Merge pull request #194 from bytestream/anchor-target-query-param

fix: query parameter parsed as character entity

Author: goetas

src/HTML5/Parser/Tokenizer.php

@@ -1181,16 +1181,11 @@ protected function decodeCharacterReference($inAttribute = false)
             return $entity;
         }
 
-        // If in an attribute, then failing to match ; means unconsume the
-        // entire string. Otherwise, failure to match is an error.
-        if ($inAttribute) {
-            $this->scanner->unconsume($this->scanner->position() - $start);
-
-            return '&';
-        }
+        // Failing to match ; means unconsume the entire string.
+        $this->scanner->unconsume($this->scanner->position() - $start);
 
         $this->parseError('Expected &ENTITY;, got &ENTITY%s (no trailing ;) ', $tok);
 
-        return '&' . $entity;
+        return '&';
     }
 }

test/HTML5/Html5Test.php

@@ -480,4 +480,13 @@ public function testCDATA()
         $res = $this->cycleFragment('a<![CDATA[ This <is> a test. ]]>b');
         $this->assertRegExp('|<!\[CDATA\[ This <is> a test\. \]\]>|', $res);
     }
+
+    public function testAnchorTargetQueryParam()
+    {
+        $res = $this->cycle('<a href="https://domain.com/page.php?foo=bar&target=baz">https://domain.com/page.php?foo=bar&target=baz</a>');
+        $this->assertContains(
+            '<a href="https://domain.com/page.php?foo=bar&amp;target=baz">https://domain.com/page.php?foo=bar&amp;target=baz</a>',
+            $res
+        );
+    }
 }