From 9351d1c046ed3a6a82db3daa7eaab2336d5b204d Mon Sep 17 00:00:00 2001
From: Technosophos <technosophos@gmail.com>
Date: Fri, 19 Apr 2013 17:43:28 -0500
Subject: Full support for rawtext. Unit tests finished.

---
 src/HTML5/Parser/EventHandler.php | 27 ++++++++++++++++++++++++++-
 src/HTML5/Parser/Tokenizer.php    |  7 ++++++-
 2 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'src')

diff --git a/src/HTML5/Parser/EventHandler.php b/src/HTML5/Parser/EventHandler.php
index 8282cb7..ebb30b2 100644
--- a/src/HTML5/Parser/EventHandler.php
+++ b/src/HTML5/Parser/EventHandler.php
@@ -27,7 +27,32 @@ interface EventHandler {
   /**
    * A start tag.
    *
-   * 
+   * IMPORTANT: The parser watches the return value of this event. If this returns
+   * an integer, the parser will switch TEXTMODE patters according to the int.
+   *
+   * This is how the Tree Builder can tell the Tokenizer when a certain tag should
+   * cause the parser to go into RAW text mode.
+   *
+   * The HTML5 standard requires that the builder is the one that initiates this
+   * step, and this is the only way short of a circular reference that we can
+   * do that.
+   *
+   * Example: if a startTag even for a `script` name is fired, and the startTag()
+   * implementation returns Tokenizer::TEXTMODE_RAW, then the tokenizer will
+   * switch into RAW text mode and consume data until it reaches a closing
+   * `script` tag.
+   *
+   * The textmode is automatically reset to Tokenizer::TEXTMODE_NORMAL when the
+   * closing tag is encounter. **This behavior may change.**
+   *
+   * @param string $name
+   *   The tag name.
+   * @param array $attributes
+   *   An array with all of the tag's attributes.
+   * @param boolean $selfClosing
+   *   An indicator of whether or not this tag is self-closing (<foo/>)
+   * @return numeric
+   *   One of the Tokenizer::TEXTMODE_* constants.
    */
   public function startTag($name, $attributes = array(), $selfClosing = FALSE);
   /**
diff --git a/src/HTML5/Parser/Tokenizer.php b/src/HTML5/Parser/Tokenizer.php
index 4f2f792..02bb328 100644
--- a/src/HTML5/Parser/Tokenizer.php
+++ b/src/HTML5/Parser/Tokenizer.php
@@ -303,11 +303,15 @@ class Tokenizer {
     }
     while (!$this->isTagEnd($selfClose));
 
-    $this->events->startTag($name, $attributes, $selfClose);
+    $mode = $this->events->startTag($name, $attributes, $selfClose);
     // Should we do this? What does this buy that selfClose doesn't?
     if ($selfClose) {
       $this->events->endTag($name);
     }
+    elseif (is_int($mode)) {
+      //fprintf(STDOUT, "Event response says move into mode %d for tag %s", $mode, $name);
+      $this->setTextMode($mode, $name);
+    }
 
     $this->scanner->next();
 
@@ -816,6 +820,7 @@ class Tokenizer {
     }
 
     // If we get here, we hit the EOF.
+    $this->parseError("Unexpected EOF during text read.");
     return $buffer;
   }
 
-- 
cgit v1.2.3