mozilla
/
pjs
зеркало из https://github.com/mozilla/pjs.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

improved newline handling in tables

This commit is contained in:
rickg 1998-04-22 19:46:40 +00:00
Родитель 305efded8c
Коммит a9058dc3c1
8 изменённых файлов: 4 добавлений и 232 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

8
htmlparser/src/nsHTMLDelegate.cpp
Просмотреть файл

@ -234,7 +234,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeEntity(PRUnichar aChar,CScanner& aScanner
return result;
}
#ifdef TOKENIZE_WHITESPACE
/**-------------------------------------------------------
* This method is called just after whitespace has been
* consumed and we know we're at the start a whitespace run.
@ -250,7 +249,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeWhitespace(PRUnichar aChar,CScanner& aSca
anErrorCode=result->Consume(aChar,aScanner);
return result;
}
#endif
/**-------------------------------------------------------
* This method is called just after a "<!" has been consumed
@ -287,7 +285,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeText(const nsString& aString,CScanner& aS
return result;
}
#ifdef TOKENIZE_CRLF
/**-------------------------------------------------------
* This method is called just after a newline has been consumed.
*
@ -304,7 +301,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeNewline(PRUnichar aChar,CScanner& aScanne
}
return result;
}
#endif
/**-------------------------------------------------------
* This method repeatedly called by the tokenizer.
@ -333,18 +329,14 @@ CToken* CHTMLTokenizerDelegate::GetToken(CScanner& aScanner,PRInt32& anErrorCode
return ConsumeEntity(aChar,aScanner,anErrorCode);
case kLessThan:
return ConsumeTag(aChar,aScanner,anErrorCode);
#ifdef TOKENIZE_CRLF
case kCR: case kLF:
return ConsumeNewline(aChar,aScanner,anErrorCode);
case kNotFound:
break;
#endif
default:
#ifdef TOKENIZE_WHITESPACE
if(nsString::IsSpace(aChar))
return ConsumeWhitespace(aChar,aScanner,anErrorCode);
else
#endif
{
nsAutoString temp(aChar);
return ConsumeText(temp,aScanner,anErrorCode);

86
htmlparser/src/nsHTMLDelegate.h
Просмотреть файл

@ -1,86 +0,0 @@
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/*
* The contents of this file are subject to the Netscape Public License
* Version 1.0 (the "NPL"); you may not use this file except in
* compliance with the NPL. You may obtain a copy of the NPL at
* http://www.mozilla.org/NPL/
*
* Software distributed under the NPL is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the NPL
* for the specific language governing rights and limitations under the
* NPL.
*
* The Initial Developer of this code under the NPL is Netscape
* Communications Corporation. Portions created by Netscape are
* Copyright (C) 1998 Netscape Communications Corporation. All Rights
* Reserved.
*/
/**
* MODULE NOTES:
* @update gess 4/1/98
*
* This class is used as the HTML tokenizer delegate.
*
* The tokenzier class has the smarts to open an source,
* and iterate over its characters to produce a list of
* tokens. The tokenizer doesn't know HTML, which is
* where this delegate comes into play.
*
* The tokenizer calls methods on this class to help
* with the creation of HTML-specific tokens from a source
* stream.
*
* The interface here is very simple, mainly the call
* to GetToken(), which Consumes bytes from the underlying
* scanner.stream, and produces an HTML specific CToken.
*/
#ifndef TOKENIZER_DELEGATE
#define TOKENIZER_DELEGATE
#include "nsHTMLTokens.h"
#include "nsITokenizerDelegate.h"
#include "nsDeque.h"
class CHTMLTokenizerDelegate : public ITokenizerDelegate {
public:
CHTMLTokenizerDelegate();
CHTMLTokenizerDelegate(CHTMLTokenizerDelegate& aDelegate);
virtual CToken* GetToken(CScanner& aScanner,PRInt32& anErrorCode);
virtual PRBool WillAddToken(CToken& aToken);
virtual PRBool WillTokenize();
virtual PRBool DidTokenize();
virtual eParseMode GetParseMode() const;
static void SelfTest();
protected:
virtual CToken* CreateTokenOfType(eHTMLTokenTypes aType);
CToken* ConsumeTag(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeStartTag(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
void ConsumeAttributes(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeText(const nsString& aString,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeEntity(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#ifdef TOKENIZE_WHITESPACE
CToken* ConsumeWhitespace(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#endif
CToken* ConsumeComment(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#ifdef TOKENIZE_CRLF
CToken* ConsumeNewline(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#endif
//the only special case method...
virtual CToken* ConsumeContentToEndTag(const nsString& aString,PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
nsDeque mTokenDeque;
};
#endif

16
htmlparser/src/nsHTMLTokens.cpp
Просмотреть файл

@ -523,16 +523,8 @@ PRInt32 CTextToken::GetTokenType(void) {
* @return error result
*------------------------------------------------------*/
PRInt32 CTextToken::Consume(PRUnichar aChar, CScanner& aScanner) {
#ifdef TOKENIZE_CRLF
static nsAutoString terminals("&<\r\n");
#else
static nsAutoString terminals("&<");
#endif
PRInt32 result=aScanner.ReadUntil(mTextValue,terminals,PR_FALSE);
#ifndef TOKENIZE_CRLF
mTextValue.StripChars("\r");
#endif
static nsAutoString terminals("&<\r\n");
PRInt32 result=aScanner.ReadUntil(mTextValue,terminals,PR_FALSE);
return result;
};
@ -607,7 +599,6 @@ PRInt32 CCommentToken::GetTokenType(void) {
return eToken_comment;
}
#ifdef TOKENIZE_CRLF
/**-------------------------------------------------------
* default constructor
*
@ -656,7 +647,6 @@ PRInt32 CNewlineToken::Consume(PRUnichar aChar, CScanner& aScanner) {
mTextValue.StripChars("\r");
return result;
};
#endif /* TOKENIZE_CRLF */
/**-------------------------------------------------------
* default constructor
@ -834,7 +824,6 @@ void CAttributeToken::DebugDumpSource(ostream& out) {
out<<">";
}
#ifdef TOKENIZE_WHITESPACE
/**-------------------------------------------------------
* default constructor
*
@ -884,7 +873,6 @@ PRInt32 CWhitespaceToken::Consume(PRUnichar aChar, CScanner& aScanner) {
mTextValue.StripChars("\r");
return result;
};
#endif /* TOKENIZE_WHITESPACE */
/**-------------------------------------------------------
* default constructor

8
htmlparser/src/nsHTMLTokens.h
Просмотреть файл

@ -35,10 +35,6 @@
#include "nsToken.h"
#include <iostream.h>
// If you define these to true then crlf sequences and whitespace come
// through the scanner as seperate tokens.
#undef TOKENIZE_CRLF
#undef TOKENIZE_WHITESPACE
class CScanner;
@ -222,7 +218,6 @@ class CEntityToken : public CHTMLToken {
*
* @update gess 3/25/98
*/ //---------------------------------------------------
#ifdef TOKENIZE_WHITESPACE
class CWhitespaceToken: public CHTMLToken {
public:
CWhitespaceToken(const nsString& aString);
@ -230,7 +225,6 @@ class CWhitespaceToken: public CHTMLToken {
virtual const char* GetClassName(void);
virtual PRInt32 GetTokenType(void);
};
#endif
/** -----------------------------------------------------
* Text tokens contain the normalized form of html text.
@ -278,7 +272,6 @@ class CAttributeToken: public CHTMLToken {
*
* @update gess 3/25/98
*/ //---------------------------------------------------
#ifdef TOKENIZE_CRLF
class CNewlineToken: public CHTMLToken {
public:
CNewlineToken(const nsString& aString);
@ -286,7 +279,6 @@ class CNewlineToken: public CHTMLToken {
virtual const char* GetClassName(void);
virtual PRInt32 GetTokenType(void);
};
#endif
/** -----------------------------------------------------

8
parser/htmlparser/src/nsHTMLDelegate.cpp
Просмотреть файл

@ -234,7 +234,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeEntity(PRUnichar aChar,CScanner& aScanner
return result;
}
#ifdef TOKENIZE_WHITESPACE
/**-------------------------------------------------------
* This method is called just after whitespace has been
* consumed and we know we're at the start a whitespace run.
@ -250,7 +249,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeWhitespace(PRUnichar aChar,CScanner& aSca
anErrorCode=result->Consume(aChar,aScanner);
return result;
}
#endif
/**-------------------------------------------------------
* This method is called just after a "<!" has been consumed
@ -287,7 +285,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeText(const nsString& aString,CScanner& aS
return result;
}
#ifdef TOKENIZE_CRLF
/**-------------------------------------------------------
* This method is called just after a newline has been consumed.
*
@ -304,7 +301,6 @@ CToken* CHTMLTokenizerDelegate::ConsumeNewline(PRUnichar aChar,CScanner& aScanne
}
return result;
}
#endif
/**-------------------------------------------------------
* This method repeatedly called by the tokenizer.
@ -333,18 +329,14 @@ CToken* CHTMLTokenizerDelegate::GetToken(CScanner& aScanner,PRInt32& anErrorCode
return ConsumeEntity(aChar,aScanner,anErrorCode);
case kLessThan:
return ConsumeTag(aChar,aScanner,anErrorCode);
#ifdef TOKENIZE_CRLF
case kCR: case kLF:
return ConsumeNewline(aChar,aScanner,anErrorCode);
case kNotFound:
break;
#endif
default:
#ifdef TOKENIZE_WHITESPACE
if(nsString::IsSpace(aChar))
return ConsumeWhitespace(aChar,aScanner,anErrorCode);
else
#endif
{
nsAutoString temp(aChar);
return ConsumeText(temp,aScanner,anErrorCode);

86
parser/htmlparser/src/nsHTMLDelegate.h
Просмотреть файл

@ -1,86 +0,0 @@
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/*
* The contents of this file are subject to the Netscape Public License
* Version 1.0 (the "NPL"); you may not use this file except in
* compliance with the NPL. You may obtain a copy of the NPL at
* http://www.mozilla.org/NPL/
*
* Software distributed under the NPL is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the NPL
* for the specific language governing rights and limitations under the
* NPL.
*
* The Initial Developer of this code under the NPL is Netscape
* Communications Corporation. Portions created by Netscape are
* Copyright (C) 1998 Netscape Communications Corporation. All Rights
* Reserved.
*/
/**
* MODULE NOTES:
* @update gess 4/1/98
*
* This class is used as the HTML tokenizer delegate.
*
* The tokenzier class has the smarts to open an source,
* and iterate over its characters to produce a list of
* tokens. The tokenizer doesn't know HTML, which is
* where this delegate comes into play.
*
* The tokenizer calls methods on this class to help
* with the creation of HTML-specific tokens from a source
* stream.
*
* The interface here is very simple, mainly the call
* to GetToken(), which Consumes bytes from the underlying
* scanner.stream, and produces an HTML specific CToken.
*/
#ifndef TOKENIZER_DELEGATE
#define TOKENIZER_DELEGATE
#include "nsHTMLTokens.h"
#include "nsITokenizerDelegate.h"
#include "nsDeque.h"
class CHTMLTokenizerDelegate : public ITokenizerDelegate {
public:
CHTMLTokenizerDelegate();
CHTMLTokenizerDelegate(CHTMLTokenizerDelegate& aDelegate);
virtual CToken* GetToken(CScanner& aScanner,PRInt32& anErrorCode);
virtual PRBool WillAddToken(CToken& aToken);
virtual PRBool WillTokenize();
virtual PRBool DidTokenize();
virtual eParseMode GetParseMode() const;
static void SelfTest();
protected:
virtual CToken* CreateTokenOfType(eHTMLTokenTypes aType);
CToken* ConsumeTag(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeStartTag(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
void ConsumeAttributes(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeText(const nsString& aString,CScanner& aScanner,PRInt32& anErrorCode);
CToken* ConsumeEntity(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#ifdef TOKENIZE_WHITESPACE
CToken* ConsumeWhitespace(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#endif
CToken* ConsumeComment(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#ifdef TOKENIZE_CRLF
CToken* ConsumeNewline(PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
#endif
//the only special case method...
virtual CToken* ConsumeContentToEndTag(const nsString& aString,PRUnichar aChar,CScanner& aScanner,PRInt32& anErrorCode);
nsDeque mTokenDeque;
};
#endif

16
parser/htmlparser/src/nsHTMLTokens.cpp
Просмотреть файл

@ -523,16 +523,8 @@ PRInt32 CTextToken::GetTokenType(void) {
* @return error result
*------------------------------------------------------*/
PRInt32 CTextToken::Consume(PRUnichar aChar, CScanner& aScanner) {
#ifdef TOKENIZE_CRLF
static nsAutoString terminals("&<\r\n");
#else
static nsAutoString terminals("&<");
#endif
PRInt32 result=aScanner.ReadUntil(mTextValue,terminals,PR_FALSE);
#ifndef TOKENIZE_CRLF
mTextValue.StripChars("\r");
#endif
static nsAutoString terminals("&<\r\n");
PRInt32 result=aScanner.ReadUntil(mTextValue,terminals,PR_FALSE);
return result;
};
@ -607,7 +599,6 @@ PRInt32 CCommentToken::GetTokenType(void) {
return eToken_comment;
}
#ifdef TOKENIZE_CRLF
/**-------------------------------------------------------
* default constructor
*
@ -656,7 +647,6 @@ PRInt32 CNewlineToken::Consume(PRUnichar aChar, CScanner& aScanner) {
mTextValue.StripChars("\r");
return result;
};
#endif /* TOKENIZE_CRLF */
/**-------------------------------------------------------
* default constructor
@ -834,7 +824,6 @@ void CAttributeToken::DebugDumpSource(ostream& out) {
out<<">";
}
#ifdef TOKENIZE_WHITESPACE
/**-------------------------------------------------------
* default constructor
*
@ -884,7 +873,6 @@ PRInt32 CWhitespaceToken::Consume(PRUnichar aChar, CScanner& aScanner) {
mTextValue.StripChars("\r");
return result;
};
#endif /* TOKENIZE_WHITESPACE */
/**-------------------------------------------------------
* default constructor

8
parser/htmlparser/src/nsHTMLTokens.h
Просмотреть файл

@ -35,10 +35,6 @@
#include "nsToken.h"
#include <iostream.h>
// If you define these to true then crlf sequences and whitespace come
// through the scanner as seperate tokens.
#undef TOKENIZE_CRLF
#undef TOKENIZE_WHITESPACE
class CScanner;
@ -222,7 +218,6 @@ class CEntityToken : public CHTMLToken {
*
* @update gess 3/25/98
*/ //---------------------------------------------------
#ifdef TOKENIZE_WHITESPACE
class CWhitespaceToken: public CHTMLToken {
public:
CWhitespaceToken(const nsString& aString);
@ -230,7 +225,6 @@ class CWhitespaceToken: public CHTMLToken {
virtual const char* GetClassName(void);
virtual PRInt32 GetTokenType(void);
};
#endif
/** -----------------------------------------------------
* Text tokens contain the normalized form of html text.
@ -278,7 +272,6 @@ class CAttributeToken: public CHTMLToken {
*
* @update gess 3/25/98
*/ //---------------------------------------------------
#ifdef TOKENIZE_CRLF
class CNewlineToken: public CHTMLToken {
public:
CNewlineToken(const nsString& aString);
@ -286,7 +279,6 @@ class CNewlineToken: public CHTMLToken {
virtual const char* GetClassName(void);
virtual PRInt32 GetTokenType(void);
};
#endif
/** -----------------------------------------------------