summaryrefslogtreecommitdiff
path: root/src/core/recode.c
blob: 029d7ff1f95a2bcef852bc4b78a13ea049b46bf1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
/*
 recode.c : irssi

    Copyright (C) 1999-2000 Timo Sirainen

    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    This program 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 General Public License for more details.

    You should have received a copy of the GNU General Public License along
    with this program; if not, write to the Free Software Foundation, Inc.,
    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/

#include "module.h"
#include "settings.h"
#include "servers.h"
#include "signals.h"
#include "lib-config/iconfig.h"
#include "misc.h"

static char *translit_charset;
static gboolean term_is_utf8;

gboolean is_utf8(void)
{
	return term_is_utf8;
}

static gboolean is_translit(const char *charset)
{
	char *pos;

	pos = stristr(charset, "//translit");
	return (pos != NULL);
}

gboolean is_valid_charset(const char *charset)
{
	GIConv cd;
	char *to = NULL;

	if (!charset || *charset == '\0')
		return FALSE;

	if (settings_get_bool("recode_transliterate") && !is_translit(charset))
		charset = to = g_strconcat(charset, "//TRANSLIT", NULL);

	cd = g_iconv_open(charset, "UTF-8");
	g_free(to);
	if (cd != (GIConv)-1) {
		g_iconv_close(cd);
		return TRUE;
	}
	return FALSE;
}

static char *find_conversion(const SERVER_REC *server, const char *target)
{
	char *conv = NULL;

	if (server != NULL && target != NULL) {
		char *tagtarget = g_strdup_printf("%s/%s", server->tag, target);
		conv = iconfig_get_str("conversions", tagtarget, NULL);
		g_free(tagtarget);
	}
	if (conv == NULL && target != NULL)
		conv = iconfig_get_str("conversions", target, NULL);
	if (conv == NULL && server != NULL)
		conv = iconfig_get_str("conversions", server->tag, NULL);
	return conv;
}

static int str_is_ascii(const char *str)
{
	int i;

	for (i = 0; str[i] != '\0'; i++)
		if (str[i] & 0x80)
			return 0;
	return 1;
}

char *recode_in(const SERVER_REC *server, const char *str, const char *target)
{
	const char *from = NULL;
	const char *to = translit_charset;
	char *recoded = NULL;
	gboolean str_is_utf8, recode, autodetect;
	int len;

	if (!str)
		return NULL;

	recode = settings_get_bool("recode");
	if (!recode)
		return g_strdup(str);

	len = strlen(str);

	/* Only validate for UTF-8 if an 8-bit encoding. */
	str_is_utf8 = 0;
	if (!str_is_ascii(str))
		str_is_utf8 = g_utf8_validate(str, len, NULL);
	else if (!strchr(str, '\e'))
		str_is_utf8 = 1;
	autodetect = settings_get_bool("recode_autodetect_utf8");

	if (autodetect && str_is_utf8)
		if (term_is_utf8)
			return g_strdup(str);
		else
			from = "UTF-8";
	else
		from = find_conversion(server, target);

	if (from)
		recoded = g_convert_with_fallback(str, len, to, from, NULL, NULL, NULL, NULL);

	if (!recoded) {
		if (str_is_utf8)
			if (term_is_utf8)
				return g_strdup(str);
			else
				from = "UTF-8";
		else
			if (term_is_utf8)
				from = settings_get_str("recode_fallback");
			else
				from = NULL;

		if (from)
			recoded = g_convert_with_fallback(str, len, to, from, NULL, NULL, NULL, NULL);

		if (!recoded)
			recoded = g_strdup(str);
	}
	return recoded;
}

char *recode_out(const SERVER_REC *server, const char *str, const char *target)
{
	char *recoded = NULL;
	const char *from = translit_charset;
	const char *to = NULL;
	char *translit_to = NULL;
	gboolean translit, recode;
	int len;

	if (!str)
		return NULL;

	recode = settings_get_bool("recode");
	if (!recode)
		return g_strdup(str);

	len = strlen(str);

	translit = settings_get_bool("recode_transliterate");

	to = find_conversion(server, target);
	if (to == NULL)
		/* default outgoing charset if set */
		to = settings_get_str("recode_out_default_charset");

	if (to && *to != '\0') {
		if (translit && !is_translit(to))
			to = translit_to = g_strconcat(to ,"//TRANSLIT", NULL);

		recoded = g_convert(str, len, to, from, NULL, NULL, NULL);
	}
	g_free(translit_to);
	if (!recoded)
		recoded = g_strdup(str);

	return recoded;
}

char **recode_split(const SERVER_REC *server, const char *str,
		    const char *target, int len)
{
	GIConv cd = (GIConv)-1;
	const char *from = translit_charset;
	const char *to = translit_charset;
	char *translit_to = NULL;
	const char *inbuf = str;
	const char *previnbuf = inbuf;
	char *tmp = NULL;
	char *outbuf;
	gsize inbytesleft = strlen(inbuf);
	gsize outbytesleft = len;
	int n = 0;
	char **ret;

	g_return_val_if_fail(str != NULL, NULL);

	if (settings_get_bool("recode")) {
		to = find_conversion(server, target);
		if (to == NULL)
			/* default outgoing charset if set */
			to = settings_get_str("recode_out_default_charset");
		if (to != NULL && *to != '\0') {
			if (settings_get_bool("recode_transliterate") &&
			    !is_translit(to))
				to = translit_to = g_strconcat(to,
							       "//TRANSLIT",
							       NULL);
		} else {
			to = from;
		}
	}

	cd = g_iconv_open(to, from);
	if (cd == (GIConv)-1) {
		/* Fall back to splitting by byte. */
		ret = strsplit_len(str, len);
		goto out;
	}

	tmp = g_malloc(outbytesleft);
	outbuf = tmp;
	ret = g_new(char *, 1);
	while (g_iconv(cd, (char **)&inbuf, &inbytesleft, &outbuf,
		       &outbytesleft) == -1) {
		if (errno != E2BIG) {
			/*
			 * Conversion failed. Fall back to splitting
			 * by byte.
			 */
			ret[n] = NULL;
			g_strfreev(ret);
			ret = strsplit_len(str, len);
			goto out;
		}

		/* Outbuf overflowed, split the input string. */
		ret[n++] = g_strndup(previnbuf, inbuf - previnbuf);
		ret = g_renew(char *, ret, n + 1);
		previnbuf = inbuf;

		/* Reset outbuf for the next substring. */
		outbuf = tmp;
		outbytesleft = len;
	}
	/* Copy the last substring into the array. */
	ret[n++] = g_strndup(previnbuf, inbuf - previnbuf);
	ret = g_renew(char *, ret, n + 1);
	ret[n] = NULL;

out:
	if (cd != (GIConv)-1)
		g_iconv_close(cd);
	g_free(translit_to);
	g_free(tmp);

	return ret;
}

void recode_update_charset(void)
{
	const char *charset = settings_get_str("term_charset");
	term_is_utf8 = !g_ascii_strcasecmp(charset, "UTF-8");
	g_free(translit_charset);
	if (settings_get_bool("recode_transliterate") && !is_translit(charset))
		translit_charset = g_strconcat(charset, "//TRANSLIT", NULL);
	else
		translit_charset = g_strdup(charset);
}

void recode_init(void)
{
	settings_add_bool("misc", "recode", TRUE);
	settings_add_str("misc", "recode_fallback", "CP1252");
	settings_add_str("misc", "recode_out_default_charset", "");
	settings_add_bool("misc", "recode_transliterate", TRUE);
	settings_add_bool("misc", "recode_autodetect_utf8", TRUE);
}

void recode_deinit(void)
{
	g_free(translit_charset);
}