aboutsummaryrefslogtreecommitdiffstats
path: root/e-util/e-unicode.c
blob: a0d59509f87a98f4da1235d3574bcec77d8e0f58 (plain) (blame)
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
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
/*
 * e-unicode.c - utf-8 support functions for gal
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU Lesser General Public License as published by
 * the Free Software Foundation.
 *
 * 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 Lesser General Public License
 * along with this program; if not, see <http://www.gnu.org/licenses/>.
 *
 *
 * Authors:
 *      Lauris Kaplinski <lauris@ximian.com>
 *
 * Copyright (C) 1999-2008 Novell, Inc. (www.novell.com)
 *
 */

#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#include <iconv.h>

#include <gdk/gdkkeysyms.h>
#include <gtk/gtk.h>
#include <libxml/xmlmemory.h>

#include <camel/camel.h>

#include <glib/gi18n.h>
#include "e-unicode.h"

#define d(x)

#define FONT_TESTING
#define MAX_DECOMP 8

/* FIXME: this has not been ported fully yet - non ASCII people beware. */

gchar *
e_utf8_from_gtk_event_key (GtkWidget *widget,
                           guint keyval,
                           const gchar *string)
{
    gint unival;
    gchar *utf;
    gint unilen;

    if (keyval == GDK_KEY_VoidSymbol) {
        utf = e_utf8_from_locale_string_sized (string, strlen (string));
    } else {
        unival = gdk_keyval_to_unicode (keyval);

        if (unival < ' ') return NULL;

        utf = g_new (gchar, 7);

        unilen = e_unichar_to_utf8 (unival, utf);

        utf[unilen] = '\0';
    }

    return utf;
}

gchar *
e_utf8_from_iconv_string_sized (iconv_t ic,
                                const gchar *string,
                                gint bytes)
{
    gchar *new, *ob;
    const gchar *ib;
    gsize ibl, obl;

    if (!string) return NULL;

    if (ic == (iconv_t) -1) {
        gint i;
        /* iso-8859-1 */
        ib = (gchar *) string;
        new = ob = (gchar *) g_new (guchar, bytes * 2 + 1);
        for (i = 0; i < (bytes); i++) {
            ob += e_unichar_to_utf8 (ib[i], ob);
        }
        *ob = '\0';
        return new;
    }

    ib = string;
    ibl = bytes;
    new = ob = g_new (gchar, ibl * 6 + 1);
    obl = ibl * 6;

    while (ibl > 0) {
        camel_iconv (ic, &ib, &ibl, &ob, &obl);
        if (ibl > 0) {
            gint len;
            if ((*ib & 0x80) == 0x00) len = 1;
            else if ((*ib &0xe0) == 0xc0) len = 2;
            else if ((*ib &0xf0) == 0xe0) len = 3;
            else if ((*ib &0xf8) == 0xf0) len = 4;
            else {
                g_warning ("Invalid UTF-8 sequence");
                break;
            }
            ib += len;
            ibl = bytes - (ib - string);
            if (ibl > bytes) ibl = 0;
            *ob++ = '_';
            obl--;
        }
    }

    *ob = '\0';

    return new;
}

gchar *
e_utf8_to_iconv_string_sized (iconv_t ic,
                              const gchar *string,
                              gint bytes)
{
    gchar *new, *ob;
    const gchar *ib;
    gsize ibl, obl;

    if (!string) return NULL;

    if (ic == (iconv_t) -1) {
        gint len;
        const gchar *u;
        gunichar uc;

        new = (gchar *) g_new (guchar, bytes * 4 + 1);
        u = string;
        len = 0;

        while ((u) && (u - string < bytes)) {
            u = e_unicode_get_utf8 (u, &uc);
            new[len++] = uc & 0xff;
        }
        new[len] = '\0';
        return new;
    }

    ib = string;
    ibl = bytes;
    new = ob = g_new (char, ibl * 4 + 4);
    obl = ibl * 4;

    while (ibl > 0) {
        camel_iconv (ic, &ib, &ibl, &ob, &obl);
        if (ibl > 0) {
            gint len;
            if ((*ib & 0x80) == 0x00) len = 1;
            else if ((*ib &0xe0) == 0xc0) len = 2;
            else if ((*ib &0xf0) == 0xe0) len = 3;
            else if ((*ib &0xf8) == 0xf0) len = 4;
            else {
                g_warning ("Invalid UTF-8 sequence");
                break;
            }
            ib += len;
            ibl = bytes - (ib - string);
            if (ibl > bytes) ibl = 0;

            /* FIXME This is wrong.  What if the destination
             *       charset is 16 or 32 bit? */
            *ob++ = '_';
            obl--;
        }
    }

    /* Make sure to terminate with plenty of padding */
    memset (ob, 0, 4);

    return new;
}

gchar *
e_utf8_to_charset_string_sized (const gchar *charset,
                                const gchar *string,
                                gint bytes)
{
    iconv_t ic;
    gchar *ret;

    if (!string) return NULL;

    ic = camel_iconv_open (charset, "utf-8");
    ret = e_utf8_to_iconv_string_sized (ic, string, bytes);
    camel_iconv_close (ic);

    return ret;
}

gchar *
e_utf8_from_locale_string_sized (const gchar *string,
                                 gint bytes)
{
    iconv_t ic;
    gchar *ret;

    if (!string) return NULL;

    ic = camel_iconv_open ("utf-8", camel_iconv_locale_charset ());
    ret = e_utf8_from_iconv_string_sized (ic, string, bytes);
    camel_iconv_close (ic);

    return ret;
}

/**
 * e_utf8_ensure_valid:
 * @string: string to make valid UTF-8
 *
 * Ensures the returned string will be valid UTF-8 string, thus GTK+
 * functions expecting only valid UTF-8 text will not crash.
 *
 * Returned pointer should be freed with g_free().
 *
 * Returns: a newly-allocated UTF-8 string
 **/
gchar *
e_utf8_ensure_valid (const gchar *string)
{
    gchar *res = g_strdup (string), *p;

    if (!res)
        return res;

    p = res;
    while (!g_utf8_validate (p, -1, (const gchar **) &p)) {
        /* make all invalid characters appear as question marks */
        *p = '?';
    }

    return res;
}

/**
 * e_unichar_to_utf8:
 * @c: a ISO10646 character code
 * @outbuf: output buffer, must have at least 6 bytes of space.
 *          If %NULL, the length will be computed and returned
 *          and nothing will be written to @out.
 *
 * Convert a single character to utf8
 *
 * Return value: number of bytes written
 **/

gint
e_unichar_to_utf8 (gint c,
                   gchar *outbuf)
{
  gsize len = 0;
  gint first;
  gint i;

  if (c < 0x80)
    {
      first = 0;
      len = 1;
    }
  else if (c < 0x800)
    {
      first = 0xc0;
      len = 2;
    }
  else if (c < 0x10000)
    {
      first = 0xe0;
      len = 3;
    }
   else if (c < 0x200000)
    {
      first = 0xf0;
      len = 4;
    }
  else if (c < 0x4000000)
    {
      first = 0xf8;
      len = 5;
    }
  else
    {
      first = 0xfc;
      len = 6;
    }

  if (outbuf)
    {
      for (i = len - 1; i > 0; --i)
    {
      outbuf[i] = (c & 0x3f) | 0x80;
      c >>= 6;
    }
      outbuf[0] = c | first;
    }

  return len;
}

gchar *
e_unicode_get_utf8 (const gchar *text,
                    gunichar *out)
{
    *out = g_utf8_get_char (text);
    return (*out == (gunichar) - 1) ? NULL : g_utf8_next_char (text);
}

gchar *
e_xml_get_translated_utf8_string_prop_by_name (const xmlNode *parent,
                                               const xmlChar *prop_name)
{
    xmlChar *prop;
    gchar *ret_val = NULL;
    gchar *combined_name;

    g_return_val_if_fail (parent != NULL, NULL);
    g_return_val_if_fail (prop_name != NULL, NULL);

    prop = xmlGetProp ((xmlNode *) parent, prop_name);
    if (prop != NULL) {
        ret_val = g_strdup ((gchar *) prop);
        xmlFree (prop);
        return ret_val;
    }

    combined_name = g_strdup_printf ("_%s", prop_name);
    prop = xmlGetProp ((xmlNode *) parent, (guchar *) combined_name);
    if (prop != NULL) {
        ret_val = g_strdup (gettext ((gchar *) prop));
        xmlFree (prop);
    }
    g_free (combined_name);

    return ret_val;
}