Merge branch 'master' of https://github.com/manuwhat/strip-tags

manuwhat · Jun 23, 2019 · 7825575 · 7825575
2 parents 09a0ce1 + 0aae3bf
commit 7825575
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 41 deletions.
diff --git a/htmlstriptestinBrowser.php b/htmlstriptestinBrowser.php
@@ -2,7 +2,7 @@
 
 
 $DIR=__DIR__.DIRECTORY_SEPARATOR.'src'.DIRECTORY_SEPARATOR;
-foreach (array('DOMNodeRecursiveIterator','beforeStrip','prepareStrip','htmlStripHelper','htmlStrip') as $file) {
+foreach (array('DOMNodeRecursiveIterator', 'beforeStrip', 'prepareStrip', 'htmlStripHelper', 'htmlStrip') as $file) {
     require_once($DIR.$file.'.php');
 }
 
@@ -11,36 +11,17 @@
 $x='<script type="text/javascript" async="" src="./Transitioning%20from%20Data%20Developer%20to%20Data%20Scientist%20-%20Statistics%20for%20Data%20Science_files/f.txt"></script>';
 $data='aaaaa<?php echo here ; ?><!doctype><html><head>'.$x.'</head><!-- a comment --> <body>       <?php echo here ; ?><br><br> <h2 onmousedown="alert(\'keke\');">u</h2><p></p><h2>a</h2></body></html>b2b2 ';
 
-$hstrip=new htmlStrip($data, 'replace', array('<h2>',false));
-var_dump($hstrip->go()===strip_tags($data, '<h2>'));//true
+$hstrip=new htmlStrip($data, 'replace', array('<h2>', false));
+var_dump($hstrip->go()===strip_tags($data, '<h2>')); //true
 
 
 $hstrip=new htmlStrip($data);
-var_dump($hstrip->go()===strip_tags($data));//true
-
-$hstrip=new htmlStrip($data, 'replace', array('',true), array('src',true));
-var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), 'src'));//false
-
-$hstrip=new htmlStrip($data, 'replace', array('',true), array('src',false));
-var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), 'type'));//false
-var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), 'src'));//true;
-$data=$html = "
-<html>
-  \r\n\t
-  <body>
-    <ul style=''>
-      <li style='display: inline;' class='foo'>
-        \xc3\xa0
-      </li>
-      <li class='foo' style='display: inline;'>
-        \xc3\xa1
-      </li>
-    </ul>
-  </body>
-  \r\n\t
-</html>
-";
-$hstrip=new htmlStrip(mb_convert_encoding($data, 'HTML-ENTITIES', 'UTF-8'), 'replace', array('',true), array('',true),);
+var_dump($hstrip->go()===strip_tags($data)); //true
 
+$hstrip=new htmlStrip($data, 'replace', array('', true), array('src', true));
+var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), 'src')); //false
 
 
+$hstrip=new htmlStrip($data, 'replace', array('',true), array('src',false));
+var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), ' type'));//false
+var_dump((bool)stripos($hstrip->go(htmlStrip::ATTRIBUTES), 'src'));//true;
diff --git a/src/beforeStrip.php b/src/beforeStrip.php
@@ -24,11 +24,11 @@ public function __construct($html)
             array($this->doctype, $this->html_tag, '</html>', $this->head, '</head>', $this->body, '</body>'),
             array('<doctypetag'.substr($this->doctype, 9), '<htmltag '.substr($this->html_tag, 5), '</htmltag>', '<headtag '.substr($this->head, 5), '</headtag>', '<bodytag '.substr($this->body, 5), '</bodytag>'),
             $html
-                              ).'</doctypetag></div>';
+                                ).'</doctypetag></div>';
 
         $preprocessed=token_get_all($html);
 
-        $HTML=array_filter($preprocessed, function ($v) {
+        $HTML=array_filter($preprocessed, function($v) {
             return is_array($v)&&$v[0]===T_INLINE_HTML;
         });
         $PHP=array_diff_key($preprocessed, $HTML);

diff --git a/src/htmlStripHelper.php b/src/htmlStripHelper.php
@@ -374,12 +374,14 @@ abstract class htmlstripHelper
   '<video>' => 1,
   '<wbr>' => 1,
 );
+
 	protected function loadHTML($html)
     {   
-	    if (!strlen($html)) {
+        if (!strlen($html)) {
             throw new \InvalidArgumentException("Empty string given");
         }
         $xml = new \DOMDocument();
+		//Suppress warnings: proper error handling is beyond scope of example
         libxml_use_internal_errors(true);
 
         $true=$xml->loadHTML($html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
@@ -393,7 +395,7 @@ protected function handleTags($notAllowedTags, $callback, $callback1)
         if (!is_array($notAllowedTags)) {
             return false;
         }
-        if (count($notAllowedTags) !== 2) {
+        if (count($notAllowedTags)!==2) {
             return false;
         }
         $notAllowedTags=array_values($notAllowedTags);
@@ -404,7 +406,7 @@ protected function handleTags($notAllowedTags, $callback, $callback1)
         }
         if (is_array($notAllowedTags)) {
             $notAllowedTags=array_filter(array_map($callback, $notAllowedTags), $callback1);
-            $this->allowedTags=!$keep?array_fill_keys($notAllowedTags, 1):array_diff_key(self::$tags, array_flip($notAllowedTags));
+            $this->allowedTags=!$keep ?array_fill_keys($notAllowedTags, 1) : array_diff_key(self::$tags, array_flip($notAllowedTags));
         } else {
             return false;
         }
@@ -416,17 +418,17 @@ protected function handleAttributes($notAllowedAttributes, $callback, $callback2
         if (!is_array($notAllowedAttributes)) {
             return false;
         }
-        if (count($notAllowedAttributes) !== 2) {
+        if (count($notAllowedAttributes)!==2) {
             return false;
         }
         $keep=(bool)$notAllowedAttributes[1];
         $notAllowedAttributes=$notAllowedAttributes[0];
         if (is_string($notAllowedAttributes)) {
-            $notAllowedAttributes= explode(',', $notAllowedAttributes);
+            $notAllowedAttributes=explode(',', $notAllowedAttributes);
         }
         if (is_array($notAllowedAttributes)) {
             $notAllowedAttributes=array_filter(array_map($callback, $notAllowedAttributes), $callback2);
-            $this->allowedAttributes=!$keep?array_fill_keys($notAllowedAttributes, 1):array_diff_key(self::$attributes, array_flip($notAllowedAttributes));
+            $this->allowedAttributes=!$keep ?array_fill_keys($notAllowedAttributes, 1) : array_diff_key(self::$attributes, array_flip($notAllowedAttributes));
         } else {
             return false;
         }
@@ -445,8 +447,8 @@ protected static function handlePhp($is_php, $domDoc, &$allowed_tags)
     protected static function handleMainHtmlTags(&$result, &$allowed_tags)
     {
         $result=str_replace(
-            array('<doctypetag','</doctypetag>','<headtag' ,'</headtag','<htmltag','</htmltag','<bodytag','</bodytag'),
-            array('<!doctype','','<head','</head','<html','</html','<body','</body'),
+            array('<doctypetag', '</doctypetag>', '<headtag', '</headtag', '<htmltag', '</htmltag', '<bodytag', '</bodytag'),
+            array('<!doctype', '', '<head', '</head', '<html', '</html', '<body', '</body'),
             $result
                         );
         if (!isset($allowed_tags['<doctypetag>'])) {
@@ -457,7 +459,7 @@ protected static function handleMainHtmlTags(&$result, &$allowed_tags)
     protected static function handleComments($domDoc, &$allowed_tags)
     {
         if (!isset($allowed_tags['<!-- -->'])) {
-            $xpath = new \DOMXPath($domDoc);
+            $xpath=new \DOMXPath($domDoc);
             $DomComments=$xpath->query("//comment()");
             foreach ($DomComments as $DomComment) {
                 $DomComment->parentNode->removeChild($DomComment);

diff --git a/src/prepareStrip.php b/src/prepareStrip.php
@@ -26,13 +26,13 @@ public function getPrepared()
 
     public function prepareHtml()
     {
-        return  array_map(function ($v) {
+        return  array_map(function($v) {
             return is_array($v) ? $v[1] : $v;
         }, $this->prepocessed->getHTML());
     }
     public function preparePhp()
     {
-        return array_map(function ($v) {
+        return array_map(function($v) {
             return is_array($v)&&($v[0]===T_OPEN_TAG||$v[0]===T_CLOSE_TAG) ? ($v[0]===T_OPEN_TAG ? '<php>' : '</php>') : (is_array($v) ? $v[1] : $v);
         }, $this->prepocessed->getPHP());
     }