aboutsummaryrefslogtreecommitdiffstats
path: root/camel/camel-search-private.c
blob: b769a03e337ff691cc00d5efad30542452cf776c (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
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/*
 *  Authors: Jeffrey Stedfast <fejj@ximian.com>
 *       Michael Zucchi <NotZed@Ximian.com>
 *
 *  Copyright 2000 Ximian, Inc. (www.ximian.com)
 *  Copyright 2001 Ximian Inc. (www.ximian.com)
 *
 *  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 Street #330, Boston, MA 02111-1307, USA.
 *
 */

/* (from glibc headers:
   POSIX says that <sys/types.h> must be included (by the caller) before <regex.h>.  */

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

#include <sys/types.h>
#include <regex.h>
#include <string.h>
#include <ctype.h>
#include <stdio.h>

#include "camel-exception.h"
#include "camel-mime-message.h"
#include "camel-multipart.h"
#include "camel-stream-mem.h"
#include "e-util/e-sexp.h"

#include "camel-search-private.h"

#include <gal/unicode/gunicode.h>

#define d(x)

/* builds the regex into pattern */
/* taken from camel-folder-search, with added isregex & exception parameter */
/* Basically, we build a new regex, either based on subset regex's, or substrings,
   that can be executed once over the whoel body, to match anything suitable.
   This is more efficient than multiple searches, and probably most (naive) strstr
   implementations, over long content.

   A small issue is that case-insenstivity wont work entirely correct for utf8 strings. */
int
camel_search_build_match_regex (regex_t *pattern, camel_search_flags_t type, int argc,
                struct _ESExpResult **argv, CamelException *ex)
{
    GString *match = g_string_new("");
    int c, i, count=0, err;
    char *word;
    int flags;
    
    /* build a regex pattern we can use to match the words, we OR them together */
    if (argc>1)
        g_string_append_c (match, '(');
    for (i = 0; i < argc; i++) {
        if (argv[i]->type == ESEXP_RES_STRING) {
            if (count > 0)
                g_string_append_c (match, '|');
            
            word = argv[i]->value.string;
            if (type & CAMEL_SEARCH_MATCH_REGEX) {
                /* no need to escape because this should already be a valid regex */
                g_string_append (match, word);
            } else {
                /* escape any special chars (not sure if this list is complete) */
                if (type & CAMEL_SEARCH_MATCH_START)
                    g_string_append_c (match, '^');
                while ((c = *word++)) {
                    if (strchr ("*\\.()[]^$+", c) != NULL) {
                        g_string_append_c (match, '\\');
                    }
                    g_string_append_c (match, c);
                }
                if (type & CAMEL_SEARCH_MATCH_END)
                    g_string_append_c (match, '^');
            }
            count++;
        } else {
            g_warning("Invalid type passed to body-contains match function");
        }
    }
    if (argc > 1)
        g_string_append_c (match, ')');
    flags = REG_EXTENDED|REG_NOSUB;
    if (type & CAMEL_SEARCH_MATCH_ICASE)
        flags |= REG_ICASE;
    err = regcomp (pattern, match->str, flags);
    if (err != 0) {
        /* regerror gets called twice to get the full error string 
           length to do proper posix error reporting */
        int len = regerror (err, pattern, 0, 0);
        char *buffer = g_malloc0 (len + 1);
        
        regerror (err, pattern, buffer, len);
        camel_exception_setv (ex, CAMEL_EXCEPTION_SYSTEM,
                      _("Regular expression compilation failed: %s: %s"),
                      match->str, buffer);
        
        regfree (pattern);
    }
    d(printf("Built regex: '%s'\n", match->str));
    g_string_free (match, TRUE);
    
    return err;
}

static unsigned char soundex_table[256] = {
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0, 49, 50, 51,  0, 49, 50,  0,  0, 50, 50, 52, 53, 53,  0,
     49, 50, 54, 50, 51,  0, 49,  0, 50,  0, 50,  0,  0,  0,  0,  0,
      0,  0, 49, 50, 51,  0, 49, 50,  0,  0, 50, 50, 52, 53, 53,  0,
     49, 50, 54, 50, 51,  0, 49,  0, 50,  0, 50,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
      0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
};

static void
soundexify (const gchar *sound, gchar code[5])
{
    guchar *c, last = '\0';
    gint n;
    
    for (c = (guchar *) sound; *c && !isalpha (*c); c++);
    code[0] = toupper (*c);
    memset (code + 1, '0', 3);
    for (n = 1; *c && n < 5; c++) {
        guchar ch = soundex_table[*c];
        
        if (ch && ch != last) {
            code[n++] = ch;
            last = ch;
        }
    }
    code[4] = '\0';
}

static gboolean
header_soundex (const char *header, const char *match)
{
    char mcode[5], hcode[5];
    const char *p;
    char c;
    GString *word;
    int truth = FALSE;
    
    soundexify (match, mcode);
    
    /* split the header into words, and soundexify and compare each one */
    /* FIXME: Should this convert to utf8, and split based on that, and what not?
       soundex only makes sense for us-ascii though ... */
    
    word = g_string_new("");
    p = header;
    do {
        c = *p++;
        if (c == 0 || isspace (c)) {
            if (word->len > 0) {
                soundexify (word->str, hcode);
                if (strcmp (hcode, mcode) == 0)
                    truth = TRUE;
            }
            g_string_truncate (word, 0);
        } else if (isalpha (c))
            g_string_append_c (word, c);
    } while (c && !truth);
    g_string_free (word, TRUE);
    
    return truth;
}

static gunichar
utf8_get (const char **inp)
{
    const unsigned char *p = *inp;
    gunichar c;
    
    g_return_val_if_fail (p != NULL, 0);
    
    c = g_utf8_get_char (p);
    *inp = g_unichar_validate (c) ? g_utf8_next_char (p) : NULL;
    
    return c;
}

static const char *
camel_ustrstrcase (const char *haystack, const char *needle)
{
    gunichar *nuni, *puni;
    gunichar u;
    const char *p;
    
    g_return_val_if_fail (haystack != NULL, NULL);
    g_return_val_if_fail (needle != NULL, NULL);
    
    if (strlen (needle) == 0)
        return haystack;
    if (strlen (haystack) == 0)
        return NULL;
    
    puni = nuni = alloca (sizeof (gunichar) * strlen (needle));
    
    p = needle;
    while ((u = utf8_get (&p)))
        *puni++ = g_unichar_tolower (u);
    
    /* NULL means there was illegal utf-8 sequence */
    if (!p)
        return NULL;
    
    p = haystack;
    while ((u = utf8_get (&p))) {
        gunichar c;
        
        c = g_unichar_tolower (u);
        /* We have valid stripped char */
        if (c == nuni[0]) {
            const gchar *q = p;
            gint npos = 1;
            
            while (nuni + npos < puni) {
                u = utf8_get (&q);
                if (!q || !u)
                    return NULL;
                
                c = g_unichar_tolower (u);              
                if (c != nuni[npos])
                    break;
                
                npos++;
            }
            
            if (nuni + npos == puni)
                return p;
        }
    }
    
    return NULL;
}

#define CAMEL_SEARCH_COMPARE(x, y, z) G_STMT_START {   \
    if ((x) == (z)) {                              \
        if ((y) == (z))                        \
            return 0;                      \
        else                                   \
            return -1;                     \
    } else if ((y) == (z))                         \
        return 1;                              \
} G_STMT_END

static int
camel_ustrcasecmp (const char *s1, const char *s2)
{
    gunichar u1, u2 = 0;
    
    CAMEL_SEARCH_COMPARE (s1, s2, NULL);
    
    u1 = utf8_get (&s1);
    u2 = utf8_get (&s2);
    while (u1 && u2) {
        u1 = g_unichar_tolower (u1);
        u2 = g_unichar_tolower (u2);
        if (u1 < u2)
            return -1;
        else if (u1 > u2)
            return 1;
        
        u1 = utf8_get (&s1);
        u2 = utf8_get (&s2);
    }
    
    /* end of one of the strings ? */
    CAMEL_SEARCH_COMPARE (u1, u2, 0);
    
    /* if we have invalid utf8 sequence ?  */
    CAMEL_SEARCH_COMPARE (s1, s2, NULL);
    
    return 0;
}

static int
camel_ustrncasecmp (const char *s1, const char *s2, size_t len)
{
    gunichar u1, u2 = 0;
    
    CAMEL_SEARCH_COMPARE (s1, s2, NULL);
    
    u1 = utf8_get (&s1);
    u2 = utf8_get (&s2);
    while (len > 0 && u1 && u2) {
        u1 = g_unichar_tolower (u1);
        u2 = g_unichar_tolower (u2);
        if (u1 < u2)
            return -1;
        else if (u1 > u2)
            return 1;
        
        len--;
        u1 = utf8_get (&s1);
        u2 = utf8_get (&s2);
    }
    
    if (len == 0)
        return 0;
    
    /* end of one of the strings ? */
    CAMEL_SEARCH_COMPARE (u1, u2, 0);
    
    /* if we have invalid utf8 sequence ?  */
    CAMEL_SEARCH_COMPARE (s1, s2, NULL);
    
    return 0;
}

/* value is the match value suitable for exact match if required */
static int
header_match(const char *value, const char *match, camel_search_match_t how)
{
    const char *p;
    int vlen, mlen;
    
    if (how == CAMEL_SEARCH_MATCH_SOUNDEX)
        return header_soundex (value, match);
    
    vlen = strlen(value);
    mlen = strlen(match);
    if (vlen < mlen)
        return FALSE;
    
    /* from dan the man, if we have mixed case, perform a case-sensitive match,
       otherwise not */
    p = match;
    while (*p) {
        if (isupper(*p)) {
            switch (how) {
            case CAMEL_SEARCH_MATCH_EXACT:
                return strcmp(value, match) == 0;
            case CAMEL_SEARCH_MATCH_CONTAINS:
                return strstr(value, match) != NULL;
            case CAMEL_SEARCH_MATCH_STARTS:
                return strncmp(value, match, mlen) == 0;
            case CAMEL_SEARCH_MATCH_ENDS:
                return strcmp(value + vlen - mlen, match) == 0;
            default:
                break;
            }
            return FALSE;
        }
        p++;
    }
    
    switch (how) {
    case CAMEL_SEARCH_MATCH_EXACT:
        return camel_ustrcasecmp(value, match) == 0;
    case CAMEL_SEARCH_MATCH_CONTAINS:
        return camel_ustrstrcase(value, match) != NULL;
    case CAMEL_SEARCH_MATCH_STARTS:
        return camel_ustrncasecmp(value, match, mlen) == 0;
    case CAMEL_SEARCH_MATCH_ENDS:
        return camel_ustrcasecmp(value + vlen - mlen, match) == 0;
    default:
        break;
    }
    
    return FALSE;
}

/* searhces for match inside value, if match is mixed case, hten use case-sensitive,
   else insensitive */
gboolean
camel_search_header_match (const char *value, const char *match, camel_search_match_t how, camel_search_t type)
{
    const char *name, *addr;
    int truth = FALSE;
    CamelInternetAddress *cia;
    char *v;

    while (*value && isspace (*value))
        value++;
    
    switch(type) {
    case CAMEL_SEARCH_TYPE_ENCODED:
        v = header_decode_string(value, camel_charset_locale_name());
        truth = header_match(v, match, how);
        g_free(v);
        break;
    case CAMEL_SEARCH_TYPE_ASIS:
        truth = header_match(value, match, how);
        break;
    case CAMEL_SEARCH_TYPE_ADDRESS_ENCODED:
    case CAMEL_SEARCH_TYPE_ADDRESS:
        /* possible simple case to save some work if we can */
        if (header_match(value, match, how))
            return TRUE;

        /* Now we decode any addresses, and try asis matches on name and address parts */
        cia = camel_internet_address_new();
        if (type == CAMEL_SEARCH_TYPE_ADDRESS_ENCODED)
            camel_address_decode((CamelAddress *)cia, value);
        else
            camel_address_unformat((CamelAddress *)cia, value);

        if (camel_address_length((CamelAddress *)cia) == 1) {
            camel_internet_address_get(cia, 0, &name, &addr);
            truth = header_match(name, match, how)
                || header_match(addr, match, how);
        }
        camel_object_unref((CamelObject *)cia);
        break;
    }

    return truth;
}

/* performs a 'slow' content-based match */
/* there is also an identical copy of this in camel-filter-search.c */
gboolean
camel_search_message_body_contains (CamelDataWrapper *object, regex_t *pattern)
{
    CamelDataWrapper *containee;
    int truth = FALSE;
    int parts, i;
    
    containee = camel_medium_get_content_object (CAMEL_MEDIUM (object));
    
    if (containee == NULL)
        return FALSE;
    
    /* TODO: I find it odd that get_part and get_content_object do not
       add a reference, probably need fixing for multithreading */
    
    /* using the object types is more accurate than using the mime/types */
    if (CAMEL_IS_MULTIPART (containee)) {
        parts = camel_multipart_get_number (CAMEL_MULTIPART (containee));
        for (i = 0; i < parts && truth == FALSE; i++) {
            CamelDataWrapper *part = (CamelDataWrapper *)camel_multipart_get_part (CAMEL_MULTIPART (containee), i);
            if (part)
                truth = camel_search_message_body_contains (part, pattern);
        }
    } else if (CAMEL_IS_MIME_MESSAGE (containee)) {
        /* for messages we only look at its contents */
        truth = camel_search_message_body_contains ((CamelDataWrapper *)containee, pattern);
    } else if (header_content_type_is(CAMEL_DATA_WRAPPER (containee)->mime_type, "text", "*")) {
        /* for all other text parts, we look inside, otherwise we dont care */
        CamelStreamMem *mem = (CamelStreamMem *)camel_stream_mem_new ();
        
        camel_data_wrapper_write_to_stream (containee, CAMEL_STREAM (mem));
        camel_stream_write (CAMEL_STREAM (mem), "", 1);
        truth = regexec (pattern, mem->buffer->data, 0, NULL, 0) == 0;
        camel_object_unref (CAMEL_OBJECT (mem));
    }
    
    return truth;
}