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
|
/*
Unix SMB/CIFS implementation.
Character set conversion Extensions
Copyright (C) Igor Vergeichik <iverg@mail.ru> 2001
Copyright (C) Andrew Tridgell 2001
Copyright (C) Simo Sorce 2001
Copyright (C) Martin Pool 2003
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "includes.h"
/* We can parameterize this if someone complains.... JRA. */
char lp_failed_convert_char(void)
{
return '_';
}
/**
* @file
*
* @brief Character-set conversion routines built on our iconv.
*
* @note Samba's internal character set (at least in the 3.0 series)
* is always the same as the one for the Unix filesystem. It is
* <b>not</b> necessarily UTF-8 and may be different on machines that
* need i18n filenames to be compatible with Unix software. It does
* have to be a superset of ASCII. All multibyte sequences must start
* with a byte with the high bit set.
*
* @sa lib/iconv.c
*/
static smb_iconv_t conv_handles[NUM_CHARSETS][NUM_CHARSETS];
static bool conv_silent; /* Should we do a debug if the conversion fails ? */
static bool initialized;
/**
* Return the name of a charset to give to iconv().
**/
static const char *charset_name(charset_t ch)
{
const char *ret = NULL;
if (ch == CH_UTF16LE) ret = "UTF-16LE";
else if (ch == CH_UTF16BE) ret = "UTF-16BE";
else if (ch == CH_UNIX) ret = lp_unix_charset();
else if (ch == CH_DOS) ret = lp_dos_charset();
else if (ch == CH_DISPLAY) ret = lp_display_charset();
else if (ch == CH_UTF8) ret = "UTF8";
#if defined(HAVE_NL_LANGINFO) && defined(CODESET)
if (ret && !strcmp(ret, "LOCALE")) {
const char *ln = NULL;
#ifdef HAVE_SETLOCALE
setlocale(LC_ALL, "");
#endif
ln = nl_langinfo(CODESET);
if (ln) {
/* Check whether the charset name is supported
by iconv */
smb_iconv_t handle = smb_iconv_open(ln,"UCS-2LE");
if (handle == (smb_iconv_t) -1) {
DEBUG(5,("Locale charset '%s' unsupported, using ASCII instead\n", ln));
ln = NULL;
} else {
DEBUG(5,("Substituting charset '%s' for LOCALE\n", ln));
smb_iconv_close(handle);
}
}
ret = ln;
}
#endif
if (!ret || !*ret) ret = "ASCII";
return ret;
}
void lazy_initialize_conv(void)
{
if (!initialized) {
load_case_tables();
init_iconv();
initialized = true;
}
}
/**
* Destroy global objects allocated by init_iconv()
**/
void gfree_charcnv(void)
{
int c1, c2;
for (c1=0;c1<NUM_CHARSETS;c1++) {
for (c2=0;c2<NUM_CHARSETS;c2++) {
if ( conv_handles[c1][c2] ) {
smb_iconv_close( conv_handles[c1][c2] );
conv_handles[c1][c2] = 0;
}
}
}
initialized = false;
}
/**
* Initialize iconv conversion descriptors.
*
* This is called the first time it is needed, and also called again
* every time the configuration is reloaded, because the charset or
* codepage might have changed.
**/
void init_iconv(void)
{
int c1, c2;
bool did_reload = False;
/* so that charset_name() works we need to get the UNIX<->UCS2 going
first */
if (!conv_handles[CH_UNIX][CH_UTF16LE])
conv_handles[CH_UNIX][CH_UTF16LE] = smb_iconv_open(charset_name(CH_UTF16LE), "ASCII");
if (!conv_handles[CH_UTF16LE][CH_UNIX])
conv_handles[CH_UTF16LE][CH_UNIX] = smb_iconv_open("ASCII", charset_name(CH_UTF16LE));
for (c1=0;c1<NUM_CHARSETS;c1++) {
for (c2=0;c2<NUM_CHARSETS;c2++) {
const char *n1 = charset_name((charset_t)c1);
const char *n2 = charset_name((charset_t)c2);
if (conv_handles[c1][c2] &&
strcmp(n1, conv_handles[c1][c2]->from_name) == 0 &&
strcmp(n2, conv_handles[c1][c2]->to_name) == 0)
continue;
did_reload = True;
if (conv_handles[c1][c2])
smb_iconv_close(conv_handles[c1][c2]);
conv_handles[c1][c2] = smb_iconv_open(n2,n1);
if (conv_handles[c1][c2] == (smb_iconv_t)-1) {
DEBUG(0,("init_iconv: Conversion from %s to %s not supported\n",
charset_name((charset_t)c1), charset_name((charset_t)c2)));
if (c1 != CH_UTF16LE && c1 != CH_UTF16BE) {
n1 = "ASCII";
}
if (c2 != CH_UTF16LE && c2 != CH_UTF16BE) {
n2 = "ASCII";
}
DEBUG(0,("init_iconv: Attempting to replace with conversion from %s to %s\n",
n1, n2 ));
conv_handles[c1][c2] = smb_iconv_open(n2,n1);
if (!conv_handles[c1][c2]) {
DEBUG(0,("init_iconv: Conversion from %s to %s failed", n1, n2));
smb_panic("init_iconv: conv_handle initialization failed");
}
}
}
}
if (did_reload) {
/* XXX: Does this really get called every time the dos
* codepage changes? */
/* XXX: Is the did_reload test too strict? */
conv_silent = True;
init_valid_table();
conv_silent = False;
}
}
/**
* Convert string from one encoding to another, making error checking etc
* Slow path version - uses (slow) iconv.
*
* @param src pointer to source string (multibyte or singlebyte)
* @param srclen length of the source string in bytes
* @param dest pointer to destination string (multibyte or singlebyte)
* @param destlen maximal length allowed for string
* @param allow_bad_conv determines if a "best effort" conversion is acceptable (never returns errors)
* @returns the number of bytes occupied in the destination
*
* Ensure the srclen contains the terminating zero.
*
**/
static size_t convert_string_internal(charset_t from, charset_t to,
void const *src, size_t srclen,
void *dest, size_t destlen, bool allow_bad_conv)
{
size_t i_len, o_len;
size_t retval;
const char* inbuf = (const char*)src;
char* outbuf = (char*)dest;
smb_iconv_t descriptor;
lazy_initialize_conv();
descriptor = conv_handles[from][to];
if (srclen == (size_t)-1) {
if (from == CH_UTF16LE || from == CH_UTF16BE) {
srclen = (strlen_w((const smb_ucs2_t *)src)+1) * 2;
} else {
srclen = strlen((const char *)src)+1;
}
}
if (descriptor == (smb_iconv_t)-1 || descriptor == (smb_iconv_t)0) {
if (!conv_silent)
DEBUG(0,("convert_string_internal: Conversion not supported.\n"));
return (size_t)-1;
}
i_len=srclen;
o_len=destlen;
again:
retval = smb_iconv(descriptor, &inbuf, &i_len, &outbuf, &o_len);
if(retval==(size_t)-1) {
const char *reason="unknown error";
switch(errno) {
case EINVAL:
reason="Incomplete multibyte sequence";
if (!conv_silent)
DEBUG(3,("convert_string_internal: Conversion error: %s(%s)\n",reason,inbuf));
if (allow_bad_conv)
goto use_as_is;
return (size_t)-1;
case E2BIG:
reason="No more room";
if (!conv_silent) {
if (from == CH_UNIX) {
DEBUG(3,("E2BIG: convert_string(%s,%s): srclen=%u destlen=%u - '%s'\n",
charset_name(from), charset_name(to),
(unsigned int)srclen, (unsigned int)destlen, (const char *)src));
} else {
DEBUG(3,("E2BIG: convert_string(%s,%s): srclen=%u destlen=%u\n",
charset_name(from), charset_name(to),
(unsigned int)srclen, (unsigned int)destlen));
}
}
break;
case EILSEQ:
reason="Illegal multibyte sequence";
if (!conv_silent)
DEBUG(3,("convert_string_internal: Conversion error: %s(%s)\n",reason,inbuf));
if (allow_bad_conv)
goto use_as_is;
return (size_t)-1;
default:
if (!conv_silent)
DEBUG(0,("convert_string_internal: Conversion error: %s(%s)\n",reason,inbuf));
return (size_t)-1;
}
/* smb_panic(reason); */
}
return destlen-o_len;
use_as_is:
/*
* Conversion not supported. This is actually an error, but there are so
* many misconfigured iconv systems and smb.conf's out there we can't just
* fail. Do a very bad conversion instead.... JRA.
*/
{
if (o_len == 0 || i_len == 0)
return destlen - o_len;
if (((from == CH_UTF16LE)||(from == CH_UTF16BE)) &&
((to != CH_UTF16LE)||(to != CH_UTF16BE))) {
/* Can't convert from utf16 any endian to multibyte.
Replace with the default fail char.
*/
if (i_len < 2)
return destlen - o_len;
if (i_len >= 2) {
*outbuf = lp_failed_convert_char();
outbuf++;
o_len--;
inbuf += 2;
i_len -= 2;
}
if (o_len == 0 || i_len == 0)
return destlen - o_len;
/* Keep trying with the next char... */
goto again;
} else if (from != CH_UTF16LE && from != CH_UTF16BE && to == CH_UTF16LE) {
/* Can't convert to UTF16LE - just widen by adding the
default fail char then zero.
*/
if (o_len < 2)
return destlen - o_len;
outbuf[0] = lp_failed_convert_char();
outbuf[1] = '\0';
inbuf++;
i_len--;
outbuf += 2;
o_len -= 2;
if (o_len == 0 || i_len == 0)
return destlen - o_len;
/* Keep trying with the next char... */
goto again;
} else if (from != CH_UTF16LE && from != CH_UTF16BE &&
to != CH_UTF16LE && to != CH_UTF16BE) {
/* Failed multibyte to multibyte. Just copy the default fail char and
try again. */
outbuf[0] = lp_failed_convert_char();
inbuf++;
i_len--;
outbuf++;
o_len--;
if (o_len == 0 || i_len == 0)
return destlen - o_len;
/* Keep trying with the next char... */
goto again;
} else {
/* Keep compiler happy.... */
return destlen - o_len;
}
}
}
/**
* Convert string from one encoding to another, making error checking etc
* Fast path version - handles ASCII first.
*
* @param src pointer to source string (multibyte or singlebyte)
* @param srclen length of the source string in bytes, or -1 for nul terminated.
* @param dest pointer to destination string (multibyte or singlebyte)
* @param destlen maximal length allowed for string - *NEVER* -1.
* @param allow_bad_conv determines if a "best effort" conversion is acceptable (never returns errors)
* @returns the number of bytes occupied in the destination
*
* Ensure the srclen contains the terminating zero.
*
* This function has been hand-tuned to provide a fast path.
* Don't change unless you really know what you are doing. JRA.
**/
size_t convert_string(charset_t from, charset_t to,
void const *src, size_t srclen,
void *dest, size_t destlen, bool allow_bad_conv)
{
/*
* NB. We deliberately don't do a strlen here if srclen == -1.
* This is very expensive over millions of calls and is taken
* care of in the slow path in convert_string_internal. JRA.
*/
#ifdef DEVELOPER
SMB_ASSERT(destlen != (size_t)-1);
#endif
if (srclen == 0)
return 0;
if (from != CH_UTF16LE && from != CH_UTF16BE && to != CH_UTF16LE && to != CH_UTF16BE) {
const unsigned char *p = (const unsigned char *)src;
unsigned char *q = (unsigned char *)dest;
size_t slen = srclen;
size_t dlen = destlen;
unsigned char lastp = '\0';
size_t retval = 0;
/* If all characters are ascii, fast path here. */
while (slen && dlen) {
if ((lastp = *p) <= 0x7f) {
*q++ = *p++;
if (slen != (size_t)-1) {
slen--;
}
dlen--;
retval++;
if (!lastp)
break;
} else {
#ifdef BROKEN_UNICODE_COMPOSE_CHARACTERS
goto general_case;
#else
size_t ret = convert_string_internal(from, to, p, slen, q, dlen, allow_bad_conv);
if (ret == (size_t)-1) {
return ret;
}
return retval + ret;
#endif
}
}
if (!dlen) {
/* Even if we fast path we should note if we ran out of room. */
if (((slen != (size_t)-1) && slen) ||
((slen == (size_t)-1) && lastp)) {
errno = E2BIG;
}
}
return retval;
} else if (from == CH_UTF16LE && to != CH_UTF16LE) {
const unsigned char *p = (const unsigned char *)src;
unsigned char *q = (unsigned char *)dest;
size_t retval = 0;
size_t slen = srclen;
size_t dlen = destlen;
unsigned char lastp = '\0';
/* If all characters are ascii, fast path here. */
while (((slen == (size_t)-1) || (slen >= 2)) && dlen) {
if (((lastp = *p) <= 0x7f) && (p[1] == 0)) {
*q++ = *p;
if (slen != (size_t)-1) {
slen -= 2;
}
p += 2;
dlen--;
retval++;
if (!lastp)
break;
} else {
#ifdef BROKEN_UNICODE_COMPOSE_CHARACTERS
goto general_case;
#else
size_t ret = convert_string_internal(from, to, p, slen, q, dlen, allow_bad_conv);
if (ret == (size_t)-1) {
return ret;
}
return retval + ret;
#endif
}
}
if (!dlen) {
/* Even if we fast path we should note if we ran out of room. */
if (((slen != (size_t)-1) && slen) ||
((slen == (size_t)-1) && lastp)) {
errno = E2BIG;
}
}
return retval;
} else if (from != CH_UTF16LE && from != CH_UTF16BE && to == CH_UTF16LE) {
const unsigned char *p = (const unsigned char *)src;
unsigned char *q = (unsigned char *)dest;
size_t retval = 0;
size_t slen = srclen;
size_t dlen = destlen;
unsigned char lastp = '\0';
/* If all characters are ascii, fast path here. */
while (slen && (dlen >= 2)) {
if ((lastp = *p) <= 0x7F) {
*q++ = *p++;
*q++ = '\0';
if (slen != (size_t)-1) {
slen--;
}
dlen -= 2;
retval += 2;
if (!lastp)
break;
} else {
#ifdef BROKEN_UNICODE_COMPOSE_CHARACTERS
goto general_case;
#else
size_t ret = convert_string_internal(from, to, p, slen, q, dlen, allow_bad_conv);
if (ret == (size_t)-1) {
return ret;
}
return retval + ret;
#endif
}
}
if (!dlen) {
/* Even if we fast path we should note if we ran out of room. */
if (((slen != (size_t)-1) && slen) ||
((slen == (size_t)-1) && lastp)) {
errno = E2BIG;
}
}
return retval;
}
#ifdef BROKEN_UNICODE_COMPOSE_CHARACTERS
general_case:
#endif
return convert_string_internal(from, to, src, srclen, dest, destlen, allow_bad_conv);
}
/**
* Convert between character sets, allocating a new buffer using talloc for the result.
*
* @param srclen length of source buffer.
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
* @note -1 is not accepted for srclen.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
*
* Ensure the srclen contains the terminating zero.
*
* I hate the goto's in this function. It's embarressing.....
* There has to be a cleaner way to do this. JRA.
*/
bool convert_string_talloc(TALLOC_CTX *ctx, charset_t from, charset_t to,
void const *src, size_t srclen, void *dst,
size_t *converted_size, bool allow_bad_conv)
{
size_t i_len, o_len, destlen = (srclen * 3) / 2;
size_t retval;
const char *inbuf = (const char *)src;
char *outbuf = NULL, *ob = NULL;
smb_iconv_t descriptor;
void **dest = (void **)dst;
*dest = NULL;
if (!converted_size) {
errno = EINVAL;
return false;
}
if (src == NULL || srclen == (size_t)-1) {
errno = EINVAL;
return false;
}
if (srclen == 0) {
ob = talloc_strdup(ctx, "");
if (ob == NULL) {
errno = ENOMEM;
return false;
}
*dest = ob;
*converted_size = 0;
return true;
}
lazy_initialize_conv();
descriptor = conv_handles[from][to];
if (descriptor == (smb_iconv_t)-1 || descriptor == (smb_iconv_t)0) {
if (!conv_silent)
DEBUG(0,("convert_string_talloc: Conversion not supported.\n"));
errno = EOPNOTSUPP;
return false;
}
convert:
/* +2 is for ucs2 null termination. */
if ((destlen*2)+2 < destlen) {
/* wrapped ! abort. */
if (!conv_silent)
DEBUG(0, ("convert_string_talloc: destlen wrapped !\n"));
TALLOC_FREE(outbuf);
errno = EOPNOTSUPP;
return false;
} else {
destlen = destlen * 2;
}
/* +2 is for ucs2 null termination. */
ob = (char *)TALLOC_REALLOC(ctx, ob, destlen + 2);
if (!ob) {
DEBUG(0, ("convert_string_talloc: realloc failed!\n"));
errno = ENOMEM;
return false;
}
outbuf = ob;
i_len = srclen;
o_len = destlen;
again:
retval = smb_iconv(descriptor,
&inbuf, &i_len,
&outbuf, &o_len);
if(retval == (size_t)-1) {
const char *reason="unknown error";
switch(errno) {
case EINVAL:
reason="Incomplete multibyte sequence";
if (!conv_silent)
DEBUG(3,("convert_string_talloc: Conversion error: %s(%s)\n",reason,inbuf));
if (allow_bad_conv)
goto use_as_is;
break;
case E2BIG:
goto convert;
case EILSEQ:
reason="Illegal multibyte sequence";
if (!conv_silent)
DEBUG(3,("convert_string_talloc: Conversion error: %s(%s)\n",reason,inbuf));
if (allow_bad_conv)
goto use_as_is;
break;
}
if (!conv_silent)
DEBUG(0,("Conversion error: %s(%s)\n",reason,inbuf));
/* smb_panic(reason); */
TALLOC_FREE(ob);
return false;
}
out:
destlen = destlen - o_len;
/* Don't shrink unless we're reclaiming a lot of
* space. This is in the hot codepath and these
* reallocs *cost*. JRA.
*/
if (o_len > 1024) {
/* We're shrinking here so we know the +2 is safe from wrap. */
ob = (char *)TALLOC_REALLOC(ctx,ob,destlen + 2);
}
if (destlen && !ob) {
DEBUG(0, ("convert_string_talloc: out of memory!\n"));
errno = ENOMEM;
return false;
}
*dest = ob;
/* Must ucs2 null terminate in the extra space we allocated. */
ob[destlen] = '\0';
ob[destlen+1] = '\0';
*converted_size = destlen;
return true;
use_as_is:
/*
* Conversion not supported. This is actually an error, but there are so
* many misconfigured iconv systems and smb.conf's out there we can't just
* fail. Do a very bad conversion instead.... JRA.
*/
{
if (o_len == 0 || i_len == 0)
goto out;
if (((from == CH_UTF16LE)||(from == CH_UTF16BE)) &&
((to != CH_UTF16LE)||(to != CH_UTF16BE))) {
/* Can't convert from utf16 any endian to multibyte.
Replace with the default fail char.
*/
if (i_len < 2)
goto out;
if (i_len >= 2) {
*outbuf = lp_failed_convert_char();
outbuf++;
o_len--;
inbuf += 2;
i_len -= 2;
}
if (o_len == 0 || i_len == 0)
goto out;
/* Keep trying with the next char... */
goto again;
} else if (from != CH_UTF16LE && from != CH_UTF16BE && to == CH_UTF16LE) {
/* Can't convert to UTF16LE - just widen by adding the
default fail char then zero.
*/
if (o_len < 2)
goto out;
outbuf[0] = lp_failed_convert_char();
outbuf[1] = '\0';
inbuf++;
i_len--;
outbuf += 2;
o_len -= 2;
if (o_len == 0 || i_len == 0)
goto out;
/* Keep trying with the next char... */
goto again;
} else if (from != CH_UTF16LE && from != CH_UTF16BE &&
to != CH_UTF16LE && to != CH_UTF16BE) {
/* Failed multibyte to multibyte. Just copy the default fail char and
try again. */
outbuf[0] = lp_failed_convert_char();
inbuf++;
i_len--;
outbuf++;
o_len--;
if (o_len == 0 || i_len == 0)
goto out;
/* Keep trying with the next char... */
goto again;
} else {
/* Keep compiler happy.... */
goto out;
}
}
}
size_t unix_strupper(const char *src, size_t srclen, char *dest, size_t destlen)
{
size_t size;
smb_ucs2_t *buffer;
if (!push_ucs2_talloc(NULL, &buffer, src, &size)) {
return (size_t)-1;
}
if (!strupper_w(buffer) && (dest == src)) {
TALLOC_FREE(buffer);
return srclen;
}
size = convert_string(CH_UTF16LE, CH_UNIX, buffer, size, dest, destlen, True);
TALLOC_FREE(buffer);
return size;
}
/**
talloc_strdup() a unix string to upper case.
**/
char *talloc_strdup_upper(TALLOC_CTX *ctx, const char *s)
{
char *out_buffer = talloc_strdup(ctx,s);
const unsigned char *p = (const unsigned char *)s;
unsigned char *q = (unsigned char *)out_buffer;
if (!q) {
return NULL;
}
/* this is quite a common operation, so we want it to be
fast. We optimise for the ascii case, knowing that all our
supported multi-byte character sets are ascii-compatible
(ie. they match for the first 128 chars) */
while (*p) {
if (*p & 0x80)
break;
*q++ = toupper_ascii_fast(*p);
p++;
}
if (*p) {
/* MB case. */
size_t converted_size, converted_size2;
smb_ucs2_t *ubuf = NULL;
/* We're not using the ascii buffer above. */
TALLOC_FREE(out_buffer);
if (!convert_string_talloc(ctx, CH_UNIX, CH_UTF16LE, s,
strlen(s)+1, (void *)&ubuf,
&converted_size, True))
{
return NULL;
}
strupper_w(ubuf);
if (!convert_string_talloc(ctx, CH_UTF16LE, CH_UNIX, ubuf,
converted_size, (void *)&out_buffer,
&converted_size2, True))
{
TALLOC_FREE(ubuf);
return NULL;
}
/* Don't need the intermediate buffer
* anymore.
*/
TALLOC_FREE(ubuf);
}
return out_buffer;
}
char *strupper_talloc(TALLOC_CTX *ctx, const char *s) {
return talloc_strdup_upper(ctx, s);
}
size_t unix_strlower(const char *src, size_t srclen, char *dest, size_t destlen)
{
size_t size;
smb_ucs2_t *buffer = NULL;
if (!convert_string_talloc(NULL, CH_UNIX, CH_UTF16LE, src, srclen,
(void **)(void *)&buffer, &size,
True))
{
smb_panic("failed to create UCS2 buffer");
}
if (!strlower_w(buffer) && (dest == src)) {
TALLOC_FREE(buffer);
return srclen;
}
size = convert_string(CH_UTF16LE, CH_UNIX, buffer, size, dest, destlen, True);
TALLOC_FREE(buffer);
return size;
}
char *talloc_strdup_lower(TALLOC_CTX *ctx, const char *s)
{
size_t converted_size;
smb_ucs2_t *buffer = NULL;
char *out_buffer;
if (!push_ucs2_talloc(ctx, &buffer, s, &converted_size)) {
return NULL;
}
strlower_w(buffer);
if (!pull_ucs2_talloc(ctx, &out_buffer, buffer, &converted_size)) {
TALLOC_FREE(buffer);
return NULL;
}
TALLOC_FREE(buffer);
return out_buffer;
}
char *strlower_talloc(TALLOC_CTX *ctx, const char *s) {
return talloc_strdup_lower(ctx, s);
}
size_t ucs2_align(const void *base_ptr, const void *p, int flags)
{
if (flags & (STR_NOALIGN|STR_ASCII))
return 0;
return PTR_DIFF(p, base_ptr) & 1;
}
/**
* Copy a string from a char* unix src to a dos codepage string destination.
*
* @return the number of bytes occupied by the string in the destination.
*
* @param flags can include
* <dl>
* <dt>STR_TERMINATE</dt> <dd>means include the null termination</dd>
* <dt>STR_UPPER</dt> <dd>means uppercase in the destination</dd>
* </dl>
*
* @param dest_len the maximum length in bytes allowed in the
* destination.
**/
size_t push_ascii(void *dest, const char *src, size_t dest_len, int flags)
{
size_t src_len = strlen(src);
char *tmpbuf = NULL;
size_t ret;
/* No longer allow a length of -1. */
if (dest_len == (size_t)-1) {
smb_panic("push_ascii - dest_len == -1");
}
if (flags & STR_UPPER) {
tmpbuf = SMB_STRDUP(src);
if (!tmpbuf) {
smb_panic("malloc fail");
}
strupper_m(tmpbuf);
src = tmpbuf;
}
if (flags & (STR_TERMINATE | STR_TERMINATE_ASCII)) {
src_len++;
}
ret = convert_string(CH_UNIX, CH_DOS, src, src_len, dest, dest_len, True);
if (ret == (size_t)-1 &&
(flags & (STR_TERMINATE | STR_TERMINATE_ASCII))
&& dest_len > 0) {
((char *)dest)[0] = '\0';
}
SAFE_FREE(tmpbuf);
return ret;
}
size_t push_ascii_fstring(void *dest, const char *src)
{
return push_ascii(dest, src, sizeof(fstring), STR_TERMINATE);
}
/********************************************************************
Push an nstring - ensure null terminated. Written by
moriyama@miraclelinux.com (MORIYAMA Masayuki).
********************************************************************/
size_t push_ascii_nstring(void *dest, const char *src)
{
size_t i, buffer_len, dest_len;
smb_ucs2_t *buffer;
conv_silent = True;
if (!push_ucs2_talloc(NULL, &buffer, src, &buffer_len)) {
smb_panic("failed to create UCS2 buffer");
}
/* We're using buffer_len below to count ucs2 characters, not bytes. */
buffer_len /= sizeof(smb_ucs2_t);
dest_len = 0;
for (i = 0; buffer[i] != 0 && (i < buffer_len); i++) {
unsigned char mb[10];
/* Convert one smb_ucs2_t character at a time. */
size_t mb_len = convert_string(CH_UTF16LE, CH_DOS, buffer+i, sizeof(smb_ucs2_t), mb, sizeof(mb), False);
if ((mb_len != (size_t)-1) && (dest_len + mb_len <= MAX_NETBIOSNAME_LEN - 1)) {
memcpy((char *)dest + dest_len, mb, mb_len);
dest_len += mb_len;
} else {
errno = E2BIG;
break;
}
}
((char *)dest)[dest_len] = '\0';
conv_silent = False;
TALLOC_FREE(buffer);
return dest_len;
}
/********************************************************************
Push and malloc an ascii string. src and dest null terminated.
********************************************************************/
bool push_ascii_talloc(TALLOC_CTX *mem_ctx, char **dest, const char *src, size_t *converted_size)
{
size_t src_len = strlen(src)+1;
*dest = NULL;
return convert_string_talloc(mem_ctx, CH_UNIX, CH_DOS, src, src_len,
(void **)dest, converted_size, True);
}
/**
* Copy a string from a dos codepage source to a unix char* destination.
*
* The resulting string in "dest" is always null terminated.
*
* @param flags can have:
* <dl>
* <dt>STR_TERMINATE</dt>
* <dd>STR_TERMINATE means the string in @p src
* is null terminated, and src_len is ignored.</dd>
* </dl>
*
* @param src_len is the length of the source area in bytes.
* @returns the number of bytes occupied by the string in @p src.
**/
size_t pull_ascii(char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
size_t ret;
if (dest_len == (size_t)-1) {
/* No longer allow dest_len of -1. */
smb_panic("pull_ascii - invalid dest_len of -1");
}
if (flags & STR_TERMINATE) {
if (src_len == (size_t)-1) {
src_len = strlen((const char *)src) + 1;
} else {
size_t len = strnlen((const char *)src, src_len);
if (len < src_len)
len++;
src_len = len;
}
}
ret = convert_string(CH_DOS, CH_UNIX, src, src_len, dest, dest_len, True);
if (ret == (size_t)-1) {
ret = 0;
dest_len = 0;
}
if (dest_len && ret) {
/* Did we already process the terminating zero ? */
if (dest[MIN(ret-1, dest_len-1)] != 0) {
dest[MIN(ret, dest_len-1)] = 0;
}
} else {
dest[0] = 0;
}
return src_len;
}
/**
* Copy a string from a dos codepage source to a unix char* destination.
Talloc version.
Uses malloc if TALLOC_CTX is NULL (this is a bad interface and
needs fixing. JRA).
*
* The resulting string in "dest" is always null terminated.
*
* @param flags can have:
* <dl>
* <dt>STR_TERMINATE</dt>
* <dd>STR_TERMINATE means the string in @p src
* is null terminated, and src_len is ignored.</dd>
* </dl>
*
* @param src_len is the length of the source area in bytes.
* @returns the number of bytes occupied by the string in @p src.
**/
static size_t pull_ascii_base_talloc(TALLOC_CTX *ctx,
char **ppdest,
const void *src,
size_t src_len,
int flags)
{
char *dest = NULL;
size_t dest_len;
*ppdest = NULL;
if (!src_len) {
return 0;
}
if (flags & STR_TERMINATE) {
if (src_len == (size_t)-1) {
src_len = strlen((const char *)src) + 1;
} else {
size_t len = strnlen((const char *)src, src_len);
if (len < src_len)
len++;
src_len = len;
}
/* Ensure we don't use an insane length from the client. */
if (src_len >= 1024*1024) {
char *msg = talloc_asprintf(ctx,
"Bad src length (%u) in "
"pull_ascii_base_talloc",
(unsigned int)src_len);
smb_panic(msg);
}
} else {
/* Can't have an unlimited length
* non STR_TERMINATE'd.
*/
if (src_len == (size_t)-1) {
errno = EINVAL;
return 0;
}
}
/* src_len != -1 here. */
if (!convert_string_talloc(ctx, CH_DOS, CH_UNIX, src, src_len, &dest,
&dest_len, True)) {
dest_len = 0;
}
if (dest_len && dest) {
/* Did we already process the terminating zero ? */
if (dest[dest_len-1] != 0) {
size_t size = talloc_get_size(dest);
/* Have we got space to append the '\0' ? */
if (size <= dest_len) {
/* No, realloc. */
dest = TALLOC_REALLOC_ARRAY(ctx, dest, char,
dest_len+1);
if (!dest) {
/* talloc fail. */
dest_len = (size_t)-1;
return 0;
}
}
/* Yay - space ! */
dest[dest_len] = '\0';
dest_len++;
}
} else if (dest) {
dest[0] = 0;
}
*ppdest = dest;
return src_len;
}
size_t pull_ascii_fstring(char *dest, const void *src)
{
return pull_ascii(dest, src, sizeof(fstring), -1, STR_TERMINATE);
}
/* When pulling an nstring it can expand into a larger size (dos cp -> utf8). Cope with this. */
size_t pull_ascii_nstring(char *dest, size_t dest_len, const void *src)
{
return pull_ascii(dest, src, dest_len, sizeof(nstring)-1, STR_TERMINATE);
}
/**
* Copy a string from a char* src to a unicode destination.
*
* @returns the number of bytes occupied by the string in the destination.
*
* @param flags can have:
*
* <dl>
* <dt>STR_TERMINATE <dd>means include the null termination.
* <dt>STR_UPPER <dd>means uppercase in the destination.
* <dt>STR_NOALIGN <dd>means don't do alignment.
* </dl>
*
* @param dest_len is the maximum length allowed in the
* destination.
**/
size_t push_ucs2(const void *base_ptr, void *dest, const char *src, size_t dest_len, int flags)
{
size_t len=0;
size_t src_len;
size_t ret;
if (dest_len == (size_t)-1) {
/* No longer allow dest_len of -1. */
smb_panic("push_ucs2 - invalid dest_len of -1");
}
if (flags & STR_TERMINATE)
src_len = (size_t)-1;
else
src_len = strlen(src);
if (ucs2_align(base_ptr, dest, flags)) {
*(char *)dest = 0;
dest = (void *)((char *)dest + 1);
if (dest_len)
dest_len--;
len++;
}
/* ucs2 is always a multiple of 2 bytes */
dest_len &= ~1;
ret = convert_string(CH_UNIX, CH_UTF16LE, src, src_len, dest, dest_len, True);
if (ret == (size_t)-1) {
if ((flags & STR_TERMINATE) &&
dest &&
dest_len) {
*(char *)dest = 0;
}
return len;
}
len += ret;
if (flags & STR_UPPER) {
smb_ucs2_t *dest_ucs2 = (smb_ucs2_t *)dest;
size_t i;
/* We check for i < (ret / 2) below as the dest string isn't null
terminated if STR_TERMINATE isn't set. */
for (i = 0; i < (ret / 2) && i < (dest_len / 2) && dest_ucs2[i]; i++) {
smb_ucs2_t v = toupper_w(dest_ucs2[i]);
if (v != dest_ucs2[i]) {
dest_ucs2[i] = v;
}
}
}
return len;
}
/**
* Copy a string from a unix char* src to a UCS2 destination,
* allocating a buffer using talloc().
*
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
**/
bool push_ucs2_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src,
size_t *converted_size)
{
size_t src_len = strlen(src)+1;
*dest = NULL;
return convert_string_talloc(ctx, CH_UNIX, CH_UTF16LE, src, src_len,
(void **)dest, converted_size, True);
}
/**
Copy a string from a char* src to a UTF-8 destination.
Return the number of bytes occupied by the string in the destination
Flags can have:
STR_TERMINATE means include the null termination
STR_UPPER means uppercase in the destination
dest_len is the maximum length allowed in the destination. If dest_len
is -1 then no maxiumum is used.
**/
static size_t push_utf8(void *dest, const char *src, size_t dest_len, int flags)
{
size_t src_len = 0;
size_t ret;
char *tmpbuf = NULL;
if (dest_len == (size_t)-1) {
/* No longer allow dest_len of -1. */
smb_panic("push_utf8 - invalid dest_len of -1");
}
if (flags & STR_UPPER) {
tmpbuf = strupper_talloc(NULL, src);
if (!tmpbuf) {
return (size_t)-1;
}
src = tmpbuf;
src_len = strlen(src);
}
src_len = strlen(src);
if (flags & STR_TERMINATE) {
src_len++;
}
ret = convert_string(CH_UNIX, CH_UTF8, src, src_len, dest, dest_len, True);
TALLOC_FREE(tmpbuf);
return ret;
}
size_t push_utf8_fstring(void *dest, const char *src)
{
return push_utf8(dest, src, sizeof(fstring), STR_TERMINATE);
}
/**
* Copy a string from a unix char* src to a UTF-8 destination, allocating a buffer using talloc
*
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
**/
bool push_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src,
size_t *converted_size)
{
size_t src_len = strlen(src)+1;
*dest = NULL;
return convert_string_talloc(ctx, CH_UNIX, CH_UTF8, src, src_len,
(void**)dest, converted_size, True);
}
/**
Copy a string from a ucs2 source to a unix char* destination.
Flags can have:
STR_TERMINATE means the string in src is null terminated.
STR_NOALIGN means don't try to align.
if STR_TERMINATE is set then src_len is ignored if it is -1.
src_len is the length of the source area in bytes
Return the number of bytes occupied by the string in src.
The resulting string in "dest" is always null terminated.
**/
size_t pull_ucs2(const void *base_ptr, char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
size_t ret;
if (dest_len == (size_t)-1) {
/* No longer allow dest_len of -1. */
smb_panic("pull_ucs2 - invalid dest_len of -1");
}
if (!src_len) {
if (dest && dest_len > 0) {
dest[0] = '\0';
}
return 0;
}
if (ucs2_align(base_ptr, src, flags)) {
src = (const void *)((const char *)src + 1);
if (src_len != (size_t)-1)
src_len--;
}
if (flags & STR_TERMINATE) {
/* src_len -1 is the default for null terminated strings. */
if (src_len != (size_t)-1) {
size_t len = strnlen_w((const smb_ucs2_t *)src,
src_len/2);
if (len < src_len/2)
len++;
src_len = len*2;
}
}
/* ucs2 is always a multiple of 2 bytes */
if (src_len != (size_t)-1)
src_len &= ~1;
ret = convert_string(CH_UTF16LE, CH_UNIX, src, src_len, dest, dest_len, True);
if (ret == (size_t)-1) {
ret = 0;
dest_len = 0;
}
if (src_len == (size_t)-1)
src_len = ret*2;
if (dest_len && ret) {
/* Did we already process the terminating zero ? */
if (dest[MIN(ret-1, dest_len-1)] != 0) {
dest[MIN(ret, dest_len-1)] = 0;
}
} else {
dest[0] = 0;
}
return src_len;
}
/**
Copy a string from a ucs2 source to a unix char* destination.
Talloc version with a base pointer.
Uses malloc if TALLOC_CTX is NULL (this is a bad interface and
needs fixing. JRA).
Flags can have:
STR_TERMINATE means the string in src is null terminated.
STR_NOALIGN means don't try to align.
if STR_TERMINATE is set then src_len is ignored if it is -1.
src_len is the length of the source area in bytes
Return the number of bytes occupied by the string in src.
The resulting string in "dest" is always null terminated.
**/
size_t pull_ucs2_base_talloc(TALLOC_CTX *ctx,
const void *base_ptr,
char **ppdest,
const void *src,
size_t src_len,
int flags)
{
char *dest;
size_t dest_len;
*ppdest = NULL;
#ifdef DEVELOPER
/* Ensure we never use the braindead "malloc" varient. */
if (ctx == NULL) {
smb_panic("NULL talloc CTX in pull_ucs2_base_talloc\n");
}
#endif
if (!src_len) {
return 0;
}
if (ucs2_align(base_ptr, src, flags)) {
src = (const void *)((const char *)src + 1);
if (src_len != (size_t)-1)
src_len--;
}
if (flags & STR_TERMINATE) {
/* src_len -1 is the default for null terminated strings. */
if (src_len != (size_t)-1) {
size_t len = strnlen_w((const smb_ucs2_t *)src,
src_len/2);
if (len < src_len/2)
len++;
src_len = len*2;
} else {
/*
* src_len == -1 - alloc interface won't take this
* so we must calculate.
*/
src_len = (strlen_w((const smb_ucs2_t *)src)+1)*sizeof(smb_ucs2_t);
}
/* Ensure we don't use an insane length from the client. */
if (src_len >= 1024*1024) {
smb_panic("Bad src length in pull_ucs2_base_talloc\n");
}
} else {
/* Can't have an unlimited length
* non STR_TERMINATE'd.
*/
if (src_len == (size_t)-1) {
errno = EINVAL;
return 0;
}
}
/* src_len != -1 here. */
/* ucs2 is always a multiple of 2 bytes */
src_len &= ~1;
if (!convert_string_talloc(ctx, CH_UTF16LE, CH_UNIX, src, src_len,
(void *)&dest, &dest_len, True)) {
dest_len = 0;
}
if (dest_len) {
/* Did we already process the terminating zero ? */
if (dest[dest_len-1] != 0) {
size_t size = talloc_get_size(dest);
/* Have we got space to append the '\0' ? */
if (size <= dest_len) {
/* No, realloc. */
dest = TALLOC_REALLOC_ARRAY(ctx, dest, char,
dest_len+1);
if (!dest) {
/* talloc fail. */
dest_len = (size_t)-1;
return 0;
}
}
/* Yay - space ! */
dest[dest_len] = '\0';
dest_len++;
}
} else if (dest) {
dest[0] = 0;
}
*ppdest = dest;
return src_len;
}
size_t pull_ucs2_fstring(char *dest, const void *src)
{
return pull_ucs2(NULL, dest, src, sizeof(fstring), -1, STR_TERMINATE);
}
/**
* Copy a string from a UCS2 src to a unix char * destination, allocating a buffer using talloc
*
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
**/
bool pull_ucs2_talloc(TALLOC_CTX *ctx, char **dest, const smb_ucs2_t *src,
size_t *converted_size)
{
size_t src_len = (strlen_w(src)+1) * sizeof(smb_ucs2_t);
*dest = NULL;
return convert_string_talloc(ctx, CH_UTF16LE, CH_UNIX, src, src_len,
(void **)dest, converted_size, True);
}
/**
* Copy a string from a UTF-8 src to a unix char * destination, allocating a buffer using talloc
*
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
**/
bool pull_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src,
size_t *converted_size)
{
size_t src_len = strlen(src)+1;
*dest = NULL;
return convert_string_talloc(ctx, CH_UTF8, CH_UNIX, src, src_len,
(void **)dest, converted_size, True);
}
/**
* Copy a string from a DOS src to a unix char * destination, allocating a buffer using talloc
*
* @param dest always set at least to NULL
* @parm converted_size set to the number of bytes occupied by the string in
* the destination on success.
*
* @return true if new buffer was correctly allocated, and string was
* converted.
**/
bool pull_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src,
size_t *converted_size)
{
size_t src_len = strlen(src)+1;
*dest = NULL;
return convert_string_talloc(ctx, CH_DOS, CH_UNIX, src, src_len,
(void **)dest, converted_size, True);
}
/**
Copy a string from a char* src to a unicode or ascii
dos codepage destination choosing unicode or ascii based on the
flags supplied
Return the number of bytes occupied by the string in the destination.
flags can have:
STR_TERMINATE means include the null termination.
STR_UPPER means uppercase in the destination.
STR_ASCII use ascii even with unicode packet.
STR_NOALIGN means don't do alignment.
dest_len is the maximum length allowed in the destination. If dest_len
is -1 then no maxiumum is used.
**/
size_t push_string_check_fn(const char *function, unsigned int line,
void *dest, const char *src,
size_t dest_len, int flags)
{
#ifdef DEVELOPER
/* We really need to zero fill here, not clobber
* region, as we want to ensure that valgrind thinks
* all of the outgoing buffer has been written to
* so a send() or write() won't trap an error.
* JRA.
*/
#if 0
clobber_region(function, line, dest, dest_len);
#else
memset(dest, '\0', dest_len);
#endif
#endif
if (!(flags & STR_ASCII) && (flags & STR_UNICODE)) {
return push_ucs2(NULL, dest, src, dest_len, flags);
}
return push_ascii(dest, src, dest_len, flags);
}
/**
Copy a string from a char* src to a unicode or ascii
dos codepage destination choosing unicode or ascii based on the
flags in the SMB buffer starting at base_ptr.
Return the number of bytes occupied by the string in the destination.
flags can have:
STR_TERMINATE means include the null termination.
STR_UPPER means uppercase in the destination.
STR_ASCII use ascii even with unicode packet.
STR_NOALIGN means don't do alignment.
dest_len is the maximum length allowed in the destination. If dest_len
is -1 then no maxiumum is used.
**/
size_t push_string_base(const char *function, unsigned int line,
const char *base, uint16 flags2,
void *dest, const char *src,
size_t dest_len, int flags)
{
#ifdef DEVELOPER
/* We really need to zero fill here, not clobber
* region, as we want to ensure that valgrind thinks
* all of the outgoing buffer has been written to
* so a send() or write() won't trap an error.
* JRA.
*/
#if 0
clobber_region(function, line, dest, dest_len);
#else
memset(dest, '\0', dest_len);
#endif
#endif
if (!(flags & STR_ASCII) && \
((flags & STR_UNICODE || \
(flags2 & FLAGS2_UNICODE_STRINGS)))) {
return push_ucs2(base, dest, src, dest_len, flags);
}
return push_ascii(dest, src, dest_len, flags);
}
/**
Copy a string from a char* src to a unicode or ascii
dos codepage destination choosing unicode or ascii based on the
flags supplied
Return the number of bytes occupied by the string in the destination.
flags can have:
STR_TERMINATE means include the null termination.
STR_UPPER means uppercase in the destination.
STR_ASCII use ascii even with unicode packet.
STR_NOALIGN means don't do alignment.
dest_len is the maximum length allowed in the destination. If dest_len
is -1 then no maxiumum is used.
**/
ssize_t push_string(void *dest, const char *src, size_t dest_len, int flags)
{
size_t ret;
#ifdef DEVELOPER
/* We really need to zero fill here, not clobber
* region, as we want to ensure that valgrind thinks
* all of the outgoing buffer has been written to
* so a send() or write() won't trap an error.
* JRA.
*/
memset(dest, '\0', dest_len);
#endif
if (!(flags & STR_ASCII) && \
(flags & STR_UNICODE)) {
ret = push_ucs2(NULL, dest, src, dest_len, flags);
} else {
ret = push_ascii(dest, src, dest_len, flags);
}
if (ret == (size_t)-1) {
return -1;
}
return ret;
}
/**
Copy a string from a unicode or ascii source (depending on
the packet flags) to a char* destination.
Flags can have:
STR_TERMINATE means the string in src is null terminated.
STR_UNICODE means to force as unicode.
STR_ASCII use ascii even with unicode packet.
STR_NOALIGN means don't do alignment.
if STR_TERMINATE is set then src_len is ignored is it is -1
src_len is the length of the source area in bytes.
Return the number of bytes occupied by the string in src.
The resulting string in "dest" is always null terminated.
**/
size_t pull_string_fn(const char *function,
unsigned int line,
const void *base_ptr,
uint16 smb_flags2,
char *dest,
const void *src,
size_t dest_len,
size_t src_len,
int flags)
{
#ifdef DEVELOPER
clobber_region(function, line, dest, dest_len);
#endif
if ((base_ptr == NULL) && ((flags & (STR_ASCII|STR_UNICODE)) == 0)) {
smb_panic("No base ptr to get flg2 and neither ASCII nor "
"UNICODE defined");
}
if (!(flags & STR_ASCII) && \
((flags & STR_UNICODE || \
(smb_flags2 & FLAGS2_UNICODE_STRINGS)))) {
return pull_ucs2(base_ptr, dest, src, dest_len, src_len, flags);
}
return pull_ascii(dest, src, dest_len, src_len, flags);
}
/**
Copy a string from a unicode or ascii source (depending on
the packet flags) to a char* destination.
Variant that uses talloc.
Flags can have:
STR_TERMINATE means the string in src is null terminated.
STR_UNICODE means to force as unicode.
STR_ASCII use ascii even with unicode packet.
STR_NOALIGN means don't do alignment.
if STR_TERMINATE is set then src_len is ignored is it is -1
src_len is the length of the source area in bytes.
Return the number of bytes occupied by the string in src.
The resulting string in "dest" is always null terminated.
**/
size_t pull_string_talloc_fn(const char *function,
unsigned int line,
TALLOC_CTX *ctx,
const void *base_ptr,
uint16 smb_flags2,
char **ppdest,
const void *src,
size_t src_len,
int flags)
{
if ((base_ptr == NULL) && ((flags & (STR_ASCII|STR_UNICODE)) == 0)) {
smb_panic("No base ptr to get flg2 and neither ASCII nor "
"UNICODE defined");
}
if (!(flags & STR_ASCII) && \
((flags & STR_UNICODE || \
(smb_flags2 & FLAGS2_UNICODE_STRINGS)))) {
return pull_ucs2_base_talloc(ctx,
base_ptr,
ppdest,
src,
src_len,
flags);
}
return pull_ascii_base_talloc(ctx,
ppdest,
src,
src_len,
flags);
}
size_t align_string(const void *base_ptr, const char *p, int flags)
{
if (!(flags & STR_ASCII) && \
((flags & STR_UNICODE || \
(SVAL(base_ptr, smb_flg2) & FLAGS2_UNICODE_STRINGS)))) {
return ucs2_align(base_ptr, p, flags);
}
return 0;
}
/*
Return the unicode codepoint for the next multi-byte CH_UNIX character
in the string. The unicode codepoint (codepoint_t) is an unsinged 32 bit value.
Also return the number of bytes consumed (which tells the caller
how many bytes to skip to get to the next CH_UNIX character).
Return INVALID_CODEPOINT if the next character cannot be converted.
*/
codepoint_t next_codepoint(const char *str, size_t *size)
{
/* It cannot occupy more than 4 bytes in UTF16 format */
uint8_t buf[4];
smb_iconv_t descriptor;
size_t ilen_orig;
size_t ilen;
size_t olen;
char *outbuf;
if ((str[0] & 0x80) == 0) {
*size = 1;
return (codepoint_t)str[0];
}
/* We assume that no multi-byte character can take
more than 5 bytes. This is OK as we only
support codepoints up to 1M */
ilen_orig = strnlen(str, 5);
ilen = ilen_orig;
lazy_initialize_conv();
descriptor = conv_handles[CH_UNIX][CH_UTF16LE];
if (descriptor == (smb_iconv_t)-1 || descriptor == (smb_iconv_t)0) {
*size = 1;
return INVALID_CODEPOINT;
}
/* This looks a little strange, but it is needed to cope
with codepoints above 64k which are encoded as per RFC2781. */
olen = 2;
outbuf = (char *)buf;
smb_iconv(descriptor, &str, &ilen, &outbuf, &olen);
if (olen == 2) {
/* We failed to convert to a 2 byte character.
See if we can convert to a 4 UTF16-LE byte char encoding.
*/
olen = 4;
outbuf = (char *)buf;
smb_iconv(descriptor, &str, &ilen, &outbuf, &olen);
if (olen == 4) {
/* We didn't convert any bytes */
*size = 1;
return INVALID_CODEPOINT;
}
olen = 4 - olen;
} else {
olen = 2 - olen;
}
*size = ilen_orig - ilen;
if (olen == 2) {
/* 2 byte, UTF16-LE encoded value. */
return (codepoint_t)SVAL(buf, 0);
}
if (olen == 4) {
/* Decode a 4 byte UTF16-LE character manually.
See RFC2871 for the encoding machanism.
*/
codepoint_t w1 = SVAL(buf,0) & ~0xD800;
codepoint_t w2 = SVAL(buf,2) & ~0xDC00;
return (codepoint_t)0x10000 +
(w1 << 10) + w2;
}
/* no other length is valid */
return INVALID_CODEPOINT;
}
/*
push a single codepoint into a CH_UNIX string the target string must
be able to hold the full character, which is guaranteed if it is at
least 5 bytes in size. The caller may pass less than 5 bytes if they
are sure the character will fit (for example, you can assume that
uppercase/lowercase of a character will not add more than 1 byte)
return the number of bytes occupied by the CH_UNIX character, or
-1 on failure
*/
_PUBLIC_ ssize_t push_codepoint(char *str, codepoint_t c)
{
smb_iconv_t descriptor;
uint8_t buf[4];
size_t ilen, olen;
const char *inbuf;
if (c < 128) {
*str = c;
return 1;
}
lazy_initialize_conv();
descriptor = conv_handles[CH_UNIX][CH_UTF16LE];
if (descriptor == (smb_iconv_t)-1 || descriptor == (smb_iconv_t)0) {
return -1;
}
if (c < 0x10000) {
ilen = 2;
olen = 5;
inbuf = (char *)buf;
SSVAL(buf, 0, c);
smb_iconv(descriptor, &inbuf, &ilen, &str, &olen);
if (ilen != 0) {
return -1;
}
return 5 - olen;
}
c -= 0x10000;
buf[0] = (c>>10) & 0xFF;
buf[1] = (c>>18) | 0xd8;
buf[2] = c & 0xFF;
buf[3] = ((c>>8) & 0x3) | 0xdc;
ilen = 4;
olen = 5;
inbuf = (char *)buf;
smb_iconv(descriptor, &inbuf, &ilen, &str, &olen);
if (ilen != 0) {
return -1;
}
return 5 - olen;
}
|