parser/htmlparser/src/nsHTMLTokenizer.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.org 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
  38
  39 /**
  40  * MODULE NOTES:
  41  * @update  gess 4/1/98
  42  *
  43  */
  44
  45 #ifndef __NSHTMLTOKENIZER
  46 #define __NSHTMLTOKENIZER
  47
  48 #include "nsISupports.h"
  49 #include "nsITokenizer.h"
  50 #include "nsIDTD.h"
  51 #include "prtypes.h"
  52 #include "nsDeque.h"
  53 #include "nsScanner.h"
  54 #include "nsHTMLTokens.h"
  55 #include "nsDTDUtils.h"
  56
  57 /***************************************************************
  58   Notes:
  59  ***************************************************************/
  60
  61 #ifdef _MSC_VER
  62 #pragma warning( disable : 4275 )
  63 #endif
  64
  65 class nsHTMLTokenizer : public nsITokenizer {
  66 public:
  67
  68   NS_DECL_ISUPPORTS
  69   NS_DECL_NSITOKENIZER
  70   nsHTMLTokenizer(PRInt32 aParseMode = eDTDMode_quirks,
  71                   eParserDocType aDocType = eHTML_Quirks,
  72                   eParserCommands aCommand = eViewNormal,
  73                   PRUint16 aFlags = 0);
  74   virtual ~nsHTMLTokenizer();
  75
  76 protected:
  77
  78   nsresult ConsumeTag(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner,PRBool& aFlushTokens);
  79   nsresult ConsumeStartTag(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner,PRBool& aFlushTokens);
  80   nsresult ConsumeEndTag(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  81   nsresult ConsumeAttributes(PRUnichar aChar, CToken* aToken, nsScanner& aScanner);
  82   nsresult ConsumeEntity(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  83   nsresult ConsumeWhitespace(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  84   nsresult ConsumeComment(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  85   nsresult ConsumeNewline(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  86   nsresult ConsumeText(CToken*& aToken,nsScanner& aScanner);
  87   nsresult ConsumeSpecialMarkup(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  88   nsresult ConsumeProcessingInstruction(PRUnichar aChar,CToken*& aToken,nsScanner& aScanner);
  89
  90   nsresult ScanDocStructure(PRBool aIsFinalChunk);
  91
  92   static void AddToken(CToken*& aToken,nsresult aResult,nsDeque* aDeque,nsTokenAllocator* aTokenAllocator);
  93
  94   nsDeque            mTokenDeque;
  95   PRPackedBool       mIsFinalChunk;
  96   nsTokenAllocator*  mTokenAllocator;
  97   // This variable saves the position of the last tag we inspected in
  98   // ScanDocStructure. We start scanning the general well-formedness of the
  99   // document starting at this position each time.
 100   PRInt32            mTokenScanPos;
 101   PRUint32           mFlags;
 102 };
 103
 104 #endif
 105
 106