Bug 612527 - Implement spec tweaks to U+0000 handling in the HTML5 parser. rs=jonas, a=blocking2.0-betaN.

2010-12-09 11:27:58 +02:00
parent 0e46554119
commit 034b529d7e
9 changed files with 66 additions and 12 deletions
--- a/parser/html/javasrc/Tokenizer.java
+++ b/parser/html/javasrc/Tokenizer.java
@@ -3424,7 +3424,7 @@ public class Tokenizer implements Locator {
                        }
                        switch (c) {
                            case '\u0000':
-                                emitReplacementCharacter(buf, pos);
+                                emitPlaintextReplacementCharacter(buf, pos);
                                continue;
                            case '\r':
                                emitCarriageReturn(buf, pos);
@@ -5785,6 +5785,13 @@ public class Tokenizer implements Locator {
        cstart = pos + 1;
    }

+    private void emitPlaintextReplacementCharacter(@NoLength char[] buf, int pos)
+            throws SAXException {
+        flushChars(buf, pos);
+        tokenHandler.characters(REPLACEMENT_CHARACTER, 0, 1);
+        cstart = pos + 1;
+    }
+
    private void setAdditionalAndRememberAmpersandLocation(char add) {
        additional = add;
        // [NOCPP[