aboutsummaryrefslogtreecommitdiff
path: root/src/tool_formparse.c
blob: fc5162eed1a6f169989c86dbaf315e3cfd72aa73 (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
/***************************************************************************
 *                                  _   _ ____  _
 *  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"

#include "mime.h"
#include "strcase.h"

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

#include "tool_cfgable.h"
#include "tool_convert.h"
#include "tool_msgs.h"
#include "tool_formparse.h"

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


/*
 * helper function to get a word from form param
 * after call get_parm_word, str either point to string end
 * or point to any of end chars.
 */
static char *get_param_word(char **str, char **end_pos)
{
  char *ptr = *str;
  char *word_begin = NULL;
  char *ptr2;
  char *escape = NULL;
  const char *end_chars = ";,";

  /* the first non-space char is here */
  word_begin = ptr;
  if(*ptr == '"') {
    ++ptr;
    while(*ptr) {
      if(*ptr == '\\') {
        if(ptr[1] == '\\' || ptr[1] == '"') {
          /* remember the first escape position */
          if(!escape)
            escape = ptr;
          /* skip escape of back-slash or double-quote */
          ptr += 2;
          continue;
        }
      }
      if(*ptr == '"') {
        *end_pos = ptr;
        if(escape) {
          /* has escape, we restore the unescaped string here */
          ptr = ptr2 = escape;
          do {
            if(*ptr == '\\' && (ptr[1] == '\\' || ptr[1] == '"'))
              ++ptr;
            *ptr2++ = *ptr++;
          }
          while(ptr < *end_pos);
          *end_pos = ptr2;
        }
        while(*ptr && NULL==strchr(end_chars, *ptr))
          ++ptr;
        *str = ptr;
        return word_begin+1;
      }
      ++ptr;
    }
    /* end quote is missing, treat it as non-quoted. */
    ptr = word_begin;
  }

  while(*ptr && NULL==strchr(end_chars, *ptr))
    ++ptr;
  *str = *end_pos = ptr;
  return word_begin;
}

/* Append slist item and return -1 if failed. */
static int slist_append(struct curl_slist **plist, const char *data)
{
  struct curl_slist *s = curl_slist_append(*plist, data);

  if(!s)
    return -1;

  *plist = s;
  return 0;
}

/* Read headers from a file and append to list. */
static int read_field_headers(struct OperationConfig *config,
                              const char *filename, FILE *fp,
                              struct curl_slist **pheaders)
{
  size_t hdrlen = 0;
  size_t pos = 0;
  int c;
  bool incomment = FALSE;
  int lineno = 1;
  char hdrbuf[999]; /* Max. header length + 1. */

  for(;;) {
    c = getc(fp);
    if(c == EOF || (!pos && !ISSPACE(c))) {
      /* Strip and flush the current header. */
      while(hdrlen && ISSPACE(hdrbuf[hdrlen - 1]))
        hdrlen--;
      if(hdrlen) {
        hdrbuf[hdrlen] = '\0';
        if(slist_append(pheaders, hdrbuf)) {
          fprintf(config->global->errors,
                  "Out of memory for field headers!\n");
          return -1;
        }
        hdrlen = 0;
      }
    }

    switch(c) {
    case EOF:
      if(ferror(fp)) {
        fprintf(config->global->errors,
                "Header file %s read error: %s\n", filename, strerror(errno));
        return -1;
      }
      return 0;    /* Done. */
    case '\r':
      continue;    /* Ignore. */
    case '\n':
      pos = 0;
      incomment = FALSE;
      lineno++;
      continue;
    case '#':
      if(!pos)
        incomment = TRUE;
      break;
    }

    pos++;
    if(!incomment) {
      if(hdrlen == sizeof hdrbuf - 1) {
        warnf(config->global, "File %s line %d: header too long (truncated)\n",
              filename, lineno);
        c = ' ';
      }
      if(hdrlen <= sizeof hdrbuf - 1)
        hdrbuf[hdrlen++] = (char) c;
    }
  }
  /* NOTREACHED */
}

static int get_param_part(struct OperationConfig *config, char **str,
                          char **pdata, char **ptype, char **pfilename,
                          struct curl_slist **pheaders)
{
  char *p = *str;
  char *type = NULL;
  char *filename = NULL;
  char *endpos;
  char *tp;
  char sep;
  char type_major[128] = "";
  char type_minor[128] = "";
  char *endct = NULL;
  struct curl_slist *headers = NULL;

  if(ptype)
    *ptype = NULL;
  if(pfilename)
    *pfilename = NULL;
  if(pheaders)
    *pheaders = NULL;
  while(ISSPACE(*p))
    p++;
  tp = p;
  *pdata = get_param_word(&p, &endpos);
  /* If not quoted, strip trailing spaces. */
  if(*pdata == tp)
    while(endpos > *pdata && ISSPACE(endpos[-1]))
      endpos--;
  sep = *p;
  *endpos = '\0';
  while(sep == ';') {
    while(ISSPACE(*++p))
      ;

    if(!endct && checkprefix("type=", p)) {
      for(p += 5; ISSPACE(*p); p++)
        ;
      /* set type pointer */
      type = p;

      /* verify that this is a fine type specifier */
      if(2 != sscanf(type, "%127[^/ ]/%127[^;, \n]", type_major, type_minor)) {
        warnf(config->global, "Illegally formatted content-type field!\n");
        curl_slist_free_all(headers);
        return -1; /* illegal content-type syntax! */
      }

      /* now point beyond the content-type specifier */
      endpos = type + strlen(type_major) + strlen(type_minor) + 1;
      for(p = endpos; ISSPACE(*p); p++)
        ;
      while(*p && *p != ';' && *p != ',')
        p++;
      endct = p;
      sep = *p;
    }
    else if(checkprefix("filename=", p)) {
      if(endct) {
        *endct = '\0';
        endct = NULL;
      }
      for(p += 9; ISSPACE(*p); p++)
        ;
      tp = p;
      filename = get_param_word(&p, &endpos);
      /* If not quoted, strip trailing spaces. */
      if(filename == tp)
        while(endpos > filename && ISSPACE(endpos[-1]))
          endpos--;
      sep = *p;
      *endpos = '\0';
    }
    else if(checkprefix("headers=", p)) {
      if(endct) {
        *endct = '\0';
        endct = NULL;
      }
      p += 8;
      if(*p == '@' || *p == '<') {
        char *hdrfile;
        FILE *fp;
        /* Read headers from a file. */

        do {
          p++;
        } while(ISSPACE(*p));
        tp = p;
        hdrfile = get_param_word(&p, &endpos);
        /* If not quoted, strip trailing spaces. */
        if(hdrfile == tp)
          while(endpos > hdrfile && ISSPACE(endpos[-1]))
            endpos--;
        sep = *p;
        *endpos = '\0';
        /* TODO: maybe special fopen for VMS? */
        fp = fopen(hdrfile, FOPEN_READTEXT);
        if(!fp)
          warnf(config->global, "Cannot read from %s: %s\n", hdrfile,
                strerror(errno));
        else {
          int i = read_field_headers(config, hdrfile, fp, &headers);

          fclose(fp);
          if(i) {
            curl_slist_free_all(headers);
            return -1;
          }
        }
      }
      else {
        char *hdr;

        while(ISSPACE(*p))
          p++;
        tp = p;
        hdr = get_param_word(&p, &endpos);
        /* If not quoted, strip trailing spaces. */
        if(hdr == tp)
          while(endpos > hdr && ISSPACE(endpos[-1]))
            endpos--;
        sep = *p;
        *endpos = '\0';
        if(slist_append(&headers, hdr)) {
          fprintf(config->global->errors, "Out of memory for field header!\n");
          curl_slist_free_all(headers);
          return -1;
        }
      }
    }
    else {
      /* unknown prefix, skip to next block */
      char *unknown = get_param_word(&p, &endpos);

      sep = *p;
      if(endct)
        endct = p;
      else {
        *endpos = '\0';
         if(*unknown)
           warnf(config->global, "skip unknown form field: %s\n", unknown);
      }
    }
  }

  /* Terminate and strip content type. */
  if(type) {
    if(!endct)
      endct = type + strlen(type);
    while(endct > type && ISSPACE(endct[-1]))
      endct--;
    *endct = '\0';
  }

  if(ptype)
    *ptype = type;
  else if(type)
    warnf(config->global, "Field content type not allowed here: %s\n", type);

  if(pfilename)
    *pfilename = filename;
  else if(filename)
    warnf(config->global,
          "Field file name not allowed here: %s\n", filename);

  if(pheaders)
    *pheaders = headers;
  else if(headers) {
    warnf(config->global,
          "Field headers not allowed here: %s\n", headers->data);
    curl_slist_free_all(headers);
  }

  *str = p;
  return sep & 0xFF;
}

/* Check if file is "-". If so, use a callback to read OUR stdin (to
 * workaround Windows DLL file handle caveat).
 * Else use curl_mime_filedata(). */
static CURLcode file_or_stdin(curl_mimepart *part, const char *file)
{
  CURLcode ret = CURLE_OK;

  if(strcmp(file, "-"))
    return curl_mime_filedata(part, file);

  return curl_mime_data_cb(part, -1, (curl_read_callback) fread,
                           (curl_seek_callback) fseek, NULL, stdin);
}


/***************************************************************************
 *
 * formparse()
 *
 * Reads a 'name=value' parameter and builds the appropriate linked list.
 *
 * Specify files to upload with 'name=@filename', or 'name=@"filename"'
 * in case the filename contain ',' or ';'. Supports specified
 * given Content-Type of the files. Such as ';type=<content-type>'.
 *
 * If literal_value is set, any initial '@' or '<' in the value string
 * loses its special meaning, as does any embedded ';type='.
 *
 * You may specify more than one file for a single name (field). Specify
 * multiple files by writing it like:
 *
 * 'name=@filename,filename2,filename3'
 *
 * or use double-quotes quote the filename:
 *
 * 'name=@"filename","filename2","filename3"'
 *
 * If you want content-types specified for each too, write them like:
 *
 * 'name=@filename;type=image/gif,filename2,filename3'
 *
 * If you want custom headers added for a single part, write them in a separate
 * file and do like this:
 *
 * 'name=foo;headers=@headerfile' or why not
 * 'name=@filemame;headers=@headerfile'
 *
 * To upload a file, but to fake the file name that will be included in the
 * formpost, do like this:
 *
 * 'name=@filename;filename=/dev/null' or quote the faked filename like:
 * 'name=@filename;filename="play, play, and play.txt"'
 *
 * If filename/path contains ',' or ';', it must be quoted by double-quotes,
 * else curl will fail to figure out the correct filename. if the filename
 * tobe quoted contains '"' or '\', '"' and '\' must be escaped by backslash.
 *
 * This function uses curl_formadd to fulfill it's job. Is heavily based on
 * the old curl_formparse code.
 *
 ***************************************************************************/

int formparse(struct OperationConfig *config,
              const char *input,
              curl_mime **mimepost,
              curl_mime **mimecurrent,
              bool literal_value)
{
  /* input MUST be a string in the format 'name=contents' and we'll
     build a linked list with the info */
  char *name = NULL;
  char *contents = NULL;
  char *contp;
  char *data;
  char *type = NULL;
  char *filename = NULL;
  struct curl_slist *headers = NULL;
  curl_mimepart *part = NULL;
  CURLcode res;
  int sep = '\0';

  /* Allocate the main mime structure if needed. */
  if(!*mimepost) {
    *mimepost = curl_mime_init(config->easy);
    if(!*mimepost) {
      warnf(config->global, "curl_mime_init failed!\n");
      return 1;
    }
    *mimecurrent = *mimepost;
  }

  /* Make a copy we can overwrite. */
  contents = strdup(input);
  if(!contents) {
    fprintf(config->global->errors, "out of memory\n");
    return 2;
  }

  /* Scan for the end of the name. */
  contp = strchr(contents, '=');
  if(contp) {
    if(contp > contents)
      name = contents;
    *contp++ = '\0';

    if(*contp == '(' && !literal_value) {
      curl_mime *subparts;

      /* Starting a multipart. */
      sep = get_param_part(config, &contp, &data, &type, NULL, &headers);
      if(sep < 0) {
        Curl_safefree(contents);
        return 3;
      }
      subparts = curl_mime_init(config->easy);
      if(!subparts) {
        warnf(config->global, "curl_mime_init failed!\n");
        curl_slist_free_all(headers);
        Curl_safefree(contents);
        return 4;
      }
      part = curl_mime_addpart(*mimecurrent);
      if(!part) {
        warnf(config->global, "curl_mime_addpart failed!\n");
        curl_mime_free(subparts);
        curl_slist_free_all(headers);
        Curl_safefree(contents);
        return 5;
      }
      if(curl_mime_subparts(part, subparts)) {
        warnf(config->global, "curl_mime_subparts failed!\n");
        curl_mime_free(subparts);
        curl_slist_free_all(headers);
        Curl_safefree(contents);
        return 6;
      }
      *mimecurrent = subparts;
      if(curl_mime_headers(part, headers, 1)) {
        warnf(config->global, "curl_mime_headers failed!\n");
        curl_slist_free_all(headers);
        Curl_safefree(contents);
        return 7;
      }
      if(curl_mime_type(part, type)) {
        warnf(config->global, "curl_mime_type failed!\n");
        Curl_safefree(contents);
        return 8;
      }
    }
    else if(!name && !strcmp(contp, ")") && !literal_value) {
      /* Ending a mutipart. */
      if(*mimecurrent == *mimepost) {
        warnf(config->global, "no multipart to terminate!\n");
        Curl_safefree(contents);
        return 9;
        }
      *mimecurrent = (*mimecurrent)->parent->parent;
    }
    else if('@' == contp[0] && !literal_value) {

      /* we use the @-letter to indicate file name(s) */

      curl_mime *subparts = NULL;

      do {
        /* since this was a file, it may have a content-type specifier
           at the end too, or a filename. Or both. */
        ++contp;
        sep = get_param_part(config,
                             &contp, &data, &type, &filename, &headers);
        if(sep < 0) {
          if(subparts != *mimecurrent)
            curl_mime_free(subparts);
          Curl_safefree(contents);
          return 10;
        }

        /* now contp point to comma or string end.
           If more files to come, make sure we have multiparts. */
        if(!subparts) {
          if(sep != ',')    /* If there is a single file. */
            subparts = *mimecurrent;
          else {
            subparts = curl_mime_init(config->easy);
            if(!subparts) {
              warnf(config->global, "curl_mime_init failed!\n");
              curl_slist_free_all(headers);
              Curl_safefree(contents);
              return 11;
            }
          }
        }

        /* Allocate a part for that file. */
        part = curl_mime_addpart(subparts);
        if(!part) {
          warnf(config->global, "curl_mime_addpart failed!\n");
          if(subparts != *mimecurrent)
            curl_mime_free(subparts);
          curl_slist_free_all(headers);
          Curl_safefree(contents);
          return 12;
        }

        /* Set part headers. */
        if(curl_mime_headers(part, headers, 1)) {
          warnf(config->global, "curl_mime_headers failed!\n");
          if(subparts != *mimecurrent)
            curl_mime_free(subparts);
          curl_slist_free_all(headers);
          Curl_safefree(contents);
          return 13;
        }

        /* Setup file in part. */
        res = file_or_stdin(part, data);
        if(res) {
          warnf(config->global, "setting file %s  failed!\n", data);
          if(res != CURLE_READ_ERROR) {
            if(subparts != *mimecurrent)
              curl_mime_free(subparts);
            Curl_safefree(contents);
            return 14;
          }
        }
        if(filename && curl_mime_filename(part, filename)) {
          warnf(config->global, "curl_mime_filename failed!\n");
          if(subparts != *mimecurrent)
            curl_mime_free(subparts);
          Curl_safefree(contents);
          return 15;
        }
        if(type && curl_mime_type(part, type)) {
          warnf(config->global, "curl_mime_type failed!\n");
          if(subparts != *mimecurrent)
            curl_mime_free(subparts);
          Curl_safefree(contents);
          return 16;
        }

        /* *contp could be '\0', so we just check with the delimiter */
      } while(sep); /* loop if there's another file name */

      /* now we add the multiple files section */
      if(subparts != *mimecurrent) {
        part = curl_mime_addpart(*mimecurrent);
        if(!part) {
          warnf(config->global, "curl_mime_addpart failed!\n");
          curl_mime_free(subparts);
          Curl_safefree(contents);
          return 17;
        }
        if(curl_mime_subparts(part, subparts)) {
          warnf(config->global, "curl_mime_subparts failed!\n");
          curl_mime_free(subparts);
          Curl_safefree(contents);
          return 18;
        }
      }
    }
    else {
        /* Allocate a mime part. */
        part = curl_mime_addpart(*mimecurrent);
        if(!part) {
          warnf(config->global, "curl_mime_addpart failed!\n");
          Curl_safefree(contents);
          return 19;
        }

      if(*contp == '<' && !literal_value) {
        ++contp;
        sep = get_param_part(config,
                             &contp, &data, &type, &filename, &headers);
        if(sep < 0) {
          Curl_safefree(contents);
          return 20;
        }

        /* Set part headers. */
        if(curl_mime_headers(part, headers, 1)) {
          warnf(config->global, "curl_mime_headers failed!\n");
          curl_slist_free_all(headers);
          Curl_safefree(contents);
          return 21;
        }

        /* Setup file in part. */
        res = file_or_stdin(part, data);
        if(res) {
          warnf(config->global, "setting file %s failed!\n", data);
          if(res != CURLE_READ_ERROR) {
            Curl_safefree(contents);
            return 22;
          }
        }
      }
      else {
        if(literal_value)
          data = contp;
        else {
          sep = get_param_part(config,
                               &contp, &data, &type, &filename, &headers);
          if(sep < 0) {
            Curl_safefree(contents);
            return 23;
          }
        }

        /* Set part headers. */
        if(curl_mime_headers(part, headers, 1)) {
          warnf(config->global, "curl_mime_headers failed!\n");
          curl_slist_free_all(headers);
          Curl_safefree(contents);
          return 24;
        }

#ifdef CURL_DOES_CONVERSIONS
        if(convert_to_network(data, strlen(data))) {
          warnf(config->global, "curl_formadd failed!\n");
          Curl_safefree(contents);
          return 25;
        }
#endif

        if(curl_mime_data(part, data, -1)) {
          warnf(config->global, "curl_mime_data failed!\n");
          Curl_safefree(contents);
          return 26;
        }
      }

      if(curl_mime_filename(part, filename)) {
        warnf(config->global, "curl_mime_filename failed!\n");
        Curl_safefree(contents);
        return 27;
      }
      if(curl_mime_type(part, type)) {
        warnf(config->global, "curl_mime_type failed!\n");
        Curl_safefree(contents);
        return 28;
      }

      if(sep) {
        *contp = (char) sep;
        warnf(config->global,
              "garbage at end of field specification: %s\n", contp);
      }
    }

    /* Set part name. */
    if(name && curl_mime_name(part, name, -1)) {
      warnf(config->global, "curl_mime_name failed!\n");
      Curl_safefree(contents);
      return 29;
    }
  }
  else {
    warnf(config->global, "Illegally formatted input field!\n");
    Curl_safefree(contents);
    return 30;
  }
  Curl_safefree(contents);
  return 0;
}