summaryrefslogtreecommitdiffabout
path: root/imap4d/search.c
blob: 3c243eddf5a4da1e33c289501657de0b6533a679 (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
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
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
/* GNU Mailutils -- a suite of utilities for electronic mail
   Copyright (C) 1999-2019 Free Software Foundation, Inc.

   GNU Mailutils 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 3, or (at your option)
   any later version.

   GNU Mailutils 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 GNU Mailutils.  If not, see <http://www.gnu.org/licenses/>. */

#include "imap4d.h"
#include <mailutils/assoc.h>

/*
 * This will be a royal pain in the arse to implement
 * Alain: True, but the new lib mailbox should coming handy with
 * some sort of query interface.
 * Sergey: It was, indeed.
 */

/* Implementation details:

   The searching criteria are parsed and a parse tree is created. Each
   node is of type search_node (see below) and contains either data
   (struct value) or an instruction, which evaluates to a boolean value.

   The function search_run recursively evaluates the tree and returns a
   boolean number, 0 or 1 depending on whether the current message meets
   the search conditions. */

struct parsebuf;

enum value_type
  {
    value_undefined,
    value_number,
    value_string,
    value_date,
    value_msgset
  };

enum node_type
  {
    node_call,
    node_and,
    node_or,
    node_not,
    node_value
  };

struct value
{
  enum value_type type;
  union
  {
    char *string;
    mu_off_t number;
    time_t date;
    mu_msgset_t msgset;
  } v;
};

#define MAX_NODE_ARGS 2

struct search_node;

typedef void (*instr_fn) (struct parsebuf *, struct search_node *,
			  struct value *, struct value *);

struct search_node
{
  enum node_type type;
  union
  {
    struct key_node
    {
      char *keyword;
      instr_fn fun;
      int narg;
      struct search_node *arg[MAX_NODE_ARGS];
    } key;
    struct search_node *arg[2]; /* Binary operation */
    struct value value;
  } v;
};

static void cond_msgset (struct parsebuf *, struct search_node *,
			 struct value *, struct value *);
static void cond_bcc (struct parsebuf *, struct search_node *,
		      struct value *, struct value *);
static void cond_before (struct parsebuf *, struct search_node *,
			 struct value *, struct value *);
static void cond_body (struct parsebuf *, struct search_node *,
		       struct value *, struct value *);
static void cond_cc (struct parsebuf *, struct search_node *,
		     struct value *, struct value *);
static void cond_from (struct parsebuf *, struct search_node *,
		       struct value *, struct value *);
static void cond_header (struct parsebuf *, struct search_node *,
			 struct value *, struct value *);
static void cond_keyword (struct parsebuf *, struct search_node *,
			  struct value *, struct value *);
static void cond_larger (struct parsebuf *, struct search_node *,
			 struct value *, struct value *);
static void cond_on (struct parsebuf *, struct search_node *,
		     struct value *, struct value *);
static void cond_sentbefore (struct parsebuf *, struct search_node *,
			     struct value *, struct value *);
static void cond_senton (struct parsebuf *, struct search_node *,
			 struct value *, struct value *);
static void cond_sentsince (struct parsebuf *, struct search_node *,
			    struct value *, struct value *);
static void cond_since (struct parsebuf *, struct search_node *,
			struct value *, struct value *);
static void cond_smaller (struct parsebuf *, struct search_node *,
			  struct value *, struct value *);
static void cond_subject (struct parsebuf *, struct search_node *,
			  struct value *, struct value *);
static void cond_text (struct parsebuf *, struct search_node *,
		       struct value *, struct value *);
static void cond_to (struct parsebuf *, struct search_node *,
		     struct value *, struct value *);
static void cond_uid (struct parsebuf *, struct search_node *,
		      struct value *, struct value *);

/* A basic condition structure */
struct cond
{
  char *name;          /* Condition name */
  char *argtypes;      /* String of argument types or NULL if it takes no
			  args */
  instr_fn inst;       /* Corresponding instruction function */
};

/* Types are: s -- string
	      n -- number
	      d -- date
	      m -- message set
*/

/* List of basic conditions. "ALL" and <message set> is handled separately */
struct cond condlist[] =
{
  { "BCC",        "s",  cond_bcc },
  { "BEFORE",     "d",  cond_before },
  { "BODY",       "s",  cond_body },
  { "CC",         "s",  cond_cc },
  { "FROM",       "s",  cond_from },
  { "HEADER",     "ss", cond_header },
  { "KEYWORD",    "s",  cond_keyword },
  { "LARGER",     "n",  cond_larger },
  { "ON",         "d",  cond_on },
  { "SENTBEFORE", "d",  cond_sentbefore },
  { "SENTON",     "d",  cond_senton },
  { "SENTSINCE",  "d",  cond_sentsince },
  { "SINCE",      "d",  cond_since },
  { "SMALLER",    "n",  cond_smaller },
  { "SUBJECT",    "s",  cond_subject },
  { "TEXT",       "s",  cond_text },
  { "TO",         "s",  cond_to },
  { "UID",        "u",  cond_uid },
  { NULL }
};

/* Other search keys described by rfc2060 are implemented on top of these
   basic conditions. Condition equivalence structure defines the equivalent
   condition in terms of basic ones. (Kind of macro substitution) */

struct cond_equiv
{
  char *name;           /* RFC2060 search key name */
  char *equiv;          /* Equivalent query in terms of basic conds */
};

struct cond_equiv equiv_list[] =
{
  { "ANSWERED",   "KEYWORD \\Answered" },
  { "DELETED",    "KEYWORD \\Deleted" },
  { "DRAFT",      "KEYWORD \\Draft" },
  { "FLAGGED",    "KEYWORD \\Flagged" },
  { "NEW",        "(RECENT UNSEEN)" },
  { "OLD",        "NOT RECENT" },
  { "RECENT",     "KEYWORD \\Recent" },
  { "SEEN",       "KEYWORD \\Seen" },
  { "UNANSWERED", "NOT KEYWORD \\Answered" },
  { "UNDELETED",  "NOT KEYWORD \\Deleted" },
  { "UNDRAFT",    "NOT KEYWORD \\Draft" },
  { "UNFLAGGED",  "NOT KEYWORD \\Flagged" },
  { "UNKEYWORD",  "NOT KEYWORD" },
  { "UNSEEN",     "NOT KEYWORD \\Seen" },
  { NULL }
};

/* A memory allocation chain used to keep track of objects allocated during
   the recursive-descend parsing. */
struct mem_chain
{
  struct mem_chain *next;
  void *mem;
  void (*free_fun) (void *);
};

/* Code and stack sizes for execution of compiled search statement */
#define CODESIZE 64
#define CODEINCR 16
#define STACKSIZE 64
#define STACKINCR 16

/* Maximum length of a token. Tokens longer than that are accepted, provided
   that they are enclosed in doublequotes */
#define MAXTOKEN 64

/* Parse buffer structure */
struct parsebuf
{
  imap4d_tokbuf_t tok;          /* Token buffer */
  int arg;                      /* Argument number */
  char *token;                  /* Current token */
  int isuid;                    /* UIDs instead of msgnos are required */
  char *err_mesg;               /* Error message if a parse error occured */
  struct mem_chain *alloc;      /* Chain of objects allocated during parsing */
  char *charset;                /* Charset, other than US-ASCII requested */

  struct search_node *tree;     /* Parse tree */

				/* Execution time only: */
  size_t msgno;                 /* Number of current message */
  mu_message_t msg;             /* Current message */
};

static void parse_free_mem (struct parsebuf *pb);
static void *parse_regmem (struct parsebuf *pb, void *mem, void (*f)(void*));
static char *parse_strdup (struct parsebuf *pb, char *s);
static void *parse_alloc (struct parsebuf *pb, size_t size);
static struct search_node *parse_search_key_list (struct parsebuf *pb);
static struct search_node *parse_search_key (struct parsebuf *pb);
static int parse_gettoken (struct parsebuf *pb, int req);
static int search_run (struct parsebuf *pb);
static void do_search (struct parsebuf *pb);
static int available_charset (const char *charset);

/*
6.4.4.  SEARCH Command

   Arguments:  OPTIONAL [CHARSET] specification
	       searching criteria (one or more)

   Responses:  REQUIRED untagged response: SEARCH

   Result:     OK - search completed
	       NO - search error: can't search that [CHARSET] or
		    criteria
	       BAD - command unknown or arguments invalid
*/

int
imap4d_search (struct imap4d_session *session,
	       struct imap4d_command *command, imap4d_tokbuf_t tok)
{
  int rc;
  char *err_text= "";

  rc = imap4d_search0 (tok, 0, &err_text);
  return io_completion_response (command, rc, "%s", err_text);
}

int
imap4d_search0 (imap4d_tokbuf_t tok, int isuid, char **err_text)
{
  struct parsebuf parsebuf;

  memset (&parsebuf, 0, sizeof(parsebuf));
  parsebuf.tok = tok;
  parsebuf.arg = IMAP4_ARG_1 + !!isuid;
  parsebuf.err_mesg = NULL;
  parsebuf.alloc = NULL;
  parsebuf.isuid = isuid;

  if (!parse_gettoken (&parsebuf, 0))
    {
      *err_text = "Too few args";
      return RESP_BAD;
    }

  if (mu_c_strcasecmp (parsebuf.token, "CHARSET") == 0)
    {
      if (!parse_gettoken (&parsebuf, 0))
	{
	  *err_text = "Too few args";
	  return RESP_BAD;
	}

      /* Currently only ASCII is supported */
      if (mu_c_strcasecmp (parsebuf.token, "US-ASCII"))
	{
	  parsebuf.charset = parse_strdup (&parsebuf, parsebuf.token);
	  if (!available_charset (parsebuf.charset))
	    {
	      *err_text = "[BADCHARSET] Charset not supported";
	      return RESP_NO;
	    }
	}
      else
	parsebuf.charset = NULL;

      if (!parse_gettoken (&parsebuf, 0))
	{
	  *err_text = "Too few args";
	  return RESP_BAD;
	}
    }

  /* Compile the expression */
  parsebuf.tree = parse_search_key_list (&parsebuf);
  if (!parsebuf.tree)
    {
      *err_text = parsebuf.err_mesg ? parsebuf.err_mesg : "Parse error";
      parse_free_mem (&parsebuf);
      return RESP_BAD;
    }

  if (parsebuf.token)
    {
      parse_free_mem (&parsebuf);
      *err_text = "Junk at the end of statement";
      return RESP_BAD;
    }

  /* Execute compiled expression */
  do_search (&parsebuf);

  parse_free_mem (&parsebuf);

  *err_text = "Completed";
  return RESP_OK;
}

/* For each message from the mailbox execute the query from `pb' and
   output the message number if the query returned 1 */
void
do_search (struct parsebuf *pb)
{
  size_t count = 0;

  mu_mailbox_messages_count (mbox, &count);

  io_sendf ("* SEARCH");
  for (pb->msgno = 1; pb->msgno <= count; pb->msgno++)
    {
      if (mu_mailbox_get_message (mbox, pb->msgno, &pb->msg) == 0
	  && search_run (pb))
	{
	  if (pb->isuid)
	    {
	      size_t uid;
	      mu_message_get_uid (pb->msg, &uid);
	      io_sendf (" %s", mu_umaxtostr (0, uid));
	    }
	  else
	    io_sendf (" %s", mu_umaxtostr (0, pb->msgno));
	}
    }
  io_sendf ("\n");
}

/* Parse buffer functions */

int
parse_gettoken (struct parsebuf *pb, int req)
{
  if (req && pb->arg >= imap4d_tokbuf_argc (pb->tok))
    {
      pb->err_mesg = "Unexpected end of statement";
      return 0;
    }
  pb->token = imap4d_tokbuf_getarg (pb->tok, pb->arg++);
  return 1;
}

/* Memory handling */

/* Free all memory allocated for parsebuf structure */
void
parse_free_mem (struct parsebuf *pb)
{
  struct mem_chain *alloc, *next;
  alloc = pb->alloc;
  while (alloc)
    {
      next = alloc->next;
      if (alloc->free_fun)
	alloc->free_fun (alloc->mem);
      else
	free (alloc->mem);
      free (alloc);
      alloc = next;
    }
}

/* Register a memory pointer mem with the parsebuf */
void *
parse_regmem (struct parsebuf *pb, void *mem, void (*f) (void*))
{
  struct mem_chain *mp;

  mp = mu_alloc (sizeof(*mp));
  mp->next = pb->alloc;
  pb->alloc = mp;
  mp->mem = mem;
  mp->free_fun = f;
  return mem;
}

/* Allocate `size' bytes of memory within parsebuf structure */
void *
parse_alloc (struct parsebuf *pb, size_t size)
{
  void *p = mu_alloc (size);
  return parse_regmem (pb, p, NULL);
}

/* Create a copy of the string. */
char *
parse_strdup (struct parsebuf *pb, char *s)
{
  s = mu_strdup (s);
  if (!s)
    imap4d_bye (ERR_NO_MEM);
  return parse_regmem (pb, s, NULL);
}

static void
free_msgset (void *ptr)
{
  mu_msgset_free (ptr);
}

mu_msgset_t
parse_msgset_create (struct parsebuf *pb, mu_mailbox_t mbox, int flags)
{
  mu_msgset_t msgset;

  if (mu_msgset_create (&msgset, mbox, flags))
    imap4d_bye (ERR_NO_MEM);
  return parse_regmem (pb, msgset, free_msgset);
}

/* A recursive-descent parser for the following grammar:
   search_key_list : search_key
		   | search_key_list search_key
		   ;

   search_key      : simple_key
		   | NOT simple_key
		   | OR simple_key simple_key
		   | '(' search_key_list ')'
		   ;
*/

struct search_node *parse_simple_key (struct parsebuf *pb);
struct search_node *parse_equiv_key (struct parsebuf *pb);

struct search_node *
parse_search_key_list (struct parsebuf *pb)
{
  struct search_node *leftarg = NULL;

  while (pb->token && pb->token[0] != ')')
    {
      struct search_node *rightarg = parse_search_key (pb);
      if (!rightarg)
	return NULL;
      if (!leftarg)
	leftarg = rightarg;
      else
	{
	  struct search_node *node = parse_alloc (pb, sizeof *node);
	  node->type = node_and;
	  node->v.arg[0] = leftarg;
	  node->v.arg[1] = rightarg;
	  leftarg = node;
	}
    }
  return leftarg;
}

struct search_node *
parse_search_key (struct parsebuf *pb)
{
  struct search_node *node;

  if (strcmp (pb->token, "(") == 0)
    {
      if (parse_gettoken (pb, 1) == 0)
	return NULL;

      node = parse_search_key_list (pb);
      if (!node)
	return NULL;

      if (strcmp (pb->token, ")"))
	{
	  pb->err_mesg = "Unbalanced parenthesis";
	  return NULL;
	}
      parse_gettoken (pb, 0);
      return node;
    }
  else if (mu_c_strcasecmp (pb->token, "ALL") == 0)
    {
      node = parse_alloc (pb, sizeof *node);
      node->type = node_value;
      node->v.value.type = value_number;
      node->v.value.v.number = 1;

      parse_gettoken (pb, 0);
      return node;
    }
  else if (mu_c_strcasecmp (pb->token, "NOT") == 0)
    {
      struct search_node *np;

      if (parse_gettoken (pb, 1) == 0)
	 return NULL;

      np = parse_search_key (pb);
      if (!np)
	 return NULL;

      node = parse_alloc (pb, sizeof *node);
      node->type = node_not;
      node->v.arg[0] = np;

      return node;
    }
  else if (mu_c_strcasecmp (pb->token, "OR") == 0)
    {
      struct search_node *leftarg, *rightarg;

      if (parse_gettoken (pb, 1) == 0)
	 return NULL;

      if ((leftarg = parse_search_key (pb)) == NULL
	   || (rightarg = parse_search_key (pb)) == NULL)
	 return NULL;

      node = parse_alloc (pb, sizeof *node);
      node->type = node_or;
      node->v.arg[0] = leftarg;
      node->v.arg[1] = rightarg;

      return node;
    }
  else
    return parse_equiv_key (pb);
}

struct search_node *
parse_equiv_key (struct parsebuf *pb)
{
  struct search_node *node;
  struct cond_equiv *condp;
  int save_arg;
  imap4d_tokbuf_t save_tok;

  for (condp = equiv_list; condp->name && mu_c_strcasecmp (condp->name, pb->token);
	condp++)
    ;

  if (!condp->name)
    return parse_simple_key (pb);

  save_arg = pb->arg;
  save_tok = pb->tok;
  pb->tok = imap4d_tokbuf_from_string (condp->equiv);
  pb->arg = 0;

  parse_gettoken (pb, 0);

  node = parse_search_key_list (pb);
  if (!node)
    {
      /* shouldn't happen? */
      mu_diag_output (MU_DIAG_CRIT, _("%s:%d: INTERNAL ERROR (please report)"),
		       __FILE__, __LINE__);
      abort ();
    }
  imap4d_tokbuf_destroy (&pb->tok);

  pb->arg = save_arg;
  pb->tok = save_tok;
  parse_gettoken (pb, 0);
  return node;
}

struct search_node *
parse_simple_key (struct parsebuf *pb)
{
  struct search_node *node;
  struct cond *condp;
  time_t time;

  for (condp = condlist; condp->name && mu_c_strcasecmp (condp->name, pb->token);
       condp++)
    ;

  if (!condp->name)
    {
      mu_msgset_t msgset = parse_msgset_create (pb, mbox, MU_MSGSET_NUM);

      if (mu_msgset_parse_imap (msgset,
				pb->isuid ? MU_MSGSET_UID : MU_MSGSET_NUM,
				pb->token, NULL) == 0)
	{
	  struct search_node *np = parse_alloc (pb, sizeof *np);
	  np->type = node_value;
	  np->v.value.type = value_msgset;
	  np->v.value.v.msgset = msgset;

	  node = parse_alloc (pb, sizeof *node);
	  node->type = node_call;
	  node->v.key.keyword = "msgset";
	  node->v.key.narg = 1;
	  node->v.key.arg[0] = np;
	  node->v.key.fun = cond_msgset;

	  parse_gettoken (pb, 0);

	  return node;
	}
      else
	{
	  pb->err_mesg = "Unknown search criterion";
	  return NULL;
	}
    }

  node = parse_alloc (pb, sizeof *node);
  node->type = node_call;
  node->v.key.keyword = condp->name;
  node->v.key.fun = condp->inst;
  node->v.key.narg = 0;

  parse_gettoken (pb, 0);
  if (condp->argtypes)
    {
      char *t = condp->argtypes;
      char *s;
      mu_off_t number;
      struct search_node *arg;

      for (; *t; t++, parse_gettoken (pb, 0))
	{
	  if (node->v.key.narg >= MAX_NODE_ARGS)
	    {
	      pb->err_mesg = "INTERNAL ERROR: too many arguments";
	      return NULL;
	    }

	  if (!pb->token)
	    {
	      pb->err_mesg = "Not enough arguments for criterion";
	      return NULL;
	    }

	  arg = parse_alloc (pb, sizeof *arg);
	  arg->type = node_value;
	  switch (*t)
	    {
	    case 's': /* string */
	      arg->v.value.type = value_string;
	      arg->v.value.v.string = parse_strdup (pb, pb->token);
	      break;

	    case 'n': /* number */
	      number = strtoul (pb->token, &s, 10);
	      if (*s)
		{
		  pb->err_mesg = "Invalid number";
		  return NULL;
		}
	      arg->v.value.type = value_number;
	      arg->v.value.v.number = number;
	      break;

	    case 'd': /* date */
	      if (util_parse_internal_date (pb->token, &time,
					    datetime_date_only))
		{
		  pb->err_mesg = "Bad date format";
		  return NULL;
		}
	      arg->v.value.type = value_date;
	      arg->v.value.v.date = time;
	      break;

	    case 'u': /* UID message set */
	      arg->v.value.v.msgset = parse_msgset_create (pb, NULL,
							   MU_MSGSET_NUM);
	      arg->v.value.type = value_msgset;
	      if (mu_msgset_parse_imap (arg->v.value.v.msgset, MU_MSGSET_UID,
					pb->token, NULL))
		{
		  pb->err_mesg = "Bogus number set";
		  return NULL;
		}
	      break;

	    default:
	      mu_diag_output (MU_DIAG_CRIT,
			      _("%s:%d: INTERNAL ERROR (please report)"),
			      __FILE__, __LINE__);
	      abort (); /* should never happen */
	    }
	  node->v.key.arg[node->v.key.narg++] = arg;
	}
    }
  return node;
}

/* Executes a query from parsebuf */
void
evaluate_node (struct search_node *node, struct parsebuf *pb,
	       struct value *val)
{
  int i;
  struct value argval[MAX_NODE_ARGS];

  switch (node->type)
    {
    case node_call:
      for (i = 0; i < node->v.key.narg; i++)
	{
	  /* FIXME: if (i >= MAX_NODE_ARGS) */
	  evaluate_node (node->v.key.arg[i], pb, &argval[i]);
	  /* FIXME: node types? */
	}

      node->v.key.fun (pb, node, argval, val);
      break;

    case node_and:
      val->type = value_number;
      evaluate_node (node->v.arg[0], pb, &argval[0]);
      if (argval[0].v.number == 0)
	val->v.number = 0;
      else
	{
	  evaluate_node (node->v.arg[1], pb, &argval[1]);
	  val->v.number = argval[1].v.number;
	}
      break;

    case node_or:
      val->type = value_number;
      evaluate_node (node->v.arg[0], pb, &argval[0]);
      if (argval[0].v.number)
	val->v.number = 1;
      else
	{
	  evaluate_node (node->v.arg[1], pb, &argval[1]);
	  val->v.number = argval[1].v.number;
	}
      break;

    case node_not:
      evaluate_node (node->v.arg[0], pb, &argval[0]);
      val->type = value_number;
      val->v.number = !argval[0].v.number;
      break;

    case node_value:
      *val = node->v.value;
      break;
    }
}

int
search_run (struct parsebuf *pb)
{
  struct value value;

  value.type = value_undefined;
  evaluate_node (pb->tree, pb, &value);
  if (value.type != value_number)
    {
      mu_diag_output (MU_DIAG_CRIT, _("%s:%d: INTERNAL ERROR (please report)"),
	     __FILE__, __LINE__);
      abort (); /* should never happen */
    }
  return value.v.number != 0;
}

/* Helper functions for evaluationg conditions */

/* Scan the header of a message for the occurence of field named `name'.
   Return true if any of the occurences contained substring `value' */
static int
_scan_header (struct parsebuf *pb, char *name, char *value)
{
  char *hval;
  mu_header_t header = NULL;
  int i, rc;
  int result = 0;

  mu_message_get_header (pb->msg, &header);

  for (i = 1;
       result == 0
	 && (rc = mu_header_aget_value_unfold_n (header, name, i, &hval)) == 0;
       i++)
    {
      if (pb->charset)
	{
	  char *tmp;
	  rc = mu_rfc2047_decode (pb->charset, hval, &tmp);
	  if (rc)
	    {
	      mu_diag_funcall (MU_DIAG_ERR, "mu_rfc2047_decode", hval, rc);
	      free (hval);
	      continue;
	    }
	  free (hval);
	  hval = tmp;
	}
      result = mu_c_strcasestr (hval, value) != NULL;
      free (hval);
    }
  if (!(rc == 0 || rc == MU_ERR_NOENT))
    mu_diag_funcall (MU_DIAG_ERR, "mu_header_aget_value_unfold_n", NULL, rc);

  return result;
}

/* Get the value of Date: field and convert it to timestamp */
static int
_header_date (struct parsebuf *pb, time_t *timep)
{
  const char *hval;
  mu_header_t header = NULL;

  mu_message_get_header (pb->msg, &header);
  if (mu_header_sget_value (header, "Date", &hval) == 0
      && util_parse_822_date (hval, timep, datetime_date_only))
    return 0;
  return 1;
}

/* Scan all header fields for the occurence of a substring `text' */
static int
_scan_header_all (struct parsebuf *pb, char *text)
{
  mu_header_t header = NULL;
  size_t fcount = 0;
  int i, rc;
  int result;

  mu_message_get_header (pb->msg, &header);
  mu_header_get_field_count (header, &fcount);
  result = 0;
  for (i = 1; result == 0 && i < fcount; i++)
    {
      char *hval;

      rc = mu_header_aget_field_value_unfold (header, i, &hval);
      if (rc)
	{
	  mu_diag_funcall (MU_DIAG_ERR, "mu_header_aget_field_value_unfold",
			   NULL, rc);
	  continue;
	}

      if (pb->charset)
	{
	  char *tmp;
	  rc = mu_rfc2047_decode (pb->charset, hval, &tmp);
	  if (rc)
	    {
	      mu_diag_funcall (MU_DIAG_ERR, "mu_rfc2047_decode", hval, rc);
	      free (hval);
	      continue;
	    }

	  free (hval);
	  hval = tmp;
	}
       result = mu_c_strcasestr (hval, text) != NULL;
       free (hval);
    }
  return result;
}

static int
_match_text (struct parsebuf *pb, mu_message_t msg, mu_content_type_t ct,
	     char const *encoding,
	     char *text)
{
  mu_body_t body;
  mu_stream_t str;
  int rc;
  int result;
  char *buffer = NULL;
  size_t bufsize = 0;
  size_t n;

  mu_message_get_body (msg, &body);
  mu_body_get_streamref (body, &str);

  if (encoding)
    {
      mu_stream_t flt;
      rc = mu_filter_create (&flt, str, encoding,
			     MU_FILTER_DECODE,
			     MU_STREAM_READ);
      mu_stream_unref (str);
      if (rc)
	{
	  mu_error (_("can't handle encoding %s: %s"),
		    encoding, mu_strerror (rc));
	  return 0;
	}
      str = flt;
    }

  if (pb->charset)
    {
      struct mu_mime_param *param;
      if (mu_assoc_lookup (ct->param, "charset", &param) == 0
	  && mu_c_strcasecmp (param->value, pb->charset))
	{
	  char const *argv[] = { "iconv", NULL, NULL, NULL };
	  mu_stream_t flt;

	  argv[1] = param->value;
	  argv[2] = pb->charset;
	  rc = mu_filter_chain_create (&flt, str,
				       MU_FILTER_ENCODE,
				       MU_STREAM_READ,
				       MU_ARRAY_SIZE (argv) - 1,
				       (char**) argv);
	  mu_stream_unref (str);
	  if (rc)
	    {
	      mu_error (_("can't convert from charset %s to %s"),
			param->value, pb->charset);
	      return 0;
	    }
	  str = flt;
	}
    }

  result = 0;
  while ((rc = mu_stream_getline (str, &buffer, &bufsize, &n)) == 0
	 && n > 0)
    {
      result = mu_c_strcasestr (buffer, text) != NULL;
      if (result)
	break;
    }
  mu_stream_destroy (&str);
  if (rc)
    mu_diag_funcall (MU_DIAG_ERR, "mu_stream_getline", NULL, rc);
  return result;
}

static int
_match_multipart (struct parsebuf *pb, mu_message_t msg, char *text)
{
  mu_header_t hdr;
  char *encoding;
  int ismp;
  int result;
  mu_content_type_t ct;
  char *buf;
  int rc;

  if (mu_message_is_multipart (msg, &ismp))
    return 0;
  if (mu_message_get_header (msg, &hdr))
    return 0;

  if (mu_header_aget_value_unfold (hdr, MU_HEADER_CONTENT_TYPE, &buf))
    {
      buf = strdup ("text/plain");
      if (!buf)
	return 0;
    }
  rc = mu_content_type_parse (buf, NULL, &ct);
  free (buf);
  if (rc)
    return 0;

  if (mu_header_aget_value_unfold (hdr, MU_HEADER_CONTENT_TRANSFER_ENCODING,
				   &encoding))
    encoding = NULL;

  if (ismp)
    {
      size_t i, nparts;

      mu_message_get_num_parts (msg, &nparts);

      for (i = 1; i <= nparts; i++)
	{
	  mu_message_t submsg = NULL;

	  if (mu_message_get_part (msg, i, &submsg) == 0)
	    {
	      result = _match_multipart (pb, submsg, text);
	      if (result)
		break;
	    }
	}
    }
  else if (mu_c_strcasecmp (ct->type, "message") == 0
	   && mu_c_strcasecmp (ct->subtype, "rfc822") == 0)
    {
      mu_message_t submsg = NULL;

      if (mu_message_unencapsulate (msg, &submsg, NULL) == 0)
	{
	  result = _match_multipart (pb, submsg, text);
	}
    }
  else if (mu_c_strcasecmp (ct->type, "text") == 0)
    result = _match_text (pb, msg, ct, encoding, text);

  free (encoding);
  mu_content_type_destroy (&ct);

  return result;
}

/* Scan body of the message for the occurrence of a substring */
static int
_scan_body (struct parsebuf *pb, char *text)
{
  return _match_multipart (pb, pb->msg, text);
}

/* Basic instructions */

static void
cond_msgset (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  int rc = mu_msgset_locate (arg[0].v.msgset, pb->msgno, NULL);
  retval->type = value_number;
  retval->v.number = rc == 0;
}

static void
cond_bcc (struct parsebuf *pb, struct search_node *node, struct value *arg,
	  struct value *retval)
{
  retval->type = value_number;
  retval->v.number = _scan_header (pb, MU_HEADER_BCC, arg[0].v.string);
}

static void
cond_before (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time;
  const char *date;
  mu_envelope_t env;

  mu_message_get_envelope (pb->msg, &env);
  retval->type = value_number;
  if (mu_envelope_sget_date (env, &date))
    retval->v.number = 0;
  else
    {
      util_parse_ctime_date (date, &mesg_time, datetime_date_only);
      retval->v.number = mesg_time < t;
    }
}

static void
cond_body (struct parsebuf *pb, struct search_node *node, struct value *arg,
	   struct value *retval)
{
  retval->type = value_number;
  retval->v.number = _scan_body (pb, arg[0].v.string);
}

static void
cond_cc (struct parsebuf *pb, struct search_node *node, struct value *arg,
	 struct value *retval)
{
  retval->type = value_number;
  retval->v.number = _scan_header (pb, MU_HEADER_CC, arg[0].v.string);
}

static void
cond_from (struct parsebuf *pb, struct search_node *node, struct value *arg,
	   struct value *retval)
{
  char *s = arg[0].v.string;
  mu_envelope_t env;
  const char *from;
  int rc = 0;

  mu_message_get_envelope (pb->msg, &env);
  if (mu_envelope_sget_sender (env, &from) == 0)
    rc = mu_c_strcasestr (from, s) != NULL;

  retval->type = value_number;
  retval->v.number = rc || _scan_header (pb, MU_HEADER_FROM, s);
}

static void
cond_header (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  char *name = arg[0].v.string;
  char *value = arg[1].v.string;

  retval->type = value_number;
  retval->v.number = _scan_header (pb, name, value);
}

static void
cond_keyword (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  char *s = arg[0].v.string;
  mu_attribute_t attr = NULL;

  mu_message_get_attribute (pb->msg, &attr);
  retval->type = value_number;
  retval->v.number = util_attribute_matches_flag (attr, s);
}

static void
cond_larger (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  size_t size = 0;

  mu_message_size (pb->msg, &size);
  retval->type = value_number;
  retval->v.number = size > arg[0].v.number;
}

static void
cond_on (struct parsebuf *pb, struct search_node *node, struct value *arg,
	 struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time;
  const char *date;
  mu_envelope_t env;

  mu_message_get_envelope (pb->msg, &env);
  retval->type = value_number;
  if (mu_envelope_sget_date (env, &date))
    retval->v.number = 0;
  else
    {
      util_parse_ctime_date (date, &mesg_time, datetime_date_only);
      retval->v.number = t <= mesg_time && mesg_time <= t + 86400;
    }
}

static void
cond_sentbefore (struct parsebuf *pb, struct search_node *node,
		 struct value *arg,
		 struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time = 0;

  _header_date (pb, &mesg_time);
  retval->type = value_number;
  retval->v.number = mesg_time < t;
}

static void
cond_senton (struct parsebuf *pb, struct search_node *node, struct value *arg,
	     struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time = 0;

  _header_date (pb, &mesg_time);
  retval->type = value_number;
  retval->v.number = t <= mesg_time && mesg_time <= t + 86400;
}

static void
cond_sentsince (struct parsebuf *pb, struct search_node *node,
		struct value *arg,
		struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time = 0;

  _header_date (pb, &mesg_time);
  retval->type = value_number;
  retval->v.number = mesg_time >= t;
}

static void
cond_since (struct parsebuf *pb, struct search_node *node, struct value *arg,
	    struct value *retval)
{
  time_t t = arg[0].v.date;
  time_t mesg_time;
  const char *date;
  mu_envelope_t env;

  mu_message_get_envelope (pb->msg, &env);
  retval->type = value_number;
  if (mu_envelope_sget_date (env, &date))
    retval->v.number = 0;
  else
    {
      util_parse_ctime_date (date, &mesg_time, datetime_date_only);
      retval->v.number = mesg_time >= t;
    }
}

static void
cond_smaller (struct parsebuf *pb, struct search_node *node, struct value *arg,
	      struct value *retval)
{
  size_t size = 0;

  mu_message_size (pb->msg, &size);
  retval->type = value_number;
  retval->v.number = size < arg[0].v.number;
}

static void
cond_subject (struct parsebuf *pb, struct search_node *node, struct value *arg,
	      struct value *retval)
{
  retval->type = value_number;
  retval->v.number = _scan_header (pb, MU_HEADER_SUBJECT, arg[0].v.string);
}

static void
cond_text (struct parsebuf *pb, struct search_node *node, struct value *arg,
	   struct value *retval)
{
  char *s = arg[0].v.string;
  retval->type = value_number;
  retval->v.number = _scan_header_all (pb, s) || _scan_body (pb, s);
}

static void
cond_to (struct parsebuf *pb, struct search_node *node, struct value *arg,
	 struct value *retval)
{
  retval->type = value_number;
  retval->v.number = _scan_header (pb, MU_HEADER_TO, arg[0].v.string);
}

static void
cond_uid (struct parsebuf *pb, struct search_node *node, struct value *arg,
	  struct value *retval)
{
  int rc;
  size_t uid = 0;

  mu_message_get_uid (pb->msg, &uid);
  rc = mu_msgset_locate (arg[0].v.msgset, pb->msgno, NULL);
  retval->type = value_number;
  retval->v.number = rc == 0;
}

/* Return 1 if the CHARSET is available.
   This function assumes that charset is available if it is possible
   to create a filter for encoding ASCII data into it.
 */
static int
available_charset (const char *charset)
{
  int rc;
  mu_stream_t flt;
  mu_stream_t null;
  char const *argv[] = { "iconv", "US-ASCII", NULL, NULL };

  rc = mu_nullstream_create (&null, MU_STREAM_READ);
  if (rc)
    return 0;
  argv[2] = charset;
  rc = mu_filter_chain_create (&flt, null, MU_FILTER_ENCODE, MU_STREAM_READ,
			       MU_ARRAY_SIZE (argv) - 1, (char**) argv);
  mu_stream_unref (null);
  if (rc)
    return 0;
  mu_stream_destroy (&flt);
  return 1;
}

Return to:

Send suggestions and report system problems to the System administrator.