2 /* $NetBSD: citrus_ues.c,v 1.3 2012/02/12 13:51:29 wiz Exp $ */
5 * Copyright (c)2006 Citrus Project,
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 #include <sys/cdefs.h>
41 #include "citrus_namespace.h"
42 #include "citrus_types.h"
43 #include "citrus_bcs.h"
44 #include "citrus_module.h"
45 #include "citrus_stdenc.h"
46 #include "citrus_ues.h"
59 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
60 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
62 #define _FUNCNAME(m) _citrus_UES_##m
63 #define _ENCODING_INFO _UESEncodingInfo
64 #define _ENCODING_STATE _UESState
65 #define _ENCODING_MB_CUR_MAX(_ei_) (_ei_)->mb_cur_max
66 #define _ENCODING_IS_STATE_DEPENDENT 0
67 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
71 _citrus_UES_init_state(_UESEncodingInfo * __restrict ei __unused,
72 _UESState * __restrict psenc)
81 _citrus_UES_pack_state(_UESEncodingInfo * __restrict ei __unused,
82 void *__restrict pspriv, const _UESState * __restrict psenc)
85 memcpy(pspriv, (const void *)psenc, sizeof(*psenc));
90 _citrus_UES_unpack_state(_UESEncodingInfo * __restrict ei __unused,
91 _UESState * __restrict psenc, const void * __restrict pspriv)
94 memcpy((void *)psenc, pspriv, sizeof(*psenc));
102 if (ch >= '0' && ch <= '9')
104 else if (ch >= 'A' && ch <= 'F')
105 return ((ch - 'A') + 10);
106 else if (ch >= 'a' && ch <= 'f')
107 return ((ch - 'a') + 10);
117 #define BMP_MAX UINT32_C(0xFFFF)
118 #define UCS2_MAX UINT32_C(0x10FFFF)
119 #define UCS4_MAX UINT32_C(0x7FFFFFFF)
121 static const char *xdig = "0123456789abcdef";
124 to_str(char *s, wchar_t wc, int bit)
141 *p++ = xdig[(wc >> (bit -= 4)) & 0xF];
147 is_hi_surrogate(wchar_t wc)
150 return (wc >= 0xD800 && wc <= 0xDBFF);
154 is_lo_surrogate(wchar_t wc)
157 return (wc >= 0xDC00 && wc <= 0xDFFF);
160 static __inline wchar_t
161 surrogate_to_ucs(wchar_t hi, wchar_t lo)
166 return ((hi << 10 | lo) + 0x10000);
170 ucs_to_surrogate(wchar_t wc, wchar_t * __restrict hi, wchar_t * __restrict lo)
174 *hi = (wc >> 10) + 0xD800;
175 *lo = (wc & 0x3FF) + 0xDC00;
182 return ((uint32_t)wc <= 0x9F && wc != 0x24 && wc != 0x40 &&
187 _citrus_UES_mbrtowc_priv(_UESEncodingInfo * __restrict ei,
188 wchar_t * __restrict pwc, char ** __restrict s, size_t n,
189 _UESState * __restrict psenc, size_t * __restrict nresult)
192 int ch, head, num, tail;
196 _citrus_UES_init_state(ei, psenc);
208 if (psenc->chlen == head) {
211 psenc->ch[psenc->chlen++] = *s0++;
213 ch = (unsigned char)psenc->ch[head++];
215 if (psenc->chlen == head) {
218 psenc->ch[psenc->chlen++] = *s0++;
220 switch (psenc->ch[head]) {
225 if (ei->mode & MODE_C99) {
235 for (; head < tail; ++head) {
236 if (psenc->chlen == head) {
240 *nresult = (size_t)-2;
243 psenc->ch[psenc->chlen++] = *s0++;
245 num = to_int((int)(unsigned char)psenc->ch[head]);
250 wc = (wc << 4) | num;
257 if (hi != (wchar_t)0)
259 if ((ei->mode & MODE_C99) == 0) {
260 if (is_hi_surrogate(wc) != 0) {
264 if ((uint32_t)wc <= 0x7F /* XXX */ ||
265 is_lo_surrogate(wc) != 0)
271 if (is_basic(wc) == 0 && (uint32_t)wc <= UCS4_MAX &&
272 is_hi_surrogate(wc) == 0 && is_lo_surrogate(wc) == 0)
274 *nresult = (size_t)-1;
277 if (is_lo_surrogate(wc) == 0)
279 wc = surrogate_to_ucs(hi, wc);
282 ch = (unsigned char)psenc->ch[0];
285 memmove(&psenc->ch[0], &psenc->ch[1], head);
291 *nresult = (size_t)((wc == 0) ? 0 : (s0 - *s));
298 _citrus_UES_wcrtomb_priv(_UESEncodingInfo * __restrict ei,
299 char * __restrict s, size_t n, wchar_t wc,
300 _UESState * __restrict psenc, size_t * __restrict nresult)
304 if (psenc->chlen != 0)
307 if ((ei->mode & MODE_C99) ? is_basic(wc) : (uint32_t)wc <= 0x7F) {
310 psenc->ch[psenc->chlen++] = (char)wc;
311 } else if ((uint32_t)wc <= BMP_MAX) {
314 psenc->chlen = to_str(&psenc->ch[0], wc, UCS2_BIT);
315 } else if ((ei->mode & MODE_C99) == 0 && (uint32_t)wc <= UCS2_MAX) {
318 ucs_to_surrogate(wc, &hi, &lo);
319 psenc->chlen += to_str(&psenc->ch[0], hi, UCS2_BIT);
320 psenc->chlen += to_str(&psenc->ch[6], lo, UCS2_BIT);
321 } else if ((ei->mode & MODE_C99) && (uint32_t)wc <= UCS4_MAX) {
324 psenc->chlen = to_str(&psenc->ch[0], wc, UCS4_BIT);
326 *nresult = (size_t)-1;
329 memcpy(s, psenc->ch, psenc->chlen);
330 *nresult = psenc->chlen;
336 *nresult = (size_t)-1;
342 _citrus_UES_stdenc_wctocs(_UESEncodingInfo * __restrict ei __unused,
343 _csid_t * __restrict csid, _index_t * __restrict idx, wchar_t wc)
354 _citrus_UES_stdenc_cstowc(_UESEncodingInfo * __restrict ei __unused,
355 wchar_t * __restrict wc, _csid_t csid, _index_t idx)
367 _citrus_UES_stdenc_get_state_desc_generic(_UESEncodingInfo * __restrict ei __unused,
368 _UESState * __restrict psenc, int * __restrict rstate)
371 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL :
372 _STDENC_SDGEN_INCOMPLETE_CHAR;
378 _citrus_UES_encoding_module_uninit(_UESEncodingInfo *ei __unused)
381 /* ei seems to be unused */
386 _citrus_UES_encoding_module_init(_UESEncodingInfo * __restrict ei,
387 const void * __restrict var, size_t lenvar)
392 memset((void *)ei, 0, sizeof(*ei));
394 switch (_bcs_toupper(*p)) {
396 MATCH(C99, ei->mode |= MODE_C99);
402 ei->mb_cur_max = (ei->mode & MODE_C99) ? 10 : 12;
407 /* ----------------------------------------------------------------------
408 * public interface for stdenc
411 _CITRUS_STDENC_DECLS(UES);
412 _CITRUS_STDENC_DEF_OPS(UES);
414 #include "citrus_stdenc_template.h"