1: /*
2: * Copyright (C) 1999-2002, 2004-2009 Free Software Foundation, Inc.
3: * This file is part of the GNU LIBICONV Library.
4: *
5: * The GNU LIBICONV Library is free software; you can redistribute it
6: * and/or modify it under the terms of the GNU Library General Public
7: * License as published by the Free Software Foundation; either version 2
8: * of the License, or (at your option) any later version.
9: *
10: * The GNU LIBICONV Library is distributed in the hope that it will be
11: * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
12: * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13: * Library General Public License for more details.
14: *
15: * You should have received a copy of the GNU Library General Public
16: * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
17: * If not, write to the Free Software Foundation, Inc., 51 Franklin Street,
18: * Fifth Floor, Boston, MA 02110-1301, USA.
19: */
20:
21: /* This file defines all the converters. */
22:
23:
24: /* Our own notion of wide character, as UCS-4, according to ISO-10646-1. */
25: typedef unsigned int ucs4_t;
26:
27: /* State used by a conversion. 0 denotes the initial state. */
28: typedef unsigned int state_t;
29:
30: /* iconv_t is an opaque type. This is the real iconv_t type. */
31: typedef struct conv_struct * conv_t;
32:
33: /*
34: * Data type for conversion multibyte -> unicode
35: */
36: struct mbtowc_funcs {
37: int (*xxx_mbtowc) (conv_t conv, ucs4_t *pwc, unsigned char const *s, int n);
38: /*
39: * int xxx_mbtowc (conv_t conv, ucs4_t *pwc, unsigned char const *s, int n)
40: * converts the byte sequence starting at s to a wide character. Up to n bytes
41: * are available at s. n is >= 1.
42: * Result is number of bytes consumed (if a wide character was read),
43: * or -1 if invalid, or -2 if n too small, or -2-(number of bytes consumed)
44: * if only a shift sequence was read.
45: */
46: int (*xxx_flushwc) (conv_t conv, ucs4_t *pwc);
47: /*
48: * int xxx_flushwc (conv_t conv, ucs4_t *pwc)
49: * returns to the initial state and stores the pending wide character, if any.
50: * Result is 1 (if a wide character was read) or 0 if none was pending.
51: */
52: };
53:
54: /* Return code if invalid input after a shift sequence of n bytes was read.
55: (xxx_mbtowc) */
56: #define RET_SHIFT_ILSEQ(n) (-1-2*(n))
57: /* Return code if invalid. (xxx_mbtowc) */
58: #define RET_ILSEQ RET_SHIFT_ILSEQ(0)
59: /* Return code if only a shift sequence of n bytes was read. (xxx_mbtowc) */
60: #define RET_TOOFEW(n) (-2-2*(n))
61: /* Retrieve the n from the encoded RET_... value. */
62: #define DECODE_SHIFT_ILSEQ(r) ((unsigned int)(RET_SHIFT_ILSEQ(0) - (r)) / 2)
63: #define DECODE_TOOFEW(r) ((unsigned int)(RET_TOOFEW(0) - (r)) / 2)
64:
65: /*
66: * Data type for conversion unicode -> multibyte
67: */
68: struct wctomb_funcs {
69: int (*xxx_wctomb) (conv_t conv, unsigned char *r, ucs4_t wc, int n);
70: /*
71: * int xxx_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, int n)
72: * converts the wide character wc to the character set xxx, and stores the
73: * result beginning at r. Up to n bytes may be written at r. n is >= 1.
74: * Result is number of bytes written, or -1 if invalid, or -2 if n too small.
75: */
76: int (*xxx_reset) (conv_t conv, unsigned char *r, int n);
77: /*
78: * int xxx_reset (conv_t conv, unsigned char *r, int n)
79: * stores a shift sequences returning to the initial state beginning at r.
80: * Up to n bytes may be written at r. n is >= 0.
81: * Result is number of bytes written, or -2 if n too small.
82: */
83: };
84:
85: /* Return code if invalid. (xxx_wctomb) */
86: #define RET_ILUNI -1
87: /* Return code if output buffer is too small. (xxx_wctomb, xxx_reset) */
88: #define RET_TOOSMALL -2
89:
90: /*
91: * Contents of a conversion descriptor.
92: */
93: struct conv_struct {
94: struct loop_funcs lfuncs;
95: /* Input (conversion multibyte -> unicode) */
96: int iindex;
97: struct mbtowc_funcs ifuncs;
98: state_t istate;
99: /* Output (conversion unicode -> multibyte) */
100: int oindex;
101: struct wctomb_funcs ofuncs;
102: int oflags;
103: state_t ostate;
104: /* Operation flags */
105: int transliterate;
106: int discard_ilseq;
107: #ifndef LIBICONV_PLUG
108: struct iconv_fallbacks fallbacks;
109: struct iconv_hooks hooks;
110: #endif
111: };
112:
113: /*
114: * Include all the converters.
115: */
116:
117: #include "ascii.h"
118:
119: /* General multi-byte encodings */
120: #include "utf8.h"
121: #include "ucs2.h"
122: #include "ucs2be.h"
123: #include "ucs2le.h"
124: #include "ucs4.h"
125: #include "ucs4be.h"
126: #include "ucs4le.h"
127: #include "utf16.h"
128: #include "utf16be.h"
129: #include "utf16le.h"
130: #include "utf32.h"
131: #include "utf32be.h"
132: #include "utf32le.h"
133: #include "utf7.h"
134: #include "ucs2internal.h"
135: #include "ucs2swapped.h"
136: #include "ucs4internal.h"
137: #include "ucs4swapped.h"
138: #include "c99.h"
139: #include "java.h"
140:
141: /* 8-bit encodings */
142: #include "iso8859_1.h"
143: #include "iso8859_2.h"
144: #include "iso8859_3.h"
145: #include "iso8859_4.h"
146: #include "iso8859_5.h"
147: #include "iso8859_6.h"
148: #include "iso8859_7.h"
149: #include "iso8859_8.h"
150: #include "iso8859_9.h"
151: #include "iso8859_10.h"
152: #include "iso8859_11.h"
153: #include "iso8859_13.h"
154: #include "iso8859_14.h"
155: #include "iso8859_15.h"
156: #include "iso8859_16.h"
157: #include "koi8_r.h"
158: #include "koi8_u.h"
159: #include "koi8_ru.h"
160: #include "cp1250.h"
161: #include "cp1251.h"
162: #include "cp1252.h"
163: #include "cp1253.h"
164: #include "cp1254.h"
165: #include "cp1255.h"
166: #include "cp1256.h"
167: #include "cp1257.h"
168: #include "cp1258.h"
169: #include "cp850.h"
170: #include "cp862.h"
171: #include "cp866.h"
172: #include "cp1131.h"
173: #include "mac_roman.h"
174: #include "mac_centraleurope.h"
175: #include "mac_iceland.h"
176: #include "mac_croatian.h"
177: #include "mac_romania.h"
178: #include "mac_cyrillic.h"
179: #include "mac_ukraine.h"
180: #include "mac_greek.h"
181: #include "mac_turkish.h"
182: #include "mac_hebrew.h"
183: #include "mac_arabic.h"
184: #include "mac_thai.h"
185: #include "hp_roman8.h"
186: #include "nextstep.h"
187: #include "armscii_8.h"
188: #include "georgian_academy.h"
189: #include "georgian_ps.h"
190: #include "koi8_t.h"
191: #include "pt154.h"
192: #include "rk1048.h"
193: #include "mulelao.h"
194: #include "cp1133.h"
195: #include "tis620.h"
196: #include "cp874.h"
197: #include "viscii.h"
198: #include "tcvn.h"
199:
200: /* CJK character sets [CCS = coded character set] [CJKV.INF chapter 3] */
201:
202: typedef struct {
203: unsigned short indx; /* index into big table */
204: unsigned short used; /* bitmask of used entries */
205: } Summary16;
206:
207: #include "iso646_jp.h"
208: #include "jisx0201.h"
209: #include "jisx0208.h"
210: #include "jisx0212.h"
211:
212: #include "iso646_cn.h"
213: #include "gb2312.h"
214: #include "isoir165.h"
215: /*#include "gb12345.h"*/
216: #include "gbk.h"
217: #include "cns11643.h"
218: #include "big5.h"
219:
220: #include "ksc5601.h"
221: #include "johab_hangul.h"
222:
223: /* CJK encodings [CES = character encoding scheme] [CJKV.INF chapter 4] */
224:
225: #include "euc_jp.h"
226: #include "sjis.h"
227: #include "cp932.h"
228: #include "iso2022_jp.h"
229: #include "iso2022_jp1.h"
230: #include "iso2022_jp2.h"
231:
232: #include "euc_cn.h"
233: #include "ces_gbk.h"
234: #include "cp936.h"
235: #include "gb18030.h"
236: #include "iso2022_cn.h"
237: #include "iso2022_cnext.h"
238: #include "hz.h"
239: #include "euc_tw.h"
240: #include "ces_big5.h"
241: #include "cp950.h"
242: #include "big5hkscs1999.h"
243: #include "big5hkscs2001.h"
244: #include "big5hkscs2004.h"
245:
246: #include "euc_kr.h"
247: #include "cp949.h"
248: #include "johab.h"
249: #include "iso2022_kr.h"
250:
251: /* Encodings used by system dependent locales. */
252:
253: #ifdef USE_AIX
254: #include "cp856.h"
255: #include "cp922.h"
256: #include "cp943.h"
257: #include "cp1046.h"
258: #include "cp1124.h"
259: #include "cp1129.h"
260: #include "cp1161.h"
261: #include "cp1162.h"
262: #include "cp1163.h"
263: #endif
264:
265: #ifdef USE_OSF1
266: #include "dec_kanji.h"
267: #include "dec_hanyu.h"
268: #endif
269:
270: #ifdef USE_DOS
271: #include "cp437.h"
272: #include "cp737.h"
273: #include "cp775.h"
274: #include "cp852.h"
275: #include "cp853.h"
276: #include "cp855.h"
277: #include "cp857.h"
278: #include "cp858.h"
279: #include "cp860.h"
280: #include "cp861.h"
281: #include "cp863.h"
282: #include "cp864.h"
283: #include "cp865.h"
284: #include "cp869.h"
285: #include "cp1125.h"
286: #endif
287:
288: #ifdef USE_EXTRA
289: #include "euc_jisx0213.h"
290: #include "shift_jisx0213.h"
291: #include "iso2022_jp3.h"
292: #include "big5_2003.h"
293: #include "tds565.h"
294: #include "atarist.h"
295: #include "riscos1.h"
296: #endif
297:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to converters.h CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / libiconv / lib