htmltidy/src/tidylib.c

/* 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

  Modified 2016-09-09 by Bob Rudis for the R package htmltidy

*/

#include <errno.h>

#include "tidy-int.h"
#include "parser.h"
#include "clean.h"
#include "gdoc.h"
#include "config.h"
#include "message.h"
#include "pprint.h"
#include "entities.h"
#include "tmbstr.h"
#include "utf8.h"
#include "mappedio.h"

#ifdef TIDY_WIN32_MLANG_SUPPORT
#include "win32tc.h"
#endif
#if !defined(NDEBUG) && defined(_MSC_VER)
#include "sprtf.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 );

#ifdef NEVER
TidyDocImpl* tidyDocToImpl( TidyDoc tdoc )
{
  return (TidyDocImpl*) tdoc;
}
TidyDoc      tidyImplToDoc( TidyDocImpl* impl )
{
  return (TidyDoc) impl;
}

Node*        tidyNodeToImpl( TidyNode tnod )
{
  return (Node*) tnod;
}
TidyNode     tidyImplToNode( Node* node )
{
  return (TidyNode) node;
}

AttVal*      tidyAttrToImpl( TidyAttr tattr )
{
  return (AttVal*) tattr;
}
TidyAttr     tidyImplToAttr( AttVal* attval )
{
  return (TidyAttr) attval;
}

const TidyOptionImpl* tidyOptionToImpl( TidyOption topt )
{
  return (const TidyOptionImpl*) topt;
}
TidyOption   tidyImplToOption( const TidyOptionImpl* option )
{
  return (TidyOption) option;
}
#endif

/* 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 );

    /* 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_(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 );
        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)();
}


/* 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;
}


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;
}
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 );
    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;
    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 )
    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 )
        opti = cfg( impl, optId );
    return opti;
}

Bool TIDY_CALL        tidyOptSetInt( TidyDoc tdoc, TidyOptionId optId, ulong val )
{
    TidyDocImpl* impl = tidyDocToImpl( tdoc );
    if ( impl )
        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 )
{
    const TidyOptionImpl* option = TY_(getOption)( optId );
    if ( option && option->pickList )
    {
        uint ix, pick = tidyOptGetInt( tdoc, optId );
        const ctmbstr* pL = option->pickList;
        for ( ix=0; *pL && ix < pick; ++ix )
            ++pL;
        if ( *pL )
            return *pL;
    }
    return NULL;
}


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;
}

ctmbstr TIDY_CALL tidyOptGetDoc( TidyDoc ARG_UNUSED(tdoc), TidyOption opt )
{
    const TidyOptionId optId = tidyOptGetId( opt );
    return tidyLocalizedString(optId);
}

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;
}

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
** tdocances 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.
*/

/* 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->mssgFilt = filt;
    return yes;
  }
  return no;
}

/* TidyReportFilter2 functions similar to TidyReportFilter, but provides the
** built-in English format string and va_list so that LibTidy users can use
** the format string as a lookup key for providing their own error
** localizations.
*/
Bool TIDY_CALL        tidySetReportFilter2( TidyDoc tdoc, TidyReportFilter2 filt )
{
  TidyDocImpl* impl = tidyDocToImpl( tdoc );
  if ( impl )
  {
    impl->mssgFilt2 = filt;
    return yes;
  }
  return no;
}

/* TidyReportFilter3 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 definitions in language.h
*/
Bool TIDY_CALL        tidySetReportFilter3( TidyDoc tdoc, TidyReportFilter3 filt )
{
  TidyDocImpl* impl = tidyDocToImpl( tdoc );
  if ( impl )
  {
    impl->mssgFilt3 = filt;
    return yes;
  }
  return no;
}

#if 0   /* Not yet */
int         tidySetContentOutputSink( TidyDoc tdoc, TidyOutputSink* outp )
{
  TidyDocImpl* impl = tidyDocToImpl( tdoc );
  if ( impl )
  {
    impl->docOut = outp;
    return 0;
  }
  return -EINVAL;
}
int         tidySetDiagnosticOutputSink( TidyDoc tdoc, TidyOutputSink* outp )
{
  TidyDocImpl* impl = tidyDocToImpl( tdoc );
  if ( impl )
  {
    impl->msgOut = outp;
    return 0;
  }
  return -EINVAL;
}


/* Library helpers
*/
cmbstr       tidyLookupMessage( TidyDoc tdoc, int errorNo )
{
  TidyDocImpl* impl = tidyDocToImpl( tdoc );
  cmbstr mssg = NULL;
  if ( impl )
    mssg = tidyMessage_Lookup( impl->messages, errorNo );
  return mssg;
}
#endif


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_(FileError)( impl, errfilnam, TidyError );
    }
    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 0;
}
Bool TIDY_CALL        tidyDetectedXhtml( TidyDoc ARG_UNUSED(tdoc) )
{
/*    TidyDocImpl* impl = tidyDocToImpl( tdoc ); */
    return no;
}
Bool TIDY_CALL        tidyDetectedGenericXml( TidyDoc ARG_UNUSED(tdoc) )
{
/*    TidyDocImpl* impl = tidyDocToImpl( tdoc ); */
    return no;
}

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_(GeneralInfo)( impl );
}


/* 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 );
}


int   tidyDocParseFile( TidyDocImpl* doc, ctmbstr filnam )
{
#ifdef _WIN32
    return TY_(DocParseFileWithMappedFile)( doc, filnam );
#else
    int status = -ENOENT;
    FILE* fin = fopen( filnam, "rb" );

#if PRESERVE_FILE_TIMES
    struct stat sbuf = {0};
    /* 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_(FileError)( doc, filnam, TidyError );
    return status;
#endif
}

int   tidyDocParseStdin( TidyDocImpl* doc )
{
    StreamIn* in = TY_(FileInput)( doc, stdin, cfg( doc, TidyInCharEncoding ));
    int status = TY_(DocParseStream)( doc, in );
    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_(FileError)( doc, filnam, TidyError );
    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 <fcntl.h>
#include <io.h>
#endif

#endif

int         tidyDocSaveStdout( TidyDocImpl* doc )
{
#if !defined(NO_SETMODE_SUPPORT)

#endif
    int status = 0;
//    uint outenc = cfg( doc, TidyOutCharEncoding );
//    uint nl = cfg( doc, TidyNewline );
//    StreamOut* out = TY_(FileOutput)( doc, stdout, outenc, nl );

//    if ( 0 == status )
//      status = tidyDocSaveStream( doc, out );

//    fflush(stdout);
//    fflush(stderr);



//    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;
}