strepsirrhini/office-gobmx
9
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
office-gobmx/sal/textenc/tcvtmb.c

727 lines
28 KiB
C
Raw Normal View History

initial import
2000-09-18 09:18:43 -05:00
/*************************************************************************
*
* $RCSfile: tcvtmb.c,v $
*
INTEGRATION: CWS ooo20031216 (1.10.120); FILE MERGED 2003/12/20 14:01:32 waratah 1.10.120.1: #i1858# correct some unitialised fields in code
2004-02-04 06:52:05 -06:00
* $Revision: 1.11 $
initial import
2000-09-18 09:18:43 -05:00
*
INTEGRATION: CWS ooo20031216 (1.10.120); FILE MERGED 2003/12/20 14:01:32 waratah 1.10.120.1: #i1858# correct some unitialised fields in code
2004-02-04 06:52:05 -06:00
* last change: $Author: hr $ $Date: 2004-02-04 13:52:05 $
initial import
2000-09-18 09:18:43 -05:00
*
* The Contents of this file are made available subject to the terms of
* either of the following licenses
*
* - GNU Lesser General Public License Version 2.1
* - Sun Industry Standards Source License Version 1.1
*
* Sun Microsystems Inc., October, 2000
*
* GNU Lesser General Public License Version 2.1
* =============================================
* Copyright 2000 by Sun Microsystems, Inc.
* 901 San Antonio Road, Palo Alto, CA 94303, USA
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License version 2.1, as published by the Free Software Foundation.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston,
* MA 02111-1307 USA
*
*
* Sun Industry Standards Source License Version 1.1
* =================================================
* The contents of this file are subject to the Sun Industry Standards
* Source License Version 1.1 (the "License"); You may not use this file
* except in compliance with the License. You may obtain a copy of the
* License at http://www.openoffice.org/license.html.
*
* Software provided under this License is provided on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
* WITHOUT LIMITATION, WARRANTIES THAT THE SOFTWARE IS FREE OF DEFECTS,
* MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE, OR NON-INFRINGING.
* See the License for the specific provisions governing your rights and
* obligations concerning the Software.
*
* The Initial Developer of the Original Code is: Sun Microsystems, Inc.
*
* Copyright: 2000 by Sun Microsystems, Inc.
*
* All Rights Reserved.
*
* Contributor(s): _______________________________________
*
*
************************************************************************/
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
#ifndef INCLUDED_RTL_TEXTENC_TENCHELP_H
#include "tenchelp.h"
initial import
2000-09-18 09:18:43 -05:00
#endif
#87140# More cleanup.
2001-10-17 08:35:30 -05:00
#ifndef INCLUDED_RTL_TEXTENC_UNICHARS_H
#include "unichars.h"
#endif
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
initial import
2000-09-18 09:18:43 -05:00
#ifndef _RTL_TEXTCVT_H
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
#include "rtl/textcvt.h"
initial import
2000-09-18 09:18:43 -05:00
#endif
/* ======================================================================= */
/* DBCS to Unicode conversion routine use a lead table for the first byte, */
/* where we determine the trail table or for single byte chars the unicode */
/* value. We have for all lead byte a separate table, because we can */
/* then share many tables for diffrent charset encodings. */
/* ======================================================================= */
sal_Size ImplDBCSToUnicode( const ImplTextConverterData* pData, void* pContext,
const sal_Char* pSrcBuf, sal_Size nSrcBytes,
sal_Unicode* pDestBuf, sal_Size nDestChars,
sal_uInt32 nFlags, sal_uInt32* pInfo,
sal_Size* pSrcCvtBytes )
{
sal_uChar cLead;
sal_uChar cTrail;
sal_Unicode cConv;
const ImplDBCSToUniLeadTab* pLeadEntry;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
const ImplDBCSConvertData* pConvertData = (const ImplDBCSConvertData*)pData;
initial import
2000-09-18 09:18:43 -05:00
const ImplDBCSToUniLeadTab* pLeadTab = pConvertData->mpToUniLeadTab;
sal_Unicode* pEndDestBuf;
const sal_Char* pEndSrcBuf;
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestChars;
pEndSrcBuf = pSrcBuf+nSrcBytes;
while ( pSrcBuf < pEndSrcBuf )
{
cLead = (sal_uChar)*pSrcBuf;
/* get entry for the lead byte */
pLeadEntry = pLeadTab+cLead;
/* SingleByte char? */
MWS_SRX644: migrate branch mws_srx644 -> HEAD
2003-03-26 09:47:28 -06:00
if (pLeadEntry->mpToUniTrailTab == NULL
|| cLead < pConvertData->mnLeadStart
|| cLead > pConvertData->mnLeadEnd)
initial import
2000-09-18 09:18:43 -05:00
{
cConv = pLeadEntry->mnUniChar;
if ( !cConv && (cLead != 0) )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_UNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_ERROR )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
else if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_IGNORE )
{
pSrcBuf++;
continue;
}
else
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
cConv = ImplGetUndefinedUnicodeChar(cLead, nFlags);
initial import
2000-09-18 09:18:43 -05:00
}
}
else
{
/* Source buffer to small */
Bug #92156#: detect correct the end of the source buffer
2001-09-19 08:02:35 -05:00
if ( pSrcBuf +1 == pEndSrcBuf )
initial import
2000-09-18 09:18:43 -05:00
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
break;
}
pSrcBuf++;
cTrail = (sal_uChar)*pSrcBuf;
if ( (cTrail >= pLeadEntry->mnTrailStart) && (cTrail <= pLeadEntry->mnTrailEnd) )
cConv = pLeadEntry->mpToUniTrailTab[cTrail-pLeadEntry->mnTrailStart];
else
cConv = 0;
if ( !cConv )
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
/* EUDC Ranges */
initial import
2000-09-18 09:18:43 -05:00
sal_uInt16 i;
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
const ImplDBCSEUDCData* pEUDCTab = pConvertData->mpEUDCTab;
for ( i = 0; i < pConvertData->mnEUDCCount; i++ )
initial import
2000-09-18 09:18:43 -05:00
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
if ( (cLead >= pEUDCTab->mnLeadStart) &&
(cLead <= pEUDCTab->mnLeadEnd) )
initial import
2000-09-18 09:18:43 -05:00
{
sal_uInt16 nTrailCount = 0;
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
if ( (cTrail >= pEUDCTab->mnTrail1Start) &&
(cTrail <= pEUDCTab->mnTrail1End) )
initial import
2000-09-18 09:18:43 -05:00
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
cConv = pEUDCTab->mnUniStart+
((cLead-pEUDCTab->mnLeadStart)*pEUDCTab->mnTrailRangeCount)+
(cTrail-pEUDCTab->mnTrail1Start);
initial import
2000-09-18 09:18:43 -05:00
break;
}
else
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
nTrailCount = pEUDCTab->mnTrail1End-pEUDCTab->mnTrail1Start+1;
if ( (pEUDCTab->mnTrailCount >= 2) &&
(cTrail >= pEUDCTab->mnTrail2Start) &&
(cTrail <= pEUDCTab->mnTrail2End) )
initial import
2000-09-18 09:18:43 -05:00
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
cConv = pEUDCTab->mnUniStart+
((cLead-pEUDCTab->mnLeadStart)*pEUDCTab->mnTrailRangeCount)+
initial import
2000-09-18 09:18:43 -05:00
nTrailCount+
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
(cTrail-pEUDCTab->mnTrail2Start);
initial import
2000-09-18 09:18:43 -05:00
break;
}
else
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
nTrailCount = pEUDCTab->mnTrail2End-pEUDCTab->mnTrail2Start+1;
if ( (pEUDCTab->mnTrailCount >= 3) &&
(cTrail >= pEUDCTab->mnTrail3Start) &&
(cTrail <= pEUDCTab->mnTrail3End) )
initial import
2000-09-18 09:18:43 -05:00
{
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
cConv = pEUDCTab->mnUniStart+
((cLead-pEUDCTab->mnLeadStart)*pEUDCTab->mnTrailRangeCount)+
initial import
2000-09-18 09:18:43 -05:00
nTrailCount+
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
(cTrail-pEUDCTab->mnTrail3Start);
initial import
2000-09-18 09:18:43 -05:00
break;
}
}
}
}
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
pEUDCTab++;
initial import
2000-09-18 09:18:43 -05:00
}
if ( !cConv )
{
/* Wir vergleichen den kompletten Trailbereich den wir */
/* definieren, der normalerweise groesser sein kann als */
/* der definierte. Dies machen wir, damit Erweiterungen von */
/* uns nicht beruecksichtigten Encodings so weit wie */
/* moeglich auch richtig zu behandeln, das double byte */
/* characters auch als ein einzelner Character behandelt */
/* wird. */
MWS_SRX644: migrate branch mws_srx644 -> HEAD
2003-03-26 09:47:28 -06:00
if (cLead < pConvertData->mnLeadStart
|| cLead > pConvertData->mnLeadEnd
|| cTrail < pConvertData->mnTrailStart
|| cTrail > pConvertData->mnTrailEnd)
initial import
2000-09-18 09:18:43 -05:00
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
else if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_IGNORE )
{
pSrcBuf++;
continue;
}
else
#87140# More cleanup.
2001-10-17 08:35:30 -05:00
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
initial import
2000-09-18 09:18:43 -05:00
}
else
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_MBUNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
else if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_IGNORE )
{
pSrcBuf++;
continue;
}
else
#87140# More cleanup.
2001-10-17 08:35:30 -05:00
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
initial import
2000-09-18 09:18:43 -05:00
}
}
}
}
if ( pDestBuf == pEndDestBuf )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = cConv;
pDestBuf++;
pSrcBuf++;
}
*pSrcCvtBytes = nSrcBytes - (pEndSrcBuf-pSrcBuf);
return (nDestChars - (pEndDestBuf-pDestBuf));
}
/* ----------------------------------------------------------------------- */
sal_Size ImplUnicodeToDBCS( const ImplTextConverterData* pData, void* pContext,
const sal_Unicode* pSrcBuf, sal_Size nSrcChars,
sal_Char* pDestBuf, sal_Size nDestBytes,
sal_uInt32 nFlags, sal_uInt32* pInfo,
sal_Size* pSrcCvtChars )
{
sal_uInt16 cConv;
sal_Unicode c;
sal_uChar nHighChar;
sal_uChar nLowChar;
const ImplUniToDBCSHighTab* pHighEntry;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
const ImplDBCSConvertData* pConvertData = (const ImplDBCSConvertData*)pData;
initial import
2000-09-18 09:18:43 -05:00
const ImplUniToDBCSHighTab* pHighTab = pConvertData->mpToDBCSHighTab;
sal_Char* pEndDestBuf;
const sal_Unicode* pEndSrcBuf;
MWS_SRX644: migrate branch mws_srx644 -> HEAD
2003-03-26 09:47:28 -06:00
sal_Bool bCheckRange = (pConvertData->mnLeadStart != 0
|| pConvertData->mnLeadEnd != 0xFF);
/* this statement has the effect that this extra check is only done for
EUC-KR, which uses the MS-949 tables, but does not support the full
range of MS-949 */
initial import
2000-09-18 09:18:43 -05:00
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestBytes;
pEndSrcBuf = pSrcBuf+nSrcChars;
while ( pSrcBuf < pEndSrcBuf )
{
c = *pSrcBuf;
nHighChar = (sal_uChar)((c >> 8) & 0xFF);
nLowChar = (sal_uChar)(c & 0xFF);
/* get entry for the high byte */
pHighEntry = pHighTab+nHighChar;
/* is low byte in the table range */
if ( (nLowChar >= pHighEntry->mnLowStart) && (nLowChar <= pHighEntry->mnLowEnd) )
MWS_SRX644: migrate branch mws_srx644 -> HEAD
2003-03-26 09:47:28 -06:00
{
initial import
2000-09-18 09:18:43 -05:00
cConv = pHighEntry->mpToUniTrailTab[nLowChar-pHighEntry->mnLowStart];
MWS_SRX644: migrate branch mws_srx644 -> HEAD
2003-03-26 09:47:28 -06:00
if (bCheckRange && cConv > 0x7F
&& ((cConv >> 8) < pConvertData->mnLeadStart
|| (cConv >> 8) > pConvertData->mnLeadEnd
|| (cConv & 0xFF) < pConvertData->mnTrailStart
|| (cConv & 0xFF) > pConvertData->mnTrailEnd))
cConv = 0;
}
initial import
2000-09-18 09:18:43 -05:00
else
cConv = 0;
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
if (cConv == 0 && c != 0)
initial import
2000-09-18 09:18:43 -05:00
{
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
/* Map to EUDC ranges: */
ImplDBCSEUDCData const * pEUDCTab = pConvertData->mpEUDCTab;
sal_uInt32 i;
for (i = 0; i < pConvertData->mnEUDCCount; ++i)
initial import
2000-09-18 09:18:43 -05:00
{
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
if (c >= pEUDCTab->mnUniStart && c <= pEUDCTab->mnUniEnd)
initial import
2000-09-18 09:18:43 -05:00
{
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
sal_uInt32 nIndex = c - pEUDCTab->mnUniStart;
sal_uInt32 nLeadOff
= nIndex / pEUDCTab->mnTrailRangeCount;
sal_uInt32 nTrailOff
= nIndex % pEUDCTab->mnTrailRangeCount;
sal_uInt32 nSize;
cConv = (sal_uInt16)
((pEUDCTab->mnLeadStart + nLeadOff) << 8);
nSize
= pEUDCTab->mnTrail1End - pEUDCTab->mnTrail1Start + 1;
if (nTrailOff < nSize)
initial import
2000-09-18 09:18:43 -05:00
{
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
cConv |= pEUDCTab->mnTrail1Start + nTrailOff;
break;
initial import
2000-09-18 09:18:43 -05:00
}
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
nTrailOff -= nSize;
nSize
= pEUDCTab->mnTrail2End - pEUDCTab->mnTrail2Start + 1;
if (nTrailOff < nSize)
{
cConv |= pEUDCTab->mnTrail2Start + nTrailOff;
break;
}
nTrailOff -= nSize;
cConv |= pEUDCTab->mnTrail3Start + nTrailOff;
initial import
2000-09-18 09:18:43 -05:00
break;
}
#81658# - remove JIS Convert Function
2000-12-13 15:20:31 -06:00
pEUDCTab++;
initial import
2000-09-18 09:18:43 -05:00
}
#97705# Fixed mapping of Big5 EUDC points.
2002-02-25 07:57:35 -06:00
/* FIXME
* SB: Not sure why this is in here. Plus, it does not work as
* intended when (c & 0xFF) == 0, because the next !cConv check
* will then think c has not yet been converted...
*/
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
if (c >= RTL_TEXTCVT_BYTE_PRIVATE_START
&& c <= RTL_TEXTCVT_BYTE_PRIVATE_END)
initial import
2000-09-18 09:18:43 -05:00
{
if ( nFlags & RTL_UNICODETOTEXT_FLAGS_PRIVATE_MAPTO0 )
cConv = (sal_Char)(sal_uChar)(c & 0xFF);
}
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
}
initial import
2000-09-18 09:18:43 -05:00
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
if ( !cConv )
{
if ( nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACE )
initial import
2000-09-18 09:18:43 -05:00
{
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
/* !!! */
}
initial import
2000-09-18 09:18:43 -05:00
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
if ( nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACESTR )
{
/* !!! */
initial import
2000-09-18 09:18:43 -05:00
}
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
/* Handle undefined and surrogates characters */
/* (all surrogates characters are undefined) */
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
if (ImplHandleUndefinedUnicodeToTextChar(pData,
&pSrcBuf,
pEndSrcBuf,
&pDestBuf,
pEndDestBuf,
nFlags,
pInfo))
#81346# - Fix for unconverted characters for DBCS encodings
2000-12-07 03:48:42 -06:00
continue;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
else
break;
initial import
2000-09-18 09:18:43 -05:00
}
/* SingleByte */
if ( !(cConv & 0xFF00) )
{
if ( pDestBuf == pEndDestBuf )
{
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = (sal_Char)(sal_uChar)(cConv & 0xFF);
pDestBuf++;
}
else
{
if ( pDestBuf+1 >= pEndDestBuf )
{
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = (sal_Char)(sal_uChar)((cConv >> 8) & 0xFF);
pDestBuf++;
*pDestBuf = (sal_Char)(sal_uChar)(cConv & 0xFF);
pDestBuf++;
}
pSrcBuf++;
}
*pSrcCvtChars = nSrcChars - (pEndSrcBuf-pSrcBuf);
return (nDestBytes - (pEndDestBuf-pDestBuf));
}
/* ======================================================================= */
#define JIS_EUC_LEAD_OFF 0x80
#define JIS_EUC_TRAIL_OFF 0x80
/* ----------------------------------------------------------------------- */
sal_Size ImplEUCJPToUnicode( const ImplTextConverterData* pData,
void* pContext,
const sal_Char* pSrcBuf, sal_Size nSrcBytes,
sal_Unicode* pDestBuf, sal_Size nDestChars,
sal_uInt32 nFlags, sal_uInt32* pInfo,
sal_Size* pSrcCvtBytes )
{
sal_uChar c;
INTEGRATION: CWS ooo20031216 (1.10.120); FILE MERGED 2003/12/20 14:01:32 waratah 1.10.120.1: #i1858# correct some unitialised fields in code
2004-02-04 06:52:05 -06:00
sal_uChar cLead = '\0';
sal_uChar cTrail = '\0';
initial import
2000-09-18 09:18:43 -05:00
sal_Unicode cConv;
const ImplDBCSToUniLeadTab* pLeadEntry;
const ImplDBCSToUniLeadTab* pLeadTab;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
const ImplEUCJPConvertData* pConvertData = (const ImplEUCJPConvertData*)pData;
initial import
2000-09-18 09:18:43 -05:00
sal_Unicode* pEndDestBuf;
const sal_Char* pEndSrcBuf;
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestChars;
pEndSrcBuf = pSrcBuf+nSrcBytes;
while ( pSrcBuf < pEndSrcBuf )
{
c = (sal_uChar)*pSrcBuf;
/* ASCII */
if ( c <= 0x7F )
cConv = c;
else
{
/* SS2 - Half-width katakana */
/* 8E + A1-DF */
if ( c == 0x8E )
{
/* Source buffer to small */
Bug #92156#: detect correct the end of the source buffer
2001-09-19 08:02:35 -05:00
if ( pSrcBuf + 1 == pEndSrcBuf )
initial import
2000-09-18 09:18:43 -05:00
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
break;
}
pSrcBuf++;
c = (sal_uChar)*pSrcBuf;
if ( (c >= 0xA1) && (c <= 0xDF) )
cConv = 0xFF61+(c-0xA1);
else
{
cConv = 0;
cLead = 0x8E;
cTrail = c;
}
}
else
{
/* SS3 - JIS 0212-1990 */
/* 8F + A1-FE + A1-FE */
if ( c == 0x8F )
{
/* Source buffer to small */
#96665# Fixed source-buffer-too-small check in ImplEUCJPToUnicode.
2002-01-18 03:49:51 -06:00
if (pEndSrcBuf - pSrcBuf < 3)
initial import
2000-09-18 09:18:43 -05:00
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
break;
}
pSrcBuf++;
cLead = (sal_uChar)*pSrcBuf;
pSrcBuf++;
cTrail = (sal_uChar)*pSrcBuf;
pLeadTab = pConvertData->mpJIS0212ToUniLeadTab;
}
/* CodeSet 2 JIS 0208-1997 */
/* A1-FE + A1-FE */
else
{
/* Source buffer to small */
Bug #92156#: detect correct the end of the source buffer
2001-09-19 08:02:35 -05:00
if ( pSrcBuf + 1 == pEndSrcBuf )
initial import
2000-09-18 09:18:43 -05:00
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
break;
}
cLead = c;
pSrcBuf++;
cTrail = (sal_uChar)*pSrcBuf;
pLeadTab = pConvertData->mpJIS0208ToUniLeadTab;
}
/* Undefined Range */
if ( (cLead < JIS_EUC_LEAD_OFF) || (cTrail < JIS_EUC_TRAIL_OFF) )
cConv = 0;
else
{
cLead -= JIS_EUC_LEAD_OFF;
cTrail -= JIS_EUC_TRAIL_OFF;
pLeadEntry = pLeadTab+cLead;
if ( (cTrail >= pLeadEntry->mnTrailStart) && (cTrail <= pLeadEntry->mnTrailEnd) )
cConv = pLeadEntry->mpToUniTrailTab[cTrail-pLeadEntry->mnTrailStart];
else
cConv = 0;
}
}
if ( !cConv )
{
/* Wir vergleichen den kompletten Trailbereich den wir */
/* definieren, der normalerweise groesser sein kann als */
/* der definierte. Dies machen wir, damit Erweiterungen von */
/* uns nicht beruecksichtigten Encodings so weit wie */
/* moeglich auch richtig zu behandeln, das double byte */
/* characters auch als ein einzelner Character behandelt */
/* wird. */
if ( (cLead < JIS_EUC_LEAD_OFF) || (cTrail < JIS_EUC_TRAIL_OFF) )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
else if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_IGNORE )
{
pSrcBuf++;
continue;
}
else
#87140# More cleanup.
2001-10-17 08:35:30 -05:00
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
initial import
2000-09-18 09:18:43 -05:00
}
else
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_MBUNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
else if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) == RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_IGNORE )
{
pSrcBuf++;
continue;
}
else
#87140# More cleanup.
2001-10-17 08:35:30 -05:00
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
initial import
2000-09-18 09:18:43 -05:00
}
}
}
if ( pDestBuf == pEndDestBuf )
{
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = cConv;
pDestBuf++;
pSrcBuf++;
}
*pSrcCvtBytes = nSrcBytes - (pEndSrcBuf-pSrcBuf);
return (nDestChars - (pEndDestBuf-pDestBuf));
}
/* ----------------------------------------------------------------------- */
sal_Size ImplUnicodeToEUCJP( const ImplTextConverterData* pData,
void* pContext,
const sal_Unicode* pSrcBuf, sal_Size nSrcChars,
sal_Char* pDestBuf, sal_Size nDestBytes,
sal_uInt32 nFlags, sal_uInt32* pInfo,
sal_Size* pSrcCvtChars )
{
sal_uInt32 cConv;
sal_Unicode c;
sal_uChar nHighChar;
sal_uChar nLowChar;
const ImplUniToDBCSHighTab* pHighEntry;
const ImplUniToDBCSHighTab* pHighTab;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
const ImplEUCJPConvertData* pConvertData = (const ImplEUCJPConvertData*)pData;
initial import
2000-09-18 09:18:43 -05:00
sal_Char* pEndDestBuf;
const sal_Unicode* pEndSrcBuf;
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestBytes;
pEndSrcBuf = pSrcBuf+nSrcChars;
while ( pSrcBuf < pEndSrcBuf )
{
c = *pSrcBuf;
/* ASCII */
if ( c <= 0x7F )
cConv = c;
/* Half-width katakana */
else if ( (c >= 0xFF61) && (c <= 0xFF9F) )
cConv = 0x8E00+0xA1+(c-0xFF61);
else
{
nHighChar = (sal_uChar)((c >> 8) & 0xFF);
nLowChar = (sal_uChar)(c & 0xFF);
/* JIS 0208 */
pHighTab = pConvertData->mpUniToJIS0208HighTab;
pHighEntry = pHighTab+nHighChar;
if ( (nLowChar >= pHighEntry->mnLowStart) && (nLowChar <= pHighEntry->mnLowEnd) )
{
cConv = pHighEntry->mpToUniTrailTab[nLowChar-pHighEntry->mnLowStart];
#104776# Fixed conversion of undefined characters from Unicode to EUC-JP.
2002-11-06 03:06:03 -06:00
if (cConv != 0)
cConv |= 0x8080;
initial import
2000-09-18 09:18:43 -05:00
}
else
cConv = 0;
/* JIS 0212 */
if ( !cConv )
{
pHighTab = pConvertData->mpUniToJIS0212HighTab;
pHighEntry = pHighTab+nHighChar;
if ( (nLowChar >= pHighEntry->mnLowStart) && (nLowChar <= pHighEntry->mnLowEnd) )
{
#104776# Fixed conversion of undefined characters from Unicode to EUC-JP.
2002-11-06 03:06:03 -06:00
cConv = pHighEntry->mpToUniTrailTab[nLowChar-pHighEntry->mnLowStart];
if (cConv != 0)
cConv |= 0x8F8080;
initial import
2000-09-18 09:18:43 -05:00
}
if ( !cConv )
{
if ( nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACE )
{
/* !!! */
}
if ( nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACESTR )
{
/* !!! */
}
/* Handle undefined and surrogates characters */
/* (all surrogates characters are undefined) */
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
if (ImplHandleUndefinedUnicodeToTextChar(pData,
&pSrcBuf,
pEndSrcBuf,
&pDestBuf,
pEndDestBuf,
nFlags,
pInfo))
initial import
2000-09-18 09:18:43 -05:00
continue;
#87140# Cleaned up, added EUC-TW and GB-18030.
2001-10-12 04:44:53 -05:00
else
break;
initial import
2000-09-18 09:18:43 -05:00
}
}
}
/* SingleByte */
if ( !(cConv & 0xFFFF00) )
{
if ( pDestBuf == pEndDestBuf )
{
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = (sal_Char)(sal_uChar)(cConv & 0xFF);
pDestBuf++;
}
/* DoubleByte */
else if ( !(cConv & 0xFF0000) )
{
if ( pDestBuf+1 >= pEndDestBuf )
{
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = (sal_Char)(sal_uChar)((cConv >> 8) & 0xFF);
pDestBuf++;
*pDestBuf = (sal_Char)(sal_uChar)(cConv & 0xFF);
pDestBuf++;
}
else
{
if ( pDestBuf+2 >= pEndDestBuf )
{
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
*pDestBuf = (sal_Char)(sal_uChar)((cConv >> 16) & 0xFF);
pDestBuf++;
*pDestBuf = (sal_Char)(sal_uChar)((cConv >> 8) & 0xFF);
pDestBuf++;
*pDestBuf = (sal_Char)(sal_uChar)(cConv & 0xFF);
pDestBuf++;
}
pSrcBuf++;
}
*pSrcCvtChars = nSrcChars - (pEndSrcBuf-pSrcBuf);
return (nDestBytes - (pEndDestBuf-pDestBuf));
}
Reference in a new issue Copy permalink