source: gaycko/trunk/src/parsing/parse.c @ 4720 Tweet

#include "parse.h"


gDOM *gaycko_parse(char *data, unsigned int size) {

        /* Clean up and repair bad HTML */
        TidyDoc tdoc = tidyCreate();
        TidyBuffer errbuf = {0};

        TidyBuffer output = {0};

        Bool ok;
        int rc = -1;

        ok = tidyOptSetBool( tdoc, TidyXhtmlOut, yes );  // Convert to XHTML
        if ( ok )
                rc = tidySetErrorBuffer( tdoc, &errbuf );      // Capture diagnostics
        if ( rc >= 0 )
                rc = tidyParseString( tdoc, data );           // Parse the input
        if ( rc >= 0 )
                rc = tidyCleanAndRepair( tdoc );               // Tidy it up!
        if ( rc > 1 )                                    // If error, force output.
                rc = ( tidyOptSetBool(tdoc, TidyForceOutput, yes) ? rc : -1 );
        if ( rc >= 0 )
                rc = tidySaveBuffer( tdoc, &output );          // Pretty Print

        /* Actual parsing */
        htmlDocPtr doc = htmlParseDoc((unsigned char*)output.bp, NULL);


        //tidyBufFree( &output );
        //tidyBufFree( &errbuf );
        tidyRelease( tdoc );


        gDOM *dom = gaycko_convert_dom(doc);

        return dom;
}