Changeset ca0cd05 in github

Timestamp:

Nov 28, 2011 3:10:44 AM (19 months ago)

Author:

alecpl <alec@…>

Branches:

master, HEAD, courier-fix, dev-browser-capabilities, pdo, release-0.8

Children:

6e0fded

Parents:

79db330

Message:

• Fix handling HTML entities when converting HTML to text (#1488212)

Files:

• CHANGELOG (modified) (1 diff)
• program/js/app.js (modified) (1 diff)
• program/lib/html2text.php (modified) (11 diffs)

CHANGELOG

@@ -2 +2 @@
 ===========================
 
+- Fix handling HTML entities when converting HTML to text (#1488212)
 - Fix fit_string_to_size() renders browser and ui unresponsive (#1488207)
 - Fix handling of invalid characters in request (#1488124)

program/js/app.js

@@ -5766 +5766 @@
   };
 
-  this.plain2html = function(plainText, id)
+  this.plain2html = function(plain, id)
   {
     var lock = this.set_busy(true, 'converting');
-    $('#'+id).val(plainText ? '<pre>'+plainText+'</pre>' : '');
+
+    plain = plain.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
+    $('#'+id).val(plain ? '<pre>'+plain+'</pre>' : '');
+
     this.set_busy(false, null, lock);
   };

program/lib/html2text.php

@@ -146 +146 @@
         "/\r/",                                  // Non-legal carriage return
         "/[\n\t]+/",                             // Newlines and tabs
-        '/[ ]{2,}/',                             // Runs of spaces, pre-handling
         '/<script[^>]*>.*?<\/script>/i',         // <script>s -- which strip_tags supposedly has problems with
         '/<style[^>]*>.*?<\/style>/i',           // <style>s -- which strip_tags supposedly has problems with
@@ -162 +161 @@
         '/(<tr[^>]*>|<\/tr>)/i',                 // <tr> and </tr>
         '/<td[^>]*>(.*?)<\/td>/i',               // <td> and </td>
+    );
+
+    /**
+     *  List of pattern replacements corresponding to patterns searched.
+     *
+     *  @var array $replace
+     *  @access public
+     *  @see $search
+     */
+    var $replace = array(
+        '',                                     // Non-legal carriage return
+        ' ',                                    // Newlines and tabs
+        '',                                     // <script>s -- which strip_tags supposedly has problems with
+        '',                                     // <style>s -- which strip_tags supposedly has problems with
+        "\n\n",                                 // <P>
+        "\n",                                   // <br>
+        '_\\1_',                                // <i>
+        '_\\1_',                                // <em>
+        "\n\n",                                 // <ul> and </ul>
+        "\n\n",                                 // <ol> and </ol>
+        "\t* \\1\n",                            // <li> and </li>
+        "\n\t* ",                               // <li>
+        "\n-------------------------\n",        // <hr>
+        "<div>\n",                              // <div>
+        "\n\n",                                 // <table> and </table>
+        "\n",                                   // <tr> and </tr>
+        "\t\t\\1\n",                            // <td> and </td>
+    );
+
+    /**
+     *  List of preg* regular expression patterns to search for,
+     *  used in conjunction with $ent_replace.
+     *
+     *  @var array $ent_search
+     *  @access public
+     *  @see $ent_replace
+     */
+    var $ent_search = array(
         '/&(nbsp|#160);/i',                      // Non-breaking space
         '/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
@@ -177 +214 @@
         '/&(euro|#8364);/i',                     // Euro sign
         '/&(amp|#38);/i',                        // Ampersand: see _converter()
-        '/[ ]{2,}/'                              // Runs of spaces, post-handling
+        '/[ ]{2,}/',                             // Runs of spaces, post-handling
     );
 
@@ -183 +220 @@
      *  List of pattern replacements corresponding to patterns searched.
      *
-     *  @var array $replace
-     *  @access public
-     *  @see $search
-     */
-    var $replace = array(
-        '',                                     // Non-legal carriage return
-        ' ',                                    // Newlines and tabs
-        ' ',                                    // Runs of spaces, pre-handling
-        '',                                     // <script>s -- which strip_tags supposedly has problems with
-        '',                                     // <style>s -- which strip_tags supposedly has problems with
-        "\n\n",                                 // <P>
-        "\n",                                   // <br>
-        '_\\1_',                                // <i>
-        '_\\1_',                                // <em>
-        "\n\n",                                 // <ul> and </ul>
-        "\n\n",                                 // <ol> and </ol>
-        "\t* \\1\n",                            // <li> and </li>
-        "\n\t* ",                               // <li>
-        "\n-------------------------\n",        // <hr>
-        "<div>\n",                              // <div>
-        "\n\n",                                 // <table> and </table>
-        "\n",                                   // <tr> and </tr>
-        "\t\t\\1\n",                            // <td> and </td>
+     *  @var array $ent_replace
+     *  @access public
+     *  @see $ent_search
+     */
+    var $ent_replace = array(
         ' ',                                    // Non-breaking space
         '"',                                    // Double quotes
@@ -220 +239 @@
         'EUR',                                  // Euro sign. € ?
         '|+|amp|+|',                            // Ampersand: see _converter()
-        ' '                                     // Runs of spaces, post-handling
+        ' ',                                    // Runs of spaces, post-handling
     );
 
@@ -304 +323 @@
      */
     var $_link_list = '';
-    
+
     /**
      *  Number of valid links detected in the text, used for plain text
@@ -315 +334 @@
     var $_link_count = 0;
 
-    /** 
-     * Boolean flag, true if a table of link URLs should be listed after the text. 
-     *  
-     * @var boolean $_do_links 
-     * @access private 
-     * @see html2text() 
+    /**
+     * Boolean flag, true if a table of link URLs should be listed after the text.
+     *
+     * @var boolean $_do_links
+     * @access private
+     * @see html2text()
      */
     var $_do_links = true;
- 
+
     /**
      *  Constructor.
@@ -493 +512 @@
         $this->_convert_pre($text);
 
-        // Run our defined search-and-replace
+        // Run our defined tags search-and-replace
         $text = preg_replace($this->search, $this->replace, $text);
+
+        // Run our defined tags search-and-replace with callback
+        $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);
+
+        // Strip any other HTML tags
+        $text = strip_tags($text, $this->allowed_tags);
+
+        // Run our defined entities/characters search-and-replace
+        $text = preg_replace($this->ent_search, $this->ent_replace, $text);
 
         // Replace known html entities
         $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');
-
-        // Run our defined search-and-replace with callback
-        $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);
 
         // Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
@@ -509 +534 @@
         $text = str_replace('|+|amp|+|', '&', $text);
 
-        // Strip any other HTML tags
-        $text = strip_tags($text, $this->allowed_tags);
-
         // Bring down number of empty lines to 2 max
         $text = preg_replace("/\n\s+\n/", "\n\n", $text);
@@ -517 +539 @@
 
         // remove leading empty lines (can be produced by eg. P tag on the beginning)
-        $text = preg_replace('/^\n+/', '', $text);
+        $text = ltrim($text, "\n");
 
         // Wrap the text to a readable format
@@ -545 +567 @@
                 return $display;
 
-            if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' ||
-            substr($link, 0, 7) == 'mailto:'
-        ) {
+            if ( preg_match('!^(https?://|mailto:)!', $link) ) {
             $this->_link_count++;
             $this->_link_list .= '[' . $this->_link_count . "] $link\n";