Thread: [KoCo-CVS] [Commit] KoreanCodecs/src cp949_codec.c euckr_codec.c _koco.c
Brought to you by:
perky
Menu
▾
▴
koco-cvs
|
From: Chang <pe...@us...> - 2002-04-26 21:06:17
|
perky 02/04/26 14:06:10
Modified: src _koco.c
Added: src cp949_codec.c euckr_codec.c
Log:
- Split euc-kr and cp949 codec from _koco.c
Revision Changes Path
1.14 +7 -242 KoreanCodecs/src/_koco.c
Index: _koco.c
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/src/_koco.c,v
retrieving revision 1.13
retrieving revision 1.14
diff -u -r1.13 -r1.14
--- _koco.c 26 Apr 2002 08:21:54 -0000 1.13
+++ _koco.c 26 Apr 2002 21:06:09 -0000 1.14
@@ -4,14 +4,14 @@
* KoreanCodecs C Implementations
*
* Author : Hye-Shik Chang <pe...@fa...>
- * Date : $Date: 2002/04/26 08:21:54 $
+ * Date : $Date: 2002/04/26 21:06:09 $
* Created : 15 March 2002
*
- * $Revision: 1.13 $
+ * $Revision: 1.14 $
*/
static char *version =
-"$Id: _koco.c,v 1.13 2002/04/26 08:21:54 perky Exp $";
+"$Id: _koco.c,v 1.14 2002/04/26 21:06:09 perky Exp $";
#define UNIFIL 0xfffd
@@ -65,246 +65,11 @@
}
}
+#define KOCOCODEC_INCLUDE
+#include "euckr_codec.c"
+#include "cp949_codec.c"
+#undef KOCOCODEC_INCLUDE
-static char euc_kr_decode__doc__[] = "EUC-KR decoder";
-
-static PyObject *
-euc_kr_decode(PyObject *self, PyObject *args)
-{
- unsigned char *argstr, *srccur, *srcend;
- int arglen, errtype = error_strict;
- char *errors = NULL;
- Py_UNICODE *destptr, *destcur, *codemap, code;
- PyObject *r;
-
- if (!PyArg_ParseTuple(args, "s#|z:euc_kr_decode", &argstr, &arglen, &errors))
- return NULL;
-
- errtype = error_type(errors);
- if (errtype == error_undef)
- return NULL;
-
- destcur = destptr = PyMem_New(Py_UNICODE, arglen+1);
- for (srccur = argstr, srcend = argstr + arglen; srccur < srcend; srccur++) {
- if ((*srccur & 0x80) && (srccur+1 < srcend)) {
- codemap = ksc5601_decode_map[*srccur & 0x7F];
- if (!codemap)
- goto invalid;
- if (ksc5601_decode_bottom <= srccur[1] && srccur[1] <= ksc5601_decode_top) {
- code = codemap[srccur[1] - ksc5601_decode_bottom];
- if (code == UNIFIL)
- goto invalid;
- *(destcur++) = code;
- srccur++;
- continue;
- } else {
-invalid: srccur++; /* skip 2byte */
- switch (errtype) {
- case error_strict:
- PyMem_Del(destptr);
- PyErr_Format(PyExc_UnicodeError,
- "EUC-KR decoding error: invalid character \\x%02x%02x",
- srccur[0], srccur[1]);
- return NULL;
- break;
- case error_replace:
- *(destcur++) = UNIFIL;
- break;
- /* case error_ignore: break; */
- }
- continue;
- }
- } else
- *(destcur++) = *srccur;
- }
-
- r = codec_tuple(PyUnicode_FromUnicode(destptr, destcur-destptr), arglen);
- PyMem_Del(destptr);
- return r;
-}
-
-static char euc_kr_encode__doc__[] = "EUC-KR encoder";
-
-static PyObject *
-euc_kr_encode(PyObject *self, PyObject *args)
-{
- Py_UNICODE *argptr, *srccur, *srcend;
- int arglen, errtype = error_strict;
- char *errors = NULL;
- unsigned char *destptr, *destcur, *decbuf;
- PyObject *r;
-
- if (!PyArg_ParseTuple(args, "u#|z:euc_kr_encode", &argptr, &arglen, &errors))
- return NULL;
-
- errtype = error_type(errors);
- if (errtype == error_undef)
- return NULL;
-
- destcur = destptr = PyMem_New(unsigned char, arglen*2+1);
- for (srccur = argptr, srcend = argptr + arglen; srccur < srcend; srccur++) {
- if (*srccur <= 0x7F)
- *(destcur++) = (unsigned char)*srccur;
- else
- if((decbuf = _ksc5601_encode(*srccur)) == 0) {
- switch (errtype) {
- case error_strict:
- PyMem_Del(destptr);
- PyErr_Format(PyExc_UnicodeError,
- "EUC-KR encoding error: invalid character \\u%04x",
- *srccur);
- return NULL;
- break;
- case error_replace:
- *(destcur++) = 0xa1;
- *(destcur++) = 0xa1;
- break;
- /* case error_ignore: break; */
- }
- } else {
- *(destcur++) = decbuf[0];
- *(destcur++) = decbuf[1];
- }
- }
-
- r = codec_tuple(PyString_FromStringAndSize((char*)destptr, destcur - destptr), arglen);
- PyMem_Del(destptr);
- return r;
-}
-
-static char cp949_decode__doc__[] = "CP949 decoder";
-
-static PyObject *
-cp949_decode(PyObject *self, PyObject *args)
-{
- unsigned char *argstr, *srccur, *srcend;
- int arglen, errtype = error_strict;
- char *errors = NULL;
- Py_UNICODE *destptr, *destcur, *codemap, code;
- PyObject *r;
-
- if (!PyArg_ParseTuple(args, "s#|z:cp949_decode", &argstr, &arglen, &errors))
- return NULL;
-
- errtype = error_type(errors);
- if (errtype == error_undef)
- return NULL;
-
- destcur = destptr = PyMem_New(Py_UNICODE, arglen+1);
- for (srccur = argstr, srcend = argstr + arglen; srccur < srcend; srccur++) {
- if ((*srccur & 0x80) && (srccur+1 < srcend)) {
- if (uhc_decode_hint[*srccur]) { /* UHC page0 region */
- codemap = uhc_decode_map[*srccur & 0x7F];
- /* codemap DOES have all maps on 0x81-0xA0, alphabet area can't on this */
- if (uhc_page0_bottom <= srccur[1] && srccur[1] <= uhc_page0_top) {
- code = codemap[srccur[1] - uhc_page0_bottom];
- if (code == UNIFIL)
- goto invalid;
- *(destcur++) = code;
- srccur++; /* skip 2byte */
- } else
- goto invalid;
- } else if (uhc_decode_hint[srccur[1]]) { /* UHC page1 region */
- codemap = uhc_decode_map[*srccur & 0x7F];
- if (!codemap)
- goto invalid;
- /* srccur[1] has tested already */
- code = codemap[srccur[1] - uhc_page1_bottom];
- if (code == UNIFIL)
- goto invalid;
- *(destcur++) = code;
- srccur++; /* skip 2byte */
- } else {
- /* ksc5601 area */
- codemap = ksc5601_decode_map[*srccur & 0x7F];
- if (!codemap)
- goto invalid;
- if (ksc5601_decode_bottom <= srccur[1] && srccur[1] <= ksc5601_decode_top) {
- code = codemap[srccur[1] - ksc5601_decode_bottom];
- if (code == UNIFIL)
- goto invalid;
- *(destcur++) = code;
- srccur++;
- continue;
- } else {
-invalid: srccur++; /* skip 2byte */
- switch (errtype) {
- case error_strict:
- PyMem_Del(destptr);
- PyErr_Format(PyExc_UnicodeError,
- "CP949 decoding error: invalid character \\x%02x%02x",
- srccur[0], srccur[1]);
- return NULL;
- break;
- case error_replace:
- *(destcur++) = UNIFIL;
- break;
- /* case error_ignore: break; */
- }
- continue;
- }
- }
- } else
- *(destcur++) = *srccur;
- }
-
- r = codec_tuple(PyUnicode_FromUnicode(destptr, destcur-destptr), arglen);
- PyMem_Del(destptr);
- return r;
-}
-
-static char cp949_encode__doc__[] = "CP949 encoder";
-
-static PyObject *
-cp949_encode(PyObject *self, PyObject *args)
-{
- Py_UNICODE *argptr, *srccur, *srcend;
- int arglen, errtype = error_strict;
- char *errors = NULL;
- unsigned char *destptr, *destcur, *decbuf;
- PyObject *r;
-
- if (!PyArg_ParseTuple(args, "u#|z:cp949_encode", &argptr, &arglen, &errors))
- return NULL;
-
- errtype = error_type(errors);
- if (errtype == error_undef)
- return NULL;
-
- destcur = destptr = PyMem_New(unsigned char, arglen*2+1);
- for (srccur = argptr, srcend = argptr + arglen; srccur < srcend; srccur++) {
- if (*srccur <= 0x7F)
- *(destcur++) = (unsigned char)*srccur;
- else {
- decbuf = _ksc5601_encode(*srccur);
- if (!decbuf)
- decbuf = _uhc_encode(*srccur);
- if(decbuf == 0) {
- switch (errtype) {
- case error_strict:
- PyMem_Del(destptr);
- PyErr_Format(PyExc_UnicodeError,
- "CP949 encoding error: invalid character \\u%04x",
- *srccur);
- return NULL;
- break;
- case error_replace:
- *(destcur++) = 0xa1;
- *(destcur++) = 0xa1;
- break;
- /* case error_ignore: break; */
- }
- } else {
- *(destcur++) = decbuf[0];
- *(destcur++) = decbuf[1];
- }
- }
- }
-
- r = codec_tuple(PyString_FromStringAndSize((char*)destptr, destcur - destptr), arglen);
- PyMem_Del(destptr);
- return r;
-}
/* List of methods defined in the module */
1.1 KoreanCodecs/src/cp949_codec.c
Index: cp949_codec.c
===================================================================
/*
* cp949_codec.c
*
* KoreanCodecs CP949 Codec C Implementation
*
* Author : Hye-Shik Chang <pe...@fa...>
* Date : $Date: 2002/04/26 21:06:10 $
* Created : 15 March 2002
*
* $Revision: 1.1 $
*/
#ifdef KOCOCODEC_INCLUDE
static char cp949_decode__doc__[] = "CP949 decoder";
static PyObject *
cp949_decode(PyObject *self, PyObject *args)
{
unsigned char *argstr, *srccur, *srcend;
int arglen, errtype = error_strict;
char *errors = NULL;
Py_UNICODE *destptr, *destcur, *codemap, code;
PyObject *r;
if (!PyArg_ParseTuple(args, "s#|z:cp949_decode", &argstr, &arglen, &errors))
return NULL;
errtype = error_type(errors);
if (errtype == error_undef)
return NULL;
destcur = destptr = PyMem_New(Py_UNICODE, arglen+1);
for (srccur = argstr, srcend = argstr + arglen; srccur < srcend; srccur++) {
if ((*srccur & 0x80) && (srccur+1 < srcend)) {
if (uhc_decode_hint[*srccur]) { /* UHC page0 region */
codemap = uhc_decode_map[*srccur & 0x7F];
/* codemap DOES have all maps on 0x81-0xA0, alphabet area can't on this */
if (uhc_page0_bottom <= srccur[1] && srccur[1] <= uhc_page0_top) {
code = codemap[srccur[1] - uhc_page0_bottom];
if (code == UNIFIL)
goto invalid;
*(destcur++) = code;
srccur++; /* skip 2byte */
} else
goto invalid;
} else if (uhc_decode_hint[srccur[1]]) { /* UHC page1 region */
codemap = uhc_decode_map[*srccur & 0x7F];
if (!codemap)
goto invalid;
/* srccur[1] has tested already */
code = codemap[srccur[1] - uhc_page1_bottom];
if (code == UNIFIL)
goto invalid;
*(destcur++) = code;
srccur++; /* skip 2byte */
} else {
/* ksc5601 area */
codemap = ksc5601_decode_map[*srccur & 0x7F];
if (!codemap)
goto invalid;
if (ksc5601_decode_bottom <= srccur[1] && srccur[1] <= ksc5601_decode_top) {
code = codemap[srccur[1] - ksc5601_decode_bottom];
if (code == UNIFIL)
goto invalid;
*(destcur++) = code;
srccur++;
continue;
} else {
invalid: srccur++; /* skip 2byte */
switch (errtype) {
case error_strict:
PyMem_Del(destptr);
PyErr_Format(PyExc_UnicodeError,
"CP949 decoding error: invalid character \\x%02x%02x",
srccur[0], srccur[1]);
return NULL;
break;
case error_replace:
*(destcur++) = UNIFIL;
break;
/* case error_ignore: break; */
}
continue;
}
}
} else
*(destcur++) = *srccur;
}
r = codec_tuple(PyUnicode_FromUnicode(destptr, destcur-destptr), arglen);
PyMem_Del(destptr);
return r;
}
static char cp949_encode__doc__[] = "CP949 encoder";
static PyObject *
cp949_encode(PyObject *self, PyObject *args)
{
Py_UNICODE *argptr, *srccur, *srcend;
int arglen, errtype = error_strict;
char *errors = NULL;
unsigned char *destptr, *destcur, *decbuf;
PyObject *r;
if (!PyArg_ParseTuple(args, "u#|z:cp949_encode", &argptr, &arglen, &errors))
return NULL;
errtype = error_type(errors);
if (errtype == error_undef)
return NULL;
destcur = destptr = PyMem_New(unsigned char, arglen*2+1);
for (srccur = argptr, srcend = argptr + arglen; srccur < srcend; srccur++) {
if (*srccur <= 0x7F)
*(destcur++) = (unsigned char)*srccur;
else {
decbuf = _ksc5601_encode(*srccur);
if (!decbuf)
decbuf = _uhc_encode(*srccur);
if(decbuf == 0) {
switch (errtype) {
case error_strict:
PyMem_Del(destptr);
PyErr_Format(PyExc_UnicodeError,
"CP949 encoding error: invalid character \\u%04x",
*srccur);
return NULL;
break;
case error_replace:
*(destcur++) = 0xa1;
*(destcur++) = 0xa1;
break;
/* case error_ignore: break; */
}
} else {
*(destcur++) = decbuf[0];
*(destcur++) = decbuf[1];
}
}
}
r = codec_tuple(PyString_FromStringAndSize((char*)destptr, destcur - destptr), arglen);
PyMem_Del(destptr);
return r;
}
#endif
1.1 KoreanCodecs/src/euckr_codec.c
Index: euckr_codec.c
===================================================================
/*
* euckr_codec.c
*
* KoreanCodecs EUC-KR Codec C Implementation
*
* Author : Hye-Shik Chang <pe...@fa...>
* Date : $Date: 2002/04/26 21:06:10 $
* Created : 15 March 2002
*
* $Revision: 1.1 $
*/
#ifdef KOCOCODEC_INCLUDE
static char euc_kr_decode__doc__[] = "EUC-KR decoder";
static PyObject *
euc_kr_decode(PyObject *self, PyObject *args)
{
unsigned char *argstr, *srccur, *srcend;
int arglen, errtype = error_strict;
char *errors = NULL;
Py_UNICODE *destptr, *destcur, *codemap, code;
PyObject *r;
if (!PyArg_ParseTuple(args, "s#|z:euc_kr_decode", &argstr, &arglen, &errors))
return NULL;
errtype = error_type(errors);
if (errtype == error_undef)
return NULL;
destcur = destptr = PyMem_New(Py_UNICODE, arglen+1);
for (srccur = argstr, srcend = argstr + arglen; srccur < srcend; srccur++) {
if ((*srccur & 0x80) && (srccur+1 < srcend)) {
codemap = ksc5601_decode_map[*srccur & 0x7F];
if (!codemap)
goto invalid;
if (ksc5601_decode_bottom <= srccur[1] && srccur[1] <= ksc5601_decode_top) {
code = codemap[srccur[1] - ksc5601_decode_bottom];
if (code == UNIFIL)
goto invalid;
*(destcur++) = code;
srccur++;
continue;
} else {
invalid: srccur++; /* skip 2byte */
switch (errtype) {
case error_strict:
PyMem_Del(destptr);
PyErr_Format(PyExc_UnicodeError,
"EUC-KR decoding error: invalid character \\x%02x%02x",
srccur[0], srccur[1]);
return NULL;
break;
case error_replace:
*(destcur++) = UNIFIL;
break;
/* case error_ignore: break; */
}
continue;
}
} else
*(destcur++) = *srccur;
}
r = codec_tuple(PyUnicode_FromUnicode(destptr, destcur-destptr), arglen);
PyMem_Del(destptr);
return r;
}
static char euc_kr_encode__doc__[] = "EUC-KR encoder";
static PyObject *
euc_kr_encode(PyObject *self, PyObject *args)
{
Py_UNICODE *argptr, *srccur, *srcend;
int arglen, errtype = error_strict;
char *errors = NULL;
unsigned char *destptr, *destcur, *decbuf;
PyObject *r;
if (!PyArg_ParseTuple(args, "u#|z:euc_kr_encode", &argptr, &arglen, &errors))
return NULL;
errtype = error_type(errors);
if (errtype == error_undef)
return NULL;
destcur = destptr = PyMem_New(unsigned char, arglen*2+1);
for (srccur = argptr, srcend = argptr + arglen; srccur < srcend; srccur++) {
if (*srccur <= 0x7F)
*(destcur++) = (unsigned char)*srccur;
else
if((decbuf = _ksc5601_encode(*srccur)) == 0) {
switch (errtype) {
case error_strict:
PyMem_Del(destptr);
PyErr_Format(PyExc_UnicodeError,
"EUC-KR encoding error: invalid character \\u%04x",
*srccur);
return NULL;
break;
case error_replace:
*(destcur++) = 0xa1;
*(destcur++) = 0xa1;
break;
/* case error_ignore: break; */
}
} else {
*(destcur++) = decbuf[0];
*(destcur++) = decbuf[1];
}
}
r = codec_tuple(PyString_FromStringAndSize((char*)destptr, destcur - destptr), arglen);
PyMem_Del(destptr);
return r;
}
#endif
|
×
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