Upgrade 1-11.38

vendor/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php

@@ -52,14 +52,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
         // attempt to armor stray angled brackets that cannot possibly
         // form tags and thus are probably being used as emoticons
         if ($config->get('Core.AggressivelyFixLt')) {
-            $char = '[^a-z!\/]';
-            $comment = "/<!--(.*?)(-->|\z)/is";
-            $html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html);
-            do {
-                $old = $html;
-                $html = preg_replace("/<($char)/i", '&lt;\\1', $html);
-            } while ($html !== $old);
-            $html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments
+            $html = $this->aggressivelyFixLt($html);
         }
 
         // preprocess html, essential for UTF-8
@@ -288,7 +281,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
      */
     public function callbackUndoCommentSubst($matches)
     {
-        return '<!--' . strtr($matches[1], array('&amp;' => '&', '&lt;' => '<')) . $matches[2];
+        return '<!--' . $this->undoCommentSubstr($matches[1]) . $matches[2];
     }
 
     /**
@@ -299,7 +292,25 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
      */
     public function callbackArmorCommentEntities($matches)
     {
-        return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
+        return '<!--' . $this->armorEntities($matches[1]) . $matches[2];
+    }
+
+    /**
+     * @param string $string
+     * @return string
+     */
+    protected function armorEntities($string)
+    {
+        return str_replace('&', '&amp;', $string);
+    }
+
+    /**
+     * @param string $string
+     * @return string
+     */
+    protected function undoCommentSubstr($string)
+    {
+        return strtr($string, array('&amp;' => '&', '&lt;' => '<'));
     }
 
     /**
@@ -335,6 +346,66 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
         $ret .= '</body></html>';
         return $ret;
     }
+
+    /**
+     * @param string $html
+     * @return string
+     */
+    protected function aggressivelyFixLt($html)
+    {
+        $char = '[^a-z!\/]';
+        $html = $this->manipulateHtmlComments($html, array($this, 'armorEntities'));
+
+        do {
+            $old = $html;
+            $html = preg_replace("/<($char)/i", '&lt;\\1', $html);
+        } while ($html !== $old);
+
+        return $this->manipulateHtmlComments($html, array($this, 'undoCommentSubstr'));
+    }
+
+    /**
+     * Modify HTML comments in the given HTML content using a callback.
+     *
+     * @param string $html
+     * @param callable $callback
+     * @return string
+     */
+    protected function manipulateHtmlComments($html, callable $callback)
+    {
+        $offset = 0;
+        $startTag = '<!--';
+        $endTag = '-->';
+
+        while (($startPos = strpos($html, $startTag, $offset)) !== false) {
+            $startPos += strlen($startTag); // Move past `<!--`
+            $endPos = strpos($html, $endTag, $startPos);
+
+            if ($endPos === false) {
+                // No matching ending comment tag found
+                break;
+            }
+
+            // Extract the original comment content
+            $commentContent = substr($html, $startPos, $endPos - $startPos);
+
+            // Apply the callback to the comment content
+            $newCommentContent = $callback($commentContent);
+
+            // Reconstruct the entire comment with the new content
+            $newComment = $startTag . $newCommentContent . $endTag;
+
+            // Replace the old comment in the HTML content with the new one
+            $html = substr($html, 0, $startPos - strlen($startTag)) .
+                $newComment .
+                substr($html, $endPos + strlen($endTag));
+
+            // Move offset to the end of the new comment for the next iteration
+            $offset = strpos($html, $newComment, $offset) + strlen($newComment);
+        }
+
+        return $html;
+    }
 }
 
 // vim: et sw=4 sts=4

vendor/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/DirectLex.php

@@ -111,7 +111,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 if ($synchronize_interval && // synchronization is on
                     $cursor > 0 && // cursor is further than zero
                     $loops % $synchronize_interval === 0) { // time to synchronize!
-                    $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
+                    $current_line = 1 + substr_count($html, $nl, 0, $cursor);
                 }
             }
 
@@ -139,7 +139,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 );
                 if ($maintain_line_numbers) {
                     $token->rawPosition($current_line, $current_col);
-                    $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
+                    $current_line += substr_count($html, $nl, $cursor, $position_next_lt - $cursor);
                 }
                 $array[] = $token;
                 $cursor = $position_next_lt + 1;
@@ -214,7 +214,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     );
                     if ($maintain_line_numbers) {
                         $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
+                        $current_line += substr_count($html, $nl, $cursor, $strlen_segment);
                     }
                     $array[] = $token;
                     $cursor = $end ? $position_comment_end : $position_comment_end + 3;
@@ -229,7 +229,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     $token = new HTMLPurifier_Token_End($type);
                     if ($maintain_line_numbers) {
                         $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+                        $current_line += substr_count($html, $nl, $cursor, $position_next_gt - $cursor);
                     }
                     $array[] = $token;
                     $inside_tag = false;
@@ -248,7 +248,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     $token = new HTMLPurifier_Token_Text('<');
                     if ($maintain_line_numbers) {
                         $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+                        $current_line += substr_count($html, $nl, $cursor, $position_next_gt - $cursor);
                     }
                     $array[] = $token;
                     $inside_tag = false;
@@ -276,7 +276,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     }
                     if ($maintain_line_numbers) {
                         $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+                        $current_line += substr_count($html, $nl, $cursor, $position_next_gt - $cursor);
                     }
                     $array[] = $token;
                     $inside_tag = false;
@@ -310,7 +310,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 }
                 if ($maintain_line_numbers) {
                     $token->rawPosition($current_line, $current_col);
-                    $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+                    $current_line += substr_count($html, $nl, $cursor, $position_next_gt - $cursor);
                 }
                 $array[] = $token;
                 $cursor = $position_next_gt + 1;
@@ -343,28 +343,6 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
         return $array;
     }
 
-    /**
-     * PHP 5.0.x compatible substr_count that implements offset and length
-     * @param string $haystack
-     * @param string $needle
-     * @param int $offset
-     * @param int $length
-     * @return int
-     */
-    protected function substrCount($haystack, $needle, $offset, $length)
-    {
-        static $oldVersion;
-        if ($oldVersion === null) {
-            $oldVersion = version_compare(PHP_VERSION, '5.1', '<');
-        }
-        if ($oldVersion) {
-            $haystack = substr($haystack, $offset, $length);
-            return substr_count($haystack, $needle);
-        } else {
-            return substr_count($haystack, $needle, $offset, $length);
-        }
-    }
-
     /**
      * Takes the inside of an HTML tag and makes an assoc array of attributes.
      *

vendor/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/PH5P.php

@@ -1223,14 +1223,14 @@ class HTML5
                 'type' => self::COMMENT
             );
 
-            /* Otherwise if the next seven chacacters are a case-insensitive match
+            /* 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 (strtolower($this->character($this->char + 1, 7)) === 'doctype') {
             $this->char += 7;
             $this->state = 'doctype';
 
-            /* Otherwise, is is a parse error. Switch to the bogus comment state.
+            /* Otherwise, it 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 {