parser/htmlparser/public/nsIHTMLContentSink.h

   1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is Mozilla Communicator client code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Netscape Communications Corporation.
  19  * Portions created by the Initial Developer are Copyright (C) 1998
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either of the GNU General Public License Version 2 or later (the "GPL"),
  26  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37 #ifndef nsIHTMLContentSink_h___
  38 #define nsIHTMLContentSink_h___
  39
  40 /**
  41  * This file declares the concrete HTMLContentSink class.
  42  * This class is used during the parsing process as the
  43  * primary interface between the parser and the content
  44  * model.
  45  *
  46  * After the tokenizer completes, the parser iterates over
  47  * the known token list. As the parser identifies valid
  48  * elements, it calls the contentsink interface to notify
  49  * the content model that a new node or child node is being
  50  * created and added to the content model.
  51  *
  52  * The HTMLContentSink interface assumes 4 underlying
  53  * containers: HTML, HEAD, BODY and FRAMESET. Before
  54  * accessing any these, the parser will call the appropriate
  55  * OpennsIHTMLContentSink method: OpenHTML,OpenHead,OpenBody,OpenFrameSet;
  56  * likewise, the ClosensIHTMLContentSink version will be called when the
  57  * parser is done with a given section.
  58  *
  59  * IMPORTANT: The parser may Open each container more than
  60  * once! This is due to the irregular nature of HTML files.
  61  * For example, it is possible to encounter plain text at
  62  * the start of an HTML document (that preceeds the HTML tag).
  63  * Such text is treated as if it were part of the body.
  64  * In such cases, the parser will Open the body, pass the text-
  65  * node in and then Close the body. The body will likely be
  66  * re-Opened later when the actual <BODY> tag has been seen.
  67  *
  68  * Containers within the body are Opened and Closed
  69  * using the OpenContainer(...) and CloseContainer(...) calls.
  70  * It is assumed that the document or contentSink is
  71  * maintaining its state to manage where new content should
  72  * be added to the underlying document.
  73  *
  74  * NOTE: OpenHTML() and OpenBody() may get called multiple times
  75  *       in the same document. That's fine, and it doesn't mean
  76  *       that we have multiple bodies or HTML's.
  77  *
  78  * NOTE: I haven't figured out how sub-documents (non-frames)
  79  *       are going to be handled. Stay tuned.
  80  */
  81 #include "nsIParserNode.h"
  82 #include "nsIContentSink.h"
  83 #include "nsHTMLTags.h"
  84
  85 #define NS_IHTML_CONTENT_SINK_IID \
  86 { 0x73b5a072, 0x0f87, 0x4d07, \
  87   { 0xa8, 0x16, 0xe6, 0xac, 0x73, 0xa7, 0x04, 0x3c } }
  88
  89
  90 #if defined(XP_MAC) || defined(WINCE)
  91 #define MAX_REFLOW_DEPTH  75    //setting to 75 to prevent layout from crashing on mac. Bug 55095.
  92                                 //We will also change this for WinCE as it usually has a strict
  93                                 //memory upper limit (no vm, ~32mb)
  94 #else
  95 #define MAX_REFLOW_DEPTH  200   //windows and linux (etc) can do much deeper structures.
  96 #endif
  97
  98 class nsIHTMLContentSink : public nsIContentSink
  99 {
 100 public:
 101
 102   NS_DECLARE_STATIC_IID_ACCESSOR(NS_IHTML_CONTENT_SINK_IID)
 103
 104   /**
 105    * This method is used to open the HEAD container. It is useful if a tag
 106    * is forcing us to open the head (probably again), like if we find a <meta>
 107    * tag in the body.
 108    */
 109   NS_IMETHOD OpenHead() = 0;
 110
 111   /**
 112    * This gets called when handling illegal contents, especially
 113    * in dealing with tables. This method creates a new context.
 114    *
 115    * @update 04/04/99 harishd
 116    * @param aPosition - The position from where the new context begins.
 117    */
 118   NS_IMETHOD BeginContext(PRInt32 aPosition) = 0;
 119
 120   /**
 121    * This method terminates any new context that got created by
 122    * BeginContext and switches back to the main context.
 123    *
 124    * @update 04/04/99 harishd
 125    * @param aPosition - Validates the end of a context.
 126    */
 127   NS_IMETHOD EndContext(PRInt32 aPosition) = 0;
 128
 129   /**
 130    * @update 01/09/2003 harishd
 131    * @param aTag - Check if this tag is enabled or not.
 132    */
 133   NS_IMETHOD IsEnabled(PRInt32 aTag, PRBool* aReturn) = 0;
 134
 135    /**
 136    * This method is called when parser is about to begin
 137    * synchronously processing a chunk of tokens.
 138    */
 139   NS_IMETHOD WillProcessTokens(void) = 0;
 140
 141   /**
 142    * This method is called when parser has
 143    * completed processing a chunk of tokens. The processing of the
 144    * tokens may be interrupted by returning NS_ERROR_HTMLPARSER_INTERRUPTED from
 145    * DidProcessAToken.
 146    */
 147   NS_IMETHOD DidProcessTokens() = 0;
 148
 149   /**
 150    * This method is called when parser is about to
 151    * process a single token
 152    */
 153   NS_IMETHOD WillProcessAToken(void) = 0;
 154
 155   /**
 156    * This method is called when parser has completed
 157    * the processing for a single token.
 158    * @return NS_OK if processing should not be interrupted
 159    *         NS_ERROR_HTMLPARSER_INTERRUPTED if the parsing should be interrupted
 160    */
 161   NS_IMETHOD DidProcessAToken(void) = 0;
 162
 163     /**
 164    * This method is used to open a generic container in the sink.
 165    *
 166    * @update 4/1/98 gess
 167    * @param  nsIParserNode reference to parser node interface
 168    */
 169   NS_IMETHOD OpenContainer(const nsIParserNode& aNode) = 0;
 170
 171   /**
 172    *  This method gets called by the parser when a close
 173    *  container tag has been consumed and needs to be closed.
 174    *
 175    * @param  aTag - The tag to be closed.
 176    */
 177   NS_IMETHOD CloseContainer(const nsHTMLTag aTag) = 0;
 178
 179   /**
 180    * This method is used when we're closing a tag that was malformed
 181    * in some way. This way, the content sink can do special processing
 182    * (e.g., not execute a malformed script tag).
 183    *
 184    * @param aTag The tag to be closed.
 185    */
 186   NS_IMETHOD CloseMalformedContainer(const nsHTMLTag aTag)
 187   {
 188     return CloseContainer(aTag);
 189   }
 190
 191   /**
 192    * This gets called by the parser when you want to add
 193    * a leaf node to the current container in the content
 194    * model.
 195    *
 196    * @update 4/1/98 gess
 197    * @param  nsIParserNode reference to parser node interface
 198    */
 199   NS_IMETHOD AddLeaf(const nsIParserNode& aNode) = 0;
 200
 201   /**
 202    * This gets called by the parser when you want to add
 203    * a leaf node to the current container in the content
 204    * model.
 205    *
 206    * @update 4/1/98 gess
 207    * @param  nsIParserNode reference to parser node interface
 208    */
 209   NS_IMETHOD AddComment(const nsIParserNode& aNode) = 0;
 210
 211   /**
 212    * This gets called by the parser when you want to add
 213    * a leaf node to the current container in the content
 214    * model.
 215    *
 216    * @update 4/1/98 gess
 217    * @param  nsIParserNode reference to parser node interface
 218    */
 219   NS_IMETHOD AddProcessingInstruction(const nsIParserNode& aNode) = 0;
 220
 221   /**
 222    * This method is called by the parser when it encounters
 223    * a document type declaration.
 224    *
 225    * XXX Should the parser also parse the internal subset?
 226    *
 227    * @param  nsIParserNode reference to parser node interface
 228    */
 229   NS_IMETHOD AddDocTypeDecl(const nsIParserNode& aNode) = 0;
 230
 231   /**
 232    * This gets called by the parser to notify observers of
 233    * the tag
 234    *
 235    * @param aErrorResult the error code
 236    */
 237   NS_IMETHOD NotifyTagObservers(nsIParserNode* aNode) = 0;
 238
 239   /**
 240    * Call this method to determnine if a FORM is on the sink's stack
 241    *
 242    * @return PR_TRUE if found else PR_FALSE
 243    */
 244   NS_IMETHOD_(PRBool) IsFormOnStack() = 0;
 245
 246 };
 247
 248 NS_DEFINE_STATIC_IID_ACCESSOR(nsIHTMLContentSink, NS_IHTML_CONTENT_SINK_IID)
 249
 250 #endif /* nsIHTMLContentSink_h___ */
 251