DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (a81015259a98)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
/* ***** BEGIN LICENSE BLOCK *****
 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Mozilla Public License Version
 * 1.1 (the "License"); you may not use this file except in compliance with
 * the License. You may obtain a copy of the License at
 * http://www.mozilla.org/MPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the
 * License.
 *
 * The Original Code is HTML Parser C++ Translator code.
 *
 * The Initial Developer of the Original Code is
 * Mozilla Foundation.
 * Portions created by the Initial Developer are Copyright (C) 2008-2009
 * the Initial Developer. All Rights Reserved.
 *
 * Contributor(s):
 *   Henri Sivonen <hsivonen@iki.fi>
 *
 * Alternatively, the contents of this file may be used under the terms of
 * either the GNU General Public License Version 2 or later (the "GPL"), or
 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
 * in which case the provisions of the GPL or the LGPL are applicable instead
 * of those above. If you wish to allow use of your version of this file only
 * under the terms of either the GPL or the LGPL, and not to allow others to
 * use your version of this file under the terms of the MPL, indicate your
 * decision by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL or the LGPL. If you do not delete
 * the provisions above, a recipient may use your version of this file under
 * the terms of any one of the MPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */

#define NS_HTML5_TREE_BUILDER_HANDLE_ARRAY_LENGTH 512

  private:
    nsHtml5Highlighter*                    mViewSource;
    nsTArray<nsHtml5TreeOperation>         mOpQueue;
    nsTArray<nsHtml5SpeculativeLoad>       mSpeculativeLoadQueue;
    nsAHtml5TreeOpSink*                    mOpSink;
    nsAutoArrayPtr<nsIContent*>            mHandles;
    PRInt32                                mHandlesUsed;
    nsTArray<nsAutoArrayPtr<nsIContent*> > mOldHandles;
    nsHtml5TreeOpStage*                    mSpeculativeLoadStage;
    nsIContent**                           mDeepTreeSurrogateParent;
    bool                                   mCurrentHtmlScriptIsAsyncOrDefer;
#ifdef DEBUG
    bool                                   mActive;
#endif

    // DocumentModeHandler
    /**
     * Tree builder uses this to report quirkiness of the document
     */
    void documentMode(nsHtml5DocumentMode m);

    /**
     * Using nsIContent** instead of nsIContent* is the parser deals with DOM
     * nodes in a way that works off the main thread. Non-main-thread code
     * can't refcount or otherwise touch nsIContent objects in any way.
     * Yet, the off-the-main-thread code needs to have a way to hold onto a
     * particular node and repeatedly operate on the same node.
     *
     * The way this works is that the off-the-main-thread code has an
     * nsIContent** for each DOM node and a given nsIContent** is only ever
     * actually dereferenced into an actual nsIContent* on the main thread.
     * When the off-the-main-thread code requests a new node, it gets an
     * nsIContent** immediately and a tree op is enqueued for later allocating
     * an actual nsIContent object and writing a pointer to it into the memory
     * location pointed to by the nsIContent**.
     *
     * Since tree ops are in a queue, the node creating tree op will always
     * run before tree ops that try to further operate on the node that the
     * nsIContent** is a handle to.
     *
     * On-the-main-thread parts of the parser use the same mechanism in order
     * to avoid having to have duplicate code paths for on-the-main-thread and
     * off-the-main-thread tree builder instances.)
     */
    nsIContent** AllocateContentHandle();
    
    void accumulateCharactersForced(const PRUnichar* aBuf, PRInt32 aStart, PRInt32 aLength)
    {
      accumulateCharacters(aBuf, aStart, aLength);
    }

  public:

    nsHtml5TreeBuilder(nsAHtml5TreeOpSink* aOpSink,
                       nsHtml5TreeOpStage* aStage);

    ~nsHtml5TreeBuilder();
    
    void StartPlainText();

    bool HasScript();
    
    void SetOpSink(nsAHtml5TreeOpSink* aOpSink) {
      mOpSink = aOpSink;
    }

    void ClearOps() {
      mOpQueue.Clear();
    }
    
    bool Flush(bool aDiscretionary = false);
    
    void FlushLoads();

    void SetDocumentCharset(nsACString& aCharset, PRInt32 aCharsetSource);

    void StreamEnded();

    void NeedsCharsetSwitchTo(const nsACString& aEncoding, PRInt32 aSource);

    void AddSnapshotToScript(nsAHtml5TreeBuilderState* aSnapshot, PRInt32 aLine);

    void DropHandles();

    void EnableViewSource(nsHtml5Highlighter* aHighlighter);

    void errStrayStartTag(nsIAtom* aName);

    void errStrayEndTag(nsIAtom* aName);

    void errUnclosedElements(PRInt32 aIndex, nsIAtom* aName);

    void errUnclosedElementsImplied(PRInt32 aIndex, nsIAtom* aName);

    void errUnclosedElementsCell(PRInt32 aIndex);

    void errStrayDoctype();

    void errAlmostStandardsDoctype();

    void errQuirkyDoctype();

    void errNonSpaceInTrailer();

    void errNonSpaceAfterFrameset();

    void errNonSpaceInFrameset();

    void errNonSpaceAfterBody();

    void errNonSpaceInColgroupInFragment();

    void errNonSpaceInNoscriptInHead();

    void errFooBetweenHeadAndBody(nsIAtom* aName);

    void errStartTagWithoutDoctype();

    void errNoSelectInTableScope();

    void errStartSelectWhereEndSelectExpected();

    void errStartTagWithSelectOpen(nsIAtom* aName);

    void errBadStartTagInHead(nsIAtom* aName);

    void errImage();

    void errIsindex();

    void errFooSeenWhenFooOpen(nsIAtom* aName);

    void errHeadingWhenHeadingOpen();

    void errFramesetStart();

    void errNoCellToClose();

    void errStartTagInTable(nsIAtom* aName);

    void errFormWhenFormOpen();

    void errTableSeenWhileTableOpen();

    void errStartTagInTableBody(nsIAtom* aName);

    void errEndTagSeenWithoutDoctype();

    void errEndTagAfterBody();

    void errEndTagSeenWithSelectOpen(nsIAtom* aName);

    void errGarbageInColgroup();

    void errEndTagBr();

    void errNoElementToCloseButEndTagSeen(nsIAtom* aName);

    void errHtmlStartTagInForeignContext(nsIAtom* aName);

    void errTableClosedWhileCaptionOpen();

    void errNoTableRowToClose();

    void errNonSpaceInTable();

    void errUnclosedChildrenInRuby();

    void errStartTagSeenWithoutRuby(nsIAtom* aName);

    void errSelfClosing();

    void errNoCheckUnclosedElementsOnStack();

    void errEndTagDidNotMatchCurrentOpenElement(nsIAtom* aName, nsIAtom* aOther);

    void errEndTagViolatesNestingRules(nsIAtom* aName);

    void errEndWithUnclosedElements(nsIAtom* aName);

    void MarkAsBroken();