1 /* Conversion module for ISO-2022-KR.
2 Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc.
3 This file is part of the GNU C Library.
4 Contributed by Ulrich Drepper <drepper@cygnus.com>, 1998.
6 The GNU C Library is free software; you can redistribute it and/or
7 modify it under the terms of the GNU Library General Public License as
8 published by the Free Software Foundation; either version 2 of the
9 License, or (at your option) any later version.
11 The GNU C Library is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 Library General Public License for more details.
16 You should have received a copy of the GNU Library General Public
17 License along with the GNU C Library; see the file COPYING.LIB. If not,
18 write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 Boston, MA 02111-1307, USA. */
28 /* This makes obvious what everybody knows: 0x1b is the Esc character. */
31 /* The shift sequences for this charset (it does not use ESC). */
35 /* Definitions used in the body of the `gconv' function. */
36 #define CHARSET_NAME "ISO-2022-KR//"
39 #define FROM_LOOP from_iso2022kr_loop
40 #define TO_LOOP to_iso2022kr_loop
41 #define MIN_NEEDED_FROM 1
42 #define MAX_NEEDED_FROM 3
43 #define MIN_NEEDED_TO 4
44 #define MAX_NEEDED_TO 4
45 #define PREPARE_LOOP \
47 int *setp = &data->__statep->count; \
48 if (!FROM_DIRECTION && !data->__internal_use \
49 && data->__invocation_counter == 0) \
51 /* Emit the designator sequence. */ \
52 if (outbuf + 4 > outend) \
53 return __GCONV_FULL_OUTPUT; \
60 #define EXTRA_LOOP_ARGS , setp
63 /* The COUNT element of the state keeps track of the currently selected
64 character set. The possible values are: */
72 /* Since this is a stateful encoding we have to provide code which resets
73 the output state to the initial state. This has to be done during the
75 #define EMIT_SHIFT_TO_INIT \
76 if (data->__statep->count != ASCII_set) \
79 /* It's easy, we don't have to emit anything, we just reset the \
80 state for the input. */ \
81 data->__statep->count = ASCII_set; \
84 unsigned char *outbuf = data->__outbuf; \
86 /* We are not in the initial state. To switch back we have \
88 if (outbuf == data->__outbufend) \
89 /* We don't have enough room in the output buffer. */ \
90 status = __GCONV_FULL_OUTPUT; \
93 /* Write out the shift sequence. */ \
95 if (data->__is_last) \
97 data->__outbuf = outbuf; \
98 data->__statep->count = ASCII_set; \
104 /* Since we might have to reset input pointer we must be able to save
105 and retore the state. */
106 #define SAVE_RESET_STATE(Save) \
113 /* First define the conversion function from ISO-2022-KR to UCS4. */
114 #define MIN_NEEDED_INPUT MIN_NEEDED_FROM
115 #define MAX_NEEDED_INPUT MAX_NEEDED_FROM
116 #define MIN_NEEDED_OUTPUT MIN_NEEDED_TO
117 #define LOOPFCT FROM_LOOP
120 uint32_t ch = *inptr; \
122 /* This is a 7bit character set, disallow all 8bit characters. */ \
125 result = __GCONV_ILLEGAL_INPUT; \
129 /* Recognize escape sequences. */ \
132 /* We don't really have to handle escape sequences since all the \
133 switching is done using the SI and SO bytes. But we have to \
134 recognize `Esc $ ) C' since this is a kind of flag for this \
135 encoding. We simply ignore it. */ \
136 if ((NEED_LENGTH_TEST && inptr + 1 > inend) \
137 || (inptr[1] == '$' \
138 && ((NEED_LENGTH_TEST && inptr + 2 > inend) \
139 || (inptr[2] == ')' && inptr + 3 > inend)))) \
142 result = __GCONV_EMPTY_INPUT; \
145 if (inptr[1] == '$' && inptr[2] == ')' && inptr[3] == 'C') \
147 /* Yeah, yeah, we know this is ISO 2022-KR. */ \
154 /* Switch to use KSC. */ \
161 /* Switch to use ASCII. */ \
167 if (set == ASCII_set) \
169 /* Almost done, just advance the input pointer. */ \
174 assert (set == KSC5601_set); \
176 /* Use the KSC 5601 table. */ \
177 ch = ksc5601_to_ucs4 (&inptr, \
178 NEED_LENGTH_TEST ? inend - inptr : 2, 0); \
180 if (NEED_LENGTH_TEST && ch == 0) \
182 result = __GCONV_EMPTY_INPUT; \
185 else if (ch == __UNKNOWN_10646_CHAR) \
187 result = __GCONV_ILLEGAL_INPUT; \
192 put32 (outptr, ch); \
195 #define EXTRA_LOOP_DECLS , int *setp
196 #define INIT_PARAMS int set = *setp
197 #define UPDATE_PARAMS *setp = set
198 #include <iconv/loop.c>
201 /* Next, define the other direction. */
202 #define MIN_NEEDED_INPUT MIN_NEEDED_TO
203 #define MIN_NEEDED_OUTPUT MIN_NEEDED_FROM
204 #define MAX_NEEDED_OUTPUT MAX_NEEDED_FROM
205 #define LOOPFCT TO_LOOP
209 size_t written = 0; \
211 ch = get32 (inptr); \
213 /* First see whether we can write the character using the currently \
214 selected character set. */ \
217 if (set != ASCII_set) \
221 if (NEED_LENGTH_TEST && outptr == outend) \
223 result = __GCONV_FULL_OUTPUT; \
235 written = ucs4_to_ksc5601 (ch, buf, 2); \
237 if (written == __UNKNOWN_10646_CHAR) \
239 /* Illegal character. */ \
240 result = __GCONV_ILLEGAL_INPUT; \
243 assert (written == 2); \
245 /* We use KSC 5601. */ \
246 if (set != KSC5601_set) \
252 if (NEED_LENGTH_TEST && outptr + 2 > outend) \
254 result = __GCONV_FULL_OUTPUT; \
258 *outptr++ = buf[0]; \
259 *outptr++ = buf[1]; \
262 /* Now that we wrote the output increment the input pointer. */ \
265 #define EXTRA_LOOP_DECLS , int *setp
266 #define INIT_PARAMS int set = *setp
267 #define UPDATE_PARAMS *setp = set
268 #include <iconv/loop.c>
271 /* Now define the toplevel functions. */
272 #include <iconv/skeleton.c>