aboutsummaryrefslogtreecommitdiffstats
path: root/camel/gmime-rfc2047.c
blob: 72f376d00cc33e4c932ba1a23017742eab34b7b0 (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
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/* gmime-rfc2047.c: implemention of RFC2047 */

/*
 * Copyright (C) 1999 Bertrand Guiheneuf <Bertrand.Guiheneuf@inria.fr> .
 * 
 * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307
 * USA
 *
 */

/* 
 * Authors:  Robert Brady <rwb197@ecs.soton.ac.uk>
 */

#include <stdio.h>
#include <ctype.h>
#include <unicode.h>
#include <string.h>

#include "gmime-rfc2047.h"

#define NOT_RANKED -1

/* This should be changed ASAP to use the base64 code Miguel comitted */

const char *base64_alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

static unsigned char base64_rank[256];
static int base64_rank_table_built;
static void build_base64_rank_table (void);

static int 
hexval (gchar c) {
    if (isdigit (c)) return c-'0';
    c = tolower (c);
    return c - 'a' + 10;
}

static gchar *
decode_quoted (const gchar *text, const gchar *end) 
{
    gchar *to = malloc(end - text + 1), *to_2 = to;

        if (!to) return NULL;
    while (*text && text < end) {
        if (*text == '=') {
            gchar a = hexval (text[1]);
            gchar b = hexval (text[2]);
            int c = (a << 4) + b;
            *to = c;
            to++;
            text+=3;
        } else if (*text == '_') {
            *to = ' ';
            to++;
            text++;
        } else {
            *to = *text;
            to++;
            text++;
        }
    }
    return to_2;
}

static gchar *
decode_base64 (const gchar *data, const gchar *end) 
{
    unsigned short pattern = 0;
    int bits = 0;
    int delimiter = '=';
    gchar x;
    gchar *buffer = g_malloc((end - data) * 3);
    gchar *t = buffer;
    int Q = 0;

    if (!buffer) return NULL;

    while (*data != delimiter) {
        x = base64_rank[(unsigned char)(*data++)];
        if (x == NOT_RANKED)
            continue;
        pattern <<= 6;
        pattern |= x;
        bits += 6;
        if (bits >= 8) {
            x = (pattern >> (bits - 8)) & 0xff;
            *t++ = x;
            Q++;
            bits -= 8;
        }
    }
    *t = 0;
    return buffer;
}

static void
build_base64_rank_table (void)
{
    int i;
    
    if (!base64_rank_table_built) {
        for (i = 0; i < 256; i++)
            base64_rank[i] = NOT_RANKED;
        for (i = 0; i < 64; i++)
            base64_rank[(int) base64_alphabet[i]] = i;
        base64_rank_table_built = 1;
    }
}


gchar *
rfc2047_decode_word (const gchar *data, const gchar *into_what) 
{
    const char *charset = strstr (data, "=?"), *encoding, *text, *end;

    char *buffer, *b, *cooked_data;
    
    buffer = g_malloc (strlen(data) * 2);
    b = buffer;

    if (!charset) return strdup (data);
    charset+=2;

    encoding = strchr (charset, '?');
    if (!encoding) return strdup (data);
    encoding++;

    text = strchr(encoding, '?');
    if (!text) return strdup (data);
    text++;

    end = strstr(text, "?=");
    if (!end) return strdup (data);

    b[0] = 0;

    if (toupper(*encoding)=='Q')
        cooked_data = decode_quoted (text, end);
    else if (toupper (*encoding)=='B')
        cooked_data = decode_base64 (text, end);
    else
        return g_strdup(data);

    {
        char *c = strchr (charset, '?');
        char *q = g_malloc (c - charset + 1);
        char *cook_2 = cooked_data;
        int cook_len = strlen (cook_2);
        int b_len = 4096;
        iconv_t i;
        strncpy (q, charset, c - charset);
        q[c - charset] = 0;
        i = unicode_iconv_open (into_what, q);
        if (!i) {
            g_free (q);
            return g_strdup (buffer);
        }
        if (unicode_iconv (i, &cook_2, &cook_len, &b, &b_len)==-1)
            /* FIXME : use approximation code if we can't convert it properly. */
            ;
        unicode_iconv_close (i);
        *b = 0;
    }

    return g_strdup (buffer);
}

static const gchar *
find_end_of_encoded_word (const gchar *data) 
{
    /* We can't just search for ?=,
           because of the case :
           "=?charset?q?=ff?=" :( */
    if (!data) return NULL;
    data = strstr (data, "=?");
    if (!data) return NULL;
    data = strchr(data+2, '?');
    if (!data) return NULL;
    data = strchr (data+1, '?');
    if (!data) return NULL;
    data = strstr (data+1, "?=");
    if (!data) return NULL;
    return data + 2;
}

gchar *
gmime_rfc2047_decode (const gchar *data, const gchar *into_what) 
{
    char *buffer = malloc (strlen(data) * 4), *b = buffer;

    int was_encoded_word = 0;

    build_base64_rank_table ();

    while (data && *data) {
        char *word_start = strstr (data, "=?"), *decoded;
        if (!word_start) {
            strcpy (b, data);
            b[strlen (data)] = 0;
            return buffer;
        }
        if (word_start != data) {

            if (strspn (data, " \t\n\r") != (word_start - data)) {
                strncpy (b, data, word_start - data);
                b += word_start - data;
                *b = 0;
            }
        }
        decoded = rfc2047_decode_word (word_start, into_what);
        strcpy (b, decoded);
        b += strlen (decoded);
        *b = 0;
        g_free (decoded);

        data = find_end_of_encoded_word (data);
    }

    *b = 0;
    return buffer;
}

#define isnt_ascii(a) ((a) <= 0x1f || (a) >= 0x7f)

static int 
rfc2047_clean (const gchar *string) {
    if (strstr (string, "?=")) return 1;
    while (*string) {
        if (!isnt_ascii ((unsigned char)*string))
            return 0;
        string++;
    }
    return 1;
}

static gchar *
encode_word (const gchar *string, const gchar *said_charset) 
{
    if (rfc2047_clean(string)) 
        /* don't bother encoding it if it has no odd characters in it */
        return g_strdup (string);
    {
        char *temp = malloc (strlen(string) * 4 + 1), *t = temp;
        t += sprintf (t, "=?%s?q?", said_charset);
        while (*string) {
            if (*string == ' ')
                *(t++) = '_';
            else if ((*string <= 0x1f) || (*string >= 0x7f) || (*string == '=') || (*string == '?')) 
                t += sprintf (t, "=%2x", (unsigned char)*string);
            else
                *(t++) = *string;
                  
            string++;
        }
        t += sprintf (t, "?=");
        *t = 0;
            return temp;
    }
}

gchar *
gmime_rfc2047_encode (const gchar *string, const gchar *charset) 
{
    int temp_len = strlen (string)*4 + 1;
    char *temp = g_malloc (temp_len), *temp_2 = temp;
    int string_length = strlen (string);
    char *encoded = NULL;

    /* first, let us convert to UTF-8 */
    iconv_t i = unicode_iconv_open ("UTF-8", charset);
    unicode_iconv (i, &string, &string_length, &temp_2, &temp_len);
    unicode_iconv_close (i);
    
    /* null terminate it */
    *temp_2 = 0;

    /* now encode it as if it were a single word */
    encoded = encode_word (temp, "UTF-8");
    
    /*
      
      real algorithm :
      
      we need to 
      
      split it into words
      
      identify portions that have NOT to be encoded (i.e. <> and the comment starter/ender )
      
      identify the best character set for each word
      
      merge words which share a character set, allow jumping and merging with words which 
      would be ok to encode in non-US-ASCII.
      
      if we have to use 2 character sets, try and collapse them into one.
      
      (e.g. if one word contains letters in latin-1, and another letters in latin-2, use
      latin-2 for the first word as well if possible).
      
      finally :
      
      if utf-8 will still be used, use it for everything.
      
      and then, at last, generate the encoded text, using base64/quoted-printable for
      each word depending upon which is more efficient.
      
      TODO :
      create a priority list of encodings
      
      i.e.

            US-ASCII, ISO-8859-1, ISO-8859-2, ISO-8859-3, KOI8, 

          Should survey for most popular charsets :
          what do people usually use for the following scripts?

      * Chinese/Japanese/Korean
          * Greek
          * Cyrillic

          (any other scripts commonly used in mail/news?)

      This algorithm is probably far from optimal, but should be
      reasonably efficient for simple cases. (and almost free if
      the text is just in US-ASCII : like 99% of the text that will
      pass through it)
      
    */
    
        g_free(temp);
    
    return encoded;
}