/* -*- mode: C++; tab-width: 4; c-basic-offset: 4; -*- */
/* AbiWord: ie_imp_HTML - plugin for Multipart [X]HTML
*
* Copyright (C) 2001-2003 Francis James Franklin <fjf@alinameridon.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
* 02111-1307, USA.
*/
#include "ut_html.h"
#include "ie_FileInfo.h"
#include "ie_imp_HTML.h"
IE_Imp_HTML_Sniffer::IE_Imp_HTML_Sniffer ()
#ifdef XHTML_NAMED_CONSTRUCTORS
: IE_ImpSniffer("AbiXHTML::HTML libxml2")
#endif
{
//
}
#ifdef XHTML_NAMED_CONSTRUCTORS
UT_Confidence_t IE_Imp_HTML_Sniffer::supportsMIME (const char * szMIME)
{
if (UT_strcmp (IE_FileInfo::mapAlias (szMIME), IE_MIME_HTML) == 0)
{
return UT_CONFIDENCE_GOOD;
}
return UT_CONFIDENCE_ZILCH;
}
#endif /* XHTML_NAMED_CONSTRUCTORS */
UT_Confidence_t IE_Imp_HTML_Sniffer::recognizeContents (const char * szBuf, UT_uint32 iNumbytes)
{
UT_uint32 iLinesToRead = 6 ; // Only examine the first few lines of the file
UT_uint32 iBytesScanned = 0 ;
const char *p ;
char *magic ;
p = szBuf ;
while( iLinesToRead-- )
{
magic = "<html" ;
if ( (iNumbytes - iBytesScanned) < strlen(magic) ) return(UT_CONFIDENCE_ZILCH);
if ( strncmp(p, magic, strlen(magic)) == 0 ) return(UT_CONFIDENCE_PERFECT);
magic = "<!DOCTYPE html" ;
if ( (iNumbytes - iBytesScanned) < strlen(magic) ) return(UT_CONFIDENCE_ZILCH);
if ( strncmp(p, magic, strlen(magic)) == 0 ) return(UT_CONFIDENCE_PERFECT);
magic = "<!DOCTYPE HTML" ;
if ( (iNumbytes - iBytesScanned) < strlen(magic) ) return(UT_CONFIDENCE_ZILCH);
if ( strncmp(p, magic, strlen(magic)) == 0 ) return(UT_CONFIDENCE_PERFECT);
/* Seek to the next newline: */
while ( *p != '\n' && *p != '\r' )
{
iBytesScanned++ ; p++ ;
if( iBytesScanned+2 >= iNumbytes ) return(UT_CONFIDENCE_ZILCH);
}
/* Seek past the next newline: */
if ( *p == '\n' || *p == '\r' )
{
iBytesScanned++ ; p++ ;
if ( *p == '\n' || *p == '\r' )
{
iBytesScanned++ ; p++ ;
}
}
}
return UT_CONFIDENCE_ZILCH;
}
UT_Confidence_t IE_Imp_HTML_Sniffer::recognizeSuffix (const char * szSuffix)
{
if (!(UT_stricmp(szSuffix,".html")) || !(UT_stricmp(szSuffix,".htm")))
return UT_CONFIDENCE_PERFECT;
return UT_CONFIDENCE_ZILCH;
}
UT_Error IE_Imp_HTML_Sniffer::constructImporter (PD_Document * pDocument, IE_Imp ** ppie)
{
IE_Imp_XHTML * p = new IE_Imp_HTML(pDocument);
*ppie = p;
return UT_OK;
}
bool IE_Imp_HTML_Sniffer::getDlgLabels (const char ** pszDesc,
const char ** pszSuffixList,
IEFileType * ft)
{
*pszDesc = "HTML [via libxml2] (.html, .htm)";
*pszSuffixList = "*.html; *.htm";
*ft = getFileType();
return true;
}
IE_Imp_HTML::IE_Imp_HTML (PD_Document * pDocument) :
IE_Imp_XHTML(pDocument)
{
//
}
IE_Imp_HTML::~IE_Imp_HTML ()
{
//
}
UT_Error IE_Imp_HTML::importFile (const char * szFilename)
{
UT_HTML parser;
setParser (&parser);
UT_Error e = IE_Imp_XHTML::importFile (szFilename);
setParser (0);
return e;
}