Files
harbour-core/src/rtl/cdpapihb.c
Przemysław Czerpak 75ff90a49d 2025-09-09 13:50 UTC+0200 Przemyslaw Czerpak (druzus/at/poczta.onet.pl)
* include/hbdefs.h
    + added new types HB_WCHAR16 and HB_WCHAR32, existing type HB_WCHAR
      is mapped to HB_WCHAR16 (just like before)

  * include/hbapicdp.h
  * src/harbour.def
  * src/rtl/cdpapi.c
    + added new C functions for encoding and decoding UTF-8 string using
      which HB_WCHAR32:
         int hb_cdpU32CharToUTF8( char * szUTF8, HB_WCHAR32 wc );
         HB_BOOL hb_cdpUTF8GetU32( const char * pSrc, HB_SIZE nLen,
                                   HB_SIZE * pnIndex, HB_WCHAR32 * pWC );
         HB_BOOL hb_cdpUTF8GetUCS( const char * pSrc, HB_SIZE nLen,
                                   HB_SIZE * pnIndex, HB_WCHAR32 * pWC );
         HB_BOOL hb_cdpUTF8GetU16( const char * pSrc, HB_SIZE nLen,
                                   HB_SIZE * pnIndex, HB_WCHAR16 * pWC );
         HB_BOOL hb_cdpUTF8Validate( const char * pSrc, HB_SIZE nLen );
      They support full UCS and are much more restrictive against errors and
      wrong UTF-8 encoding, i.e. now overlong encoding is forbidden.
      The wrong characters are translated to 0xFFFD and later if such
      character does not exist in final CP to '?' ASCII character.
    * declaration of the following UTF-8 C functions have been changed to
      operate on HB_WCHAR32 instead of HB_WCHAR:
         int hb_cdpUTF8CharSize( HB_WCHAR32 wc );
         HB_WCHAR32 hb_cdpUTF8StringPeek( const char * pSrc, HB_SIZE nLen,
                                          HB_SIZE nPos );
    * the following C functions have been changed to internally operate on
      HB_WCHAR32 instead of HB_WCHAR:
         hb_cdpUTF8StringLength()
         hb_cdpUTF8StringAt()
         hb_cdpUTF8StringSubstr()
    * the following C functions have been changed to use new hb_cdpUTF8GetU*()
      instead of step by step decoding with hb_cdpUTF8ToU16NextChar()
         hb_cdpStrToUTF8Disp()
         hb_cdpUTF8AsStrLen()
         hb_cdpUTF8ToStr()
         hb_cdpStrToU16()
         hb_cdpUtf8Char()
    * use HB_CDP_ERROR_* macros to mark wrong encoding

  * src/rtl/cdpapihb.c
    * the following UTF-8 C functions have been changed to operate on
      HB_WCHAR32 instead of HB_WCHAR:
         hb_utf8Chr()
         hb_utf8Asc()
         hb_utf8Poke()
         hb_utf8Peek()
      Other UTF-8 PRG functions have been adopted to HB_WCHAR32 by changes
      in corresponding C functions.

  * src/codepage/cp_utf8.c
    * use new function hb_cdpUTF8GetU16() to decode UTF-8 strings in UTF8EX CP

  * src/rtl/arc4.c
    + added new macro HB_NO_SYSCTL which allow to disable sysctl() in Linux
      builds for GLIBC < 2.30
2025-09-09 13:50:42 +02:00

560 lines
15 KiB
C

/*
* The CodePages API
*
* Copyright 2002 Alexander S.Kresin <alex@belacy.belgorod.su>
* Copyright 2009-2012 Przemyslaw Czerpak <druzus / at / priv.onet.pl>
*
* 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, 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; see the file LICENSE.txt. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301 USA (or visit https://www.gnu.org/licenses/).
*
* As a special exception, the Harbour Project gives permission for
* additional uses of the text contained in its release of Harbour.
*
* The exception is that, if you link the Harbour libraries with other
* files to produce an executable, this does not by itself cause the
* resulting executable to be covered by the GNU General Public License.
* Your use of that executable is in no way restricted on account of
* linking the Harbour library code into it.
*
* This exception does not however invalidate any other reasons why
* the executable file might be covered by the GNU General Public License.
*
* This exception applies only to the code released by the Harbour
* Project under the name Harbour. If you copy code from other
* Harbour Project or Free Software Foundation releases into a copy of
* Harbour, as the General Public License permits, the exception does
* not apply to the code that you add in this way. To avoid misleading
* anyone as to the status of such modified files, you must delete
* this exception notice from them.
*
* If you write modifications of your own for Harbour, it is your choice
* whether to permit this exception to apply to your modifications.
* If you do not wish that, delete this exception notice.
*
*/
#include "hbapi.h"
#include "hbapiitm.h"
#include "hbapierr.h"
#include "hbapicdp.h"
static HB_SIZE utf8pos( const char * szUTF8, HB_SIZE nLen, HB_SIZE nUTF8Pos )
{
if( nUTF8Pos > 0 && nUTF8Pos <= nLen )
{
HB_SIZE n1, n2;
HB_WCHAR32 wc;
for( n1 = n2 = 0; n1 < nLen; )
{
hb_cdpUTF8GetU32( szUTF8, nLen, &n1, &wc );
if( --nUTF8Pos == 0 )
return n2 + 1;
n2 = n1;
}
}
return 0;
}
HB_FUNC( HB_CDPSELECT )
{
const char * id = hb_parc( 1 );
hb_retc( hb_cdpID() );
if( id )
hb_cdpSelectID( id );
}
HB_FUNC( HB_CDPEXISTS )
{
const char * id = hb_parc( 1 );
if( id )
hb_retl( hb_cdpFind( id ) != NULL );
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_CDPUNIID )
{
const char * id = hb_parc( 1 );
PHB_CODEPAGE cdp = id ? hb_cdpFindExt( id ) : hb_vmCDP();
hb_retc( cdp ? cdp->uniTable->uniID : NULL );
}
HB_FUNC( HB_CDPINFO )
{
const char * id = hb_parc( 1 );
PHB_CODEPAGE cdp = id ? hb_cdpFindExt( id ) : hb_vmCDP();
hb_retc( cdp ? cdp->info : NULL );
}
HB_FUNC( HB_CDPISCHARIDX )
{
const char * id = hb_parc( 1 );
PHB_CODEPAGE cdp = id ? hb_cdpFindExt( id ) : hb_vmCDP();
HB_BOOL fResult = HB_FALSE;
if( cdp )
{
fResult = HB_CDP_ISCHARIDX( cdp );
if( HB_CDP_ISCUSTOM( cdp ) && HB_ISLOG( 2 ) )
{
if( hb_parl( 2 ) )
cdp->type |= HB_CDP_TYPE_CHARIDX;
else
cdp->type &= ~HB_CDP_TYPE_CHARIDX;
}
}
hb_retl( fResult );
}
HB_FUNC( HB_CDPCHARMAX )
{
hb_retnl( ( 1 << ( ( int ) ( hb_cdpIsUTF8( hb_cdpFindExt( hb_parc( 1 ) ) ) ? sizeof( HB_WCHAR ) : sizeof( HB_UCHAR ) ) * 8 ) ) - 1 );
}
HB_FUNC( HB_CDPISUTF8 )
{
hb_retl( hb_cdpIsUTF8( hb_cdpFindExt( hb_parc( 1 ) ) ) );
}
HB_FUNC( HB_CDPLIST )
{
const char ** list = hb_cdpList();
HB_ISIZ nPos;
nPos = 0;
while( list[ nPos ] )
++nPos;
hb_reta( nPos );
nPos = 0;
while( list[ nPos ] )
{
hb_storvc( list[ nPos ], -1, nPos + 1 );
++nPos;
}
hb_xfree( ( void * ) list );
}
/* NOTE: CA-Cl*pper 5.2e Intl. will return: "NATSORT v1.2i x14 19/Mar/93" */
/* NOTE: CA-Cl*pper 5.3 Intl. will return: "NATSORT v1.3i x19 06/Mar/95" */
HB_FUNC_TRANSLATE( __NATSORTVER, HB_CDPINFO )
/*
* extended CP PRG functions
*/
HB_FUNC( HB_TRANSLATE )
{
HB_SIZE nLen = hb_parclen( 1 );
const char * szIdIn = hb_parc( 2 );
const char * szIdOut = hb_parc( 3 );
if( nLen )
{
PHB_CODEPAGE cdpIn = szIdIn ? hb_cdpFindExt( szIdIn ) : hb_vmCDP();
PHB_CODEPAGE cdpOut = szIdOut ? hb_cdpFindExt( szIdOut ) : hb_vmCDP();
if( cdpIn && cdpOut && cdpIn != cdpOut &&
( cdpIn->uniTable != cdpOut->uniTable ||
HB_CDP_ISCUSTOM( cdpIn ) ||
HB_CDP_ISCUSTOM( cdpOut ) ) )
{
char * szResult = hb_cdpnDup( hb_parc( 1 ), &nLen, cdpIn, cdpOut );
hb_retclen_buffer( szResult, nLen );
}
else
hb_itemReturn( hb_param( 1, HB_IT_STRING ) );
}
else
hb_retc_null();
}
HB_FUNC( HB_UTF8CHR )
{
if( HB_ISNUM( 1 ) )
{
char utf8Char[ HB_MAX_CHAR_LEN ];
int iLen;
iLen = hb_cdpU32CharToUTF8( utf8Char, ( HB_WCHAR32 ) hb_parni( 1 ) );
hb_retclen( utf8Char, iLen );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8ASC )
{
const char * pszString = hb_parc( 1 );
if( pszString )
{
HB_SIZE nLen = hb_parclen( 1 ), nIndex = 0;
HB_WCHAR32 wc = 0;
hb_cdpUTF8GetU32( pszString, nLen, &nIndex, &wc );
hb_retnint( wc );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_STRTOUTF8 )
{
HB_SIZE nLen = hb_parclen( 1 ), nDest = 0;
char * szDest = NULL;
if( nLen )
{
const char * szCP = hb_parc( 2 );
PHB_CODEPAGE cdp = szCP ? hb_cdpFindExt( szCP ) : hb_vmCDP();
if( cdp )
{
if( hb_cdpIsUTF8( cdp ) )
{
hb_itemReturn( hb_param( 1, HB_IT_STRING ) );
return;
}
else
{
const char * szString = hb_parc( 1 );
nDest = hb_cdpStrAsUTF8Len( cdp, szString, nLen, 0 );
szDest = ( char * ) hb_xgrab( nDest + 1 );
hb_cdpStrToUTF8( cdp, szString, nLen, szDest, nDest + 1 );
}
}
}
if( szDest )
hb_retclen_buffer( szDest, nDest );
else
hb_retc_null();
}
HB_FUNC( HB_UTF8TOSTR )
{
const char * szString = hb_parc( 1 );
if( szString )
{
HB_SIZE nLen = hb_parclen( 1 ), nDest = 0;
char * szDest = NULL;
if( nLen )
{
const char * szCP = hb_parc( 2 );
PHB_CODEPAGE cdp = szCP ? hb_cdpFindExt( szCP ) : hb_vmCDP();
if( cdp )
{
if( hb_cdpIsUTF8( cdp ) )
{
hb_itemReturn( hb_param( 1, HB_IT_STRING ) );
return;
}
else
{
szString = hb_parc( 1 );
nDest = hb_cdpUTF8AsStrLen( cdp, szString, nLen, 0 );
szDest = ( char * ) hb_xgrab( nDest + 1 );
hb_cdpUTF8ToStr( cdp, szString, nLen, szDest, nDest + 1 );
}
}
}
if( szDest )
hb_retclen_buffer( szDest, nDest );
else
hb_retc_null();
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8AT )
{
PHB_ITEM pSub = hb_param( 1, HB_IT_STRING );
PHB_ITEM pText = hb_param( 2, HB_IT_STRING );
if( pText && pSub )
{
HB_SIZE nTextLength = hb_itemGetCLen( pText );
HB_SIZE nStart = hb_parnsdef( 3, 1 );
HB_SIZE nEnd = hb_parnsdef( 4, nTextLength ); /* nTextLength can be > UTF8 len. No problem.*/
if( nEnd < nStart )
hb_retns( 0 );
else
hb_retns( hb_cdpUTF8StringAt( hb_itemGetCPtr( pSub ), hb_itemGetCLen( pSub ),
hb_itemGetCPtr( pText ), nTextLength, nStart, nEnd, HB_FALSE ) );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
/*
* NOTE: In HB_UTF8RAT we are still traversing from
* left to right, as it would be required anyway to
* determine the real string length. [bacco]
*/
HB_FUNC( HB_UTF8RAT )
{
PHB_ITEM pSub = hb_param( 1, HB_IT_STRING );
PHB_ITEM pText = hb_param( 2, HB_IT_STRING );
if( pText && pSub )
{
HB_SIZE nTextLength = hb_itemGetCLen( pText );
HB_SIZE nStart = hb_parnsdef( 3, 1 );
HB_SIZE nEnd = hb_parnsdef( 4, nTextLength ); /* nTextLength can be > UTF8 len. No problem.*/
if( nEnd < nStart )
hb_retns( 0 );
else
hb_retns( hb_cdpUTF8StringAt( hb_itemGetCPtr( pSub ), hb_itemGetCLen( pSub ),
hb_itemGetCPtr( pText ), nTextLength, nStart, nEnd, HB_TRUE ) );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8SUBSTR )
{
const char * szString = hb_parc( 1 );
int iPCount = hb_pcount();
if( szString && ( iPCount < 2 || ( HB_ISNUM( 2 ) && ( iPCount < 3 || HB_ISNUM( 3 ) ) ) ) )
{
char * szDest = NULL;
HB_SIZE nLen = hb_parclen( 1 ), nDest = 0;
HB_ISIZ nFrom = hb_parns( 2 );
HB_ISIZ nCount = iPCount < 3 ? ( HB_ISIZ ) nLen : hb_parns( 3 );
if( nFrom < 0 )
{
nFrom += hb_cdpUTF8StringLength( szString, nLen );
if( nFrom < 0 )
nFrom = 0;
}
else if( nFrom )
--nFrom;
if( nLen > ( HB_SIZE ) nFrom && nCount > 0 )
szDest = hb_cdpUTF8StringSubstr( szString, nLen,
nFrom, nCount, &nDest );
if( szDest )
hb_retclen_buffer( szDest, nDest );
else
hb_retc_null();
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8LEFT )
{
const char * szString = hb_parc( 1 );
if( szString && HB_ISNUM( 2 ) )
{
HB_ISIZ nLenReq = hb_parns( 2 );
HB_SIZE nDest = 0;
char * szDest = NULL;
if( nLenReq > 0 )
szDest = hb_cdpUTF8StringSubstr( szString, hb_parclen( 1 ),
0, nLenReq, &nDest );
if( szDest )
hb_retclen_buffer( szDest, nDest );
else
hb_retc_null();
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8RIGHT )
{
const char * szString = hb_parc( 1 );
if( szString && HB_ISNUM( 2 ) )
{
HB_ISIZ nLenReq = hb_parns( 2 ), nFrom;
HB_SIZE nLen = hb_parclen( 1 ), nDest = 0;
char * szDest = NULL;
if( nLen && nLenReq > 0 )
{
nFrom = hb_cdpUTF8StringLength( szString, nLen ) - nLenReq;
if( nFrom < 0 )
nFrom = 0;
szDest = hb_cdpUTF8StringSubstr( szString, nLen,
nFrom, nLenReq, &nDest );
}
if( szDest )
hb_retclen_buffer( szDest, nDest );
else
hb_retc_null();
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8PEEK )
{
const char * szString = hb_parc( 1 );
if( szString && HB_ISNUM( 2 ) )
{
HB_SIZE nPos = hb_parns( 2 );
HB_SIZE nLen = hb_parclen( 1 );
if( nPos > 0 && nPos <= nLen )
hb_retnint( hb_cdpUTF8StringPeek( szString, nLen, nPos - 1 ) );
else
hb_retni( 0 );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8POKE )
{
PHB_ITEM pText = hb_param( 1, HB_IT_STRING );
if( pText && HB_ISNUM( 2 ) && HB_ISNUM( 3 ) )
{
const char * szString = hb_itemGetCPtr( pText );
HB_SIZE nLen = hb_itemGetCLen( pText ), nPos;
nPos = utf8pos( szString, nLen, hb_parns( 2 ) );
if( nPos )
{
HB_WCHAR32 uc, uc2;
HB_SIZE nDstLen = 0;
int n;
--nPos;
uc = ( HB_WCHAR32 ) hb_parni( 3 );
n = hb_cdpUTF8CharSize( uc );
hb_cdpUTF8GetU32( &szString[ nPos ], nLen - nPos, &nDstLen, &uc2 );
if( n == ( int ) nDstLen )
{
char * szText;
if( hb_itemGetWriteCL( pText, &szText, &nLen ) &&
nPos + n <= nLen )
{
hb_cdpU32CharToUTF8( &szText[ nPos ], uc );
}
hb_itemReturn( pText );
}
else
{
char * szResult = ( char * ) hb_xgrab( nLen - nDstLen + n + 1 );
memcpy( szResult, szString, nPos );
hb_cdpU32CharToUTF8( &szResult[ nPos ], uc );
memcpy( szResult + nPos + n, szString + nPos + nDstLen, nLen - nPos - nDstLen );
if( HB_ISBYREF( 1 ) )
hb_storclen( szResult, nLen - nDstLen + n, 1 );
hb_retclen_buffer( szResult, nLen - nDstLen + n );
}
}
else
hb_itemReturn( pText );
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8STUFF )
{
const char * szText = hb_parc( 1 );
const char * szIns = hb_parc( 4 );
if( szText && szIns && HB_ISNUM( 2 ) && HB_ISNUM( 3 ) )
{
HB_SIZE nLen = hb_parclen( 1 );
HB_SIZE nPos = hb_parns( 2 );
HB_SIZE nDel = hb_parns( 3 );
HB_SIZE nIns = hb_parclen( 4 );
HB_SIZE nTot;
if( nPos )
{
nPos = utf8pos( szText, nLen, nPos );
if( nPos == 0 )
nPos = nLen;
else
nPos--;
}
if( nDel )
{
if( nPos < nLen )
{
nDel = utf8pos( szText + nPos, nLen - nPos, nDel + 1 );
if( nDel == 0 )
nDel = nLen - nPos;
else
nDel--;
}
else
nDel = 0;
}
if( ( nTot = nLen + nIns - nDel ) > 0 )
{
char * szResult = ( char * ) hb_xgrab( nTot + 1 );
hb_xmemcpy( szResult, szText, nPos );
hb_xmemcpy( szResult + nPos, szIns, nIns );
hb_xmemcpy( szResult + nPos + nIns, szText + nPos + nDel,
nLen - ( nPos + nDel ) );
hb_retclen_buffer( szResult, nTot );
}
else
hb_retc_null();
}
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
HB_FUNC( HB_UTF8LEN )
{
const char * szText = hb_parc( 1 );
if( szText )
hb_retnint( hb_cdpUTF8StringLength( szText, hb_parclen( 1 ) ) );
else
hb_errRT_BASE_SubstR( EG_ARG, 3012, NULL, HB_ERR_FUNCNAME, HB_ERR_ARGS_BASEPARAMS );
}
/* none of numeric parameters in StrTran() (4-th and 5-th) refers to
* character position in string so we do not need to create new
* hb_utf8StrTran() but we can safely use normal StrTran() function
*/
HB_FUNC_TRANSLATE( HB_UTF8STRTRAN, STRTRAN )