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
|
/**
* Copyright 2014 JogAmp Community. All rights reserved.
* Copyright 2006, 2010 The Apache Software Foundation.
*
* This code is derived from the Apache Harmony project's {@code class java.net.URI.Helper},
* and has been heavily modified for GlueGen/JogAmp.
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the LICENSE.txt file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.jogamp.common.net;
import java.io.File;
import java.io.UnsupportedEncodingException;
import java.net.MalformedURLException;
import java.net.URISyntaxException;
import java.util.StringTokenizer;
import java.util.regex.Pattern;
import jogamp.common.Debug;
import com.jogamp.common.util.IOUtil;
import com.jogamp.common.util.PropertyAccess;
/**
* This class implements an immutable Uri as defined by <a href="https://tools.ietf.org/html/rfc2396">RFC 2396</a>.
* <p>
* Character encoding is employed as defined by <a href="https://tools.ietf.org/html/rfc3986">RFC 3986</a>,
* see <a href="https://tools.ietf.org/html/rfc3986#section-2.1">RFC 3986 section 2.1</a>,
* while multibyte unicode characters are preserved in encoded parts.
* </p>
*
* <pre>
1 [scheme:]scheme-specific-part[#fragment]
2 [scheme:][//authority]path[?query][#fragment]
3 [scheme:][//[user-info@]host[:port]]path[?query][#fragment]
scheme-specific-part: [//authority]path[?query]
authority: [user-info@]host[:port]
* </pre>
* <p>
* <a href="https://tools.ietf.org/html/rfc3986#section-2.2">RFC 3986 section 2.2</a> <i>Reserved Characters</i> (January 2005)
* <table border="1">
<tr>
<td><code>!</code></td>
<td><code>*</code></td>
<td><code>'</code></td>
<td><code>(</code></td>
<td><code>)</code></td>
<td><code>;</code></td>
<td><code>:</code></td>
<td><code>@</code></td>
<td><code>&</code></td>
<td><code>=</code></td>
<td><code>+</code></td>
<td><code>$</code></td>
<td><code>,</code></td>
<td><code>/</code></td>
<td><code>?</code></td>
<td><code>#</code></td>
<td><code>[</code></td>
<td><code>]</code></td>
</tr>
* </table>
* </p>
* <p>
* <a href="https://tools.ietf.org/html/rfc3986#section-2.3">RFC 3986 section 2.3</a> <i>Unreserved Characters</i> (January 2005)
* <table border="1">
<tr>
<td><code>A</code></td>
<td><code>B</code></td>
<td><code>C</code></td>
<td><code>D</code></td>
<td><code>E</code></td>
<td><code>F</code></td>
<td><code>G</code></td>
<td><code>H</code></td>
<td><code>I</code></td>
<td><code>J</code></td>
<td><code>K</code></td>
<td><code>L</code></td>
<td><code>M</code></td>
<td><code>N</code></td>
<td><code>O</code></td>
<td><code>P</code></td>
<td><code>Q</code></td>
<td><code>R</code></td>
<td><code>S</code></td>
<td><code>T</code></td>
<td><code>U</code></td>
<td><code>V</code></td>
<td><code>W</code></td>
<td><code>X</code></td>
<td><code>Y</code></td>
<td><code>Z</code></td>
</tr>
<tr>
<td><code>a</code></td>
<td><code>b</code></td>
<td><code>c</code></td>
<td><code>d</code></td>
<td><code>e</code></td>
<td><code>f</code></td>
<td><code>g</code></td>
<td><code>h</code></td>
<td><code>i</code></td>
<td><code>j</code></td>
<td><code>k</code></td>
<td><code>l</code></td>
<td><code>m</code></td>
<td><code>n</code></td>
<td><code>o</code></td>
<td><code>p</code></td>
<td><code>q</code></td>
<td><code>r</code></td>
<td><code>s</code></td>
<td><code>t</code></td>
<td><code>u</code></td>
<td><code>v</code></td>
<td><code>w</code></td>
<td><code>x</code></td>
<td><code>y</code></td>
<td><code>z</code></td>
</tr>
<tr>
<td><code>0</code></td>
<td><code>1</code></td>
<td><code>2</code></td>
<td><code>3</code></td>
<td><code>4</code></td>
<td><code>5</code></td>
<td><code>6</code></td>
<td><code>7</code></td>
<td><code>8</code></td>
<td><code>9</code></td>
<td><code>-</code></td>
<td><code>_</code></td>
<td><code>.</code></td>
<td><code>~</code></td>
</tr>
* </table>
* </p>
* <p>
* Other characters in a Uri must be percent encoded.
* </p>
* @since 2.2.1
*/
public class Uri {
private static final boolean DEBUG;
private static final boolean DEBUG_SHOWFIX;
static {
Debug.initSingleton();
DEBUG = IOUtil.DEBUG || Debug.debug("Uri");
DEBUG_SHOWFIX = PropertyAccess.isPropertyDefined("jogamp.debug.Uri.ShowFix", true);
}
/**
* Usually used to fix a path from a previously contained and opaque Uri,
* i.e. {@link #getContainedUri()}.
* <p>
* Such an opaque Uri w/ erroneous encoding may have been injected via
* {@link #valueOf(URI)} and {@link #valueOf(URL)} where the given URL or URI was opaque!
* </p>
* <p>
* This remedies issues when dealing w/ java URI/URL opaque sources,
* which do not comply to the spec, i.e. containe un-encoded chars, e.g. ':', '$', ..
* </p>
*/
private static final int PARSE_HINT_FIX_PATH = 1 << 0;
private static final String DIGITS = "0123456789ABCDEF";
private static final String ENCODING = "UTF8";
private static final String MSG_ENCODING_NA = "Charset UTF8 not available";
private static final Pattern patternSingleFS = Pattern.compile("/{1}");
/**
* RFC 3986 section 2.3 Unreserved Characters (January 2005)
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String UNRESERVED = "_-.~";
// Harmony: _ - ! . ~ ' ( ) *
private static final String punct = ",;:$&+=";
// Harmony: , ; : $ & + =
/**
* RFC 3986 section 2.2 Reserved Characters (January 2005)
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String RESERVED = punct + "!*\'()@/?#[]";
// Harmony: , ; : $ & + = ? / [ ] @
public static final String RESERVED_2 = punct + "!*\'()@/?[]";
// Harmony: , ; : $ & + = ? / [ ] @
// Bug 908, issues w/ windows file path char: $ ^ ~ # [ ]
// Windows invalid File characters: * ? " < > |
/**
* Valid charset for RFC 2396 {@code authority}'s {@code user-info},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String USERINFO_LEGAL = UNRESERVED + punct;
// Harmony: someLegal = unreserved + punct -> _ - ! . ~ ' ( ) * , ; : $ & + =
/**
* Valid charset for RFC 2396 {@code authority},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String AUTHORITY_LEGAL = "@[]" + USERINFO_LEGAL;
/**
* Valid charset for RFC 2396 {@code path},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String PATH_LEGAL = "/!" + UNRESERVED; // no RESERVED chars but '!', to allow JAR Uris;
// Harmony: "/@" + unreserved + punct -> / @ _ - ! . ~ \ ' ( ) * , ; : $ & + =
/**
* Valid charset for RFC 2396 {@code query},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String QUERY_LEGAL = UNRESERVED + RESERVED_2 + "\\\"";
// Harmony: unreserved + reserved + "\\\""
/**
* Valid charset for RFC 2396 {@code scheme-specific-part},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String SSP_LEGAL = QUERY_LEGAL;
// Harmony: unreserved + reserved
/**
* Valid charset for RFC 2396 {@code fragment},
* additional to legal {@code alphanum} characters.
* <p>
* {@value} + {@code alphanum}
* </p>
*/
public static final String FRAG_LEGAL = UNRESERVED + RESERVED;
// Harmony: unreserved + reserved
/** {@value} */
public static final char SCHEME_SEPARATOR = ':';
/** {@value} */
public static final char QUERY_SEPARATOR = '?';
/** {@value} */
public static final char FRAGMENT_SEPARATOR = '#';
/** {@value} */
public static final String FILE_SCHEME = "file";
/** {@value} */
public static final String HTTP_SCHEME = "http";
/** {@value} */
public static final String HTTPS_SCHEME = "https";
/** {@value} */
public static final String JAR_SCHEME = "jar";
/** A JAR sub-protocol is separated from the JAR entry w/ this separator {@value}. Even if no class is specified '!/' must follow!. */
public static final char JAR_SCHEME_SEPARATOR = '!';
/**
* Immutable RFC3986 encoded string.
*/
public static class Encoded implements Comparable<Encoded>, CharSequence {
private final String s;
/**
* Casts the given encoded String by creating a new Encoded instance.
* <p>
* No encoding will be performed, use with care.
* </p>
*/
public static Encoded cast(final String encoded) {
return new Encoded(encoded);
}
Encoded(final String encodedString) {
this.s = encodedString;
}
/**
* Encodes all characters into their hexadecimal value prepended by '%', except:
* <ol>
* <li>letters ('a'..'z', 'A'..'Z')</li>
* <li>numbers ('0'..'9')</li>
* <li>characters in the legal-set parameter</li>
* <li> others (unicode characters that are not in
* US-ASCII set, and are not ISO Control or are not ISO Space characters)</li>
* </ol>
* <p>
* Uses {@link Uri#encode(String, String)} for implementation..
* </p>
*
* @param vanilla the string to be encoded
* @param legal extended character set, allowed to be preserved in the vanilla string
*/
public Encoded(final String vanilla, final String legal) {
this.s = encode(vanilla, legal);
}
public boolean isASCII() { return false; }
/** Returns the encoded String */
public final String get() { return s; }
/**
* Decodes the string argument which is assumed to be encoded in the {@code
* x-www-form-urlencoded} MIME content type using the UTF-8 encoding scheme.
* <p>
*'%' and two following hex digit characters are converted to the
* equivalent byte value. All other characters are passed through
* unmodified.
* </p>
* <p>
* e.g. "A%20B%20C %24%25" -> "A B C $%"
* </p>
* <p>
* Uses {@link Uri#decode(String)} for implementation..
* </p>
*/
public final String decode() { return Uri.decode(s); }
//
// Basic Object / Identity
//
/**
* {@inheritDoc}
* <p>
* Returns the encoded String, same as {@link #get()}.
* </p>
*/
@Override
public final String toString() { return s; }
@Override
public final int hashCode() { return s.hashCode(); }
/**
* {@inheritDoc}
*
* @param o The comparison argument, either a {@link Encoded} or a {@link String}
*
* @return {@code true} if the given object is equivalent to this instance,
* otherwise {@code false}.
*
* @see #compareTo(Encoded)
* @see #equalsIgnoreCase(Encoded)
*/
@Override
public final boolean equals(final Object o) {
if (this == o) {
return true;
}
if (o instanceof Encoded) {
return s.equals(((Encoded)o).s);
}
return s.equals(o);
}
//
// CharSequence
//
@Override
public final int length() { return s.length(); }
@Override
public final char charAt(final int index) { return s.charAt(index); }
@Override
public final CharSequence subSequence(final int start, final int end) { return s.subSequence(start, end); }
@Override
public final int compareTo(final Encoded o) { return s.compareTo(o.s); }
//
// String derived ..
//
/** See {@link String#concat(String)}. */
public Encoded concat(final Encoded encoded) { return new Encoded(s.concat(encoded.s)); }
/** See {@link String#substring(int)}. */
public final Encoded substring(final int start) { return new Encoded(s.substring(start)); }
/** See {@link String#substring(int, int)}. */
public final Encoded substring(final int start, final int end) { return new Encoded(s.substring(start, end)); }
/** See {@link String#indexOf(int)}. */
public final int indexOf(final int ch) { return s.indexOf(ch); }
/** See {@link String#indexOf(int, int)}. */
public final int indexOf(final int ch, final int fromIndex) { return s.indexOf(ch, fromIndex); }
/** See {@link String#indexOf(String)}. */
public final int indexOf(final String str) { return s.indexOf(str); }
/** See {@link String#indexOf(String, int)}. */
public final int indexOf(final String str, final int fromIndex) { return s.indexOf(str, fromIndex); }
/** See {@link String#lastIndexOf(int)}. */
public final int lastIndexOf(final int ch) { return s.lastIndexOf(ch); }
/** See {@link String#lastIndexOf(int, int)}. */
public int lastIndexOf(final int ch, final int fromIndex) { return s.lastIndexOf(ch, fromIndex); }
/** See {@link String#lastIndexOf(String)}. */
public int lastIndexOf(final String str) { return s.lastIndexOf(str); }
/** See {@link String#lastIndexOf(String, int)}. */
public int lastIndexOf(final String str, final int fromIndex) { return s.lastIndexOf(str, fromIndex); }
/** See {@link String#startsWith(String, int)} */
public boolean startsWith(final String prefix, final int toffset) { return s.startsWith(prefix, toffset); }
/** See {@link String#endsWith(String)} */
public boolean endsWith(final String suffix) { return s.endsWith(suffix); }
/** See {@link String#equalsIgnoreCase(String)}. */
public final boolean equalsIgnoreCase(final Encoded anotherEncoded) { return s.equalsIgnoreCase(anotherEncoded.s); }
}
public static class ASCIIEncoded extends Encoded {
/**
* Casts the given encoded String by creating a new ASCIIEncoded instance.
* <p>
* No encoding will be performed, use with care.
* </p>
*/
public static ASCIIEncoded cast(final String encoded) {
return new ASCIIEncoded(encoded, null);
}
private ASCIIEncoded(final String encoded, final Object unused) {
super(encoded);
}
/**
* Other characters, which are Unicode chars that are not US-ASCII, and are
* not ISO Control or are not ISO Space chars are not preserved
* and encoded into their hexidecimal value prepended by '%'.
* <p>
* For example: Euro currency symbol -> "%E2%82%AC".
* </p>
* <p>
* Uses {@link Uri#encodeToASCIIString(String)} for implementation.
* </p>
* @param unicode unencoded input
*/
public ASCIIEncoded(final String unicode) {
super(encodeToASCIIString(unicode));
}
public boolean isASCII() { return true; }
}
private static void encodeChar2UTF8(final StringBuilder buf, final char ch) {
final byte[] bytes;
try {
bytes = new String(new char[] { ch }).getBytes(ENCODING);
} catch (final UnsupportedEncodingException e) {
throw new RuntimeException(MSG_ENCODING_NA, e);
}
// FIXME: UTF-8 produces more than one byte ? Optimization might be possible.
for (int j = 0; j < bytes.length; j++) {
final byte b = bytes[j];
buf.append('%');
buf.append(DIGITS.charAt( ( b & 0xf0 ) >> 4 ));
buf.append(DIGITS.charAt( b & 0xf ));
}
}
/**
* All characters are encoded into their hexadecimal value prepended by '%', except:
* <ol>
* <li>letters ('a'..'z', 'A'..'Z')</li>
* <li>numbers ('0'..'9')</li>
* <li>characters in the legal-set parameter</li>
* <li> others (unicode characters that are not in
* US-ASCII set, and are not ISO Control or are not ISO Space characters)</li>
* </ol>
* <p>
* Use {@link #encodeToASCIIString(String)} for US-ASCII encoding.
* </p>
* <p>
* Consider using {@link Encoded#Encoded(String, String)} in APIs
* to distinguish encoded from unencoded data by type.
* </p>
*
* @param vanilla the string to be encoded
* @param legal extended character set, allowed to be preserved in the vanilla string
* @return java.lang.String the converted string
*/
public static String encode(final String vanilla, final String legal) {
if( null == vanilla ) {
return null;
}
final StringBuilder buf = new StringBuilder();
for (int i = 0; i < vanilla.length(); i++) {
final char ch = vanilla.charAt(i);
if ( (ch >= 'a' && ch <= 'z') ||
(ch >= 'A' && ch <= 'Z') ||
(ch >= '0' && ch <= '9') ||
legal.indexOf(ch) > -1 ||
( ch > 127 && !Character.isSpaceChar(ch) && !Character.isISOControl(ch) )
) {
buf.append(ch);
} else {
encodeChar2UTF8(buf, ch);
}
}
return buf.toString();
}
/**
* Other characters, which are Unicode chars that are not US-ASCII, and are
* not ISO Control or are not ISO Space chars are not preserved
* and encoded into their hexidecimal value prepended by '%'.
* <p>
* For example: Euro currency symbol -> "%E2%82%AC".
* </p>
* <p>
* Consider using {@link ASCIIEncoded#ASCIIEncoded(String)} in APIs
* to distinguish encoded from unencoded data by type.
* </p>
* @param unicode string to be converted
* @return java.lang.String the converted string
*/
public static String encodeToASCIIString(final String unicode) {
final StringBuilder buf = new StringBuilder();
for (int i = 0; i < unicode.length(); i++) {
final char ch = unicode.charAt(i);
if (ch <= 127) {
buf.append(ch);
} else {
encodeChar2UTF8(buf, ch);
}
}
return buf.toString();
}
/**
* Safe {@link Encoded#decode()} call on optional {@code encoded} instance.
* @param encoded {@link Encoded} instance to be decoded, may be {@code null}.
* @return the {@link Encoded#decode() decoded} String or {@code null} if {@code encoded} was {@code null}.
*/
public static String decode(final Encoded encoded) {
return null != encoded ? encoded.decode() : null;
}
/**
* Decodes the string argument which is assumed to be encoded in the {@code
* x-www-form-urlencoded} MIME content type using the UTF-8 encoding scheme.
* <p>
*'%' and two following hex digit characters are converted to the
* equivalent byte value. All other characters are passed through
* unmodified.
* </p>
* <p>
* e.g. "A%20B%20C %24%25" -> "A B C $%"
* </p>
*
* @param encoded The encoded string.
* @return java.lang.String The decoded version.
*/
public static String decode(final String encoded) {
if( null == encoded ) {
return null;
}
final StringBuilder result = new StringBuilder();
final byte[] buf = new byte[32];
int bufI = 0;
for (int i = 0; i < encoded.length();) {
final char c = encoded.charAt(i);
if (c == '%') {
bufI = 0;
do {
if (i + 2 >= encoded.length()) {
throw new IllegalArgumentException("missing '%' hex-digits at index "+i);
}
final int d1 = Character.digit(encoded.charAt(i + 1), 16);
final int d2 = Character.digit(encoded.charAt(i + 2), 16);
if (d1 == -1 || d2 == -1) {
throw new IllegalArgumentException("invalid hex-digits at index "+i+": "+encoded.substring(i, i + 3));
}
buf[bufI++] = (byte) ((d1 << 4) + d2);
if( 32 == bufI ) {
appendUTF8(result, buf, bufI);
bufI = 0;
}
i += 3;
} while (i < encoded.length() && encoded.charAt(i) == '%');
if( 0 < bufI ) {
appendUTF8(result, buf, bufI);
}
} else {
result.append(c);
i++;
}
}
return result.toString();
}
private static void appendUTF8(final StringBuilder sb, final byte[] buf, final int count) {
try {
sb.append(new String(buf, 0, count, ENCODING));
} catch (final UnsupportedEncodingException e) {
throw new RuntimeException(MSG_ENCODING_NA, e);
}
}
/**
* Creates a new Uri instance using the given arguments.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code [scheme:]scheme-specific-part[#fragment]}
* </p>
*
* @param scheme the unencoded scheme part of the Uri.
* @param ssp the unencoded scheme-specific-part of the Uri.
* @param fragment the unencoded fragment part of the Uri.
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri create(final String scheme, final String ssp, final String fragment) throws URISyntaxException {
if ( emptyString(scheme) && emptyString(ssp) && emptyString(fragment) ) {
throw new URISyntaxException("", "all empty parts");
}
final StringBuilder uri = new StringBuilder();
if ( !emptyString(scheme) ) {
uri.append(scheme);
uri.append(SCHEME_SEPARATOR);
}
if ( !emptyString(ssp) ) {
// QUOTE ILLEGAL CHARACTERS
uri.append(encode(ssp, SSP_LEGAL));
}
if ( !emptyString(fragment) ) {
uri.append(FRAGMENT_SEPARATOR);
// QUOTE ILLEGAL CHARACTERS
uri.append(encode(fragment, FRAG_LEGAL));
}
return new Uri(new Encoded(uri.toString()), false, 0);
}
/**
* Creates a new Uri instance using the given arguments.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code [scheme:][user-info@]host[:port][path][?query][#fragment]}
* </p>
*
* @param scheme the unencoded scheme part of the Uri.
* @param userinfo the unencoded user information of the Uri for authentication and authorization.
* @param host the unencoded host name of the Uri.
* @param port the port number of the Uri.
* @param path the unencoded path to the resource on the host.
* @param query the unencoded query part of the Uri to specify parameters for the resource.
* @param fragment the unencoded fragment part of the Uri.
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri create (final String scheme, final String userinfo, String host, final int port,
final String path, final String query, final String fragment) throws URISyntaxException {
if ( emptyString(scheme) && emptyString(userinfo) && emptyString(host) && emptyString(path) &&
emptyString(query) && emptyString(fragment) ) {
throw new URISyntaxException("", "all empty parts");
}
if ( !emptyString(scheme) && !emptyString(path) && path.length() > 0 && path.charAt(0) != '/') {
throw new URISyntaxException(path, "path doesn't start with '/'");
}
final StringBuilder uri = new StringBuilder();
if ( !emptyString(scheme) ) {
uri.append(scheme);
uri.append(SCHEME_SEPARATOR);
}
if ( !emptyString(userinfo) || !emptyString(host) || port != -1) {
uri.append("//");
}
if ( !emptyString(userinfo) ) {
// QUOTE ILLEGAL CHARACTERS in userinfo
uri.append(encode(userinfo, USERINFO_LEGAL));
uri.append('@');
}
if ( !emptyString(host) ) {
// check for ipv6 addresses that hasn't been enclosed
// in square brackets
if (host.indexOf(SCHEME_SEPARATOR) != -1 && host.indexOf(']') == -1
&& host.indexOf('[') == -1) {
host = "[" + host + "]";
}
uri.append(host);
}
if ( port != -1 ) {
uri.append(SCHEME_SEPARATOR);
uri.append(port);
}
if ( !emptyString(path) ) {
// QUOTE ILLEGAL CHARS
uri.append(encode(path, PATH_LEGAL));
}
if ( !emptyString(query) ) {
uri.append(QUERY_SEPARATOR);
// QUOTE ILLEGAL CHARS
uri.append(encode(query, QUERY_LEGAL));
}
if ( !emptyString(fragment) ) {
// QUOTE ILLEGAL CHARS
uri.append(FRAGMENT_SEPARATOR);
uri.append(encode(fragment, FRAG_LEGAL));
}
return new Uri(new Encoded(uri.toString()), true, 0);
}
/**
* Creates a new Uri instance using the given arguments.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code [scheme:]host[path][#fragment]}
* </p>
*
* @param scheme the unencoded scheme part of the Uri.
* @param host the unencoded host name of the Uri.
* @param path the unencoded path to the resource on the host.
* @param fragment the unencoded fragment part of the Uri.
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri create(final String scheme, final String host, final String path, final String fragment) throws URISyntaxException {
return create(scheme, null, host, -1, path, null, fragment);
}
/**
* Creates a new Uri instance using the given arguments.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code [scheme:][//authority][path][?query][#fragment]}
* </p>
*
* @param scheme the unencoded scheme part of the Uri.
* @param authority the unencoded authority part of the Uri.
* @param path the unencoded path to the resource on the host.
* @param query the unencoded query part of the Uri to specify parameters for the resource.
* @param fragment the unencoded fragment part of the Uri.
*
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri create(final String scheme, final String authority, final String path, final String query, final String fragment) throws URISyntaxException {
if ( emptyString(scheme) && emptyString(authority) && emptyString(path) &&
emptyString(query) && emptyString(fragment) ) {
throw new URISyntaxException("", "all empty parts");
}
if ( !emptyString(scheme) && !emptyString(path) && path.length() > 0 && path.charAt(0) != '/') {
throw new URISyntaxException(path, "path doesn't start with '/'");
}
final StringBuilder uri = new StringBuilder();
if ( !emptyString(scheme) ) {
uri.append(scheme);
uri.append(SCHEME_SEPARATOR);
}
if ( !emptyString(authority) ) {
uri.append("//");
// QUOTE ILLEGAL CHARS
uri.append(encode(authority, AUTHORITY_LEGAL));
}
if ( !emptyString(path) ) {
// QUOTE ILLEGAL CHARS
uri.append(encode(path, PATH_LEGAL));
}
if ( !emptyString(query) ) {
// QUOTE ILLEGAL CHARS
uri.append(QUERY_SEPARATOR);
uri.append(encode(query, QUERY_LEGAL));
}
if ( !emptyString(fragment) ) {
// QUOTE ILLEGAL CHARS
uri.append(FRAGMENT_SEPARATOR);
uri.append(encode(fragment, FRAG_LEGAL));
}
return new Uri(new Encoded(uri.toString()), false, 0);
}
/**
* Casts the given encoded String to a {@link Encoded#cast(String) new Encoded instance}
* used to create the resulting Uri instance via {@link #Uri(Encoded)}.
* <p>
* No encoding will be performed on the given {@code encodedUri}, use with care.
* </p>
* @throws URISyntaxException
*/
public static Uri cast(final String encodedUri) throws URISyntaxException {
return new Uri(Encoded.cast(encodedUri));
}
/**
* Creates a new Uri instance using the given file-path argument.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code file:path}
* </p>
*
* @param path the path of the {@code file} {@code schema}.
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri valueOfFilepath(final String path) throws URISyntaxException {
if ( emptyString(path) ) {
throw new URISyntaxException("", "empty path");
}
if ( path.charAt(0) != '/' ) {
throw new URISyntaxException(path, "path doesn't start with '/'");
}
final StringBuilder uri = new StringBuilder();
uri.append(FILE_SCHEME);
uri.append(SCHEME_SEPARATOR);
// QUOTE ILLEGAL CHARS
uri.append(encode(path, PATH_LEGAL));
return new Uri(new Encoded(uri.toString()), false, 0);
}
/**
* Creates a new Uri instance using the given File instance.
* <p>
* This constructor first creates a temporary Uri string from the given components. This
* string will be parsed later on to create the Uri instance.
* </p>
* <p>
* {@code file:path}
* </p>
*
* @param file using {@link IOUtil#slashify(String, boolean, boolean) slashified} {@link File#getAbsolutePath() absolute-path}
* for the path of the {@code file} {@code schema}, utilizing {@link #valueOfFilepath(String)}.
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri valueOf(final File file) throws URISyntaxException {
return Uri.valueOfFilepath(IOUtil.slashify(file.getAbsolutePath(), true, file.isDirectory()));
}
/**
* Creates a new Uri instance using the given URI instance.
* <p>
* Re-encoding will be performed if the given URI is {@link URI#isOpaque() not opaque}.
* </p>
* <p>
* See {@link #PARSE_HINT_FIX_PATH} for issues of injecting opaque URLs.
* </p>
*
* @param uri A given URI instance
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri valueOf(final java.net.URI uri) throws URISyntaxException {
if( uri.isOpaque()) {
// opaque, without host validation.
// Note: This may induce encoding errors of authority and path, see {@link #PARSE_HINT_FIX_PATH}
return new Uri(new Encoded( uri.toString() ), false, 0);
} else if( null != uri.getHost() ) {
// with host validation
return Uri.create(uri.getScheme(), uri.getUserInfo(), uri.getHost(), uri.getPort(),
uri.getPath(), uri.getQuery(), uri.getFragment());
} else {
// without host validation
return Uri.create(uri.getScheme(), uri.getAuthority(),
uri.getPath(), uri.getQuery(), uri.getFragment());
}
}
/**
* Creates a new Uri instance using the given URL instance,
* convenient wrapper for {@link #valueOf(URI)} and {@link URL#toURI()}.
* <p>
* Re-encoding will be performed if the given URL is {@link URI#isOpaque() not opaque}, see {@link #valueOf(URI)}.
* </p>
* <p>
* See {@link #PARSE_HINT_FIX_PATH} for issues of injecting opaque URLs.
* </p>
*
* @param url A given URL instance
*
* @throws URISyntaxException
* if the temporary created string doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
*/
public static Uri valueOf(final java.net.URL url) throws URISyntaxException {
return valueOf(url.toURI());
}
//
// All string fields are encoded!
//
/** Encoded input string used at construction, never {@code null}. */
public final Encoded input;
private final Object lazyLock = new Object();
/** Encoded input string used at construction, in US-ASCII encoding. */
private ASCIIEncoded inputASCII;
private int hash;
/** Encoded {@code scheme}, {@code null} if undefined. */
public final Encoded scheme;
/** Encoded {@code scheme-specific-part}, never {@code null}. */
public final Encoded schemeSpecificPart;
/** Encoded {@code path} part of {@code scheme-specific-part}, never {@code null}. */
public final Encoded path;
/** Indicating whether {@code authority} part is defined or not. */
public final boolean hasAuthority;
/** Encoded {@code authority} part of {@code scheme-specific-part}, {@code null} if undefined. */
public final Encoded authority;
/** Encoded {@code userinfo} part of {@code authority} and {@code scheme-specific-part}, {@code null} if undefined. */
public final Encoded userInfo; // part of authority
/** Encoded {@code host} part of {@code authority} and {@code scheme-specific-part}, {@code null} if undefined. */
public final Encoded host; // part of authority
/** Encoded {@code port} part of {@code authority} and {@code scheme-specific-part}, {@code -1} if undefined. */
public final int port; // part of authority
/** Encoded {@code query} part of {@code scheme-specific-part}, {@code null} if undefined. */
public final Encoded query;
/** Encoded {@code fragment}, {@code null} if undefined. */
public final Encoded fragment;
/** Indicating whether this Uri is absolute, i.e. has a {@code scheme} and hence an absolute {@code scheme-specific-part}. */
public final boolean absolute;
/**
* Indicating whether this Uri is opaque, i.e. non-hierarchical {@code scheme-specific-part}.
* <p>
* An opaque Uri has no {@code scheme-specific-part} being parsed,
* i.e. {@code path}, {@code query} and {@code authority} are {@code null}.
* </p>
*/
public final boolean opaque;
/**
* Creates a new Uri instance according to the given encoded string {@code uri}.
*
* @param uri the RFC3986 encoded RFC2396 Uri representation to be parsed into a Uri object
* @throws URISyntaxException
* if the given string {@code uri} doesn't fit to the
* specification RFC2396 and RFC3986 or could not be parsed correctly.
*/
public Uri(final Encoded uri) throws URISyntaxException {
this(uri, false, 0);
}
/** Returns true, if this instance is a {@code file} {@code scheme}, otherwise false. */
public final boolean isFileScheme() {
return FILE_SCHEME.equals( scheme.get() );
}
/**
* Returns the encoded {@link #input}, never {@code null}.
*/
public final Encoded getEncoded() {
return input;
}
/**
* Returns the encoded {@link #input} as String, never {@code null}, same as {@link #getEncoded()}.
*/
@Override
public final String toString() {
return input.get();
}
/**
* Returns the encoded {@link #input} encoded in US-ASCII.
*/
public ASCIIEncoded toASCIIString() {
synchronized( lazyLock ) {
if( null == inputASCII ) {
inputASCII = new ASCIIEncoded(input.get());
}
return inputASCII;
}
}
/**
* Returns a new {@link URI} instance using the encoded {@link #input} string, {@code new URI(uri.input)},
* i.e. no re-encoding will be performed.
* @see #toURIReencoded(boolean)
* @see #valueOf(URI)
*/
public final java.net.URI toURI() {
try {
return new java.net.URI(input.get());
} catch (final URISyntaxException e) {
throw new Error(e); // Can't happen
}
}
/**
* Returns a new {@link URI} instance based upon this instance.
* <p>
* All Uri parts of this instance will be decoded
* and encoded by the URI constructor, i.e. re-encoding will be performed.
* </p>
*
* @throws URISyntaxException
* if the given string {@code uri} doesn't fit to the
* specification RFC2396 or could not be parsed correctly.
* @see #toURI()
* @see #valueOf(URI)
*/
public final java.net.URI toURIReencoded() throws URISyntaxException {
final java.net.URI recomposedURI;
if( opaque ) {
// opaque, without host validation
recomposedURI = new java.net.URI(decode(scheme), decode(schemeSpecificPart), decode(fragment));
} else if( null != host ) {
// with host validation
recomposedURI = new java.net.URI(decode(scheme), decode(userInfo), decode(host), port,
decode(path), decode(query), decode(fragment));
} else {
// without host validation
recomposedURI = new java.net.URI(decode(scheme), decode(authority),
decode(path), decode(query), decode(fragment));
}
return recomposedURI;
}
/**
* Returns a new {@link URL} instance using the encoded {@link #input} string, {@code new URL(uri.input)},
* i.e. no re-encoding will be performed.
* @throws MalformedURLException
* if an error occurs while creating the URL or no protocol
* handler could be found.
*/
public final java.net.URL toURL() throws MalformedURLException {
if (!absolute) {
throw new IllegalArgumentException("Cannot convert relative Uri: "+input);
}
return new java.net.URL(input.get());
}
/**
* If this instance {@link #isFileScheme() is a file scheme},
* implementation decodes <i>[ "//"+{@link #authority} ] + {@link #path}</i>,<br>
* then it processes the result if {@link File#separatorChar} <code> == '\\'</code>
* as follows:
* <ul>
* <li>slash -> backslash</li>
* <li>drop a starting single backslash, preserving windows UNC</li>
* </ul>
* and returns the resulting new {@link File} instance.
* <p>
* Otherwise implementation returns {@code null}.
* </p>
*/
public final File toFile() {
if( isFileScheme() ) {
final String authorityS;
if( null == authority ) {
authorityS = "";
} else {
authorityS = "//"+authority.decode();
}
final String path = authorityS+this.path.decode();
if( File.separator.equals("\\") ) {
final String r = patternSingleFS.matcher(path).replaceAll("\\\\");
if( r.startsWith("\\") && !r.startsWith("\\\\") ) { // '\\\\' denotes UNC hostname, which shall not be cut-off
return new File(r.substring(1));
} else {
return new File(r);
}
}
return new File(path);
}
return null;
}
/**
* If this instance's {@link #schemeSpecificPart} contains a Uri itself, a sub-Uri,
* return {@link #schemeSpecificPart} + {@code #} {@link #fragment} via it's own new Uri instance.
* <p>
* In case this Uri is a {@code jar-scheme}, the {@code query} is omitted,
* since it shall be invalid for {@code jar-schemes} anyway.
* </p>
* <p>
* Otherwise method returns {@code null}.
* </p>
* <pre>
* Example 1:
* This instance: <code>jar:<i>scheme2</i>:/some/path/gluegen-rt.jar!/com/jogamp/common/GlueGenVersion.class</code>
* Returned Uri: <code><i>scheme2</i>:/some/path/gluegen-rt.jar</code>
*
* Example 2:
* This instance: <code>jar:<i>scheme2</i>:/some/path/gluegen-rt.jar!/com/jogamp/common/GlueGenVersion.class?lala=01#fragment</code>
* Returned Uri: <code><i>scheme2</i>:/some/path/gluegen-rt.jar#fragment</code>
*
* Example 3:
* This instance: <code>scheme1:<i>scheme2</i>:/some/path/gluegen-rt.jar?lala=01#fragment</code>
* Returned Uri: <code><i>scheme2</i>:/some/path/gluegen-rt.jar?lala=01#fragment</code>
* </pre>
* @throws URISyntaxException
*/
public final Uri getContainedUri() throws URISyntaxException {
if( !emptyString(schemeSpecificPart) ) {
final StringBuilder sb = new StringBuilder();
if( scheme.equals(JAR_SCHEME) ) {
final int idx = schemeSpecificPart.lastIndexOf(JAR_SCHEME_SEPARATOR);
if (0 > idx) {
throw new URISyntaxException(input.get(), "missing jar separator");
}
sb.append( schemeSpecificPart.get().substring(0, idx) ); // exclude '!/'
} else {
sb.append( schemeSpecificPart.get() );
}
if ( !emptyString(fragment) ) {
sb.append(FRAGMENT_SEPARATOR);
sb.append(fragment);
}
try {
final int parseHints = opaque ? PARSE_HINT_FIX_PATH : 0;
final Uri res = new Uri(new Encoded(sb.toString()), false, parseHints);
if( null != res.scheme ) {
return res;
}
} catch(final URISyntaxException e) {
// OK, does not contain uri
if( DEBUG ) {
e.printStackTrace();
}
}
}
return null;
}
/**
* Return a new Uri instance representing the parent path of this Uri,
* while cutting of optional {@code query} and {@code fragment} parts.
* <p>
* Method is {@code jar-file-entry} aware, i.e. will return the parent entry if exists.
* </p>
* <p>
* If this Uri does not contain any path separator, or a parent folder Uri cannot be found, method returns {@code null}.
* </p>
* <pre>
* Example-1:
* This instance : <code>jar:http://some/path/gluegen-rt.jar!/com/jogamp/common/GlueGenVersion.class</code>
* Returned Uri #1: <code>jar:http://some/path/gluegen-rt.jar!/com/jogamp/common/</code>
* Returned Uri #2: <code>jar:http://some/path/gluegen-rt.jar!/com/jogamp/</code>
*
* Example-2:
* This instance : <code>http://some/path/gluegen-rt.jar</code>
* Returned Uri #1: <code>http://some/path/</code>
* Returned Uri #2: <code>http://some/</code>
* </pre>
*/
public final Uri getParent() {
final int pl = null!=schemeSpecificPart? schemeSpecificPart.length() : 0;
if(pl != 0) {
final int e = schemeSpecificPart.lastIndexOf("/");
if( e > 0 ) { // 0 == e: no path
if( e < pl - 1 ) {
// path is file or has a query
try {
return new Uri( new Encoded( scheme.get()+SCHEME_SEPARATOR+schemeSpecificPart.get().substring(0, e+1) ) );
} catch (final URISyntaxException ue) {
// not complete, hence removed authority, or even root folder -> return null
}
}
// path is a directory ..
final int p = schemeSpecificPart.lastIndexOf("/", e-1);
if( p > 0 ) {
try {
return new Uri( new Encoded( scheme.get()+SCHEME_SEPARATOR+schemeSpecificPart.get().substring(0, p+1) ) );
} catch (final URISyntaxException ue) {
// not complete, hence removed authority, or even root folder -> return null
}
}
}
}
return null;
}
/**
* Concatenates the given encoded string to the {@link #getEncoded() encoded uri}
* of this instance and returns {@link #Uri(Encoded) a new Uri instance} with the result.
*
* @throws URISyntaxException
* if the concatenated string {@code uri} doesn't fit to the
* specification RFC2396 and RFC3986 or could not be parsed correctly.
*/
public final Uri concat(final Uri.Encoded suffix) throws URISyntaxException {
if( null == suffix ) {
return this;
} else {
return new Uri( input.concat(suffix) );
}
}
/**
* Returns a new Uri instance w/ the given new query {@code newQuery}.
*
* @throws URISyntaxException if this Uri is {@link #opaque}
* or if the new string {@code uri} doesn't fit to the
* specification RFC2396 and RFC3986 or could not be parsed correctly.
*/
public final Uri getNewQuery(final String newQuery) throws URISyntaxException {
if( opaque ) {
throw new URISyntaxException(input.decode(), "Opaque Uri cannot permute by query");
} else if( null != host ) {
// with host validation
return Uri.create(decode(scheme), decode(userInfo), decode(host), port,
decode(path), newQuery, decode(fragment));
} else {
// without host validation
return Uri.create(decode(scheme), decode(authority),
decode(path), newQuery, decode(fragment));
}
}
/// NEW START
/**
* The URI's <code><i>protocol</i>:/some/path/gluegen-rt.jar</code>
* parent dirname URI <code><i>protocol</i>:/some/path/</code> will be returned,
* or {@code null} if not applicable.
* <p>
* <i>protocol</i> may be "file", "http", etc..
* </p>
*
* @return "<i>protocol</i>:/some/path/"
* @throws IllegalArgumentException if the URI doesn't match the expected formatting, or is null
* @throws URISyntaxException
*/
public Uri getDirectory() throws URISyntaxException {
final String uriS = input.get();
// from
// file:/some/path/gluegen-rt.jar _or_ rsrc:gluegen-rt.jar
// to
// file:/some/path/ _or_ rsrc:
int idx = uriS.lastIndexOf('/');
if(0 > idx) {
// no abs-path, check for protocol terminator ':'
idx = uriS.lastIndexOf(':');
if(0 > idx) {
throw new URISyntaxException(input.get(), "no scheme terminator ':'");
}
}
try {
return Uri.cast(uriS.substring(0, idx+1)); // exclude jar name, include terminal '/' or ':'
} catch (final URISyntaxException ue) {
if( DEBUG ) {
ue.printStackTrace();
}
}
return null;
}
/**
* Generates a URI for the <i>relativePath</i> relative to the <i>baseURI</i>,
* hence the result is a absolute location.
* <p>
* Impl. operates on the <i>scheme-specific-part</i>, and hence is sub-protocol savvy.
* </p>
* <p>
* In case <i>baseURI</i> is not a path ending w/ '/', it's a assumed to be a file and it's parent is being used.
* </p>
*
* @param baseURI denotes a URI to a directory ending w/ '/', or a file. In the latter case the file's directory is being used.
* @param relativePath denotes a relative file to the baseLocation's parent directory (URI encoded)
* @throws URISyntaxException if path is empty or has no parent directory available while resolving <code>../</code>
*/
public Uri getRelativeOf(final Encoded relativePath) throws URISyntaxException {
return compose(scheme, schemeSpecificPart, relativePath, fragment);
}
static Uri compose(final Encoded scheme, final Encoded schemeSpecificPart, final Encoded relativePath, final Encoded fragment) throws URISyntaxException {
String schemeSpecificPartS = schemeSpecificPart.get();
// cut off optional query in scheme-specific-part
final String query;
final int queryI = schemeSpecificPartS.lastIndexOf(QUERY_SEPARATOR);
if( queryI >= 0 ) {
query = schemeSpecificPartS.substring(queryI+1);
schemeSpecificPartS = schemeSpecificPartS.substring(0, queryI);
} else {
query = null;
}
if( null != relativePath ) {
if( !schemeSpecificPartS.endsWith("/") ) {
schemeSpecificPartS = IOUtil.getParentOf(schemeSpecificPartS);
}
schemeSpecificPartS = schemeSpecificPartS + relativePath.get();
}
schemeSpecificPartS = IOUtil.cleanPathString( schemeSpecificPartS );
final StringBuilder uri = new StringBuilder();
uri.append(scheme.get());
uri.append(':');
uri.append(schemeSpecificPartS);
if ( null != query ) {
uri.append(QUERY_SEPARATOR);
uri.append(query);
}
if ( null != fragment ) {
uri.append(FRAGMENT_SEPARATOR);
uri.append(fragment.get());
}
return Uri.cast(uri.toString());
}
/// NEW END
/**
* {@inheritDoc}
* <p>
* Compares this Uri instance with the given argument {@code o} and
* determines if both are equal. Two Uri instances are equal if all single
* parts are identical in their meaning.
* </p>
*
* @param o
* the Uri this instance has to be compared with.
* @return {@code true} if both Uri instances point to the same resource,
* {@code false} otherwise.
*/
@Override
public final boolean equals(final Object o) {
if (!(o instanceof Uri)) {
return false;
}
final Uri uri = (Uri) o;
if (uri.fragment == null && fragment != null || uri.fragment != null && fragment == null) {
return false;
} else if (uri.fragment != null && fragment != null) {
if (!equalsHexCaseInsensitive(uri.fragment, fragment)) {
return false;
}
}
if (uri.scheme == null && scheme != null || uri.scheme != null && scheme == null) {
return false;
} else if (uri.scheme != null && scheme != null) {
if (!uri.scheme.equalsIgnoreCase(scheme)) {
return false;
}
}
if (uri.opaque && opaque) {
return equalsHexCaseInsensitive(uri.schemeSpecificPart, schemeSpecificPart);
} else if (!uri.opaque && !opaque) {
if (!equalsHexCaseInsensitive(path, uri.path)) {
return false;
}
if (uri.query != null && query == null || uri.query == null && query != null) {
return false;
} else if (uri.query != null && query != null) {
if (!equalsHexCaseInsensitive(uri.query, query)) {
return false;
}
}
if (uri.authority != null && authority == null || uri.authority == null && authority != null) {
return false;
} else if (uri.authority != null && authority != null) {
if (uri.host != null && host == null || uri.host == null && host != null) {
return false;
} else if (uri.host == null && host == null) {
// both are registry based, so compare the whole authority
return equalsHexCaseInsensitive(uri.authority, authority);
} else { // uri.host != null && host != null, so server-based
if (!host.equalsIgnoreCase(uri.host)) {
return false;
}
if (port != uri.port) {
return false;
}
if ( uri.userInfo != null && userInfo == null ||
uri.userInfo == null && userInfo != null
) {
return false;
} else if (uri.userInfo != null && userInfo != null) {
return equalsHexCaseInsensitive(userInfo, uri.userInfo);
} else {
return true;
}
}
} else {
// no authority
return true;
}
} else {
// one is opaque, the other hierarchical
return false;
}
}
/**
* {@inheritDoc}
* <p>
* Gets the hashcode value of this Uri instance.
* </p>
*/
@Override
public final int hashCode() {
synchronized( lazyLock ) {
if (hash == -1) {
hash = getHashString().hashCode();
}
return hash;
}
}
/*
* Takes a string that may contain hex sequences like %F1 or %2b and
* converts the hex values following the '%' to lowercase
*/
private String convertHexToLowerCase(final String s) {
if (s.indexOf('%') == -1) {
return s;
}
final StringBuilder result = new StringBuilder("");
int index = 0, previndex = 0;
while ((index = s.indexOf('%', previndex)) != -1) {
result.append(s.substring(previndex, index + 1));
result.append(s.substring(index + 1, index + 3).toLowerCase());
index += 3;
previndex = index;
}
return result.toString();
}
/*
* Takes two strings that may contain hex sequences like %F1 or %2b and
* compares them, ignoring case for the hex values. Hex values must always
* occur in pairs as above
*/
private boolean equalsHexCaseInsensitive(final Encoded first, final Encoded second) {
if (first.indexOf('%') != second.indexOf('%')) {
return first.equals(second);
}
int index = 0, previndex = 0;
while ( ( index = first.indexOf('%', previndex) ) != -1 &&
second.indexOf('%', previndex) == index
) {
if( !first.get().substring(previndex, index).equals( second.get().substring(previndex, index) ) ) {
return false;
}
if( !first.get().substring(index + 1, index + 3).equalsIgnoreCase( second.get().substring(index + 1, index + 3) ) ) {
return false;
}
index += 3;
previndex = index;
}
return first.get().substring(previndex).equals( second.get().substring(previndex) );
}
/*
* Form a string from the components of this Uri, similarly to the
* toString() method. But this method converts scheme and host to lowercase,
* and converts escaped octets to lowercase.
*/
private String getHashString() {
final StringBuilder result = new StringBuilder();
if (scheme != null) {
result.append(scheme.get().toLowerCase());
result.append(SCHEME_SEPARATOR);
}
if (opaque) {
result.append(schemeSpecificPart.get());
} else {
if (authority != null) {
result.append("//");
if (host == null) {
result.append(authority.get());
} else {
if (userInfo != null) {
result.append(userInfo.get() + "@");
}
result.append(host.get().toLowerCase());
if (port != -1) {
result.append(SCHEME_SEPARATOR + port);
}
}
}
if (path != null) {
result.append(path.get());
}
if (query != null) {
result.append(QUERY_SEPARATOR);
result.append(query.get());
}
}
if (fragment != null) {
result.append(FRAGMENT_SEPARATOR);
result.append(fragment.get());
}
return convertHexToLowerCase(result.toString());
}
/**
*
* @param input
* @param expectServer
* @param parseHints TODO
* @throws URISyntaxException
*/
private Uri(final Encoded input, final boolean expectServer, final int parseHints) throws URISyntaxException {
if( emptyString(input) ) {
throw new URISyntaxException(input.get(), "empty input");
}
String temp = input.get();
int index;
// parse into Fragment, Scheme, and SchemeSpecificPart
// then parse SchemeSpecificPart if necessary
// Fragment
index = temp.indexOf(FRAGMENT_SEPARATOR);
if (index != -1) {
// remove the fragment from the end
fragment = new Encoded( temp.substring(index + 1) );
validateFragment(input, fragment, index + 1);
temp = temp.substring(0, index);
} else {
fragment = null;
}
String inputTemp = input.get(); // may get modified due to error correction
// Scheme and SchemeSpecificPart
final int indexSchemeSep = temp.indexOf(SCHEME_SEPARATOR);
index = indexSchemeSep;
final int indexSSP = temp.indexOf('/');
final int indexQuerySep = temp.indexOf(QUERY_SEPARATOR);
String sspTemp; // may get modified due to error correction
// if a '/' or '?' occurs before the first ':' the uri has no
// specified scheme, and is therefore not absolute
if ( indexSchemeSep != -1 &&
( indexSSP >= indexSchemeSep || indexSSP == -1 ) &&
( indexQuerySep >= indexSchemeSep || indexQuerySep == -1 )
) {
// the characters up to the first ':' comprise the scheme
absolute = true;
scheme = new Encoded( temp.substring(0, indexSchemeSep) );
if (scheme.length() == 0) {
failExpecting(input, "scheme", indexSchemeSep);
}
validateScheme(input, scheme, 0);
sspTemp = temp.substring(indexSchemeSep + 1);
if (sspTemp.length() == 0) {
failExpecting(input, "scheme-specific-part", indexSchemeSep);
}
} else {
absolute = false;
scheme = null;
sspTemp = temp;
}
if ( scheme == null || sspTemp.length() > 0 && sspTemp.charAt(0) == '/' ) {
// Uri is hierarchical, not opaque
opaque = false;
// Query
temp = sspTemp;
index = temp.indexOf(QUERY_SEPARATOR);
if (index != -1) {
query = new Encoded( temp.substring(index + 1) );
temp = temp.substring(0, index);
validateQuery(input, query, indexSSP + 1 + index);
} else {
query = null;
}
String pathTemp; // may get modified due to error correction
final int indexPathInSSP;
// Authority and Path
if (temp.startsWith("//")) {
index = temp.indexOf('/', 2);
final String authorityS;
if (index != -1) {
authorityS = temp.substring(2, index);
pathTemp = temp.substring(index);
indexPathInSSP = index;
} else {
authorityS = temp.substring(2);
if (authorityS.length() == 0 && query == null && fragment == null) {
failExpecting(input, "authority, path [, query, fragment]", index);
}
pathTemp = "";
indexPathInSSP = -1;
// nothing left, so path is empty
// (not null, path should never be null if hierarchical/non-opaque)
}
if ( emptyString(authorityS) ) {
authority = null;
} else {
authority = new Encoded( authorityS );
validateAuthority(input, authority, indexSchemeSep + 3);
}
} else { // no authority specified
pathTemp = temp;
indexPathInSSP = 0;
authority = null;
}
int indexPath = 0; // in input
if (indexSSP > -1) {
indexPath += indexSSP;
}
if (indexPathInSSP > -1) {
indexPath += indexPathInSSP;
}
final int pathErrIdx = validateEncoded(pathTemp, PATH_LEGAL);
if( 0 <= pathErrIdx ) {
// Perform error correction on PATH if requested!
if( 0 != ( parseHints & PARSE_HINT_FIX_PATH ) ) {
if( DEBUG_SHOWFIX ) {
System.err.println("Uri FIX_FILEPATH: input at index "+(indexPath+pathErrIdx)+": "+inputTemp);
System.err.println("Uri FIX_FILEPATH: ssp at index "+(indexPathInSSP+pathErrIdx)+": "+sspTemp);
System.err.println("Uri FIX_FILEPATH: path at index "+pathErrIdx+": "+pathTemp);
}
final int pathTempOldLen = pathTemp.length();
pathTemp = encode( decode( pathTemp ), PATH_LEGAL); // re-encode, and hope for the best!
validatePath(input, pathTemp, indexPath); // re-validate!
{
// Patch SSP + INPUT !
final StringBuilder sb = new StringBuilder();
if( indexPathInSSP > 0 ) {
sb.append( sspTemp.substring(0, indexPathInSSP) );
}
sb.append( pathTemp ).append( sspTemp.substring( indexPathInSSP + pathTempOldLen ) );
sspTemp = sb.toString(); // update
sb.setLength(0);
if( indexPath > 0 ) {
sb.append( inputTemp.substring(0, indexPath) );
}
sb.append( pathTemp ).append( inputTemp.substring( indexPath + pathTempOldLen ) );
inputTemp = sb.toString(); // update
}
if( DEBUG_SHOWFIX ) {
System.err.println("Uri FIX_FILEPATH: result : "+pathTemp);
System.err.println("Uri FIX_FILEPATH: ssp after : "+sspTemp);
System.err.println("Uri FIX_FILEPATH: input after : "+inputTemp);
}
} else {
fail(input, "invalid path", indexPath+pathErrIdx);
}
}
path = new Encoded( pathTemp );
} else {
// Uri is not hierarchical, Uri is opaque
opaque = true;
query = null;
path = null;
authority = null;
validateSsp(input, sspTemp, indexSchemeSep + 1);
}
schemeSpecificPart = new Encoded( sspTemp );
this.input = inputTemp == input.get() ? input : new Encoded( inputTemp );
/**
* determine the host, port and userinfo if the authority parses
* successfully to a server based authority
*
* Behavior in error cases: if forceServer is true, throw
* URISyntaxException with the proper diagnostic messages. if
* forceServer is false assume this is a registry based uri, and just
* return leaving the host, port and userinfo fields undefined.
*
* and there are some error cases where URISyntaxException is thrown
* regardless of the forceServer parameter e.g. malformed ipv6 address
*/
Encoded tempUserinfo = null, tempHost = null;
int tempPort = -1;
boolean authorityComplete;
if ( null != authority ) {
authorityComplete = true; // set to false later
int hostindex = 0;
temp = authority.get();
index = temp.indexOf('@');
if (index != -1) {
// remove user info
tempUserinfo = new Encoded( temp.substring(0, index) );
validateUserinfo(authority, tempUserinfo, 0);
temp = temp.substring(index + 1); // host[:port] is left
hostindex = index + 1;
}
index = temp.lastIndexOf(SCHEME_SEPARATOR);
final int endindex = temp.indexOf(']');
if (index != -1 && endindex < index) {
// determine port and host
tempHost = new Encoded( temp.substring(0, index) );
if (index < (temp.length() - 1)) { // port part is not empty
try {
tempPort = Integer.parseInt(temp.substring(index + 1));
if (tempPort < 0) {
if (expectServer) {
fail(authority, "invalid port <"+authority+">", hostindex + index + 1);
}
authorityComplete = false;
}
} catch (final NumberFormatException e) {
if (expectServer) {
fail(authority, "invalid port <"+authority+">, "+e.getMessage(), hostindex + index + 1);
}
authorityComplete = false;
}
}
} else {
tempHost = new Encoded( temp );
}
if( authorityComplete ) {
if ( emptyString(tempHost) ) {
if (expectServer) {
fail(authority, "empty host <"+authority+">", hostindex);
}
authorityComplete = false;
} else if (!isValidHost(expectServer, tempHost)) {
if (expectServer) {
fail(authority, "invalid host <"+tempHost+">", hostindex);
}
authorityComplete = false;
}
}
} else {
authorityComplete = false;
}
if( authorityComplete ) {
// this is a server based uri,
// fill in the userinfo, host and port fields
userInfo = tempUserinfo;
host = tempHost;
port = tempPort;
hasAuthority = true;
} else {
userInfo = null;
host = null;
port = -1;
hasAuthority = false;
}
}
private static void validateScheme(final Encoded uri, final Encoded scheme, final int index) throws URISyntaxException {
// first char needs to be an alpha char
final char ch = scheme.charAt(0);
if ( !((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z')) ) {
fail(uri, "invalid scheme", index);
}
final int errIdx = validateAlphaNum(scheme.get(), "+-.");
if( 0 <= errIdx ) {
fail(uri, "invalid scheme", index+errIdx);
}
}
private static void validateSsp(final Encoded uri, final String ssp, final int index) throws URISyntaxException {
final int errIdx = validateEncoded(ssp, SSP_LEGAL);
if( 0 <= errIdx ) {
fail(uri, "invalid scheme-specific-part", index+errIdx);
}
}
private static void validateAuthority(final Encoded uri, final Encoded authority, final int index) throws URISyntaxException {
final int errIdx = validateEncoded(authority.get(), AUTHORITY_LEGAL);
if( 0 <= errIdx ) {
fail(uri, "invalid authority", index+errIdx);
}
}
private static void validatePath(final Encoded uri, final String path, final int index) throws URISyntaxException {
final int errIdx = validateEncoded(path, PATH_LEGAL);
if( 0 <= errIdx ) {
fail(uri, "invalid path", index+errIdx);
}
}
private static void validateQuery(final Encoded uri, final Encoded query, final int index) throws URISyntaxException {
final int errIdx = validateEncoded(query.get(), QUERY_LEGAL);
if( 0 <= errIdx ) {
fail(uri, "invalid query", index+errIdx);
}
}
private static void validateFragment(final Encoded uri, final Encoded fragment, final int index) throws URISyntaxException {
final int errIdx = validateEncoded(fragment.get(), FRAG_LEGAL);
if( 0 <= errIdx ) {
fail(uri, "invalid fragment", index+errIdx);
}
}
private static void validateUserinfo(final Encoded uri, final Encoded userinfo, final int index) throws URISyntaxException {
for (int i = 0; i < userinfo.length(); i++) {
final char ch = userinfo.charAt(i);
if (ch == ']' || ch == '[') {
fail(uri, "invalid userinfo", index+i);
}
}
}
/**
* distinguish between IPv4, IPv6, domain name and validate it based on
* its type
*/
private boolean isValidHost(final boolean expectServer, final Encoded host) throws URISyntaxException {
if (host.charAt(0) == '[') {
// ipv6 address
if (host.charAt(host.length() - 1) != ']') {
fail(input, "invalid host, missing closing ipv6: "+host, 0);
}
if (!isValidIP6Address(host.get())) {
fail(input, "invalid ipv6: "+host, 0);
}
return true;
}
// '[' and ']' can only be the first char and last char
// of the host name
if (host.indexOf('[') != -1 || host.indexOf(']') != -1) {
fail(input, "invalid host: "+host, 0);
}
final int index = host.lastIndexOf('.');
if ( index < 0 || index == host.length() - 1 ||
!Character.isDigit(host.charAt(index + 1)) )
{
// domain name
if (isValidDomainName(host)) {
return true;
}
if (expectServer) {
fail(input, "invalid host, invalid domain-name or ipv4: "+host, 0);
}
return false;
}
// IPv4 address
if (isValidIPv4Address(host.get())) {
return true;
}
if (expectServer) {
fail(input, "invalid host, invalid ipv4: "+host, 0);
}
return false;
}
private static boolean isValidDomainName(final Encoded host) {
final String hostS = host.get();
if( 0 <= validateAlphaNum(hostS, "-.") ) {
return false;
}
String label = null;
final StringTokenizer st = new StringTokenizer(hostS, ".");
while (st.hasMoreTokens()) {
label = st.nextToken();
if (label.startsWith("-") || label.endsWith("-")) {
return false;
}
}
if (!label.equals(hostS)) {
final char ch = label.charAt(0);
if (ch >= '0' && ch <= '9') {
return false;
}
}
return true;
}
private static boolean isValidIPv4Address(final String ipv4Address) {
int index;
int index2;
try {
int num;
index = ipv4Address.indexOf('.');
num = Integer.parseInt(ipv4Address.substring(0, index));
if (num < 0 || num > 255) {
return false;
}
index2 = ipv4Address.indexOf('.', index + 1);
num = Integer.parseInt(ipv4Address.substring(index + 1, index2));
if (num < 0 || num > 255) {
return false;
}
index = ipv4Address.indexOf('.', index2 + 1);
num = Integer.parseInt(ipv4Address.substring(index2 + 1, index));
if (num < 0 || num > 255) {
return false;
}
num = Integer.parseInt(ipv4Address.substring(index + 1));
if (num < 0 || num > 255) {
return false;
}
} catch (final Exception e) {
return false;
}
return true;
}
private static boolean isValidIP6Address(final String ipv6Address) {
final int length = ipv6Address.length();
boolean doubleColon = false;
int numberOfColons = 0;
int numberOfPeriods = 0;
String word = "";
char c = 0;
char prevChar = 0;
int offset = 0; // offset for [] ip addresses
if (length < 2) {
return false;
}
for (int i = 0; i < length; i++) {
prevChar = c;
c = ipv6Address.charAt(i);
switch (c) {
// case for an open bracket [x:x:x:...x]
case '[':
if (i != 0) {
return false; // must be first character
}
if (ipv6Address.charAt(length - 1) != ']') {
return false; // must have a close ]
}
if ((ipv6Address.charAt(1) == SCHEME_SEPARATOR)
&& (ipv6Address.charAt(2) != SCHEME_SEPARATOR)) {
return false;
}
offset = 1;
if (length < 4) {
return false;
}
break;
// case for a closed bracket at end of IP [x:x:x:...x]
case ']':
if (i != length - 1) {
return false; // must be last character
}
if (ipv6Address.charAt(0) != '[') {
return false; // must have a open [
}
break;
// case for the last 32-bits represented as IPv4
// x:x:x:x:x:x:d.d.d.d
case '.':
numberOfPeriods++;
if (numberOfPeriods > 3) {
return false;
}
if (!isValidIP4Word(word)) {
return false;
}
if (numberOfColons != 6 && !doubleColon) {
return false;
}
// a special case ::1:2:3:4:5:d.d.d.d allows 7 colons
// with
// an IPv4 ending, otherwise 7 :'s is bad
if (numberOfColons == 7
&& ipv6Address.charAt(0 + offset) != SCHEME_SEPARATOR
&& ipv6Address.charAt(1 + offset) != SCHEME_SEPARATOR) {
return false;
}
word = "";
break;
case SCHEME_SEPARATOR:
numberOfColons++;
if (numberOfColons > 7) {
return false;
}
if (numberOfPeriods > 0) {
return false;
}
if (prevChar == SCHEME_SEPARATOR) {
if (doubleColon) {
return false;
}
doubleColon = true;
}
word = "";
break;
default:
if (word.length() > 3) {
return false;
}
if (!isValidHexChar(c)) {
return false;
}
word += c;
}
}
// Check if we have an IPv4 ending
if (numberOfPeriods > 0) {
if (numberOfPeriods != 3 || !isValidIP4Word(word)) {
return false;
}
} else {
// If we're at then end and we haven't had 7 colons then there
// is a problem unless we encountered a doubleColon
if (numberOfColons != 7 && !doubleColon) {
return false;
}
// If we have an empty word at the end, it means we ended in
// either a : or a .
// If we did not end in :: then this is invalid
if (word == "" && ipv6Address.charAt(length - 1 - offset) != SCHEME_SEPARATOR
&& ipv6Address.charAt(length - 2 - offset) != SCHEME_SEPARATOR) {
return false;
}
}
return true;
}
private static boolean isValidIP4Word(final String word) {
char c;
if (word.length() < 1 || word.length() > 3) {
return false;
}
for (int i = 0; i < word.length(); i++) {
c = word.charAt(i);
if (!(c >= '0' && c <= '9')) {
return false;
}
}
if (Integer.parseInt(word) > 255) {
return false;
}
return true;
}
/**
* Validate a string by checking if it contains any characters other than:
* <ol>
* <li>letters ('a'..'z', 'A'..'Z')</li>
* <li>numbers ('0'..'9')</li>
* <li>characters in the legal-set parameter</li>
* <li> others (unicode characters that are not in
* US-ASCII set, and are not ISO Control or are not ISO Space characters)</li>
* </ol>
*
* @param encoded
* {@code java.lang.String} the string to be validated
* @param legal
* {@code java.lang.String} the characters allowed in the String
* s
*/
private static int validateEncoded(final String encoded, final String legal) {
for (int i = 0; i < encoded.length();) {
final char ch = encoded.charAt(i);
if (ch == '%') {
do {
if (i + 2 >= encoded.length()) {
throw new IllegalArgumentException("missing '%' hex-digits at index "+i);
}
final int d1 = Character.digit(encoded.charAt(i + 1), 16);
final int d2 = Character.digit(encoded.charAt(i + 2), 16);
if (d1 == -1 || d2 == -1) {
throw new IllegalArgumentException("invalid hex-digits at index "+i+": "+encoded.substring(i, i + 3));
}
i += 3;
} while (i < encoded.length() && encoded.charAt(i) == '%');
continue;
}
if ( !( (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') ||
(ch >= '0' && ch <= '9') || legal.indexOf(ch) > -1 ||
(ch > 127 && !Character.isSpaceChar(ch) && !Character.isISOControl(ch))
)
) {
return i;
}
i++;
}
return -1;
}
private static int validateAlphaNum(final String s, final String legal) {
for (int i = 0; i < s.length();) {
final char ch = s.charAt(i);
if ( !( (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') ||
(ch >= '0' && ch <= '9') || legal.indexOf(ch) > -1
)
) {
return i;
}
i++;
}
return -1;
}
private static boolean isValidHexChar(final char c) {
return (c >= '0' && c <= '9') || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f');
}
private static boolean emptyString(final Encoded s) {
return null == s || 0 == s.length();
}
private static boolean emptyString(final String s) {
return null == s || 0 == s.length();
}
private static void fail(final Encoded input, final String reason, final int p) throws URISyntaxException {
throw new URISyntaxException(input.get(), reason, p);
}
private static void failExpecting(final Encoded input, final String expected, final int p) throws URISyntaxException {
fail(input, "Expecting " + expected, p);
}
}
|