Thread: [KoCo-CVS] [Commit] cjkcodecs/src _iso_2022_kr.c iso2022common.h
Brought to you by:
perky
Menu
▾
▴
koco-cvs
|
From: Hye-Shik C. <pe...@us...> - 2003-06-02 07:39:24
|
perky 03/06/02 00:39:23
Added: src _iso_2022_kr.c iso2022common.h
Log:
Add iso-2022-kr codec finally!
Revision Changes Path
1.1 cjkcodecs/src/_iso_2022_kr.c
Index: _iso_2022_kr.c
===================================================================
/*
* _iso_2022_kr.c: the ISO-2022-KR codec
*
* Copyright (C) 2003 Hye-Shik Chang <pe...@Fr...>.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
* INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
* IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*
* $Id: _iso_2022_kr.c,v 1.1 2003/06/02 07:39:22 perky Exp $
*/
#include "codeccommon.h"
#include "iso2022common.h"
ENCMAP(cp949)
DECMAP(ksx1001)
#define HAVE_ENCODER_INIT
ENCODER_INIT(iso_2022_kr)
{
state->i = 0;
STATE_SETG0(state, CHARSET_ASCII)
STATE_SETG1(state, CHARSET_ASCII)
return 0;
}
#define HAVE_ENCODER_RESET
ENCODER_RESET(iso_2022_kr)
{
if (STATE_GETFLAG(state, F_SHIFTED)) {
RESERVE_OUTBUF(1)
**outbuf = SI;
NEXT_OUT(1)
STATE_CLEARFLAG(state, F_SHIFTED)
}
return 0;
}
ENCODER(iso_2022_kr)
{
while (inleft > 0) {
Py_UNICODE c = **inbuf;
DBCHAR code;
if (c < 0x80) {
if (STATE_GETFLAG(state, F_SHIFTED)) {
RESERVE_OUTBUF(2)
STATE_CLEARFLAG(state, F_SHIFTED)
(*outbuf)[0] = SI;
(*outbuf)[1] = c;
NEXT(1, 2)
} else {
RESERVE_OUTBUF(1)
(*outbuf)[0] = c;
NEXT(1, 1)
}
if (c == '\n')
STATE_CLEARFLAG(state, F_SHIFTED)
} else UCS4INVALID(c)
else {
if (STATE_GETG1(state) != CHARSET_KSX1001) {
RESERVE_OUTBUF(4)
STATE_SETG1(state, CHARSET_KSX1001)
(*outbuf)[0] = ESC;
(*outbuf)[1] = '$';
(*outbuf)[2] = ')';
(*outbuf)[3] = 'C';
NEXT_OUT(4)
}
if (!STATE_GETFLAG(state, F_SHIFTED)) {
RESERVE_OUTBUF(1)
STATE_SETFLAG(state, F_SHIFTED)
(*outbuf)[0] = SO;
NEXT_OUT(1)
}
TRYMAP_ENC(cp949, code, c) {
if (code & 0x8000) /* MSB set: CP949 */
return 1;
RESERVE_OUTBUF(1)
(*outbuf)[0] = code >> 8;
(*outbuf)[1] = code & 0xff;
NEXT(1, 2)
} else
return 1;
}
}
return 0;
}
#define HAVE_DECODER_INIT
DECODER_INIT(iso_2022_kr)
{
state->i = 0;
STATE_SETG0(state, CHARSET_ASCII)
STATE_SETG1(state, CHARSET_ASCII)
return 0;
}
#define HAVE_DECODER_RESET
DECODER_RESET(iso_2022_kr)
{
STATE_CLEARFLAG(state, F_SHIFTED)
return 0;
}
DECODER(iso_2022_kr)
{
while (inleft > 0) {
unsigned char c = **inbuf;
if (STATE_GETFLAG(state, F_ESCTHROUGHOUT)) {
/* ESC throughout mode: for non-iso2022 escape sequences */
RESERVE_OUTBUF(1)
**outbuf = c; /* assume as ISO-8859-1 */
NEXT(1, 1)
if (IS_ESCEND(c)) {
STATE_CLEARFLAG(state, F_ESCTHROUGHOUT)
}
continue;
}
switch (c) {
case ESC:
RESERVE_INBUF(2)
if (IS_ISO2022ESC((*inbuf)[1])) {
int eslen;
eslen = iso2022esclen(*inbuf, inleft);
if (eslen < 0)
return eslen == MBERR_INTERNAL ? 1 : eslen;
if (eslen == 3) {
if ((*inbuf)[2] == 'B') { /* ASCII */
if ((*inbuf)[1] == '(') {
STATE_SETG0(state, CHARSET_ASCII)
} else if ((*inbuf)[1] == ')') {
STATE_SETG1(state, CHARSET_ASCII)
} else
return 3;
} else
return 3;
} else if (eslen == 4) {
if ((*inbuf)[1] == '$' && (*inbuf)[3] == 'C') {
/* KS X 1001 */
if ((*inbuf)[2] == '(') {
STATE_SETG0(state, CHARSET_KSX1001)
} else if ((*inbuf)[2] == ')') {
STATE_SETG1(state, CHARSET_KSX1001)
} else
return 4;
} else
return 4;
} else
return eslen;
NEXT_IN(eslen)
} else {
STATE_SETFLAG(state, F_ESCTHROUGHOUT)
**outbuf = ESC;
NEXT(1, 1)
}
break;
case SI:
STATE_CLEARFLAG(state, F_SHIFTED)
NEXT_IN(1)
break;
case SO:
STATE_SETFLAG(state, F_SHIFTED)
NEXT_IN(1)
break;
case '\n':
STATE_CLEARFLAG(state, F_SHIFTED)
/* FALLTHROUGH */
case SP: /* FALLTHROUGH */
case DEL:
RESERVE_OUTBUF(1)
**outbuf = c;
NEXT(1, 1)
break;
default:
if ((c & 0x7f) < 0x20) { /* C0 and C1 */
RESERVE_OUTBUF(1)
**outbuf = c & 0x7f;
NEXT(1, 1)
} else {
unsigned char charset;
if (!STATE_GETFLAG(state, F_SHIFTED) && c < 0x80) /* G0 */
charset = STATE_GETG0(state);
else /* G1 */
charset = STATE_GETG1(state);
if (charset & CHARSET_DOUBLEBYTE) {
/* all double byte character sets are in KS X 1001 here */
RESERVE_OUTBUF(1)
TRYMAP_DEC(ksx1001, **outbuf, c & 0x7f, (*inbuf)[1] & 0x7f){
NEXT(2, 1)
} else
return 2;
} else {
RESERVE_OUTBUF(1)
**outbuf = c;
NEXT(1, 1)
}
}
}
}
return 0;
}
#include "codecentry.h"
BEGIN_CODEC_REGISTRY(iso_2022_kr)
MAPOPEN(ko_KR)
IMPORTMAP_DEC(ksx1001)
IMPORTMAP_ENC(cp949)
MAPCLOSE()
END_CODEC_REGISTRY(iso_2022_kr)
/*
* ex: ts=8 sts=4 et
*/
1.1 cjkcodecs/src/iso2022common.h
Index: iso2022common.h
===================================================================
/*
* iso2022common.h: Common Codec Routines for ISO-2022 codecs.
*
* Copyright (C) 2003 Hye-Shik Chang <pe...@Fr...>.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
* INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
* IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*
* $Id: iso2022common.h,v 1.1 2003/06/02 07:39:22 perky Exp $
*/
/* This ISO-2022 implementation is intended to comply ECMA-43 Level 1
* rather than RFCs itself */
#define ESC 0x1b
#define SO 0x0e
#define SI 0x0f
#define SP 0x20
#define DEL 0x7f
#define MAX_ESCSEQLEN 16
#define IS_ESCEND(c) ((c) >= 'A' && (c) <= 'Z')
#define IS_ISO2022ESC(c2) ((c2) == '(' || (c2) == ')' || (c2) == '$')
/* this is not a full list of ISO-2022 escape sequence headers.
* but, it's enough to implement CJK instances of iso-2022. */
/* STATE
00000000 00000000 00000000
|| ||^^^^^| ||^^^^^|
|| || | |+-----+---- G0 Character Set
|| || | +----------- Is G0 double byte?
|| |+-----+------------- G1 Character Set
|| +-------------------- Is G1 double byte?
|+---------------------- Shifted in?
+----------------------- ESC Throughout
*/
#define CHARSET_DOUBLEBYTE 0x80
#define CHARSET_ASCII 'B'
#define CHARSET_KSX1001 ('C'|CHARSET_DOUBLEBYTE)
#define CHARSET_JISX0201_R 'J'
#define CHARSET_JISX0201_K 'I'
#define CHARSET_JISX0208 ('B'|CHARSET_DOUBLEBYTE)
#define CHARSET_JISX0208_O ('@'|CHARSET_DOUBLEBYTE)
#define CHARSET_JISX0212 ('D'|CHARSET_DOUBLEBYTE)
#define CHARSET_JISX0213_1 ('O'|CHARSET_DOUBLEBYTE)
#define CHARSET_JISX0213_2 ('P'|CHARSET_DOUBLEBYTE)
#define CHARSET_GB2312 ('A'|CHARSET_DOUBLEBYTE)
#define CHARSET_GB2312_8565 ('E'|CHARSET_DOUBLEBYTE)
#define CHARSET_DESIGN(c) ((c) & 0x7f)
#define CHARSET_ISDBCS(c) ((c) & 0x80)
#define F_SHIFTED 0x010000
#define F_ESCTHROUGHOUT 0x020000
#define STATE_SETG0(s, v) ((s)->i) = (((s)->i) & ~0x0000ff) | (v);
#define STATE_GETG0(s) ((s)->i & 0x0000ff)
#define STATE_SETG1(s, v) ((s)->i) = (((s)->i) & ~0x00ff00) | ((v) << 8);
#define STATE_GETG1(s) (((s)->i & 0x00ff00) >> 8)
#define STATE_SETFLAG(s, f) ((s)->i) |= (f);
#define STATE_GETFLAG(s, f) ((s)->i & (f))
#define STATE_CLEARFLAG(s, f) ((s)->i) &= ~(f);
static int
iso2022esclen(const unsigned char *s, size_t len)
{
int i;
for (i = 1;i < MAX_ESCSEQLEN;i++) {
if (i >= len)
return MBERR_TOOFEW;
if (IS_ESCEND(s[i]))
return i + 1;
}
return MBERR_INTERNAL; /* unterminated escape sequence */
}
/*
* ex: ts=8 sts=4 et
*/
|
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X