aboutsummaryrefslogtreecommitdiff
path: root/lib/transform.c
blob: e9b2474853bd90f3fafa0c9ee92a75dfcebbd652 (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
/* This file is part of Mailfromd.
   Copyright (C) 2006-2011, 2015-2017 Sergey Poznyakoff.
   (using my implementation for the GNU tar and rush).

   Mailfromd 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.

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

#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <stdlib.h>
#include <regex.h>
#include <mailutils/alloc.h>
#include <mailutils/cctype.h>
#include <libmf.h>

enum transform_type
  {
    transform_incomplete,
    transform_first,
    transform_global
  };

enum replace_segm_type
  {
    segm_literal,   /* Literal segment */
    segm_backref,   /* Back-reference segment */
    segm_case_ctl   /* Case control segment (GNU extension) */
  };

enum case_ctl_type
  {
    ctl_stop,       /* Stop case conversion */ 
    ctl_upcase_next,/* Turn the next character to uppercase */ 
    ctl_locase_next,/* Turn the next character to lowercase */
    ctl_upcase,     /* Turn the replacement to uppercase until ctl_stop */
    ctl_locase      /* Turn the replacement to lowercase until ctl_stop */
  };

struct replace_segm
{
  struct replace_segm *next;
  enum replace_segm_type type;
  union
  {
    struct
    {
      char *ptr;
      size_t size;
    } literal;                /* type == segm_literal */   
    size_t ref;               /* type == segm_backref */
    enum case_ctl_type ctl;   /* type == segm_case_ctl */ 
  } v;
};

struct transform
{
  struct transform *next;
  enum transform_type transform_type;
  unsigned match_number;
  regex_t regex;
  /* Compiled replacement expression */
  struct replace_segm *repl_head, *repl_tail;
  size_t segm_count; /* Number of elements in the above list */
};

struct transform_list
{
  struct transform *head, *tail;
};

struct transform_error
{
  const char *diag;
  int pos;
  const char *arg;
  void *mem;
};

struct transform_error last_transform_error;

static void
init_transform_error ()
{
  if (last_transform_error.mem)
    free(last_transform_error.mem);
  memset(&last_transform_error, 0, sizeof(last_transform_error));
}

const char *
transform_error_string ()
{
  static char transform_error_buf[1024];
  
  if (!last_transform_error.diag)
    return NULL;
  if (last_transform_error.arg)
    snprintf (transform_error_buf, sizeof (transform_error_buf),
	      "%s, in \"%s\" pos. %d",
	      last_transform_error.diag,
	      last_transform_error.arg,
	      last_transform_error.pos);
  else
    strncpy (transform_error_buf, last_transform_error.diag,
	     sizeof (transform_error_buf));
  init_transform_error ();
  return transform_error_buf;
}


static struct transform *
new_transform (struct transform_list *tlist)
{
  struct transform *p = mu_zalloc (sizeof *p);
  p->transform_type = transform_incomplete;
  if (tlist->tail)
    tlist->tail->next = p;
  else
    tlist->head = p;
  tlist->tail = p;
  return p;
}

static struct replace_segm *
add_segment (struct transform *tf)
{
  struct replace_segm *segm = mu_alloc (sizeof *segm);
  segm->next = NULL;
  if (tf->repl_tail)
    tf->repl_tail->next = segm;
  else
    tf->repl_head = segm;
  tf->repl_tail = segm;
  tf->segm_count++;
  return segm;
}

static void
add_literal_segment (struct transform *tf, char *str, char *end)
{
  size_t len = end - str;
  if (len)
    {
      struct replace_segm *segm = add_segment (tf);
      segm->type = segm_literal;
      segm->v.literal.ptr = mu_alloc (len + 1);
      memcpy (segm->v.literal.ptr, str, len);
      segm->v.literal.ptr[len] = 0;
      segm->v.literal.size = len;
    }
}

static void
add_char_segment (struct transform *tf, int chr)
{
  struct replace_segm *segm = add_segment (tf);
  segm->type = segm_literal;
  segm->v.literal.ptr = mu_alloc (2);
  segm->v.literal.ptr[0] = chr;
  segm->v.literal.ptr[1] = 0;
  segm->v.literal.size = 1;
}

static void
add_backref_segment (struct transform *tf, size_t ref)
{
  struct replace_segm *segm = add_segment (tf);
  segm->type = segm_backref;
  segm->v.ref = ref;
}

static void
add_case_ctl_segment (struct transform *tf, enum case_ctl_type ctl)
{
  struct replace_segm *segm = add_segment (tf);
  segm->type = segm_case_ctl;
  segm->v.ctl = ctl;
}

void
replace_segm_free (struct replace_segm *segm)
{
  while (segm)
    {
      struct replace_segm *next = segm->next;
      switch (segm->type)
	{
	case segm_literal:
	  free (segm->v.literal.ptr);
	  break;

	case segm_backref:
	case segm_case_ctl:
	  break;
	}
      free (segm);
      segm = next;
    }
}

void
transform_free(struct transform *xform)
{
  while (xform)
    {
      struct transform *next = xform->next;
      if (xform->transform_type != transform_incomplete)
	regfree (&xform->regex);
      replace_segm_free (xform->repl_head);
      free (xform);
      xform = next;
    }
}

static int
parse_transform_expr (struct transform_list *tlist, const char *expr,
		      int cflags, const char **endp)
{
  int delim;
  int i, j, rc;
  char *str, *beg, *cur;
  const char *p;
  struct transform *tf = new_transform (tlist);
  enum transform_type transform_type;
  
  if (expr[0] != 's')
    {
      last_transform_error.diag = _("invalid transform expression");
      last_transform_error.pos = 0;
      last_transform_error.arg = expr;
      return 1;
    }

  delim = expr[1];

  /* Scan regular expression */
  for (i = 2; expr[i] && expr[i] != delim; i++)
    if (expr[i] == '\\' && expr[i+1])
      i++;

  if (expr[i] != delim)
    {
      last_transform_error.diag = _("missing 2nd delimiter");
      last_transform_error.pos = i;
      last_transform_error.arg = expr;
      return 1;
    }

  /* Scan replacement expression */
  for (j = i + 1; expr[j] && expr[j] != delim; j++)
    if (expr[j] == '\\' && expr[j+1])
      j++;

  if (expr[j] != delim)
    {
      last_transform_error.diag = _("missing trailing delimiter");
      last_transform_error.pos = j;
      last_transform_error.arg = expr;
      return 1;
    }

  /* Check flags */
  transform_type = transform_first;
  for (p = expr + j + 1; *p && *p != ';'; p++)
    switch (*p)
      {
      case 'g':
	transform_type = transform_global;
	break;

      case 'i':
	cflags |= REG_ICASE;
	break;

      case 'x':
	cflags |= REG_EXTENDED;
	break;
	
      case '0': case '1': case '2': case '3': case '4':
      case '5': case '6': case '7': case '8': case '9':
	tf->match_number = strtoul (p, (char**) &p, 0);
	p--;
	break;

      default:
	last_transform_error.diag = _("unknown flag");
	last_transform_error.pos = p - expr;
	last_transform_error.arg = expr;
	return 1;
    }

  if (*p == ';')
    p++;
  
  /* Extract and compile regex */
  str = mu_alloc (i - 1);
  memcpy (str, expr + 2, i - 2);
  str[i - 2] = 0;

  rc = regcomp (&tf->regex, str, cflags);
  tf->transform_type = transform_type;
  if (rc)
    {
      char errbuf[512];
      regerror (rc, &tf->regex, errbuf, sizeof (errbuf));
      last_transform_error.diag = _("invalid transform expression");
      last_transform_error.pos = 0;
      last_transform_error.mem = mu_strdup(errbuf);
      last_transform_error.arg = last_transform_error.mem;
      free (str);
      return 1;
    }

  if (str[0] == '^' || str[strlen (str) - 1] == '$')
    tf->transform_type = transform_first;
  
  free (str);

  /* Extract and compile replacement expr */
  i++;
  str = mu_alloc (j - i + 1);
  memcpy (str, expr + i, j - i);
  str[j - i] = 0;

  for (cur = beg = str; *cur;)
    {
      if (*cur == '\\')
	{
	  size_t n;
	  
	  add_literal_segment (tf, beg, cur);
	  switch (*++cur)
	    {
	    case '0': case '1': case '2': case '3': case '4':
	    case '5': case '6': case '7': case '8': case '9':
	      n = strtoul (cur, &cur, 10);
	      if (n > tf->regex.re_nsub)
		{
		  last_transform_error.diag = _("back reference out of range");
		  last_transform_error.pos = cur - str;
		  last_transform_error.mem = str;
		  last_transform_error.arg = last_transform_error.mem;
		  return 1;
		}
	      add_backref_segment (tf, n);
	      break;

	    case '\\':
	      add_char_segment (tf, '\\');
	      cur++;
	      break;

	    case 'a':
	      add_char_segment (tf, '\a');
	      cur++;
	      break;
	      
	    case 'b':
	      add_char_segment (tf, '\b');
	      cur++;
	      break;
	      
	    case 'f':
	      add_char_segment (tf, '\f');
	      cur++;
	      break;
	      
	    case 'n':
	      add_char_segment (tf, '\n');
	      cur++;
	      break;
	      
	    case 'r':
	      add_char_segment (tf, '\r');
	      cur++;
	      break;
	      
	    case 't':
	      add_char_segment (tf, '\t');
	      cur++;
	      break;
	      
	    case 'v':
	      add_char_segment (tf, '\v');
	      cur++;
	      break;

	    case '&':
	      add_char_segment (tf, '&');
	      cur++;
	      break;
	      
	    case 'L':
	      /* Turn the replacement to lowercase until a `\U' or `\E'
		 is found, */
	      add_case_ctl_segment (tf, ctl_locase);
	      cur++;
	      break;
 
	    case 'l':
	      /* Turn the next character to lowercase, */
	      add_case_ctl_segment (tf, ctl_locase_next);
	      cur++;
	      break;
	      
	    case 'U':
	      /* Turn the replacement to uppercase until a `\L' or `\E'
		 is found, */
	      add_case_ctl_segment (tf, ctl_upcase);
	      cur++;
	      break;
	      
	    case 'u':
	      /* Turn the next character to uppercase, */
	      add_case_ctl_segment (tf, ctl_upcase_next);
	      cur++;
	      break;
	      
	    case 'E':
	      /* Stop case conversion started by `\L' or `\U'. */
	      add_case_ctl_segment (tf, ctl_stop);
	      cur++;
	      break;
  
	    default:
	      /* Try to be nice */
	      {
		char buf[2];
		buf[0] = '\\';
		buf[1] = *cur;
		add_literal_segment (tf, buf, buf + 2);
	      }
	      cur++;
	      break;
	    }
	  beg = cur;
	}
      else if (*cur == '&')
	{
	  add_literal_segment (tf, beg, cur);
	  add_backref_segment (tf, 0);
	  beg = ++cur;
	}
      else
	cur++;
    }
  add_literal_segment (tf, beg, cur);
  *endp = p;
  return 0;
}

transform_t 
transform_compile (const char *expr, int cflags)
{
  struct transform_list tlist = { NULL, NULL };

  init_transform_error ();

  while (*expr)
    if (parse_transform_expr (&tlist, expr, cflags, &expr))
      {
	transform_free (tlist.head);
	return NULL;
      }
  return tlist.head;
}

/* Run case conversion specified by CASE_CTL on array PTR of SIZE
   characters. Returns pointer to statically allocated storage. */
static const char *
run_case_conv (enum case_ctl_type case_ctl, const char *ptr, size_t size)
{
  static char *case_ctl_buffer;
  static size_t case_ctl_bufsize;
  char *p;
  
  if (case_ctl_bufsize < size)
    {
      case_ctl_bufsize = size;
      case_ctl_buffer = mu_realloc (case_ctl_buffer, case_ctl_bufsize);
    }
  memcpy (case_ctl_buffer, ptr, size);
  switch (case_ctl)
    {
    case ctl_upcase_next:
      case_ctl_buffer[0] = mu_toupper (case_ctl_buffer[0]);
      break;
      
    case ctl_locase_next:
      case_ctl_buffer[0] = mu_tolower (case_ctl_buffer[0]);
      break;
      
    case ctl_upcase:
      for (p = case_ctl_buffer; p < case_ctl_buffer + size; p++)
	*p = mu_toupper (*p);
      break;
      
    case ctl_locase:
      for (p = case_ctl_buffer; p < case_ctl_buffer + size; p++)
	*p = mu_tolower (*p);
      break;

    case ctl_stop:
      break;
    }
  return case_ctl_buffer;
}


void
_single_transform_name_to_slist (struct transform *tf,
				 const char *input,
				 void *slist,
				 transform_append_t append)
{
  regmatch_t *rmp;
  int rc;
  size_t nmatches = 0;
  enum case_ctl_type case_ctl = ctl_stop,  /* Current case conversion op */
                     save_ctl = ctl_stop;  /* Saved case_ctl for \u and \l */
  
  /* Reset case conversion after a single-char operation */
#define CASE_CTL_RESET()  if (case_ctl == ctl_upcase_next     \
			      || case_ctl == ctl_locase_next) \
                            {                                 \
                              case_ctl = save_ctl;            \
                              save_ctl = ctl_stop;            \
			    }
  
  rmp = mu_alloc ((tf->regex.re_nsub + 1) * sizeof (*rmp));

  while (*input)
    {
      size_t disp;
      const char *ptr;
      
      rc = regexec (&tf->regex, input, tf->regex.re_nsub + 1, rmp, 0);
      
      if (rc == 0)
	{
	  struct replace_segm *segm;
	  
	  disp = rmp[0].rm_eo;

	  if (rmp[0].rm_so)
	    append (slist, input, rmp[0].rm_so);

	  nmatches++;
	  if (tf->match_number && nmatches < tf->match_number)
	    {
	      append (slist, input, disp);
	      input += disp;
	      continue;
	    }

	  for (segm = tf->repl_head; segm; segm = segm->next)
	    {
	      switch (segm->type)
		{
		case segm_literal:    /* Literal segment */
		  if (case_ctl == ctl_stop)
		    ptr = segm->v.literal.ptr;
		  else
		    {
		      ptr = run_case_conv (case_ctl,
					   segm->v.literal.ptr,
					   segm->v.literal.size);
		      CASE_CTL_RESET();
		    }
		  append (slist, ptr, segm->v.literal.size);
		  break;
	      
		case segm_backref:    /* Back-reference segment */
		  if (rmp[segm->v.ref].rm_so != -1
		      && rmp[segm->v.ref].rm_eo != -1)
		    {
		      size_t size = rmp[segm->v.ref].rm_eo
			              - rmp[segm->v.ref].rm_so;
		      ptr = input + rmp[segm->v.ref].rm_so;
		      if (case_ctl != ctl_stop)
			{
			  ptr = run_case_conv (case_ctl, ptr, size);
			  CASE_CTL_RESET();
			}
		      
		      append (slist, ptr, size);
		    }
		  break;

		case segm_case_ctl:
		  switch (segm->v.ctl)
		    {
		    case ctl_upcase_next:
		    case ctl_locase_next:
		      switch (save_ctl)
			{
			case ctl_stop:
			case ctl_upcase:
			case ctl_locase:
			  save_ctl = case_ctl;
			default:
			  break;
			}
		      /*FALL THROUGH*/
		      
		    case ctl_upcase:
		    case ctl_locase:
		    case ctl_stop:
		      case_ctl = segm->v.ctl;
		    }
		}
	    }
	}
      else
	{
	  disp = strlen (input);
	  append (slist, input, disp);
	}

      input += disp;

      if (tf->transform_type == transform_first)
	{
	  append (slist, input, strlen (input));
	  break;
	}
    }

  free (rmp);
}

char *
transform_string (transform_t tf, const char *input,
		  void *slist,
		  transform_append_t append,
		  transform_reduce_t reduce)
{
  if (tf) 
    {
      for (; tf; tf = tf->next)
	{
	  _single_transform_name_to_slist (tf, input, slist, append);
	  append (slist, "", 1);
	  input = reduce (slist);
	}
    }
  return mu_strdup (input);
}
  

/*
 Local Variables:
 c-file-style: "gnu"
 End:
*/
/* EOF */

Return to:

Send suggestions and report system problems to the System administrator.