aboutsummaryrefslogtreecommitdiff
path: root/src/tool_urlglob.c
blob: e1b994108675934d73ef636a538ff67866bdde1b (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
/***************************************************************************
 *                                  _   _ ____  _
 *  Project                     ___| | | |  _ \| |
 *                             / __| | | | |_) | |
 *                            | (__| |_| |  _ <| |___
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) 1998 - 2017, Daniel Stenberg, <daniel@haxx.se>, et al.
 *
 * This software is licensed as described in the file COPYING, which
 * you should have received as part of this distribution. The terms
 * are also available at https://curl.haxx.se/docs/copyright.html.
 *
 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
 * copies of the Software, and permit persons to whom the Software is
 * furnished to do so, under the terms of the COPYING file.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 ***************************************************************************/
#include "tool_setup.h"

#define ENABLE_CURLX_PRINTF
/* use our own printf() functions */
#include "curlx.h"
#include "tool_cfgable.h"
#include "tool_doswin.h"
#include "tool_urlglob.h"
#include "tool_vms.h"

#include "memdebug.h" /* keep this as LAST include */

#define GLOBERROR(string, column, code) \
  glob->error = string, glob->pos = column, code

static CURLcode glob_fixed(URLGlob *glob, char *fixed, size_t len)
{
  URLPattern *pat = &glob->pattern[glob->size];
  pat->type = UPTSet;
  pat->content.Set.size = 1;
  pat->content.Set.ptr_s = 0;
  pat->globindex = -1;

  pat->content.Set.elements = malloc(sizeof(char *));

  if(!pat->content.Set.elements)
    return GLOBERROR("out of memory", 0, CURLE_OUT_OF_MEMORY);

  pat->content.Set.elements[0] = malloc(len + 1);
  if(!pat->content.Set.elements[0])
    return GLOBERROR("out of memory", 0, CURLE_OUT_OF_MEMORY);

  memcpy(pat->content.Set.elements[0], fixed, len);
  pat->content.Set.elements[0][len] = 0;

  return CURLE_OK;
}

/* multiply
 *
 * Multiplies and checks for overflow.
 */
static int multiply(unsigned long *amount, long with)
{
  unsigned long sum = *amount * with;
  if(!with) {
    *amount = 0;
    return 0;
  }
  if(sum/with != *amount)
    return 1; /* didn't fit, bail out */
  *amount = sum;
  return 0;
}

static CURLcode glob_set(URLGlob *glob, char **patternp,
                         size_t *posp, unsigned long *amount,
                         int globindex)
{
  /* processes a set expression with the point behind the opening '{'
     ','-separated elements are collected until the next closing '}'
  */
  URLPattern *pat;
  bool done = FALSE;
  char *buf = glob->glob_buffer;
  char *pattern = *patternp;
  char *opattern = pattern;
  size_t opos = *posp-1;

  pat = &glob->pattern[glob->size];
  /* patterns 0,1,2,... correspond to size=1,3,5,... */
  pat->type = UPTSet;
  pat->content.Set.size = 0;
  pat->content.Set.ptr_s = 0;
  pat->content.Set.elements = NULL;
  pat->globindex = globindex;

  while(!done) {
    switch (*pattern) {
    case '\0':                  /* URL ended while set was still open */
      return GLOBERROR("unmatched brace", opos, CURLE_URL_MALFORMAT);

    case '{':
    case '[':                   /* no nested expressions at this time */
      return GLOBERROR("nested brace", *posp, CURLE_URL_MALFORMAT);

    case '}':                           /* set element completed */
      if(opattern == pattern)
        return GLOBERROR("empty string within braces", *posp,
                         CURLE_URL_MALFORMAT);

      /* add 1 to size since it'll be incremented below */
      if(multiply(amount, pat->content.Set.size + 1))
        return GLOBERROR("range overflow", 0, CURLE_URL_MALFORMAT);

      /* FALLTHROUGH */
    case ',':

      *buf = '\0';
      if(pat->content.Set.elements) {
        char **new_arr = realloc(pat->content.Set.elements,
                                 (pat->content.Set.size + 1) * sizeof(char *));
        if(!new_arr)
          return GLOBERROR("out of memory", 0, CURLE_OUT_OF_MEMORY);

        pat->content.Set.elements = new_arr;
      }
      else
        pat->content.Set.elements = malloc(sizeof(char *));

      if(!pat->content.Set.elements)
        return GLOBERROR("out of memory", 0, CURLE_OUT_OF_MEMORY);

      pat->content.Set.elements[pat->content.Set.size] =
        strdup(glob->glob_buffer);
      if(!pat->content.Set.elements[pat->content.Set.size])
        return GLOBERROR("out of memory", 0, CURLE_OUT_OF_MEMORY);
      ++pat->content.Set.size;

      if(*pattern == '}') {
        pattern++; /* pass the closing brace */
        done = TRUE;
        continue;
      }

      buf = glob->glob_buffer;
      ++pattern;
      ++(*posp);
      break;

    case ']':                           /* illegal closing bracket */
      return GLOBERROR("unexpected close bracket", *posp, CURLE_URL_MALFORMAT);

    case '\\':                          /* escaped character, skip '\' */
      if(pattern[1]) {
        ++pattern;
        ++(*posp);
      }
      /* FALLTHROUGH */
    default:
      *buf++ = *pattern++;              /* copy character to set element */
      ++(*posp);
    }
  }

  *patternp = pattern; /* return with the new position */
  return CURLE_OK;
}

static CURLcode glob_range(URLGlob *glob, char **patternp,
                           size_t *posp, unsigned long *amount,
                           int globindex)
{
  /* processes a range expression with the point behind the opening '['
     - char range: e.g. "a-z]", "B-Q]"
     - num range: e.g. "0-9]", "17-2000]"
     - num range with leading zeros: e.g. "001-999]"
     expression is checked for well-formedness and collected until the next ']'
  */
  URLPattern *pat;
  int rc;
  char *pattern = *patternp;
  char *c;

  pat = &glob->pattern[glob->size];
  pat->globindex = globindex;

  if(ISALPHA(*pattern)) {
    /* character range detected */
    char min_c;
    char max_c;
    char end_c;
    unsigned long step = 1;

    pat->type = UPTCharRange;

    rc = sscanf(pattern, "%c-%c%c", &min_c, &max_c, &end_c);

    if(rc == 3) {
      if(end_c == ':') {
        char *endp;
        errno = 0;
        step = strtoul(&pattern[4], &endp, 10);
        if(errno || &pattern[4] == endp || *endp != ']')
          step = 0;
        else
          pattern = endp + 1;
      }
      else if(end_c != ']')
        /* then this is wrong */
        rc = 0;
      else
        /* end_c == ']' */
        pattern += 4;
    }

    *posp += (pattern - *patternp);

    if(rc != 3 || !step || step > (unsigned)INT_MAX ||
       (min_c == max_c && step != 1) ||
       (min_c != max_c && (min_c > max_c || step > (unsigned)(max_c - min_c) ||
                           (max_c - min_c) > ('z' - 'a'))))
      /* the pattern is not well-formed */
      return GLOBERROR("bad range", *posp, CURLE_URL_MALFORMAT);

    /* if there was a ":[num]" thing, use that as step or else use 1 */
    pat->content.CharRange.step = (int)step;
    pat->content.CharRange.ptr_c = pat->content.CharRange.min_c = min_c;
    pat->content.CharRange.max_c = max_c;

    if(multiply(amount, ((pat->content.CharRange.max_c -
                          pat->content.CharRange.min_c) /
                         pat->content.CharRange.step + 1)))
      return GLOBERROR("range overflow", *posp, CURLE_URL_MALFORMAT);
  }
  else if(ISDIGIT(*pattern)) {
    /* numeric range detected */
    unsigned long min_n;
    unsigned long max_n = 0;
    unsigned long step_n = 0;
    char *endp;

    pat->type = UPTNumRange;
    pat->content.NumRange.padlength = 0;

    if(*pattern == '0') {
      /* leading zero specified, count them! */
      c = pattern;
      while(ISDIGIT(*c)) {
        c++;
        ++pat->content.NumRange.padlength; /* padding length is set for all
                                              instances of this pattern */
      }
    }

    errno = 0;
    min_n = strtoul(pattern, &endp, 10);
    if(errno || (endp == pattern))
      endp = NULL;
    else {
      if(*endp != '-')
        endp = NULL;
      else {
        pattern = endp + 1;
        while(*pattern && ISBLANK(*pattern))
          pattern++;
        if(!ISDIGIT(*pattern)) {
          endp = NULL;
          goto fail;
        }
        errno = 0;
        max_n = strtoul(pattern, &endp, 10);
        if(errno)
          /* overflow */
          endp = NULL;
        else if(*endp == ':') {
          pattern = endp + 1;
          errno = 0;
          step_n = strtoul(pattern, &endp, 10);
          if(errno)
            /* over/underflow situation */
            endp = NULL;
        }
        else
          step_n = 1;
        if(endp && (*endp == ']')) {
          pattern = endp + 1;
        }
        else
          endp = NULL;
      }
    }

    fail:
    *posp += (pattern - *patternp);

    if(!endp || !step_n ||
       (min_n == max_n && step_n != 1) ||
       (min_n != max_n && (min_n > max_n || step_n > (max_n - min_n))))
      /* the pattern is not well-formed */
      return GLOBERROR("bad range", *posp, CURLE_URL_MALFORMAT);

    /* typecasting to ints are fine here since we make sure above that we
       are within 31 bits */
    pat->content.NumRange.ptr_n = pat->content.NumRange.min_n = min_n;
    pat->content.NumRange.max_n = max_n;
    pat->content.NumRange.step = step_n;

    if(multiply(amount, ((pat->content.NumRange.max_n -
                          pat->content.NumRange.min_n) /
                         pat->content.NumRange.step + 1)))
      return GLOBERROR("range overflow", *posp, CURLE_URL_MALFORMAT);
  }
  else
    return GLOBERROR("bad range specification", *posp, CURLE_URL_MALFORMAT);

  *patternp = pattern;
  return CURLE_OK;
}

static bool peek_ipv6(const char *str, size_t *skip)
{
  /*
   * Scan for a potential IPv6 literal.
   * - Valid globs contain a hyphen and <= 1 colon.
   * - IPv6 literals contain no hyphens and >= 2 colons.
   */
  size_t i = 0;
  size_t colons = 0;
  if(str[i++] != '[') {
    return FALSE;
  }
  for(;;) {
    const char c = str[i++];
    if(ISALNUM(c) || c == '.' || c == '%') {
      /* ok */
    }
    else if(c == ':') {
      colons++;
    }
    else if(c == ']') {
      *skip = i;
      return colons >= 2 ? TRUE : FALSE;
    }
    else {
      return FALSE;
    }
  }
}

static CURLcode glob_parse(URLGlob *glob, char *pattern,
                           size_t pos, unsigned long *amount)
{
  /* processes a literal string component of a URL
     special characters '{' and '[' branch to set/range processing functions
   */
  CURLcode res = CURLE_OK;
  int globindex = 0; /* count "actual" globs */

  *amount = 1;

  while(*pattern && !res) {
    char *buf = glob->glob_buffer;
    size_t sublen = 0;
    while(*pattern && *pattern != '{') {
      if(*pattern == '[') {
        /* skip over IPv6 literals and [] */
        size_t skip = 0;
        if(!peek_ipv6(pattern, &skip) && (pattern[1] == ']'))
          skip = 2;
        if(skip) {
          memcpy(buf, pattern, skip);
          buf += skip;
          pattern += skip;
          sublen += skip;
          continue;
        }
        break;
      }
      if(*pattern == '}' || *pattern == ']')
        return GLOBERROR("unmatched close brace/bracket", pos,
                         CURLE_URL_MALFORMAT);

      /* only allow \ to escape known "special letters" */
      if(*pattern == '\\' &&
         (*(pattern + 1) == '{' || *(pattern + 1) == '[' ||
          *(pattern + 1) == '}' || *(pattern + 1) == ']') ) {

        /* escape character, skip '\' */
        ++pattern;
        ++pos;
      }
      *buf++ = *pattern++; /* copy character to literal */
      ++pos;
      sublen++;
    }
    if(sublen) {
      /* we got a literal string, add it as a single-item list */
      *buf = '\0';
      res = glob_fixed(glob, glob->glob_buffer, sublen);
    }
    else {
      switch (*pattern) {
      case '\0': /* done  */
        break;

      case '{':
        /* process set pattern */
        pattern++;
        pos++;
        res = glob_set(glob, &pattern, &pos, amount, globindex++);
        break;

      case '[':
        /* process range pattern */
        pattern++;
        pos++;
        res = glob_range(glob, &pattern, &pos, amount, globindex++);
        break;
      }
    }

    if(++glob->size >= GLOB_PATTERN_NUM)
      return GLOBERROR("too many globs", pos, CURLE_URL_MALFORMAT);
  }
  return res;
}

CURLcode glob_url(URLGlob **glob, char *url, unsigned long *urlnum,
                  FILE *error)
{
  /*
   * We can deal with any-size, just make a buffer with the same length
   * as the specified URL!
   */
  URLGlob *glob_expand;
  unsigned long amount = 0;
  char *glob_buffer;
  CURLcode res;

  *glob = NULL;

  glob_buffer = malloc(strlen(url) + 1);
  if(!glob_buffer)
    return CURLE_OUT_OF_MEMORY;
  glob_buffer[0] = 0;

  glob_expand = calloc(1, sizeof(URLGlob));
  if(!glob_expand) {
    Curl_safefree(glob_buffer);
    return CURLE_OUT_OF_MEMORY;
  }
  glob_expand->urllen = strlen(url);
  glob_expand->glob_buffer = glob_buffer;

  res = glob_parse(glob_expand, url, 1, &amount);
  if(!res)
    *urlnum = amount;
  else {
    if(error && glob_expand->error) {
      char text[128];
      const char *t;
      if(glob_expand->pos) {
        snprintf(text, sizeof(text), "%s in column %zu", glob_expand->error,
                 glob_expand->pos);
        t = text;
      }
      else
        t = glob_expand->error;

      /* send error description to the error-stream */
      fprintf(error, "curl: (%d) [globbing] %s\n", res, t);
    }
    /* it failed, we cleanup */
    glob_cleanup(glob_expand);
    *urlnum = 1;
    return res;
  }

  *glob = glob_expand;
  return CURLE_OK;
}

void glob_cleanup(URLGlob* glob)
{
  size_t i;
  int elem;

  for(i = 0; i < glob->size; i++) {
    if((glob->pattern[i].type == UPTSet) &&
       (glob->pattern[i].content.Set.elements)) {
      for(elem = glob->pattern[i].content.Set.size - 1;
          elem >= 0;
          --elem) {
        Curl_safefree(glob->pattern[i].content.Set.elements[elem]);
      }
      Curl_safefree(glob->pattern[i].content.Set.elements);
    }
  }
  Curl_safefree(glob->glob_buffer);
  Curl_safefree(glob);
}

CURLcode glob_next_url(char **globbed, URLGlob *glob)
{
  URLPattern *pat;
  size_t i;
  size_t len;
  size_t buflen = glob->urllen + 1;
  char *buf = glob->glob_buffer;

  *globbed = NULL;

  if(!glob->beenhere)
    glob->beenhere = 1;
  else {
    bool carry = TRUE;

    /* implement a counter over the index ranges of all patterns, starting
       with the rightmost pattern */
    for(i = 0; carry && (i < glob->size); i++) {
      carry = FALSE;
      pat = &glob->pattern[glob->size - 1 - i];
      switch(pat->type) {
      case UPTSet:
        if((pat->content.Set.elements) &&
           (++pat->content.Set.ptr_s == pat->content.Set.size)) {
          pat->content.Set.ptr_s = 0;
          carry = TRUE;
        }
        break;
      case UPTCharRange:
        pat->content.CharRange.ptr_c =
          (char)(pat->content.CharRange.step +
                 (int)((unsigned char)pat->content.CharRange.ptr_c));
        if(pat->content.CharRange.ptr_c > pat->content.CharRange.max_c) {
          pat->content.CharRange.ptr_c = pat->content.CharRange.min_c;
          carry = TRUE;
        }
        break;
      case UPTNumRange:
        pat->content.NumRange.ptr_n += pat->content.NumRange.step;
        if(pat->content.NumRange.ptr_n > pat->content.NumRange.max_n) {
          pat->content.NumRange.ptr_n = pat->content.NumRange.min_n;
          carry = TRUE;
        }
        break;
      default:
        printf("internal error: invalid pattern type (%d)\n", (int)pat->type);
        return CURLE_FAILED_INIT;
      }
    }
    if(carry) {         /* first pattern ptr has run into overflow, done! */
      /* TODO: verify if this should actally return CURLE_OK. */
      return CURLE_OK; /* CURLE_OK to match previous behavior */
    }
  }

  for(i = 0; i < glob->size; ++i) {
    pat = &glob->pattern[i];
    switch(pat->type) {
    case UPTSet:
      if(pat->content.Set.elements) {
        snprintf(buf, buflen, "%s",
                 pat->content.Set.elements[pat->content.Set.ptr_s]);
        len = strlen(buf);
        buf += len;
        buflen -= len;
      }
      break;
    case UPTCharRange:
      if(buflen) {
        *buf++ = pat->content.CharRange.ptr_c;
        *buf = '\0';
        buflen--;
      }
      break;
    case UPTNumRange:
      snprintf(buf, buflen, "%0*lu",
               pat->content.NumRange.padlength,
               pat->content.NumRange.ptr_n);
      len = strlen(buf);
      buf += len;
      buflen -= len;
      break;
    default:
      printf("internal error: invalid pattern type (%d)\n", (int)pat->type);
      return CURLE_FAILED_INIT;
    }
  }

  *globbed = strdup(glob->glob_buffer);
  if(!*globbed)
    return CURLE_OUT_OF_MEMORY;

  return CURLE_OK;
}

CURLcode glob_match_url(char **result, char *filename, URLGlob *glob)
{
  char *target;
  size_t allocsize;
  char numbuf[18];
  char *appendthis = NULL;
  size_t appendlen = 0;
  size_t stringlen = 0;

  *result = NULL;

  /* We cannot use the glob_buffer for storage here since the filename may
   * be longer than the URL we use. We allocate a good start size, then
   * we need to realloc in case of need.
   */
  allocsize = strlen(filename) + 1; /* make it at least one byte to store the
                                       trailing zero */
  target = malloc(allocsize);
  if(!target)
    return CURLE_OUT_OF_MEMORY;

  while(*filename) {
    if(*filename == '#' && ISDIGIT(filename[1])) {
      char *ptr = filename;
      unsigned long num = strtoul(&filename[1], &filename, 10);
      URLPattern *pat = NULL;

      if(num < glob->size) {
        unsigned long i;
        num--; /* make it zero based */
        /* find the correct glob entry */
        for(i = 0; i<glob->size; i++) {
          if(glob->pattern[i].globindex == (int)num) {
            pat = &glob->pattern[i];
            break;
          }
        }
      }

      if(pat) {
        switch(pat->type) {
        case UPTSet:
          if(pat->content.Set.elements) {
            appendthis = pat->content.Set.elements[pat->content.Set.ptr_s];
            appendlen =
              strlen(pat->content.Set.elements[pat->content.Set.ptr_s]);
          }
          break;
        case UPTCharRange:
          numbuf[0] = pat->content.CharRange.ptr_c;
          numbuf[1] = 0;
          appendthis = numbuf;
          appendlen = 1;
          break;
        case UPTNumRange:
          snprintf(numbuf, sizeof(numbuf), "%0*lu",
                   pat->content.NumRange.padlength,
                   pat->content.NumRange.ptr_n);
          appendthis = numbuf;
          appendlen = strlen(numbuf);
          break;
        default:
          fprintf(stderr, "internal error: invalid pattern type (%d)\n",
                  (int)pat->type);
          Curl_safefree(target);
          return CURLE_FAILED_INIT;
        }
      }
      else {
        /* #[num] out of range, use the #[num] in the output */
        filename = ptr;
        appendthis = filename++;
        appendlen = 1;
      }
    }
    else {
      appendthis = filename++;
      appendlen = 1;
    }
    if(appendlen + stringlen >= allocsize) {
      char *newstr;
      /* we append a single byte to allow for the trailing byte to be appended
         at the end of this function outside the while() loop */
      allocsize = (appendlen + stringlen) * 2;
      newstr = realloc(target, allocsize + 1);
      if(!newstr) {
        Curl_safefree(target);
        return CURLE_OUT_OF_MEMORY;
      }
      target = newstr;
    }
    memcpy(&target[stringlen], appendthis, appendlen);
    stringlen += appendlen;
  }
  target[stringlen]= '\0';

#if defined(MSDOS) || defined(WIN32)
  {
    char *sanitized;
    SANITIZEcode sc = sanitize_file_name(&sanitized, target,
                                         (SANITIZE_ALLOW_PATH |
                                          SANITIZE_ALLOW_RESERVED));
    Curl_safefree(target);
    if(sc)
      return CURLE_URL_MALFORMAT;
    target = sanitized;
  }
#endif /* MSDOS || WIN32 */

  *result = target;
  return CURLE_OK;
}