN (<) U+003D EQUALS SIGN (=) Parse error. Treat it as per the "anything else" entry below. */ if ($char === '"' || $char === "'" || $char === '<' || $char === '=') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'invalid-character-in-attribute-name')); } /* 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' => $char, 'value' => ''); $state = 'attribute name'; } break; case 'attribute name': // Consume the next input character: $char = $this->stream->char(); // this conditional is optimized, check bottom if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the after attribute name state. */ $state = 'after attribute name'; } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the self-closing start tag state. */ $state = 'self-closing start tag'; } elseif ($char === '=') { /* U+003D EQUALS SIGN (=) Switch to the before attribute value state. */ $state = 'before attribute value'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Append the lowercase version of the current input character (add 0x0020 to the character's code point) to the current attribute's name. Stay in the attribute name state. */ $chars = $this->stream->charsWhile(self::UPPER_ALPHA); $last = count($this->token['attr']) - 1; $this->token['attr'][$last]['name'] .= strtolower($char . $chars); $state = 'attribute name'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-attribute-name')); $this->stream->unget(); $state = 'data'; } else { /* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE (') U+003C LESS-THAN SIGN (<) Parse error. Treat it as per the "anything else" entry below. */ if ($char === '"' || $char === "'" || $char === '<') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'invalid-character-in-attribute-name')); } /* Anything else Append the current input character to the current attribute's name. Stay in the attribute name state. */ $chars = $this->stream->charsUntil("\t\n\f /=>\"'" . self::UPPER_ALPHA); $last = count($this->token['attr']) - 1; $this->token['attr'][$last]['name'] .= $char . $chars; $state = 'attribute name'; } /* When the user agent leaves the attribute name state (and before emitting the tag token, if appropriate), the complete attribute's name must be compared to the other attributes on the same token; if there is already an attribute on the token with the exact same name, then this is a parse error and the new attribute must be dropped, along with the value that gets associated with it (if any). */ // this might be implemented in the emitToken method break; case 'after attribute name': // Consume the next input character: $char = $this->stream->char(); // this is an optimized conditional, check the bottom if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the after attribute name state. */ $state = 'after attribute name'; } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the self-closing start tag state. */ $state = 'self-closing start tag'; } elseif ($char === '=') { /* U+003D EQUALS SIGN (=) Switch to the before attribute value state. */ $state = 'before attribute value'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Start a new attribute in the current tag token. Set that attribute's name to the lowercase version of the current input character (add 0x0020 to the character's code point), and its value to the empty string. Switch to the attribute name state. */ $this->token['attr'][] = array('name' => strtolower($char), 'value' => ''); $state = 'attribute name'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-end-of-tag-but-got-eof')); $this->stream->unget(); $state = 'data'; } else { /* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE (') U+003C LESS-THAN SIGN(<) Parse error. Treat it as per the "anything else" entry below. */ if ($char === '"' || $char === "'" || $char === "<") { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'invalid-character-after-attribute-name')); } /* 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' => $char, 'value' => ''); $state = 'attribute name'; } break; case 'before attribute value': // Consume the next input character: $char = $this->stream->char(); // this is an optimized conditional if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the before attribute value state. */ $state = 'before attribute value'; } elseif ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the attribute value (double-quoted) state. */ $state = 'attribute value (double-quoted)'; } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the attribute value (unquoted) state and reconsume this input character. */ $this->stream->unget(); $state = 'attribute value (unquoted)'; } elseif ($char === '\'') { /* U+0027 APOSTROPHE (') Switch to the attribute value (single-quoted) state. */ $state = 'attribute value (single-quoted)'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Emit the current tag token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-attribute-value-but-got-right-bracket')); $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-attribute-value-but-got-eof')); $this->stream->unget(); $state = 'data'; } else { /* U+003D EQUALS SIGN (=) * U+003C LESS-THAN SIGN (<) Parse error. Treat it as per the "anything else" entry below. */ if ($char === '=' || $char === '<') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'equals-in-unquoted-attribute-value')); } /* 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; $state = 'attribute value (unquoted)'; } break; case 'attribute value (double-quoted)': // Consume the next input character: $char = $this->stream->char(); if ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the after attribute value (quoted) state. */ $state = 'after attribute value (quoted)'; } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the character reference in attribute value state, with the additional allowed character being U+0022 QUOTATION MARK ("). */ $this->characterReferenceInAttributeValue('"'); } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-attribute-value-double-quote')); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current attribute's value. Stay in the attribute value (double-quoted) state. */ $chars = $this->stream->charsUntil('"&'); $last = count($this->token['attr']) - 1; $this->token['attr'][$last]['value'] .= $char . $chars; $state = 'attribute value (double-quoted)'; } break; case 'attribute value (single-quoted)': // Consume the next input character: $char = $this->stream->char(); if ($char === "'") { /* U+0022 QUOTATION MARK (') Switch to the after attribute value state. */ $state = 'after attribute value (quoted)'; } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the entity in attribute value state. */ $this->characterReferenceInAttributeValue("'"); } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-attribute-value-single-quote')); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current attribute's value. Stay in the attribute value (single-quoted) state. */ $chars = $this->stream->charsUntil("'&"); $last = count($this->token['attr']) - 1; $this->token['attr'][$last]['value'] .= $char . $chars; $state = 'attribute value (single-quoted)'; } break; case 'attribute value (unquoted)': // Consume the next input character: $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the before attribute name state. */ $state = 'before attribute name'; } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the entity in attribute value state, with the additional allowed character being U+003E GREATER-THAN SIGN (>). */ $this->characterReferenceInAttributeValue('>'); } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-attribute-value-no-quotes')); $this->stream->unget(); $state = 'data'; } else { /* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE (') U+003C LESS-THAN SIGN (<) U+003D EQUALS SIGN (=) Parse error. Treat it as per the "anything else" entry below. */ if ($char === '"' || $char === "'" || $char === '=' || $char == '<') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-character-in-unquoted-attribute-value')); } /* Anything else Append the current input character to the current attribute's value. Stay in the attribute value (unquoted) state. */ $chars = $this->stream->charsUntil("\t\n\f &>\"'="); $last = count($this->token['attr']) - 1; $this->token['attr'][$last]['value'] .= $char . $chars; $state = 'attribute value (unquoted)'; } break; case 'after attribute value (quoted)': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the before attribute name state. */ $state = 'before attribute name'; } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the self-closing start tag state. */ $state = 'self-closing start tag'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-EOF-after-attribute-value')); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Reconsume the character in the before attribute name state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-character-after-attribute-value')); $this->stream->unget(); $state = 'before attribute name'; } break; case 'self-closing start tag': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Set the self-closing flag of the current tag token. Emit the current tag token. Switch to the data state. */ // not sure if this is the name we want $this->token['self-closing'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-eof-after-self-closing')); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Reconsume the character in the before attribute name state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-character-after-self-closing')); $this->stream->unget(); $state = 'before attribute name'; } break; case 'bogus comment': /* (This can only happen if the content model flag is set to the PCDATA state.) */ /* 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.) */ $this->token['data'] .= (string) $this->stream->charsUntil('>'); $this->stream->char(); $this->emitToken($this->token); /* Switch to the data state. */ $state = 'data'; break; case 'markup declaration open': // Consume for below $hyphens = $this->stream->charsWhile('-', 2); if ($hyphens === '-') { $this->stream->unget(); } if ($hyphens !== '--') { $alpha = $this->stream->charsWhile(self::ALPHA, 7); } /* If the next two characters are both U+002D HYPHEN-MINUS (-) characters, consume those two characters, create a comment token whose data is the empty string, and switch to the comment state. */ if ($hyphens === '--') { $state = 'comment start'; $this->token = array('data' => '', 'type' => self::COMMENT); /* Otherwise if the next seven characters are a case-insensitive match for the word "DOCTYPE", then consume those characters and switch to the DOCTYPE state. */ } elseif (strtoupper($alpha) === 'DOCTYPE') { $state = 'DOCTYPE'; // XXX not implemented /* Otherwise, if the insertion mode is "in foreign content" and the current node is not an element in the HTML namespace and the next seven characters are an ASCII case-sensitive match for the string "[CDATA[" (the five uppercase letters "CDATA" with a U+005B LEFT SQUARE BRACKET character before and after), then consume those characters and switch to the CDATA section state (which is unrelated to the content model flag's CDATA state). */ /* 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->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-dashes-or-doctype')); $this->token = array('data' => (string) $alpha, 'type' => self::COMMENT); $state = 'bogus comment'; } break; case 'comment start': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '-') { /* U+002D HYPHEN-MINUS (-) Switch to the comment start dash state. */ $state = 'comment start dash'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Emit the comment token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'incorrect-comment')); $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Emit the comment token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the input character to the comment token's data. Switch to the comment state. */ $this->token['data'] .= $char; $state = 'comment'; } break; case 'comment start dash': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '-') { /* U+002D HYPHEN-MINUS (-) Switch to the comment end state */ $state = 'comment end'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Emit the comment token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'incorrect-comment')); $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* Parse error. Emit the comment token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { $this->token['data'] .= '-' . $char; $state = 'comment'; } break; case 'comment': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '-') { /* U+002D HYPHEN-MINUS (-) Switch to the comment end dash state */ $state = 'comment end dash'; } elseif ($char === false) { /* EOF Parse error. Emit the comment token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the input character to the comment token's data. Stay in the comment state. */ $chars = $this->stream->charsUntil('-'); $this->token['data'] .= $char . $chars; } break; case 'comment end dash': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '-') { /* U+002D HYPHEN-MINUS (-) Switch to the comment end state */ $state = 'comment end'; } elseif ($char === false) { /* EOF Parse error. Emit the comment token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment-end-dash')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything 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; $state = 'comment'; } break; case 'comment end': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the comment token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === '-') { /* U+002D HYPHEN-MINUS (-) Parse error. Append a U+002D HYPHEN-MINUS (-) character to the comment token's data. Stay in the comment end state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-dash-after-double-dash-in-comment')); $this->token['data'] .= '-'; } elseif ($char === "\t" || $char === "\n" || $char === "\n" || $char === ' ') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-space-after-double-dash-in-comment')); $this->token['data'] .= '--' . $char; $state = 'comment end space'; } elseif ($char === '!') { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-bang-after-double-dash-in-comment')); $state = 'comment end bang'; } elseif ($char === false) { /* EOF Parse error. Emit the comment token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment-double-dash')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Append two U+002D HYPHEN-MINUS (-) characters and the input character to the comment token's data. Switch to the comment state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-comment')); $this->token['data'] .= '--' . $char; $state = 'comment'; } break; case 'comment end bang': $char = $this->stream->char(); if ($char === '>') { $this->emitToken($this->token); $state = 'data'; } elseif ($char === "-") { $this->token['data'] .= '--!'; $state = 'comment end dash'; } elseif ($char === false) { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-comment-end-bang')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { $this->token['data'] .= '--!' . $char; $state = 'comment'; } break; case 'comment end space': $char = $this->stream->char(); if ($char === '>') { $this->emitToken($this->token); $state = 'data'; } elseif ($char === '-') { $state = 'comment end dash'; } elseif ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { $this->token['data'] .= $char; } elseif ($char === false) { $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-eof-in-comment-end-space')); $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { $this->token['data'] .= $char; $state = 'comment'; } break; case 'DOCTYPE': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the before DOCTYPE name state. */ $state = 'before DOCTYPE name'; } elseif ($char === false) { /* EOF Parse error. Create a new DOCTYPE token. Set its force-quirks flag to on. Emit the token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'need-space-after-doctype-but-got-eof')); $this->emitToken(array('name' => '', 'type' => self::DOCTYPE, 'force-quirks' => true, 'error' => true)); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Reconsume the current character in the before DOCTYPE name state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'need-space-after-doctype')); $this->stream->unget(); $state = 'before DOCTYPE name'; } break; case 'before DOCTYPE name': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the before DOCTYPE name state. */ } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Create a new DOCTYPE token. Set its force-quirks flag to on. Emit the token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-doctype-name-but-got-right-bracket')); $this->emitToken(array('name' => '', 'type' => self::DOCTYPE, 'force-quirks' => true, 'error' => true)); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Create a new DOCTYPE token. Set the token's name to the lowercase version of the input character (add 0x0020 to the character's code point). Switch to the DOCTYPE name state. */ $this->token = array('name' => strtolower($char), 'type' => self::DOCTYPE, 'error' => true); $state = 'DOCTYPE name'; } elseif ($char === false) { /* EOF Parse error. Create a new DOCTYPE token. Set its force-quirks flag to on. Emit the token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-doctype-name-but-got-eof')); $this->emitToken(array('name' => '', 'type' => self::DOCTYPE, 'force-quirks' => true, 'error' => true)); $this->stream->unget(); $state = 'data'; } else { /* Anything else Create a new DOCTYPE token. Set the token's name to the current input character. Switch to the DOCTYPE name state. */ $this->token = array('name' => $char, 'type' => self::DOCTYPE, 'error' => true); $state = 'DOCTYPE name'; } break; case 'DOCTYPE name': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Switch to the after DOCTYPE name state. */ $state = 'after DOCTYPE name'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current DOCTYPE token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ('A' <= $char && $char <= 'Z') { /* U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z Append the lowercase version of the input character (add 0x0020 to the character's code point) to the current DOCTYPE token's name. Stay in the DOCTYPE name state. */ $this->token['name'] .= strtolower($char); } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype-name')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current DOCTYPE token's name. Stay in the DOCTYPE name state. */ $this->token['name'] .= $char; } // XXX this is probably some sort of quirks mode designation, // check tree-builder to be sure. In general 'error' needs // to be specc'ified, this probably means removing it at the end $this->token['error'] = $this->token['name'] === 'HTML' ? false : true; break; case 'after DOCTYPE name': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the after DOCTYPE name state. */ } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current DOCTYPE token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else */ $nextSix = strtoupper($char . $this->stream->charsWhile(self::ALPHA, 5)); if ($nextSix === 'PUBLIC') { /* If the next six characters are an ASCII case-insensitive match for the word "PUBLIC", then consume those characters and switch to the before DOCTYPE public identifier state. */ $state = 'before DOCTYPE public identifier'; } elseif ($nextSix === 'SYSTEM') { /* Otherwise, if the next six characters are an ASCII case-insensitive match for the word "SYSTEM", then consume those characters and switch to the before DOCTYPE system identifier state. */ $state = 'before DOCTYPE system identifier'; } else { /* Otherwise, this is the parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the bogus DOCTYPE state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'expected-space-or-right-bracket-in-doctype')); $this->token['force-quirks'] = true; $this->token['error'] = true; $state = 'bogus DOCTYPE'; } } break; case 'before DOCTYPE public identifier': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the before DOCTYPE public identifier state. */ } elseif ($char === '"') { /* U+0022 QUOTATION MARK (") Set the DOCTYPE token's public identifier to the empty string (not missing), then switch to the DOCTYPE public identifier (double-quoted) state. */ $this->token['public'] = ''; $state = 'DOCTYPE public identifier (double-quoted)'; } elseif ($char === "'") { /* U+0027 APOSTROPHE (') Set the DOCTYPE token's public identifier to the empty string (not missing), then switch to the DOCTYPE public identifier (single-quoted) state. */ $this->token['public'] = ''; $state = 'DOCTYPE public identifier (single-quoted)'; } elseif ($char === '>') { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-end-of-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the bogus DOCTYPE state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-doctype')); $this->token['force-quirks'] = true; $state = 'bogus DOCTYPE'; } break; case 'DOCTYPE public identifier (double-quoted)': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the after DOCTYPE public identifier state. */ $state = 'after DOCTYPE public identifier'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-end-of-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current DOCTYPE token's public identifier. Stay in the DOCTYPE public identifier (double-quoted) state. */ $this->token['public'] .= $char; } break; case 'DOCTYPE public identifier (single-quoted)': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "'") { /* U+0027 APOSTROPHE (') Switch to the after DOCTYPE public identifier state. */ $state = 'after DOCTYPE public identifier'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-end-of-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current DOCTYPE token's public identifier. Stay in the DOCTYPE public identifier (double-quoted) state. */ $this->token['public'] .= $char; } break; case 'after DOCTYPE public identifier': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the after DOCTYPE public identifier state. */ } elseif ($char === '"') { /* U+0022 QUOTATION MARK (") Set the DOCTYPE token's system identifier to the empty string (not missing), then switch to the DOCTYPE system identifier (double-quoted) state. */ $this->token['system'] = ''; $state = 'DOCTYPE system identifier (double-quoted)'; } elseif ($char === "'") { /* U+0027 APOSTROPHE (') Set the DOCTYPE token's system identifier to the empty string (not missing), then switch to the DOCTYPE system identifier (single-quoted) state. */ $this->token['system'] = ''; $state = 'DOCTYPE system identifier (single-quoted)'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current DOCTYPE token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the bogus DOCTYPE state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-doctype')); $this->token['force-quirks'] = true; $state = 'bogus DOCTYPE'; } break; case 'before DOCTYPE system identifier': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the before DOCTYPE system identifier state. */ } elseif ($char === '"') { /* U+0022 QUOTATION MARK (") Set the DOCTYPE token's system identifier to the empty string (not missing), then switch to the DOCTYPE system identifier (double-quoted) state. */ $this->token['system'] = ''; $state = 'DOCTYPE system identifier (double-quoted)'; } elseif ($char === "'") { /* U+0027 APOSTROPHE (') Set the DOCTYPE token's system identifier to the empty string (not missing), then switch to the DOCTYPE system identifier (single-quoted) state. */ $this->token['system'] = ''; $state = 'DOCTYPE system identifier (single-quoted)'; } elseif ($char === '>') { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the bogus DOCTYPE state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-doctype')); $this->token['force-quirks'] = true; $state = 'bogus DOCTYPE'; } break; case 'DOCTYPE system identifier (double-quoted)': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the after DOCTYPE system identifier state. */ $state = 'after DOCTYPE system identifier'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-end-of-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current DOCTYPE token's system identifier. Stay in the DOCTYPE system identifier (double-quoted) state. */ $this->token['system'] .= $char; } break; case 'DOCTYPE system identifier (single-quoted)': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "'") { /* U+0027 APOSTROPHE (') Switch to the after DOCTYPE system identifier state. */ $state = 'after DOCTYPE system identifier'; } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Switch to the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-end-of-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Append the current input character to the current DOCTYPE token's system identifier. Stay in the DOCTYPE system identifier (double-quoted) state. */ $this->token['system'] .= $char; } break; case 'after DOCTYPE system identifier': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === "\t" || $char === "\n" || $char === "\f" || $char === ' ') { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay in the after DOCTYPE system identifier state. */ } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current DOCTYPE token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* Parse error. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'eof-in-doctype')); $this->token['force-quirks'] = true; $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Parse error. Switch to the bogus DOCTYPE state. (This does not set the DOCTYPE token's force-quirks flag to on.) */ $this->emitToken(array('type' => self::PARSEERROR, 'data' => 'unexpected-char-in-doctype')); $state = 'bogus DOCTYPE'; } break; case 'bogus DOCTYPE': /* Consume the next input character: */ $char = $this->stream->char(); if ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the DOCTYPE token. Switch to the data state. */ $this->emitToken($this->token); $state = 'data'; } elseif ($char === false) { /* EOF Emit the DOCTYPE token. Reconsume the EOF character in the data state. */ $this->emitToken($this->token); $this->stream->unget(); $state = 'data'; } else { /* Anything else Stay in the bogus DOCTYPE state. */ } break; // case 'cdataSection': // case 'cdataSection': case 'bbcode tag open': $char = $this->stream->char(); if ($char === '/') { $state = 'bbcode close tag open'; } elseif ('A' <= $char && $char <= 'Z' || 'a' <= $char && $char <= 'z') { $this->token = array('name' => strtolower($char), 'type' => self::BBCODESTARTTAG, 'attr' => NULL); $state = 'bbcode tag name'; } else { $this->emitToken(array('type' => self::CHARACTER, 'data' => '[')); $state = 'data'; $this->stream->unget(); } break; case 'bbcode close tag open': $char = $this->stream->char(); if ('A' <= $char && $char <= 'Z' || 'a' <= $char && $char <= 'z') { $this->token = array('name' => strtolower($char), 'type' => self::BBCODEENDTAG); $state = 'bbcode tag name'; } else { $this->emitToken(array('type' => self::CHARACTER, 'data' => '[/')); $this->stream->unget(); $state = 'data'; } break; case 'bbcode tag name': $char = $this->stream->char(); if ('A' <= $char && $char <= 'Z' || 'a' <= $char && $char <= 'z') { $this->token['name'] .= strtolower($char); } else { if (isset($this->bbcode[$this->token['name']])) { $equals_found = FALSE; $state = 'bbcode before attribute value'; $this->stream->unget(); } else { // PANIC! $this->emitToken(array('type' => self::CHARACTER, 'data' => '[')); $this->stream->char = $tag_begin_position; $state = 'data'; } } break; case 'bbcode before attribute value': $begin_attr = $this->stream->char; $char = $this->stream->char(); if ($char === '=' && !$equals_found) { $equals_found = TRUE; $this->token['attr'] = ""; $this->token['found'] = TRUE; } elseif ($char === ' ' || $char === "\n" || $char === "\t") { $this->token['found'] = TRUE; } elseif ($char === ']') { $state = 'bbcode check pre'; } elseif ($char === '"') { $state = 'bbcode quoted attribute'; } elseif ($char === "'") { $state = 'bbcode single quoted attribute'; } elseif (!isset($this->token['found'])) { $this->emitToken(array('type' => self::CHARACTER, 'data' => '[')); $this->stream->char = $tag_begin_position; $state = 'data'; } else { $this->token['attr'] = ""; $this->stream->unget(); $state = 'bbcode attribute'; } break; case 'bbcode quoted attribute': while (true) { $this->token['attr'] .= $this->stream->charsUntil('&"'); if ($this->stream->char() === '&') { $this->token['attr'] .= $this->consumeCharacterReference(false, true); } else { break; } } $this->stream->charsWhile(" \t\n"); if ($this->stream->char() !== ']') { $this->token['attr'] = ""; $this->token['borked'] = true; $this->stream->char = $begin_attr; $state = 'bbcode attribute'; } else { $state = 'bbcode check pre'; } break; case 'bbcode single quoted attribute': while (true) { $this->token['attr'] .= $this->stream->charsUntil("&'"); if ($this->stream->char() === '&') { $this->token['attr'] .= $this->consumeCharacterReference(false, true); } else { break; } } $this->stream->charsWhile(" \t\n"); if ($this->stream->char() !== ']') { $this->token['borked'] = ""; $this->token['attr'] = true; $this->stream->char = $begin_attr; $state = 'bbcode attribute'; } else { $state = 'bbcode check pre'; } break; case 'bbcode attribute': while (true) { $this->token['attr'] .= $this->stream->charsUntil('&]'); if ($this->stream->char() === '&') { $this->token['attr'] .= $this->consumeCharacterReference(false, true); } else { break; } } $state = 'bbcode check pre'; break; case 'bbcode check pre': $void = isset($this->bbcode[$this->token['name']]['void']) ? $this->bbcode[$this->token['name']]['void'] : NULL; $this->token['void'] = $void === TRUE || $void !== NULL && $void($this->token['attr']); $pre = isset($this->bbcode[$this->token['name']]['pre']) ? $this->bbcode[$this->token['name']]['pre'] : NULL; if ($this->token['void'] || $this->token['type'] !== self::BBCODESTARTTAG || !$pre || $pre !== TRUE && !$pre($this->token['attr'])) { $this->emitToken($this->token); $state = 'data'; break; } $pre = ""; $token = "[/{$this->token['name']}"; $token_len = strlen($token); while ($this->stream->chars($token_len) !== $token) { $char = $this->stream->char(); if ($char === FALSE) { break; } $pre .= $char . $this->stream->charsUntil('['); } $this->token['pre'] = $pre; $this->emitToken($this->token); // The sequence '[/' $this->stream->char(); $this->stream->char(); $state = 'bbcode close tag open'; break; } } }
function PutASmileOnThatFace($s) { global $smilies; LoadSmilies(); $s = preg_replace_callback("'\\[user=([0-9]+)\\]'si", "MakeUserLink", $s); for ($i = 0; $i < count($smilies); $i++) { $preg_special = array("\\", "^", "\$", ".", "*", "+", "?", "|", "(", ")", "[", "]", "{", "}", "@"); $preg_special_escape = array("\\\\", "\\^", "\\\$", "\\.", "\\*", "\\+", "\\?", "\\|", "\\(", "\\)", "\\[", "\\]", "\\{", "\\}", "\\@"); $s = preg_replace("@<([^>]+)(" . str_replace($preg_special, $preg_special_escape, $smilies[$i]['code']) . ")+([^>]+)>@si", "<\$1##LOLDONTREPLACESMILIESINHTMLTAGZLOL##\$3>", $s); $s = str_replace($smilies[$i]['code'], "«" . $smilies[$i]['image'] . "»", $s); $s = str_replace("«" . $smilies[$i]['image'] . "»", "<img src=\"img/smilies/" . $smilies[$i]['image'] . "\" alt=\"" . str_replace(">", ">", $smilies[$i]['code']) . "\" />", $s); $s = str_replace("##LOLDONTREPLACESMILIESINHTMLTAGZLOL##", $smilies[$i]['code'], $s); } return $s; }
function DoSmileyBar($taname = "text") { global $smiliesOrdered; $expandAt = 26; LoadSmilies(TRUE); write("\n\t<div class=\"PoRT margin\" style=\"width: 90%\">\n\t\t<div class=\"errort\">\n\t\t\t<strong>" . __("Smilies") . "</strong>\n\t\t</div>\n\t\t<div class=\"errorc cell0\" id=\"smiliesContainer\">\n"); if (count($smiliesOrdered) > $expandAt) { write("<button class=\"expander\" id=\"smiliesExpand\" onclick=\"expandSmilies();\">▼</button>"); } print "<div class=\"smilies\" id=\"commonSet\">"; for ($i = 0; $i < count($smiliesOrdered) - 1; $i++) { if ($i == $expandAt) { print "</div><div class=\"smilies\" id=\"expandedSet\">"; } $s = $smiliesOrdered[$i]; print "<img src=\"img/smilies/" . $s['image'] . "\" alt=\"" . htmlentities($s['code']) . "\" title=\"" . htmlentities($s['code']) . "\" onclick=\"insertSmiley(' " . str_replace("'", "\\'", $s['code']) . " ');\" />"; } write("\n\t\t\t</div>\n\t\t</div>\n\t</div>\n"); }
function CleanUpPost($postText, $poster = "", $noSmilies = false, $noBr = false) { global $smilies, $text; static $orig, $repl; LoadSmilies(); $s = $postText; $s = str_replace("\r\n", "\n", $s); $s = EatThatPork($s); $s = preg_replace_callback("'\\[source=(.*?)\\](.*?)\\[/source\\]'si", "GeshiCallbackL", $s); $s = preg_replace_callback("'\\[source\\](.*?)\\[/source\\]'si", "GeshiCallback", $s); $s = preg_replace_callback("'\\[user=([0-9]+)\\]'si", "MakeUserLink", $s); //$s = str_replace("Xkeeper","XKitten", $s); //I couldn't help myself -- Kawa //$s = preg_replace("'([c|C])lassic'si","\\1lbuttic", $s); //Same here -- Kawa $s = preg_replace_callback("'\\[code\\](.*?)\\[/code\\]'si", 'code_block', $s); $s = preg_replace("'\\[b\\](.*?)\\[/b\\]'si", "<strong>\\1</strong>", $s); $s = preg_replace("'\\[i\\](.*?)\\[/i\\]'si", "<em>\\1</em>", $s); $s = preg_replace("'\\[u\\](.*?)\\[/u\\]'si", "<u>\\1</u>", $s); $s = preg_replace("'\\[s\\](.*?)\\[/s\\]'si", "<del>\\1</del>", $s); $s = preg_replace("'<b>(.*?)\\</b>'si", "<strong>\\1</strong>", $s); $s = preg_replace("'<i>(.*?)\\</i>'si", "<em>\\1</em>", $s); $s = preg_replace("'<u>(.*?)\\</u>'si", "<span class=\"underline\">\\1</span>", $s); $s = preg_replace("'<s>(.*?)\\</s>'si", "<del>\\1</del>", $s); //Do we need this? //$s = preg_replace("'\[c=([0123456789ABCDEFabcdef]+)\](.*?)\[/c\]'si","<span style=\"color: #\\1\">\\2</span>", $s); if ($noBr == FALSE) { $s = str_replace("\n", "<br />", $s); } //Blacklisted tags $badTags = array('script', 'iframe', 'frame', 'blink', 'textarea', 'noscript', 'meta', 'xmp', 'plaintext', 'marquee', 'embed', 'object'); foreach ($badTags as $tag) { $s = preg_replace("'<{$tag}(.*?)>'si", "<{$tag}\\1>", $s); $s = preg_replace("'</{$tag}(.*?)>'si", "</{$tag}>", $s); } //Bad sites $s = preg_replace("'g****e'si", "goat<span>se</span>", $s); $s = preg_replace("'tubgirl.com'si", "www.youtube.com/watch?v=EK2tWVj6lXw", $s); $s = preg_replace("'ogrish.com'si", "www.youtube.com/watch?v=2iveTJXcp6k", $s); $s = preg_replace("'liveleak.com'si", "www.youtube.com/watch?v=xhLxnlNcxv8", $s); $s = preg_replace("'charonboat.com'si", "www.youtube.com/watch?v=c9BA5e2Of_U", $s); $s = preg_replace("'shrewsburycollege.co.uk'si", "www.youtube.com/watch?v=EK2tWVj6lXw", $s); $s = preg_replace("'lemonparty.com'si", "www.youtube.com/watch?v=EK2tWVj6lXw", $s); $s = preg_replace("'meatspin.com'si", "www.youtube.com/watch?v=2iveTJXcp6k", $s); //Various other stuff //[SUGGESTION] Block "display: none" instead of just "display:" -- Mega-Mario $s = preg_replace("'display:'si", "display<em></em>:", $s); $s = preg_replace("@(on)(\\w+?\\s*?)=@si", '$1$2=', $s); $s = preg_replace("'-moz-binding'si", " -mo<em></em>z-binding", $s); $s = preg_replace("'filter:'si", "filter<em></em>:>", $s); $s = preg_replace("'javascript:'si", "javascript<em></em>:>", $s); $s = str_replace("[spoiler]", "<div class=\"spoiler\"><button onclick=\"toggleSpoiler(this.parentNode);\">Show spoiler</button><div class=\"spoiled hidden\">", $s); $s = preg_replace("'\\[spoiler=(.*?)\\]'si", "<div class=\"spoiler\"><button onclick=\"toggleSpoiler(this.parentNode);\" class=\"named\">\\1</button><div class=\"spoiled hidden\">", $s); $s = str_replace("[/spoiler]", "</div></div>", $s); $s = preg_replace("'\\[url\\](.*?)\\[/url\\]'si", "<a href=\"\\1\">\\1</a>", $s); $s = preg_replace("'\\[url=[\\'\"]?(.*?)[\\'\"]?\\](.*?)\\[/url\\]'si", "<a href=\"\\1\">\\2</a>", $s); $s = preg_replace("'\\[url=(.*?)\\](.*?)\\[/url\\]'si", "<a href=\"\\1\">\\2</a>", $s); $s = preg_replace("'\\[img\\](.*?)\\[/img\\]'si", "<img src=\"\\1\" alt=\"\">", $s); $s = preg_replace("'\\[img=(.*?)\\](.*?)\\[/img\\]'si", "<img src=\"\\1\" alt=\"\\2\" title=\"\\2\">", $s); $s = str_replace("[quote]", "<blockquote><div><hr />", $s); $s = str_replace("[/quote]", "<hr /></div></blockquote>", $s); $s = preg_replace("'\\[quote=\"(.*?)\" id=\"(.*?)\"\\]'si", "<blockquote><div><small><i>Posted by <a href=\"thread.php?pid=\\2#\\2\">\\1</a></i></small><hr />", $s); $s = preg_replace("'\\[quote=(.*?)\\]'si", "<blockquote><div><small><i>Posted by \\1</i></small><hr />", $s); $s = preg_replace("'\\[reply=\"(.*?)\"\\]'si", "<blockquote><div><small><i>Sent by \\1</i></small><hr />", $s); $bucket = "bbCode"; include "./lib/pluginloader.php"; $s = preg_replace_callback("@(href|src)\\s*=\\s*\"([^\"]+)\"@si", "FilterJS", $s); $s = preg_replace_callback("@(href|src)\\s*=\\s*'([^']+)'@si", "FilterJS", $s); $s = preg_replace_callback("@(href|src)\\s*=\\s*([^\\s>]+)@si", "FilterJS", $s); $s = preg_replace("'>>([0-9]+)'si", ">><a href=\"thread.php?pid=\\1#\\1\">\\1</a>", $s); if ($poster) { $s = preg_replace("'/me '", "<b>* " . $poster . "</b> ", $s); } //Smilies if (!$noSmilies) { if (!isset($orig)) { $orig = $repl = array(); for ($i = 0; $i < count($smilies); $i++) { $orig[] = "/(?<=.\\W|\\W.|^\\W)" . preg_quote($smilies[$i]['code'], "/") . "(?=.\\W|\\W.|\\W\$)/"; $repl[] = "<img src=\"img/smilies/" . $smilies[$i]['image'] . "\" />"; } } $s = preg_replace($orig, $repl, " " . $s . " "); $s = substr($s, 1, -1); } $s = preg_replace_callback("@<a[^>]+href\\s*=\\s*\"(.*?)\"@si", 'ApplyNetiquetteToLinks', $s); $s = preg_replace_callback("@<a[^>]+href\\s*=\\s*'(.*?)'@si", 'ApplyNetiquetteToLinks', $s); $s = preg_replace_callback("@<a[^>]+href\\s*=\\s*([^\"'][^\\s>]*)@si", 'ApplyNetiquetteToLinks', $s); include "macros.php"; foreach ($macros as $macro => $img) { $s = str_replace(":" . $macro . ":", "<img src=\"img/macros/" . $img . "\" alt=\":" . $macro . ":\" />", $s); } return $s; }