aboutsummaryrefslogblamecommitdiffstats
path: root/contrib/libs/libxml/uri.c
blob: ccc26aa59428118fe32d04d1dc4825c09e163721 (plain) (tree)
1
2
3
4
5
6
7
8
9
10
11
12
13
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
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466











                                                 
                   









                                                                      
                                                               

































































































































































































































































































                                                                               
                                                        








                                                 
                 

                                






                                       
 
                  
                             









                                     
                                                                     























































































                                                                           
                                                                      

























































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































                                                                                     
                          











































































































































































                                                                              
                      
                                             
                                
                                                  
                                     
                                                  
                                     
                                             
                                         
                                                  
                                              
                                                  
                                              
                     
                              

































































































                                                                            



















                                                            




                                                   


















                                                                          
                                           






                                                                          
                                                




























































































































































                                                                            

                                                              



























































                                                                            

                                                          
























































































































                                                                         
                                                                       




















































































                                                                         







                                                                           
                                               
                                                  
                   
                                                            
                  
                                     








                                                                                
                                    
                      
                                    


                                                                    

                                     
         





                                                 
         
 
























































































                                                                                
                   





























































                                                                             
                            















                                                                             
                                                          

                                                                       
                                                                   



                                          
                                           
            
                                             




                                
                                                  















































                                                                                    
                                                                                      





















                                                                                   
/**
 * uri.c: set of generic URI related routines
 *
 * Reference: RFCs 3986, 2732 and 2373
 *
 * See Copyright for the status of this software.
 *
 * daniel@veillard.com
 */

#define IN_LIBXML
#include "libxml.h"

#include <limits.h>
#include <string.h>

#include <libxml/xmlmemory.h>
#include <libxml/uri.h>
#include <libxml/globals.h>
#include <libxml/xmlerror.h>

/**
 * MAX_URI_LENGTH:
 *
 * The definition of the URI regexp in the above RFC has no size limit
 * In practice they are usually relatively short except for the
 * data URI scheme as defined in RFC 2397. Even for data URI the usual
 * maximum size before hitting random practical limits is around 64 KB
 * and 4KB is usually a maximum admitted limit for proper operations.
 * The value below is more a security limit than anything else and
 * really should never be hit by 'normal' operations
 * Set to 1 MByte in 2012, this is only enforced on output
 */
#define MAX_URI_LENGTH 1024 * 1024

static void
xmlURIErrMemory(const char *extra)
{
    if (extra)
        __xmlRaiseError(NULL, NULL, NULL,
                        NULL, NULL, XML_FROM_URI,
                        XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0,
                        extra, NULL, NULL, 0, 0,
                        "Memory allocation failed : %s\n", extra);
    else
        __xmlRaiseError(NULL, NULL, NULL,
                        NULL, NULL, XML_FROM_URI,
                        XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0,
                        NULL, NULL, NULL, 0, 0,
                        "Memory allocation failed\n");
}

static void xmlCleanURI(xmlURIPtr uri);

/*
 * Old rule from 2396 used in legacy handling code
 * alpha    = lowalpha | upalpha
 */
#define IS_ALPHA(x) (IS_LOWALPHA(x) || IS_UPALPHA(x))


/*
 * lowalpha = "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" | "j" |
 *            "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" | "s" | "t" |
 *            "u" | "v" | "w" | "x" | "y" | "z"
 */

#define IS_LOWALPHA(x) (((x) >= 'a') && ((x) <= 'z'))

/*
 * upalpha = "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" | "J" |
 *           "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" | "S" | "T" |
 *           "U" | "V" | "W" | "X" | "Y" | "Z"
 */
#define IS_UPALPHA(x) (((x) >= 'A') && ((x) <= 'Z'))

#ifdef IS_DIGIT
#undef IS_DIGIT
#endif
/*
 * digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
 */
#define IS_DIGIT(x) (((x) >= '0') && ((x) <= '9'))

/*
 * alphanum = alpha | digit
 */

#define IS_ALPHANUM(x) (IS_ALPHA(x) || IS_DIGIT(x))

/*
 * mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
 */

#define IS_MARK(x) (((x) == '-') || ((x) == '_') || ((x) == '.') ||     \
    ((x) == '!') || ((x) == '~') || ((x) == '*') || ((x) == '\'') ||    \
    ((x) == '(') || ((x) == ')'))

/*
 * unwise = "{" | "}" | "|" | "\" | "^" | "`"
 */

#define IS_UNWISE(p)                                                    \
      (((*(p) == '{')) || ((*(p) == '}')) || ((*(p) == '|')) ||         \
       ((*(p) == '\\')) || ((*(p) == '^')) || ((*(p) == '[')) ||        \
       ((*(p) == ']')) || ((*(p) == '`')))
/*
 * reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | "$" | "," |
 *            "[" | "]"
 */

#define IS_RESERVED(x) (((x) == ';') || ((x) == '/') || ((x) == '?') || \
        ((x) == ':') || ((x) == '@') || ((x) == '&') || ((x) == '=') || \
        ((x) == '+') || ((x) == '$') || ((x) == ',') || ((x) == '[') || \
        ((x) == ']'))

/*
 * unreserved = alphanum | mark
 */

#define IS_UNRESERVED(x) (IS_ALPHANUM(x) || IS_MARK(x))

/*
 * Skip to next pointer char, handle escaped sequences
 */

#define NEXT(p) ((*p == '%')? p += 3 : p++)

/*
 * Productions from the spec.
 *
 *    authority     = server | reg_name
 *    reg_name      = 1*( unreserved | escaped | "$" | "," |
 *                        ";" | ":" | "@" | "&" | "=" | "+" )
 *
 * path          = [ abs_path | opaque_part ]
 */

#define STRNDUP(s, n) (char *) xmlStrndup((const xmlChar *)(s), (n))

/************************************************************************
 *									*
 *                         RFC 3986 parser				*
 *									*
 ************************************************************************/

#define ISA_DIGIT(p) ((*(p) >= '0') && (*(p) <= '9'))
#define ISA_ALPHA(p) (((*(p) >= 'a') && (*(p) <= 'z')) ||		\
                      ((*(p) >= 'A') && (*(p) <= 'Z')))
#define ISA_HEXDIG(p)							\
       (ISA_DIGIT(p) || ((*(p) >= 'a') && (*(p) <= 'f')) ||		\
        ((*(p) >= 'A') && (*(p) <= 'F')))

/*
 *    sub-delims    = "!" / "$" / "&" / "'" / "(" / ")"
 *                     / "*" / "+" / "," / ";" / "="
 */
#define ISA_SUB_DELIM(p)						\
      (((*(p) == '!')) || ((*(p) == '$')) || ((*(p) == '&')) ||		\
       ((*(p) == '(')) || ((*(p) == ')')) || ((*(p) == '*')) ||		\
       ((*(p) == '+')) || ((*(p) == ',')) || ((*(p) == ';')) ||		\
       ((*(p) == '=')) || ((*(p) == '\'')))

/*
 *    gen-delims    = ":" / "/" / "?" / "#" / "[" / "]" / "@"
 */
#define ISA_GEN_DELIM(p)						\
      (((*(p) == ':')) || ((*(p) == '/')) || ((*(p) == '?')) ||         \
       ((*(p) == '#')) || ((*(p) == '[')) || ((*(p) == ']')) ||         \
       ((*(p) == '@')))

/*
 *    reserved      = gen-delims / sub-delims
 */
#define ISA_RESERVED(p) (ISA_GEN_DELIM(p) || (ISA_SUB_DELIM(p)))

/*
 *    unreserved    = ALPHA / DIGIT / "-" / "." / "_" / "~"
 */
#define ISA_UNRESERVED(p)						\
      ((ISA_ALPHA(p)) || (ISA_DIGIT(p)) || ((*(p) == '-')) ||		\
       ((*(p) == '.')) || ((*(p) == '_')) || ((*(p) == '~')))

/*
 *    pct-encoded   = "%" HEXDIG HEXDIG
 */
#define ISA_PCT_ENCODED(p)						\
     ((*(p) == '%') && (ISA_HEXDIG(p + 1)) && (ISA_HEXDIG(p + 2)))

/*
 *    pchar         = unreserved / pct-encoded / sub-delims / ":" / "@"
 */
#define ISA_PCHAR(p)							\
     (ISA_UNRESERVED(p) || ISA_PCT_ENCODED(p) || ISA_SUB_DELIM(p) ||	\
      ((*(p) == ':')) || ((*(p) == '@')))

/**
 * xmlParse3986Scheme:
 * @uri:  pointer to an URI structure
 * @str:  pointer to the string to analyze
 *
 * Parse an URI scheme
 *
 * ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Scheme(xmlURIPtr uri, const char **str) {
    const char *cur;

    if (str == NULL)
	return(-1);

    cur = *str;
    if (!ISA_ALPHA(cur))
	return(2);
    cur++;
    while (ISA_ALPHA(cur) || ISA_DIGIT(cur) ||
           (*cur == '+') || (*cur == '-') || (*cur == '.')) cur++;
    if (uri != NULL) {
	if (uri->scheme != NULL) xmlFree(uri->scheme);
	uri->scheme = STRNDUP(*str, cur - *str);
    }
    *str = cur;
    return(0);
}

/**
 * xmlParse3986Fragment:
 * @uri:  pointer to an URI structure
 * @str:  pointer to the string to analyze
 *
 * Parse the query part of an URI
 *
 * fragment      = *( pchar / "/" / "?" )
 * NOTE: the strict syntax as defined by 3986 does not allow '[' and ']'
 *       in the fragment identifier but this is used very broadly for
 *       xpointer scheme selection, so we are allowing it here to not break
 *       for example all the DocBook processing chains.
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Fragment(xmlURIPtr uri, const char **str)
{
    const char *cur;

    if (str == NULL)
        return (-1);

    cur = *str;

    while ((ISA_PCHAR(cur)) || (*cur == '/') || (*cur == '?') ||
           (*cur == '[') || (*cur == ']') ||
           ((uri != NULL) && (uri->cleanup & 1) && (IS_UNWISE(cur))))
        NEXT(cur);
    if (uri != NULL) {
        if (uri->fragment != NULL)
            xmlFree(uri->fragment);
	if (uri->cleanup & 2)
	    uri->fragment = STRNDUP(*str, cur - *str);
	else
	    uri->fragment = xmlURIUnescapeString(*str, cur - *str, NULL);
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986Query:
 * @uri:  pointer to an URI structure
 * @str:  pointer to the string to analyze
 *
 * Parse the query part of an URI
 *
 * query = *uric
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Query(xmlURIPtr uri, const char **str)
{
    const char *cur;

    if (str == NULL)
        return (-1);

    cur = *str;

    while ((ISA_PCHAR(cur)) || (*cur == '/') || (*cur == '?') ||
           ((uri != NULL) && (uri->cleanup & 1) && (IS_UNWISE(cur))))
        NEXT(cur);
    if (uri != NULL) {
        if (uri->query != NULL)
            xmlFree(uri->query);
	if (uri->cleanup & 2)
	    uri->query = STRNDUP(*str, cur - *str);
	else
	    uri->query = xmlURIUnescapeString(*str, cur - *str, NULL);

	/* Save the raw bytes of the query as well.
	 * See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00114
	 */
	if (uri->query_raw != NULL)
	    xmlFree (uri->query_raw);
	uri->query_raw = STRNDUP (*str, cur - *str);
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986Port:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse a port part and fills in the appropriate fields
 * of the @uri structure
 *
 * port          = *DIGIT
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Port(xmlURIPtr uri, const char **str)
{
    const char *cur = *str;
    int port = 0;

    if (ISA_DIGIT(cur)) {
	while (ISA_DIGIT(cur)) {
            int digit = *cur - '0';

            if (port > INT_MAX / 10)
                return(1);
            port *= 10;
            if (port > INT_MAX - digit)
                return(1);
	    port += digit;

	    cur++;
	}
	if (uri != NULL)
	    uri->port = port;
	*str = cur;
	return(0);
    }
    return(1);
}

/**
 * xmlParse3986Userinfo:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an user information part and fills in the appropriate fields
 * of the @uri structure
 *
 * userinfo      = *( unreserved / pct-encoded / sub-delims / ":" )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Userinfo(xmlURIPtr uri, const char **str)
{
    const char *cur;

    cur = *str;
    while (ISA_UNRESERVED(cur) || ISA_PCT_ENCODED(cur) ||
           ISA_SUB_DELIM(cur) || (*cur == ':'))
	NEXT(cur);
    if (*cur == '@') {
	if (uri != NULL) {
	    if (uri->user != NULL) xmlFree(uri->user);
	    if (uri->cleanup & 2)
		uri->user = STRNDUP(*str, cur - *str);
	    else
		uri->user = xmlURIUnescapeString(*str, cur - *str, NULL);
	}
	*str = cur;
	return(0);
    }
    return(1);
}

/**
 * xmlParse3986DecOctet:
 * @str:  the string to analyze
 *
 *    dec-octet     = DIGIT                 ; 0-9
 *                  / %x31-39 DIGIT         ; 10-99
 *                  / "1" 2DIGIT            ; 100-199
 *                  / "2" %x30-34 DIGIT     ; 200-249
 *                  / "25" %x30-35          ; 250-255
 *
 * Skip a dec-octet.
 *
 * Returns 0 if found and skipped, 1 otherwise
 */
static int
xmlParse3986DecOctet(const char **str) {
    const char *cur = *str;

    if (!(ISA_DIGIT(cur)))
        return(1);
    if (!ISA_DIGIT(cur+1))
	cur++;
    else if ((*cur != '0') && (ISA_DIGIT(cur + 1)) && (!ISA_DIGIT(cur+2)))
	cur += 2;
    else if ((*cur == '1') && (ISA_DIGIT(cur + 1)) && (ISA_DIGIT(cur + 2)))
	cur += 3;
    else if ((*cur == '2') && (*(cur + 1) >= '0') &&
	     (*(cur + 1) <= '4') && (ISA_DIGIT(cur + 2)))
	cur += 3;
    else if ((*cur == '2') && (*(cur + 1) == '5') &&
	     (*(cur + 2) >= '0') && (*(cur + 1) <= '5'))
	cur += 3;
    else
        return(1);
    *str = cur;
    return(0);
}
/**
 * xmlParse3986Host:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an host part and fills in the appropriate fields
 * of the @uri structure
 *
 * host          = IP-literal / IPv4address / reg-name
 * IP-literal    = "[" ( IPv6address / IPvFuture  ) "]"
 * IPv4address   = dec-octet "." dec-octet "." dec-octet "." dec-octet
 * reg-name      = *( unreserved / pct-encoded / sub-delims )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Host(xmlURIPtr uri, const char **str)
{
    const char *cur = *str;
    const char *host;

    host = cur;
    /*
     * IPv6 and future addressing scheme are enclosed between brackets
     */
    if (*cur == '[') {
        cur++;
	while ((*cur != ']') && (*cur != 0))
	    cur++;
	if (*cur != ']')
	    return(1);
	cur++;
	goto found;
    }
    /*
     * try to parse an IPv4
     */
    if (ISA_DIGIT(cur)) {
        if (xmlParse3986DecOctet(&cur) != 0)
	    goto not_ipv4;
	if (*cur != '.')
	    goto not_ipv4;
	cur++;
        if (xmlParse3986DecOctet(&cur) != 0)
	    goto not_ipv4;
	if (*cur != '.')
	    goto not_ipv4;
        if (xmlParse3986DecOctet(&cur) != 0)
	    goto not_ipv4;
	if (*cur != '.')
	    goto not_ipv4;
        if (xmlParse3986DecOctet(&cur) != 0)
	    goto not_ipv4;
	goto found;
not_ipv4:
        cur = *str;
    }
    /*
     * then this should be a hostname which can be empty
     */
    while (ISA_UNRESERVED(cur) || ISA_PCT_ENCODED(cur) || ISA_SUB_DELIM(cur))
        NEXT(cur);
found:
    if (uri != NULL) {
	if (uri->authority != NULL) xmlFree(uri->authority);
	uri->authority = NULL;
	if (uri->server != NULL) xmlFree(uri->server);
	if (cur != host) {
	    if (uri->cleanup & 2)
		uri->server = STRNDUP(host, cur - host);
	    else
		uri->server = xmlURIUnescapeString(host, cur - host, NULL);
	} else
	    uri->server = NULL;
    }
    *str = cur;
    return(0);
}

/**
 * xmlParse3986Authority:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an authority part and fills in the appropriate fields
 * of the @uri structure
 *
 * authority     = [ userinfo "@" ] host [ ":" port ]
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Authority(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;
    /*
     * try to parse an userinfo and check for the trailing @
     */
    ret = xmlParse3986Userinfo(uri, &cur);
    if ((ret != 0) || (*cur != '@'))
        cur = *str;
    else
        cur++;
    ret = xmlParse3986Host(uri, &cur);
    if (ret != 0) return(ret);
    if (*cur == ':') {
        cur++;
        ret = xmlParse3986Port(uri, &cur);
	if (ret != 0) return(ret);
    }
    *str = cur;
    return(0);
}

/**
 * xmlParse3986Segment:
 * @str:  the string to analyze
 * @forbid: an optional forbidden character
 * @empty: allow an empty segment
 *
 * Parse a segment and fills in the appropriate fields
 * of the @uri structure
 *
 * segment       = *pchar
 * segment-nz    = 1*pchar
 * segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
 *               ; non-zero-length segment without any colon ":"
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986Segment(const char **str, char forbid, int empty)
{
    const char *cur;

    cur = *str;
    if (!ISA_PCHAR(cur)) {
        if (empty)
	    return(0);
	return(1);
    }
    while (ISA_PCHAR(cur) && (*cur != forbid))
        NEXT(cur);
    *str = cur;
    return (0);
}

/**
 * xmlParse3986PathAbEmpty:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an path absolute or empty and fills in the appropriate fields
 * of the @uri structure
 *
 * path-abempty  = *( "/" segment )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986PathAbEmpty(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;

    while (*cur == '/') {
        cur++;
	ret = xmlParse3986Segment(&cur, 0, 1);
	if (ret != 0) return(ret);
    }
    if (uri != NULL) {
	if (uri->path != NULL) xmlFree(uri->path);
        if (*str != cur) {
            if (uri->cleanup & 2)
                uri->path = STRNDUP(*str, cur - *str);
            else
                uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
        } else {
            uri->path = NULL;
        }
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986PathAbsolute:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an path absolute and fills in the appropriate fields
 * of the @uri structure
 *
 * path-absolute = "/" [ segment-nz *( "/" segment ) ]
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986PathAbsolute(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;

    if (*cur != '/')
        return(1);
    cur++;
    ret = xmlParse3986Segment(&cur, 0, 0);
    if (ret == 0) {
	while (*cur == '/') {
	    cur++;
	    ret = xmlParse3986Segment(&cur, 0, 1);
	    if (ret != 0) return(ret);
	}
    }
    if (uri != NULL) {
	if (uri->path != NULL) xmlFree(uri->path);
        if (cur != *str) {
            if (uri->cleanup & 2)
                uri->path = STRNDUP(*str, cur - *str);
            else
                uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
        } else {
            uri->path = NULL;
        }
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986PathRootless:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an path without root and fills in the appropriate fields
 * of the @uri structure
 *
 * path-rootless = segment-nz *( "/" segment )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986PathRootless(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;

    ret = xmlParse3986Segment(&cur, 0, 0);
    if (ret != 0) return(ret);
    while (*cur == '/') {
        cur++;
	ret = xmlParse3986Segment(&cur, 0, 1);
	if (ret != 0) return(ret);
    }
    if (uri != NULL) {
	if (uri->path != NULL) xmlFree(uri->path);
        if (cur != *str) {
            if (uri->cleanup & 2)
                uri->path = STRNDUP(*str, cur - *str);
            else
                uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
        } else {
            uri->path = NULL;
        }
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986PathNoScheme:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an path which is not a scheme and fills in the appropriate fields
 * of the @uri structure
 *
 * path-noscheme = segment-nz-nc *( "/" segment )
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986PathNoScheme(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;

    ret = xmlParse3986Segment(&cur, ':', 0);
    if (ret != 0) return(ret);
    while (*cur == '/') {
        cur++;
	ret = xmlParse3986Segment(&cur, 0, 1);
	if (ret != 0) return(ret);
    }
    if (uri != NULL) {
	if (uri->path != NULL) xmlFree(uri->path);
        if (cur != *str) {
            if (uri->cleanup & 2)
                uri->path = STRNDUP(*str, cur - *str);
            else
                uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
        } else {
            uri->path = NULL;
        }
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986HierPart:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an hierarchical part and fills in the appropriate fields
 * of the @uri structure
 *
 * hier-part     = "//" authority path-abempty
 *                / path-absolute
 *                / path-rootless
 *                / path-empty
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986HierPart(xmlURIPtr uri, const char **str)
{
    const char *cur;
    int ret;

    cur = *str;

    if ((*cur == '/') && (*(cur + 1) == '/')) {
        cur += 2;
	ret = xmlParse3986Authority(uri, &cur);
	if (ret != 0) return(ret);
	if (uri->server == NULL)
	    uri->port = -1;
	ret = xmlParse3986PathAbEmpty(uri, &cur);
	if (ret != 0) return(ret);
	*str = cur;
	return(0);
    } else if (*cur == '/') {
        ret = xmlParse3986PathAbsolute(uri, &cur);
	if (ret != 0) return(ret);
    } else if (ISA_PCHAR(cur)) {
        ret = xmlParse3986PathRootless(uri, &cur);
	if (ret != 0) return(ret);
    } else {
	/* path-empty is effectively empty */
	if (uri != NULL) {
	    if (uri->path != NULL) xmlFree(uri->path);
	    uri->path = NULL;
	}
    }
    *str = cur;
    return (0);
}

/**
 * xmlParse3986RelativeRef:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an URI string and fills in the appropriate fields
 * of the @uri structure
 *
 * relative-ref  = relative-part [ "?" query ] [ "#" fragment ]
 * relative-part = "//" authority path-abempty
 *               / path-absolute
 *               / path-noscheme
 *               / path-empty
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986RelativeRef(xmlURIPtr uri, const char *str) {
    int ret;

    if ((*str == '/') && (*(str + 1) == '/')) {
        str += 2;
	ret = xmlParse3986Authority(uri, &str);
	if (ret != 0) return(ret);
	ret = xmlParse3986PathAbEmpty(uri, &str);
	if (ret != 0) return(ret);
    } else if (*str == '/') {
	ret = xmlParse3986PathAbsolute(uri, &str);
	if (ret != 0) return(ret);
    } else if (ISA_PCHAR(str)) {
        ret = xmlParse3986PathNoScheme(uri, &str);
	if (ret != 0) return(ret);
    } else {
	/* path-empty is effectively empty */
	if (uri != NULL) {
	    if (uri->path != NULL) xmlFree(uri->path);
	    uri->path = NULL;
	}
    }

    if (*str == '?') {
	str++;
	ret = xmlParse3986Query(uri, &str);
	if (ret != 0) return(ret);
    }
    if (*str == '#') {
	str++;
	ret = xmlParse3986Fragment(uri, &str);
	if (ret != 0) return(ret);
    }
    if (*str != 0) {
	xmlCleanURI(uri);
	return(1);
    }
    return(0);
}


/**
 * xmlParse3986URI:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an URI string and fills in the appropriate fields
 * of the @uri structure
 *
 * scheme ":" hier-part [ "?" query ] [ "#" fragment ]
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986URI(xmlURIPtr uri, const char *str) {
    int ret;

    ret = xmlParse3986Scheme(uri, &str);
    if (ret != 0) return(ret);
    if (*str != ':') {
	return(1);
    }
    str++;
    ret = xmlParse3986HierPart(uri, &str);
    if (ret != 0) return(ret);
    if (*str == '?') {
	str++;
	ret = xmlParse3986Query(uri, &str);
	if (ret != 0) return(ret);
    }
    if (*str == '#') {
	str++;
	ret = xmlParse3986Fragment(uri, &str);
	if (ret != 0) return(ret);
    }
    if (*str != 0) {
	xmlCleanURI(uri);
	return(1);
    }
    return(0);
}

/**
 * xmlParse3986URIReference:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an URI reference string and fills in the appropriate fields
 * of the @uri structure
 *
 * URI-reference = URI / relative-ref
 *
 * Returns 0 or the error code
 */
static int
xmlParse3986URIReference(xmlURIPtr uri, const char *str) {
    int ret;

    if (str == NULL)
	return(-1);
    xmlCleanURI(uri);

    /*
     * Try first to parse absolute refs, then fallback to relative if
     * it fails.
     */
    ret = xmlParse3986URI(uri, str);
    if (ret != 0) {
	xmlCleanURI(uri);
        ret = xmlParse3986RelativeRef(uri, str);
	if (ret != 0) {
	    xmlCleanURI(uri);
	    return(ret);
	}
    }
    return(0);
}

/**
 * xmlParseURI:
 * @str:  the URI string to analyze
 *
 * Parse an URI based on RFC 3986
 *
 * URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
 *
 * Returns a newly built xmlURIPtr or NULL in case of error
 */
xmlURIPtr
xmlParseURI(const char *str) {
    xmlURIPtr uri;
    int ret;

    if (str == NULL)
	return(NULL);
    uri = xmlCreateURI();
    if (uri != NULL) {
	ret = xmlParse3986URIReference(uri, str);
        if (ret) {
	    xmlFreeURI(uri);
	    return(NULL);
	}
    }
    return(uri);
}

/**
 * xmlParseURIReference:
 * @uri:  pointer to an URI structure
 * @str:  the string to analyze
 *
 * Parse an URI reference string based on RFC 3986 and fills in the
 * appropriate fields of the @uri structure
 *
 * URI-reference = URI / relative-ref
 *
 * Returns 0 or the error code
 */
int
xmlParseURIReference(xmlURIPtr uri, const char *str) {
    return(xmlParse3986URIReference(uri, str));
}

/**
 * xmlParseURIRaw:
 * @str:  the URI string to analyze
 * @raw:  if 1 unescaping of URI pieces are disabled
 *
 * Parse an URI but allows to keep intact the original fragments.
 *
 * URI-reference = URI / relative-ref
 *
 * Returns a newly built xmlURIPtr or NULL in case of error
 */
xmlURIPtr
xmlParseURIRaw(const char *str, int raw) {
    xmlURIPtr uri;
    int ret;

    if (str == NULL)
	return(NULL);
    uri = xmlCreateURI();
    if (uri != NULL) {
        if (raw) {
	    uri->cleanup |= 2;
	}
	ret = xmlParseURIReference(uri, str);
        if (ret) {
	    xmlFreeURI(uri);
	    return(NULL);
	}
    }
    return(uri);
}

/************************************************************************
 *									*
 *			Generic URI structure functions			*
 *									*
 ************************************************************************/

/**
 * xmlCreateURI:
 *
 * Simply creates an empty xmlURI
 *
 * Returns the new structure or NULL in case of error
 */
xmlURIPtr
xmlCreateURI(void) {
    xmlURIPtr ret;

    ret = (xmlURIPtr) xmlMalloc(sizeof(xmlURI));
    if (ret == NULL) {
        xmlURIErrMemory("creating URI structure\n");
	return(NULL);
    }
    memset(ret, 0, sizeof(xmlURI));
    return(ret);
}

/**
 * xmlSaveUriRealloc:
 *
 * Function to handle properly a reallocation when saving an URI
 * Also imposes some limit on the length of an URI string output
 */
static xmlChar *
xmlSaveUriRealloc(xmlChar *ret, int *max) {
    xmlChar *temp;
    int tmp;

    if (*max > MAX_URI_LENGTH) {
        xmlURIErrMemory("reaching arbitrary MAX_URI_LENGTH limit\n");
        return(NULL);
    }
    tmp = *max * 2;
    temp = (xmlChar *) xmlRealloc(ret, (tmp + 1));
    if (temp == NULL) {
        xmlURIErrMemory("saving URI\n");
        return(NULL);
    }
    *max = tmp;
    return(temp);
}

/**
 * xmlSaveUri:
 * @uri:  pointer to an xmlURI
 *
 * Save the URI as an escaped string
 *
 * Returns a new string (to be deallocated by caller)
 */
xmlChar *
xmlSaveUri(xmlURIPtr uri) {
    xmlChar *ret = NULL;
    xmlChar *temp;
    const char *p;
    int len;
    int max;

    if (uri == NULL) return(NULL);


    max = 80;
    ret = (xmlChar *) xmlMallocAtomic((max + 1) * sizeof(xmlChar));
    if (ret == NULL) {
        xmlURIErrMemory("saving URI\n");
	return(NULL);
    }
    len = 0;

    if (uri->scheme != NULL) {
	p = uri->scheme;
	while (*p != 0) {
	    if (len >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
		ret = temp;
	    }
	    ret[len++] = *p++;
	}
	if (len >= max) {
            temp = xmlSaveUriRealloc(ret, &max);
            if (temp == NULL) goto mem_error;
            ret = temp;
	}
	ret[len++] = ':';
    }
    if (uri->opaque != NULL) {
	p = uri->opaque;
	while (*p != 0) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    if (IS_RESERVED(*(p)) || IS_UNRESERVED(*(p)))
		ret[len++] = *p++;
	    else {
		int val = *(unsigned char *)p++;
		int hi = val / 0x10, lo = val % 0x10;
		ret[len++] = '%';
		ret[len++] = hi + (hi > 9? 'A'-10 : '0');
		ret[len++] = lo + (lo > 9? 'A'-10 : '0');
	    }
	}
    } else {
	if ((uri->server != NULL) || (uri->port == -1)) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    ret[len++] = '/';
	    ret[len++] = '/';
	    if (uri->user != NULL) {
		p = uri->user;
		while (*p != 0) {
		    if (len + 3 >= max) {
                        temp = xmlSaveUriRealloc(ret, &max);
                        if (temp == NULL) goto mem_error;
                        ret = temp;
		    }
		    if ((IS_UNRESERVED(*(p))) ||
			((*(p) == ';')) || ((*(p) == ':')) ||
			((*(p) == '&')) || ((*(p) == '=')) ||
			((*(p) == '+')) || ((*(p) == '$')) ||
			((*(p) == ',')))
			ret[len++] = *p++;
		    else {
			int val = *(unsigned char *)p++;
			int hi = val / 0x10, lo = val % 0x10;
			ret[len++] = '%';
			ret[len++] = hi + (hi > 9? 'A'-10 : '0');
			ret[len++] = lo + (lo > 9? 'A'-10 : '0');
		    }
		}
		if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		ret[len++] = '@';
	    }
	    if (uri->server != NULL) {
		p = uri->server;
		while (*p != 0) {
		    if (len >= max) {
			temp = xmlSaveUriRealloc(ret, &max);
			if (temp == NULL) goto mem_error;
			ret = temp;
		    }
		    ret[len++] = *p++;
		}
		if (uri->port > 0) {
		    if (len + 10 >= max) {
			temp = xmlSaveUriRealloc(ret, &max);
			if (temp == NULL) goto mem_error;
			ret = temp;
		    }
		    len += snprintf((char *) &ret[len], max - len, ":%d", uri->port);
		}
	    }
	} else if (uri->authority != NULL) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    ret[len++] = '/';
	    ret[len++] = '/';
	    p = uri->authority;
	    while (*p != 0) {
		if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		if ((IS_UNRESERVED(*(p))) ||
                    ((*(p) == '$')) || ((*(p) == ',')) || ((*(p) == ';')) ||
                    ((*(p) == ':')) || ((*(p) == '@')) || ((*(p) == '&')) ||
                    ((*(p) == '=')) || ((*(p) == '+')))
		    ret[len++] = *p++;
		else {
		    int val = *(unsigned char *)p++;
		    int hi = val / 0x10, lo = val % 0x10;
		    ret[len++] = '%';
		    ret[len++] = hi + (hi > 9? 'A'-10 : '0');
		    ret[len++] = lo + (lo > 9? 'A'-10 : '0');
		}
	    }
	} else if (uri->scheme != NULL) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	}
	if (uri->path != NULL) {
	    p = uri->path;
	    /*
	     * the colon in file:///d: should not be escaped or
	     * Windows accesses fail later.
	     */
	    if ((uri->scheme != NULL) &&
		(p[0] == '/') &&
		(((p[1] >= 'a') && (p[1] <= 'z')) ||
		 ((p[1] >= 'A') && (p[1] <= 'Z'))) &&
		(p[2] == ':') &&
	        (xmlStrEqual(BAD_CAST uri->scheme, BAD_CAST "file"))) {
		if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		ret[len++] = *p++;
		ret[len++] = *p++;
		ret[len++] = *p++;
	    }
	    while (*p != 0) {
		if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		if ((IS_UNRESERVED(*(p))) || ((*(p) == '/')) ||
                    ((*(p) == ';')) || ((*(p) == '@')) || ((*(p) == '&')) ||
	            ((*(p) == '=')) || ((*(p) == '+')) || ((*(p) == '$')) ||
	            ((*(p) == ',')))
		    ret[len++] = *p++;
		else {
		    int val = *(unsigned char *)p++;
		    int hi = val / 0x10, lo = val % 0x10;
		    ret[len++] = '%';
		    ret[len++] = hi + (hi > 9? 'A'-10 : '0');
		    ret[len++] = lo + (lo > 9? 'A'-10 : '0');
		}
	    }
	}
	if (uri->query_raw != NULL) {
	    if (len + 1 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    ret[len++] = '?';
	    p = uri->query_raw;
	    while (*p != 0) {
		if (len + 1 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		ret[len++] = *p++;
	    }
	} else if (uri->query != NULL) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    ret[len++] = '?';
	    p = uri->query;
	    while (*p != 0) {
		if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
		}
		if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
		    ret[len++] = *p++;
		else {
		    int val = *(unsigned char *)p++;
		    int hi = val / 0x10, lo = val % 0x10;
		    ret[len++] = '%';
		    ret[len++] = hi + (hi > 9? 'A'-10 : '0');
		    ret[len++] = lo + (lo > 9? 'A'-10 : '0');
		}
	    }
	}
    }
    if (uri->fragment != NULL) {
	if (len + 3 >= max) {
            temp = xmlSaveUriRealloc(ret, &max);
            if (temp == NULL) goto mem_error;
            ret = temp;
	}
	ret[len++] = '#';
	p = uri->fragment;
	while (*p != 0) {
	    if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
	    }
	    if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
		ret[len++] = *p++;
	    else {
		int val = *(unsigned char *)p++;
		int hi = val / 0x10, lo = val % 0x10;
		ret[len++] = '%';
		ret[len++] = hi + (hi > 9? 'A'-10 : '0');
		ret[len++] = lo + (lo > 9? 'A'-10 : '0');
	    }
	}
    }
    if (len >= max) {
        temp = xmlSaveUriRealloc(ret, &max);
        if (temp == NULL) goto mem_error;
        ret = temp;
    }
    ret[len] = 0;
    return(ret);

mem_error:
    xmlFree(ret);
    return(NULL);
}

/**
 * xmlPrintURI:
 * @stream:  a FILE* for the output
 * @uri:  pointer to an xmlURI
 *
 * Prints the URI in the stream @stream.
 */
void
xmlPrintURI(FILE *stream, xmlURIPtr uri) {
    xmlChar *out;

    out = xmlSaveUri(uri);
    if (out != NULL) {
	fprintf(stream, "%s", (char *) out);
	xmlFree(out);
    }
}

/**
 * xmlCleanURI:
 * @uri:  pointer to an xmlURI
 *
 * Make sure the xmlURI struct is free of content
 */
static void
xmlCleanURI(xmlURIPtr uri) {
    if (uri == NULL) return;

    if (uri->scheme != NULL) xmlFree(uri->scheme);
    uri->scheme = NULL;
    if (uri->server != NULL) xmlFree(uri->server);
    uri->server = NULL;
    if (uri->user != NULL) xmlFree(uri->user);
    uri->user = NULL;
    if (uri->path != NULL) xmlFree(uri->path);
    uri->path = NULL;
    if (uri->fragment != NULL) xmlFree(uri->fragment);
    uri->fragment = NULL;
    if (uri->opaque != NULL) xmlFree(uri->opaque);
    uri->opaque = NULL;
    if (uri->authority != NULL) xmlFree(uri->authority);
    uri->authority = NULL;
    if (uri->query != NULL) xmlFree(uri->query);
    uri->query = NULL;
    if (uri->query_raw != NULL) xmlFree(uri->query_raw);
    uri->query_raw = NULL;
}

/**
 * xmlFreeURI:
 * @uri:  pointer to an xmlURI
 *
 * Free up the xmlURI struct
 */
void
xmlFreeURI(xmlURIPtr uri) {
    if (uri == NULL) return;

    if (uri->scheme != NULL) xmlFree(uri->scheme);
    if (uri->server != NULL) xmlFree(uri->server);
    if (uri->user != NULL) xmlFree(uri->user);
    if (uri->path != NULL) xmlFree(uri->path);
    if (uri->fragment != NULL) xmlFree(uri->fragment);
    if (uri->opaque != NULL) xmlFree(uri->opaque);
    if (uri->authority != NULL) xmlFree(uri->authority);
    if (uri->query != NULL) xmlFree(uri->query);
    if (uri->query_raw != NULL) xmlFree(uri->query_raw);
    xmlFree(uri);
}

/************************************************************************
 *									*
 *			Helper functions				*
 *									*
 ************************************************************************/

/**
 * xmlNormalizeURIPath:
 * @path:  pointer to the path string
 *
 * Applies the 5 normalization steps to a path string--that is, RFC 2396
 * Section 5.2, steps 6.c through 6.g.
 *
 * Normalization occurs directly on the string, no new allocation is done
 *
 * Returns 0 or an error code
 */
int
xmlNormalizeURIPath(char *path) {
    char *cur, *out;

    if (path == NULL)
	return(-1);

    /* Skip all initial "/" chars.  We want to get to the beginning of the
     * first non-empty segment.
     */
    cur = path;
    while (cur[0] == '/')
      ++cur;
    if (cur[0] == '\0')
      return(0);

    /* Keep everything we've seen so far.  */
    out = cur;

    /*
     * Analyze each segment in sequence for cases (c) and (d).
     */
    while (cur[0] != '\0') {
	/*
	 * c) All occurrences of "./", where "." is a complete path segment,
	 *    are removed from the buffer string.
	 */
	if ((cur[0] == '.') && (cur[1] == '/')) {
	    cur += 2;
	    /* '//' normalization should be done at this point too */
	    while (cur[0] == '/')
		cur++;
	    continue;
	}

	/*
	 * d) If the buffer string ends with "." as a complete path segment,
	 *    that "." is removed.
	 */
	if ((cur[0] == '.') && (cur[1] == '\0'))
	    break;

	/* Otherwise keep the segment.  */
	while (cur[0] != '/') {
            if (cur[0] == '\0')
              goto done_cd;
	    (out++)[0] = (cur++)[0];
	}
	/* normalize // */
	while ((cur[0] == '/') && (cur[1] == '/'))
	    cur++;

        (out++)[0] = (cur++)[0];
    }
 done_cd:
    out[0] = '\0';

    /* Reset to the beginning of the first segment for the next sequence.  */
    cur = path;
    while (cur[0] == '/')
      ++cur;
    if (cur[0] == '\0')
	return(0);

    /*
     * Analyze each segment in sequence for cases (e) and (f).
     *
     * e) All occurrences of "<segment>/../", where <segment> is a
     *    complete path segment not equal to "..", are removed from the
     *    buffer string.  Removal of these path segments is performed
     *    iteratively, removing the leftmost matching pattern on each
     *    iteration, until no matching pattern remains.
     *
     * f) If the buffer string ends with "<segment>/..", where <segment>
     *    is a complete path segment not equal to "..", that
     *    "<segment>/.." is removed.
     *
     * To satisfy the "iterative" clause in (e), we need to collapse the
     * string every time we find something that needs to be removed.  Thus,
     * we don't need to keep two pointers into the string: we only need a
     * "current position" pointer.
     */
    while (1) {
        char *segp, *tmp;

        /* At the beginning of each iteration of this loop, "cur" points to
         * the first character of the segment we want to examine.
         */

        /* Find the end of the current segment.  */
        segp = cur;
        while ((segp[0] != '/') && (segp[0] != '\0'))
          ++segp;

        /* If this is the last segment, we're done (we need at least two
         * segments to meet the criteria for the (e) and (f) cases).
         */
        if (segp[0] == '\0')
          break;

        /* If the first segment is "..", or if the next segment _isn't_ "..",
         * keep this segment and try the next one.
         */
        ++segp;
        if (((cur[0] == '.') && (cur[1] == '.') && (segp == cur+3))
            || ((segp[0] != '.') || (segp[1] != '.')
                || ((segp[2] != '/') && (segp[2] != '\0')))) {
          cur = segp;
          continue;
        }

        /* If we get here, remove this segment and the next one and back up
         * to the previous segment (if there is one), to implement the
         * "iteratively" clause.  It's pretty much impossible to back up
         * while maintaining two pointers into the buffer, so just compact
         * the whole buffer now.
         */

        /* If this is the end of the buffer, we're done.  */
        if (segp[2] == '\0') {
          cur[0] = '\0';
          break;
        }
        /* Valgrind complained, strcpy(cur, segp + 3); */
        /* string will overlap, do not use strcpy */
        tmp = cur;
        segp += 3;
        while ((*tmp++ = *segp++) != 0)
          ;

        /* If there are no previous segments, then keep going from here.  */
        segp = cur;
        while ((segp > path) && ((--segp)[0] == '/'))
          ;
        if (segp == path)
          continue;

        /* "segp" is pointing to the end of a previous segment; find it's
         * start.  We need to back up to the previous segment and start
         * over with that to handle things like "foo/bar/../..".  If we
         * don't do this, then on the first pass we'll remove the "bar/..",
         * but be pointing at the second ".." so we won't realize we can also
         * remove the "foo/..".
         */
        cur = segp;
        while ((cur > path) && (cur[-1] != '/'))
          --cur;
    }
    out[0] = '\0';

    /*
     * g) If the resulting buffer string still begins with one or more
     *    complete path segments of "..", then the reference is
     *    considered to be in error. Implementations may handle this
     *    error by retaining these components in the resolved path (i.e.,
     *    treating them as part of the final URI), by removing them from
     *    the resolved path (i.e., discarding relative levels above the
     *    root), or by avoiding traversal of the reference.
     *
     * We discard them from the final path.
     */
    if (path[0] == '/') {
      cur = path;
      while ((cur[0] == '/') && (cur[1] == '.') && (cur[2] == '.')
             && ((cur[3] == '/') || (cur[3] == '\0')))
	cur += 3;

      if (cur != path) {
	out = path;
	while (cur[0] != '\0')
          (out++)[0] = (cur++)[0];
	out[0] = 0;
      }
    }

    return(0);
}

static int is_hex(char c) {
    if (((c >= '0') && (c <= '9')) ||
        ((c >= 'a') && (c <= 'f')) ||
        ((c >= 'A') && (c <= 'F')))
	return(1);
    return(0);
}

/**
 * xmlURIUnescapeString:
 * @str:  the string to unescape
 * @len:   the length in bytes to unescape (or <= 0 to indicate full string)
 * @target:  optional destination buffer
 *
 * Unescaping routine, but does not check that the string is an URI. The
 * output is a direct unsigned char translation of %XX values (no encoding)
 * Note that the length of the result can only be smaller or same size as
 * the input string.
 *
 * Returns a copy of the string, but unescaped, will return NULL only in case
 * of error
 */
char *
xmlURIUnescapeString(const char *str, int len, char *target) {
    char *ret, *out;
    const char *in;

    if (str == NULL)
	return(NULL);
    if (len <= 0) len = strlen(str);
    if (len < 0) return(NULL);

    if (target == NULL) {
	ret = (char *) xmlMallocAtomic(len + 1);
	if (ret == NULL) {
            xmlURIErrMemory("unescaping URI value\n");
	    return(NULL);
	}
    } else
	ret = target;
    in = str;
    out = ret;
    while(len > 0) {
	if ((len > 2) && (*in == '%') && (is_hex(in[1])) && (is_hex(in[2]))) {
            int c = 0;
	    in++;
	    if ((*in >= '0') && (*in <= '9'))
	        c = (*in - '0');
	    else if ((*in >= 'a') && (*in <= 'f'))
	        c = (*in - 'a') + 10;
	    else if ((*in >= 'A') && (*in <= 'F'))
	        c = (*in - 'A') + 10;
	    in++;
	    if ((*in >= '0') && (*in <= '9'))
	        c = c * 16 + (*in - '0');
	    else if ((*in >= 'a') && (*in <= 'f'))
	        c = c * 16 + (*in - 'a') + 10;
	    else if ((*in >= 'A') && (*in <= 'F'))
	        c = c * 16 + (*in - 'A') + 10;
	    in++;
	    len -= 3;
	    *out++ = (char) c;
	} else {
	    *out++ = *in++;
	    len--;
	}
    }
    *out = 0;
    return(ret);
}

/**
 * xmlURIEscapeStr:
 * @str:  string to escape
 * @list: exception list string of chars not to escape
 *
 * This routine escapes a string to hex, ignoring reserved characters (a-z)
 * and the characters in the exception list.
 *
 * Returns a new escaped string or NULL in case of error.
 */
xmlChar *
xmlURIEscapeStr(const xmlChar *str, const xmlChar *list) {
    xmlChar *ret, ch;
    xmlChar *temp;
    const xmlChar *in;
    int len, out;

    if (str == NULL)
	return(NULL);
    if (str[0] == 0)
	return(xmlStrdup(str));
    len = xmlStrlen(str);
    if (!(len > 0)) return(NULL);

    len += 20;
    ret = (xmlChar *) xmlMallocAtomic(len);
    if (ret == NULL) {
        xmlURIErrMemory("escaping URI value\n");
	return(NULL);
    }
    in = (const xmlChar *) str;
    out = 0;
    while(*in != 0) {
	if (len - out <= 3) {
            temp = xmlSaveUriRealloc(ret, &len);
	    if (temp == NULL) {
                xmlURIErrMemory("escaping URI value\n");
		xmlFree(ret);
		return(NULL);
	    }
	    ret = temp;
	}

	ch = *in;

	if ((ch != '@') && (!IS_UNRESERVED(ch)) && (!xmlStrchr(list, ch))) {
	    unsigned char val;
	    ret[out++] = '%';
	    val = ch >> 4;
	    if (val <= 9)
		ret[out++] = '0' + val;
	    else
		ret[out++] = 'A' + val - 0xA;
	    val = ch & 0xF;
	    if (val <= 9)
		ret[out++] = '0' + val;
	    else
		ret[out++] = 'A' + val - 0xA;
	    in++;
	} else {
	    ret[out++] = *in++;
	}

    }
    ret[out] = 0;
    return(ret);
}

/**
 * xmlURIEscape:
 * @str:  the string of the URI to escape
 *
 * Escaping routine, does not do validity checks !
 * It will try to escape the chars needing this, but this is heuristic
 * based it's impossible to be sure.
 *
 * Returns an copy of the string, but escaped
 *
 * 25 May 2001
 * Uses xmlParseURI and xmlURIEscapeStr to try to escape correctly
 * according to RFC2396.
 *   - Carl Douglas
 */
xmlChar *
xmlURIEscape(const xmlChar * str)
{
    xmlChar *ret, *segment = NULL;
    xmlURIPtr uri;
    int ret2;

    if (str == NULL)
        return (NULL);

    uri = xmlCreateURI();
    if (uri != NULL) {
	/*
	 * Allow escaping errors in the unescaped form
	 */
        uri->cleanup = 1;
        ret2 = xmlParseURIReference(uri, (const char *)str);
        if (ret2) {
            xmlFreeURI(uri);
            return (NULL);
        }
    }

    if (!uri)
        return NULL;

    ret = NULL;

#define NULLCHK(p) if(!p) { \
         xmlURIErrMemory("escaping URI value\n"); \
         xmlFreeURI(uri); \
         xmlFree(ret); \
         return NULL; } \

    if (uri->scheme) {
        segment = xmlURIEscapeStr(BAD_CAST uri->scheme, BAD_CAST "+-.");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        ret = xmlStrcat(ret, BAD_CAST ":");
        xmlFree(segment);
    }

    if (uri->authority) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->authority, BAD_CAST "/?;:@");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    if (uri->user) {
        segment = xmlURIEscapeStr(BAD_CAST uri->user, BAD_CAST ";:&=+$,");
        NULLCHK(segment)
        ret = xmlStrcat(ret,BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        ret = xmlStrcat(ret, BAD_CAST "@");
        xmlFree(segment);
    }

    if (uri->server) {
        segment = xmlURIEscapeStr(BAD_CAST uri->server, BAD_CAST "/?;:@");
        NULLCHK(segment)
        if (uri->user == NULL)
            ret = xmlStrcat(ret, BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    if (uri->port) {
        xmlChar port[10];

        snprintf((char *) port, 10, "%d", uri->port);
        ret = xmlStrcat(ret, BAD_CAST ":");
        ret = xmlStrcat(ret, port);
    }

    if (uri->path) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->path, BAD_CAST ":@&=+$,/?;");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    if (uri->query_raw) {
        ret = xmlStrcat(ret, BAD_CAST "?");
        ret = xmlStrcat(ret, BAD_CAST uri->query_raw);
    }
    else if (uri->query) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->query, BAD_CAST ";/?:@&=+,$");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "?");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    if (uri->opaque) {
        segment = xmlURIEscapeStr(BAD_CAST uri->opaque, BAD_CAST "");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    if (uri->fragment) {
        segment = xmlURIEscapeStr(BAD_CAST uri->fragment, BAD_CAST "#");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "#");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }

    xmlFreeURI(uri);
#undef NULLCHK

    return (ret);
}

/************************************************************************
 *									*
 *			Public functions				*
 *									*
 ************************************************************************/

/**
 * xmlBuildURI:
 * @URI:  the URI instance found in the document
 * @base:  the base value
 *
 * Computes he final URI of the reference done by checking that
 * the given URI is valid, and building the final URI using the
 * base URI. This is processed according to section 5.2 of the
 * RFC 2396
 *
 * 5.2. Resolving Relative References to Absolute Form
 *
 * Returns a new URI string (to be freed by the caller) or NULL in case
 *         of error.
 */
xmlChar *
xmlBuildURI(const xmlChar *URI, const xmlChar *base) {
    xmlChar *val = NULL;
    int ret, len, indx, cur, out;
    xmlURIPtr ref = NULL;
    xmlURIPtr bas = NULL;
    xmlURIPtr res = NULL;

    /*
     * 1) The URI reference is parsed into the potential four components and
     *    fragment identifier, as described in Section 4.3.
     *
     *    NOTE that a completely empty URI is treated by modern browsers
     *    as a reference to "." rather than as a synonym for the current
     *    URI.  Should we do that here?
     */
    if (URI == NULL)
	ret = -1;
    else {
	if (*URI) {
	    ref = xmlCreateURI();
	    if (ref == NULL)
		goto done;
	    ret = xmlParseURIReference(ref, (const char *) URI);
	}
	else
	    ret = 0;
    }
    if (ret != 0)
	goto done;
    if ((ref != NULL) && (ref->scheme != NULL)) {
	/*
	 * The URI is absolute don't modify.
	 */
	val = xmlStrdup(URI);
	goto done;
    }
    if (base == NULL)
	ret = -1;
    else {
	bas = xmlCreateURI();
	if (bas == NULL)
	    goto done;
	ret = xmlParseURIReference(bas, (const char *) base);
    }
    if (ret != 0) {
	if (ref)
	    val = xmlSaveUri(ref);
	goto done;
    }
    if (ref == NULL) {
	/*
	 * the base fragment must be ignored
	 */
	if (bas->fragment != NULL) {
	    xmlFree(bas->fragment);
	    bas->fragment = NULL;
	}
	val = xmlSaveUri(bas);
	goto done;
    }

    /*
     * 2) If the path component is empty and the scheme, authority, and
     *    query components are undefined, then it is a reference to the
     *    current document and we are done.  Otherwise, the reference URI's
     *    query and fragment components are defined as found (or not found)
     *    within the URI reference and not inherited from the base URI.
     *
     *    NOTE that in modern browsers, the parsing differs from the above
     *    in the following aspect:  the query component is allowed to be
     *    defined while still treating this as a reference to the current
     *    document.
     */
    res = xmlCreateURI();
    if (res == NULL)
	goto done;
    if ((ref->scheme == NULL) && (ref->path == NULL) &&
	((ref->authority == NULL) && (ref->server == NULL))) {
	if (bas->scheme != NULL)
	    res->scheme = xmlMemStrdup(bas->scheme);
	if (bas->authority != NULL)
	    res->authority = xmlMemStrdup(bas->authority);
	else if ((bas->server != NULL) || (bas->port == -1)) {
	    if (bas->server != NULL)
		res->server = xmlMemStrdup(bas->server);
	    if (bas->user != NULL)
		res->user = xmlMemStrdup(bas->user);
	    res->port = bas->port;
	}
	if (bas->path != NULL)
	    res->path = xmlMemStrdup(bas->path);
	if (ref->query_raw != NULL)
	    res->query_raw = xmlMemStrdup (ref->query_raw);
	else if (ref->query != NULL)
	    res->query = xmlMemStrdup(ref->query);
	else if (bas->query_raw != NULL)
	    res->query_raw = xmlMemStrdup(bas->query_raw);
	else if (bas->query != NULL)
	    res->query = xmlMemStrdup(bas->query);
	if (ref->fragment != NULL)
	    res->fragment = xmlMemStrdup(ref->fragment);
	goto step_7;
    }

    /*
     * 3) If the scheme component is defined, indicating that the reference
     *    starts with a scheme name, then the reference is interpreted as an
     *    absolute URI and we are done.  Otherwise, the reference URI's
     *    scheme is inherited from the base URI's scheme component.
     */
    if (ref->scheme != NULL) {
	val = xmlSaveUri(ref);
	goto done;
    }
    if (bas->scheme != NULL)
	res->scheme = xmlMemStrdup(bas->scheme);

    if (ref->query_raw != NULL)
	res->query_raw = xmlMemStrdup(ref->query_raw);
    else if (ref->query != NULL)
	res->query = xmlMemStrdup(ref->query);
    if (ref->fragment != NULL)
	res->fragment = xmlMemStrdup(ref->fragment);

    /*
     * 4) If the authority component is defined, then the reference is a
     *    network-path and we skip to step 7.  Otherwise, the reference
     *    URI's authority is inherited from the base URI's authority
     *    component, which will also be undefined if the URI scheme does not
     *    use an authority component.
     */
    if ((ref->authority != NULL) || (ref->server != NULL)) {
	if (ref->authority != NULL)
	    res->authority = xmlMemStrdup(ref->authority);
	else {
	    res->server = xmlMemStrdup(ref->server);
	    if (ref->user != NULL)
		res->user = xmlMemStrdup(ref->user);
            res->port = ref->port;
	}
	if (ref->path != NULL)
	    res->path = xmlMemStrdup(ref->path);
	goto step_7;
    }
    if (bas->authority != NULL)
	res->authority = xmlMemStrdup(bas->authority);
    else if ((bas->server != NULL) || (bas->port == -1)) {
	if (bas->server != NULL)
	    res->server = xmlMemStrdup(bas->server);
	if (bas->user != NULL)
	    res->user = xmlMemStrdup(bas->user);
	res->port = bas->port;
    }

    /*
     * 5) If the path component begins with a slash character ("/"), then
     *    the reference is an absolute-path and we skip to step 7.
     */
    if ((ref->path != NULL) && (ref->path[0] == '/')) {
	res->path = xmlMemStrdup(ref->path);
	goto step_7;
    }


    /*
     * 6) If this step is reached, then we are resolving a relative-path
     *    reference.  The relative path needs to be merged with the base
     *    URI's path.  Although there are many ways to do this, we will
     *    describe a simple method using a separate string buffer.
     *
     * Allocate a buffer large enough for the result string.
     */
    len = 2; /* extra / and 0 */
    if (ref->path != NULL)
	len += strlen(ref->path);
    if (bas->path != NULL)
	len += strlen(bas->path);
    res->path = (char *) xmlMallocAtomic(len);
    if (res->path == NULL) {
        xmlURIErrMemory("resolving URI against base\n");
	goto done;
    }
    res->path[0] = 0;

    /*
     * a) All but the last segment of the base URI's path component is
     *    copied to the buffer.  In other words, any characters after the
     *    last (right-most) slash character, if any, are excluded.
     */
    cur = 0;
    out = 0;
    if (bas->path != NULL) {
	while (bas->path[cur] != 0) {
	    while ((bas->path[cur] != 0) && (bas->path[cur] != '/'))
		cur++;
	    if (bas->path[cur] == 0)
		break;

	    cur++;
	    while (out < cur) {
		res->path[out] = bas->path[out];
		out++;
	    }
	}
    }
    res->path[out] = 0;

    /*
     * b) The reference's path component is appended to the buffer
     *    string.
     */
    if (ref->path != NULL && ref->path[0] != 0) {
	indx = 0;
	/*
	 * Ensure the path includes a '/'
	 */
	if ((out == 0) && (bas->server != NULL))
	    res->path[out++] = '/';
	while (ref->path[indx] != 0) {
	    res->path[out++] = ref->path[indx++];
	}
    }
    res->path[out] = 0;

    /*
     * Steps c) to h) are really path normalization steps
     */
    xmlNormalizeURIPath(res->path);

step_7:

    /*
     * 7) The resulting URI components, including any inherited from the
     *    base URI, are recombined to give the absolute form of the URI
     *    reference.
     */
    val = xmlSaveUri(res);

done:
    if (ref != NULL)
	xmlFreeURI(ref);
    if (bas != NULL)
	xmlFreeURI(bas);
    if (res != NULL)
	xmlFreeURI(res);
    return(val);
}

/**
 * xmlBuildRelativeURI:
 * @URI:  the URI reference under consideration
 * @base:  the base value
 *
 * Expresses the URI of the reference in terms relative to the
 * base.  Some examples of this operation include:
 *     base = "http://site1.com/docs/book1.html"
 *        URI input                        URI returned
 *     docs/pic1.gif                    pic1.gif
 *     docs/img/pic1.gif                img/pic1.gif
 *     img/pic1.gif                     ../img/pic1.gif
 *     http://site1.com/docs/pic1.gif   pic1.gif
 *     http://site2.com/docs/pic1.gif   http://site2.com/docs/pic1.gif
 *
 *     base = "docs/book1.html"
 *        URI input                        URI returned
 *     docs/pic1.gif                    pic1.gif
 *     docs/img/pic1.gif                img/pic1.gif
 *     img/pic1.gif                     ../img/pic1.gif
 *     http://site1.com/docs/pic1.gif   http://site1.com/docs/pic1.gif
 *
 *
 * Note: if the URI reference is really weird or complicated, it may be
 *       worthwhile to first convert it into a "nice" one by calling
 *       xmlBuildURI (using 'base') before calling this routine,
 *       since this routine (for reasonable efficiency) assumes URI has
 *       already been through some validation.
 *
 * Returns a new URI string (to be freed by the caller) or NULL in case
 * error.
 */
xmlChar *
xmlBuildRelativeURI (const xmlChar * URI, const xmlChar * base)
{
    xmlChar *val = NULL;
    int ret;
    int ix;
    int nbslash = 0;
    int len;
    xmlURIPtr ref = NULL;
    xmlURIPtr bas = NULL;
    xmlChar *bptr, *uptr, *vptr;
    int remove_path = 0;

    if ((URI == NULL) || (*URI == 0))
	return NULL;

    /*
     * First parse URI into a standard form
     */
    ref = xmlCreateURI ();
    if (ref == NULL)
	return NULL;
    /* If URI not already in "relative" form */
    if (URI[0] != '.') {
	ret = xmlParseURIReference (ref, (const char *) URI);
	if (ret != 0)
	    goto done;		/* Error in URI, return NULL */
    } else
	ref->path = (char *)xmlStrdup(URI);

    /*
     * Next parse base into the same standard form
     */
    if ((base == NULL) || (*base == 0)) {
	val = xmlStrdup (URI);
	goto done;
    }
    bas = xmlCreateURI ();
    if (bas == NULL)
	goto done;
    if (base[0] != '.') {
	ret = xmlParseURIReference (bas, (const char *) base);
	if (ret != 0)
	    goto done;		/* Error in base, return NULL */
    } else
	bas->path = (char *)xmlStrdup(base);

    /*
     * If the scheme / server on the URI differs from the base,
     * just return the URI
     */
    if ((ref->scheme != NULL) &&
	((bas->scheme == NULL) ||
	 (xmlStrcmp ((xmlChar *)bas->scheme, (xmlChar *)ref->scheme)) ||
	 (xmlStrcmp ((xmlChar *)bas->server, (xmlChar *)ref->server)))) {
	val = xmlStrdup (URI);
	goto done;
    }
    if (xmlStrEqual((xmlChar *)bas->path, (xmlChar *)ref->path)) {
	val = xmlStrdup(BAD_CAST "");
	goto done;
    }
    if (bas->path == NULL) {
	val = xmlStrdup((xmlChar *)ref->path);
	goto done;
    }
    if (ref->path == NULL) {
        ref->path = (char *) "/";
	remove_path = 1;
    }

    /*
     * At this point (at last!) we can compare the two paths
     *
     * First we take care of the special case where either of the
     * two path components may be missing (bug 316224)
     */
    bptr = (xmlChar *)bas->path;
    {
        xmlChar *rptr = (xmlChar *) ref->path;
        int pos = 0;

        /*
         * Next we compare the two strings and find where they first differ
         */
	if ((*rptr == '.') && (rptr[1] == '/'))
            rptr += 2;
	if ((*bptr == '.') && (bptr[1] == '/'))
            bptr += 2;
	else if ((*bptr == '/') && (*rptr != '/'))
	    bptr++;
	while ((bptr[pos] == rptr[pos]) && (bptr[pos] != 0))
	    pos++;

	if (bptr[pos] == rptr[pos]) {
	    val = xmlStrdup(BAD_CAST "");
	    goto done;		/* (I can't imagine why anyone would do this) */
	}

	/*
	 * In URI, "back up" to the last '/' encountered.  This will be the
	 * beginning of the "unique" suffix of URI
	 */
	ix = pos;
	for (; ix > 0; ix--) {
	    if (rptr[ix - 1] == '/')
		break;
	}
	uptr = (xmlChar *)&rptr[ix];

	/*
	 * In base, count the number of '/' from the differing point
	 */
	for (; bptr[ix] != 0; ix++) {
	    if (bptr[ix] == '/')
		nbslash++;
	}

	/*
	 * e.g: URI="foo/" base="foo/bar" -> "./"
	 */
	if (nbslash == 0 && !uptr[0]) {
	    val = xmlStrdup(BAD_CAST "./");
	    goto done;
	}

	len = xmlStrlen (uptr) + 1;
    }

    if (nbslash == 0) {
	if (uptr != NULL)
	    /* exception characters from xmlSaveUri */
	    val = xmlURIEscapeStr(uptr, BAD_CAST "/;&=+$,");
	goto done;
    }

    /*
     * Allocate just enough space for the returned string -
     * length of the remainder of the URI, plus enough space
     * for the "../" groups, plus one for the terminator
     */
    val = (xmlChar *) xmlMalloc (len + 3 * nbslash);
    if (val == NULL) {
        xmlURIErrMemory("building relative URI\n");
	goto done;
    }
    vptr = val;
    /*
     * Put in as many "../" as needed
     */
    for (; nbslash>0; nbslash--) {
	*vptr++ = '.';
	*vptr++ = '.';
	*vptr++ = '/';
    }
    /*
     * Finish up with the end of the URI
     */
    if (uptr != NULL) {
        if ((vptr > val) && (len > 0) &&
	    (uptr[0] == '/') && (vptr[-1] == '/')) {
	    memcpy (vptr, uptr + 1, len - 1);
	    vptr[len - 2] = 0;
	} else {
	    memcpy (vptr, uptr, len);
	    vptr[len - 1] = 0;
	}
    } else {
	vptr[len - 1] = 0;
    }

    /* escape the freshly-built path */
    vptr = val;
	/* exception characters from xmlSaveUri */
    val = xmlURIEscapeStr(vptr, BAD_CAST "/;&=+$,");
    xmlFree(vptr);

done:
    /*
     * Free the working variables
     */
    if (remove_path != 0)
        ref->path = NULL;
    if (ref != NULL)
	xmlFreeURI (ref);
    if (bas != NULL)
	xmlFreeURI (bas);

    return val;
}

/**
 * xmlCanonicPath:
 * @path:  the resource locator in a filesystem notation
 *
 * Constructs a canonic path from the specified path.
 *
 * Returns a new canonic path, or a duplicate of the path parameter if the
 * construction fails. The caller is responsible for freeing the memory occupied
 * by the returned string. If there is insufficient memory available, or the
 * argument is NULL, the function returns NULL.
 */
#define IS_WINDOWS_PATH(p)					\
	((p != NULL) &&						\
	 (((p[0] >= 'a') && (p[0] <= 'z')) ||			\
	  ((p[0] >= 'A') && (p[0] <= 'Z'))) &&			\
	 (p[1] == ':') && ((p[2] == '/') || (p[2] == '\\')))
xmlChar *
xmlCanonicPath(const xmlChar *path)
{
/*
 * For Windows implementations, additional work needs to be done to
 * replace backslashes in pathnames with "forward slashes"
 */
#if defined(_WIN32) && !defined(__CYGWIN__)
    int len = 0;
    char *p = NULL;
#endif
    xmlURIPtr uri;
    xmlChar *ret;
    const xmlChar *absuri;

    if (path == NULL)
	return(NULL);

#if defined(_WIN32)
    /*
     * We must not change the backslashes to slashes if the the path
     * starts with \\?\
     * Those paths can be up to 32k characters long.
     * Was added specifically for OpenOffice, those paths can't be converted
     * to URIs anyway.
     */
    if ((path[0] == '\\') && (path[1] == '\\') && (path[2] == '?') &&
        (path[3] == '\\') )
	return xmlStrdup((const xmlChar *) path);
#endif

	/* sanitize filename starting with // so it can be used as URI */
    if ((path[0] == '/') && (path[1] == '/') && (path[2] != '/'))
        path++;

    if ((uri = xmlParseURI((const char *) path)) != NULL) {
	xmlFreeURI(uri);
	return xmlStrdup(path);
    }

    /* Check if this is an "absolute uri" */
    absuri = xmlStrstr(path, BAD_CAST "://");
    if (absuri != NULL) {
        int l, j;
	unsigned char c;
	xmlChar *escURI;

        /*
	 * this looks like an URI where some parts have not been
	 * escaped leading to a parsing problem.  Check that the first
	 * part matches a protocol.
	 */
	l = absuri - path;
	/* Bypass if first part (part before the '://') is > 20 chars */
	if ((l <= 0) || (l > 20))
	    goto path_processing;
	/* Bypass if any non-alpha characters are present in first part */
	for (j = 0;j < l;j++) {
	    c = path[j];
	    if (!(((c >= 'a') && (c <= 'z')) || ((c >= 'A') && (c <= 'Z'))))
	        goto path_processing;
	}

	/* Escape all except the characters specified in the supplied path */
        escURI = xmlURIEscapeStr(path, BAD_CAST ":/?_.#&;=");
	if (escURI != NULL) {
	    /* Try parsing the escaped path */
	    uri = xmlParseURI((const char *) escURI);
	    /* If successful, return the escaped string */
	    if (uri != NULL) {
	        xmlFreeURI(uri);
		return escURI;
	    }
            xmlFree(escURI);
	}
    }

path_processing:
/* For Windows implementations, replace backslashes with 'forward slashes' */
#if defined(_WIN32) && !defined(__CYGWIN__)
    /*
     * Create a URI structure
     */
    uri = xmlCreateURI();
    if (uri == NULL) {		/* Guard against 'out of memory' */
        return(NULL);
    }

    len = xmlStrlen(path);
    if ((len > 2) && IS_WINDOWS_PATH(path)) {
        /* make the scheme 'file' */
	uri->scheme = (char *) xmlStrdup(BAD_CAST "file");
	/* allocate space for leading '/' + path + string terminator */
	uri->path = xmlMallocAtomic(len + 2);
	if (uri->path == NULL) {
	    xmlFreeURI(uri);	/* Guard against 'out of memory' */
	    return(NULL);
	}
	/* Put in leading '/' plus path */
	uri->path[0] = '/';
	p = uri->path + 1;
	strncpy(p, (char *) path, len + 1);
    } else {
	uri->path = (char *) xmlStrdup(path);
	if (uri->path == NULL) {
	    xmlFreeURI(uri);
	    return(NULL);
	}
	p = uri->path;
    }
    /* Now change all occurrences of '\' to '/' */
    while (*p != '\0') {
	if (*p == '\\')
	    *p = '/';
	p++;
    }

    if (uri->scheme == NULL) {
	ret = xmlStrdup((const xmlChar *) uri->path);
    } else {
	ret = xmlSaveUri(uri);
    }

    xmlFreeURI(uri);
#else
    ret = xmlStrdup((const xmlChar *) path);
#endif
    return(ret);
}

/**
 * xmlPathToURI:
 * @path:  the resource locator in a filesystem notation
 *
 * Constructs an URI expressing the existing path
 *
 * Returns a new URI, or a duplicate of the path parameter if the
 * construction fails. The caller is responsible for freeing the memory
 * occupied by the returned string. If there is insufficient memory available,
 * or the argument is NULL, the function returns NULL.
 */
xmlChar *
xmlPathToURI(const xmlChar *path)
{
    xmlURIPtr uri;
    xmlURI temp;
    xmlChar *ret, *cal;

    if (path == NULL)
        return(NULL);

    if ((uri = xmlParseURI((const char *) path)) != NULL) {
	xmlFreeURI(uri);
	return xmlStrdup(path);
    }
    cal = xmlCanonicPath(path);
    if (cal == NULL)
        return(NULL);
#if defined(_WIN32) && !defined(__CYGWIN__)
    /* xmlCanonicPath can return an URI on Windows (is that the intended behaviour?)
       If 'cal' is a valid URI already then we are done here, as continuing would make
       it invalid. */
    if ((uri = xmlParseURI((const char *) cal)) != NULL) {
	xmlFreeURI(uri);
	return cal;
    }
    /* 'cal' can contain a relative path with backslashes. If that is processed
       by xmlSaveURI, they will be escaped and the external entity loader machinery
       will fail. So convert them to slashes. Misuse 'ret' for walking. */
    ret = cal;
    while (*ret != '\0') {
	if (*ret == '\\')
	    *ret = '/';
	ret++;
    }
#endif
    memset(&temp, 0, sizeof(temp));
    temp.path = (char *) cal;
    ret = xmlSaveUri(&temp);
    xmlFree(cal);
    return(ret);
}
#define bottom_uri
#include "elfgcchack.h"