gettext_iconv.c revision 1.6 
1/*	$NetBSD: gettext_iconv.c,v 1.6 2004/08/02 03:15:33 yamt Exp $	*/
2
3/*-
4 * Copyright (c) 2004 Citrus Project,
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 *    notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 *    notice, this list of conditions and the following disclaimer in the
14 *    documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 *
28 * $Citrus$
29 */
30
31
32#include <sys/types.h>
33#include <sys/param.h>
34
35#include <errno.h>
36#include <iconv.h>
37#include <libintl.h>
38#include <langinfo.h>
39#include <search.h>
40#include <stdlib.h>
41#include <string.h>
42
43#include "libintl_local.h"
44
45struct cache {
46	const char *c_origmsg;
47	const char *c_resultmsg;
48};
49
50static const struct cache *cache_find(const char *, struct domainbinding *);
51static int cache_enter(const char *, const char *);
52static int cache_cmp(const void *, const void *);
53
54static void *cacheroot;
55
56/* ARGSUSED1 */
57static const struct cache *
58cache_find(const char *msg, struct domainbinding *db)
59{
60	struct cache key;
61	struct cache **c;
62
63	key.c_origmsg = msg;
64	c = tfind(&key, &cacheroot, cache_cmp);
65
66	return c ? *c : NULL;
67}
68
69static int
70cache_enter(const char *origmsg, const char *resultmsg)
71{
72	struct cache *c;
73
74	c = malloc(sizeof(*c));
75	if (c == NULL)
76		return -1;
77
78	c->c_origmsg = origmsg;
79	c->c_resultmsg = resultmsg;
80
81	if (tsearch(c, &cacheroot, cache_cmp) == NULL) {
82		free(c);
83		return -1;
84	}
85
86	return 0;
87}
88
89static int
90cache_cmp(const void *va, const void *vb)
91{
92	const struct cache *a = va;
93	const struct cache *b = vb;
94	int result;
95
96	result = a->c_origmsg - b->c_origmsg;
97
98	return result;
99}
100
101#define	GETTEXT_ICONV_MALLOC_CHUNK	(16 * 1024)
102
103const char *
104__gettext_iconv(const char *origmsg, struct domainbinding *db)
105{
106	const char *tocode;
107	const char *fromcode = db->mohandle.mo.mo_charset;
108	const struct cache *cache;
109	const char *result;
110	iconv_t cd;
111	const char *src;
112	char *dst;
113	size_t origlen;
114	size_t srclen;
115	size_t dstlen;
116	size_t nvalid;
117	int savederrno = errno;
118
119	/*
120	 * static buffer for converted texts.
121	 *
122	 * note:
123	 * we never free buffers once returned to callers.
124	 * because of interface design of gettext, we can't know
125	 * the lifetime of them.
126	 */
127	static char *buffer;
128	static size_t bufferlen;
129
130	/*
131	 * don't convert message if *.mo doesn't specify codeset.
132	 */
133	if (fromcode == NULL)
134		return origmsg;
135
136	tocode = db->codeset;
137	if (tocode == NULL) {
138		/*
139		 * codeset isn't specified explicitly by
140		 * bind_textdomain_codeset().
141		 * use current locale(LC_CTYPE)'s codeset.
142		 *
143		 * XXX maybe wrong; it can mismatch with
144		 * environment variable setting.
145		 */
146		tocode = nl_langinfo(CODESET);
147	}
148
149	/*
150	 * shortcut if possible.
151	 * XXX should handle aliases
152	 */
153	if (!strcasecmp(tocode, fromcode))
154		return origmsg;
155
156	/* XXX LOCK */
157
158	/* XXX should detect change of tocode and purge caches? */
159
160	/*
161	 * see if we have already converted this message.
162	 */
163	cache = cache_find(origmsg, db);
164	if (cache) {
165		result = cache->c_resultmsg;
166		goto out;
167	}
168
169	origlen = strlen(origmsg) + 1;
170again:
171	cd = iconv_open(tocode, fromcode);
172	if (cd == (iconv_t)-1) {
173		result = origmsg;
174		goto out;
175	}
176
177	src = origmsg;
178	srclen = origlen;
179	dst = buffer;
180	dstlen = bufferlen;
181	nvalid = iconv(cd, (char **)&src, &srclen, &dst, &dstlen);
182	iconv_close(cd);
183
184	if (nvalid == (size_t)-1) {
185		/*
186		 * try to allocate a new buffer.
187		 *
188		 * just give up if GETTEXT_ICONV_MALLOC_CHUNK was not enough.
189		 */
190		if (errno == E2BIG &&
191		    bufferlen != GETTEXT_ICONV_MALLOC_CHUNK) {
192			buffer = malloc(GETTEXT_ICONV_MALLOC_CHUNK);
193			if (buffer) {
194				bufferlen = GETTEXT_ICONV_MALLOC_CHUNK;
195				goto again;
196			}
197		}
198
199		result = origmsg;
200	} else if (cache_enter(origmsg, buffer)) {
201		/*
202		 * failed to enter cache.  give up.
203		 */
204		result = origmsg;
205	} else {
206		size_t resultlen = dst - buffer;
207
208		result = buffer;
209		bufferlen -= resultlen;
210		buffer += resultlen;
211	}
212
213out:
214	/* XXX UNLOCK */
215	errno = savederrno;
216
217	return result;
218}
219