aboutsummaryrefslogtreecommitdiff
path: root/lib/formdata.c
blob: bcdb71c11abd5a7d35c0dbb8ece5891ffc2bec0d (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
/*****************************************************************************
 *                                  _   _ ____  _     
 *  Project                     ___| | | |  _ \| |    
 *                             / __| | | | |_) | |    
 *                            | (__| |_| |  _ <| |___ 
 *                             \___|\___/|_| \_\_____|
 *
 *  The contents of this file are subject to the Mozilla Public License
 *  Version 1.0 (the "License"); you may not use this file except in
 *  compliance with the License. You may obtain a copy of the License at
 *  http://www.mozilla.org/MPL/
 *
 *  Software distributed under the License is distributed on an "AS IS"
 *  basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
 *  License for the specific language governing rights and limitations
 *  under the License.
 *
 *  The Original Code is Curl.
 *
 *  The Initial Developer of the Original Code is Daniel Stenberg.
 *
 *  Portions created by the Initial Developer are Copyright (C) 1998.
 *  All Rights Reserved.
 *
 * ------------------------------------------------------------
 * Main author:
 * - Daniel Stenberg <daniel@haxx.se>
 *
 * 	http://curl.haxx.se
 *
 * $Source$
 * $Revision$
 * $Date$
 * $Author$
 * $State$
 * $Locker$
 *
 * ------------------------------------------------------------
 ****************************************************************************/

/*
  Debug the form generator stand-alone by compiling this source file with:

  gcc -DHAVE_CONFIG_H -I../ -g -D_FORM_DEBUG -o formdata -I../include formdata.c

  run the 'formdata' executable and make sure the output is ok!

  try './formdata "name=Daniel" "poo=noo" "foo=bar"' and similarly

 */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>

#include <time.h>

#include "setup.h"
#include <curl/curl.h>
#include "formdata.h"

#include "strequal.h"

/* Length of the random boundary string. The risk of this being used
   in binary data is very close to zero, 64^32 makes
   6277101735386680763835789423207666416102355444464034512896
   combinations... */
#define BOUNDARY_LENGTH 32

/* What kind of Content-Type to use on un-specified files with unrecognized
   extensions. */
#define HTTPPOST_CONTENTTYPE_DEFAULT "text/plain"

/* This is a silly duplicate of the function in main.c to enable this source
   to compile stand-alone for better debugging */
static void GetStr(char **string,
		   char *value)
{
  if(*string)
    free(*string);
  *string = strdup(value);
}

/***************************************************************************
 *
 * FormParse()
 *	
 * Reads a 'name=value' paramter and builds the appropriate linked list.
 *
 * Specify files to upload with 'name=@filename'. Supports specified
 * given Content-Type of the files. Such as ';type=<content-type>'.
 *
 * You may specify more than one file for a single name (field). Specify
 * multiple files by writing it like:
 *
 * 'name=@filename,filename2,filename3'
 *
 * If you want content-types specified for each too, write them like:
 *
 * 'name=@filename;type=image/gif,filename2,filename3'
 *
 ***************************************************************************/

int curl_formparse(char *input,
                   struct HttpPost **httppost,
                   struct HttpPost **last_post)
{
  return FormParse(input, httppost, last_post);
}

#define FORM_FILE_SEPARATOR ','
#define FORM_TYPE_SEPARATOR ';'

int FormParse(char *input,
	      struct HttpPost **httppost,
	      struct HttpPost **last_post)
{
  /* nextarg MUST be a string in the format 'name=contents' and we'll
     build a linked list with the info */
  char name[256];
  char contents[1024]="";
  char major[128];
  char minor[128];
  long flags = 0;
  char *contp;
  char *type = NULL;
  char *prevtype = NULL;
  char *sep;
  char *sep2;
  struct HttpPost *post;
  struct HttpPost *subpost; /* a sub-node */
  unsigned int i;

  if(1 <= sscanf(input, "%255[^ =] = %1023[^\n]", name, contents)) {
    /* the input was using the correct format */
    contp = contents;

    if('@' == contp[0]) {
      /* we use the @-letter to indicate file name(s) */
      
      flags = HTTPPOST_FILENAME;
      contp++;

      post=NULL;

      do {
	/* since this was a file, it may have a content-type specifier
	   at the end too */

	sep=strchr(contp, FORM_TYPE_SEPARATOR);
	sep2=strchr(contp, FORM_FILE_SEPARATOR);

	/* pick the closest */
	if(sep2 && (sep2 < sep)) {
	  sep = sep2;

	  /* no type was specified! */
	}
	if(sep) {

	  /* if we got here on a comma, don't do much */
	  if(FORM_FILE_SEPARATOR != *sep)
	    type = strstr(sep+1, "type=");
	  else
	    type=NULL;

	  *sep=0; /* terminate file name at separator */

	  if(type) {
	    type += strlen("type=");
	    
	    if(2 != sscanf(type, "%127[^/]/%127[^,\n]",
			   major, minor)) {
	      fprintf(stderr, "Illegally formatted content-type field!\n");
	      return 2; /* illegal content-type syntax! */
	    }
	    /* now point beyond the content-type specifier */
	    sep = type + strlen(major)+strlen(minor)+1;

	    /* find the following comma */
	    sep=strchr(sep, FORM_FILE_SEPARATOR);
	  }
	}
	else {
	  type=NULL;
	  sep=strchr(contp, FORM_FILE_SEPARATOR);
	}
	if(sep) {
	  /* the next file name starts here */
	  *sep =0;
	  sep++;
	}
	if(!type) {
	  /*
	   * No type was specified, we scan through a few well-known
	   * extensions and pick the first we match!
	   */
	  struct ContentType {
	    char *extension;
	    char *type;
	  };
	  static struct ContentType ctts[]={
	    {".gif",  "image/gif"},
	    {".jpg",  "image/jpeg"},
	    {".jpeg", "image/jpeg"},
	    {".txt",  "text/plain"},
	    {".html", "text/plain"}
	  };

	  if(prevtype)
	    /* default to the previously set/used! */
	    type = prevtype;
	  else
	    /* It seems RFC1867 defines no Content-Type to default to
	       text/plain so we don't actually need to set this: */
	    type = HTTPPOST_CONTENTTYPE_DEFAULT;

	  for(i=0; i<sizeof(ctts)/sizeof(ctts[0]); i++) {
	    if(strlen(contp) >= strlen(ctts[i].extension)) {
	      if(strequal(contp +
			  strlen(contp) - strlen(ctts[i].extension),
			  ctts[i].extension)) {
		type = ctts[i].type;
		break;
	      }	      
	    }
	  }
	  /* we have a type by now */
	}

	if(NULL == post) {
	  /* For the first file name, we allocate and initiate the main list
	     node */

	  post = (struct HttpPost *)malloc(sizeof(struct HttpPost));
	  if(post) {
	    memset(post, 0, sizeof(struct HttpPost));
	    GetStr(&post->name, name);      /* get the name */
	    GetStr(&post->contents, contp); /* get the contents */
	    post->flags = flags;
	    if(type) {
	      GetStr(&post->contenttype, type); /* get type */
	      prevtype=post->contenttype; /* point to the allocated string! */
	    }
	    /* make the previous point to this */
	    if(*last_post)
	      (*last_post)->next = post;
	    else
	      (*httppost) = post;

	    (*last_post) = post;	  
	  }

	}
	else {
	  /* we add a file name to the previously allocated node, known as
             'post' now */
	  subpost =(struct HttpPost *)malloc(sizeof(struct HttpPost));
	  if(subpost) {
	     memset(subpost, 0, sizeof(struct HttpPost));
	     GetStr(&subpost->name, name);      /* get the name */
	     GetStr(&subpost->contents, contp); /* get the contents */
	     subpost->flags = flags;
	     if(type) {
	       GetStr(&subpost->contenttype, type); /* get type */
	       prevtype=subpost->contenttype; /* point to the allocated string! */
	     }
	     /* now, point our 'more' to the original 'more' */
	     subpost->more = post->more;

	     /* then move the original 'more' to point to ourselves */
	     post->more = subpost;	     
	  }
	}
	contp = sep; /* move the contents pointer to after the separator */
      } while(sep && *sep); /* loop if there's another file name */
    }
    else {
      post = (struct HttpPost *)malloc(sizeof(struct HttpPost));
      if(post) {
	memset(post, 0, sizeof(struct HttpPost));
	GetStr(&post->name, name);      /* get the name */
	GetStr(&post->contents, contp); /* get the contents */
	post->flags = 0;

	/* make the previous point to this */
	if(*last_post)
	  (*last_post)->next = post;
	else
	  (*httppost) = post;

	(*last_post) = post;	  
      }

    }

  }
  else {
    fprintf(stderr, "Illegally formatted input field!\n");
    return 1;
  }
  return 0;
}

static int AddFormData(struct FormData **formp,
			void *line,
			long length)
{
  struct FormData *newform = (struct FormData *)
    malloc(sizeof(struct FormData));
  newform->next = NULL;

  /* we make it easier for plain strings: */
  if(!length)
    length = strlen((char *)line);

  newform->line = (char *)malloc(length+1);
  memcpy(newform->line, line, length+1);
  newform->length = length;
  newform->line[length]=0; /* zero terminate for easier debugging */
  
  if(*formp) {
    (*formp)->next = newform;
    *formp = newform;
  }
  else
    *formp = newform;

  return length;
}


static int AddFormDataf(struct FormData **formp,
			 char *fmt, ...)
{
  char s[1024];
  va_list ap;
  va_start(ap, fmt);
  vsprintf(s, fmt, ap);
  va_end(ap);

  return AddFormData(formp, s, 0);
}


char *MakeFormBoundary(void)
{
  char *retstring;
  static int randomizer=0; /* this is just so that two boundaries within
			      the same form won't be identical */
  int i;

  static char table64[]=
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

  retstring = (char *)malloc(BOUNDARY_LENGTH);

  if(!retstring)
    return NULL; /* failed */

  srand(time(NULL)+randomizer++); /* seed */

  strcpy(retstring, "curl"); /* bonus commercials 8*) */

  for(i=4; i<(BOUNDARY_LENGTH-1); i++) {
    retstring[i] = table64[rand()%64];
  }
  retstring[BOUNDARY_LENGTH-1]=0; /* zero terminate */

  return retstring;
}
 

void FormFree(struct FormData *form)
{
  struct FormData *next;
  do {
    next=form->next;  /* the following form line */
    free(form->line); /* free the line */
    free(form);       /* free the struct */

  } while((form=next)); /* continue */
}

struct FormData *getFormData(struct HttpPost *post,
			     int *sizep)
{
  struct FormData *form = NULL;
  struct FormData *firstform;

  struct HttpPost *file;

  int size =0;
  char *boundary;
  char *fileboundary=NULL;

  if(!post)
    return NULL; /* no input => no output! */

  boundary = MakeFormBoundary();
  
  /* Make the first line of the output */
  AddFormDataf(&form,
               "Content-Type: multipart/form-data;"
               " boundary=%s\r\n",
               boundary);
  /* we DO NOT count that line since that'll be part of the header! */

  firstform = form;
  
  do {

    /* boundary */
    size += AddFormDataf(&form, "\r\n--%s\r\n", boundary);

    size += AddFormDataf(&form,
			 "Content-Disposition: form-data; name=\"%s\"",
			 post->name);

    if(post->more) {
      /* If used, this is a link to more file names, we must then do
         the magic to include several files with the same field name */

      fileboundary = MakeFormBoundary();

      size += AddFormDataf(&form,
			   "\r\nContent-Type: multipart/mixed,"
			   " boundary=%s\r\n",
			   fileboundary);
    }

    file = post;

    do {
      if(post->more) {
	/* if multiple-file */
	size += AddFormDataf(&form,
			     "\r\n--%s\r\nContent-Disposition: attachment; filename=\"%s\"",
			     fileboundary, file->contents);
      }
      else if(post->flags & HTTPPOST_FILENAME) {
	size += AddFormDataf(&form,
			     "; filename=\"%s\"",
			     post->contents);
      }
      
      if(file->contenttype) {
	/* we have a specified type */
	size += AddFormDataf(&form,
			     "\r\nContent-Type: %s",
			     file->contenttype);
      }
      if(file->contenttype &&
	 !strnequal("text/", file->contenttype, 5)) {
	/* this is not a text content, mention our binary encoding */
	size += AddFormDataf(&form,
			     "\r\nContent-Transfer-Encoding: binary");
      }


      size += AddFormDataf(&form,
			   "\r\n\r\n");

      if(post->flags & HTTPPOST_FILENAME) {
	/* we should include the contents from the specified file */
	FILE *fileread;
	char buffer[1024];
	int nread;

	fileread = strequal("-", file->contents)?stdin:
          /* binary read for win32 crap */
          fopen(file->contents, "rb");
	if(fileread) {
	  while((nread = fread(buffer, 1, 1024, fileread))) {
	    size += AddFormData(&form,
				buffer,
				nread);
	  }
          if(fileread != stdin)
            fclose(fileread);
	}
	else {
	  size += AddFormDataf(&form, "[File wasn't found by client]");
	}
      }
      else {
	/* include the contents we got */
	size += AddFormDataf(&form,
			     post->contents);
      }
    } while((file = file->more)); /* for each specified file for this field */

    if(post->more) {
      /* this was a multiple-file inclusion, make a termination file
         boundary: */
      size += AddFormDataf(&form,
			   "\r\n--%s--",
			   fileboundary);     
      free(fileboundary);
    }

  } while((post=post->next)); /* for each field */

  /* end-boundary for everything */
  size += AddFormDataf(&form,
		       "\r\n--%s--\r\n",
		       boundary);

  *sizep = size;

  free(boundary);

  return firstform;
}

int FormInit(struct Form *form, struct FormData *formdata )
{
  if(!formdata)
    return 1; /* error */

#if 0  
  struct FormData *lastnode=formdata;

  /* find the last node in the list */
  while(lastnode->next) {
    lastnode = lastnode->next;
  }

  /* Now, make sure that we'll send a nice terminating sequence at the end
   * of the post. We *DONT* add this string to the size of the data since this
   * is actually AFTER the data. */
  AddFormDataf(&lastnode, "\r\n\r\n");
#endif
  form->data = formdata;
  form->sent = 0;

  return 0;
}

/* fread() emulation */
int FormReader(char *buffer,
	       size_t size,
	       size_t nitems,
	       FILE *mydata)
{
  struct Form *form;
  int wantedsize;
  int gotsize;

  form=(struct Form *)mydata;

  wantedsize = size * nitems;

  if(!form->data)
    return -1; /* nothing, error, empty */

  do {
  
    if( (form->data->length - form->sent ) > wantedsize ) {

      memcpy(buffer, form->data->line + form->sent, wantedsize);

      form->sent += wantedsize;

      return wantedsize;
    }

    memcpy(buffer,
           form->data->line + form->sent,
           gotsize = (form->data->length - form->sent) );

    form->sent = 0;

    form->data = form->data->next; /* advance */

  } while(!gotsize && form->data);
  /* If we got an empty line and we have more data, we proceed to the next
     line immediately to avoid returning zero before we've reached the end.
     This is the bug reported November 22 1999 on curl 6.3. (Daniel) */

  return gotsize;
}


#ifdef _FORM_DEBUG

int main(int argc, char **argv)
{
#if 0
  char *testargs[]={
    "name1 = data in number one",
    "name2 = number two data",
    "test = @upload"
  };
#endif
  int i;
  char *nextarg;
  struct HttpPost *httppost=NULL;
  struct HttpPost *last_post=NULL;
  struct HttpPost *post;
  int size;
  int nread;
  char buffer[4096];

  struct FormData *form;
  struct Form formread;

  for(i=1; i<argc; i++) {

    if( FormParse( argv[i],
		   &httppost,
		   &last_post)) {
      fprintf(stderr, "Illegally formatted input field: '%s'!\n",
	      argv[i]);
      return 1;
    }
  }

  form=getFormData(httppost, &size);

  FormInit(&formread, form);

  while(nread = FormReader(buffer, 1, sizeof(buffer), (FILE *)&formread)) {
    fwrite(buffer, nread, 1, stderr);
  }

  fprintf(stderr, "size: %d\n", size);

  return 0;
}

#endif