summaryrefslogtreecommitdiff
path: root/content/urldb.c
blob: 435e0f61430a53713b10459bbd1011fee1a703fe (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
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
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
/*
 * This file is part of NetSurf, http://netsurf.sourceforge.net/
 * Licensed under the GNU General Public License,
 *                http://www.opensource.org/licenses/gpl-license
 * Copyright 2006 John M Bell <jmb202@ecs.soton.ac.uk>
 */

/** \file
 * Unified URL information database (implementation)
 *
 * URLs are stored in a tree-based structure as follows:
 *
 * The host component is extracted from each URL and, if a FQDN, split on
 * every '.'.The tree is constructed by inserting each FQDN segment in
 * reverse order. Duplicate nodes are merged.
 *
 * If the host part of an URL is an IP address, then this is added to the
 * tree verbatim (as if it were a TLD).
 *
 * This provides something looking like:
 *
 * 			      root (a sentinel)
 * 				|
 * 	-------------------------------------------------
 * 	|	|	|	|	|	|	|
 *     com     edu     gov  127.0.0.1  net     org     uk	TLDs
 * 	|	|	|		|	|	|
 *    google   ...     ...             ...     ...     co	2LDs
 * 	|						|
 *     www					       bbc  Hosts/Subdomains
 *							|
 *						       www	...
 *
 * Each of the nodes in this tree is a struct host_part. This stores the
 * FQDN segment (or IP address) with which the node is concerned. Each node
 * may contain further information about paths on a host (struct path_data)
 * or SSL certificate processing on a host-wide basis
 * (host_part::permit_invalid_certs).
 *
 * Path data is concerned with storing various metadata about the path in
 * question. This includes global history data, HTTP authentication details
 * and any associated HTTP cookies. This is stored as a tree of path segments
 * hanging off the relevant host_part node.
 *
 * Therefore, to find the last visited time of the URL
 * http://www.example.com/path/to/resource.html, the FQDN tree would be
 * traversed in the order root -> "com" -> "example" -> "www". The "www"
 * node would have attached to it a tree of struct path_data:
 *
 *			    (sentinel)
 *				|
 * 			       path
 * 				|
 * 			       to
 * 				|
 * 			   resource.html
 *
 * This represents the absolute path "/path/to/resource.html". The leaf node
 * "resource.html" contains the last visited time of the resource.
 *
 * The mechanism described above is, however, not particularly conducive to
 * fast searching of the database for a given URL (or URLs beginning with a
 * given prefix). Therefore, an anciliary data structure is used to enable
 * fast searching. This structure simply reflects the contents of the
 * database, with entries being added/removed at the same time as for the
 * core database. In order to ensure that degenerate cases are kept to a
 * minimum, we use an AAtree. This is an approximation of a Red-Black tree
 * with similar performance characteristics, but with a significantly
 * simpler implementation. Entries in this tree comprise pointers to the
 * leaf nodes of the host tree described above.
 */

#include <assert.h>
#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include "netsurf/image/bitmap.h"
#include "netsurf/content/urldb.h"
#include "netsurf/desktop/options.h"
#ifdef riscos
/** \todo lose this */
#include "netsurf/riscos/bitmap.h"
#endif
#include "netsurf/utils/log.h"
#include "netsurf/utils/url.h"
#include "netsurf/utils/utils.h"

struct cookie {
	char *name;		/**< Cookie name */
	char *value;		/**< Cookie value */
	char *comment;		/**< Cookie comment */
	time_t expires;		/**< Expiry timestamp, or 0 for session */
	time_t last_used;	/**< Last used time */
	bool secure;		/**< Only send for HTTPS requests */
	enum { COOKIE_NETSCAPE = 0,
		COOKIE_RFC2109 = 1,
		COOKIE_RFC2965 = 2
	} version;		/**< Specification compliance */
	bool no_destroy;	/**< Never destroy this cookie,
				 * unless it's expired */

	struct cookie *next;	/**< Next in list */
};

struct auth_data {
	char *realm;		/**< Protection realm */
	char *auth;		/**< Authentication details in form
				 * username:password */
};

struct url_internal_data {
	char *title;		/**< Resource title */
	unsigned int visits;	/**< Visit count */
	time_t last_visit;	/**< Last visit time */
	content_type type;	/**< Type of resource */
};

struct path_data {
	char *scheme;		/**< URL scheme for data */
	unsigned int port;	/**< Port number for data */
	char *segment;		/**< Path segment for this node */
	unsigned int frag_cnt;	/**< Number of entries in ::fragment */
	char **fragment;	/**< Array of fragments */

	struct bitmap *thumb;	/**< Thumbnail image of resource */
	struct url_internal_data url;	/**< URL data for resource */
	struct auth_data auth;	/**< Authentication data for resource */
	struct cookie *cookies;	/**< Cookies associated with resource */

	struct path_data *next;	/**< Next sibling */
	struct path_data *prev;	/**< Previous sibling */
	struct path_data *parent;	/**< Parent path segment */
	struct path_data *children;	/**< Child path segments */
	struct path_data *last;		/**< Last child */
};

struct host_part {
	/**< Known paths on this host. This _must_ be first so that
	 * struct host_part *h = (struct host_part *)mypath; works */
	struct path_data paths;
	bool permit_invalid_certs;	/**< Allow access to SSL protected
					 * resources on this host without
					 * verifying certificate authenticity
					 */

	char *part;		/**< Part of host string */

	struct host_part *next;	/**< Next sibling */
	struct host_part *prev;	/**< Previous sibling */
	struct host_part *parent;	/**< Parent host part */
	struct host_part *children;	/**< Child host parts */
};

struct search_node {
	const struct host_part *data;	/**< Host tree entry */

	unsigned int level;		/**< Node level */

	struct search_node *left;	/**< Left subtree */
	struct search_node *right;	/**< Right subtree */
};

/* Saving */
static void urldb_save_search_tree(struct search_node *root, FILE *fp);
static void urldb_count_urls(const struct path_data *root, time_t expiry,
		unsigned int *count);
static void urldb_write_paths(const struct path_data *parent,
		const char *host, FILE *fp, char **path, int *path_alloc,
		int *path_used, time_t expiry);

/* Iteration */
static bool urldb_iterate_partial_host(struct search_node *root,
		const char *prefix, bool (*callback)(const char *url));
static bool urldb_iterate_partial_path(const struct path_data *parent,
		const char *host, const char *prefix,
		char **path, int *path_alloc, int *path_used,
		bool (*callback)(const char *url));
static bool urldb_iterate_entries_host(struct search_node *parent,
		bool (*callback)(const char *url));
static bool urldb_iterate_entries_path(const char *host, char **path,
		int *path_alloc, int *path_used,
		const struct path_data *parent,
		bool (*callback)(const char *url));

/* Insertion */
static struct host_part *urldb_add_host_node(const char *part,
		struct host_part *parent);
static struct host_part *urldb_add_host(const char *host);
static struct path_data *urldb_add_path_node(const char *scheme,
		unsigned int port, const char *segment, const char *fragment,
		struct path_data *parent);
static struct path_data *urldb_add_path(const char *scheme,
		unsigned int port, const struct host_part *host,
		const char *path, const char *fragment);
static int urldb_add_path_fragment_cmp(const void *a, const void *b);
static struct path_data *urldb_add_path_fragment(struct path_data *segment,
		const char *fragment);

/* Lookup */
static struct path_data *urldb_find_url(const char *url);
static struct path_data *urldb_match_path(const struct path_data *parent,
		const char *path, const char *scheme, unsigned short port);

/* Dump */
static void urldb_dump_hosts(struct host_part *parent);
static void urldb_dump_paths(struct path_data *parent);
static void urldb_dump_search(struct search_node *parent, int depth);

/* Search tree */
static struct search_node *urldb_search_insert(struct search_node *root,
		const struct host_part *data);
static struct search_node *urldb_search_insert_internal(
		struct search_node *root, struct search_node *n);
static struct search_node *urldb_search_remove(struct search_node *root,
		const struct host_part *data);
static const struct host_part *urldb_search_find(struct search_node *root,
		const char *host);
static struct search_node *urldb_search_skew(struct search_node *root);
static struct search_node *urldb_search_split(struct search_node *root);
static int urldb_search_match_host(const struct host_part *a,
		const struct host_part *b);
static int urldb_search_match_string(const struct host_part *a,
		const char *b);
static int urldb_search_match_prefix(const struct host_part *a,
		const char *b);

/** Root database handle */
static struct host_part db_root;

/** Search trees - one per letter + 1 for IPs */
#define NUM_SEARCH_TREES 27
#define ST_IP 0
#define ST_DN 1
static struct search_node empty = { 0, 0, &empty, &empty };
static struct search_node *search_trees[NUM_SEARCH_TREES] = {
	&empty, &empty, &empty, &empty, &empty, &empty, &empty, &empty,
	&empty, &empty, &empty, &empty, &empty, &empty, &empty, &empty,
	&empty, &empty, &empty, &empty, &empty, &empty, &empty, &empty,
	&empty, &empty, &empty
};

/**
 * Import an URL database from file, replacing any existing database
 *
 * \param filename Name of file containing data
 */
void urldb_load(const char *filename)
{
#define MAXIMUM_URL_LENGTH 4096
	char s[MAXIMUM_URL_LENGTH];
	struct host_part *h;
	int urls;
	int i;
	int version;
	int length;
	FILE *fp;

	assert(filename);

	LOG(("Loading URL file"));

	fp = fopen(filename, "r");
	if (!fp) {
		LOG(("Failed to open file '%s' for reading", filename));
		return;
	}

	if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
		return;
	version = atoi(s);
	if (version < 105) {
		LOG(("Unsupported URL file version."));
		return;
	}
	if (version > 106) {
		LOG(("Unknown URL file version."));
		return;
	}

	while (fgets(s, MAXIMUM_URL_LENGTH, fp)) {
		/* get the hostname */
		length = strlen(s) - 1;
		s[length] = '\0';

		/* skip data that has ended up with a host of '' */
		if (length == 0) {
			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
			urls = atoi(s);
			for (i = 0; i < ((version == 105 ? 6 : 8) * urls);
					i++)
				if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
					break;
			continue;
		}

		h = urldb_add_host(s);
		if (!h)
			die("Memory exhausted whilst loading URL file");

		if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
			break;
		urls = atoi(s);

		/* load the non-corrupt data */
		for (i = 0; i < urls; i++) {
			struct path_data *p = NULL;

			if (version == 105) {
				if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
					break;
				length = strlen(s) - 1;
				s[length] = '\0';

				urldb_add_url(s);
				p = urldb_find_url(s);
			} else {
				char scheme[64];
				unsigned int port;

				if (!fgets(scheme, sizeof scheme, fp))
					break;
				length = strlen(scheme) - 1;
				scheme[length] = '\0';

				if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
					break;
				port = atoi(s);

				if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
					break;
				length = strlen(s) - 1;
				s[length] = '\0';

				p = urldb_add_path(scheme, port, h, s, NULL);
			}

			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
			if (p)
				p->url.visits = (unsigned int)atoi(s);

			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
			if (p)
				p->url.last_visit = (time_t)atoi(s);

			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
			if (p)
				p->url.type = (content_type)atoi(s);

			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
#ifdef riscos
			if (p && strlen(s) == 12) {
				/* ensure filename is 'XX.XX.XX.XX' */
				if ((s[2] == '.') && (s[5] == '.') &&
						(s[8] == '.')) {
					s[11] = '\0';
					p->thumb = bitmap_create_file(s);
				}
			}
#endif

			if (!fgets(s, MAXIMUM_URL_LENGTH, fp))
				break;
			length = strlen(s) - 1;
			if (p && length > 0) {
				s[length] = '\0';
				p->url.title = malloc(length + 1);
				if (p->url.title)
					memcpy(p->url.title, s, length + 1);
			}
		}
	}

	fclose(fp);
	LOG(("Successfully loaded URL file"));
#undef MAXIMUM_URL_LENGTH
}

/**
 * Export the current database to file
 *
 * \param filename Name of file to export to
 */
void urldb_save(const char *filename)
{
	FILE *fp;
	int i;

	assert(filename);

	fp = fopen(filename, "w");
	if (!fp) {
		LOG(("Failed to open file '%s' for writing", filename));
		return;
	}

	/* file format version number */
	fprintf(fp, "106\n");

	for (i = 0; i != NUM_SEARCH_TREES; i++) {
		urldb_save_search_tree(search_trees[i], fp);
	}

	fclose(fp);
}

/**
 * Save a search (sub)tree
 *
 * \param root Root of (sub)tree to save
 * \param fp File to write to
 */
void urldb_save_search_tree(struct search_node *parent, FILE *fp)
{
	char host[256];
	const struct host_part *h;
	unsigned int path_count = 0;
	char *path, *p, *end;
	int path_alloc = 64, path_used = 2;
	time_t expiry = time(NULL) - (60 * 60 * 24) * option_expire_url;

	if (parent == &empty)
		return;

	urldb_save_search_tree(parent->left, fp);

	path = malloc(path_alloc);
	if (!path)
		return;

	path[0] = '/';
	path[1] = '\0';

	for (h = parent->data, p = host, end = host + sizeof host;
			h && h != &db_root && p < end; h = h->parent) {
		int written = snprintf(p, end - p, "%s%s", h->part,
				(h->parent && h->parent->parent) ? "." : "");
		if (written < 0) {
			free(path);
			return;
		}
		p += written;
	}

	urldb_count_urls(&parent->data->paths, expiry, &path_count);

	if (path_count > 0) {
		fprintf(fp, "%s\n%i\n", host, path_count);

		urldb_write_paths(&parent->data->paths, host, fp,
				&path, &path_alloc, &path_used, expiry);
	}

	free(path);

	urldb_save_search_tree(parent->right, fp);
}

/**
 * Count number of URLs associated with a host
 *
 * \param root Root of path data tree
 * \param expiry Expiry time for URLs
 * \param count Pointer to count
 */
void urldb_count_urls(const struct path_data *root, time_t expiry,
		unsigned int *count)
{
	const struct path_data *p;

	if (!root->children) {
		if ((root->url.last_visit > expiry) &&
				(root->url.visits > 0))
			(*count)++;
	}

	for (p = root->children; p; p = p->next)
		urldb_count_urls(p, expiry, count);
}

/**
 * Write paths associated with a host
 *
 * \param parent Root of (sub)tree to write
 * \param host Current host name
 * \param fp File to write to
 * \param path Current path string
 * \param path_alloc Allocated size of path
 * \param path_used Used size of path
 * \param expiry Expiry time of URLs
 */
void urldb_write_paths(const struct path_data *parent, const char *host,
		FILE *fp, char **path, int *path_alloc, int *path_used,
		time_t expiry)
{
	const struct path_data *p;
	int i;
	int pused = *path_used;

	if (!parent->children) {
		/* leaf node */
		if (!((parent->url.last_visit > expiry) &&
				(parent->url.visits > 0)))
			/* expired */
			return;

		fprintf(fp, "%s\n", parent->scheme);

		if (parent->port)
			fprintf(fp,"%d\n", parent->port);
		else
			fprintf(fp, "\n");

		fprintf(fp, "%s\n", *path);

		/** \todo handle fragments? */

		fprintf(fp, "%i\n%i\n%i\n", parent->url.visits,
				(int)parent->url.last_visit,
				(int)parent->url.type);

#ifdef riscos
		if (parent->thumb)
			fprintf(fp, "%s\n", parent->thumb->filename);
		else
			fprintf(fp, "\n");
#else
		fprintf(fp, "\n");
#endif

		if (parent->url.title) {
			char *s = parent->url.title;
			for (i = 0; s[i] != '\0'; i++)
				if (s[i] < 32)
					s[i] = ' ';
			for (--i; ((i > 0) && (s[i] == ' ')); i--)
					s[i] = '\0';
			fprintf(fp, "%s\n", parent->url.title);
		} else
			fprintf(fp, "\n");
	}

	for (p = parent->children; p; p = p->next) {
		int len = *path_used + strlen(p->segment) + 1;
		if (*path_alloc < len) {
			char *temp = realloc(*path,
				(len > 64) ? len : *path_alloc + 64);
			if (!temp)
				return;
			*path = temp;
			*path_alloc = (len > 64) ? len : *path_alloc + 64;
		}

		strcat(*path, p->segment);
		if (p->children) {
			strcat(*path, "/");
		} else {
			len -= 1;
		}

		*path_used = len;

		urldb_write_paths(p, host, fp, path, path_alloc, path_used,
				expiry);

		/* restore path to its state on entry to this function */
		*path_used = pused;
		(*path)[pused - 1] = '\0';
	}
}

/**
 * Insert an URL into the database
 *
 * \param url URL to insert
 * \return true on success, false otherwise
 */
bool urldb_add_url(const char *url)
{
	struct host_part *h;
	struct path_data *p;
	char *fragment = NULL, *host, *plq, *scheme, *colon;
	unsigned short port;
	url_func_result ret;
	assert(url);

	/** \todo consider file: URLs */

	host = strchr(url, '#');
	if (host) {
		fragment = strdup(host+1);
		if (!fragment)
			return false;
	}

	/* extract host */
	ret = url_host(url, &host);
	if (ret != URL_FUNC_OK)
		return false;

	/* extract path, leafname, query */
	ret = url_plq(url, &plq);
	if (ret != URL_FUNC_OK) {
		free(host);
		free(fragment);
		return false;
	}

	/* extract scheme */
	ret = url_scheme(url, &scheme);
	if (ret != URL_FUNC_OK) {
		free(plq);
		free(host);
		free(fragment);
		return false;
	}

	colon = strrchr(host, ':');
	if (!colon) {
		port = 0;
	} else {
		*colon = '\0';
		port = atoi(colon + 1);
	}

	/* Get host entry */
	h = urldb_add_host(host);
	if (!h) {
		free(scheme);
		free(plq);
		free(host);
		free(fragment);
		return false;
	}

	/* Get path entry */
	p = urldb_add_path(scheme, port, h, plq, fragment);
	if (!p) {
		free(scheme);
		free(plq);
		free(host);
		free(fragment);
		return false;
	}

	return true;
}

/**
 * Set an URL's title string, replacing any existing one
 *
 * \param url The URL to look for
 * \param title The title string to use (copied)
 */
void urldb_set_url_title(const char *url, const char *title)
{
	struct path_data *p;
	char *temp;

	assert(url && title);

	p = urldb_find_url(url);
	if (!p)
		return;

	temp = strdup(title);
	if (!temp)
		return;

	free(p->url.title);
	p->url.title = temp;
}

/**
 * Set an URL's content type
 *
 * \param url The URL to look for
 * \param type The type to set
 */
void urldb_set_url_content_type(const char *url, content_type type)
{
	struct path_data *p;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return;

	p->url.type = type;
}

/**
 * Update an URL's visit data
 *
 * \param url The URL to update
 */
void urldb_update_url_visit_data(const char *url)
{
	struct path_data *p;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return;

	p->url.last_visit = time(NULL);
	p->url.visits++;
}

/**
 * Reset an URL's visit statistics
 *
 * \param url The URL to reset
 */
void urldb_reset_url_visit_data(const char *url)
{
	struct path_data *p;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return;

	p->url.last_visit = (time_t)0;
	p->url.visits = 0;
}


/**
 * Find data for an URL.
 *
 * \param url Absolute URL to look for
 * \return Pointer to result struct, or NULL
 */
const struct url_data *urldb_get_url_data(const char *url)
{
	struct path_data *p;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return NULL;

	return (struct url_data *)&p->url;
}

/**
 * Look up authentication details in database
 *
 * \param url Absolute URL to search for
 * \return Pointer to authentication details, or NULL if not found
 */
const char *urldb_get_auth_details(const char *url)
{
	struct path_data *p, *q;

	assert(url);

	/* add to the db, so our lookup will work */
	urldb_add_url(url);

	p = urldb_find_url(url);
	if (!p)
		return NULL;

	for (; p; p = p->parent) {
		/* The parent path entry is stored hung off the
		 * parent entry with an empty (not NULL) segment string.
		 * We look for this here.
		 */
		for (q = p->children; q; q = q->next) {
			if (strlen(q->segment) == 0)
				break;
		}

		if (q && q->auth.realm && q->auth.auth)
			break;
	}

	if (!q)
		return NULL;

	return q->auth.auth;
}

/**
 * Retrieve certificate verification permissions from database
 *
 * \param url Absolute URL to search for
 * \return true to permit connections to hosts with invalid certificates,
 * false otherwise.
 */
bool urldb_get_cert_permissions(const char *url)
{
	struct path_data *p;
	struct host_part *h;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return false;

	for (; p && p->parent; p = p->parent)
		/* do nothing */;

	h = (struct host_part *)p;

	return h->permit_invalid_certs;
}

/**
 * Set authentication data for an URL
 *
 * \param url The URL to consider
 * \param realm The authentication realm
 * \param auth The authentication details (in form username:password)
 */
void urldb_set_auth_details(const char *url, const char *realm,
		const char *auth)
{
	struct path_data *p;
	char *t1, *t2;

	assert(url && realm && auth);

	/* add url, in case it's missing */
	urldb_add_url(url);

	p = urldb_find_url(url);
	if (!p)
		return;

	/** \todo search subtree for same realm/auth details
	 * and remove them (as the lookup routine searches up the tree) */

	t1 = strdup(realm);
	t2 = strdup(auth);

	if (!t1 || !t2) {
		free(t1);
		free(t2);
		return;
	}

	free(p->auth.realm);
	free(p->auth.auth);

	p->auth.realm = t1;
	p->auth.auth = t2;
}

/**
 * Set certificate verification permissions
 *
 * \param url URL to consider
 * \param permit Set to true to allow invalid certificates
 */
void urldb_set_cert_permissions(const char *url, bool permit)
{
	struct path_data *p;
	struct host_part *h;

	assert(url);

	/* add url, in case it's missing */
	urldb_add_url(url);

	p = urldb_find_url(url);
	if (!p)
		return;

	for (; p && p->parent; p = p->parent)
		/* do nothing */;

	h = (struct host_part *)p;

	h->permit_invalid_certs = permit;
}

/**
 * Set thumbnail for url, replacing any existing thumbnail
 *
 * \param url Absolute URL to consider
 * \param bitmap Opaque pointer to thumbnail data
 */
void urldb_set_thumbnail(const char *url, struct bitmap *bitmap)
{
	struct path_data *p;

	assert(url && bitmap);

	p = urldb_find_url(url);
	if (!p)
		return;

	if (p->thumb)
		bitmap_destroy(p->thumb);

	p->thumb = bitmap;
}

/**
 * Retrieve thumbnail data for given URL
 *
 * \param url Absolute URL to search for
 * \return Pointer to thumbnail data, or NULL if not found.
 */
const struct bitmap *urldb_get_thumbnail(const char *url)
{
	struct path_data *p;

	assert(url);

	p = urldb_find_url(url);
	if (!p)
		return NULL;

	return p->thumb;
}

/**
 * Iterate over entries in the database which match the given prefix
 *
 * \param prefix Prefix to match
 * \param callback Callback function
 */
void urldb_iterate_partial(const char *prefix,
		bool (*callback)(const char *url))
{
	char host[256];
	char buf[260]; /* max domain + "www." */
	const char *slash;
	struct search_node *tree;
	const struct host_part *h;

	assert(prefix && callback);

	slash = strchr(prefix, '/');

	if (*prefix >= '0' && *prefix <= '9')
		tree = search_trees[ST_IP];
	else if (isalpha(*prefix))
		tree = search_trees[ST_DN + tolower(*prefix) - 'a'];
	else
		return;

	if (slash) {
		/* if there's a slash in the input, then we can
		 * assume that we're looking for a path */
		char *path, *domain = host;
		int path_alloc = 64, path_used = 2;

		snprintf(host, sizeof host, "%.*s", slash - prefix, prefix);

		h = urldb_search_find(tree, host);
		if (!h) {
			int len = slash - prefix;

			if ((len == 1 && tolower(host[0]) != 'w') ||
				(len == 2 && (tolower(host[0]) != 'w' ||
					tolower(host[1]) != 'w')) ||
				(len >= 3 &&
					strncasecmp(host, "www", 3))) {
				snprintf(buf, sizeof buf, "www.%s", host);
				h = urldb_search_find(
					search_trees[ST_DN + 'w' - 'a'],
					buf);
				if (!h)
					return;
				domain = buf;
			} else
				return;
		}

		path = malloc(path_alloc);
		if (!path)
			return;

		path[0] = '/';
		path[1] = '\0';

		urldb_iterate_partial_path(&h->paths, domain, slash + 1,
				&path, &path_alloc, &path_used, callback);

		free(path);
	} else {
		int len = strlen(prefix);

		/* looking for hosts */
		if (!urldb_iterate_partial_host(tree, prefix, callback))
			return;

		if ((len == 1 && tolower(prefix[0]) != 'w') ||
				(len == 2 && (tolower(prefix[0]) != 'w' ||
					tolower(prefix[1]) != 'w')) ||
				(len >= 3 &&
					strncasecmp(prefix, "www", 3))) {
			/* now look for www.prefix */
			snprintf(buf, sizeof buf, "www.%s", prefix);
			if(!urldb_iterate_partial_host(
					search_trees[ST_DN + 'w' - 'a'],
					buf, callback))
				return;
		}
	}
}

/**
 * Partial host iterator (internal)
 *
 * \param root Root of (sub)tree to traverse
 * \param prefix Prefix to match
 * \param callback Callback function
 * \return true to continue, false otherwise
 */
bool urldb_iterate_partial_host(struct search_node *root, const char *prefix,
		bool (*callback)(const char *url))
{
	int c;
	const struct host_part *h;
	char domain[256], *p, *end;
	char *path;
	int path_alloc = 64, path_used = 2;

	assert(root && prefix && callback);

	if (root == &empty)
		return true;

	c = urldb_search_match_prefix(root->data, prefix);

	if (c > 0)
		/* No match => look in left subtree */
		return urldb_iterate_partial_host(root->left, prefix,
				callback);
	else if (c < 0)
		/* No match => look in right subtree */
		return urldb_iterate_partial_host(root->right, prefix,
				callback);
	else {
		/* Match => iterate over l/r subtrees & process this node */
		if (!urldb_iterate_partial_host(root->left, prefix,
				callback))
			return false;

		/* Generate host string */
		for (h = root->data, p = domain,
				end = domain + sizeof domain;
				h && h != &db_root && p < end;
				h = h->parent) {
			int written = snprintf(p, end - p, "%s%s", h->part,
				(h->parent && h->parent->parent) ? "." : "");
			if (written < 0)
				return false;
			p += written;
		}

		path = malloc(path_alloc);
		if (!path)
			return false;

		path[0] = '/';
		path[1] = '\0';

		/* and extract all paths attached to this host */
		if (!urldb_iterate_entries_path(domain, &path, &path_alloc,
				&path_used, &root->data->paths, callback)) {
			free(path);
			return false;
		}

		free(path);

		if (!urldb_iterate_partial_host(root->right, prefix,
				callback))
			return false;
	}

	return true;
}

/**
 * Partial path iterator (internal)
 *
 * \param parent Root of (sub)tree to traverse
 * \param host Host string
 * \param prefix Prefix to match
 * \param path The built path up to this point
 * \param path_alloc Allocated size of path
 * \param path_used Used size of path
 * \param callback Callback function
 * \return true to continue, false otherwise
 */
bool urldb_iterate_partial_path(const struct path_data *parent,
		const char *host, const char *prefix,
		char **path, int *path_alloc, int *path_used,
		bool (*callback)(const char *url))
{
	const struct path_data *p;
	const char *slash, *end = prefix + strlen(prefix);
	int pused = *path_used;
	int c;

	slash = strchr(prefix, '/');
	if (!slash)
		slash = end;

	if (slash == prefix && *prefix == '/')
		/* Ignore "//" */
		return true;

	for (p = parent->children; p; p = p->next) {
		if ((c = strncasecmp(p->segment, prefix, slash - prefix)) < 0)
			/* didn't match, but may be more */
			continue;
		else if (c > 0)
			/* no more possible matches */
			break;

		/* prefix matches so far */
		int len = *path_used + strlen(p->segment) + 1;
		if (*path_alloc < len) {
			char *temp = realloc(*path,
					(len > 64) ? len : *path_alloc + 64);
			if (!temp)
				return false;
			*path = temp;
			*path_alloc = (len > 64) ? len : *path_alloc + 64;
		}

		strcat(*path, p->segment);
		if (p->children)
			strcat(*path, "/");
		else
			len -= 1;

		*path_used = len;

		if (slash == end) {
			/* we've run out of prefix, so all
			 * paths below this one match */
			if (!urldb_iterate_entries_path(host, path,
					path_alloc, path_used, p, callback))
				return false;
		} else {
			/* more prefix to go => recurse */
			if (!urldb_iterate_partial_path(p, host, slash + 1,
					path, path_alloc, path_used,
					callback))
				return false;
		}

		/* restore path to that from input for next child */
		*path_used = pused;
		(*path)[pused - 1] = '\0';
	}

	return true;
}

/**
 * Iterate over all entries in database
 *
 * \param callback Function to callback for each entry
 */
void urldb_iterate_entries(bool (*callback)(const char *url))
{
	int i;

	assert(callback);

	for (i = 0; i < NUM_SEARCH_TREES; i++) {
		if (!urldb_iterate_entries_host(search_trees[i],
				callback))
			break;
	}
}

/**
 * Host data iterator (internal)
 *
 * \param parent Root of subtree to iterate over
 * \param callback Callback function
 * \return true to continue, false otherwise
 */
bool urldb_iterate_entries_host(struct search_node *parent,
		bool (*callback)(const char *url))
{
	char domain[256], *p, *end;
	const struct host_part *h;
	char *path;
	int path_alloc = 64, path_used = 2;

	if (parent == &empty)
		return true;

	if (!urldb_iterate_entries_host(parent->left, callback))
		return false;

	for (h = parent->data, p = domain, end = domain + sizeof domain;
			h && h != &db_root && p < end; h = h->parent) {
		int written = snprintf(p, end - p, "%s%s", h->part,
				(h->parent && h->parent->parent) ? "." : "");
		if (written < 0)
			return false;
		p += written;
	}

	path = malloc(path_alloc);
	if (!path)
		return false;

	path[0] = '/';
	path[1] = '\0';

	if (!urldb_iterate_entries_path(domain, &path, &path_alloc,
			&path_used, &parent->data->paths, callback)) {
		free(path);
		return false;
	}

	free(path);

	if (!urldb_iterate_entries_host(parent->right, callback))
		return false;

	return true;
}

/**
 * Path data iterator (internal)
 *
 * \param host Host component of output URI
 * \param path The built path up to this point
 * \param path_alloc Allocated size of path
 * \param path_used Used size of path
 * \param parent Root of subtree to iterate over
 * \param callback Callback function to call
 * \return true to continue, false otherwise
 */
bool urldb_iterate_entries_path(const char *host, char **path,
		int *path_alloc, int *path_used,
		const struct path_data *parent,
		bool (*callback)(const char *url))
{
	const struct path_data *p;
	int pused = *path_used;

	if (!parent->children) {
		/* leaf node */
		int schemelen = strlen(parent->scheme);
		int hostlen = strlen(host);
		int prefixlen = schemelen + 3 /* :// */ +
				hostlen + 6 /* :NNNNN */;
		static char *url;
		static int url_alloc;
		int written;

		if (url_alloc < *path_used + prefixlen + 2) {
			char *temp = realloc(url, *path_used + prefixlen + 2);
			if (!temp)
				return false;
			url = temp;
			url_alloc = *path_used + prefixlen + 2;
		}

		written = sprintf(url, "%s://%s", parent->scheme, host);
		if (written < 0) {
			return false;
		}

		if (parent->port) {
			written = sprintf(url + schemelen + 3 + hostlen,
					":%d", parent->port);
			if (written < 0) {
				return false;
			}
			written += schemelen + 3 + hostlen;
		}

		written = sprintf(url + written, "%s", *path);
		if (written < 0) {
			return false;
		}

		/** \todo handle fragments? */

		if (!callback(url))
			return false;
	}

	for (p = parent->children; p; p = p->next) {
		int len = *path_used + strlen(p->segment) + 1;
		if (*path_alloc < len) {
			char *temp = realloc(*path,
				(len > 64) ? len : *path_alloc + 64);
			if (!temp)
				return false;
			*path = temp;
			*path_alloc = (len > 64) ? len : *path_alloc + 64;
		}

		strcat(*path, p->segment);
		if (p->children) {
			strcat(*path, "/");
		} else {
			len -= 1;
		}

		*path_used = len;

		if (!urldb_iterate_entries_path(host, path, path_alloc,
				path_used, p, callback))
			return false;

		/* restore path to its state on entry to this function */
		*path_used = pused;
		(*path)[pused - 1] = '\0';
	}

	return true;
}

/**
 * Add a host node to the tree
 *
 * \param part Host segment to add (or whole IP address) (copied)
 * \param parent Parent node to add to
 * \return Pointer to added node, or NULL on memory exhaustion
 */
struct host_part *urldb_add_host_node(const char *part,
		struct host_part *parent)
{
	struct host_part *d;

	assert(part && parent);

	d = calloc(1, sizeof(struct host_part));
	if (!d)
		return NULL;

	d->part = strdup(part);
	if (!d->part) {
		free(d);
		return NULL;
	}

	d->next = parent->children;
	if (parent->children)
		parent->children->prev = d;
	d->parent = parent;
	parent->children = d;

	return d;
}

/**
 * Add a host to the database, creating any intermediate entries
 *
 * \param host Hostname to add
 * \return Pointer to leaf node, or NULL on memory exhaustion
 */
struct host_part *urldb_add_host(const char *host)
{
	struct host_part *d = (struct host_part *) &db_root, *e;
	struct search_node *s;
	char buf[256]; /* 256 bytes is sufficient - domain names are
			* limited to 255 chars. */
	char *part;

	assert(host);

	if (*(host) >= '0' && *(host) <= '9') {
		/* Host is an IP, so simply add as TLD */

		/* Check for existing entry */
		for (e = d->children; e; e = e->next)
			if (strcasecmp(host, e->part) == 0)
				/* found => return it */
				return e;

		d = urldb_add_host_node(host, d);

		s = urldb_search_insert(search_trees[ST_IP], d);
		if (!s) {
			/* failed */
			d = NULL;
		} else {
			search_trees[ST_IP] = s;
		}

		return d;
	}

	/* Copy host string, so we can corrupt it */
	strncpy(buf, host, sizeof buf);
	buf[sizeof buf - 1] = '\0';

	/* Process FQDN segments backwards */
	do {
		part = strrchr(buf, '.');
		if (!part) {
			/* last segment */
			/* Check for existing entry */
			for (e = d->children; e; e = e->next)
				if (strcasecmp(buf, e->part) == 0)
					break;

			if (e) {
				d = e;
			} else {
				d = urldb_add_host_node(buf, d);
			}

			/* And insert into search tree */
			if (d) {
				if (isalpha(*buf)) {
					struct search_node **r;
					r = &search_trees[
						tolower(*buf) - 'a' + ST_DN];

					s = urldb_search_insert(*r, d);
					if (!s) {
						/* failed */
						d = NULL;
					} else {
						*r = s;
					}
				} else {
					d = NULL;
				}
			}
			break;
		}

		/* Check for existing entry */
		for (e = d->children; e; e = e->next)
			if (strcasecmp(part + 1, e->part) == 0)
				break;

		d = e ? e : urldb_add_host_node(part + 1, d);
		if (!d)
			break;

		*part = '\0';
	} while (1);

	return d;
}

/**
 * Add a path node to the tree
 *
 * \param scheme URL scheme associated with path (copied)
 * \param port Port number on host associated with path
 * \param segment Path segment to add (copied)
 * \param fragment URL fragment (copied), or NULL
 * \param parent Parent node to add to
 * \return Pointer to added node, or NULL on memory exhaustion
 */
struct path_data *urldb_add_path_node(const char *scheme, unsigned int port,
		const char *segment, const char *fragment,
		struct path_data *parent)
{
	struct path_data *d, *e;

	assert(scheme && segment && parent);

	d = calloc(1, sizeof(struct path_data));
	if (!d)
		return NULL;

	d->scheme = strdup(scheme);
	if (!d->scheme) {
		free(d);
		return NULL;
	}

	d->port = port;

	d->segment = strdup(segment);
	if (!d->segment) {
		free(d->scheme);
		free(d);
		return NULL;
	}

	if (fragment) {
		if (!urldb_add_path_fragment(d, fragment)) {
			free(d->segment);
			free(d->scheme);
			free(d);
			return NULL;
		}
	}

	for (e = parent->children; e; e = e->next)
		if (strcmp(e->segment, d->segment) > 0)
			break;

	if (e) {
		d->prev = e->prev;
		d->next = e;
		if (e->prev)
			e->prev->next = d;
		else
			parent->children = d;
		e->prev = d;
	} else if (!parent->children) {
		d->prev = d->next = NULL;
		parent->children = parent->last = d;
	} else {
		d->next = NULL;
		d->prev = parent->last;
		parent->last->next = d;
		parent->last = d;
	}
	d->parent = parent;

	return d;
}

/**
 * Add a path to the database, creating any intermediate entries
 *
 * \param scheme URL scheme associated with path
 * \param port Port number on host associated with path
 * \param host Host tree node to attach to
 * \param path Absolute path to add
 * \param fragment URL fragment, or NULL
 * \return Pointer to leaf node, or NULL on memory exhaustion
 */
struct path_data *urldb_add_path(const char *scheme, unsigned int port,
		const struct host_part *host, const char *path,
		const char *fragment)
{
	struct path_data *d, *e;
	char *buf;
	char *segment, *slash;

	assert(scheme && host && path);

	d = (struct path_data *) &host->paths;

	/* Copy path string, so we can corrupt it */
	buf = malloc(strlen(path) + 1);
	if (!buf)
		return NULL;

	/* + 1 to strip leading '/' */
	strcpy(buf, path + 1);

	segment = buf;

	/* Process path segments */
	do {
		slash = strchr(segment, '/');
		if (!slash) {
			/* last segment */
			/* look for existing entry */
			for (e = d->children; e; e = e->next)
				if (strcmp(segment, e->segment) == 0 &&
						strcasecmp(scheme,
						e->scheme) == 0 &&
						e->port == port)
					break;

			d = e ? urldb_add_path_fragment(e, fragment) :
					urldb_add_path_node(scheme, port,
					segment, fragment, d);
			break;
		}

		*slash = '\0';

		/* look for existing entry */
		for (e = d->children; e; e = e->next)
			if (strcmp(segment, e->segment) == 0 &&
					strcasecmp(scheme, e->scheme) == 0 &&
					e->port == port)
				break;

		d = e ? e : urldb_add_path_node(scheme, port, segment,
				NULL, d);
		if (!d)
			break;

		segment = slash + 1;
	} while (1);

	free(buf);

	return d;
}

/**
 * Fragment comparator callback for qsort
 */
int urldb_add_path_fragment_cmp(const void *a, const void *b)
{
	return strcasecmp(*((const char **) a), *((const char **) b));
}

/**
 * Add a fragment to a path segment
 *
 * \param segment Path segment to add to
 * \param fragment Fragment to add (copied), or NULL
 * \return segment or NULL on memory exhaustion
 */
struct path_data *urldb_add_path_fragment(struct path_data *segment,
		const char *fragment)
{
	char **temp;

	assert(segment);

	/* If no fragment, this function is a NOP
	 * This may seem strange, but it makes the rest
	 * of the code cleaner */
	if (!fragment)
		return segment;

	temp = realloc(segment->fragment,
			(segment->frag_cnt + 1) * sizeof(char *));
	if (!temp)
		return NULL;

	segment->fragment = temp;
	segment->fragment[segment->frag_cnt] = strdup(fragment);
	if (!segment->fragment[segment->frag_cnt]) {
		/* Don't free temp - it's now our buffer */
		return NULL;
	}

	segment->frag_cnt++;

	/* We want fragments in alphabetical order, so sort them
	 * It may prove better to insert in alphabetical order instead */
	qsort(segment->fragment, segment->frag_cnt, sizeof (char *),
			urldb_add_path_fragment_cmp);

	return segment;
}

/**
 * Find an URL in the database
 *
 * \param url The URL to find
 * \return Pointer to path data, or NULL if not found
 */
struct path_data *urldb_find_url(const char *url)
{
	const struct host_part *h;
	struct path_data *p;
	struct search_node *tree;
	char *host, *plq, *scheme, *colon;
	unsigned short port;
	url_func_result ret;

	assert(url);

	/** \todo consider file: URLs */

	/* extract host */
	ret = url_host(url, &host);
	if (ret != URL_FUNC_OK)
		return NULL;

	/* extract path, leafname, query */
	ret = url_plq(url, &plq);
	if (ret != URL_FUNC_OK) {
		free(host);
		return NULL;
	}

	/* extract scheme */
	ret = url_scheme(url, &scheme);
	if (ret != URL_FUNC_OK) {
		free(plq);
		free(host);
		return NULL;
	}

	colon = strrchr(host, ':');
	if (!colon) {
		port = 0;
	} else {
		*colon = '\0';
		port = atoi(colon + 1);
	}

	if (*host >= '0' && *host <= '9')
		tree = search_trees[ST_IP];
	else if (isalpha(*host))
		tree = search_trees[ST_DN + tolower(*host) - 'a'];
	else {
		free(plq);
		free(host);
		free(scheme);
		return NULL;
	}

	h = urldb_search_find(tree, host);
	if (!h) {
		free(plq);
		free(host);
		free(scheme);
		return NULL;
	}

	p = urldb_match_path(&h->paths, plq, scheme, port);

	free(plq);
	free(host);
	free(scheme);

	return p;
}

/**
 * Match a path string
 *
 * \param parent Path (sub)tree to look in
 * \param path The path to search for
 * \param scheme The URL scheme associated with the path
 * \param port The port associated with the path
 * \return Pointer to path data or NULL if not found.
 */
struct path_data *urldb_match_path(const struct path_data *parent,
		const char *path, const char *scheme, unsigned short port)
{
	struct path_data *p;
	const char *slash;

	if (*path == '\0')
		return (struct path_data *)parent;

	slash = strchr(path + 1, '/');
	if (!slash)
		slash = path + strlen(path);

	for (p = parent->children; p; p = p->next) {
		if (strncmp(p->segment, path + 1, slash - path - 1) == 0 &&
				strcmp(p->scheme, scheme) == 0 &&
				p->port == port)
			break;
	}

	if (p) {
		return urldb_match_path(p, slash, scheme, port);
	}

	return NULL;
}

/**
 * Dump URL database to stderr
 */
void urldb_dump(void)
{
	int i;

	urldb_dump_hosts(&db_root);

	for (i = 0; i != NUM_SEARCH_TREES; i++)
		urldb_dump_search(search_trees[i], 0);
}

/**
 * Dump URL database hosts to stderr
 *
 * \param parent Parent node of tree to dump
 */
void urldb_dump_hosts(struct host_part *parent)
{
	struct host_part *h;

	if (parent->part) {
		LOG(("%s", parent->part));

		LOG(("\t%s invalid SSL certs",
			parent->permit_invalid_certs ? "Permits" : "Denies"));
	}

	/* Dump path data */
	urldb_dump_paths(&parent->paths);

	/* and recurse */
	for (h = parent->children; h; h = h->next)
		urldb_dump_hosts(h);
}

/**
 * Dump URL database paths to stderr
 *
 * \param parent Parent node of tree to dump
 */
void urldb_dump_paths(struct path_data *parent)
{
	struct path_data *p;
	unsigned int i;

	if (parent->segment) {
		LOG(("\t%s : %u", parent->scheme, parent->port));

		LOG(("\t\t'%s'", parent->segment));

		for (i = 0; i != parent->frag_cnt; i++)
			LOG(("\t\t\t#%s", parent->fragment[i]));
	}

	/* and recurse */
	for (p = parent->children; p; p = p->next)
		urldb_dump_paths(p);
}

/**
 * Dump search tree
 *
 * \param parent Parent node of tree to dump
 * \param depth Tree depth
 */
void urldb_dump_search(struct search_node *parent, int depth)
{
	const struct host_part *h;
	int i;

	if (parent == &empty)
		return;

	urldb_dump_search(parent->left, depth + 1);

	for (i = 0; i != depth; i++)
			fputc(' ', stderr);

	for (h = parent->data; h; h = h->parent) {
		fprintf(stderr, "%s", h->part);
		if (h->parent && h->parent->parent)
			fputc('.', stderr);
	}

	fputc('\n', stderr);

	urldb_dump_search(parent->right, depth + 1);
}

/**
 * Insert a node into the search tree
 *
 * \param root Root of tree to insert into
 * \param data User data to insert
 * \return Pointer to updated root, or NULL if failed
 */
struct search_node *urldb_search_insert(struct search_node *root,
		const struct host_part *data)
{
	struct search_node *n;

	assert(root && data);

	n = malloc(sizeof(struct search_node));
	if (!n)
		return NULL;

	n->level = 1;
	n->data = data;
	n->left = n->right = &empty;

	root = urldb_search_insert_internal(root, n);

	return root;
}

/**
 * Insert node into search tree
 *
 * \param root Root of (sub)tree to insert into
 * \param n Node to insert
 * \return Pointer to updated root
 */
struct search_node *urldb_search_insert_internal(struct search_node *root,
		struct search_node *n)
{
	assert(root && n);

	if (root == &empty) {
		root = n;
	} else {
		int c = urldb_search_match_host(root->data, n->data);

		if (c > 0) {
			root->left = urldb_search_insert_internal(
					root->left, n);
		} else if (c < 0) {
			root->right = urldb_search_insert_internal(
					root->right, n);
		} else {
			/* exact match */
			free(n);
			return root;
		}

		root = urldb_search_skew(root);
		root = urldb_search_split(root);
	}

	return root;
}

/**
 * Delete a node from a search tree
 *
 * \param root Tree to remove from
 * \param data Data to delete
 * \return Updated root of tree
 */
struct search_node *urldb_search_remove(struct search_node *root,
		const struct host_part *data)
{
	static struct search_node *last, *deleted;

	assert(root && data);

	if (root != &empty) {
		int c = urldb_search_match_host(root->data, data);

		last = root;
		if (c > 0) {
			root->left = urldb_search_remove(root->left, data);
		} else {
			deleted = root;
			root->right = urldb_search_remove(root->right, data);
		}
	}

	if (root == last) {
		if (deleted != &empty &&
				urldb_search_match_host(deleted->data,
						data) == 0) {
			deleted->data = last->data;
			deleted = &empty;
			root = root->right;
		}
	} else {
		if (root->left->level < root->level - 1 ||
				root->right->level < root->level - 1) {
			if (root->right->level > --root->level)
				root->right->level = root->level;

			root = urldb_search_skew(root);
			root->right = urldb_search_skew(root->right);
			root->right->right =
				urldb_search_skew(root->right->right);
			root = urldb_search_split(root);
			root->right = urldb_search_split(root->right);
		}
	}

	return root;
}

/**
 * Find a node in a search tree
 *
 * \param root Tree to look in
 * \param host Host to find
 * \return Pointer to host tree node, or NULL if not found
 */
const struct host_part *urldb_search_find(struct search_node *root,
		const char *host)
{
	int c;

	assert(root && host);

	if (root == &empty) {
		return NULL;
	}

	c = urldb_search_match_string(root->data, host);

	if (c > 0)
		return urldb_search_find(root->left, host);
	else if (c < 0)
		return urldb_search_find(root->right, host);
	else
		return root->data;
}

/**
 * Compare a pair of host_parts
 *
 * \param a
 * \param b
 * \return 0 if match, non-zero, otherwise
 */
int urldb_search_match_host(const struct host_part *a,
		const struct host_part *b)
{
	int ret;

	assert(a && b);

	/* traverse up tree to root, comparing parts as we go. */
	for (; a && b; a = a->parent, b = b->parent)
		if ((ret = strcasecmp(a->part, b->part)) != 0)
			/* They differ => return the difference here */
			return ret;

	/* If we get here then either:
	 *    a) The path lengths differ
	 * or b) The hosts are identical
	 */
	if (a && !b)
		/* len(a) > len(b) */
		return 1;
	else if (!a && b)
		/* len(a) < len(b) */
		return -1;

	/* identical */
	return 0;
}

/**
 * Compare host_part with a string
 *
 * \param a
 * \param b
 * \return 0 if match, non-zero, otherwise
 */
int urldb_search_match_string(const struct host_part *a,
		const char *b)
{
	const char *end, *dot;
	int plen, ret;

	assert(a && b);

	if (*b >= '0' && *b <= '9') {
		/* IP address */
		return strcasecmp(a->part, b);
	}

	end = b + strlen(b);

	while (b < end && a) {
		dot = strchr(b, '.');
		if (!dot) {
			/* last segment */
			dot = end;
		}

		/* Compare strings (length limited) */
		if ((ret = strncasecmp(a->part, b, dot - b)) != 0)
			/* didn't match => return difference */
			return ret;

		/* The strings matched, now check that the lengths do, too */
		plen = strlen(a->part);

		if (plen > dot - b)
			/* len(a) > len(b) */
			return 1;
		else if (plen < dot - b)
			/* len(a) < len(b) */
			return -1;

		b = dot + 1;
		a = a->parent;
	}

	/* If we get here then either:
	 *    a) The path lengths differ
	 * or b) The hosts are identical
	 */
	if (a && a != &db_root && b >= end)
		/* len(a) > len(b) */
		return 1;
	else if (!a && b < end)
		/* len(a) < len(b) */
		return -1;

	/* Identical */
	return 0;
}

/**
 * Compare host_part with prefix
 *
 * \param a
 * \param b
 * \return 0 if match, non-zero, otherwise
 */
int urldb_search_match_prefix(const struct host_part *a,
		const char *b)
{
	const char *end, *dot;
	int plen, ret;

	assert(a && b);

	if (*b >= '0' && *b <= '9') {
		/* IP address */
		return strncasecmp(a->part, b, strlen(b));
	}

	end = b + strlen(b);

	while (b < end && a) {
		dot = strchr(b, '.');
		if (!dot) {
			/* last segment */
			dot = end;
		}

		/* Compare strings (length limited) */
		if ((ret = strncasecmp(a->part, b, dot - b)) != 0)
			/* didn't match => return difference */
			return ret;

		/* The strings matched */
		if (dot < end) {
			/* Consider segment lengths only in the case
			 * where the prefix contains segments */
			plen = strlen(a->part);
			if (plen > dot - b)
				/* len(a) > len(b) */
				return 1;
			else if (plen < dot - b)
				/* len(a) < len(b) */
				return -1;
		}

		b = dot + 1;
		a = a->parent;
	}

	/* If we get here then either:
	 *    a) The path lengths differ
	 * or b) The hosts are identical
	 */
	if (a && a != &db_root && b >= end)
		/* len(a) > len(b) => prefix matches */
		return 0;
	else if (!a && b < end)
		/* len(a) < len(b) => prefix does not match */
		return -1;

	/* Identical */
	return 0;
}

/**
 * Rotate a subtree right
 *
 * \param root Root of subtree to rotate
 * \return new root of subtree
 */
struct search_node *urldb_search_skew(struct search_node *root)
{
	struct search_node *temp;

	assert(root);

	if (root->left->level == root->level) {
		temp = root->left;
		root->left = temp->right;
		temp->right = root;
		root = temp;
	}

	return root;
}

/**
 * Rotate a node left, increasing the parent's level
 *
 * \param root Root of subtree to rotate
 * \return New root of subtree
 */
struct search_node *urldb_search_split(struct search_node *root)
{
	struct search_node *temp;

	assert(root);

	if (root->right->right->level == root->level) {
		temp = root->right;
		root->right = temp->left;
		temp->left = root;
		root = temp;

		root->level++;
	}

	return root;
}

#ifdef TEST
int main(void)
{
	struct host_part *h;
	struct path_data *p;

	h = urldb_add_host("127.0.0.1");
	if (!h) {
		LOG(("failed adding host"));
		return 1;
	}

	/* Get host entry */
	h = urldb_add_host("netsurf.strcprstskrzkrk.co.uk");
	if (!h) {
		LOG(("failed adding host"));
		return 1;
	}

	/* Get path entry */
	p = urldb_add_path("http", 80, h, "/path/to/resource.htm?a=b", "zz");
	if (!p) {
		LOG(("failed adding path"));
		return 1;
	}

	p = urldb_add_path("http", 80, h, "/path/to/resource.htm?a=b", "aa");
	if (!p) {
		LOG(("failed adding path"));
		return 1;
	}

	p = urldb_add_path("http", 80, h, "/path/to/resource.htm?a=b", "yy");
	if (!p) {
		LOG(("failed adding path"));
		return 1;
	}

	urldb_dump();

	return 0;
}
#endif