aboutsummaryrefslogtreecommitdiff
path: root/lib/url.c
blob: d253fe566c1db060419aa7a6dbb726648559302d (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
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
/*****************************************************************************
 *                                  _   _ ____  _     
 *  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
 *
 * $Source$
 * $Revision$
 * $Date$
 * $Author$
 * $State$
 * $Locker$
 *
 * ------------------------------------------------------------
 ****************************************************************************/

/* -- WIN32 approved -- */
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#include <stdlib.h>
#include <ctype.h>
#include <sys/types.h>
#include <sys/stat.h>

#include <errno.h>

#include "setup.h"

#if defined(WIN32) && !defined(__GNUC__) || defined(__MINGW32__)
#include <winsock.h>
#include <time.h>
#include <io.h>
#else
#ifdef HAVE_SYS_SOCKET_H
#include <sys/socket.h>
#endif
#include <netinet/in.h>
#include <sys/time.h>
#include <sys/resource.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include <netdb.h>
#ifdef HAVE_ARPA_INET_H
#include <arpa/inet.h>
#endif
#ifdef HAVE_NET_IF_H
#include <net/if.h>
#endif
#include <sys/ioctl.h>
#include <signal.h>

#ifdef HAVE_SYS_PARAM_H
#include <sys/param.h>
#endif

#ifdef HAVE_SYS_SELECT_H
#include <sys/select.h>
#endif

#ifndef HAVE_VPRINTF
#error "We can't compile without vprintf() support!"
#endif
#ifndef HAVE_SELECT
#error "We can't compile without select() support!"
#endif
#ifndef HAVE_SOCKET
#error "We can't compile without socket() support!"
#endif

#endif

#include "urldata.h"
#include "netrc.h"

#include "formdata.h"
#include "getenv.h"
#include "base64.h"
#include "ssluse.h"
#include "hostip.h"
#include "if2ip.h"
#include "download.h"
#include "sendf.h"
#include "speedcheck.h"
#include "getpass.h"
#include "progress.h"
#include "cookie.h"
#include "strequal.h"
#include "writeout.h"

/* And now for the protocols */
#include "ftp.h"
#include "dict.h"
#include "telnet.h"
#include "http.h"
#include "file.h"
#include "ldap.h"

#include <curl/types.h>

#define _MPRINTF_REPLACE /* use our functions only */
#include <curl/mprintf.h>

/* -- -- */


CURLcode _urlget(struct UrlData *data);

/* does nothing, returns OK */
CURLcode curl_init(void)
{
  return CURLE_OK;
}

/* does nothing */
void curl_free(void)
{
}

void urlfree(struct UrlData *data, bool totally)
{
#ifdef USE_SSLEAY
  if (data->use_ssl) {
    if(data->ssl) {
      SSL_shutdown(data->ssl);
      SSL_set_connect_state(data->ssl);

      SSL_free (data->ssl);
      data->ssl = NULL;
    }
    if(data->ctx) {
      SSL_CTX_free (data->ctx);
      data->ctx = NULL;
    }
    data->use_ssl = FALSE; /* get back to ordinary socket usage */
  }
#endif /* USE_SSLEAY */

  /* close possibly still open sockets */
  if(-1 != data->secondarysocket) {
    sclose(data->secondarysocket);
    data->secondarysocket = -1;	
  }
  if(-1 != data->firstsocket) {
    sclose(data->firstsocket);
    data->firstsocket=-1;
  }

  if(data->bits.proxystringalloc) {
    data->bits.proxystringalloc=0;
    free(data->proxy);
    data->proxy=NULL;
  }
  

  if(data->ptr_proxyuserpwd) {
    free(data->ptr_proxyuserpwd);
    data->ptr_proxyuserpwd=NULL;
  }
  if(data->ptr_uagent) {
    free(data->ptr_uagent);
    data->ptr_uagent=NULL;
  }
  if(data->ptr_userpwd) {
    free(data->ptr_userpwd);
    data->ptr_userpwd=NULL;
  }
  if(data->ptr_rangeline) {
    free(data->ptr_rangeline);
    data->ptr_rangeline=NULL;
  }
  if(data->ptr_ref) {
    free(data->ptr_ref);
    data->ptr_ref=NULL;
  }
  if(data->ptr_cookie) {
    free(data->ptr_cookie);
    data->ptr_cookie=NULL;
  }
  if(data->ptr_host) {
    free(data->ptr_host);
    data->ptr_host=NULL;
  }

  if(totally) {
    /* we let the switch decide whether we're doing a part or total
       cleanup */

    /* check for allocated [URL] memory to free: */
    if(data->freethis)
      free(data->freethis);

    if(data->headerbuff)
      free(data->headerbuff);

    if(data->free_referer)
      free(data->referer);

    cookie_cleanup(data->cookies);

    free(data);

    /* global cleanup */
    curl_free();
  }
}

CURLcode curl_close(CURL *curl)
{
  struct UrlData *data=(struct UrlData *)curl;
  
  void *protocol = data->proto.generic;

  /* total session cleanup (frees 'data' as well!)*/
  urlfree(data, TRUE);

  if(protocol)
    free(protocol);

  return CURLE_OK;
}

CURLcode curl_open(CURL **curl, char *url)
{
  /* We don't yet support specifying the URL at this point */
  struct UrlData *data;

  /* Very simple start-up: alloc the struct, init it with zeroes and return */
  data = (struct UrlData *)malloc(sizeof(struct UrlData));
  if(data) {
    memset(data, 0, sizeof(struct UrlData));
    data->handle = STRUCT_OPEN;
    data->interf = CURLI_NORMAL; /* normal interface by default */

    /* We do some initial setup here, all those fields that can't be just 0 */

    data-> headerbuff=(char*)malloc(HEADERSIZE);
    if(!data->headerbuff) {
      free(data); /* free the memory again */
      return CURLE_OUT_OF_MEMORY;
    }

    data-> headersize=HEADERSIZE;

#if 0
    /* Let's set some default values: */
    curl_setopt(data, CURLOPT_FILE, stdout); /* default output to stdout */
    curl_setopt(data, CURLOPT_INFILE, stdin);  /* default input from stdin */
    curl_setopt(data, CURLOPT_STDERR, stderr);  /* default stderr to stderr! */
#endif

    data->out = stdout; /* default output to stdout */
    data->in  = stdin;  /* default input from stdin */
    data->err  = stderr;  /* default stderr to stderr */

    data->firstsocket = -1; /* no file descriptor */
    data->secondarysocket = -1; /* no file descriptor */

    /* use fwrite as default function to store output */
    data->fwrite = (size_t (*)(char *, size_t, size_t, FILE *))fwrite;

    /* use fread as default function to read input */
    data->fread = (size_t (*)(char *, size_t, size_t, FILE *))fread;

    data->infilesize = -1; /* we don't know any size */

    data->current_speed = -1; /* init to negative == impossible */

    *curl = data;
    return CURLE_OK;
  }

  /* this is a very serious error */
  return CURLE_OUT_OF_MEMORY;
}

CURLcode curl_setopt(CURL *curl, CURLoption option, ...)
{
  struct UrlData *data = curl;
  va_list param;
  char *cookiefile;

  va_start(param, option);

  switch(option) {
  case CURLOPT_VERBOSE:
    data->bits.verbose = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_HEADER:
    data->bits.http_include_header = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_NOPROGRESS:
    data->bits.hide_progress = va_arg(param, long)?TRUE:FALSE;
    if(data->bits.hide_progress)
      data->progress.flags |= PGRS_HIDE;
    break;
  case CURLOPT_NOBODY:
    data->bits.no_body = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_FAILONERROR:
    data->bits.http_fail_on_error = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_UPLOAD:
    data->bits.upload = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_POST:
    data->bits.http_post = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_FTPLISTONLY:
    data->bits.ftp_list_only = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_FTPAPPEND:
    data->bits.ftp_append = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_NETRC:
    data->bits.use_netrc = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_FOLLOWLOCATION:
    data->bits.http_follow_location = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_FTPASCII:
    data->bits.ftp_ascii = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_PUT:
    data->bits.http_put = va_arg(param, long)?TRUE:FALSE;
    break;
  case CURLOPT_MUTE:
    data->bits.mute = va_arg(param, long)?TRUE:FALSE;
    break;

  case CURLOPT_TIMECONDITION:
    data->timecondition = va_arg(param, long);
    break;

  case CURLOPT_TIMEVALUE:
    data->timevalue = va_arg(param, long);
    break;

  case CURLOPT_SSLVERSION:
    data->ssl_version = va_arg(param, long);
    break;

  case CURLOPT_COOKIEFILE:
    cookiefile = (char *)va_arg(param, void *);
    if(cookiefile) {
      data->cookies = cookie_init(cookiefile);
    }
    break;
  case CURLOPT_WRITEHEADER:
    data->writeheader = (FILE *)va_arg(param, FILE *);
    break;
  case CURLOPT_COOKIE:
    data->cookie = va_arg(param, char *);
    break;
  case CURLOPT_ERRORBUFFER:
    data->errorbuffer = va_arg(param, char *);
    break;
  case CURLOPT_FILE:
    data->out = va_arg(param, FILE *);
    break;
  case CURLOPT_FTPPORT:
    data->ftpport = va_arg(param, char *);
    data->bits.ftp_use_port = data->ftpport?1:0;
    break;
  case CURLOPT_HTTPHEADER:
    data->headers = va_arg(param, struct curl_slist *);
    break;
  case CURLOPT_CUSTOMREQUEST:
    data->customrequest = va_arg(param, char *);
    break;
  case CURLOPT_HTTPPOST:
    data->httppost = va_arg(param, struct HttpPost *);
    data->bits.http_formpost = data->httppost?1:0;
    break;
  case CURLOPT_INFILE:
    data->in = va_arg(param, FILE *);
    break;
  case CURLOPT_INFILESIZE:
    data->infilesize = va_arg(param, long);
    break;
  case CURLOPT_LOW_SPEED_LIMIT:
    data->low_speed_limit=va_arg(param, long);
    break;
  case CURLOPT_LOW_SPEED_TIME:
    data->low_speed_time=va_arg(param, long);
    break;
  case CURLOPT_URL:
    data->url = va_arg(param, char *);
    break;
  case CURLOPT_PORT:
    /* this typecast is used to fool the compiler to NOT warn for a
       "cast from pointer to integer of different size" */
    data->port = (unsigned short)(va_arg(param, long));
    break;
  case CURLOPT_POSTFIELDS:
    data->postfields = va_arg(param, char *);
    break;
  case CURLOPT_REFERER:
    data->referer = va_arg(param, char *);
    data->bits.http_set_referer = (data->referer && *data->referer)?1:0;
    break;
  case CURLOPT_AUTOREFERER:
    data->bits.http_auto_referer = va_arg(param, long)?1:0;
    break;
  case CURLOPT_PROXY:
    data->proxy = va_arg(param, char *);
    data->bits.httpproxy = data->proxy?1:0;
    break;
  case CURLOPT_PROXYPORT:
    data->proxyport = va_arg(param, long);
    break;
  case CURLOPT_TIMEOUT:
    data->timeout = va_arg(param, long);
    break;
  case CURLOPT_USERAGENT:
    data->useragent = va_arg(param, char *);
    break;
  case CURLOPT_USERPWD:
    data->userpwd = va_arg(param, char *);
    data->bits.user_passwd = data->userpwd?1:0;
    break;
  case CURLOPT_POSTQUOTE:
    data->postquote = va_arg(param, struct curl_slist *);
    break;
  case CURLOPT_PROGRESSFUNCTION:
    data->fprogress = va_arg(param, curl_progress_callback);
    data->progress.callback = TRUE; /* no longer internal */
    break;
  case CURLOPT_PROGRESSDATA:
    data->progress_client = va_arg(param, void *);
    break;
  case CURLOPT_PROXYUSERPWD:
    data->proxyuserpwd = va_arg(param, char *);
    data->bits.proxy_user_passwd = data->proxyuserpwd?1:0;
    break;
  case CURLOPT_RANGE:
    data->range = va_arg(param, char *);
    data->bits.set_range = data->range?1:0;
    break;
  case CURLOPT_RESUME_FROM:
    data->resume_from = va_arg(param, long);
    break;
  case CURLOPT_STDERR:
    data->err = va_arg(param, FILE *);
    break;
  case CURLOPT_WRITEFUNCTION:
    data->fwrite = va_arg(param, curl_write_callback);
    break;
  case CURLOPT_WRITEINFO:
    data->writeinfo = va_arg(param, char *);
    break;
  case CURLOPT_READFUNCTION:
    data->fread = va_arg(param, curl_read_callback);
    break;
  case CURLOPT_SSLCERT:
    data->cert = va_arg(param, char *);
    break;
  case CURLOPT_SSLCERTPASSWD:
    data->cert_passwd = va_arg(param, char *);
    break;
  case CURLOPT_CRLF:
    data->crlf = va_arg(param, long);
    break;
  case CURLOPT_QUOTE:
    data->quote = va_arg(param, struct curl_slist *);
    break;
  default:
    /* unknown tag and its companion, just ignore: */
    return CURLE_READ_ERROR; /* correct this */
  }
  return CURLE_OK;
}


/*
 * Read everything until a newline.
 */

int GetLine(int sockfd, char *buf, struct UrlData *data)
{
  int nread;
  int read_rc=1;
  char *ptr;
  ptr=buf;

  /* get us a full line, terminated with a newline */
  for(nread=0;
      (nread<BUFSIZE) && read_rc;
      nread++, ptr++) {
#ifdef USE_SSLEAY
    if (data->use_ssl) {
      read_rc = SSL_read(data->ssl, ptr, 1);
    }
    else {
#endif
      read_rc = sread(sockfd, ptr, 1);
#ifdef USE_SSLEAY
    }
#endif /* USE_SSLEAY */
    if (*ptr == '\n')
      break;
  }
  *ptr=0; /* zero terminate */

  if(data->bits.verbose) {
    fputs("< ", data->err);
    fwrite(buf, 1, nread, data->err);
    fputs("\n", data->err);
  }
  return nread;
}


#ifndef WIN32
#ifndef RETSIGTYPE
#define RETSIGTYPE void
#endif
RETSIGTYPE alarmfunc(int signal)
{
  /* this is for "-ansi -Wall -pedantic" to stop complaining!   (rabe) */
  (void)signal;
  return;
}
#endif

CURLcode curl_write(CURLconnect *c_conn, char *buf, size_t amount,
                   size_t *n)
{
  struct connectdata *conn = (struct connectdata *)c_conn;
  struct UrlData *data;
  size_t bytes_written;

  if(!n || !conn || (conn->handle != STRUCT_CONNECT))
    return CURLE_FAILED_INIT;
  data = conn->data;

#ifdef USE_SSLEAY
  if (data->use_ssl) {
    bytes_written = SSL_write(data->ssl, buf, amount);
  }
  else {
#endif
    bytes_written = swrite(conn->writesockfd, buf, amount);
#ifdef USE_SSLEAY
  }
#endif /* USE_SSLEAY */

  *n = bytes_written;
  return CURLE_OK;
}

CURLcode curl_read(CURLconnect *c_conn, char *buf, size_t buffersize,
                   size_t *n)
{
  struct connectdata *conn = (struct connectdata *)c_conn;
  struct UrlData *data;
  size_t nread;

  if(!n || !conn || (conn->handle != STRUCT_CONNECT))
    return CURLE_FAILED_INIT;
  data = conn->data;

#ifdef USE_SSLEAY
  if (data->use_ssl) {
    nread = SSL_read (data->ssl, buf, buffersize);
  }
  else {
#endif
    nread = sread (conn->sockfd, buf, buffersize);
#ifdef USE_SSLEAY
  }
#endif /* USE_SSLEAY */
  *n = nread;
  return CURLE_OK;
}

CURLcode curl_disconnect(CURLconnect *c_connect)
{
  struct connectdata *conn = c_connect;

  struct UrlData *data = conn->data;

  free(conn); /* free the connection oriented data */

  /* clean up the sockets and SSL stuff from the previous "round" */
  urlfree(data, FALSE);

  return CURLE_OK;
}

/*
 * NAME curl_connect()
 *
 * DESCRIPTION
 *
 * Connects to the peer server and performs the initial setup. This function
 * writes a connect handle to its second argument that is a unique handle for
 * this connect. This allows multiple connects from the same handle returned
 * by curl_open().
 *
 * EXAMPLE
 *
 * CURLCode result;
 * CURL curl;
 * CURLconnect connect;
 * result = curl_connect(curl, &connect);
 */

CURLcode curl_connect(CURL *curl, CURLconnect **in_connect)
{
  char *tmp;
  char *buf;
  CURLcode result;
  char resumerange[12]="";
  struct UrlData *data = curl;
  struct connectdata *conn;

  /* I believe the longest possible name in a DNS is set to 255 letters, FQDN
     so this should be safe: */
  char hostent_buf[512];

  if(!data || (data->handle != STRUCT_OPEN))
    return CURLE_BAD_FUNCTION_ARGUMENT; /* TBD: make error codes */

  if(!data->url)
    return CURLE_URL_MALFORMAT;

  conn = (struct connectdata *)malloc(sizeof(struct connectdata));
  if(!conn) {
    *in_connect = NULL; /* clear the pointer */
    return CURLE_OUT_OF_MEMORY;
  }
  *in_connect = conn;

  memset(conn, 0, sizeof(struct connectdata));
  conn->handle = STRUCT_CONNECT;

  conn->data = data; /* remember our daddy */
  conn->state = CONN_INIT;

  buf = data->buffer; /* this is our buffer */

#if 0
  signal(SIGALRM, alarmfunc);
#endif

  /* Parse <url> */
  /* We need to parse the url, even when using the proxy, because
   * we will need the hostname and port in case we are trying
   * to SSL connect through the proxy -- and we don't know if we
   * will need to use SSL until we parse the url ...
   */
  if((2 == sscanf(data->url, "%64[^:]://%" URL_MAX_LENGTH_TXT "[^\n]",
                  conn->proto,
                  conn->path)) && strequal(conn->proto, "file")) {
    /* we deal with file://<host>/<path> differently since it
       supports no hostname other than "localhost" and "127.0.0.1",
       which is unique among the protocols specified in RFC 1738 */
    if (strnequal(conn->path, "localhost/", 10) ||
        strnequal(conn->path, "127.0.0.1/", 10))
      /* ... since coincidentally both host strings are of equal length
         otherwise, <host>/ is quietly ommitted */
      strcpy(conn->path, &conn->path[10]);

    strcpy(conn->proto, "file");
  }
  else {
    /* Set default host and default path */
    strcpy(conn->gname, "curl.haxx.se");
    strcpy(conn->path, "/");

    if (2 > sscanf(data->url,
                   "%64[^\n:]://%256[^\n/]%" URL_MAX_LENGTH_TXT "[^\n]",
                   conn->proto, conn->gname, conn->path)) {
      
      /* badly formatted, let's try the browser-style _without_ 'http://' */
      if((1 > sscanf(data->url, "%256[^\n/]%" URL_MAX_LENGTH_TXT "[^\n]",
                     conn->gname, conn->path)) ) {
        failf(data, "<url> malformed");
        return CURLE_URL_MALFORMAT;
      }
      if(strnequal(conn->gname, "FTP", 3)) {
        strcpy(conn->proto, "ftp");
      }
      else if(strnequal(conn->gname, "GOPHER", 6))
        strcpy(conn->proto, "gopher");
#ifdef USE_SSLEAY
      else if(strnequal(conn->gname, "HTTPS", 5))
        strcpy(conn->proto, "https");
#endif /* USE_SSLEAY */
      else if(strnequal(conn->gname, "TELNET", 6))
        strcpy(conn->proto, "telnet");
      else if (strnequal(conn->gname, "DICT", sizeof("DICT")-1))
        strcpy(conn->proto, "DICT");
      else if (strnequal(conn->gname, "LDAP", sizeof("LDAP")-1))
        strcpy(conn->proto, "LDAP");
      else {
        strcpy(conn->proto, "http");
      }

      conn->protocol |= PROT_MISSING; /* not given in URL */
    }
  }


  if(data->bits.user_passwd && !data->bits.use_netrc) {
    if(':' != *data->userpwd) {
      if((1 <= sscanf(data->userpwd, "%127[^:]:%127s",
                      data->user, data->passwd))) {
        /* check for password, if no ask for one */
        if( !data->passwd[0] )
        {
          strncpy(data->passwd, getpass("password: "), sizeof(data->passwd));
        }
      }
    }
    if(!data->user[0]) {
      failf(data, "USER malformat: user name can't be zero length");
      return CURLE_MALFORMAT_USER;
    }
  }

  if(data->bits.proxy_user_passwd) {
    if(':' != *data->proxyuserpwd) {
      if((1 <= sscanf(data->proxyuserpwd, "%127[^:]:%127s",
                      data->proxyuser, data->proxypasswd))) {
        /* check for password, if no ask for one */
        if( !data->proxypasswd[0] )
        {
          strncpy(data->proxypasswd, getpass("proxy password: "), sizeof(data->proxypasswd));
        }
      }
    }
    if(!data->proxyuser[0]) {
      failf(data, " Proxy USER malformat: user name can't be zero length");
      return CURLE_MALFORMAT_USER;
    }
  }

  conn->name = conn->gname;
  conn->ppath = conn->path;
  data->hostname = conn->name;


  if(!data->bits.httpproxy) {
    /* If proxy was not specified, we check for default proxy environment
       variables, to enable i.e Lynx compliance:

       HTTP_PROXY http://some.server.dom:port/
       HTTPS_PROXY http://some.server.dom:port/
       FTP_PROXY http://some.server.dom:port/
       GOPHER_PROXY http://some.server.dom:port/
       NO_PROXY host.domain.dom  (a comma-separated list of hosts which should
       not be proxied, or an asterisk to override all proxy variables)
       ALL_PROXY seems to exist for the CERN www lib. Probably the first to
       check for.
 
       */
    char *no_proxy=GetEnv("NO_PROXY");
    char *proxy=NULL;
    char proxy_env[128];

    if(!no_proxy || !strequal("*", no_proxy)) {
      /* NO_PROXY wasn't specified or it wasn't just an asterisk */
      char *nope;

      nope=no_proxy?strtok(no_proxy, ", "):NULL;
      while(nope) {
        if(strlen(nope) <= strlen(conn->name)) {
          char *checkn=
            conn->name + strlen(conn->name) - strlen(nope);
          if(strnequal(nope, checkn, strlen(nope))) {
            /* no proxy for this host! */
            break;
          }
        }
	nope=strtok(NULL, ", ");
      }
      if(!nope) {
	/* It was not listed as without proxy */
	char *protop = conn->proto;
	char *envp = proxy_env;
	char *prox;

	/* Now, build <PROTOCOL>_PROXY and check for such a one to use */
	while(*protop) {
	  *envp++ = toupper(*protop++);
	}
	/* append _PROXY */
	strcpy(envp, "_PROXY");
#if 0
	infof(data, "DEBUG: checks the environment variable %s\n", proxy_env);
#endif
	/* read the protocol proxy: */
	prox=GetEnv(proxy_env);

	if(prox && *prox) { /* don't count "" strings */
	  proxy = prox; /* use this */
        }
        else
          proxy = GetEnv("ALL_PROXY"); /* default proxy to use */

        if(proxy && *proxy) {
          /* we have a proxy here to set */
          data->proxy = proxy;
          data->bits.proxystringalloc=1; /* this needs to be freed later */
          data->bits.httpproxy=1;
        }
      } /* if (!nope) - it wasn't specfied non-proxy */
    } /* NO_PROXY wasn't specified or '*' */
    if(no_proxy)
      free(no_proxy);
  } /* if not using proxy */

  if((conn->protocol&PROT_MISSING) && data->bits.httpproxy ) {
    /* We're guessing prefixes here and since we're told to use a proxy, we
       need to add the protocol prefix to the URL string before we continue!
       */
    char *reurl;

    reurl = maprintf("%s://%s", conn->proto, data->url);

    if(!reurl)
      return CURLE_OUT_OF_MEMORY;

    data->url = reurl;
    if(data->freethis)
      free(data->freethis);
    data->freethis = reurl;

    conn->protocol &= ~PROT_MISSING; /* switch that one off again */
  }

  /* RESUME on a HTTP page is a tricky business. First, let's just check that
     'range' isn't used, then set the range parameter and leave the resume as
     it is to inform about this situation for later use. We will then
     "attempt" to resume, and if we're talking to a HTTP/1.1 (or later)
     server, we will get the document resumed. If we talk to a HTTP/1.0
     server, we just fail since we can't rewind the file writing from within
     this function. */
  if(data->resume_from) {
    if(!data->bits.set_range) {
      /* if it already was in use, we just skip this */
      sprintf(resumerange, "%d-", data->resume_from);
      data->range=resumerange; /* tell ourselves to fetch this range */
      data->bits.set_range = 1; /* switch on range usage */
    }
  }


  if(data->timeout) {
    /* We set the timeout on the connection/resolving phase first, separately
       from the download/upload part to allow a maximum time on everything */
    myalarm(data->timeout); /* this sends a signal when the timeout fires
			       off, and that will abort system calls */
  }

  /*
   * Hmm, if we are using a proxy, then we can skip the GOPHER and the
   * FTP steps, although we cannot skip the HTTPS step (since the proxy
   * works differently, depending on whether its SSL or not).
   */

  if (strequal(conn->proto, "HTTP")) {
    if(!data->port)
      data->port = PORT_HTTP;
    data->remote_port = PORT_HTTP;
    conn->protocol |= PROT_HTTP;
    conn->curl_do = http;
    conn->curl_done = http_done;
    conn->curl_close = http_close;
  }
  else if (strequal(conn->proto, "HTTPS")) {
#ifdef USE_SSLEAY
    if(!data->port)
      data->port = PORT_HTTPS;
    data->remote_port = PORT_HTTPS;
    conn->protocol |= PROT_HTTP;
    conn->protocol |= PROT_HTTPS;

    conn->curl_do = http;
    conn->curl_done = http_done;
    conn->curl_connect = http_connect;
    conn->curl_close = http_close;

#else /* USE_SSLEAY */
    failf(data, "SSL is disabled, https: not supported!");
    return CURLE_UNSUPPORTED_PROTOCOL;
#endif /* !USE_SSLEAY */
  }
  else if (strequal(conn->proto, "GOPHER")) {
    if(!data->port)
      data->port = PORT_GOPHER;
    data->remote_port = PORT_GOPHER;
    /* Skip /<item-type>/ in path if present */
    if (isdigit((int)conn->path[1])) {
      conn->ppath = strchr(&conn->path[1], '/');
      if (conn->ppath == NULL)
	conn->ppath = conn->path;
      }
    conn->protocol |= PROT_GOPHER;
    conn->curl_do = http;
    conn->curl_done = http_done;
    conn->curl_close = http_close;
  }
  else if(strequal(conn->proto, "FTP")) {
    char *type;
    if(!data->port)
      data->port = PORT_FTP;
    data->remote_port = PORT_FTP;
    conn->protocol |= PROT_FTP;

    if(data->bits.httpproxy) {
      conn->curl_do = http;
      conn->curl_done = http_done;
      conn->curl_close = http_close;
    }
    else {
      conn->curl_do = ftp;
      conn->curl_done = ftp_done;
      conn->curl_connect = ftp_connect;
    }

    conn->ppath++; /* don't include the initial slash */

    /* FTP URLs support an extension like ";type=<typecode>" that
       we'll try to get now! */
    type=strstr(conn->ppath, ";type=");
    if(!type) {
      type=strstr(conn->gname, ";type=");
    }
    if(type) {
      char command;
      *type=0;
      command = toupper(type[6]);
      switch(command) {
      case 'A': /* ASCII mode */
	data->bits.ftp_ascii = 1;
	break;
      case 'D': /* directory mode */
	data->bits.ftp_list_only = 1;
	break;
      case 'I': /* binary mode */
      default:
	/* switch off ASCII */
	data->bits.ftp_ascii = 0;
	break;
      }
    }
  }
  else if(strequal(conn->proto, "TELNET")) {
    /* telnet testing factory */
    conn->protocol |= PROT_TELNET;
    if(!data->port)
      data->port = PORT_TELNET;
    data->remote_port = PORT_TELNET;

    conn->curl_do = telnet;
    conn->curl_done = telnet_done;

  }
  else if (strequal(conn->proto, "DICT")) {
    conn->protocol |= PROT_DICT;
    if(!data->port)
      data->port = PORT_DICT;
    data->remote_port = PORT_DICT;
    conn->curl_do = dict;
    conn->curl_done = dict_done;
  }
  else if (strequal(conn->proto, "LDAP")) {
    conn->protocol |= PROT_LDAP;
    if(!data->port)
      data->port = PORT_LDAP;
    data->remote_port = PORT_LDAP;
    conn->curl_do = ldap;
    conn->curl_done = ldap_done;
  }
  else if (strequal(conn->proto, "FILE")) {
    conn->protocol |= PROT_FILE;

    conn->curl_do = file;
    /* no done() function */
  }

  else {
    failf(data, "Unsupported protocol: %s", conn->proto);
    return CURLE_UNSUPPORTED_PROTOCOL;
  }

  if(data->bits.use_netrc) {
    if(ParseNetrc(data->hostname, data->user, data->passwd)) {
      infof(data, "Couldn't find host %s in the .netrc file, using defaults",
            data->hostname);
    }
    /* weather we failed or not, we don't know which fields that were filled
       in anyway */
    if(!data->user[0])
      strcpy(data->user, CURL_DEFAULT_USER);
    if(!data->passwd[0])
      strcpy(data->passwd, CURL_DEFAULT_PASSWORD);
    if(conn->protocol&PROT_HTTP) {
      data->bits.user_passwd = 1; /* enable user+password */
    }
  }
  else if(!(data->bits.user_passwd) &&
	  (conn->protocol & (PROT_FTP|PROT_HTTP)) ) {
    /* This is a FTP or HTTP URL, and we haven't got the user+password in
       the extra parameter, we will now try to extract the possible
       user+password pair in a string like:
       ftp://user:password@ftp.my.site:8021/README */
    char *ptr=NULL; /* assign to remove possible warnings */
    if(':' == *conn->name) {
      failf(data, "URL malformat: user can't be zero length");
      return CURLE_URL_MALFORMAT_USER;
    }
    if((1 <= sscanf(conn->name, "%127[^:]:%127[^@]",
		    data->user, data->passwd)) &&
       (ptr=strchr(conn->name, '@'))) {
      conn->name = ++ptr;
      data->bits.user_passwd=1; /* enable user+password */
    }
    else {
      strcpy(data->user, CURL_DEFAULT_USER);
      strcpy(data->passwd, CURL_DEFAULT_PASSWORD);
    }
  }

  if(!data->bits.httpproxy) {
    /* If not connecting via a proxy, extract the port from the URL, if it is
     * there, thus overriding any defaults that might have been set above. */
    tmp = strchr(conn->name, ':');
    if (tmp) {
      *tmp++ = '\0';
      data->port = atoi(tmp);
    }
    
    /* Connect to target host right on */
    if(!(conn->hp = GetHost(data, conn->name, hostent_buf, sizeof(hostent_buf)))) {
      failf(data, "Couldn't resolv host '%s'", conn->name);
      return CURLE_COULDNT_RESOLVE_HOST;
    }
  }
  else {
    char *prox_portno;
    char *endofprot;

    /* We need to make a duplicate of the proxy so that we can modify the
       string safely. */
    char *proxydup=strdup(data->proxy);

    /* We use 'proxyptr' to point to the proxy name from now on... */
    char *proxyptr=proxydup;

    if(NULL == proxydup) {
      failf(data, "memory shortage");
      return CURLE_OUT_OF_MEMORY;
    }

    /* we use proxy all right, but we wanna know the remote port for SSL
       reasons */
    tmp = strchr(conn->name, ':');
    if (tmp) {
      *tmp++ = '\0'; /* cut off the name there */
      data->remote_port = atoi(tmp);
    }

    /* Daniel Dec 10, 1998:
       We do the proxy host string parsing here. We want the host name and the
       port name. Accept a protocol:// prefix, even though it should just be
       ignored. */

    /* 1. skip the protocol part if present */
    endofprot=strstr(proxyptr, "://");
    if(endofprot) {
      proxyptr = endofprot+3;
    }

    /* allow user to specify proxy.server.com:1080 if desired */
    prox_portno = strchr (proxyptr, ':');
    if (prox_portno) {
      *prox_portno = 0x0; /* cut off number from host name */
      prox_portno ++;
      /* now set the local port number */
      data->port = atoi(prox_portno);
    }
    else if(data->proxyport) {
      /* None given in the proxy string, then get the default one if it is
         given */
      data->port = data->proxyport;
    }

    /* connect to proxy */
    if(!(conn->hp = GetHost(data, proxyptr, hostent_buf, sizeof(hostent_buf)))) {
      failf(data, "Couldn't resolv proxy '%s'", proxyptr);
      return CURLE_COULDNT_RESOLVE_PROXY;
    }

    free(proxydup); /* free the duplicate pointer and not the modified */
  }
  pgrsTime(data, TIMER_NAMELOOKUP);

  data->firstsocket = socket(AF_INET, SOCK_STREAM, 0);

  memset((char *) &conn->serv_addr, '\0', sizeof(conn->serv_addr));
  memcpy((char *)&(conn->serv_addr.sin_addr),
         conn->hp->h_addr, conn->hp->h_length);
  conn->serv_addr.sin_family = conn->hp->h_addrtype;
  conn->serv_addr.sin_port = htons(data->port);

  if (connect(data->firstsocket,
              (struct sockaddr *) &(conn->serv_addr),
              sizeof(conn->serv_addr)
              ) < 0) {
    switch(errno) {
#ifdef ECONNREFUSED
      /* this should be made nicer */
    case ECONNREFUSED:
      failf(data, "Connection refused");
      break;
#endif
#ifdef EINTR
    case EINTR:
      failf(data, "Connection timeouted");
      break;
#endif
    default:
      failf(data, "Can't connect to server: %d", errno);
      break;
    }
    return CURLE_COULDNT_CONNECT;
  }

  if(data->bits.proxy_user_passwd) {
    char authorization[512];
    sprintf(data->buffer, "%s:%s", data->proxyuser, data->proxypasswd);
    base64Encode(data->buffer, authorization);

    data->ptr_proxyuserpwd = maprintf("Proxy-authorization: Basic %s\015\012",
				      authorization);
  }
  if((conn->protocol&PROT_HTTP) || data->bits.httpproxy) {
    if(data->useragent) {
      data->ptr_uagent = maprintf("User-Agent: %s\015\012", data->useragent);
    }
  }

  if(conn->curl_connect) {
    /* is there a connect() procedure? */
    conn->now = tvnow(); /* set this here for timeout purposes in the
                            connect procedure, it is later set again for the
                            progress meter purpose */
    result = conn->curl_connect(conn);
    if(result != CURLE_OK)
      return result; /* pass back errors */
  }

  pgrsTime(data, TIMER_CONNECT); /* we're connected */

  conn->now = tvnow(); /* time this *after* the connect is done */
  conn->bytecount = 0;
  
  /* Figure out the ip-number and the first host name it shows: */
  {
    struct in_addr in;
    (void) memcpy(&in.s_addr, *conn->hp->h_addr_list, sizeof (in.s_addr));
    infof(data, "Connected to %s (%s)\n", conn->hp->h_name, inet_ntoa(in));
  }

#if 0 /* Kerberos experiements! Beware! Take cover! */
  kerberos_connect(data, name);
#endif

#ifdef __EMX__
  /* 20000330 mgs
   * the check is quite a hack...
   * we're calling _fsetmode to fix the problem with fwrite converting newline
   * characters (you get mangled text files, and corrupted binary files when
   * you download to stdout and redirect it to a file). */

  if ((data->out)->_handle == NULL) {
    _fsetmode(stdout, "b");
  }
#endif

  return CURLE_OK;
}

CURLcode curl_done(CURLconnect *c_connect)
{
  struct connectdata *conn = c_connect;
  struct UrlData *data;
  CURLcode result;

  if(!conn || (conn->handle!= STRUCT_CONNECT)) {
    return CURLE_BAD_FUNCTION_ARGUMENT;
  }
  if(conn->state != CONN_DO) {
    /* This can only be called after a curl_do() */
    return CURLE_BAD_CALLING_ORDER;
  }
  data = conn->data;

  /* this calls the protocol-specific function pointer previously set */
  if(conn->curl_done)
    result = conn->curl_done(conn);
  else
    result = CURLE_OK;

  pgrsDone(data); /* done with the operation */

  conn->state = CONN_DONE;

  return result;
}

CURLcode curl_do(CURLconnect *in_conn)
{
  struct connectdata *conn = in_conn;
  CURLcode result;

  if(!conn || (conn->handle!= STRUCT_CONNECT)) {
    return CURLE_BAD_FUNCTION_ARGUMENT;
  }
  if(conn->state != CONN_INIT) {
    return CURLE_BAD_CALLING_ORDER;
  }

  if(conn->curl_do) {
    /* generic protocol-specific function pointer set in curl_connect() */
    result = conn->curl_do(conn);
    if(result) {
      conn->state = CONN_ERROR;
      return result;
    }
  }

  conn->state = CONN_DO; /* we have entered this state */

#if 0
  if(conn->bytecount) {
    double ittook = tvdiff (tvnow(), conn->now);
    infof(data, "%i bytes transfered in %.3lf seconds (%.0lf bytes/sec).\n",
          conn->bytecount, ittook, (double)conn->bytecount/(ittook!=0.0?ittook:1));
  }
#endif
  return CURLE_OK;
}