/* tidylib.c -- internal library definitions (c) 1998-2008 (W3C) MIT, ERCIM, Keio University See tidy.h for the copyright notice. Defines HTML Tidy API implemented by tidy library. Very rough initial cut for discussion purposes. Public interface is const-correct and doesn't explicitly depend on any globals. Thus, thread-safety may be introduced w/out changing the interface. Looking ahead to a C++ wrapper, C functions always pass this-equivalent as 1st arg. Created 2001-05-20 by Charles Reitzel */ #include #include "tidy-int.h" #include "parser.h" #include "clean.h" #include "gdoc.h" #include "config.h" #include "message.h" #include "messageobj.h" #include "pprint.h" #include "entities.h" #include "tmbstr.h" #include "utf8.h" #include "mappedio.h" #include "language.h" #include "attrs.h" #include "sprtf.h" #if SUPPORT_LOCALIZATIONS # include "stdlib.h" # include "locale.h" #endif /* Create/Destroy a Tidy "document" object */ static TidyDocImpl* tidyDocCreate( TidyAllocator *allocator ); static void tidyDocRelease( TidyDocImpl* impl ); static int tidyDocStatus( TidyDocImpl* impl ); /* Parse Markup */ static int tidyDocParseFile( TidyDocImpl* impl, ctmbstr htmlfil ); static int tidyDocParseStdin( TidyDocImpl* impl ); static int tidyDocParseString( TidyDocImpl* impl, ctmbstr content ); static int tidyDocParseBuffer( TidyDocImpl* impl, TidyBuffer* inbuf ); static int tidyDocParseSource( TidyDocImpl* impl, TidyInputSource* docIn ); /* Execute post-parse diagnostics and cleanup. ** Note, the order is important. You will get different ** results from the diagnostics depending on if they are run ** pre-or-post repair. */ static int tidyDocRunDiagnostics( TidyDocImpl* doc ); static void tidyDocReportDoctype( TidyDocImpl* doc ); static int tidyDocCleanAndRepair( TidyDocImpl* doc ); /* Save cleaned up file to file/buffer/sink */ static int tidyDocSaveFile( TidyDocImpl* impl, ctmbstr htmlfil ); static int tidyDocSaveStdout( TidyDocImpl* impl ); static int tidyDocSaveString( TidyDocImpl* impl, tmbstr buffer, uint* buflen ); static int tidyDocSaveBuffer( TidyDocImpl* impl, TidyBuffer* outbuf ); static int tidyDocSaveSink( TidyDocImpl* impl, TidyOutputSink* docOut ); static int tidyDocSaveStream( TidyDocImpl* impl, StreamOut* out ); /* Tidy public interface ** ** Most functions return an integer: ** ** 0 -> SUCCESS ** >0 -> WARNING ** <0 -> ERROR ** */ TidyDoc TIDY_CALL tidyCreate(void) { TidyDocImpl* impl = tidyDocCreate( &TY_(g_default_allocator) ); return tidyImplToDoc( impl ); } TidyDoc TIDY_CALL tidyCreateWithAllocator( TidyAllocator *allocator ) { TidyDocImpl* impl = tidyDocCreate( allocator ); return tidyImplToDoc( impl ); } void TIDY_CALL tidyRelease( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); tidyDocRelease( impl ); } TidyDocImpl* tidyDocCreate( TidyAllocator *allocator ) { TidyDocImpl* doc = (TidyDocImpl*)TidyAlloc( allocator, sizeof(TidyDocImpl) ); TidyClearMemory( doc, sizeof(*doc) ); doc->allocator = allocator; TY_(InitMap)(); TY_(InitTags)( doc ); TY_(InitAttrs)( doc ); TY_(InitConfig)( doc ); TY_(InitPrintBuf)( doc ); TY_(InitParserStack)( doc ); /* Set the locale for tidy's output. This both configures ** LibTidy to use the environment's locale as well as the ** standard library. */ #if SUPPORT_LOCALIZATIONS if ( TY_(tidyGetLanguageSetByUser)() == no ) { if( ! TY_(tidySetLanguage)( getenv( "LC_MESSAGES" ) ) ) { if( ! TY_(tidySetLanguage)( getenv( "LANG" ) ) ) { /*\ * Is. #770 #783 #780 #790 and maybe others - * TY_(tidySetLanguage)( setlocale( LC_ALL, "" ) ); * this seems a 'bad' choice! \*/ } } } #endif /* By default, wire tidy messages to standard error. ** Document input will be set by parsing routines. ** Document output will be set by pretty print routines. ** Config input will be set by config parsing routines. ** But we need to start off with a way to report errors. */ doc->errout = TY_(StdErrOutput)(); return doc; } void tidyDocRelease( TidyDocImpl* doc ) { /* doc in/out opened and closed by parse/print routines */ if ( doc ) { assert( doc->docIn == NULL ); assert( doc->docOut == NULL ); TY_(ReleaseStreamOut)( doc, doc->errout ); doc->errout = NULL; TY_(FreePrintBuf)( doc ); TY_(FreeNode)(doc, &doc->root); TidyClearMemory(&doc->root, sizeof(Node)); if (doc->givenDoctype) TidyDocFree(doc, doc->givenDoctype); TY_(FreeConfig)( doc ); TY_(FreeAttrTable)( doc ); TY_(FreeAttrPriorityList)( doc ); TY_(FreeMutedMessageList( doc )); TY_(FreeTags)( doc ); /*\ * Issue #186 - Now FreeNode depend on the doctype, so the lexer is needed * to determine which hash is to be used, so free it last. \*/ TY_(FreeLexer)( doc ); TY_(FreeParserStack)( doc ); TidyDocFree( doc, doc ); } } /* Let application store a chunk of data w/ each Tidy tdocance. ** Useful for callbacks. */ void TIDY_CALL tidySetAppData( TidyDoc tdoc, void* appData ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) impl->appData = appData; } void* TIDY_CALL tidyGetAppData( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return impl->appData; return NULL; } ctmbstr TIDY_CALL tidyReleaseDate(void) { return TY_(ReleaseDate)(); } ctmbstr TIDY_CALL tidyLibraryVersion(void) { return TY_(tidyLibraryVersion)(); } ctmbstr TIDY_CALL tidyPlatform(void) { #ifdef PLATFORM_NAME return PLATFORM_NAME; #else return NULL; #endif } /* Get/set configuration options */ Bool TIDY_CALL tidySetOptionCallback( TidyDoc tdoc, TidyOptCallback pOptCallback ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->pOptCallback = pOptCallback; return yes; } return no; } Bool TIDY_CALL tidySetConfigCallback(TidyDoc tdoc, TidyConfigCallback pConfigCallback) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->pConfigCallback = pConfigCallback; return yes; } return no; } Bool TIDY_CALL tidySetConfigChangeCallback(TidyDoc tdoc, TidyConfigChangeCallback pCallback) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->pConfigChangeCallback = pCallback; return yes; } return no; } int TIDY_CALL tidyLoadConfig( TidyDoc tdoc, ctmbstr cfgfil ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ParseConfigFile)( impl, cfgfil ); return -EINVAL; } int TIDY_CALL tidyLoadConfigEnc( TidyDoc tdoc, ctmbstr cfgfil, ctmbstr charenc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ParseConfigFileEnc)( impl, cfgfil, charenc ); return -EINVAL; } int TIDY_CALL tidySetCharEncoding( TidyDoc tdoc, ctmbstr encnam ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { int enc = TY_(CharEncodingId)( impl, encnam ); if ( enc >= 0 && TY_(AdjustCharEncoding)(impl, enc) ) return 0; TY_(ReportBadArgument)( impl, "char-encoding" ); } return -EINVAL; } int TIDY_CALL tidySetInCharEncoding( TidyDoc tdoc, ctmbstr encnam ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { int enc = TY_(CharEncodingId)( impl, encnam ); if ( enc >= 0 && TY_(SetOptionInt)( impl, TidyInCharEncoding, enc ) ) return 0; TY_(ReportBadArgument)( impl, "in-char-encoding" ); } return -EINVAL; } int TIDY_CALL tidySetOutCharEncoding( TidyDoc tdoc, ctmbstr encnam ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { int enc = TY_(CharEncodingId)( impl, encnam ); if ( enc >= 0 && TY_(SetOptionInt)( impl, TidyOutCharEncoding, enc ) ) return 0; TY_(ReportBadArgument)( impl, "out-char-encoding" ); } return -EINVAL; } TidyOptionId TIDY_CALL tidyOptGetIdForName( ctmbstr optnam ) { const TidyOptionImpl* option = TY_(lookupOption)( optnam ); if ( option ) return option->id; return N_TIDY_OPTIONS; /* Error */ } TidyIterator TIDY_CALL tidyGetOptionList( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(getOptionList)( impl ); return (TidyIterator) -1; } TidyOption TIDY_CALL tidyGetNextOption( TidyDoc tdoc, TidyIterator* pos ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); const TidyOptionImpl* option = NULL; if ( impl ) option = TY_(getNextOption)( impl, pos ); else if ( pos ) *pos = 0; return tidyImplToOption( option ); } TidyOption TIDY_CALL tidyGetOption( TidyDoc ARG_UNUSED(tdoc), TidyOptionId optId ) { const TidyOptionImpl* option = TY_(getOption)( optId ); return tidyImplToOption( option ); } TidyOption TIDY_CALL tidyGetOptionByName( TidyDoc ARG_UNUSED(doc), ctmbstr optnam ) { const TidyOptionImpl* option = TY_(lookupOption)( optnam ); return tidyImplToOption( option ); } TidyOptionId TIDY_CALL tidyOptGetId( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return option->id; return N_TIDY_OPTIONS; } ctmbstr TIDY_CALL tidyOptGetName( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return option->name; return NULL; } TidyOptionType TIDY_CALL tidyOptGetType( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return option->type; return (TidyOptionType) -1; } Bool TIDY_CALL tidyOptionIsList( TidyOption opt ) { const TidyOptionImpl* option = tidyOptionToImpl( opt ); if ( option ) return TY_(getOptionIsList)( option->id ); return no; } TidyConfigCategory TIDY_CALL tidyOptGetCategory( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return option->category; return (TidyConfigCategory) -1; } ctmbstr TIDY_CALL tidyOptGetDefault( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); /* Special case for TidyDoctype, because it is declared as string */ if ( option && option->id == TidyDoctype ) { const TidyOptionImpl* newopt = TY_(getOption)( TidyDoctypeMode ); return TY_(GetPickListLabelForPick)( TidyDoctypeMode, newopt->dflt ); } if ( option && option->type == TidyString ) return option->pdflt; /* Issue #306 - fix an old typo hidden by a cast! */ return NULL; } ulong TIDY_CALL tidyOptGetDefaultInt( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option && option->type != TidyString ) return option->dflt; /* Special case for TidyDoctype, because it has a picklist */ if ( option->id == TidyDoctype ) { const TidyOptionImpl* newopt = TY_(getOption)( TidyDoctypeMode ); return newopt->dflt; } return ~0U; } Bool TIDY_CALL tidyOptGetDefaultBool( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option && option->type != TidyString ) return ( option->dflt ? yes : no ); return no; } Bool TIDY_CALL tidyOptIsReadOnly( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return ( option->parser == NULL ); return yes; } TidyIterator TIDY_CALL tidyOptGetPickList( TidyOption topt ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return TY_(getOptionPickList)( option ); return (TidyIterator) -1; } ctmbstr TIDY_CALL tidyOptGetNextPick( TidyOption topt, TidyIterator* pos ) { const TidyOptionImpl* option = tidyOptionToImpl( topt ); if ( option ) return TY_(getNextOptionPick)( option, pos ); return NULL; } ctmbstr TIDY_CALL tidyOptGetValue( TidyDoc tdoc, TidyOptionId optId ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); ctmbstr optval = NULL; if ( impl ) { if ( optId == TidyDoctype ) { /* Special case for TidyDoctype, because it has a picklist and is a string. */ uint pick = tidyOptGetInt( tdoc, TidyDoctypeMode ); if ( pick != TidyDoctypeUser ) { optval = TY_(GetPickListLabelForPick)( TidyDoctypeMode, pick ); } else { optval = cfgStr( impl, optId ); } } else { /* Standard case. */ optval = cfgStr( impl, optId ); } } return optval; } Bool TIDY_CALL tidyOptSetValue( TidyDoc tdoc, TidyOptionId optId, ctmbstr val ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ParseConfigValue)( impl, optId, val ); return no; } Bool TIDY_CALL tidyOptParseValue( TidyDoc tdoc, ctmbstr optnam, ctmbstr val ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ParseConfigOption)( impl, optnam, val ); return no; } ulong TIDY_CALL tidyOptGetInt( TidyDoc tdoc, TidyOptionId optId ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); ulong opti = 0; if ( impl ) { /* Special case for TidyDoctype, because it has a picklist */ if ( optId == TidyDoctype ) opti = cfg( impl, TidyDoctypeMode); else opti = cfg( impl, optId ); } return opti; } Bool TIDY_CALL tidyOptSetInt( TidyDoc tdoc, TidyOptionId optId, ulong val ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { /* Special case for TidyDoctype, because it has a picklist */ if ( optId == TidyDoctype ) return TY_(SetOptionInt)( impl, TidyDoctypeMode, val ); else return TY_(SetOptionInt)( impl, optId, val ); } return no; } Bool TIDY_CALL tidyOptGetBool( TidyDoc tdoc, TidyOptionId optId ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); Bool optb = no; if ( impl ) { const TidyOptionImpl* option = TY_(getOption)( optId ); if ( option ) { optb = cfgBool( impl, optId ); } } return optb; } Bool TIDY_CALL tidyOptSetBool( TidyDoc tdoc, TidyOptionId optId, Bool val ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(SetOptionBool)( impl, optId, val ); return no; } ctmbstr TIDY_CALL tidyOptGetEncName( TidyDoc tdoc, TidyOptionId optId ) { uint enc = tidyOptGetInt( tdoc, optId ); return TY_(CharEncodingOptName)( enc ); } ctmbstr TIDY_CALL tidyOptGetCurrPick( TidyDoc tdoc, TidyOptionId optId ) { uint pick = tidyOptGetInt( tdoc, optId ); return TY_(GetPickListLabelForPick)( optId, pick ); } TidyIterator TIDY_CALL tidyOptGetDeclTagList( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); TidyIterator declIter = 0; if ( impl ) declIter = TY_(GetDeclaredTagList)( impl ); return declIter; } ctmbstr TIDY_CALL tidyOptGetNextDeclTag( TidyDoc tdoc, TidyOptionId optId, TidyIterator* iter ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); ctmbstr tagnam = NULL; if ( impl ) { UserTagType tagtyp = tagtype_null; if ( optId == TidyInlineTags ) tagtyp = tagtype_inline; else if ( optId == TidyBlockTags ) tagtyp = tagtype_block; else if ( optId == TidyEmptyTags ) tagtyp = tagtype_empty; else if ( optId == TidyPreTags ) tagtyp = tagtype_pre; if ( tagtyp != tagtype_null ) tagnam = TY_(GetNextDeclaredTag)( impl, tagtyp, iter ); } return tagnam; } TidyIterator TIDY_CALL tidyOptGetPriorityAttrList( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(getPriorityAttrList)( impl ); return (TidyIterator) -1; } ctmbstr TIDY_CALL tidyOptGetNextPriorityAttr(TidyDoc tdoc, TidyIterator* iter ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); ctmbstr result = NULL; if ( impl ) result = TY_(getNextPriorityAttr)( impl, iter ); else if ( iter ) *iter = 0; return result; } TidyIterator TIDY_CALL tidyOptGetMutedMessageList( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(getMutedMessageList)( impl ); return (TidyIterator) -1; } ctmbstr TIDY_CALL tidyOptGetNextMutedMessage(TidyDoc tdoc, TidyIterator* iter ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); ctmbstr result = NULL; if ( impl ) result = TY_(getNextMutedMessage)( impl, iter ); else if ( iter ) *iter = 0; return result; } ctmbstr TIDY_CALL tidyOptGetDoc( TidyDoc ARG_UNUSED(tdoc), TidyOption opt ) { const TidyOptionId optId = tidyOptGetId( opt ); return tidyLocalizedString(optId); } #if SUPPORT_CONSOLE_APP /* TODO - GROUP ALL CONSOLE-ONLY FUNCTIONS */ TidyIterator TIDY_CALL tidyOptGetDocLinksList( TidyDoc ARG_UNUSED(tdoc), TidyOption opt ) { const TidyOptionId optId = tidyOptGetId( opt ); const TidyOptionDoc* docDesc = TY_(OptGetDocDesc)( optId ); if (docDesc && docDesc->links) return (TidyIterator)docDesc->links; return (TidyIterator)NULL; } #endif /* SUPPORT_CONSOLE_APP */ TidyOption TIDY_CALL tidyOptGetNextDocLinks( TidyDoc tdoc, TidyIterator* pos ) { const TidyOptionId* curr = (const TidyOptionId *)*pos; TidyOption opt; if (*curr == TidyUnknownOption) { *pos = (TidyIterator)NULL; return (TidyOption)0; } opt = tidyGetOption(tdoc, *curr); curr++; *pos = (*curr == TidyUnknownOption ) ? (TidyIterator)NULL:(TidyIterator)curr; return opt; } int TIDY_CALL tidyOptSaveFile( TidyDoc tdoc, ctmbstr cfgfil ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(SaveConfigFile)( impl, cfgfil ); return -EINVAL; } int TIDY_CALL tidyOptSaveSink( TidyDoc tdoc, TidyOutputSink* sink ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(SaveConfigSink)( impl, sink ); return -EINVAL; } Bool TIDY_CALL tidyOptSnapshot( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { TY_(TakeConfigSnapshot)( impl ); return yes; } return no; } Bool TIDY_CALL tidyOptResetToSnapshot( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { TY_(ResetConfigToSnapshot)( impl ); return yes; } return no; } Bool TIDY_CALL tidyOptResetAllToDefault( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { TY_(ResetConfigToDefault)( impl ); return yes; } return no; } Bool TIDY_CALL tidyOptResetToDefault( TidyDoc tdoc, TidyOptionId optId ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ResetOptionToDefault)( impl, optId ); return no; } Bool TIDY_CALL tidyOptDiffThanDefault( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ConfigDiffThanDefault)( impl ); return no; } Bool TIDY_CALL tidyOptDiffThanSnapshot( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return TY_(ConfigDiffThanSnapshot)( impl ); return no; } Bool TIDY_CALL tidyOptCopyConfig( TidyDoc to, TidyDoc from ) { TidyDocImpl* docTo = tidyDocToImpl( to ); TidyDocImpl* docFrom = tidyDocToImpl( from ); if ( docTo && docFrom ) { TY_(CopyConfig)( docTo, docFrom ); return yes; } return no; } /* I/O and Message handling interface ** ** By default, Tidy will define, create and use instance of input and output ** handlers for standard C buffered I/O (i.e. FILE* stdin, FILE* stdout and ** FILE* stderr for content input, content output and diagnostic output, ** respectively. A FILE* cfgFile input handler will be used for config files. ** Command line options will just be set directly. */ void TIDY_CALL tidySetEmacsFile( TidyDoc tdoc, ctmbstr filePath ) { tidyOptSetValue( tdoc, TidyEmacsFile, filePath ); } ctmbstr TIDY_CALL tidyGetEmacsFile( TidyDoc tdoc ) { return tidyOptGetValue( tdoc, TidyEmacsFile ); } /* Use TidyReportFilter to filter messages by diagnostic level: ** info, warning, etc. Just set diagnostic output ** handler to redirect all diagnostics output. Return true ** to proceed with output, false to cancel. */ Bool TIDY_CALL tidySetReportFilter( TidyDoc tdoc, TidyReportFilter filt ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->reportFilter = filt; return yes; } return no; } /* tidySetReportCallback functions similar to TidyReportFilter, but provides the * string version of the internal enum name so that LibTidy users can use ** the string as a lookup key for providing their own error localizations. ** See the string key definitions in tidyenum.h. */ Bool TIDY_CALL tidySetReportCallback( TidyDoc tdoc, TidyReportCallback filt ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->reportCallback = filt; return yes; } return no; } Bool TIDY_CALL tidySetMessageCallback( TidyDoc tdoc, TidyMessageCallback filt ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->messageCallback = filt; return yes; } return no; } TidyDoc TIDY_CALL tidyGetMessageDoc( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); TidyDocImpl* doc = TY_(getMessageDoc)(*message); return tidyImplToDoc(doc); } uint TIDY_CALL tidyGetMessageCode( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageCode)(*message); } ctmbstr TIDY_CALL tidyGetMessageKey( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageKey)(*message); } int TIDY_CALL tidyGetMessageLine( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageLine)(*message); } int TIDY_CALL tidyGetMessageColumn( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageColumn)(*message); } TidyReportLevel TIDY_CALL tidyGetMessageLevel( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageLevel)(*message); } Bool TIDY_CALL tidyGetMessageIsMuted( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageIsMuted)(*message); } ctmbstr TIDY_CALL tidyGetMessageFormatDefault( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageFormatDefault)(*message); } ctmbstr TIDY_CALL tidyGetMessageFormat( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageFormat)(*message); } ctmbstr TIDY_CALL tidyGetMessageDefault( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageDefault)(*message); } ctmbstr TIDY_CALL tidyGetMessage( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessage)(*message); } ctmbstr TIDY_CALL tidyGetMessagePosDefault( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessagePosDefault)(*message); } ctmbstr TIDY_CALL tidyGetMessagePos( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessagePos)(*message); } ctmbstr TIDY_CALL tidyGetMessagePrefixDefault( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessagePrefixDefault)(*message); } ctmbstr TIDY_CALL tidyGetMessagePrefix( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessagePrefix)(*message); } ctmbstr TIDY_CALL tidyGetMessageOutputDefault( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageOutputDefault)(*message); } ctmbstr TIDY_CALL tidyGetMessageOutput( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageOutput)(*message); } TidyIterator TIDY_CALL tidyGetMessageArguments( TidyMessage tmessage ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getMessageArguments)(*message); } TidyMessageArgument TIDY_CALL tidyGetNextMessageArgument( TidyMessage tmessage, TidyIterator* iter ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getNextMessageArgument)(*message, iter); } TidyFormatParameterType TIDY_CALL tidyGetArgType( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgType)(*message, arg); } ctmbstr TIDY_CALL tidyGetArgFormat( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgFormat)(*message, arg); } ctmbstr TIDY_CALL tidyGetArgValueString( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgValueString)(*message, arg); } uint TIDY_CALL tidyGetArgValueUInt( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgValueUInt)(*message, arg); } int TIDY_CALL tidyGetArgValueInt( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgValueInt)(*message, arg); } double TIDY_CALL tidyGetArgValueDouble( TidyMessage tmessage, TidyMessageArgument* arg ) { TidyMessageImpl *message = tidyMessageToImpl(tmessage); return TY_(getArgValueDouble)(*message, arg); } FILE* TIDY_CALL tidySetErrorFile( TidyDoc tdoc, ctmbstr errfilnam ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { FILE* errout = fopen( errfilnam, "wb" ); if ( errout ) { uint outenc = cfg( impl, TidyOutCharEncoding ); uint nl = cfg( impl, TidyNewline ); TY_(ReleaseStreamOut)( impl, impl->errout ); impl->errout = TY_(FileOutput)( impl, errout, outenc, nl ); return errout; } else /* Emit message to current error sink */ TY_(ReportFileError)( impl, errfilnam, FILE_CANT_OPEN ); } return NULL; } int TIDY_CALL tidySetErrorBuffer( TidyDoc tdoc, TidyBuffer* errbuf ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { uint outenc = cfg( impl, TidyOutCharEncoding ); uint nl = cfg( impl, TidyNewline ); TY_(ReleaseStreamOut)( impl, impl->errout ); impl->errout = TY_(BufferOutput)( impl, errbuf, outenc, nl ); return ( impl->errout ? 0 : -ENOMEM ); } return -EINVAL; } int TIDY_CALL tidySetErrorSink( TidyDoc tdoc, TidyOutputSink* sink ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { uint outenc = cfg( impl, TidyOutCharEncoding ); uint nl = cfg( impl, TidyNewline ); TY_(ReleaseStreamOut)( impl, impl->errout ); impl->errout = TY_(UserOutput)( impl, sink, outenc, nl ); return ( impl->errout ? 0 : -ENOMEM ); } return -EINVAL; } /* Use TidyPPProgress to monitor the progress of the pretty printer. */ Bool TIDY_CALL tidySetPrettyPrinterCallback(TidyDoc tdoc, TidyPPProgress callback) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { impl->progressCallback = callback; return yes; } return no; } /* Document info */ int TIDY_CALL tidyStatus( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); int tidyStat = -EINVAL; if ( impl ) tidyStat = tidyDocStatus( impl ); return tidyStat; } int TIDY_CALL tidyDetectedHtmlVersion( TidyDoc ARG_UNUSED(tdoc) ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); return TY_(HTMLVersionNumberFromCode)( impl->lexer->versionEmitted ); } Bool TIDY_CALL tidyDetectedXhtml( TidyDoc ARG_UNUSED(tdoc) ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); return impl->lexer->isvoyager; } Bool TIDY_CALL tidyDetectedGenericXml( TidyDoc ARG_UNUSED(tdoc) ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); return impl->xmlDetected; } uint TIDY_CALL tidyErrorCount( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); uint count = 0xFFFFFFFF; if ( impl ) count = impl->errors; return count; } uint TIDY_CALL tidyWarningCount( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); uint count = 0xFFFFFFFF; if ( impl ) count = impl->warnings; return count; } uint TIDY_CALL tidyAccessWarningCount( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); uint count = 0xFFFFFFFF; if ( impl ) count = impl->accessErrors; return count; } uint TIDY_CALL tidyConfigErrorCount( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); uint count = 0xFFFFFFFF; if ( impl ) count = impl->optionErrors; return count; } /* Error reporting functions */ void TIDY_CALL tidyErrorSummary( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) TY_(ErrorSummary)( impl ); } void TIDY_CALL tidyGeneralInfo( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { TY_(Dialogue)( impl, TEXT_GENERAL_INFO ); TY_(Dialogue)( impl, TEXT_GENERAL_INFO_PLEA ); } } /* I/O Functions ** ** Initial version supports only whole-file operations. ** Do not expose Tidy StreamIn or Out data structures - yet. */ /* Parse/load Functions ** ** HTML/XHTML version determined from input. */ int TIDY_CALL tidyParseFile( TidyDoc tdoc, ctmbstr filnam ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocParseFile( doc, filnam ); } int TIDY_CALL tidyParseStdin( TidyDoc tdoc ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocParseStdin( doc ); } int TIDY_CALL tidyParseString( TidyDoc tdoc, ctmbstr content ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocParseString( doc, content ); } int TIDY_CALL tidyParseBuffer( TidyDoc tdoc, TidyBuffer* inbuf ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocParseBuffer( doc, inbuf ); } int TIDY_CALL tidyParseSource( TidyDoc tdoc, TidyInputSource* source ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocParseSource( doc, source ); } #ifdef WIN32 #define M_IS_DIR _S_IFDIR #else // !WIN32 #define M_IS_DIR S_IFDIR #endif int tidyDocParseFile( TidyDocImpl* doc, ctmbstr filnam ) { int status = -ENOENT; FILE* fin = 0; struct stat sbuf = { 0 }; /* Is. #681 - read-only files */ if ( stat(filnam,&sbuf) != 0 ) { TY_(ReportFileError)( doc, filnam, FILE_NOT_FILE ); return status; } if (sbuf.st_mode & M_IS_DIR) /* and /NOT/ if a DIRECTORY */ { TY_(ReportFileError)(doc, filnam, FILE_NOT_FILE); return status; } #ifdef _WIN32 return TY_(DocParseFileWithMappedFile)( doc, filnam ); #else fin = fopen( filnam, "rb" ); #if PRESERVE_FILE_TIMES { /* get last modified time */ TidyClearMemory(&doc->filetimes, sizeof(doc->filetimes)); if (fin && cfgBool(doc, TidyKeepFileTimes) && fstat(fileno(fin), &sbuf) != -1) { doc->filetimes.actime = sbuf.st_atime; doc->filetimes.modtime = sbuf.st_mtime; } } #endif if ( fin ) { StreamIn* in = TY_(FileInput)( doc, fin, cfg( doc, TidyInCharEncoding )); if ( !in ) { fclose( fin ); return status; } status = TY_(DocParseStream)( doc, in ); TY_(freeFileSource)(&in->source, yes); TY_(freeStreamIn)(in); } else /* Error message! */ TY_(ReportFileError)( doc, filnam, FILE_CANT_OPEN ); return status; #endif } int tidyDocParseStdin( TidyDocImpl* doc ) { StreamIn* in = TY_(FileInput)( doc, stdin, cfg( doc, TidyInCharEncoding )); int status = TY_(DocParseStream)( doc, in ); TY_(freeFileSource)(&in->source, yes); TY_(freeStreamIn)(in); return status; } int tidyDocParseBuffer( TidyDocImpl* doc, TidyBuffer* inbuf ) { int status = -EINVAL; if ( inbuf ) { StreamIn* in = TY_(BufferInput)( doc, inbuf, cfg( doc, TidyInCharEncoding )); status = TY_(DocParseStream)( doc, in ); TY_(freeStreamIn)(in); } return status; } int tidyDocParseString( TidyDocImpl* doc, ctmbstr content ) { int status = -EINVAL; TidyBuffer inbuf; StreamIn* in = NULL; if ( content ) { tidyBufInitWithAllocator( &inbuf, doc->allocator ); tidyBufAttach( &inbuf, (byte*)content, TY_(tmbstrlen)(content)+1 ); in = TY_(BufferInput)( doc, &inbuf, cfg( doc, TidyInCharEncoding )); status = TY_(DocParseStream)( doc, in ); tidyBufDetach( &inbuf ); TY_(freeStreamIn)(in); } return status; } int tidyDocParseSource( TidyDocImpl* doc, TidyInputSource* source ) { StreamIn* in = TY_(UserInput)( doc, source, cfg( doc, TidyInCharEncoding )); int status = TY_(DocParseStream)( doc, in ); TY_(freeStreamIn)(in); return status; } /* Print/save Functions ** */ int TIDY_CALL tidySaveFile( TidyDoc tdoc, ctmbstr filnam ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocSaveFile( doc, filnam ); } int TIDY_CALL tidySaveStdout( TidyDoc tdoc ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocSaveStdout( doc ); } int TIDY_CALL tidySaveString( TidyDoc tdoc, tmbstr buffer, uint* buflen ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocSaveString( doc, buffer, buflen ); } int TIDY_CALL tidySaveBuffer( TidyDoc tdoc, TidyBuffer* outbuf ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocSaveBuffer( doc, outbuf ); } int TIDY_CALL tidySaveSink( TidyDoc tdoc, TidyOutputSink* sink ) { TidyDocImpl* doc = tidyDocToImpl( tdoc ); return tidyDocSaveSink( doc, sink ); } int tidyDocSaveFile( TidyDocImpl* doc, ctmbstr filnam ) { int status = -ENOENT; FILE* fout = NULL; /* Don't zap input file if no output */ if ( doc->errors > 0 && cfgBool(doc, TidyWriteBack) && !cfgBool(doc, TidyForceOutput) ) status = tidyDocStatus( doc ); else fout = fopen( filnam, "wb" ); if ( fout ) { uint outenc = cfg( doc, TidyOutCharEncoding ); uint nl = cfg( doc, TidyNewline ); StreamOut* out = TY_(FileOutput)( doc, fout, outenc, nl ); status = tidyDocSaveStream( doc, out ); fclose( fout ); TidyDocFree( doc, out ); #if PRESERVE_FILE_TIMES if ( doc->filetimes.actime ) { /* set file last accessed/modified times to original values */ utime( filnam, &doc->filetimes ); TidyClearMemory( &doc->filetimes, sizeof(doc->filetimes) ); } #endif /* PRESERVFILETIMES */ } if ( status < 0 ) /* Error message! */ TY_(ReportFileError)( doc, filnam, FILE_CANT_OPEN ); return status; } /* Note, _setmode() does NOT work on Win2K Pro w/ VC++ 6.0 SP3. ** The code has been left in in case it works w/ other compilers ** or operating systems. If stdout is in Text mode, be aware that ** it will garble UTF16 documents. In text mode, when it encounters ** a single byte of value 10 (0xA), it will insert a single byte ** value 13 (0xD) just before it. This has the effect of garbling ** the entire document. */ #if !defined(NO_SETMODE_SUPPORT) # if defined(_WIN32) || defined(OS2_OS) # include # include # endif #endif int tidyDocSaveStdout( TidyDocImpl* doc ) { #if !defined(NO_SETMODE_SUPPORT) # if defined(_WIN32) || defined(OS2_OS) int oldstdoutmode = -1, oldstderrmode = -1; # endif #endif int status = 0; uint outenc = cfg( doc, TidyOutCharEncoding ); uint nl = cfg( doc, TidyNewline ); StreamOut* out = TY_(FileOutput)( doc, stdout, outenc, nl ); #if !defined(NO_SETMODE_SUPPORT) # if defined(_WIN32) || defined(OS2_OS) oldstdoutmode = setmode( fileno(stdout), _O_BINARY ); oldstderrmode = setmode( fileno(stderr), _O_BINARY ); # endif #endif if ( 0 == status ) status = tidyDocSaveStream( doc, out ); fflush(stdout); fflush(stderr); #if !defined(NO_SETMODE_SUPPORT) # if defined(_WIN32) || defined(OS2_OS) if ( oldstdoutmode != -1 ) oldstdoutmode = setmode( fileno(stdout), oldstdoutmode ); if ( oldstderrmode != -1 ) oldstderrmode = setmode( fileno(stderr), oldstderrmode ); # endif #endif TidyDocFree( doc, out ); return status; } int tidyDocSaveString( TidyDocImpl* doc, tmbstr buffer, uint* buflen ) { uint outenc = cfg( doc, TidyOutCharEncoding ); uint nl = cfg( doc, TidyNewline ); TidyBuffer outbuf; StreamOut* out; int status; tidyBufInitWithAllocator( &outbuf, doc->allocator ); out = TY_(BufferOutput)( doc, &outbuf, outenc, nl ); status = tidyDocSaveStream( doc, out ); if ( outbuf.size > *buflen ) status = -ENOMEM; else memcpy( buffer, outbuf.bp, outbuf.size ); *buflen = outbuf.size; tidyBufFree( &outbuf ); TidyDocFree( doc, out ); return status; } int tidyDocSaveBuffer( TidyDocImpl* doc, TidyBuffer* outbuf ) { int status = -EINVAL; if ( outbuf ) { uint outenc = cfg( doc, TidyOutCharEncoding ); uint nl = cfg( doc, TidyNewline ); StreamOut* out = TY_(BufferOutput)( doc, outbuf, outenc, nl ); status = tidyDocSaveStream( doc, out ); TidyDocFree( doc, out ); } return status; } int tidyDocSaveSink( TidyDocImpl* doc, TidyOutputSink* sink ) { uint outenc = cfg( doc, TidyOutCharEncoding ); uint nl = cfg( doc, TidyNewline ); StreamOut* out = TY_(UserOutput)( doc, sink, outenc, nl ); int status = tidyDocSaveStream( doc, out ); TidyDocFree( doc, out ); return status; } int tidyDocStatus( TidyDocImpl* doc ) { if ( doc->errors > 0 ) return 2; if ( doc->warnings > 0 || doc->accessErrors > 0 ) return 1; return 0; } int TIDY_CALL tidyCleanAndRepair( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return tidyDocCleanAndRepair( impl ); return -EINVAL; } int TIDY_CALL tidyRunDiagnostics( TidyDoc tdoc ) { TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) return tidyDocRunDiagnostics( impl ); return -EINVAL; } int TIDY_CALL tidyReportDoctype( TidyDoc tdoc ) { int iret = -EINVAL; TidyDocImpl* impl = tidyDocToImpl( tdoc ); if ( impl ) { tidyDocReportDoctype( impl ); iret = 0; } return iret; } /* Workhorse functions. ** ** Parse requires input source, all input config items ** and diagnostic sink to have all been set before calling. ** ** Emit likewise requires that document sink and all ** pretty printing options have been set. */ static ctmbstr integrity = "\nPanic - tree has lost its integrity\n"; int TY_(DocParseStream)( TidyDocImpl* doc, StreamIn* in ) { Bool xmlIn = cfgBool( doc, TidyXmlTags ); TidyConfigChangeCallback callback = doc->pConfigChangeCallback; int bomEnc; doc->pConfigChangeCallback = NULL; assert( doc != NULL && in != NULL ); assert( doc->docIn == NULL ); doc->docIn = in; TY_(ResetTags)(doc); /* Reset table to html5 mode */ TY_(TakeConfigSnapshot)( doc ); /* Save config state */ TY_(AdjustConfig)( doc ); /* Ensure config internal consistency */ TY_(FreeAnchors)( doc ); TY_(FreeNode)(doc, &doc->root); TidyClearMemory(&doc->root, sizeof(Node)); if (doc->givenDoctype) TidyDocFree(doc, doc->givenDoctype); /*\ * Issue #186 - Now FreeNode depend on the doctype, so the lexer is needed * to determine which hash is to be used, so free it last. \*/ TY_(FreeLexer)( doc ); doc->givenDoctype = NULL; doc->lexer = TY_(NewLexer)( doc ); /* doc->lexer->root = &doc->root; */ doc->root.line = doc->lexer->lines; doc->root.column = doc->lexer->columns; doc->inputHadBOM = no; doc->xmlDetected = no; bomEnc = TY_(ReadBOMEncoding)(in); if (bomEnc != -1) { in->encoding = bomEnc; TY_(SetOptionInt)(doc, TidyInCharEncoding, bomEnc); } /* Tidy doesn't alter the doctype for generic XML docs */ if ( xmlIn ) { TY_(ParseXMLDocument)( doc ); if ( !TY_(CheckNodeIntegrity)( &doc->root ) ) TidyPanic( doc->allocator, integrity ); } else { doc->warnings = 0; TY_(ParseDocument)( doc ); if ( !TY_(CheckNodeIntegrity)( &doc->root ) ) TidyPanic( doc->allocator, integrity ); } doc->docIn = NULL; doc->pConfigChangeCallback = callback; return tidyDocStatus( doc ); } int tidyDocRunDiagnostics( TidyDocImpl* doc ) { TY_(ReportMarkupVersion)( doc ); TY_(ReportNumWarnings)( doc ); if ( doc->errors > 0 && !cfgBool( doc, TidyForceOutput ) ) TY_(Dialogue)(doc, STRING_NEEDS_INTERVENTION ); return tidyDocStatus( doc ); } void tidyDocReportDoctype( TidyDocImpl* doc ) { TY_(ReportMarkupVersion)( doc ); } /***************************************************************************** * HTML5 STUFF *****************************************************************************/ #if 0 && defined(ENABLE_DEBUG_LOG) extern void show_not_html5(void); /* ----------------------------- List tags that do not have version HTML5 (HT50|XH50) acronym applet basefont big center dir font frame frameset isindex listing noframes plaintext rb rbc rtc strike tt xmp nextid align bgsound blink comment ilayer layer marquee multicol nobr noembed nolayer nosave server servlet spacer Listed total 35 tags that do not have version 393216 ------------------------------ */ static void list_not_html5(void) { static Bool done_list = no; if (done_list == no) { done_list = yes; show_not_html5(); } } #endif /* What about , stike-through, underline */ static struct _html5Info { const char *tag; uint id; } const html5Info[] = { {"acronym", TidyTag_ACRONYM}, {"applet", TidyTag_APPLET }, {"basefont",TidyTag_BASEFONT }, { "big", TidyTag_BIG }, { "center", TidyTag_CENTER }, { "dir", TidyTag_DIR }, { "font", TidyTag_FONT }, { "frame", TidyTag_FRAME}, { "frameset", TidyTag_FRAMESET}, { "noframes", TidyTag_NOFRAMES }, { "strike", TidyTag_STRIKE }, { "tt", TidyTag_TT }, { 0, 0 } }; static Bool inRemovedInfo( uint tid ) { int i; for (i = 0; ; i++) { if (html5Info[i].tag == 0) break; if (html5Info[i].id == tid) return yes; } return no; } /* Things that should not be in an HTML5 body. This is special for CheckHTML5(), and we might just want to remove CheckHTML5()'s output altogether and count on the default --strict-tags-attributes. */ static int BadBody5Attribs[] = { TidyAttr_BACKGROUND, TidyAttr_BGCOLOR, TidyAttr_TEXT, TidyAttr_LINK, TidyAttr_VLINK, TidyAttr_ALINK, TidyAttr_UNKNOWN /* Must be last! */ }; static Bool nodeHasAlignAttr( Node *node ) { /* #define attrIsALIGN(av) AttrIsId( av, TidyAttr_ALIGN ) */ AttVal* av; for ( av = node->attributes; av != NULL; av = av->next ) { if (attrIsALIGN(av)) return yes; } return no; } /* * Perform special checks for HTML, even when we're not using the default * option `--strict-tags-attributes yes`. This will ensure that HTML5 warning * and error output is given regardless of the new option, and ensure that * cleanup takes place. This provides mostly consistent Tidy behavior even with * the introduction of this new option. Note that strings have changed, though, * in order to maintain consistency with the `--strict-tags-attributes` * messages. * * See also: http://www.whatwg.org/specs/web-apps/current-work/multipage/obsolete.html#obsolete */ static void TY_(CheckHTML5)( TidyDocImpl* doc, Node* node ) { Stack *stack = TY_(newStack)(doc, 16); Bool clean = cfgBool( doc, TidyMakeClean ); Bool already_strict = cfgBool( doc, TidyStrictTagsAttr ); Node* body = TY_(FindBody)( doc ); Node* next; Bool warn = yes; /* should this be a warning, error, or report??? */ AttVal* attr = NULL; int i = 0; while (node) { next = node->next; if ( nodeHasAlignAttr( node ) ) { /* @todo: Is this for ALL elements that accept an 'align' attribute, * or should this be a sub-set test? */ /* We will only emit this message if `--strict-tags-attributes==no`; * otherwise if yes this message will be output during later * checking. */ if ( !already_strict ) TY_(ReportAttrError)(doc, node, TY_(AttrGetById)(node, TidyAttr_ALIGN), MISMATCHED_ATTRIBUTE_WARN); } if ( node == body ) { i = 0; /* We will only emit these messages if `--strict-tags-attributes==no`; * otherwise if yes these messages will be output during later * checking. */ if ( !already_strict ) { while ( BadBody5Attribs[i] != TidyAttr_UNKNOWN ) { attr = TY_(AttrGetById)(node, BadBody5Attribs[i]); if ( attr ) TY_(ReportAttrError)(doc, node, attr , MISMATCHED_ATTRIBUTE_WARN); i++; } } } else if ( nodeIsACRONYM(node) ) { if (clean) { /* Replace with 'abbr' with warning to that effect. * Maybe should use static void RenameElem( TidyDocImpl* doc, Node* node, TidyTagId tid ) */ TY_(CoerceNode)(doc, node, TidyTag_ABBR, warn, no); } else { if ( !already_strict ) TY_(Report)(doc, node, node, REMOVED_HTML5); } } else if ( nodeIsAPPLET(node) ) { if (clean) { /* replace with 'object' with warning to that effect * maybe should use static void RenameElem( TidyDocImpl* doc, Node* node, TidyTagId tid ) */ TY_(CoerceNode)(doc, node, TidyTag_OBJECT, warn, no); } else { if ( !already_strict ) TY_(Report)(doc, node, node, REMOVED_HTML5); } } else if ( nodeIsBASEFONT(node) ) { /* basefont: CSS equivalent 'font-size', 'font-family' and 'color' * on body or class on each subsequent element. * Difficult - If it is the first body element, then could consider * adding that to the as a whole, else could perhaps apply it * to all subsequent elements. But also in consideration is the fact * that it was NOT supported in many browsers. * - For now just report a warning */ if ( !already_strict ) TY_(Report)(doc, node, node, REMOVED_HTML5); } else if ( nodeIsBIG(node) ) { /* big: CSS equivalent 'font-size:larger' * so could replace the ... with * ... * then replace with * Need to think about that... * Could use - * TY_(AddStyleProperty)( doc, node, "font-size: larger" ); * TY_(CoerceNode)(doc, node, TidyTag_SPAN, no, no); * Alternatively generated a