Fix #73 with Attr.ID.HTML5

Signed-off-by: Edward Z. Yang <ezyang@cs.stanford.edu>

library/HTMLPurifier/AttrDef/HTML/ID.php

@@ -72,18 +72,26 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
 
         // we purposely avoid using regex, hopefully this is faster
 
-        if (ctype_alpha($id)) {
-            $result = true;
-        } else {
-            if (!ctype_alpha(@$id[0])) {
+        if ($config->get('Attr.ID.HTML5') === true) {
+            if (preg_match('/[\t\n\x0b\x0c ]/', $id)) {
                 return false;
             }
-            // primitive style of regexps, I suppose
-            $trim = trim(
-                $id,
-                'A..Za..z0..9:-._'
-            );
-            $result = ($trim === '');
+        } else {
+            if (ctype_alpha($id)) {
+                // OK
+            } else {
+                if (!ctype_alpha(@$id[0])) {
+                    return false;
+                }
+                // primitive style of regexps, I suppose
+                $trim = trim(
+                    $id,
+                    'A..Za..z0..9:-._'
+                );
+                if ($trim !== '') {
+                    return false;
+                }
+            }
         }
 
         $regexp = $config->get('Attr.IDBlacklistRegexp');
@@ -91,14 +99,14 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
             return false;
         }
 
-        if (!$this->selector && $result) {
+        if (!$this->selector) {
             $id_accumulator->add($id);
         }
 
         // if no change was made to the ID, return the result
         // else, return the new id if stripping whitespace made it
         //     valid, or return false.
-        return $result ? $id : false;
+        return $id;
     }
 }
 

library/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txt

@@ -0,0 +1,10 @@
+Attr.ID.HTML5
+TYPE: bool/null
+DEFAULT: null
+VERSION: 4.8.0
+--DESCRIPTION--
+In HTML5, restrictions on the format of the id attribute have been significantly
+relaxed, such that any string is valid so long as it contains no spaces and
+is at least one character.  In lieu of a general HTML5 compatibility flag,
+set this configuration directive to true to use the relaxed rules.
+--# vim: et sw=4 sts=4