Optimize the processing of text between nodes

Instead of processing the text token one by one in the main loop, it is
now processed in batch until the next special token (< and & which have
special handling in the main loop and NUL characters which need to report
a parse error).

1 files changed, 11 insertions, 5 deletions

diff --git a/src/HTML5/Parser/Tokenizer.php b/src/HTML5/Parser/Tokenizer.php
index a41fcb4..f4e9652 100644
--- a/src/HTML5/Parser/Tokenizer.php
+++ b/src/HTML5/Parser/Tokenizer.php
@@ -163,15 +163,21 @@ class Tokenizer
                     break;
 
                 default:
-                    if ('<' !== $tok && '&' !== $tok) {
-                        // NULL character
-                        if ("\00" === $tok) {
-                            $this->parseError('Received null character.');
-                        }
+                    if ('<' === $tok || '&' === $tok) {
+                        break;
+                    }
+
+                    // NULL character
+                    if ("\00" === $tok) {
+                        $this->parseError('Received null character.');
 
                         $this->text .= $tok;
                         $this->scanner->consume();
+
+                        break;
                     }
+
+                    $this->text .= $this->scanner->charsUntil("<&\0");
             }
         }