Project

General

Profile

Bug #22410 » 14050_cleaning_t3lib_parsehtml.patch

Administrator Admin, 2010-11-24 13:54

View differences:

t3lib/class.t3lib_parsehtml.php (revision )
<?php
/***************************************************************
* Copyright notice
*
* (c) 1999-2010 Kasper Sk?rh?j (kasperYYYY@typo3.com)
* All rights reserved
*
* This script is part of the TYPO3 project. The TYPO3 project is
* free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* The GNU General Public License can be found at
* http://www.gnu.org/copyleft/gpl.html.
* A copy is found in the textfile GPL.txt and important notices to the license
* from the author is found in LICENSE.txt distributed with these scripts.
*
*
* This script is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* This copyright notice MUST APPEAR in all copies of the script!
***************************************************************/
* Copyright notice
*
* (c) 1999-2010 Kasper Sk?rh?j (kasperYYYY@typo3.com)
* All rights reserved
*
* This script is part of the TYPO3 project. The TYPO3 project is
* free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* The GNU General Public License can be found at
* http://www.gnu.org/copyleft/gpl.html.
* A copy is found in the textfile GPL.txt and important notices to the license
* from the author is found in LICENSE.txt distributed with these scripts.
*
*
* This script is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* This copyright notice MUST APPEAR in all copies of the script!
***************************************************************/
/**
* Contains class with functions for parsing HTML code.
*
......
*
*
* 106: class t3lib_parsehtml
* 123: function getSubpart($content, $marker)
* 123: function getSubpart($content, $marker)
* 156: function substituteSubpart($content,$marker,$subpartContent,$recursive=1,$keepMarker=0)
* 156: function substituteSubpart($content,$marker,$subpartContent,$recursive=1,$keepMarker=0)
*
* SECTION: Parsing HTML code
* SECTION: Parsing HTML code
* 247: function splitIntoBlock($tag,$content,$eliminateExtraEndTags=0)
* 247: function splitIntoBlock($tag,$content,$eliminateExtraEndTags=0)
* 308: function splitIntoBlockRecursiveProc($tag,$content,&$procObj,$callBackContent,$callBackTags,$level=0)
* 308: function splitIntoBlockRecursiveProc($tag,$content,&$procObj,$callBackContent,$callBackTags,$level=0)
* 344: function splitTags($tag,$content)
* 344: function splitTags($tag,$content)
* 378: function getAllParts($parts,$tag_parts=1,$include_tag=1)
* 378: function getAllParts($parts,$tag_parts=1,$include_tag=1)
* 396: function removeFirstAndLastTag($str)
* 396: function removeFirstAndLastTag($str)
* 412: function getFirstTag($str)
* 412: function getFirstTag($str)
* 426: function getFirstTagName($str,$preserveCase=FALSE)
* 426: function getFirstTagName($str,$preserveCase=FALSE)
* 445: function get_tag_attributes($tag,$deHSC=0)
* 445: function get_tag_attributes($tag,$deHSC=0)
* 486: function split_tag_attributes($tag)
* 486: function split_tag_attributes($tag)
* 524: function checkTagTypeCounts($content,$blockTags='a,b,blockquote,body,div,em,font,form,h1,h2,h3,h4,h5,h6,i,li,map,ol,option,p,pre,select,span,strong,table,td,textarea,tr,u,ul', $soloTags='br,hr,img,input,area')
* 524: function checkTagTypeCounts($content,$blockTags='a,b,blockquote,body,div,em,font,form,h1,h2,h3,h4,h5,h6,i,li,map,ol,option,p,pre,select,span,strong,table,td,textarea,tr,u,ul', $soloTags='br,hr,img,input,area')
*
* SECTION: Clean HTML code
* SECTION: Clean HTML code
* 617: function HTMLcleaner($content, $tags=array(),$keepAll=0,$hSC=0,$addConfig=array())
* 617: function HTMLcleaner($content, $tags=array(),$keepAll=0,$hSC=0,$addConfig=array())
* 814: function bidir_htmlspecialchars($value,$dir)
* 814: function bidir_htmlspecialchars($value,$dir)
* 837: function prefixResourcePath($main_prefix,$content,$alternatives=array(),$suffix='')
* 837: function prefixResourcePath($main_prefix,$content,$alternatives=array(),$suffix='')
* 919: function prefixRelPath($prefix,$srcVal,$suffix='')
* 919: function prefixRelPath($prefix,$srcVal,$suffix='')
* 937: function cleanFontTags($value,$keepFace=0,$keepSize=0,$keepColor=0)
* 937: function cleanFontTags($value,$keepFace=0,$keepSize=0,$keepColor=0)
* 967: function mapTags($value,$tags=array(),$ltChar='<',$ltChar2='<')
* 967: function mapTags($value,$tags=array(),$ltChar='<',$ltChar2='<')
* 982: function unprotectTags($content,$tagList='')
* 982: function unprotectTags($content,$tagList='')
* 1015: function stripTagsExcept($value,$tagList)
* 1015: function stripTagsExcept($value,$tagList)
* 1038: function caseShift($str,$flag,$cacheKey='')
* 1038: function caseShift($str,$flag,$cacheKey='')
* 1065: function compileTagAttribs($tagAttrib,$meta=array(), $xhtmlClean=0)
* 1065: function compileTagAttribs($tagAttrib,$meta=array(), $xhtmlClean=0)
* 1093: function get_tag_attributes_classic($tag,$deHSC=0)
* 1093: function get_tag_attributes_classic($tag,$deHSC=0)
* 1106: function indentLines($content, $number=1, $indentChar=TAB)
* 1106: function indentLines($content, $number=1, $indentChar=TAB)
* 1123: function HTMLparserConfig($TSconfig,$keepTags=array())
* 1123: function HTMLparserConfig($TSconfig,$keepTags=array())
* 1247: function XHTML_clean($content)
* 1247: function XHTML_clean($content)
* 1269: function processTag($value,$conf,$endTag,$protected=0)
* 1269: function processTag($value,$conf,$endTag,$protected=0)
* 1315: function processContent($value,$dir,$conf)
* 1315: function processContent($value,$dir,$conf)
*
* TOTAL FUNCTIONS: 28
* (This index is automatically created/updated by the extension "extdeveval")
......
*/
/**
* Functions for parsing HTML.
* You are encouraged to use this class in your own applications
......
* @package TYPO3
* @subpackage t3lib
*/
class t3lib_parsehtml {
class t3lib_parsehtml {
protected $caseShift_cache = array();
......
public static function getSubpart($content, $marker) {
$start = strpos($content, $marker);
if ($start === false) {
if ($start === FALSE) {
return '';
}
$start += strlen($marker);
$stop = strpos($content, $marker, $start);
$stop = strpos($content, $marker, $start);
// Q: What shall get returned if no stop marker is given
// /*everything till the end*/ or nothing?
if ($stop===false) {
if ($stop === FALSE) {
return ''; /*substr($content, $start)*/
}
$content = substr($content, $start, $stop-$start);
$content = substr($content, $start, $stop - $start);
$matches = array();
if (preg_match('/^([^\<]*\-\-\>)(.*)(\<\!\-\-[^\>]*)$/s', $content, $matches) === 1) {
......
public static function substituteSubpart($content, $marker, $subpartContent, $recursive = 1, $keepMarker = 0) {
$start = strpos($content, $marker);
if ($start === false) {
if ($start === FALSE) {
return $content;
}
$startAM = $start + strlen($marker);
$stop = strpos($content, $marker, $startAM);
$stop = strpos($content, $marker, $startAM);
if ($stop===false) {
if ($stop === FALSE) {
return $content;
}
$stopAM = $stop + strlen($marker);
$stopAM = $stop + strlen($marker);
$before = substr($content, 0, $start);
$before = substr($content, 0, $start);
$after = substr($content, $stopAM);
$after = substr($content, $stopAM);
$between = substr($content, $startAM, $stop-$startAM);
$between = substr($content, $startAM, $stop - $startAM);
if ($recursive) {
$after = self::substituteSubpart(
......
if ($keepMarker) {
$matches = array();
if (preg_match('/^([^\<]*\-\-\>)(.*)(\<\!\-\-[^\>]*)$/s', $between, $matches) === 1) {
$before .= $marker.$matches[1];
$before .= $marker . $matches[1];
$between = $matches[2];
$between = $matches[2];
$after = $matches[3] . $marker . $after;
$after = $matches[3] . $marker . $after;
} elseif (preg_match('/^(.*)(\<\!\-\-[^\>]*)$/s', $between, $matches) === 1) {
$before .= $marker;
$before .= $marker;
$between = $matches[1];
$between = $matches[1];
$after = $matches[2] . $marker . $after;
$after = $matches[2] . $marker . $after;
} elseif (preg_match('/^([^\<]*\-\-\>)(.*)$/s', $between, $matches) === 1) {
$before .= $marker . $matches[1];
$before .= $marker . $matches[1];
$between = $matches[2];
$between = $matches[2];
$after = $marker . $after;
$after = $marker . $after;
} else {
} else {
$before .= $marker;
$after = $marker . $after;
$after = $marker . $after;
}
} else {
......
$matches = array();
if (preg_match('/^([^\<]*\-\-\>)(.*)(\<\!\-\-[^\>]*)$/s', $between, $matches) === 1) {
$between = $matches[2];
} elseif (preg_match('/^(.*)(\<\!\-\-[^\>]*)$/s', $between, $matches)===1) {
} elseif (preg_match('/^(.*)(\<\!\-\-[^\>]*)$/s', $between, $matches) === 1) {
$between = $matches[1];
} elseif (preg_match('/^([^\<]*\-\-\>)(.*)$/s', $between, $matches)===1) {
} elseif (preg_match('/^([^\<]*\-\-\>)(.*)$/s', $between, $matches) === 1) {
$between = $matches[2];
}
}
......
if (is_array($subpartContent)) {
$between = $subpartContent[0] . $between . $subpartContent[1];
} else {
} else {
$between = $subpartContent;
}
......
}
/************************************
*
* Parsing HTML code
......
* @return array Even numbers in the array are outside the blocks, Odd numbers are block-content.
* @see splitTags(), getAllParts(), removeFirstAndLastTag()
*/
function splitIntoBlock($tag,$content,$eliminateExtraEndTags=0) {
function splitIntoBlock($tag, $content, $eliminateExtraEndTags = 0) {
$tags=array_unique(t3lib_div::trimExplode(',',$tag,1));
$tags = array_unique(t3lib_div::trimExplode(',', $tag, 1));
$regexStr = '/\<\/?('.implode('|', $tags).')(\s*\>|\s[^\>]*\>)/si';
$regexStr = '/\<\/?(' . implode('|', $tags) . ')(\s*\>|\s[^\>]*\>)/si';
$parts = preg_split($regexStr, $content);
$newParts=array();
$newParts = array();
$pointer=strlen($parts[0]);
$pointer = strlen($parts[0]);
$buffer=$parts[0];
$buffer = $parts[0];
$nested=0;
$nested = 0;
reset($parts);
next($parts);
while(list($k,$v)=each($parts)) {
while (list($k, $v) = each($parts)) {
$isEndTag= substr($content,$pointer,2)=='</' ? 1 : 0;
$isEndTag = substr($content, $pointer, 2) == '</' ? 1 : 0;
$tagLen = strcspn(substr($content,$pointer),'>')+1;
$tagLen = strcspn(substr($content, $pointer), '>') + 1;
if (!$isEndTag) { // We meet a start-tag:
if (!$isEndTag) { // We meet a start-tag:
if (!$nested) { // Ground level:
if (!$nested) { // Ground level:
$newParts[]=$buffer; // previous buffer stored
$newParts[] = $buffer; // previous buffer stored
$buffer='';
$buffer = '';
}
$nested++; // We are inside now!
$nested++; // We are inside now!
$mbuffer=substr($content,$pointer,strlen($v)+$tagLen); // New buffer set and pointer increased
$mbuffer = substr($content, $pointer, strlen($v) + $tagLen); // New buffer set and pointer increased
$pointer+=strlen($mbuffer);
$pointer += strlen($mbuffer);
$buffer.=$mbuffer;
$buffer .= $mbuffer;
} else { // If we meet an endtag:
} else { // If we meet an endtag:
$nested--; // decrease nested-level
$nested--; // decrease nested-level
$eliminated=0;
$eliminated = 0;
if ($eliminateExtraEndTags && $nested<0) {
if ($eliminateExtraEndTags && $nested < 0) {
$nested=0;
$nested = 0;
$eliminated=1;
$eliminated = 1;
} else {
$buffer.=substr($content,$pointer,$tagLen); // In any case, add the endtag to current buffer and increase pointer
$buffer .= substr($content, $pointer, $tagLen); // In any case, add the endtag to current buffer and increase pointer
}
$pointer+=$tagLen;
$pointer += $tagLen;
if (!$nested && !$eliminated) { // if we're back on ground level, (and not by eliminating tags...
if (!$nested && !$eliminated) { // if we're back on ground level, (and not by eliminating tags...
$newParts[]=$buffer;
$newParts[] = $buffer;
$buffer='';
$buffer = '';
}
$mbuffer=substr($content,$pointer,strlen($v)); // New buffer set and pointer increased
$mbuffer = substr($content, $pointer, strlen($v)); // New buffer set and pointer increased
$pointer+=strlen($mbuffer);
$pointer += strlen($mbuffer);
$buffer.=$mbuffer;
$buffer .= $mbuffer;
}
}
$newParts[]=$buffer;
$newParts[] = $buffer;
return $newParts;
}
......
* @return string Processed content
* @see splitIntoBlock()
*/
function splitIntoBlockRecursiveProc($tag,$content,&$procObj,$callBackContent,$callBackTags,$level=0) {
function splitIntoBlockRecursiveProc($tag, $content, &$procObj, $callBackContent, $callBackTags, $level = 0) {
$parts = $this->splitIntoBlock($tag,$content,TRUE);
$parts = $this->splitIntoBlock($tag, $content, TRUE);
foreach($parts as $k => $v) {
foreach ($parts as $k => $v) {
if ($k%2) {
if ($k % 2) {
$firstTagName = $this->getFirstTagName($v, TRUE);
$tagsArray = array();
$tagsArray['tag_start'] = $this->getFirstTag($v);
$tagsArray['tag_end'] = '</'.$firstTagName.'>';
$tagsArray['tag_end'] = '</' . $firstTagName . '>';
$tagsArray['tag_name'] = strtolower($firstTagName);
$tagsArray['add_level'] = 1;
$tagsArray['content'] = $this->splitIntoBlockRecursiveProc($tag,$this->removeFirstAndLastTag($v),$procObj,$callBackContent,$callBackTags,$level+$tagsArray['add_level']);
$tagsArray['content'] = $this->splitIntoBlockRecursiveProc($tag, $this->removeFirstAndLastTag($v), $procObj, $callBackContent, $callBackTags, $level + $tagsArray['add_level']);
if ($callBackTags) $tagsArray = $procObj->$callBackTags($tagsArray,$level);
if ($callBackTags) {
$tagsArray = $procObj->$callBackTags($tagsArray, $level);
}
$parts[$k] =
$tagsArray['tag_start'].
$tagsArray['tag_start'] .
$tagsArray['content'].
$tagsArray['content'] .
$tagsArray['tag_end'];
$tagsArray['tag_end'];
} else {
if ($callBackContent) $parts[$k] = $procObj->$callBackContent($parts[$k],$level);
if ($callBackContent) {
$parts[$k] = $procObj->$callBackContent($parts[$k], $level);
}
}
}
}
}
return implode('',$parts);
return implode('', $parts);
}
/**
......
* @return array Even numbers in the array are outside the blocks, Odd numbers are block-content.
* @see splitIntoBlock(), getAllParts(), removeFirstAndLastTag()
*/
function splitTags($tag,$content) {
function splitTags($tag, $content) {
$tags = t3lib_div::trimExplode(',',$tag,1);
$tags = t3lib_div::trimExplode(',', $tag, 1);
$regexStr = '/\<('.implode('|', $tags).')(\s[^>]*)?\/?>/si';
$regexStr = '/\<(' . implode('|', $tags) . ')(\s[^>]*)?\/?>/si';
$parts = preg_split($regexStr, $content);
$pointer = strlen($parts[0]);
......
$newParts[] = $parts[0];
reset($parts);
next($parts);
while(list($k,$v)=each($parts)) {
while (list($k, $v) = each($parts)) {
$tagLen = strcspn(substr($content,$pointer),'>')+1;
$tagLen = strcspn(substr($content, $pointer), '>') + 1;
// Set tag:
$tag = substr($content,$pointer,$tagLen); // New buffer set and pointer increased
$tag = substr($content, $pointer, $tagLen); // New buffer set and pointer increased
$newParts[] = $tag;
$pointer+= strlen($tag);
$pointer += strlen($tag);
// Set content:
$newParts[] = $v;
$pointer+= strlen($v);
$pointer += strlen($v);
}
return $newParts;
}
......
* @return array Tag-parts/Non-tag-parts depending on input argument settings
* @see splitIntoBlock(), splitTags()
*/
function getAllParts($parts,$tag_parts=1,$include_tag=1) {
function getAllParts($parts, $tag_parts = 1, $include_tag = 1) {
$newParts=array();
$newParts = array();
foreach ($parts as $k => $v) {
foreach ($parts as $k => $v) {
if (($k+($tag_parts?0:1))%2) {
if (($k + ($tag_parts ? 0 : 1)) % 2) {
if (!$include_tag) $v=$this->removeFirstAndLastTag($v);
if (!$include_tag) {
$v = $this->removeFirstAndLastTag($v);
}
$newParts[]=$v;
$newParts[] = $v;
}
}
return $newParts;
......
* @param string String to process
* @return string
*/
function removeFirstAndLastTag($str) {
function removeFirstAndLastTag($str) {
// End of first tag:
$start = strpos($str,'>');
$start = strpos($str, '>');
// Begin of last tag:
$end = strrpos($str,'<');
$end = strrpos($str, '<');
// return
return substr($str, $start+1, $end-$start-1);
return substr($str, $start + 1, $end - $start - 1);
}
/**
......
* @param string HTML string with tags
* @return string
*/
function getFirstTag($str) {
function getFirstTag($str) {
// First:
$endLen = strpos($str,'>')+1;
$endLen = strpos($str, '>') + 1;
return substr($str,0,$endLen);
return substr($str, 0, $endLen);
}
/**
......
* @return string Tag name in upper case
* @see getFirstTag()
*/
function getFirstTagName($str,$preserveCase=FALSE) {
function getFirstTagName($str, $preserveCase = FALSE) {
$matches = array();
if (preg_match('/^\s*\<([^\s\>]+)(\s|\>)/', $str, $matches)===1) {
if (preg_match('/^\s*\<([^\s\>]+)(\s|\>)/', $str, $matches) === 1) {
if (!$preserveCase) {
if (!$preserveCase) {
return strtoupper($matches[1]);
}
return $matches[1];
......
* @param boolean If set, the attribute values are de-htmlspecialchar'ed. Should actually always be set!
* @return array array(Tag attributes,Attribute meta-data)
*/
function get_tag_attributes($tag,$deHSC=0) {
function get_tag_attributes($tag, $deHSC = 0) {
list($components,$metaC) = $this->split_tag_attributes($tag);
list($components, $metaC) = $this->split_tag_attributes($tag);
$name = ''; // attribute name is stored here
$name = ''; // attribute name is stored here
$valuemode = false;
$valuemode = FALSE;
$attributes = array();
$attributesMeta = array();
if (is_array($components)) {
if (is_array($components)) {
foreach ($components as $key => $val) {
foreach ($components as $key => $val) {
if ($val != '=') { // Only if $name is set (if there is an attribute, that waits for a value), that valuemode is enabled. This ensures that the attribute is assigned it's value
if ($val != '=') { // Only if $name is set (if there is an attribute, that waits for a value), that valuemode is enabled. This ensures that the attribute is assigned it's value
if ($valuemode) {
if ($valuemode) {
if ($name) {
if ($name) {
$attributes[$name] = $deHSC?t3lib_div::htmlspecialchars_decode($val):$val;
$attributes[$name] = $deHSC ? t3lib_div::htmlspecialchars_decode($val) : $val;
$attributesMeta[$name]['dashType']=$metaC[$key];
$attributesMeta[$name]['dashType'] = $metaC[$key];
$name = '';
}
} else {
if ($namekey = preg_replace('/[^[:alnum:]_\:\-]/','',$val)) {
if ($namekey = preg_replace('/[^[:alnum:]_\:\-]/', '', $val)) {
$name = strtolower($namekey);
$attributesMeta[$name]=array();
$attributesMeta[$name] = array();
$attributesMeta[$name]['origTag']=$namekey;
$attributesMeta[$name]['origTag'] = $namekey;
$attributes[$name] = '';
}
}
$valuemode = false;
$valuemode = FALSE;
} else {
$valuemode = true;
$valuemode = TRUE;
}
}
return array($attributes,$attributesMeta);
return array($attributes, $attributesMeta);
}
}
......
* @access private
* @see t3lib_div::split_tag_attributes()
*/
function split_tag_attributes($tag) {
function split_tag_attributes($tag) {
$matches = array();
if (preg_match('/(\<[^\s]+\s+)?(.*?)\s*(\>)?$/s', $tag, $matches)!==1) {
if (preg_match('/(\<[^\s]+\s+)?(.*?)\s*(\>)?$/s', $tag, $matches) !== 1) {
return array(array(), array());
}
$tag_tmp = $matches[2];
......
$metaValue = array();
$value = array();
$matches = array();
if (preg_match_all('/("[^"]*"|\'[^\']*\'|[^\s"\'\=]+|\=)/s', $tag_tmp, $matches)>0) {
if (preg_match_all('/("[^"]*"|\'[^\']*\'|[^\s"\'\=]+|\=)/s', $tag_tmp, $matches) > 0) {
foreach ($matches[1] as $part) {
foreach ($matches[1] as $part) {
$firstChar = substr($part, 0, 1);
if ($firstChar=='"' || $firstChar=="'") {
if ($firstChar == '"' || $firstChar == "'") {
$metaValue[] = $firstChar;
$value[] = substr($part, 1, -1);
} else {
} else {
$metaValue[] = '';
$value[] = $part;
}
}
}
return array($value,$metaValue);
return array($value, $metaValue);
}
/**
......
* @param string Tag names for solo tags (eg. img, br or input) in lowercase, commalist ("img,br,input")
* @return array Analyse data.
*/
function checkTagTypeCounts($content,$blockTags='a,b,blockquote,body,div,em,font,form,h1,h2,h3,h4,h5,h6,i,li,map,ol,option,p,pre,select,span,strong,table,td,textarea,tr,u,ul', $soloTags='br,hr,img,input,area') {
function checkTagTypeCounts($content, $blockTags = 'a,b,blockquote,body,div,em,font,form,h1,h2,h3,h4,h5,h6,i,li,map,ol,option,p,pre,select,span,strong,table,td,textarea,tr,u,ul', $soloTags = 'br,hr,img,input,area') {
$content = strtolower($content);
$analyzedOutput=array();
$analyzedOutput = array();
$analyzedOutput['counts']=array(); // Counts appearances of start-tags
$analyzedOutput['counts'] = array(); // Counts appearances of start-tags
$analyzedOutput['errors']=array(); // Lists ERRORS
$analyzedOutput['errors'] = array(); // Lists ERRORS
$analyzedOutput['warnings']=array(); // Lists warnings.
$analyzedOutput['warnings'] = array(); // Lists warnings.
$analyzedOutput['blocks']=array(); // Lists stats for block-tags
$analyzedOutput['blocks'] = array(); // Lists stats for block-tags
$analyzedOutput['solo']=array(); // Lists stats for solo-tags
$analyzedOutput['solo'] = array(); // Lists stats for solo-tags
// Block tags, must have endings...
$blockTags = explode(',',$blockTags);
$blockTags = explode(',', $blockTags);
foreach($blockTags as $tagName) {
foreach ($blockTags as $tagName) {
$countBegin = count(preg_split('/\<'.$tagName.'(\s|\>)/s',$content))-1;
$countBegin = count(preg_split('/\<' . $tagName . '(\s|\>)/s', $content)) - 1;
$countEnd = count(preg_split('/\<\/'.$tagName.'(\s|\>)/s',$content))-1;
$countEnd = count(preg_split('/\<\/' . $tagName . '(\s|\>)/s', $content)) - 1;
$analyzedOutput['blocks'][$tagName]=array($countBegin,$countEnd,$countBegin-$countEnd);
$analyzedOutput['blocks'][$tagName] = array($countBegin, $countEnd, $countBegin - $countEnd);
if ($countBegin) $analyzedOutput['counts'][$tagName]=$countBegin;
if ($countBegin) {
$analyzedOutput['counts'][$tagName] = $countBegin;
}
if ($countBegin-$countEnd) {
if ($countBegin - $countEnd) {
if ($countBegin-$countEnd > 0) {
if ($countBegin - $countEnd > 0) {
$analyzedOutput['errors'][$tagName]='There were more start-tags ('.$countBegin.') than end-tags ('.$countEnd.') for the element "'.$tagName.'". There should be an equal amount!';
$analyzedOutput['errors'][$tagName] = 'There were more start-tags (' . $countBegin . ') than end-tags (' . $countEnd . ') for the element "' . $tagName . '". There should be an equal amount!';
} else {
$analyzedOutput['warnings'][$tagName]='There were more end-tags ('.$countEnd.') than start-tags ('.$countBegin.') for the element "'.$tagName.'". There should be an equal amount! However the problem is not fatal.';
$analyzedOutput['warnings'][$tagName] = 'There were more end-tags (' . $countEnd . ') than start-tags (' . $countBegin . ') for the element "' . $tagName . '". There should be an equal amount! However the problem is not fatal.';
}
}
}
// Solo tags, must NOT have endings...
$soloTags = explode(',',$soloTags);
$soloTags = explode(',', $soloTags);
foreach($soloTags as $tagName) {
foreach ($soloTags as $tagName) {
$countBegin = count(preg_split('/\<'.$tagName.'(\s|\>)/s',$content))-1;
$countBegin = count(preg_split('/\<' . $tagName . '(\s|\>)/s', $content)) - 1;
$countEnd = count(preg_split('/\<\/'.$tagName.'(\s|\>)/s',$content))-1;
$countEnd = count(preg_split('/\<\/' . $tagName . '(\s|\>)/s', $content)) - 1;
$analyzedOutput['solo'][$tagName]=array($countBegin,$countEnd);
$analyzedOutput['solo'][$tagName] = array($countBegin, $countEnd);
if ($countBegin) $analyzedOutput['counts'][$tagName]=$countBegin;
if ($countBegin) {
$analyzedOutput['counts'][$tagName] = $countBegin;
}
if ($countEnd) {
if ($countEnd) {
$analyzedOutput['warnings'][$tagName]='There were end-tags found ('.$countEnd.') for the element "'.$tagName.'". This was not expected (although XHTML technically allows it).';
$analyzedOutput['warnings'][$tagName] = 'There were end-tags found (' . $countEnd . ') for the element "' . $tagName . '". This was not expected (although XHTML technically allows it).';
}
}
......
}
/*********************************
*
* Clean HTML code
......
* Initializing the $tags array to allow a list of tags (in this case <B>,<I>,<U> and <A>), set it like this: $tags = array_flip(explode(',','b,a,i,u'))
* If the value of the $tags[$tagname] entry is an array, advanced processing of the tags is initialized. These are the options:
*
* $tags[$tagname] = Array(
* $tags[$tagname] = Array(
* 'overrideAttribs' => '' If set, this string is preset as the attributes of the tag
* 'overrideAttribs' => '' If set, this string is preset as the attributes of the tag
* 'allowedAttribs' => '0' (zero) = no attributes allowed, '[commalist of attributes]' = only allowed attributes. If blank, all attributes are allowed.
* 'allowedAttribs' => '0' (zero) = no attributes allowed, '[commalist of attributes]' = only allowed attributes. If blank, all attributes are allowed.
* 'fixAttrib' => Array(
* 'fixAttrib' => Array(
* '[attribute name]' => Array (
* '[attribute name]' => Array (
* 'set' => Force the attribute value to this value.
* 'set' => Force the attribute value to this value.
* 'unset' => Boolean: If set, the attribute is unset.
* 'unset' => Boolean: If set, the attribute is unset.
* 'default' => If no attribute exists by this name, this value is set as default value (if this value is not blank)
* 'default' => If no attribute exists by this name, this value is set as default value (if this value is not blank)
* 'always' => Boolean. If set, the attribute is always processed. Normally an attribute is processed only if it exists
* 'always' => Boolean. If set, the attribute is always processed. Normally an attribute is processed only if it exists
* 'trim,intval,lower,upper' => All booleans. If any of these keys are set, the value is passed through the respective PHP-functions.
* 'trim,intval,lower,upper' => All booleans. If any of these keys are set, the value is passed through the respective PHP-functions.
* 'range' => Array ('[low limit]','[high limit, optional]') Setting integer range.
* 'range' => Array ('[low limit]','[high limit, optional]') Setting integer range.
* 'list' => Array ('[value1/default]','[value2]','[value3]') Attribute must be in this list. If not, the value is set to the first element.
* 'list' => Array ('[value1/default]','[value2]','[value3]') Attribute must be in this list. If not, the value is set to the first element.
* 'removeIfFalse' => Boolean/'blank'. If set, then the attribute is removed if it is 'false'. If this value is set to 'blank' then the value must be a blank string (that means a 'zero' value will not be removed)
* 'removeIfFalse' => Boolean/'blank'. If set, then the attribute is removed if it is 'false'. If this value is set to 'blank' then the value must be a blank string (that means a 'zero' value will not be removed)
* 'removeIfEquals' => [value] If the attribute value matches the value set here, then it is removed.
* 'removeIfEquals' => [value] If the attribute value matches the value set here, then it is removed.
* 'casesensitiveComp' => 1 If set, then the removeIfEquals and list comparisons will be case sensitive. Otherwise not.
* 'casesensitiveComp' => 1 If set, then the removeIfEquals and list comparisons will be case sensitive. Otherwise not.
* )
* )
* ),
* ),
* 'protect' => '', Boolean. If set, the tag <> is converted to &lt; and &gt;
* 'protect' => '', Boolean. If set, the tag <> is converted to &lt; and &gt;
* 'remap' => '', String. If set, the tagname is remapped to this tagname
* 'remap' => '', String. If set, the tagname is remapped to this tagname
* 'rmTagIfNoAttrib' => '', Boolean. If set, then the tag is removed if no attributes happend to be there.
* 'rmTagIfNoAttrib' => '', Boolean. If set, then the tag is removed if no attributes happend to be there.
* 'nesting' => '', Boolean/'global'. If set true, then this tag must have starting and ending tags in the correct order. Any tags not in this order will be discarded. Thus '</B><B><I></B></I></B>' will be converted to '<B><I></B></I>'. Is the value 'global' then true nesting in relation to other tags marked for 'global' nesting control is preserved. This means that if <B> and <I> are set for global nesting then this string '</B><B><I></B></I></B>' is converted to '<B></B>'
* 'nesting' => '', Boolean/'global'. If set true, then this tag must have starting and ending tags in the correct order. Any tags not in this order will be discarded. Thus '</B><B><I></B></I></B>' will be converted to '<B><I></B></I>'. Is the value 'global' then true nesting in relation to other tags marked for 'global' nesting control is preserved. This means that if <B> and <I> are set for global nesting then this string '</B><B><I></B></I></B>' is converted to '<B></B>'
* )
* )
*
* @param string $content; is the HTML-content being processed. This is also the result being returned.
* @param array $tags; is an array where each key is a tagname in lowercase. Only tags present as keys in this array are preserved. The value of the key can be an array with a vast number of options to configure.
......
* @param array Configuration array send along as $conf to the internal functions ->processContent() and ->processTag()
* @return string Processed HTML content
*/
function HTMLcleaner($content, $tags=array(),$keepAll=0,$hSC=0,$addConfig=array()) {
function HTMLcleaner($content, $tags = array(), $keepAll = 0, $hSC = 0, $addConfig = array()) {
$newContent = array();
$tokArr = explode('<',$content);
$tokArr = explode('<', $content);
$newContent[] = $this->processContent(current($tokArr),$hSC,$addConfig);
$newContent[] = $this->processContent(current($tokArr), $hSC, $addConfig);
next($tokArr);
$c = 1;
$tagRegister = array();
$tagStack = array();
$inComment = false; $skipTag = false;
$inComment = FALSE;
$skipTag = FALSE;
while(list(,$tok)=each($tokArr)) {
while (list(, $tok) = each($tokArr)) {
if ($inComment) {
if (($eocPos = strpos($tok, '-->')) === false) {
if (($eocPos = strpos($tok, '-->')) === FALSE) {
// End of comment is not found in the token. Go futher until end of comment is found in other tokens.
// End of comment is not found in the token. Go futher until end of comment is found in other tokens.
$newContent[$c++] = '<' . $tok;
continue;
}
// Comment ends in the middle of the token: add comment and proceed with rest of the token
// Comment ends in the middle of the token: add comment and proceed with rest of the token
$newContent[$c++] = '<' . substr($tok, 0, $eocPos + 3);
$tok = substr($tok, $eocPos + 3);
$inComment = false; $skipTag = true;
$inComment = FALSE;
$skipTag = TRUE;
}
elseif (substr($tok, 0, 3) == '!--') {
if (($eocPos = strpos($tok, '-->')) === false) {
if (($eocPos = strpos($tok, '-->')) === FALSE) {
// Comment started in this token but it does end in the same token. Set a flag to skip till the end of comment
// Comment started in this token but it does end in the same token. Set a flag to skip till the end of comment
$newContent[$c++] = '<' . $tok;
$inComment = true;
$inComment = TRUE;
continue;
}
// Start and end of comment are both in the current token. Add comment and proceed with rest of the token
// Start and end of comment are both in the current token. Add comment and proceed with rest of the token
$newContent[$c++] = '<' . substr($tok, 0, $eocPos + 3);
$tok = substr($tok, $eocPos + 3);
$skipTag = true;
$skipTag = TRUE;
}
$firstChar = substr($tok,0,1);
$firstChar = substr($tok, 0, 1);
if (!$skipTag && preg_match('/[[:alnum:]\/]/',$firstChar)==1) { // It is a tag... (first char is a-z0-9 or /) (fixed 19/01 2004). This also avoids triggering on <?xml..> and <!DOCTYPE..>
if (!$skipTag && preg_match('/[[:alnum:]\/]/', $firstChar) == 1) { // It is a tag... (first char is a-z0-9 or /) (fixed 19/01 2004). This also avoids triggering on <?xml..> and <!DOCTYPE..>
$tagEnd = strpos($tok,'>');
$tagEnd = strpos($tok, '>');
if ($tagEnd) { // If there is and end-bracket... tagEnd can't be 0 as the first character can't be a >
if ($tagEnd) { // If there is and end-bracket... tagEnd can't be 0 as the first character can't be a >
$endTag = $firstChar=='/' ? 1 : 0;
$endTag = $firstChar == '/' ? 1 : 0;
$tagContent = substr($tok,$endTag,$tagEnd-$endTag);
$tagContent = substr($tok, $endTag, $tagEnd - $endTag);
$tagParts = preg_split('/\s+/s',$tagContent,2);
$tagParts = preg_split('/\s+/s', $tagContent, 2);
$tagName = strtolower($tagParts[0]);
if (isset($tags[$tagName])) {
if (isset($tags[$tagName])) {
if (is_array($tags[$tagName])) { // If there is processing to do for the tag:
if (is_array($tags[$tagName])) { // If there is processing to do for the tag:
if (!$endTag) { // If NOT an endtag, do attribute processing (added dec. 2003)
if (!$endTag) { // If NOT an endtag, do attribute processing (added dec. 2003)
// Override attributes
if (strcmp($tags[$tagName]['overrideAttribs'],'')) {
if (strcmp($tags[$tagName]['overrideAttribs'], '')) {
$tagParts[1]=$tags[$tagName]['overrideAttribs'];
$tagParts[1] = $tags[$tagName]['overrideAttribs'];
}
// Allowed tags
if (strcmp($tags[$tagName]['allowedAttribs'],'')) {
if (strcmp($tags[$tagName]['allowedAttribs'], '')) {
if (!strcmp($tags[$tagName]['allowedAttribs'],'0')) { // No attribs allowed
if (!strcmp($tags[$tagName]['allowedAttribs'], '0')) { // No attribs allowed
$tagParts[1]='';
$tagParts[1] = '';
} elseif (trim($tagParts[1])) {
$tagAttrib = $this->get_tag_attributes($tagParts[1]);
$tagParts[1]='';
$tagParts[1] = '';
$newTagAttrib = array();
if (!($tList = $tags[$tagName]['_allowedAttribs'])) {
if (!($tList = $tags[$tagName]['_allowedAttribs'])) {
// Just explode attribts for tag once
$tList = $tags[$tagName]['_allowedAttribs'] = t3lib_div::trimExplode(',',strtolower($tags[$tagName]['allowedAttribs']),1);
$tList = $tags[$tagName]['_allowedAttribs'] = t3lib_div::trimExplode(',', strtolower($tags[$tagName]['allowedAttribs']), 1);
}
foreach ($tList as $allowTag) {
foreach ($tList as $allowTag) {
if (isset($tagAttrib[0][$allowTag])) $newTagAttrib[$allowTag]=$tagAttrib[0][$allowTag];
if (isset($tagAttrib[0][$allowTag])) {
$newTagAttrib[$allowTag] = $tagAttrib[0][$allowTag];
}
}
}
$tagParts[1]=$this->compileTagAttribs($newTagAttrib,$tagAttrib[1]);
$tagParts[1] = $this->compileTagAttribs($newTagAttrib, $tagAttrib[1]);
}
}
// Fixed attrib values
if (is_array($tags[$tagName]['fixAttrib'])) {
if (is_array($tags[$tagName]['fixAttrib'])) {
$tagAttrib = $this->get_tag_attributes($tagParts[1]);
$tagParts[1]='';
$tagParts[1] = '';
foreach ($tags[$tagName]['fixAttrib'] as $attr => $params) {
if (strlen($params['set'])) $tagAttrib[0][$attr] = $params['set'];
if (strlen($params['unset'])) unset($tagAttrib[0][$attr]);
if (strcmp($params['default'],'') && !isset($tagAttrib[0][$attr])) $tagAttrib[0][$attr]=$params['default'];
if (strlen($params['set'])) {
$tagAttrib[0][$attr] = $params['set'];
}
if (strlen($params['unset'])) {
unset($tagAttrib[0][$attr]);
}
if (strcmp($params['default'], '') && !isset($tagAttrib[0][$attr])) {
$tagAttrib[0][$attr] = $params['default'];
}
if ($params['always'] || isset($tagAttrib[0][$attr])) {
if ($params['always'] || isset($tagAttrib[0][$attr])) {
if ($params['trim']) {$tagAttrib[0][$attr]=trim($tagAttrib[0][$attr]);}
if ($params['intval']) {$tagAttrib[0][$attr]=intval($tagAttrib[0][$attr]);}
if ($params['lower']) {$tagAttrib[0][$attr]=strtolower($tagAttrib[0][$attr]);}
if ($params['upper']) {$tagAttrib[0][$attr]=strtoupper($tagAttrib[0][$attr]);}
if ($params['trim']) {
$tagAttrib[0][$attr] = trim($tagAttrib[0][$attr]);
}
if ($params['intval']) {
$tagAttrib[0][$attr] = intval($tagAttrib[0][$attr]);
}
if ($params['lower']) {
$tagAttrib[0][$attr] = strtolower($tagAttrib[0][$attr]);
}
if ($params['upper']) {
$tagAttrib[0][$attr] = strtoupper($tagAttrib[0][$attr]);
}
if ($params['range']) {
if ($params['range']) {
if (isset($params['range'][1])) {
if (isset($params['range'][1])) {
$tagAttrib[0][$attr]=t3lib_div::intInRange($tagAttrib[0][$attr],intval($params['range'][0]),intval($params['range'][1]));
$tagAttrib[0][$attr] = t3lib_div::intInRange($tagAttrib[0][$attr], intval($params['range'][0]), intval($params['range'][1]));
} else {
$tagAttrib[0][$attr]=t3lib_div::intInRange($tagAttrib[0][$attr],intval($params['range'][0]));
$tagAttrib[0][$attr] = t3lib_div::intInRange($tagAttrib[0][$attr], intval($params['range'][0]));
}
}
if (is_array($params['list'])) {
......
$tagAttrib[0][$attr] = '';
}
} else {
if (!in_array($this->caseShift($tagAttrib[0][$attr],$params['casesensitiveComp']),$this->caseShift($params['list'],$params['casesensitiveComp'],$tagName))) {
if (!in_array($this->caseShift($tagAttrib[0][$attr], $params['casesensitiveComp']), $this->caseShift($params['list'], $params['casesensitiveComp'], $tagName))) {
$tagAttrib[0][$attr]=$params['list'][0];
$tagAttrib[0][$attr] = $params['list'][0];
}
}
}
if (($params['removeIfFalse'] && $params['removeIfFalse']!='blank' && !$tagAttrib[0][$attr]) || ($params['removeIfFalse']=='blank' && !strcmp($tagAttrib[0][$attr],''))) {
if (($params['removeIfFalse'] && $params['removeIfFalse'] != 'blank' && !$tagAttrib[0][$attr]) || ($params['removeIfFalse'] == 'blank' && !strcmp($tagAttrib[0][$attr], ''))) {
unset($tagAttrib[0][$attr]);
}
if (strcmp($params['removeIfEquals'],'') && !strcmp($this->caseShift($tagAttrib[0][$attr],$params['casesensitiveComp']),$this->caseShift($params['removeIfEquals'],$params['casesensitiveComp']))) {
if (strcmp($params['removeIfEquals'], '') && !strcmp($this->caseShift($tagAttrib[0][$attr], $params['casesensitiveComp']), $this->caseShift($params['removeIfEquals'], $params['casesensitiveComp']))) {
unset($tagAttrib[0][$attr]);
}
if ($params['prefixLocalAnchors']) {
if ($params['prefixLocalAnchors']) {
if (substr($tagAttrib[0][$attr],0,1)=='#') {
if (substr($tagAttrib[0][$attr], 0, 1) == '#') {
$prefix = t3lib_div::getIndpEnv('TYPO3_REQUEST_URL');
$tagAttrib[0][$attr] = $prefix.$tagAttrib[0][$attr];
$tagAttrib[0][$attr] = $prefix . $tagAttrib[0][$attr];
if ($params['prefixLocalAnchors']==2 && t3lib_div::isFirstPartOfStr($prefix,t3lib_div::getIndpEnv('TYPO3_SITE_URL'))) {
if ($params['prefixLocalAnchors'] == 2 && t3lib_div::isFirstPartOfStr($prefix, t3lib_div::getIndpEnv('TYPO3_SITE_URL'))) {
$tagAttrib[0][$attr] = substr($tagAttrib[0][$attr],strlen(t3lib_div::getIndpEnv('TYPO3_SITE_URL')));
$tagAttrib[0][$attr] = substr($tagAttrib[0][$attr], strlen(t3lib_div::getIndpEnv('TYPO3_SITE_URL')));
}
}
}
if ($params['prefixRelPathWith']) {
if ($params['prefixRelPathWith']) {
$urlParts = parse_url($tagAttrib[0][$attr]);
if (!$urlParts['scheme'] && substr($urlParts['path'],0,1)!='/') { // If it is NOT an absolute URL (by http: or starting "/")
if (!$urlParts['scheme'] && substr($urlParts['path'], 0, 1) != '/') { // If it is NOT an absolute URL (by http: or starting "/")
$tagAttrib[0][$attr] = $params['prefixRelPathWith'].$tagAttrib[0][$attr];
$tagAttrib[0][$attr] = $params['prefixRelPathWith'] . $tagAttrib[0][$attr];
}
}
if ($params['userFunc']) {
if ($params['userFunc']) {
$tagAttrib[0][$attr] = t3lib_div::callUserFunction($params['userFunc'],$tagAttrib[0][$attr],$this);
$tagAttrib[0][$attr] = t3lib_div::callUserFunction($params['userFunc'], $tagAttrib[0][$attr], $this);
}
}
}
$tagParts[1]=$this->compileTagAttribs($tagAttrib[0],$tagAttrib[1]);
$tagParts[1] = $this->compileTagAttribs($tagAttrib[0], $tagAttrib[1]);
}
} else { // If endTag, remove any possible attributes:
} else { // If endTag, remove any possible attributes:
$tagParts[1]='';
$tagParts[1] = '';
}
// Protecting the tag by converting < and > to &lt; and &gt; ??
if ($tags[$tagName]['protect']) {
if ($tags[$tagName]['protect']) {
$lt = '&lt;'; $gt = '&gt;';
$lt = '&lt;';
$gt = '&gt;';
} else {
$lt = '<'; $gt = '>';
$lt = '<';
$gt = '>';
}
// Remapping tag name?
if ($tags[$tagName]['remap']) $tagParts[0] = $tags[$tagName]['remap'];
if ($tags[$tagName]['remap']) {
$tagParts[0] = $tags[$tagName]['remap'];
}
// rmTagIfNoAttrib
if ($endTag || trim($tagParts[1]) || !$tags[$tagName]['rmTagIfNoAttrib']) {
if ($endTag || trim($tagParts[1]) || !$tags[$tagName]['rmTagIfNoAttrib']) {
$setTag = !$tags[$tagName]['rmTagIfNoAttrib'];
if ($tags[$tagName]['nesting']) {
if ($tags[$tagName]['nesting']) {
if (!is_array($tagRegister[$tagName])) $tagRegister[$tagName]=array();
if (!is_array($tagRegister[$tagName])) {
$tagRegister[$tagName] = array();
}
if ($endTag) {
if ($endTag) {
/* if ($tags[$tagName]['nesting']=='global') {
$lastEl = end($tagStack);
$correctTag = !strcmp($tagName,$lastEl);
} else $correctTag=1;
*/
/* if ($tags[$tagName]['nesting']=='global') {
$lastEl = end($tagStack);
$correctTag = !strcmp($tagName,$lastEl);
} else $correctTag=1;
*/
$correctTag=1;
$correctTag = 1;
if ($tags[$tagName]['nesting']=='global') {
if ($tags[$tagName]['nesting'] == 'global') {
$lastEl = end($tagStack);
if (strcmp($tagName,$lastEl)) {
if (strcmp($tagName, $lastEl)) {
if (in_array($tagName,$tagStack)) {
if (in_array($tagName, $tagStack)) {
while(count($tagStack) && strcmp($tagName,$lastEl)) {
while (count($tagStack) && strcmp($tagName, $lastEl)) {
$elPos = end($tagRegister[$lastEl]);
unset($newContent[$elPos]);
......
$lastEl = end($tagStack);
}
} else {
$correctTag=0; // In this case the
$correctTag = 0; // In this case the
}
}
}
if (!count($tagRegister[$tagName]) || !$correctTag) {
if (!count($tagRegister[$tagName]) || !$correctTag) {
$setTag=0;
$setTag = 0;
} else {
array_pop($tagRegister[$tagName]);
if ($tags[$tagName]['nesting']=='global') {array_pop($tagStack);}
if ($tags[$tagName]['nesting'] == 'global') {
array_pop($tagStack);
}
}
}
} else {
array_push($tagRegister[$tagName],$c);
array_push($tagRegister[$tagName], $c);
if ($tags[$tagName]['nesting']=='global') {array_push($tagStack,$tagName);}
if ($tags[$tagName]['nesting'] == 'global') {
array_push($tagStack, $tagName);
}
}
}
}
}
if ($setTag) {
if ($setTag) {
// Setting the tag
$newContent[$c++]=$this->processTag($lt.($endTag?'/':'').trim($tagParts[0].' '.$tagParts[1]).$gt,$addConfig,$endTag,$lt=='&lt;');
$newContent[$c++] = $this->processTag($lt . ($endTag ? '/' : '') . trim($tagParts[0] . ' ' . $tagParts[1]) . $gt, $addConfig, $endTag, $lt == '&lt;');
}
}
} else {
$newContent[$c++]=$this->processTag('<'.($endTag?'/':'').$tagContent.'>',$addConfig,$endTag);
$newContent[$c++] = $this->processTag('<' . ($endTag ? '/' : '') . $tagContent . '>', $addConfig, $endTag);
}
} elseif ($keepAll) { // This is if the tag was not defined in the array for processing:
} elseif ($keepAll) { // This is if the tag was not defined in the array for processing:
if (!strcmp($keepAll,'protect')) {
if (!strcmp($keepAll, 'protect')) {
$lt = '&lt;'; $gt = '&gt;';
$lt = '&lt;';
$gt = '&gt;';
} else {
$lt = '<'; $gt = '>';
$lt = '<';
$gt = '>';
}
$newContent[$c++]=$this->processTag($lt.($endTag?'/':'').$tagContent.$gt,$addConfig,$endTag,$lt=='&lt;');
$newContent[$c++] = $this->processTag($lt . ($endTag ? '/' : '') . $tagContent . $gt, $addConfig, $endTag, $lt == '&lt;');
}
$newContent[$c++]=$this->processContent(substr($tok,$tagEnd+1),$hSC,$addConfig);
$newContent[$c++] = $this->processContent(substr($tok, $tagEnd + 1), $hSC, $addConfig);
} else {
$newContent[$c++]=$this->processContent('<'.$tok,$hSC,$addConfig); // There were not end-bracket, so no tag...
$newContent[$c++] = $this->processContent('<' . $tok, $hSC, $addConfig); // There were not end-bracket, so no tag...
}
} else {
$newContent[$c++]=$this->processContent(($skipTag ? '' : '<') . $tok, $hSC, $addConfig); // It was not a tag anyways
$newContent[$c++] = $this->processContent(($skipTag ? '' : '<') . $tok, $hSC, $addConfig); // It was not a tag anyways
$skipTag = false;
$skipTag = FALSE;
}
}
// Unsetting tags:
foreach ($tagRegister as $tag => $positions) {
foreach ($tagRegister as $tag => $positions) {
foreach ($positions as $pKey) {
foreach ($positions as $pKey) {
unset($newContent[$pKey]);
}
}
return implode('',$newContent);
return implode('', $newContent);
}
/**
......
* @param integer Direction: forth ($dir=1, dir=2 for preserving entities) AND back ($dir=-1)
* @return string Output value
*/
function bidir_htmlspecialchars($value,$dir) {
function bidir_htmlspecialchars($value, $dir) {
if ($dir==1) {
if ($dir == 1) {
$value = htmlspecialchars($value);
} elseif ($dir==2) {
} elseif ($dir == 2) {
$value = t3lib_div::deHSCentities(htmlspecialchars($value));
} elseif ($dir==-1) {
} elseif ($dir == -1) {
$value = str_replace('&gt;','>',$value);
$value = str_replace('&gt;', '>', $value);
$value = str_replace('&lt;','<',$value);
$value = str_replace('&lt;', '<', $value);
$value = str_replace('&quot;','"',$value);
$value = str_replace('&quot;', '"', $value);
$value = str_replace('&amp;','&',$value);
$value = str_replace('&amp;', '&', $value);
}
return $value;
}
......
* @param string Suffix string (put after the resource).
* @return string Processed HTML content
*/
function prefixResourcePath($main_prefix,$content,$alternatives=array(),$suffix='') {
function prefixResourcePath($main_prefix, $content, $alternatives = array(), $suffix = '') {
$parts = $this->splitTags('embed,td,table,body,img,input,form,link,script,a,param',$content);
$parts = $this->splitTags('embed,td,table,body,img,input,form,link,script,a,param', $content);
foreach ($parts as $k => $v) {
foreach ($parts as $k => $v) {
if ($k%2) {
if ($k % 2) {
$params = $this->get_tag_attributes($v);
$tagEnd = substr($v,-2)=='/>' ? ' />' : '>'; // Detect tag-ending so that it is re-applied correctly.
$tagEnd = substr($v, -2) == '/>' ? ' />' : '>'; // Detect tag-ending so that it is re-applied correctly.
$firstTagName = $this->getFirstTagName($v); // The 'name' of the first tag
$firstTagName = $this->getFirstTagName($v); // The 'name' of the first tag
$somethingDone=0;
$somethingDone = 0;
$prefix = isset($alternatives[strtoupper($firstTagName)]) ? $alternatives[strtoupper($firstTagName)] : $main_prefix;
switch(strtolower($firstTagName)) {
switch (strtolower($firstTagName)) {
// background - attribute:
case 'td':
case 'body':
case 'table':
$src = $params[0]['background'];
if ($src) {
if ($src) {
$params[0]['background'] = $this->prefixRelPath($prefix,$params[0]['background'],$suffix);
$params[0]['background'] = $this->prefixRelPath($prefix, $params[0]['background'], $suffix);
$somethingDone=1;
$somethingDone = 1;
}
break;
// src attribute
......
case 'script':
case 'embed':
$src = $params[0]['src'];
if ($src) {
if ($src) {
$params[0]['src'] = $this->prefixRelPath($prefix,$params[0]['src'],$suffix);
$params[0]['src'] = $this->prefixRelPath($prefix, $params[0]['src'], $suffix);
$somethingDone=1;
$somethingDone = 1;
}
break;
case 'link':
case 'a':
$src = $params[0]['href'];
if ($src) {
if ($src) {
$params[0]['href'] = $this->prefixRelPath($prefix,$params[0]['href'],$suffix);
$params[0]['href'] = $this->prefixRelPath($prefix, $params[0]['href'], $suffix);
$somethingDone=1;
$somethingDone = 1;
}
break;
// action attribute
case 'form':
$src = $params[0]['action'];
if ($src) {
if ($src) {
$params[0]['action'] = $this->prefixRelPath($prefix,$params[0]['action'],$suffix);
$params[0]['action'] = $this->prefixRelPath($prefix, $params[0]['action'], $suffix);
$somethingDone=1;
$somethingDone = 1;
}
break;
// value attribute
......
}
break;
}
if ($somethingDone) {
if ($somethingDone) {
$tagParts = preg_split('/\s+/s',$v,2);
$tagParts = preg_split('/\s+/s', $v, 2);
$tagParts[1]=$this->compileTagAttribs($params[0],$params[1]);
$tagParts[1] = $this->compileTagAttribs($params[0], $params[1]);
$parts[$k] = '<'.trim(strtolower($firstTagName).' '.$tagParts[1]).$tagEnd;
$parts[$k] = '<' . trim(strtolower($firstTagName) . ' ' . $tagParts[1]) . $tagEnd;
}
}
}
$content = implode('',$parts);
$content = implode('', $parts);
// Fix <style> section:
$prefix = isset($alternatives['style']) ? $alternatives['style'] : $main_prefix;
if (strlen($prefix)) {
if (strlen($prefix)) {
$parts = $this->splitIntoBlock('style',$content);
$parts = $this->splitIntoBlock('style', $content);
foreach($parts as $k => $v) {
foreach ($parts as $k => $v) {
if ($k%2) {
if ($k % 2) {
$parts[$k] = preg_replace('/(url[[:space:]]*\([[:space:]]*["\']?)([^"\')]*)(["\']?[[:space:]]*\))/i','\1'.$prefix.'\2'.$suffix.'\3',$parts[$k]);
$parts[$k] = preg_replace('/(url[[:space:]]*\([[:space:]]*["\']?)([^"\')]*)(["\']?[[:space:]]*\))/i', '\1' . $prefix . '\2' . $suffix . '\3', $parts[$k]);
}
}
$content = implode('',$parts);
$content = implode('', $parts);
}
return $content;
......
* @param boolean If set, keep "color" attribute
* @return string Processed HTML content
*/
function cleanFontTags($value,$keepFace=0,$keepSize=0,$keepColor=0) {
function cleanFontTags($value, $keepFace = 0, $keepSize = 0, $keepColor = 0) {
$fontSplit = $this->splitIntoBlock('font',$value); // ,1 ?? - could probably be more stable if splitTags() was used since this depends on end-tags being properly set!
$fontSplit = $this->splitIntoBlock('font', $value); // ,1 ?? - could probably be more stable if splitTags() was used since this depends on end-tags being properly set!
foreach ($fontSplit as $k => $v) {
foreach ($fontSplit as $k => $v) {
if ($k%2) { // font:
if ($k % 2) { // font:
$attribArray=$this->get_tag_attributes_classic($this->getFirstTag($v));
$attribArray = $this->get_tag_attributes_classic($this->getFirstTag($v));
$newAttribs=array();
$newAttribs = array();
if ($keepFace && $attribArray['face']) $newAttribs[]='face="'.$attribArray['face'].'"';
if ($keepSize && $attribArray['size']) $newAttribs[]='size="'.$attribArray['size'].'"';
if ($keepColor && $attribArray['color']) $newAttribs[]='color="'.$attribArray['color'].'"';
if ($keepFace && $attribArray['face']) {
$newAttribs[] = 'face="' . $attribArray['face'] . '"';
}
if ($keepSize && $attribArray['size']) {
$newAttribs[] = 'size="' . $attribArray['size'] . '"';
}
if ($keepColor && $attribArray['color']) {
$newAttribs[] = 'color="' . $attribArray['color'] . '"';
}
$innerContent = $this->cleanFontTags($this->removeFirstAndLastTag($v),$keepFace,$keepSize,$keepColor);
$innerContent = $this->cleanFontTags($this->removeFirstAndLastTag($v), $keepFace, $keepSize, $keepColor);
if (count($newAttribs)) {
if (count($newAttribs)) {
$fontSplit[$k]='<font '.implode(' ',$newAttribs).'>'.$innerContent.'</font>';
$fontSplit[$k] = '<font ' . implode(' ', $newAttribs) . '>' . $innerContent . '</font>';
} else {
$fontSplit[$k]=$innerContent;
$fontSplit[$k] = $innerContent;
}
}
}
return implode('',$fontSplit);
return implode('', $fontSplit);
}
/**
......
* @param string Alternative less-than char to replace with (replace regex string)
* @return string Processed HTML content
*/
function mapTags($value,$tags=array(),$ltChar='<',$ltChar2='<') {
function mapTags($value, $tags = array(), $ltChar = '<', $ltChar2 = '<') {
foreach($tags as $from => $to) {
foreach ($tags as $from => $to) {
$value = preg_replace('/'.preg_quote($ltChar).'(\/)?'.$from.'\s([^\>])*(\/)?\>/', $ltChar2.'$1'.$to.' $2$3>', $value);
$value = preg_replace('/' . preg_quote($ltChar) . '(\/)?' . $from . '\s([^\>])*(\/)?\>/', $ltChar2 . '$1' . $to . ' $2$3>', $value);
}
return $value;
}
......
* @param string Tag list, separated by comma. Lowercase!
* @return string Processed HTML content
*/
function unprotectTags($content,$tagList='') {
function unprotectTags($content, $tagList = '') {
$tagsArray = t3lib_div::trimExplode(',',$tagList,1);
$tagsArray = t3lib_div::trimExplode(',', $tagList, 1);
$contentParts = explode('&lt;',$content);
$contentParts = explode('&lt;', $content);
next($contentParts); // bypass the first
next($contentParts); // bypass the first
while(list($k,$tok)=each($contentParts)) {
while (list($k, $tok) = each($contentParts)) {
$firstChar = substr($tok,0,1);
$firstChar = substr($tok, 0, 1);
if (strcmp(trim($firstChar),'')) {
if (strcmp(trim($firstChar), '')) {
$subparts = explode('&gt;',$tok,2);
$subparts = explode('&gt;', $tok, 2);
$tagEnd = strlen($subparts[0]);
if (strlen($tok)!=$tagEnd) {
if (strlen($tok) != $tagEnd) {
$endTag = $firstChar=='/' ? 1 : 0;
$endTag = $firstChar == '/' ? 1 : 0;
$tagContent = substr($tok,$endTag,$tagEnd-$endTag);
$tagContent = substr($tok, $endTag, $tagEnd - $endTag);
$tagParts = preg_split('/\s+/s',$tagContent,2);
$tagParts = preg_split('/\s+/s', $tagContent, 2);
$tagName = strtolower($tagParts[0]);
if (!strcmp($tagList,'') || in_array($tagName,$tagsArray)) {
if (!strcmp($tagList, '') || in_array($tagName, $tagsArray)) {
$contentParts[$k] = '<'.$subparts[0].'>'.$subparts[1];
$contentParts[$k] = '<' . $subparts[0] . '>' . $subparts[1];
} else $contentParts[$k] = '&lt;'.$tok;
} else $contentParts[$k] = '&lt;'.$tok;
} else $contentParts[$k] = '&lt;'.$tok;
} else {
$contentParts[$k] = '&lt;' . $tok;
}
}
} else {
$contentParts[$k] = '&lt;' . $tok;
}
} else {
$contentParts[$k] = '&lt;' . $tok;
}
}
return implode('',$contentParts);
return implode('', $contentParts);
}
/**
......
* @return string Output value
* @ignore
*/
function stripTagsExcept($value,$tagList) {
function stripTagsExcept($value, $tagList) {
$tags=t3lib_div::trimExplode(',',$tagList,1);
$tags = t3lib_div::trimExplode(',', $tagList, 1);
$forthArr=array();
$forthArr = array();
$backArr=array();
$backArr = array();
foreach ($tags as $theTag) {
foreach ($tags as $theTag) {
$forthArr[$theTag]=md5($theTag);
$forthArr[$theTag] = md5($theTag);
$backArr[md5($theTag)]=$theTag;
$backArr[md5($theTag)] = $theTag;
}
$value = $this->mapTags($value,$forthArr,'<','_');
$value = $this->mapTags($value, $forthArr, '<', '_');
$value=strip_tags($value);
$value = strip_tags($value);
$value = $this->mapTags($value,$backArr,'_','<');
$value = $this->mapTags($value, $backArr, '_', '<');
return $value;
}
......
* @return string Output string, processed
* @access private
*/
function caseShift($str,$flag,$cacheKey='') {
function caseShift($str, $flag, $cacheKey = '') {
$cacheKey .= $flag?1:0;
$cacheKey .= $flag ? 1 : 0;
if (is_array($str)) {
if (is_array($str)) {
if (!$cacheKey || !isset($this->caseShift_cache[$cacheKey])) {
if (!$cacheKey || !isset($this->caseShift_cache[$cacheKey])) {
reset($str);
foreach ($str as $k => $v) {
foreach ($str as $k => $v) {
if (!$flag) {
if (!$flag) {
$str[$k] = strtoupper($v);
}
}
if ($cacheKey) $this->caseShift_cache[$cacheKey]=$str;
if ($cacheKey) {
$this->caseShift_cache[$cacheKey] = $str;
}
} else {
$str = $this->caseShift_cache[$cacheKey];
}
} elseif (!$flag) { $str = strtoupper($str); }
} elseif (!$flag) {
$str = strtoupper($str);
}
return $str;
}
......
* @return string Imploded attributes, eg: 'attribute="value" attrib2="value2"'
* @access private
*/
function compileTagAttribs($tagAttrib,$meta=array(), $xhtmlClean=0) {
function compileTagAttribs($tagAttrib, $meta = array(), $xhtmlClean = 0) {
$accu=array();
$accu = array();
foreach ($tagAttrib as $k =>$v) {
foreach ($tagAttrib as $k => $v) {
if ($xhtmlClean) {
if ($xhtmlClean) {
$attr=strtolower($k);
$attr = strtolower($k);
if (strcmp($v,'') || isset($meta[$k]['dashType'])) {
if (strcmp($v, '') || isset($meta[$k]['dashType'])) {
$attr.='="'.htmlspecialchars($v).'"';
$attr .= '="' . htmlspecialchars($v) . '"';
}
} else {
$attr=$meta[$k]['origTag']?$meta[$k]['origTag']:$k;
$attr = $meta[$k]['origTag'] ? $meta[$k]['origTag'] : $k;
if (strcmp($v,'') || isset($meta[$k]['dashType'])) {
if (strcmp($v, '') || isset($meta[$k]['dashType'])) {
$dash=$meta[$k]['dashType']?$meta[$k]['dashType']:(t3lib_div::testInt($v)?'':'"');
$dash = $meta[$k]['dashType'] ? $meta[$k]['dashType'] : (t3lib_div::testInt($v) ? '' : '"');
$attr.='='.$dash.$v.$dash;
$attr .= '=' . $dash . $v . $dash;
}
}
$accu[]=$attr;
$accu[] = $attr;
}
return implode(' ',$accu);
return implode(' ', $accu);
}
/**
......
* @return array
* @access private
*/
function get_tag_attributes_classic($tag,$deHSC=0) {
function get_tag_attributes_classic($tag, $deHSC = 0) {
$attr=$this->get_tag_attributes($tag,$deHSC);
$attr = $this->get_tag_attributes($tag, $deHSC);
return is_array($attr[0])?$attr[0]:array();
return is_array($attr[0]) ? $attr[0] : array();
}
/**
......
* @param string Indent character/string
* @return string Indented code (typ. HTML)
*/
function indentLines($content, $number=1, $indentChar=TAB) {
function indentLines($content, $number = 1, $indentChar = TAB) {
$preTab = str_pad('', $number*strlen($indentChar), $indentChar);
$preTab = str_pad('', $number * strlen($indentChar), $indentChar);
$lines = explode(LF,str_replace(CR,'',$content));
$lines = explode(LF, str_replace(CR, '', $content));
foreach ($lines as $k => $v) {
foreach ($lines as $k => $v) {
$lines[$k] = $preTab.$v;
$lines[$k] = $preTab . $v;
}
return implode(LF, $lines);
}
......
* @return array
* @access private
*/
function HTMLparserConfig($TSconfig,$keepTags=array()) {
function HTMLparserConfig($TSconfig, $keepTags = array()) {
// Allow tags (base list, merged with incoming array)
$alTags = array_flip(t3lib_div::trimExplode(',',strtolower($TSconfig['allowTags']),1));
$alTags = array_flip(t3lib_div::trimExplode(',', strtolower($TSconfig['allowTags']), 1));
$keepTags = array_merge($alTags,$keepTags);
$keepTags = array_merge($alTags, $keepTags);
// Set config properties.
if (is_array($TSconfig['tags.'])) {
... This diff was truncated because it exceeds the maximum size that can be displayed.
(42-42/93)