prevent infinite loop on unterminated entity declaration at end of st…

…ream
Masterminds · Feb 6, 2020 · 21eeaf0 · 21eeaf0
1 parent 104443a
commit 21eeaf0
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 0 deletions.
diff --git a/src/HTML5/Parser/Tokenizer.php b/src/HTML5/Parser/Tokenizer.php
@@ -1111,6 +1111,13 @@ protected function decodeCharacterReference($inAttribute = false)
         if ('#' === $tok) {
             $tok = $this->scanner->next();
 
+            if (false === $tok) {
+                $this->parseError('Expected &#DEC; &#HEX;, got EOF');
+                $this->scanner->unconsume(1);
+
+                return '&';
+            }
+
             // Hexidecimal encoding.
             // X[0-9a-fA-F]+;
             // x[0-9a-fA-F]+;

diff --git a/test/HTML5/Parser/DOMTreeBuilderTest.php b/test/HTML5/Parser/DOMTreeBuilderTest.php
@@ -133,6 +133,14 @@ public function testBareAmpersandNotAllowedInBody()
         </html>', $doc->saveXML());
     }
 
+    public function testEntityAtEndOfFile()
+    {
+        $fragment = $this->parseFragment('&#');
+        $this->assertInstanceOf('DOMDocumentFragment', $fragment);
+        $this->assertSame('&#', $fragment->textContent);
+        $this->assertEquals('Line 1, Col 2: Expected &#DEC; &#HEX;, got EOF', $this->errors[0]);
+    }
+
     public function testStrangeCapitalization()
     {
         $html = '<!doctype html>