? mail-decode-full-entities.patch
Index: includes/mail.inc
===================================================================
RCS file: /cvs/drupal/drupal/includes/mail.inc,v
retrieving revision 1.7
diff -u -p -r1.7 mail.inc
--- includes/mail.inc	4 Sep 2007 21:10:45 -0000	1.7
+++ includes/mail.inc	23 Jan 2008 00:27:54 -0000
@@ -388,7 +388,7 @@ function drupal_html_to_text($string, $a
     // Process blocks of text.
     else {
       // Convert inline HTML text to plain text.
-      $value = trim(preg_replace('/\s+/', ' ', decode_entities($value)));
+      $value = trim(preg_replace('/\s+/', ' ', decode_entities_full($value)));
       if (strlen($value)) {
         $chunk = $value;
       }
@@ -469,3 +469,30 @@ function _drupal_html_to_text_pad($text,
   // Add prefix and padding, and restore linebreak.
   return $text . $prefix . str_repeat($pad, $n - strlen($prefix)) ."\n";
 }
+
+/**
+ * Helper function for drupal_html_to_text().
+ *
+ * Calls helper function for HTML 4 entity decoding.
+ * Per: http://www.lazycat.org/software/html_entity_decode_full.phps
+ */
+function decode_entities_full($string, $quotes = ENT_COMPAT, $charset = 'ISO-8859-1') {
+  return html_entity_decode(preg_replace_callback('/&([a-zA-Z][a-zA-Z0-9]+);/', 'convert_entity', $string), $quotes, $charset); 
+}
+
+/**
+ * Helper function for decode_entities_full().
+ *
+ * This contains the full HTML 4 Recommendation listing of entities, so the default to discard  
+ * entities not in the table is generally good. Pass false to the second argument to return 
+ * the faulty entity unmodified, if you're ill or something.
+ * Per: http://www.lazycat.org/software/html_entity_decode_full.phps
+ */
+function convert_entity($matches, $destroy = true) {
+  static $table = array('quot' => '"','amp' => '&','lt' => '<','gt' => '>','OElig' => 'Œ','oelig' => 'œ','Scaron' => 'Š','scaron' => 'š','Yuml' => 'Ÿ','circ' => 'ˆ','tilde' => '˜','ensp' => ' ','emsp' => ' ','thinsp' => ' ','zwnj' => '‌','zwj' => '‍','lrm' => '‎','rlm' => '‏','ndash' => '–','mdash' => '—','lsquo' => '‘','rsquo' => '’','sbquo' => '‚','ldquo' => '“','rdquo' => '”','bdquo' => '„','dagger' => '†','Dagger' => '‡','permil' => '‰','lsaquo' => '‹','rsaquo' => '›','euro' => '€','fnof' => 'ƒ','Alpha' => 'Α','Beta' => 'Β','Gamma' => 'Γ','Delta' => 'Δ','Epsilon' => 'Ε','Zeta' => 'Ζ','Eta' => 'Η','Theta' => 'Θ','Iota' => 'Ι','Kappa' => 'Κ','Lambda' => 'Λ','Mu' => 'Μ','Nu' => 'Ν','Xi' => 'Ξ','Omicron' => 'Ο','Pi' => 'Π','Rho' => 'Ρ','Sigma' => 'Σ','Tau' => 'Τ','Upsilon' => 'Υ','Phi' => 'Φ','Chi' => 'Χ','Psi' => 'Ψ','Omega' => 'Ω','alpha' => 'α','beta' => 'β','gamma' => 'γ','delta' => 'δ','epsilon' => 'ε','zeta' => 'ζ','eta' => 'η','theta' => 'θ','iota' => 'ι','kappa' => 'κ','lambda' => 'λ','mu' => 'μ','nu' => 'ν','xi' => 'ξ','omicron' => 'ο','pi' => 'π','rho' => 'ρ','sigmaf' => 'ς','sigma' => 'σ','tau' => 'τ','upsilon' => 'υ','phi' => 'φ','chi' => 'χ','psi' => 'ψ','omega' => 'ω','thetasym' => 'ϑ','upsih' => 'ϒ','piv' => 'ϖ','bull' => '•','hellip' => '…','prime' => '′','Prime' => '″','oline' => '‾','frasl' => '⁄','weierp' => '℘','image' => 'ℑ','real' => 'ℜ','trade' => '™','alefsym' => 'ℵ','larr' => '←','uarr' => '↑','rarr' => '→','darr' => '↓','harr' => '↔','crarr' => '↵','lArr' => '⇐','uArr' => '⇑','rArr' => '⇒','dArr' => '⇓','hArr' => '⇔','forall' => '∀','part' => '∂','exist' => '∃','empty' => '∅','nabla' => '∇','isin' => '∈','notin' => '∉','ni' => '∋','prod' => '∏','sum' => '∑','minus' => '−','lowast' => '∗','radic' => '√','prop' => '∝','infin' => '∞','ang' => '∠','and' => '∧','or' => '∨','cap' => '∩','cup' => '∪','int' => '∫','there4' => '∴','sim' => '∼','cong' => '≅','asymp' => '≈','ne' => '≠','equiv' => '≡','le' => '≤','ge' => '≥','sub' => '⊂','sup' => '⊃','nsub' => '⊄','sube' => '⊆','supe' => '⊇','oplus' => '⊕','otimes' => '⊗','perp' => '⊥','sdot' => '⋅','lceil' => '⌈','rceil' => '⌉','lfloor' => '⌊','rfloor' => '⌋','lang' => '〈','rang' => '〉','loz' => '◊','spades' => '♠','clubs' => '♣','hearts' => '♥','diams' => '♦','nbsp' => ' ','iexcl' => '¡','cent' => '¢','pound' => '£','curren' => '¤','yen' => '¥','brvbar' => '¦','sect' => '§','uml' => '¨','copy' => '©','ordf' => 'ª','laquo' => '«','not' => '¬','shy' => '­','reg' => '®','macr' => '¯','deg' => '°','plusmn' => '±','sup2' => '²','sup3' => '³','acute' => '´','micro' => 'µ','para' => '¶','middot' => '·','cedil' => '¸','sup1' => '¹','ordm' => 'º','raquo' => '»','frac14' => '¼','frac12' => '½','frac34' => '¾','iquest' => '¿','Agrave' => 'À','Aacute' => 'Á','Acirc' => 'Â','Atilde' => 'Ã','Auml' => 'Ä','Aring' => 'Å','AElig' => 'Æ','Ccedil' => 'Ç','Egrave' => 'È','Eacute' => 'É','Ecirc' => 'Ê','Euml' => 'Ë','Igrave' => 'Ì','Iacute' => 'Í','Icirc' => 'Î','Iuml' => 'Ï','ETH' => 'Ð','Ntilde' => 'Ñ','Ograve' => 'Ò','Oacute' => 'Ó','Ocirc' => 'Ô','Otilde' => 'Õ','Ouml' => 'Ö','times' => '×','Oslash' => 'Ø','Ugrave' => 'Ù','Uacute' => 'Ú','Ucirc' => 'Û','Uuml' => 'Ü','Yacute' => 'Ý','THORN' => 'Þ','szlig' => 'ß','agrave' => 'à','aacute' => 'á','acirc' => 'â','atilde' => 'ã','auml' => 'ä','aring' => 'å','aelig' => 'æ','ccedil' => 'ç','egrave' => 'è','eacute' => 'é','ecirc' => 'ê','euml' => 'ë','igrave' => 'ì','iacute' => 'í','icirc' => 'î','iuml' => 'ï','eth' => 'ð','ntilde' => 'ñ','ograve' => 'ò','oacute' => 'ó','ocirc' => 'ô','otilde' => 'õ','ouml' => 'ö','divide' => '÷','oslash' => 'ø','ugrave' => 'ù','uacute' => 'ú','ucirc' => 'û','uuml' => 'ü','yacute' => 'ý','thorn' => 'þ','yuml' => 'ÿ'
+                        );
+  if (isset($table[$matches[1]])) return $table[$matches[1]];
+  // else 
+  return $destroy ? '' : $matches[0];
+}
+?>