Imported Upstream version 0.1~rc1~dfsg

[roundcube.git] / program / lib / html2text.inc

diff --git a/program/lib/html2text.inc b/program/lib/html2text.inc
index 82a254e562fa9a5f36e7681f4fa83c2d957641a9..7d7d9d1f4826a7f9442e56433f06d4e6a43a11db 100644 (file)
--- a/program/lib/html2text.inc
+++ b/program/lib/html2text.inc
@@ -112,7 +112,7 @@ class html2text
         "/[\n\t]+/",                             // Newlines and tabs
         '/<script[^>]*>.*?<\/script>/i',         // <script>s -- which strip_tags supposedly has problems with
         //'/<!-- .* -->/',                         // Comments -- which strip_tags might have problem a with
-        '/<a href="([^"]+)"[^>]*>(.+?)<\/a>/ie', // <a href="">
+        '/<a [^>]*href=("|\')([^"\']+)\1[^>]*>(.+?)<\/a>/ie', // <a href="">
         '/<h[123][^>]*>(.+?)<\/h[123]>/ie',      // H1 - H3
         '/<h[456][^>]*>(.+?)<\/h[456]>/ie',      // H4 - H6
         '/<p[^>]*>/i',                           // <P>
@@ -126,19 +126,18 @@ class html2text
         '/(<table[^>]*>|<\/table>)/i',           // <table> and </table>
         '/(<tr[^>]*>|<\/tr>)/i',                 // <tr> and </tr>
         '/<td[^>]*>(.+?)<\/td>/i',               // <td> and </td>
-        '/<th[^>]*>(.+?)<\/th>/i',               // <th> and </th>
+        '/<th[^>]*>(.+?)<\/th>/ie',              // <th> and </th>
         '/&nbsp;/i',
         '/&quot;/i',
         '/&gt;/i',
         '/&lt;/i',
-        '/&amp;/i',
+        '/&(amp|#38);/i',
         '/&copy;/i',
         '/&trade;/i',
         '/&#8220;/',
         '/&#8221;/',
         '/&#8211;/',
-        '/&#8217;/',
-        '/&#38;/',
+        '/&#(8217|39);/',
         '/&#169;/',
         '/&#8482;/',
         '/&#151;/',
@@ -161,11 +160,11 @@ class html2text
         '',                                     // Non-legal carriage return
         ' ',                                    // Newlines and tabs
         '',                                     // <script>s -- which strip_tags supposedly has problems with
-        //'',                                     // Comments -- which strip_tags might have problem a with
-        '$this->_build_link_list("\\1", "\\2")', // <a href="">
+        //'',                                  // Comments -- which strip_tags might have problem a with
+        '$this->_build_link_list("\\2", "\\3")', // <a href="">
         "strtoupper(\"\n\n\\1\n\n\")",          // H1 - H3
-        "ucwords(\"\n\n\\1\n\n\")",             // H4 - H6
-        "\n\n\t",                               // <P>
+        "ucwords(\"\n\n\\1\n\")",               // H4 - H6
+        "\n\n",                                 // <P>
         "\n",                                   // <br>
         'strtoupper("\\1")',                    // <b>
         '_\\1_',                                // <i>
@@ -188,7 +187,6 @@ class html2text
         '"',
         '-',
         "'",
-        '&',
         '(c)',
         '(tm)',
         '--',
@@ -234,6 +232,15 @@ class html2text
      *  @see _build_link_list()
      */
     var $_link_list = array();
+    
+    /**
+     * 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.
@@ -244,15 +251,17 @@ class html2text
      *
      *  @param string $source HTML content
      *  @param boolean $from_file Indicates $source is a file to pull content from
+     *  @param boolean $do_link_table indicate whether a table of link URLs is desired
      *  @access public
      *  @return void
      */
-    function html2text( $source = '', $from_file = false )
+    function html2text( $source = '', $from_file = false, $produce_link_table = true )
     {
         if ( !empty($source) ) {
             $this->set_html($source, $from_file);
         }
         $this->set_base_url();
+        $this->_do_links = $produce_link_table;
     }
 
     /**
@@ -411,6 +420,8 @@ class html2text
     */
     function _build_link_list($link, $display)
       {
+      if (! $this->_do_links) return $display;
+
       $link_lc = strtolower($link);
       
       if (substr($link_lc, 0, 7) == 'http://' || substr($link_lc, 0, 8) == 'https://' || substr($link_lc, 0, 7) == 'mailto:')