aboutsummaryrefslogtreecommitdiff
path: root/src/urlglob.c
blob: b7c84a7f636741e83c0b7d37a13d72d824320856 (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
/***************************************************************************
 *                                  _   _ ____  _     
 *  Project                     ___| | | |  _ \| |    
 *                             / __| | | | |_) | |    
 *                            | (__| |_| |  _ <| |___ 
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) 1998 - 2003, 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 http://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.
 *
 * $Id$
 ***************************************************************************/

/* client-local setup.h */
#include "setup.h"

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <curl/curl.h>
#include "urlglob.h"

#ifdef CURLDEBUG
#include "../lib/memdebug.h"
#endif

char globerrormsg[80]; /* nasty global error message buffer for globbing */
typedef enum {
  GLOB_OK,
  GLOB_ERROR
} GlobCode;

/*
 * glob_word()
 *
 * Input a full globbed string, set the forth argument to the amount of
 * strings we get out of this. Return GlobCode.
 */
static GlobCode glob_word(URLGlob *, /* object anchor */
                          char *,    /* globbed string */
                          int,       /* position */
                          int *);    /* returned number of strings */

static GlobCode glob_set(URLGlob *glob, char *pattern, int pos, int *amount)
{
  /* processes a set expression with the point behind the opening '{'
     ','-separated elements are collected until the next closing '}'
  */
  char* buf = glob->glob_buffer;
  URLPattern *pat;

  pat = (URLPattern*)&glob->pattern[glob->size / 2];
  /* 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 = (char**)malloc(0);
  ++glob->size;

  while (1) {
    switch (*pattern) {
    case '\0':			/* URL ended while set was still open */
      snprintf(globerrormsg, sizeof(globerrormsg),
               "unmatched brace at pos %d\n", pos);
      return GLOB_ERROR;

    case '{':
    case '[':			/* no nested expressions at this time */
      snprintf(globerrormsg, sizeof(globerrormsg),
               "nested braces not supported at pos %d\n", pos);
      return GLOB_ERROR;

    case ',':
    case '}':				/* set element completed */
      *buf = '\0';
      pat->content.Set.elements =
        realloc(pat->content.Set.elements,
                (pat->content.Set.size + 1) * sizeof(char*));
      if (!pat->content.Set.elements) {
        snprintf(globerrormsg, sizeof(globerrormsg), "out of memory");
        return GLOB_ERROR;
      }
      pat->content.Set.elements[pat->content.Set.size] =
        strdup(glob->glob_buffer);
      ++pat->content.Set.size;

      if (*pattern == '}') {
        /* entire set pattern completed */
        int wordamount;

	/* always check for a literal (may be "") between patterns */
        if(GLOB_ERROR == glob_word(glob, ++pattern, ++pos, &wordamount))
          wordamount=1;
	*amount = pat->content.Set.size * wordamount;

        return GLOB_OK;
      }

      buf = glob->glob_buffer;
      ++pattern;
      ++pos;
      break;

    case ']':				/* illegal closing bracket */
      snprintf(globerrormsg, sizeof(globerrormsg), 
               "illegal pattern at pos %d\n", pos);
      return GLOB_ERROR;

    case '\\':				/* escaped character, skip '\' */
      if (*(buf+1) == '\0') {		/* but no escaping of '\0'! */
        snprintf(globerrormsg, sizeof(globerrormsg), 
                 "illegal pattern at pos %d\n", pos);
	return GLOB_ERROR;
      }
      ++pattern;
      ++pos;				/* intentional fallthrough */

    default:
      *buf++ = *pattern++;		/* copy character to set element */
      ++pos;
    }
  }
  snprintf(globerrormsg, sizeof(globerrormsg), "malformatted pattern");
  return GLOB_ERROR;
}

static GlobCode glob_range(URLGlob *glob, char *pattern, int pos, int *amount)
{
  /* 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;
  char *c;
  int wordamount=1;
  
  pat = (URLPattern*)&glob->pattern[glob->size / 2];
  /* patterns 0,1,2,... correspond to size=1,3,5,... */
  ++glob->size;

  if (isalpha((int)*pattern)) {		/* character range detected */
    pat->type = UPTCharRange;
    if (sscanf(pattern, "%c-%c]", &pat->content.CharRange.min_c,
               &pat->content.CharRange.max_c) != 2 ||
	pat->content.CharRange.min_c >= pat->content.CharRange.max_c ||
	pat->content.CharRange.max_c - pat->content.CharRange.min_c > 'z' - 'a') {
      /* the pattern is not well-formed */ 
      snprintf(globerrormsg, sizeof(globerrormsg),
               "illegal pattern or range specification after pos %d\n", pos);
      return GLOB_ERROR;
    }
    pat->content.CharRange.ptr_c = pat->content.CharRange.min_c;
    /* always check for a literal (may be "") between patterns */

    if(GLOB_ERROR == glob_word(glob, pattern + 4, pos + 4, &wordamount))
      wordamount=1;

    *amount = (pat->content.CharRange.max_c -
               pat->content.CharRange.min_c + 1) *
      wordamount;

    return GLOB_OK;
  }

  if (isdigit((int)*pattern)) { /* numeric range detected */

    pat->type = UPTNumRange;
    pat->content.NumRange.padlength = 0;
    if (sscanf(pattern, "%d-%d]",
               &pat->content.NumRange.min_n,
               &pat->content.NumRange.max_n) != 2 ||
	pat->content.NumRange.min_n >= pat->content.NumRange.max_n) {
      /* the pattern is not well-formed */ 
      snprintf(globerrormsg, sizeof(globerrormsg), 
               "error: illegal pattern or range specification after pos %d\n",
               pos);
      return GLOB_ERROR;
    }
    if (*pattern == '0') {		/* leading zero specified */
      c = pattern;  
      while (isdigit((int)*c++))
	++pat->content.NumRange.padlength; /* padding length is set for all
                                              instances of this pattern */
    }
    pat->content.NumRange.ptr_n = pat->content.NumRange.min_n;
    c = (char*)strchr(pattern, ']'); /* continue after next ']' */
    if(c)
      c++;
    else {
      snprintf(globerrormsg, sizeof(globerrormsg), "missing ']'");
      return GLOB_ERROR; /* missing ']' */
    }

    /* always check for a literal (may be "") between patterns */

    if(GLOB_ERROR == glob_word(glob, c, pos + (c - pattern), &wordamount))
      wordamount = 1;
    
    *amount = (pat->content.NumRange.max_n - 
               pat->content.NumRange.min_n + 1) *
      wordamount;

    return GLOB_OK;
  }
  snprintf(globerrormsg, sizeof(globerrormsg), 
           "illegal character in range specification at pos %d\n", pos);
  return GLOB_ERROR;
}

static GlobCode glob_word(URLGlob *glob, char *pattern, int pos, int *amount)
{
  /* processes a literal string component of a URL
     special characters '{' and '[' branch to set/range processing functions
   */ 
  char* buf = glob->glob_buffer;
  int litindex;

  *amount = 1; /* default is one single string */

  while (*pattern != '\0' && *pattern != '{' && *pattern != '[') {
    if (*pattern == '}' || *pattern == ']')
      return GLOB_ERROR;

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

      /* escape character, skip '\' */
      ++pattern;
      ++pos;
      if (*pattern == '\0')		/* but no escaping of '\0'! */
	return GLOB_ERROR;
    }
    *buf++ = *pattern++;		/* copy character to literal */
    ++pos;
  }
  *buf = '\0';
  litindex = glob->size / 2;
  /* literals 0,1,2,... correspond to size=0,2,4,... */
  glob->literal[litindex] = strdup(glob->glob_buffer);
  ++glob->size;

  switch (*pattern) {
  case '\0':
    return GLOB_OK;			/* singular URL processed  */

  case '{':
    /* process set pattern */
    return glob_set(glob, ++pattern, ++pos, amount);

  case '[':
    /* process range pattern */
    return glob_range(glob, ++pattern, ++pos, amount);
  }

  return GLOB_ERROR; /* something got wrong */
}

int glob_url(URLGlob** glob, char* url, int *urlnum, FILE *error)
{
  /*
   * We can deal with any-size, just make a buffer with the same length
   * as the specified URL!
   */
  URLGlob *glob_expand;
  int amount;
  char *glob_buffer=(char *)malloc(strlen(url)+1);

  if(NULL == glob_buffer) {
    snprintf(globerrormsg, sizeof(globerrormsg), "out of memory");
    return CURLE_OUT_OF_MEMORY;
  }

  glob_expand = (URLGlob*)malloc(sizeof(URLGlob));
  if(NULL == glob_expand) {
    free(glob_buffer);
    snprintf(globerrormsg, sizeof(globerrormsg), "out of memory");
    return CURLE_OUT_OF_MEMORY;
  }
  glob_expand->size = 0;
  glob_expand->urllen = strlen(url);
  glob_expand->glob_buffer = glob_buffer;
  glob_expand->beenhere=0;
  if(GLOB_OK == glob_word(glob_expand, url, 1, &amount))
    *urlnum = amount;
  else {
    /* it failed, we cleanup */
    free(glob_buffer);
    free(glob_expand);
    glob_expand = NULL;
    *urlnum = 1;
    if(error && globerrormsg[0]) {
      /* send error description to the error-stream */
      fprintf(error, "curl: (%d) [globbing] %s\n",
              CURLE_URL_MALFORMAT, globerrormsg);
    }
    return CURLE_URL_MALFORMAT;
  }

  *glob = glob_expand;
  return CURLE_OK;
}

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

  for (i = glob->size - 1; i >= 0; --i) {
    if (!(i & 1)) {	/* even indexes contain literals */
      free(glob->literal[i/2]);
    } else {		/* odd indexes contain sets or ranges */
      if (glob->pattern[i/2].type == UPTSet) {
	for (elem = glob->pattern[i/2].content.Set.size - 1; elem >= 0; --elem) {
	  free(glob->pattern[i/2].content.Set.elements[elem]);
	}
	free(glob->pattern[i/2].content.Set.elements);
      }
    }
  }
  free(glob->glob_buffer);
  free(glob);
}

char *glob_next_url(URLGlob *glob)
{
  char *buf = glob->glob_buffer;
  URLPattern *pat;
  char *lit;
  signed int i;
  int carry;

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

    /* implement a counter over the index ranges of all patterns,
       starting with the rightmost pattern */
    for (i = glob->size / 2 - 1; carry && i >= 0; --i) {
      carry = 0;
      pat = &glob->pattern[i];
      switch (pat->type) {
      case UPTSet:
	if (++pat->content.Set.ptr_s == pat->content.Set.size) {
	  pat->content.Set.ptr_s = 0;
	  carry = 1;
	}
	break;
      case UPTCharRange:
	if (++pat->content.CharRange.ptr_c > pat->content.CharRange.max_c) {
	  pat->content.CharRange.ptr_c = pat->content.CharRange.min_c;
	  carry = 1;
	}
	break;
      case UPTNumRange:
	if (++pat->content.NumRange.ptr_n > pat->content.NumRange.max_n) {
	  pat->content.NumRange.ptr_n = pat->content.NumRange.min_n;
	  carry = 1;
	}
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat->type);
	exit (CURLE_FAILED_INIT);
      }
    }
    if (carry)		/* first pattern ptr has run into overflow, done! */
      return NULL;
  }

  for (i = 0; i < glob->size; ++i) {
    if (!(i % 2)) {			/* every other term (i even) is a literal */
      lit = glob->literal[i/2];
      strcpy(buf, lit);
      buf += strlen(lit);
    }
    else {				/* the rest (i odd) are patterns */
      pat = &glob->pattern[i/2];
      switch(pat->type) {
      case UPTSet:
	strcpy(buf, pat->content.Set.elements[pat->content.Set.ptr_s]);
	buf += strlen(pat->content.Set.elements[pat->content.Set.ptr_s]);
	break;
      case UPTCharRange:
	*buf++ = pat->content.CharRange.ptr_c;
	break;
      case UPTNumRange:
	sprintf(buf, "%0*d", pat->content.NumRange.padlength, pat->content.NumRange.ptr_n); 
        buf += strlen(buf); /* make no sprint() return code assumptions */
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat->type);
	exit (CURLE_FAILED_INIT);
      }
    }
  }
  *buf = '\0';
  return strdup(glob->glob_buffer);
}

char *glob_match_url(char *filename, URLGlob *glob)
{
  char *target;
  URLPattern pat;
  int i;
  int allocsize;
  int stringlen=0;
  char numbuf[18];
  char *appendthis;
  int appendlen;

  /* 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);
  target = malloc(allocsize);
  if(NULL == target)
    return NULL; /* major failure */

  while (*filename != '\0') {
    if (*filename == '#') {
      if (!isdigit((int)*++filename) ||
	  *filename == '0') {		/* only '#1' ... '#9' allowed */
	/* printf("illegal matching expression\n");
           exit(CURLE_URL_MALFORMAT);*/
        continue;
      }
      i = *filename - '1';
      if (i + 1 > glob->size / 2) {
	/*printf("match against nonexisting pattern\n");
          exit(CURLE_URL_MALFORMAT);*/
        continue;
      }
      pat = glob->pattern[i];
      switch (pat.type) {
      case UPTSet:
	appendthis = pat.content.Set.elements[pat.content.Set.ptr_s];
	appendlen = (int)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:
	sprintf(numbuf, "%0*d", pat.content.NumRange.padlength, pat.content.NumRange.ptr_n);
        appendthis = numbuf;
        appendlen = (int)strlen(numbuf);
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat.type);
        return NULL;
      }
      ++filename;
    }
    else {
      appendthis=filename++;
      appendlen=1;
    }
    if(appendlen + stringlen >= allocsize) {
      char *newstr;
      allocsize = (appendlen + stringlen)*2;
      newstr=realloc(target, allocsize);
      if(NULL ==newstr) {
        free(target);
        return NULL;
      }
      target=newstr;
    }
    memcpy(&target[stringlen], appendthis, appendlen);
    stringlen += appendlen;
  }
  target[stringlen]= '\0';
  return target;
}