Closes #78: Fixes bug where unmatched entity like string drops everything after &.

1 files changed, 7 insertions, 1 deletions

diff --git a/src/HTML5/Parser/Tokenizer.php b/src/HTML5/Parser/Tokenizer.php
index e00b9a2..a779191 100644
--- a/src/HTML5/Parser/Tokenizer.php
+++ b/src/HTML5/Parser/Tokenizer.php
@@ -1065,8 +1065,14 @@ class Tokenizer
             // [a-zA-Z0-9]+;
             $cname = $this->scanner->getAsciiAlpha();
             $entity = CharacterReference::lookupName($cname);
+
+            // When no entity is found provide the name of the unmatched string
+            // and continue on as the & is not part of an entity. The & will
+            // be converted to & elsewhere.
             if ($entity == null) {
-                $this->parseError("No match in entity table for '%s'", $entity);
+                $this->parseError("No match in entity table for '%s'", $cname);
+                $this->scanner->unconsume($this->scanner->position() - $start);
+                return '&';
             }
         }