aboutsummaryrefslogtreecommitdiffstats
path: root/camel/camel-charset-map.c
blob: 5fcd490dded7cd5caa881476bf2217fe5371eb37 (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
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8; -*- */

/* 
 * Authors:
 *   Michael Zucchi <notzed@ximian.com>
 *   Jeffrey Stedfast <fejj@ximian.com>
 *   Dan Winship <danw@ximian.com>
 *
 * Copyright 2000, 2003 Ximian, Inc. (www.ximian.com)
 *
 * This program is free software; you can redistribute it and/or 
 * modify it under the terms of version 2 of the GNU 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 General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
 * USA
 */


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

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>

/*
  if you want to build the charset map, compile this with something like:
    gcc -DBUILD_MAP camel-charset-map.c `glib-config --cflags`
  (plus any -I/-L/-l flags you need for iconv), then run it as 
    ./a.out > camel-charset-map-private.h

  Note that the big-endian variant isn't tested...

  The tables genereated work like this:

   An indirect array for each page of unicode character
   Each array element has an indirect pointer to one of the bytes of
   the generated bitmask.
*/

#ifdef BUILD_MAP
#include <iconv.h>
#include <glib.h>

static struct {
    char *name;
    unsigned int bit;   /* assigned bit */
} tables[] = {
    /* These are the 8bit character sets (other than iso-8859-1,
     * which is special-cased) which are supported by both other
     * mailers and the GNOME environment. Note that the order
     * they're listed in is the order they'll be tried in, so put
     * the more-popular ones first.
     */
    { "iso-8859-2", 0 },    /* Central/Eastern European */
    { "iso-8859-4", 0 },    /* Baltic */
    { "koi8-r", 0 },    /* Russian */
    { "koi8-u", 0 },    /* Ukranian */
    { "iso-8859-5", 0 },    /* Least-popular Russian encoding */
    { "iso-8859-7", 0 },    /* Greek */
    { "iso-8859-8", 0 },    /* Hebrew; Visual */
    { "iso-8859-9", 0 },    /* Turkish */
    { "iso-8859-13", 0 },   /* Baltic again */
    { "iso-8859-15", 0 },   /* New-and-improved iso-8859-1, but most
                 * programs that support this support UTF8
                 */
    { "windows-1251", 0 },  /* Russian */
    { 0, 0 }
};

unsigned int encoding_map[256 * 256];

#if G_BYTE_ORDER == G_BIG_ENDIAN
#define UCS "UCS-4BE"
#else
#define UCS "UCS-4LE"
#endif

int main (void)
{
    int i, j;
    int max, min;
    int bit = 0x01;
    int k;
    int bytes;
    iconv_t cd;
    char in[128];
    guint32 out[128];
    char *inptr, *outptr;
    size_t inlen, outlen;

    /* dont count the terminator */
    bytes = ((sizeof(tables)/sizeof(tables[0]))+7-1)/8;

    for (i = 0; i < 128; i++)
        in[i] = i + 128;

    for (j = 0; tables[j].name; j++) {
        cd = iconv_open (UCS, tables[j].name);
        inptr = in;
        outptr = (char *)(out);
        inlen = sizeof (in);
        outlen = sizeof (out);
        while (iconv (cd, &inptr, &inlen, &outptr, &outlen) == -1) {
            if (errno == EILSEQ) {
                inptr++;
                inlen--;
            } else {
                printf ("%s\n", strerror (errno));
                exit (1);
            }
        }
        iconv_close (cd);

        for (i = 0; i < 128 - outlen / 4; i++) {
            encoding_map[i] |= bit;
            encoding_map[out[i]] |= bit;
        }

        tables[j].bit = bit;
        bit <<= 1;
    }

    printf("/* This file is automatically generated: DO NOT EDIT */\n\n");

    for (i=0;i<256;i++) {
        /* first, do we need this block? */
        for (k=0;k<bytes;k++) {
            for (j=0;j<256;j++) {
                if ((encoding_map[i*256 + j] & (0xff << (k*8))) != 0)
                    break;
            }
            if (j < 256) {
                /* yes, dump it */
                printf("static unsigned char m%02x%x[256] = {\n\t", i, k);
                for (j=0;j<256;j++) {
                    printf("0x%02x, ", (encoding_map[i*256+j] >> (k*8)) & 0xff );
                    if (((j+1)&7) == 0 && j<255)
                        printf("\n\t");
                }
                printf("\n};\n\n");
            }
        }
    }

    printf("struct {\n");
    for (k=0;k<bytes;k++) {
        printf("\tunsigned char *bits%d;\n", k);
    }
    printf("} camel_charmap[256] = {\n\t");
    for (i=0;i<256;i++) {
        /* first, do we need this block? */
        printf("{ ");
        for (k=0;k<bytes;k++) {
            for (j=0;j<256;j++) {
                if ((encoding_map[i*256 + j] & (0xff << (k*8))) != 0)
                    break;
            }
            if (j < 256) {
                printf("m%02x%x, ", i, k);
            } else {
                printf("0, ");
            }
        }
        printf("}, ");
        if (((i+1)&7) == 0 && i<255)
            printf("\n\t");
    }
    printf("\n};\n\n");

    printf("struct {\n\tconst char *name;\n\tunsigned int bit;\n} camel_charinfo[] = {\n");
    for (j=0;tables[j].name;j++) {
        printf("\t{ \"%s\", 0x%04x },\n", tables[j].name, tables[j].bit);
    }
    printf("};\n\n");

    printf("#define charset_mask(x) \\\n");
    for (k=0;k<bytes;k++) {
        if (k!=0)
            printf("\t| ");
        else
            printf("\t");
        printf("(camel_charmap[(x)>>8].bits%d?camel_charmap[(x)>>8].bits%d[(x)&0xff]<<%d:0)", k, k, k*8);
        if (k<bytes-1)
            printf("\t\\\n");
    }
    printf("\n\n");
    
    return 0;
}

#else

#include "camel-charset-map.h"
#include "camel-charset-map-private.h"
#include "string-utils.h"

#include <glib.h>
#include <glib/gunicode.h>
#include <locale.h>
#include <ctype.h>
#ifdef ENABLE_THREADS
#include <pthread.h>
#endif
#ifdef HAVE_CODESET
#include <langinfo.h>
#endif

void
camel_charset_init (CamelCharset *c)
{
    c->mask = ~0;
    c->level = 0;
}

void
camel_charset_step (CamelCharset *c, const char *in, int len)
{
    register unsigned int mask;
    register int level;
    const char *inptr = in, *inend = in+len;

    mask = c->mask;
    level = c->level;

    /* check what charset a given string will fit in */
    while (inptr < inend) {
        gunichar c;
        const char *newinptr;
        newinptr = g_utf8_next_char(inptr);
        c = g_utf8_get_char(inptr);
        if (newinptr == NULL || !g_unichar_validate (c)) {
            inptr++;
            continue;
        }

        inptr = newinptr;
        if (c<=0xffff) {
            mask &= charset_mask(c);
        
            if (c>=128 && c<256)
                level = MAX(level, 1);
            else if (c>=256)
                level = MAX(level, 2);
        } else {
            mask = 0;
            level = MAX(level, 2);
        }
    }

    c->mask = mask;
    c->level = level;
}

/* gets the best charset from the mask of chars in it */
static const char *
camel_charset_best_mask(unsigned int mask)
{
    int i;

    for (i=0;i<sizeof(camel_charinfo)/sizeof(camel_charinfo[0]);i++) {
        if (camel_charinfo[i].bit & mask)
            return camel_charinfo[i].name;
    }
    return "UTF-8";
}

const char *
camel_charset_best_name (CamelCharset *charset)
{
    if (charset->level == 1)
        return "ISO-8859-1";
    else if (charset->level == 2)
        return camel_charset_best_mask (charset->mask);
    else
        return NULL;

}

/* finds the minimum charset for this string NULL means US-ASCII */
const char *
camel_charset_best (const char *in, int len)
{
    CamelCharset charset;

    camel_charset_init (&charset);
    camel_charset_step (&charset, in, len);
    return camel_charset_best_name (&charset);
}


#ifdef G_THREADS_ENABLED
static GStaticMutex lock = G_STATIC_MUTEX_INIT;
#define LOCK() g_static_mutex_lock(&lock)
#define UNLOCK() g_static_mutex_unlock(&lock)
#else
#define LOCK()
#define UNLOCK()
#endif

static char *locale_charset = NULL;
static GHashTable *canon_charsets = NULL;

static void
canon_charsets_init (int keep)
{
    char *locale;
    
    LOCK ();
    
    if (canon_charsets != NULL) {
        if (!keep)
            UNLOCK ();
        return;
    }
    
    canon_charsets = g_hash_table_new (g_str_hash, g_str_equal);
    
    locale = setlocale (LC_ALL, NULL);
    
    if (!locale || !strcmp (locale, "C") || !strcmp (locale, "POSIX")) {
        /* The locale "C"  or  "POSIX"  is  a  portable  locale;  its
         * LC_CTYPE  part  corresponds  to  the 7-bit ASCII character
         * set.
         */
        
        locale_charset = NULL;
    } else {
#ifdef HAVE_CODESET
        locale_charset = g_strdup (nl_langinfo (CODESET));
        g_ascii_strdown (locale_charset, -1);
#else
        /* A locale name is typically of  the  form  language[_terri-
         * tory][.codeset][@modifier],  where  language is an ISO 639
         * language code, territory is an ISO 3166 country code,  and
         * codeset  is  a  character  set or encoding identifier like
         * ISO-8859-1 or UTF-8.
         */
        char *codeset, *p;
        
        codeset = strchr (locale, '.');
        if (codeset) {
            codeset++;
            
            /* ; is a hack for debian systems and / is a hack for Solaris systems */
            for (p = codeset; *p && !strchr ("@;/", *p); p++)
                ;
            locale_charset = g_strndup (codeset, p - codeset);
            g_ascii_strdown (locale_charset, -1);
        } else {
            /* charset unknown */
            locale_charset = NULL;
        }
#endif
    }
    
    if (!keep)
        UNLOCK ();
}


/**
 * camel_charset_locale_name:
 *
 * Returns the name of the system's locale charset.
 **/
const char *
camel_charset_locale_name (void)
{
    canon_charsets_init (FALSE);
    
    return locale_charset;
}


/**
 * camel_charset_canonical_name:
 * @charset: charset to canonicalise
 *
 * Returns the charset in its canonical format. This is currently only
 * needed for iso charsets but also handles canonicalisation of
 * windows charsets. May need to expand this to handle canincalisation
 * of more charsets in the future?
 **/
const char *
camel_charset_canonical_name (const char *charset)
{
    char *name, *canon, *tmp;
    
    if (charset == NULL)
        return NULL;
    
    name = g_alloca (strlen (charset));
    strcpy (name, charset);
    g_ascii_strdown (name, -1);
    
    canon_charsets_init (TRUE);
    canon = g_hash_table_lookup (canon_charsets, name);
    if (canon != NULL) {
        UNLOCK ();
        return canon;
    }
    
    /* Unknown, try canonicalise some basic charset types to something that should work */
    if (strncmp (name, "iso", 3) == 0) {
        /* Convert iso-nnnn-n or isonnnn-n or iso_nnnn-n to iso-nnnn-n or isonnnn-n */
        int iso, codepage;
        char *p;
        
        tmp = name + 3;
        if (*tmp == '-' || *tmp == '_')
            tmp++;
        
        iso = strtoul (tmp, &p, 10);
        
        if (iso == 10646) {
            /* they all become iso-10646 */
            canon = g_strdup ("iso-10646");
        } else {
            /* iso-8859-# */
            tmp = p;
            if (*tmp == '-' || *tmp == '_')
                tmp++;
            
            codepage = strtoul (tmp, &p, 10);
            
            if (p > tmp) {
                /* codepage is numeric */
                canon = g_strdup_printf ("iso-%d-%d", iso, codepage);
            } else {
                /* codepage is a string - probably iso-2022-jp or something */
                canon = g_strdup_printf ("iso-%d-%s", iso, p);
            }
        }
    } else if (strncmp (name, "windows-", 8) == 0) {
        /* Convert windows-#### and windows-cp#### to windows-cp#### */
        tmp = name + 8;
        if (!strncmp (tmp, "cp", 2))
            tmp += 2;
        canon = g_strdup_printf ("windows-cp%s", tmp);
    } else if (strncmp (name, "microsoft-", 10) == 0) {
        /* Convert microsoft-#### or microsoft-cp#### to windows-cp#### */
        tmp = name + 10;
        if (!strncmp (tmp, "cp", 2))
            tmp += 2;
        canon = g_strdup_printf ("windows-cp%s", tmp);  
    } else if (strncmp (name, "cp125", 5) == 0) {
        /* Convert cp125# to windows-cp#### */
        canon = g_strdup_printf ("windows-%s", name);
    } else {
        /* Just assume its ok enough as is, case and all */
        canon = g_strdup (charset);
    }
    
    g_hash_table_insert (canon_charsets, g_strdup (name), canon);
    UNLOCK ();
    
    return canon;
}


/**
 * camel_charset_iso_to_windows:
 * @isocharset: a canonicalised ISO charset
 *
 * Returns the equivalent Windows charset.
 **/
const char *
camel_charset_iso_to_windows (const char *isocharset)
{
    /* According to http://czyborra.com/charsets/codepages.html,
     * the charset mapping is as follows:
     *
     * us-ascii    maps to windows-cp1252
     * iso-8859-1  maps to windows-cp1252
     * iso-8859-2  maps to windows-cp1250
     * iso-8859-3  maps to windows-cp????
     * iso-8859-4  maps to windows-cp????
     * iso-8859-5  maps to windows-cp1251
     * iso-8859-6  maps to windows-cp1256
     * iso-8859-7  maps to windows-cp1253
     * iso-8859-8  maps to windows-cp1255
     * iso-8859-9  maps to windows-cp1254
     * iso-8859-10 maps to windows-cp????
     * iso-8859-11 maps to windows-cp????
     * iso-8859-12 maps to windows-cp????
     * iso-8859-13 maps to windows-cp1257
     *
     * Assumptions:
     *  - I'm going to assume that since iso-8859-4 and
     *    iso-8859-13 are Baltic that it also maps to
     *    windows-cp1257.
     */
    
    if (!strcasecmp (isocharset, "iso-8859-1") || !strcasecmp (isocharset, "us-ascii"))
        return "windows-cp1252";
    else if (!strcasecmp (isocharset, "iso-8859-2"))
        return "windows-cp1250";
    else if (!strcasecmp (isocharset, "iso-8859-4"))
        return "windows-cp1257";
    else if (!strcasecmp (isocharset, "iso-8859-5"))
        return "windows-cp1251";
    else if (!strcasecmp (isocharset, "iso-8859-6"))
        return "windows-cp1256";
    else if (!strcasecmp (isocharset, "iso-8859-7"))
        return "windows-cp1253";
    else if (!strcasecmp (isocharset, "iso-8859-8"))
        return "windows-cp1255";
    else if (!strcasecmp (isocharset, "iso-8859-9"))
        return "windows-cp1254";
    else if (!strcasecmp (isocharset, "iso-8859-13"))
        return "windows-cp1257";
    
    return isocharset;
}

#endif /* !BUILD_MAP */