Sync the Java sources of the HTML5 parser with the parser repo. rs=sicking. NPOTB.

parser/html/javasrc/AttributeName.java

@@ -508,20 +508,45 @@ public final class AttributeName
     }
 
     // [NOCPP[
+    /**
+     * Creator for use when the XML violation policy requires an attribute name
+     * to be changed.
+     * 
+     * @param name
+     *            the name of the attribute to create
+     */
     static AttributeName create(@Local String name) {
         return new AttributeName(AttributeName.ALL_NO_NS,
                 AttributeName.SAME_LOCAL(name), ALL_NO_PREFIX,
                 AttributeName.ALL_NCNAME, false);
     }
 
+    /**
+     * Queries whether this name is an XML 1.0 4th ed. NCName.
+     * 
+     * @param mode
+     *            the SVG/MathML/HTML mode
+     * @return <code>true</code> if this is an NCName in the given mode
+     */
     public boolean isNcName(int mode) {
         return ncname[mode];
     }
 
+    /**
+     * Queries whether this is an <code>xmlns</code> attribute.
+     * 
+     * @return <code>true</code> if this is an <code>xmlns</code> attribute
+     */
     public boolean isXmlns() {
         return xmlns;
     }
 
+    /**
+     * Queries whether this attribute has a case-folded value in the HTML4 mode
+     * of the parser.
+     * 
+     * @return <code>true</code> if the value is case-folded
+     */
     boolean isCaseFolded() {
         return this == AttributeName.ACTIVE || this == AttributeName.ALIGN
                 || this == AttributeName.ASYNC

parser/html/javasrc/MetaScanner.java

@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2008-2009 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 
@@ -32,8 +32,14 @@ import org.xml.sax.SAXException;
 
 public abstract class MetaScanner {
 
+    /**
+     * Constant for "charset".
+     */
     private static final @NoLength char[] CHARSET = "charset".toCharArray();
     
+    /**
+     * Constant for "content".
+     */
     private static final @NoLength char[] CONTENT = "content".toCharArray();
 
     private static final int NO = 0;
@@ -86,18 +92,39 @@ public abstract class MetaScanner {
     
     private static final int SELF_CLOSING_START_TAG = 20;
     
+    /**
+     * The data source.
+     */
     protected ByteReadable readable;
     
+    /**
+     * The state of the state machine that recognizes the tag name "meta".
+     */
     private int metaState = NO;
 
+    /**
+     * The current position in recognizing the attribute name "content".
+     */
     private int contentIndex = -1;
     
+    /**
+     * The current position in recognizing the attribute name "charset".
+     */
     private int charsetIndex = -1;
 
+    /**
+     * The tokenizer state.
+     */
     protected int stateSave = DATA;
 
+    /**
+     * The currently filled length of strBuf.
+     */
     private int strBufLen;
 
+    /**
+     * Accumulation buffer for attribute values.
+     */
     private char[] strBuf;
     
     // [NOCPP[
@@ -119,6 +146,8 @@ public abstract class MetaScanner {
     }
     
     /**
+     * Reads a byte from the data source.
+     * 
      * -1 means end.
      * @return
      * @throws IOException
@@ -131,6 +160,9 @@ public abstract class MetaScanner {
 
     // WARNING When editing this, makes sure the bytecode length shown by javap
     // stays under 8000 bytes!
+    /**
+     * The runs the meta scanning algorithm.
+     */
     protected final void stateLoop(int state)
             throws SAXException, IOException {
         int c = -1;
@@ -658,6 +690,10 @@ public abstract class MetaScanner {
         stateSave  = state;
     }
 
+    /**
+     * Adds a character to the accumulation buffer.
+     * @param c the character to add
+     */
     private void addToBuffer(int c) {
         if (strBufLen == strBuf.length) {
             char[] newBuf = new char[strBuf.length + (strBuf.length << 1)];
@@ -668,6 +704,11 @@ public abstract class MetaScanner {
         strBuf[strBufLen++] = (char)c;
     }
 
+    /**
+     * Attempts to extract a charset name from the accumulation buffer.
+     * @return <code>true</code> if successful
+     * @throws SAXException
+     */
     private boolean tryCharset() throws SAXException {
         if (metaState != A || !(contentIndex == 6 || charsetIndex == 6)) {
             return false;
@@ -690,6 +731,13 @@ public abstract class MetaScanner {
         return success;
     }
     
+    /**
+     * Tries to switch to an encoding.
+     * 
+     * @param encoding
+     * @return <code>true</code> if successful
+     * @throws SAXException
+     */
     protected abstract boolean tryCharset(String encoding) throws SAXException;
 
     

parser/html/javasrc/Portability.java

@@ -168,7 +168,7 @@ public final class Portability {
     }
 
     public static char[] isIndexPrompt() {
-        return "This is a searchable index. Insert your search keywords here: ".toCharArray();
+        return "This is a searchable index. Enter search keywords: ".toCharArray();
     }
 
     public static void delete(Object o) {

parser/html/javasrc/UTF16Buffer.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 
@@ -24,17 +24,42 @@ package nu.validator.htmlparser.impl;
 
 import nu.validator.htmlparser.annotation.NoLength;
 
+/**
+ * An UTF-16 buffer that knows the start and end indeces of its unconsumed
+ * content.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
 public final class UTF16Buffer {
+
+    /**
+     * The backing store of the buffer. May be larger than the logical content
+     * of this <code>UTF16Buffer</code>.
+     */
     private final @NoLength char[] buffer;
 
+    /**
+     * The index of the first unconsumed character in the backing buffer.
+     */
     private int start;
 
+    /**
+     * The index of the slot immediately after the last character in the backing
+     * buffer that is part of the logical content of this
+     * <code>UTF16Buffer</code>.
+     */
     private int end;
 
     /**
+     * Constructor for wrapping an existing UTF-16 code unit array.
+     * 
      * @param buffer
+     *            the backing buffer
      * @param start
+     *            the index of the first character to consume
      * @param end
+     *            the index immediately after the last character to consume
      */
     public UTF16Buffer(@NoLength char[] buffer, int start, int end) {
         this.buffer = buffer;
@@ -43,45 +68,58 @@ public final class UTF16Buffer {
     }
 
     /**
-     * Returns the start.
+     * Returns the start index.
      * 
-     * @return the start
+     * @return the start index
      */
     public int getStart() {
         return start;
     }
 
     /**
-     * Sets the start.
+     * Sets the start index.
      * 
-     * @param start the start to set
+     * @param start
+     *            the start index
      */
     public void setStart(int start) {
         this.start = start;
     }
 
     /**
-     * Returns the buffer.
+     * Returns the backing buffer.
      * 
-     * @return the buffer
+     * @return the backing buffer
      */
     public @NoLength char[] getBuffer() {
         return buffer;
     }
 
     /**
-     * Returns the end.
+     * Returns the end index.
      * 
-     * @return the end
+     * @return the end index
      */
     public int getEnd() {
         return end;
     }
-    
+
+    /**
+     * Checks if the buffer has data left.
+     * 
+     * @return <code>true</code> if there's data left
+     */
     public boolean hasMore() {
         return start < end;
     }
-    
+
+    /**
+     * Adjusts the start index to skip over the first character if it is a line
+     * feed and the previous character was a carriage return.
+     * 
+     * @param lastWasCR
+     *            whether the previous character was a carriage return
+     */
     public void adjust(boolean lastWasCR) {
         if (lastWasCR && buffer[start] == '\n') {
             start++;
@@ -89,9 +127,10 @@ public final class UTF16Buffer {
     }
 
     /**
-     * Sets the end.
+     * Sets the end index.
      * 
-     * @param end the end to set
+     * @param end
+     *            the end index
      */
     public void setEnd(int end) {
         this.end = end;

parser/html/nsHtml5MetaScanner.cpp

@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2008-2009 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 

parser/html/nsHtml5MetaScanner.h

@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2008-2009 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 

parser/html/nsHtml5UTF16Buffer.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 

parser/html/nsHtml5UTF16Buffer.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Mozilla Foundation
+ * Copyright (c) 2008-2010 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"),