mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-03 00:10:10 +00:00
Update.
1998-04-01 17:38 Ulrich Drepper <drepper@cygnus.com> * iconv/gconv?simple.c: New builtins for UCS en/decoding. * iconv/gconv_builtin.h: Add definitions for new builtins. * iconv/gconv.h: Add prototypes for new builtins. * iconvdata/Makefile (modules): Add ISO646. Add rules for ISO646 module. (distribute): Add iso646.c. * iconvdata/gconv-modules: Add module and alias definition for ISO646 charsets. * iconvdata/iso646.c: New file.
This commit is contained in:
Ulrich Drepper
parent
8fe0fd03e5
commit
d2374599d4
13
ChangeLog
13
ChangeLog
@ -1,3 +1,16 @@
|
|||||||
|
1998-04-01 17:38 Ulrich Drepper <drepper@cygnus.com>
|
||||||
|
|
||||||
|
* iconv/gconv?simple.c: New builtins for UCS en/decoding.
|
||||||
|
* iconv/gconv_builtin.h: Add definitions for new builtins.
|
||||||
|
* iconv/gconv.h: Add prototypes for new builtins.
|
||||||
|
|
||||||
|
* iconvdata/Makefile (modules): Add ISO646.
|
||||||
|
Add rules for ISO646 module.
|
||||||
|
(distribute): Add iso646.c.
|
||||||
|
* iconvdata/gconv-modules: Add module and alias definition for
|
||||||
|
ISO646 charsets.
|
||||||
|
* iconvdata/iso646.c: New file.
|
||||||
|
|
||||||
1998-04-01 16:10 Ulrich Drepper <drepper@cygnus.com>
|
1998-04-01 16:10 Ulrich Drepper <drepper@cygnus.com>
|
||||||
|
|
||||||
* libc.map: Add __gconv_alias_db, __gconv_nmodules, __gconv_modules_db.
|
* libc.map: Add __gconv_alias_db, __gconv_nmodules, __gconv_modules_db.
|
||||||
|
|||||||
@ -1,4 +1,4 @@
|
|||||||
/* Copyright (C) 1997 Free Software Foundation, Inc.
|
/* Copyright (C) 1997, 1998 Free Software Foundation, Inc.
|
||||||
This file is part of the GNU C Library.
|
This file is part of the GNU C Library.
|
||||||
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997.
|
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997.
|
||||||
|
|
||||||
@ -200,6 +200,8 @@ extern void __gconv_get_builtin_trans __P ((__const char *__name,
|
|||||||
__BUILTIN_TRANS (__gconv_transform_dummy);
|
__BUILTIN_TRANS (__gconv_transform_dummy);
|
||||||
__BUILTIN_TRANS (__gconv_transform_ucs4_utf8);
|
__BUILTIN_TRANS (__gconv_transform_ucs4_utf8);
|
||||||
__BUILTIN_TRANS (__gconv_transform_utf8_ucs4);
|
__BUILTIN_TRANS (__gconv_transform_utf8_ucs4);
|
||||||
|
__BUILTIN_TRANS (__gconv_transform_ucs2_ucs4);
|
||||||
|
__BUILTIN_TRANS (__gconv_transform_ucs4_ucs2);
|
||||||
# undef __BUITLIN_TRANS
|
# undef __BUITLIN_TRANS
|
||||||
|
|
||||||
extern int __gconv_transform_init_rstate __P ((struct gconv_step *__step,
|
extern int __gconv_transform_init_rstate __P ((struct gconv_step *__step,
|
||||||
|
|||||||
@ -21,17 +21,32 @@
|
|||||||
BUILTIN_ALIAS ("UTF8//", "ISO-10646/UTF8/")
|
BUILTIN_ALIAS ("UTF8//", "ISO-10646/UTF8/")
|
||||||
BUILTIN_ALIAS ("UTF-8//", "ISO-10646/UTF8/")
|
BUILTIN_ALIAS ("UTF-8//", "ISO-10646/UTF8/")
|
||||||
|
|
||||||
BUILTIN_TRANSFORMATION ("([^/]+)/UCS4/([^/]*)", NULL, 0,
|
BUILTIN_TRANSFORMATION (NULL, "ISO-10646/UCS4/", 15,
|
||||||
"\\1/UTF8/\\2", 1, "=ucs4->utf8",
|
"ISO-10646/UTF8/", 1, "=ucs4->utf8",
|
||||||
__gconv_transform_ucs4_utf8,
|
__gconv_transform_ucs4_utf8,
|
||||||
__gconv_transform_init_rstate,
|
__gconv_transform_init_rstate,
|
||||||
__gconv_transform_end_rstate)
|
__gconv_transform_end_rstate)
|
||||||
|
|
||||||
BUILTIN_TRANSFORMATION ("([^/]+)/UTF-?8/([^/]*)", NULL, 0,
|
BUILTIN_TRANSFORMATION ("ISO-10646/UTF-?8/", "ISO-10646/UTF", 13,
|
||||||
"\\1/UCS4/\\2", 1, "=utf8->ucs4",
|
"ISO-10646/UCS4/", 1, "=utf8->ucs4",
|
||||||
__gconv_transform_utf8_ucs4,
|
__gconv_transform_utf8_ucs4,
|
||||||
__gconv_transform_init_rstate,
|
__gconv_transform_init_rstate,
|
||||||
__gconv_transform_end_rstate)
|
__gconv_transform_end_rstate)
|
||||||
|
|
||||||
|
BUILTIN_ALIAS ("UCS2//", "ISO-10646/UCS2/")
|
||||||
|
BUILTIN_ALIAS ("UCS-2//", "ISO-10646/UCS2/")
|
||||||
|
|
||||||
|
BUILTIN_TRANSFORMATION (NULL, "ISO-10646/UCS2/", 15, "ISO-10646/UCS4/",
|
||||||
|
1, "=ucs2->ucs4",
|
||||||
|
__gconv_transform_ucs2_ucs4,
|
||||||
|
__gconv_transform_init_rstate,
|
||||||
|
__gconv_transform_end_rstate)
|
||||||
|
|
||||||
|
BUILTIN_TRANSFORMATION (NULL, "ISO-10646/UCS4/", 15, "ISO-10646/UCS2/",
|
||||||
|
1, "=ucs4->ucs2",
|
||||||
|
__gconv_transform_ucs4_ucs2,
|
||||||
|
__gconv_transform_init_rstate,
|
||||||
|
__gconv_transform_end_rstate)
|
||||||
|
|
||||||
BUILTIN_TRANSFORMATION ("(.*)", NULL, 0, "\\1", 1, "=dummy",
|
BUILTIN_TRANSFORMATION ("(.*)", NULL, 0, "\\1", 1, "=dummy",
|
||||||
__gconv_transform_dummy, NULL, NULL)
|
__gconv_transform_dummy, NULL, NULL)
|
||||||
|
|||||||
@ -20,6 +20,7 @@
|
|||||||
|
|
||||||
#include <errno.h>
|
#include <errno.h>
|
||||||
#include <gconv.h>
|
#include <gconv.h>
|
||||||
|
#include <stdint.h>
|
||||||
#include <stdlib.h>
|
#include <stdlib.h>
|
||||||
#include <string.h>
|
#include <string.h>
|
||||||
#include <wchar.h>
|
#include <wchar.h>
|
||||||
@ -289,3 +290,253 @@ __gconv_transform_utf8_ucs4 (struct gconv_step *step,
|
|||||||
|
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int
|
||||||
|
__gconv_transform_ucs2_ucs4 (struct gconv_step *step,
|
||||||
|
struct gconv_step_data *data, const char *inbuf,
|
||||||
|
size_t *inlen, size_t *written, int do_flush)
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
gconv_fct fct = next_step->fct;
|
||||||
|
size_t do_write;
|
||||||
|
int result;
|
||||||
|
|
||||||
|
/* If the function is called with no input this means we have to reset
|
||||||
|
to the initial state. The possibly partly converted input is
|
||||||
|
dropped. */
|
||||||
|
if (do_flush)
|
||||||
|
{
|
||||||
|
/* Clear the state. */
|
||||||
|
memset (data->data, '\0', sizeof (mbstate_t));
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
/* Call the steps down the chain if there are any. */
|
||||||
|
if (data->is_last)
|
||||||
|
result = GCONV_OK;
|
||||||
|
else
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, NULL, 0, written, 1);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
int save_errno = errno;
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
do
|
||||||
|
{
|
||||||
|
const uint16_t *newinbuf = (const uint16_t *) inbuf;
|
||||||
|
wchar_t *outbuf = (wchar_t *) &data->outbuf[data->outbufavail];
|
||||||
|
size_t actually = 0;
|
||||||
|
|
||||||
|
errno = 0;
|
||||||
|
|
||||||
|
while (data->outbufavail + 4 <= data->outbufsize
|
||||||
|
&& *inlen >= 2)
|
||||||
|
{
|
||||||
|
outbuf[actually++] = *newinbuf++;
|
||||||
|
data->outbufavail += 4;
|
||||||
|
*inlen -= 2;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (*inlen != 1)
|
||||||
|
{
|
||||||
|
/* We have an incomplete input character. */
|
||||||
|
mbstate_t *state = (mbstate_t *) data->data;
|
||||||
|
state->count = 1;
|
||||||
|
state->value = *(uint8_t *) newinbuf;
|
||||||
|
--*inlen;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Remember how much we converted. */
|
||||||
|
do_write += actually * sizeof (wchar_t);
|
||||||
|
|
||||||
|
/* Check whether an illegal character appeared. */
|
||||||
|
if (errno != 0)
|
||||||
|
{
|
||||||
|
result = GCONV_ILLEGAL_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (*inlen == 0 && !mbsinit ((mbstate_t *) data->data))
|
||||||
|
{
|
||||||
|
/* We have an incomplete character at the end. */
|
||||||
|
result = GCONV_INCOMPLETE_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (data->is_last)
|
||||||
|
{
|
||||||
|
/* This is the last step. */
|
||||||
|
result = (data->outbufavail + sizeof (wchar_t) > data->outbufsize
|
||||||
|
? GCONV_FULL_OUTPUT : GCONV_EMPTY_INPUT);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Status so far. */
|
||||||
|
result = GCONV_EMPTY_INPUT;
|
||||||
|
|
||||||
|
if (data->outbufavail > 0)
|
||||||
|
{
|
||||||
|
/* Call the functions below in the chain. */
|
||||||
|
size_t newavail = data->outbufavail;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, data->outbuf, &newavail,
|
||||||
|
written, 0);
|
||||||
|
|
||||||
|
/* Correct the output buffer. */
|
||||||
|
if (newavail != data->outbufavail && newavail > 0)
|
||||||
|
{
|
||||||
|
memmove (data->outbuf,
|
||||||
|
&data->outbuf[data->outbufavail - newavail],
|
||||||
|
newavail);
|
||||||
|
data->outbufavail = newavail;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
while (*inlen > 0 && result == GCONV_EMPTY_INPUT);
|
||||||
|
|
||||||
|
__set_errno (save_errno);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (written != NULL && data->is_last)
|
||||||
|
*written = do_write;
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int
|
||||||
|
__gconv_transform_ucs4_ucs2 (struct gconv_step *step,
|
||||||
|
struct gconv_step_data *data, const char *inbuf,
|
||||||
|
size_t *inlen, size_t *written, int do_flush)
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
gconv_fct fct = next_step->fct;
|
||||||
|
size_t do_write;
|
||||||
|
int result;
|
||||||
|
|
||||||
|
/* If the function is called with no input this means we have to reset
|
||||||
|
to the initial state. The possibly partly converted input is
|
||||||
|
dropped. */
|
||||||
|
if (do_flush)
|
||||||
|
{
|
||||||
|
/* Clear the state. */
|
||||||
|
memset (data->data, '\0', sizeof (mbstate_t));
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
/* Call the steps down the chain if there are any. */
|
||||||
|
if (data->is_last)
|
||||||
|
result = GCONV_OK;
|
||||||
|
else
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, NULL, 0, written, 1);
|
||||||
|
|
||||||
|
/* Clear output buffer. */
|
||||||
|
data->outbufavail = 0;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
int save_errno = errno;
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
do
|
||||||
|
{
|
||||||
|
const wchar_t *newinbuf = (const wchar_t *) inbuf;
|
||||||
|
uint16_t *outbuf = (uint16_t *) &data->outbuf[data->outbufavail];
|
||||||
|
size_t actually = 0;
|
||||||
|
|
||||||
|
errno = 0;
|
||||||
|
|
||||||
|
while (data->outbufavail + 2 <= data->outbufsize
|
||||||
|
&& *inlen >= 4)
|
||||||
|
{
|
||||||
|
if (*newinbuf >= 0x10000)
|
||||||
|
{
|
||||||
|
__set_errno (EILSEQ);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
outbuf[actually++] = (wchar_t) *newinbuf;
|
||||||
|
*inlen -= 4;
|
||||||
|
data->outbufavail += 2;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (*inlen < 4)
|
||||||
|
{
|
||||||
|
/* We have an incomplete input character. */
|
||||||
|
mbstate_t *state = (mbstate_t *) data->data;
|
||||||
|
state->count = *inlen;
|
||||||
|
state->value = 0;
|
||||||
|
while (*inlen > 0)
|
||||||
|
{
|
||||||
|
state->value <<= 8;
|
||||||
|
state->value += *(uint8_t *) newinbuf;
|
||||||
|
--*inlen;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Remember how much we converted. */
|
||||||
|
do_write += (const char *) newinbuf - inbuf;
|
||||||
|
|
||||||
|
/* Check whether an illegal character appeared. */
|
||||||
|
if (errno != 0)
|
||||||
|
{
|
||||||
|
result = GCONV_ILLEGAL_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (*inlen == 0 && !mbsinit ((mbstate_t *) data->data))
|
||||||
|
{
|
||||||
|
/* We have an incomplete character at the end. */
|
||||||
|
result = GCONV_INCOMPLETE_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (data->is_last)
|
||||||
|
{
|
||||||
|
/* This is the last step. */
|
||||||
|
result = *inlen == 0 ? GCONV_EMPTY_INPUT : GCONV_FULL_OUTPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Status so far. */
|
||||||
|
result = GCONV_EMPTY_INPUT;
|
||||||
|
|
||||||
|
if (data->outbufavail > 0)
|
||||||
|
{
|
||||||
|
/* Call the functions below in the chain. */
|
||||||
|
size_t newavail = data->outbufavail;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, data->outbuf, &newavail,
|
||||||
|
written, 0);
|
||||||
|
|
||||||
|
/* Correct the output buffer. */
|
||||||
|
if (newavail != data->outbufavail && newavail > 0)
|
||||||
|
{
|
||||||
|
memmove (data->outbuf,
|
||||||
|
&data->outbuf[data->outbufavail - newavail],
|
||||||
|
newavail);
|
||||||
|
data->outbufavail = newavail;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
while (*inlen > 0 && result == GCONV_EMPTY_INPUT);
|
||||||
|
|
||||||
|
__set_errno (save_errno);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (written != NULL && data->is_last)
|
||||||
|
*written = do_write / sizeof (wchar_t);
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|||||||
@ -26,7 +26,7 @@ modules := ISO8859-1 ISO8859-2 ISO8859-3 ISO8859-4 ISO8859-5 \
|
|||||||
ISO8859-6 ISO8859-7 ISO8859-8 ISO8859-9 ISO8859-10 \
|
ISO8859-6 ISO8859-7 ISO8859-8 ISO8859-9 ISO8859-10 \
|
||||||
T.61 ISO_6937 SJIS KOI-8 KOI8-R LATIN-GREEK LATIN-GREEK-1 \
|
T.61 ISO_6937 SJIS KOI-8 KOI8-R LATIN-GREEK LATIN-GREEK-1 \
|
||||||
HP-ROMAN8 EBCDIC-AT-DE EBCDIC-AT-DE-A EBCDIC-CA-FR \
|
HP-ROMAN8 EBCDIC-AT-DE EBCDIC-AT-DE-A EBCDIC-CA-FR \
|
||||||
EUC-KR UHC JOHAB libJIS libKSC
|
EUC-KR UHC JOHAB libJIS libKSC ISO646
|
||||||
modules.so := $(addsuffix .so, $(modules))
|
modules.so := $(addsuffix .so, $(modules))
|
||||||
|
|
||||||
|
|
||||||
@ -42,6 +42,7 @@ ISO8859-7-routines := iso8859-7
|
|||||||
ISO8859-8-routines := iso8859-8
|
ISO8859-8-routines := iso8859-8
|
||||||
ISO8859-9-routines := iso8859-9
|
ISO8859-9-routines := iso8859-9
|
||||||
ISO8859-10-routines := iso8859-10
|
ISO8859-10-routines := iso8859-10
|
||||||
|
ISO646-routines := iso646
|
||||||
T.61-routines := t61
|
T.61-routines := t61
|
||||||
ISO_6937-routines := iso6937
|
ISO_6937-routines := iso6937
|
||||||
SJIS-routines := sjis
|
SJIS-routines := sjis
|
||||||
@ -74,7 +75,8 @@ distribute := 8bit-generic.c 8bit-gap.c gap.pl gaptab.pl gconv-modules \
|
|||||||
koi-8.c koi8-r.c koi8-r.h hp-roman8.c latin-greek.c \
|
koi-8.c koi8-r.c koi8-r.h hp-roman8.c latin-greek.c \
|
||||||
latin-greek.h latin-greek-1.c latin-greek-1.h ebcdic-at-de.c \
|
latin-greek.h latin-greek-1.c latin-greek-1.h ebcdic-at-de.c \
|
||||||
ebcdic-at-de-a.c ebcdic-ca-fr.c jis0201.c jis0208.c jis0212.c \
|
ebcdic-at-de-a.c ebcdic-ca-fr.c jis0201.c jis0208.c jis0212.c \
|
||||||
extra-module.mk euckr.c johab.c uhc.c ksc5601.c ksc5601.h
|
extra-module.mk euckr.c johab.c uhc.c ksc5601.c ksc5601.h \
|
||||||
|
iso646.c
|
||||||
|
|
||||||
# We build the transformation modules only when we build shared libs.
|
# We build the transformation modules only when we build shared libs.
|
||||||
ifeq (yes,$(build-shared))
|
ifeq (yes,$(build-shared))
|
||||||
|
|||||||
@ -38,6 +38,26 @@ alias ISO-10646// ISO-10646/UCS4/
|
|||||||
alias 10646-1:1993// ISO-10646/UCS4/
|
alias 10646-1:1993// ISO-10646/UCS4/
|
||||||
alias 10646-1:1993/UCS4/ ISO-10646/UCS4/
|
alias 10646-1:1993/UCS4/ ISO-10646/UCS4/
|
||||||
|
|
||||||
|
# from to module cost
|
||||||
|
alias ISO-IR-6// ANSI_X3.4-1968//
|
||||||
|
alias ANSI_X3.4-1986// ANSI_X3.4-1968//
|
||||||
|
alias ISO_646.IRV:1991// ANSI_X3.4-1968//
|
||||||
|
alias ASCII// ANSI_X3.4-1968//
|
||||||
|
alias ISO646-US// ANSI_X3.4-1968//
|
||||||
|
alias US-ASCII// ANSI_X3.4-1968//
|
||||||
|
alias US// ANSI_X3.4-1968//
|
||||||
|
alias IBM367// ANSI_X3.4-1968//
|
||||||
|
alias CP367// ANSI_X3.4-1968//
|
||||||
|
module ANSI_X3.4-1968// ISO-10646/UCS4/ ISO646 1
|
||||||
|
module ISO-10646/UCS4/ ANSI_X3.4-1968// ISO646 1
|
||||||
|
|
||||||
|
alias ISO-IR-4// BS_4730//
|
||||||
|
alias ISO646-GB// BS_4730//
|
||||||
|
alias GB// BS_4730//
|
||||||
|
alias UK// BS_4730//
|
||||||
|
module BS_4730// ISO-10646/UCS4/ ISO646
|
||||||
|
module ISO-10646/UCS4/ BS_4730// ISO646
|
||||||
|
|
||||||
# from to module cost
|
# from to module cost
|
||||||
alias ISO-IR-100// ISO-8859-1//
|
alias ISO-IR-100// ISO-8859-1//
|
||||||
alias ISO_8859-1:1987// ISO-8859-1//
|
alias ISO_8859-1:1987// ISO-8859-1//
|
||||||
|
|||||||
263
iconvdata/iso646.c
Normal file
263
iconvdata/iso646.c
Normal file
@ -0,0 +1,263 @@
|
|||||||
|
/* Conversion to and from the various ISO 646 CCS.
|
||||||
|
Copyright (C) 1998 Free Software Foundation, Inc.
|
||||||
|
This file is part of the GNU C Library.
|
||||||
|
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1998.
|
||||||
|
|
||||||
|
The GNU C Library is free software; you can redistribute it and/or
|
||||||
|
modify it under the terms of the GNU Library General Public License as
|
||||||
|
published by the Free Software Foundation; either version 2 of the
|
||||||
|
License, or (at your option) any later version.
|
||||||
|
|
||||||
|
The GNU C 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
|
||||||
|
Library General Public License for more details.
|
||||||
|
|
||||||
|
You should have received a copy of the GNU Library General Public
|
||||||
|
License along with the GNU C Library; see the file COPYING.LIB. If not,
|
||||||
|
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
||||||
|
Boston, MA 02111-1307, USA. */
|
||||||
|
|
||||||
|
#include <gconv.h>
|
||||||
|
#include <stdlib.h>
|
||||||
|
#include <string.h>
|
||||||
|
|
||||||
|
/* Direction of the transformation. */
|
||||||
|
enum direction
|
||||||
|
{
|
||||||
|
illegal,
|
||||||
|
to_iso646,
|
||||||
|
from_iso646
|
||||||
|
};
|
||||||
|
|
||||||
|
enum variant
|
||||||
|
{
|
||||||
|
US, /* ANSI_X3.4-1968 */
|
||||||
|
GB, /* BS_4730 */
|
||||||
|
};
|
||||||
|
|
||||||
|
struct iso646_data
|
||||||
|
{
|
||||||
|
enum direction dir;
|
||||||
|
enum variant var;
|
||||||
|
};
|
||||||
|
|
||||||
|
|
||||||
|
int
|
||||||
|
gconv_init (struct gconv_step *step, struct gconv_step_data *data)
|
||||||
|
{
|
||||||
|
/* Determine which direction. */
|
||||||
|
struct iso646_data *new_data;
|
||||||
|
enum direction dir;
|
||||||
|
enum variant var;
|
||||||
|
int result;
|
||||||
|
|
||||||
|
if (strcasestr (step->from_name, "ANSI_X3.4-1968") != NULL)
|
||||||
|
{
|
||||||
|
dir = from_iso646;
|
||||||
|
var = US;
|
||||||
|
}
|
||||||
|
else if (strcasestr (step->from_name, "BS_4730") != NULL)
|
||||||
|
{
|
||||||
|
dir = from_iso646;
|
||||||
|
var = GB;
|
||||||
|
}
|
||||||
|
else if (strcasestr (step->to_name, "ANSI_X3.4-1968") != NULL)
|
||||||
|
{
|
||||||
|
dir = to_iso646;
|
||||||
|
var = US;
|
||||||
|
}
|
||||||
|
else if (strcasestr (step->to_name, "BS_4730") != NULL)
|
||||||
|
{
|
||||||
|
dir = to_iso646;
|
||||||
|
var = GB;
|
||||||
|
}
|
||||||
|
else
|
||||||
|
dir = illegal;
|
||||||
|
|
||||||
|
result = GCONV_NOCONV;
|
||||||
|
if (dir != illegal
|
||||||
|
&& ((new_data
|
||||||
|
= (struct iso646_data *) malloc (sizeof (struct iso646_data)))
|
||||||
|
!= NULL))
|
||||||
|
{
|
||||||
|
new_data->dir = dir;
|
||||||
|
new_data->var = var;
|
||||||
|
data->data = new_data;
|
||||||
|
result = GCONV_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
void
|
||||||
|
gconv_end (struct gconv_step_data *data)
|
||||||
|
{
|
||||||
|
free (data->data);
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int
|
||||||
|
gconv (struct gconv_step *step, struct gconv_step_data *data,
|
||||||
|
const char *inbuf, size_t *inbufsize, size_t *written, int do_flush)
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
gconv_fct fct = next_step->fct;
|
||||||
|
size_t do_write;
|
||||||
|
int result;
|
||||||
|
|
||||||
|
/* If the function is called with no input this means we have to reset
|
||||||
|
to the initial state. The possibly partly converted input is
|
||||||
|
dropped. */
|
||||||
|
if (do_flush)
|
||||||
|
{
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
/* Call the steps down the chain if there are any. */
|
||||||
|
if (data->is_last)
|
||||||
|
result = GCONV_OK;
|
||||||
|
else
|
||||||
|
{
|
||||||
|
struct gconv_step *next_step = step + 1;
|
||||||
|
struct gconv_step_data *next_data = data + 1;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, NULL, 0, written, 1);
|
||||||
|
|
||||||
|
/* Clear output buffer. */
|
||||||
|
data->outbufavail = 0;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
enum direction dir = ((struct iso646_data *) data->data)->dir;
|
||||||
|
enum variant var = ((struct iso646_data *) data->data)->var;
|
||||||
|
|
||||||
|
do_write = 0;
|
||||||
|
|
||||||
|
do
|
||||||
|
{
|
||||||
|
result = GCONV_OK;
|
||||||
|
|
||||||
|
if (dir == from_iso646)
|
||||||
|
{
|
||||||
|
size_t inchars = *inbufsize;
|
||||||
|
size_t outwchars = data->outbufavail;
|
||||||
|
char *outbuf = data->outbuf;
|
||||||
|
size_t cnt = 0;
|
||||||
|
|
||||||
|
while (cnt < inchars
|
||||||
|
&& (outwchars + sizeof (wchar_t) <= data->outbufsize))
|
||||||
|
{
|
||||||
|
switch ((unsigned char) inbuf[cnt])
|
||||||
|
{
|
||||||
|
case '\x23':
|
||||||
|
if (var == GB)
|
||||||
|
*((wchar_t *) (outbuf + outwchars)) = 0xa3;
|
||||||
|
else
|
||||||
|
*((wchar_t *) (outbuf + outwchars)) = 0x23;
|
||||||
|
break;
|
||||||
|
case '\x75':
|
||||||
|
if (var == GB)
|
||||||
|
*((wchar_t *) (outbuf + outwchars)) = 0x203e;
|
||||||
|
else
|
||||||
|
*((wchar_t *) (outbuf + outwchars)) = 0x75;
|
||||||
|
break;
|
||||||
|
default:
|
||||||
|
*((wchar_t *) (outbuf + outwchars)) =
|
||||||
|
(unsigned char) inbuf[cnt];
|
||||||
|
}
|
||||||
|
++do_write;
|
||||||
|
outwchars += sizeof (wchar_t);
|
||||||
|
++cnt;
|
||||||
|
}
|
||||||
|
*inbufsize -= cnt;
|
||||||
|
data->outbufavail = outwchars;
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
size_t inwchars = *inbufsize;
|
||||||
|
size_t outchars = data->outbufavail;
|
||||||
|
char *outbuf = data->outbuf;
|
||||||
|
size_t cnt = 0;
|
||||||
|
|
||||||
|
while (inwchars >= cnt + sizeof (wchar_t)
|
||||||
|
&& outchars < data->outbufsize)
|
||||||
|
{
|
||||||
|
if (*((wchar_t *) (inbuf + cnt)) >= L'\0'
|
||||||
|
&& *((wchar_t *) (inbuf + cnt)) <= L'\177')
|
||||||
|
outbuf[outchars] = *((wchar_t *) (inbuf + cnt));
|
||||||
|
else
|
||||||
|
/* Here is where the transliteration would enter the
|
||||||
|
scene. */
|
||||||
|
break;
|
||||||
|
|
||||||
|
++do_write;
|
||||||
|
++outchars;
|
||||||
|
cnt += sizeof (wchar_t);
|
||||||
|
}
|
||||||
|
*inbufsize -= cnt;
|
||||||
|
data->outbufavail = outchars;
|
||||||
|
|
||||||
|
if (outchars < data->outbufsize)
|
||||||
|
{
|
||||||
|
/* If there is still room in the output buffer something
|
||||||
|
is wrong with the input. */
|
||||||
|
if (inwchars >= cnt + sizeof (wchar_t))
|
||||||
|
{
|
||||||
|
/* An error occurred. */
|
||||||
|
result = GCONV_ILLEGAL_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
if (inwchars != cnt)
|
||||||
|
{
|
||||||
|
/* There are some unprocessed bytes at the end of the
|
||||||
|
input buffer. */
|
||||||
|
result = GCONV_INCOMPLETE_INPUT;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (result != GCONV_OK)
|
||||||
|
break;
|
||||||
|
|
||||||
|
if (data->is_last)
|
||||||
|
{
|
||||||
|
/* This is the last step. */
|
||||||
|
result = (*inbufsize > (dir == from_iso646
|
||||||
|
? 0 : sizeof (wchar_t) - 1)
|
||||||
|
? GCONV_FULL_OUTPUT : GCONV_EMPTY_INPUT);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Status so far. */
|
||||||
|
result = GCONV_EMPTY_INPUT;
|
||||||
|
|
||||||
|
if (data->outbufavail > 0)
|
||||||
|
{
|
||||||
|
/* Call the functions below in the chain. */
|
||||||
|
size_t newavail = data->outbufavail;
|
||||||
|
|
||||||
|
result = (*fct) (next_step, next_data, data->outbuf, &newavail,
|
||||||
|
written, 0);
|
||||||
|
|
||||||
|
/* Correct the output buffer. */
|
||||||
|
if (newavail != data->outbufavail && newavail > 0)
|
||||||
|
{
|
||||||
|
memmove (data->outbuf,
|
||||||
|
&data->outbuf[data->outbufavail - newavail],
|
||||||
|
newavail);
|
||||||
|
data->outbufavail = newavail;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
while (*inbufsize > 0 && result == GCONV_EMPTY_INPUT);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (written != NULL && data->is_last)
|
||||||
|
*written = do_write;
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue
Block a user