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
|
/* xgettext Python backend.
Copyright (C) 2002-2003, 2005-2013 Free Software Foundation, Inc.
This file was written by Bruno Haible <haible@clisp.cons.org>, 2002.
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/>. */
#ifdef HAVE_CONFIG_H
# include "config.h"
#endif
/* Specification. */
#include "x-python.h"
#include <assert.h>
#include <errno.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "message.h"
#include "xgettext.h"
#include "error.h"
#include "error-progname.h"
#include "progname.h"
#include "basename.h"
#include "xerror.h"
#include "xvasprintf.h"
#include "xalloc.h"
#include "c-strstr.h"
#include "c-ctype.h"
#include "po-charset.h"
#include "uniname.h"
#include "unistr.h"
#include "gettext.h"
#define _(s) gettext(s)
#define max(a,b) ((a) > (b) ? (a) : (b))
#define SIZEOF(a) (sizeof(a) / sizeof(a[0]))
/* The Python syntax is defined in the Python Reference Manual
/usr/share/doc/packages/python/html/ref/index.html.
See also Python-2.0/Parser/tokenizer.c, Python-2.0/Python/compile.c,
Python-2.0/Objects/unicodeobject.c. */
/* ====================== Keyword set customization. ====================== */
/* If true extract all strings. */
static bool extract_all = false;
static hash_table keywords;
static bool default_keywords = true;
void
x_python_extract_all ()
{
extract_all = true;
}
void
x_python_keyword (const char *name)
{
if (name == NULL)
default_keywords = false;
else
{
const char *end;
struct callshape shape;
const char *colon;
if (keywords.table == NULL)
hash_init (&keywords, 100);
split_keywordspec (name, &end, &shape);
/* The characters between name and end should form a valid C identifier.
A colon means an invalid parse in split_keywordspec(). */
colon = strchr (name, ':');
if (colon == NULL || colon >= end)
insert_keyword_callshape (&keywords, name, end - name, &shape);
}
}
/* Finish initializing the keywords hash table.
Called after argument processing, before each file is processed. */
static void
init_keywords ()
{
if (default_keywords)
{
/* When adding new keywords here, also update the documentation in
xgettext.texi! */
x_python_keyword ("gettext");
x_python_keyword ("ugettext");
x_python_keyword ("dgettext:2");
x_python_keyword ("ngettext:1,2");
x_python_keyword ("ungettext:1,2");
x_python_keyword ("dngettext:2,3");
x_python_keyword ("_");
default_keywords = false;
}
}
void
init_flag_table_python ()
{
xgettext_record_flag ("gettext:1:pass-python-format");
xgettext_record_flag ("ugettext:1:pass-python-format");
xgettext_record_flag ("dgettext:2:pass-python-format");
xgettext_record_flag ("ngettext:1:pass-python-format");
xgettext_record_flag ("ngettext:2:pass-python-format");
xgettext_record_flag ("ungettext:1:pass-python-format");
xgettext_record_flag ("ungettext:2:pass-python-format");
xgettext_record_flag ("dngettext:2:pass-python-format");
xgettext_record_flag ("dngettext:3:pass-python-format");
xgettext_record_flag ("_:1:pass-python-format");
/* xgettext_record_flag ("%:1:python-format"); // % is an infix operator! */
xgettext_record_flag ("gettext:1:pass-python-brace-format");
xgettext_record_flag ("ugettext:1:pass-python-brace-format");
xgettext_record_flag ("dgettext:2:pass-python-brace-format");
xgettext_record_flag ("ngettext:1:pass-python-brace-format");
xgettext_record_flag ("ngettext:2:pass-python-brace-format");
xgettext_record_flag ("ungettext:1:pass-python-brace-format");
xgettext_record_flag ("ungettext:2:pass-python-brace-format");
xgettext_record_flag ("dngettext:2:pass-python-brace-format");
xgettext_record_flag ("dngettext:3:pass-python-brace-format");
xgettext_record_flag ("_:1:pass-python-brace-format");
/* xgettext_record_flag ("format:1:python-brace-format"); */
}
/* ======================== Reading of characters. ======================== */
/* Real filename, used in error messages about the input file. */
static const char *real_file_name;
/* Logical filename and line number, used to label the extracted messages. */
static char *logical_file_name;
static int line_number;
/* The input file stream. */
static FILE *fp;
/* 0. Terminate line by \n, regardless whether the external
representation of a line terminator is CR (Mac), and CR/LF
(DOS/Windows), as Python treats them equally. */
static int
phase0_getc ()
{
int c;
c = getc (fp);
if (c == EOF)
{
if (ferror (fp))
error (EXIT_FAILURE, errno, _("error while reading \"%s\""),
real_file_name);
return EOF;
}
if (c == '\r')
{
int c1 = getc (fp);
if (c1 != EOF && c1 != '\n')
ungetc (c1, fp);
/* Seen line terminator CR or CR/LF. */
return '\n';
}
return c;
}
/* Supports only one pushback character, and not '\n'. */
static inline void
phase0_ungetc (int c)
{
if (c != EOF)
ungetc (c, fp);
}
/* 1. line_number handling. */
/* Maximum used, roughly a safer MB_LEN_MAX. */
#define MAX_PHASE1_PUSHBACK 16
static unsigned char phase1_pushback[MAX_PHASE1_PUSHBACK];
static int phase1_pushback_length;
/* Read the next single byte from the input file. */
static int
phase1_getc ()
{
int c;
if (phase1_pushback_length)
c = phase1_pushback[--phase1_pushback_length];
else
c = phase0_getc ();
if (c == '\n')
++line_number;
return c;
}
/* Supports MAX_PHASE1_PUSHBACK characters of pushback. */
static void
phase1_ungetc (int c)
{
if (c != EOF)
{
if (c == '\n')
--line_number;
if (phase1_pushback_length == SIZEOF (phase1_pushback))
abort ();
phase1_pushback[phase1_pushback_length++] = c;
}
}
/* Phase 2: Conversion to Unicode.
This is done early because PEP 0263 specifies that conversion to Unicode
conceptually occurs before tokenization. A test case where it matters
is with encodings like BIG5: when a double-byte character ending in 0x5C
is followed by '\' or 'u0021', the tokenizer must not treat the second
half of the double-byte character as a backslash. */
/* End-of-file indicator for functions returning an UCS-4 character. */
#define UEOF -1
static lexical_context_ty lexical_context;
static int phase2_pushback[max (9, UNINAME_MAX + 3)];
static int phase2_pushback_length;
/* Read the next Unicode UCS-4 character from the input file. */
static int
phase2_getc ()
{
if (phase2_pushback_length)
return phase2_pushback[--phase2_pushback_length];
if (xgettext_current_source_encoding == po_charset_ascii)
{
int c = phase1_getc ();
if (c == EOF)
return UEOF;
if (!c_isascii (c))
{
multiline_error (xstrdup (""),
xasprintf ("%s\n%s\n",
non_ascii_error_message (lexical_context,
real_file_name,
line_number),
_("\
Please specify the source encoding through --from-code or through a comment\n\
as specified in http://www.python.org/peps/pep-0263.html.\n")));
exit (EXIT_FAILURE);
}
return c;
}
else if (xgettext_current_source_encoding != po_charset_utf8)
{
#if HAVE_ICONV
/* Use iconv on an increasing number of bytes. Read only as many bytes
through phase1_getc as needed. This is needed to give reasonable
interactive behaviour when fp is connected to an interactive tty. */
unsigned char buf[MAX_PHASE1_PUSHBACK];
size_t bufcount;
int c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[0] = (unsigned char) c;
bufcount = 1;
for (;;)
{
unsigned char scratchbuf[6];
const char *inptr = (const char *) &buf[0];
size_t insize = bufcount;
char *outptr = (char *) &scratchbuf[0];
size_t outsize = sizeof (scratchbuf);
size_t res = iconv (xgettext_current_source_iconv,
(ICONV_CONST char **) &inptr, &insize,
&outptr, &outsize);
/* We expect that a character has been produced if and only if
some input bytes have been consumed. */
if ((insize < bufcount) != (outsize < sizeof (scratchbuf)))
abort ();
if (outsize == sizeof (scratchbuf))
{
/* No character has been produced. Must be an error. */
if (res != (size_t)(-1))
abort ();
if (errno == EILSEQ)
{
/* An invalid multibyte sequence was encountered. */
multiline_error (xstrdup (""),
xasprintf (_("\
%s:%d: Invalid multibyte sequence.\n\
Please specify the correct source encoding through --from-code or through a\n\
comment as specified in http://www.python.org/peps/pep-0263.html.\n"),
real_file_name, line_number));
exit (EXIT_FAILURE);
}
else if (errno == EINVAL)
{
/* An incomplete multibyte character. */
int c;
if (bufcount == MAX_PHASE1_PUSHBACK)
{
/* An overlong incomplete multibyte sequence was
encountered. */
multiline_error (xstrdup (""),
xasprintf (_("\
%s:%d: Long incomplete multibyte sequence.\n\
Please specify the correct source encoding through --from-code or through a\n\
comment as specified in http://www.python.org/peps/pep-0263.html.\n"),
real_file_name, line_number));
exit (EXIT_FAILURE);
}
/* Read one more byte and retry iconv. */
c = phase1_getc ();
if (c == EOF)
{
multiline_error (xstrdup (""),
xasprintf (_("\
%s:%d: Incomplete multibyte sequence at end of file.\n\
Please specify the correct source encoding through --from-code or through a\n\
comment as specified in http://www.python.org/peps/pep-0263.html.\n"),
real_file_name, line_number));
exit (EXIT_FAILURE);
}
if (c == '\n')
{
multiline_error (xstrdup (""),
xasprintf (_("\
%s:%d: Incomplete multibyte sequence at end of line.\n\
Please specify the correct source encoding through --from-code or through a\n\
comment as specified in http://www.python.org/peps/pep-0263.html.\n"),
real_file_name, line_number - 1));
exit (EXIT_FAILURE);
}
buf[bufcount++] = (unsigned char) c;
}
else
error (EXIT_FAILURE, errno, _("%s:%d: iconv failure"),
real_file_name, line_number);
}
else
{
size_t outbytes = sizeof (scratchbuf) - outsize;
size_t bytes = bufcount - insize;
ucs4_t uc;
/* We expect that one character has been produced. */
if (bytes == 0)
abort ();
if (outbytes == 0)
abort ();
/* Push back the unused bytes. */
while (insize > 0)
phase1_ungetc (buf[--insize]);
/* Convert the character from UTF-8 to UCS-4. */
if (u8_mbtoucr (&uc, scratchbuf, outbytes) < (int) outbytes)
{
/* scratchbuf contains an out-of-range Unicode character
(> 0x10ffff). */
multiline_error (xstrdup (""),
xasprintf (_("\
%s:%d: Invalid multibyte sequence.\n\
Please specify the source encoding through --from-code or through a comment\n\
as specified in http://www.python.org/peps/pep-0263.html.\n"),
real_file_name, line_number));
exit (EXIT_FAILURE);
}
return uc;
}
}
#else
/* If we don't have iconv(), the only supported values for
xgettext_global_source_encoding and thus also for
xgettext_current_source_encoding are ASCII and UTF-8. */
abort ();
#endif
}
else
{
/* Read an UTF-8 encoded character. */
unsigned char buf[6];
unsigned int count;
int c;
ucs4_t uc;
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[0] = c;
count = 1;
if (buf[0] >= 0xc0)
{
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[1] = c;
count = 2;
}
if (buf[0] >= 0xe0
&& ((buf[1] ^ 0x80) < 0x40))
{
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[2] = c;
count = 3;
}
if (buf[0] >= 0xf0
&& ((buf[1] ^ 0x80) < 0x40)
&& ((buf[2] ^ 0x80) < 0x40))
{
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[3] = c;
count = 4;
}
if (buf[0] >= 0xf8
&& ((buf[1] ^ 0x80) < 0x40)
&& ((buf[2] ^ 0x80) < 0x40)
&& ((buf[3] ^ 0x80) < 0x40))
{
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[4] = c;
count = 5;
}
if (buf[0] >= 0xfc
&& ((buf[1] ^ 0x80) < 0x40)
&& ((buf[2] ^ 0x80) < 0x40)
&& ((buf[3] ^ 0x80) < 0x40)
&& ((buf[4] ^ 0x80) < 0x40))
{
c = phase1_getc ();
if (c == EOF)
return UEOF;
buf[5] = c;
count = 6;
}
u8_mbtouc (&uc, buf, count);
return uc;
}
}
/* Supports max (9, UNINAME_MAX + 3) pushback characters. */
static void
phase2_ungetc (int c)
{
if (c != UEOF)
{
if (phase2_pushback_length == SIZEOF (phase2_pushback))
abort ();
phase2_pushback[phase2_pushback_length++] = c;
}
}
/* ========================= Accumulating strings. ======================== */
/* A string buffer type that allows appending Unicode characters.
Returns the entire string in UTF-8 encoding. */
struct unicode_string_buffer
{
/* The part of the string that has already been converted to UTF-8. */
char *utf8_buffer;
size_t utf8_buflen;
size_t utf8_allocated;
};
/* Initialize a 'struct unicode_string_buffer' to empty. */
static inline void
init_unicode_string_buffer (struct unicode_string_buffer *bp)
{
bp->utf8_buffer = NULL;
bp->utf8_buflen = 0;
bp->utf8_allocated = 0;
}
/* Auxiliary function: Ensure count more bytes are available in bp->utf8. */
static inline void
unicode_string_buffer_append_unicode_grow (struct unicode_string_buffer *bp,
size_t count)
{
if (bp->utf8_buflen + count > bp->utf8_allocated)
{
size_t new_allocated = 2 * bp->utf8_allocated + 10;
if (new_allocated < bp->utf8_buflen + count)
new_allocated = bp->utf8_buflen + count;
bp->utf8_allocated = new_allocated;
bp->utf8_buffer = xrealloc (bp->utf8_buffer, new_allocated);
}
}
/* Auxiliary function: Append a Unicode character to bp->utf8.
uc must be < 0x110000. */
static inline void
unicode_string_buffer_append_unicode (struct unicode_string_buffer *bp,
unsigned int uc)
{
unsigned char utf8buf[6];
int count = u8_uctomb (utf8buf, uc, 6);
if (count < 0)
/* The caller should have ensured that uc is not out-of-range. */
abort ();
unicode_string_buffer_append_unicode_grow (bp, count);
memcpy (bp->utf8_buffer + bp->utf8_buflen, utf8buf, count);
bp->utf8_buflen += count;
}
/* Return the string buffer's contents. */
static char *
unicode_string_buffer_result (struct unicode_string_buffer *bp)
{
/* NUL-terminate it. */
unicode_string_buffer_append_unicode_grow (bp, 1);
bp->utf8_buffer[bp->utf8_buflen] = '\0';
/* Return it. */
return bp->utf8_buffer;
}
/* Free the memory pointed to by a 'struct unicode_string_buffer'. */
static inline void
free_unicode_string_buffer (struct unicode_string_buffer *bp)
{
free (bp->utf8_buffer);
}
/* ======================== Accumulating comments. ======================== */
/* Accumulating a single comment line. */
static struct unicode_string_buffer comment_buffer;
static inline void
comment_start ()
{
lexical_context = lc_comment;
comment_buffer.utf8_buflen = 0;
}
static inline bool
comment_at_start ()
{
return (comment_buffer.utf8_buflen == 0);
}
static inline void
comment_add (int c)
{
unicode_string_buffer_append_unicode (&comment_buffer, c);
}
static inline const char *
comment_line_end ()
{
char *buffer = unicode_string_buffer_result (&comment_buffer);
size_t buflen = strlen (buffer);
while (buflen >= 1
&& (buffer[buflen - 1] == ' ' || buffer[buflen - 1] == '\t'))
--buflen;
buffer[buflen] = '\0';
savable_comment_add (buffer);
lexical_context = lc_outside;
return buffer;
}
/* These are for tracking whether comments count as immediately before
keyword. */
static int last_comment_line;
static int last_non_comment_line;
/* ======================== Recognizing comments. ======================== */
/* Recognizing the "coding" comment.
As specified in PEP 0263, it takes the form
"coding" [":"|"="] {alphanumeric or "-" or "_" or "*"}*
or
"set" "fileencoding" "=" {alphanumeric or "-" or "_" or "*"}*
and is located in a comment in a line that
- is either the first or second line,
- is not a continuation line,
- in the first form, contains no other tokens except this comment. */
/* Canonicalized encoding name for the current input file. */
static const char *xgettext_current_file_source_encoding;
#if HAVE_ICONV
/* Converter from xgettext_current_file_source_encoding to UTF-8 (except from
ASCII or UTF-8, when this conversion is a no-op). */
static iconv_t xgettext_current_file_source_iconv;
#endif
static inline void
set_current_file_source_encoding (const char *canon_encoding)
{
xgettext_current_file_source_encoding = canon_encoding;
if (xgettext_current_file_source_encoding != po_charset_ascii
&& xgettext_current_file_source_encoding != po_charset_utf8)
{
#if HAVE_ICONV
iconv_t cd;
/* Avoid glibc-2.1 bug with EUC-KR. */
# if ((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
&& !defined _LIBICONV_VERSION
if (strcmp (xgettext_current_file_source_encoding, "EUC-KR") == 0)
cd = (iconv_t)(-1);
else
# endif
cd = iconv_open (po_charset_utf8, xgettext_current_file_source_encoding);
if (cd == (iconv_t)(-1))
error_at_line (EXIT_FAILURE, 0, logical_file_name, line_number - 1, _("\
Cannot convert from \"%s\" to \"%s\". %s relies on iconv(), \
and iconv() does not support this conversion."),
xgettext_current_file_source_encoding, po_charset_utf8,
basename (program_name));
xgettext_current_file_source_iconv = cd;
#else
error_at_line (EXIT_FAILURE, 0, logical_file_name, line_number - 1, _("\
Cannot convert from \"%s\" to \"%s\". %s relies on iconv(). \
This version was built without iconv()."),
xgettext_global_source_encoding, po_charset_utf8,
basename (program_name));
#endif
}
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
#if HAVE_ICONV
xgettext_current_source_iconv = xgettext_current_file_source_iconv;
#endif
}
static inline void
try_to_extract_coding (const char *comment)
{
const char *p = c_strstr (comment, "coding");
if (p != NULL)
{
p += 6;
if (*p == ':' || *p == '=')
{
p++;
while (*p == ' ' || *p == '\t')
p++;
{
const char *encoding_start = p;
while (c_isalnum (*p) || *p == '-' || *p == '_' || *p == '.')
p++;
{
const char *encoding_end = p;
if (encoding_end > encoding_start)
{
/* Extract the encoding string. */
size_t encoding_len = encoding_end - encoding_start;
char *encoding = XNMALLOC (encoding_len + 1, char);
memcpy (encoding, encoding_start, encoding_len);
encoding[encoding_len] = '\0';
{
/* Canonicalize it. */
const char *canon_encoding = po_charset_canonicalize (encoding);
if (canon_encoding == NULL)
{
error_at_line (0, 0,
logical_file_name, line_number - 1, _("\
Unknown encoding \"%s\". Proceeding with ASCII instead."),
encoding);
canon_encoding = po_charset_ascii;
}
/* Activate it. */
set_current_file_source_encoding (canon_encoding);
}
free (encoding);
}
}
}
}
}
}
/* Tracking whether the current line is a continuation line or contains a
non-blank character. */
static bool continuation_or_nonblank_line = false;
/* Phase 3: Outside strings, replace backslash-newline with nothing and a
comment with nothing. */
static int
phase3_getc ()
{
int c;
for (;;)
{
c = phase2_getc ();
if (c == '\\')
{
c = phase2_getc ();
if (c != '\n')
{
phase2_ungetc (c);
/* This shouldn't happen usually, because "A backslash is
illegal elsewhere on a line outside a string literal." */
return '\\';
}
/* Eat backslash-newline. */
continuation_or_nonblank_line = true;
}
else if (c == '#')
{
/* Eat a comment. */
const char *comment;
last_comment_line = line_number;
comment_start ();
for (;;)
{
c = phase2_getc ();
if (c == UEOF || c == '\n')
break;
/* We skip all leading white space, but not EOLs. */
if (!(comment_at_start () && (c == ' ' || c == '\t')))
comment_add (c);
}
comment = comment_line_end ();
if (line_number - 1 <= 2 && !continuation_or_nonblank_line)
try_to_extract_coding (comment);
continuation_or_nonblank_line = false;
return c;
}
else
{
if (c == '\n')
continuation_or_nonblank_line = false;
else if (!(c == ' ' || c == '\t' || c == '\f'))
continuation_or_nonblank_line = true;
return c;
}
}
}
/* Supports only one pushback character. */
static void
phase3_ungetc (int c)
{
phase2_ungetc (c);
}
/* ========================= Accumulating strings. ======================== */
/* Return value of phase7_getuc when EOF is reached. */
#define P7_EOF (-1)
#define P7_STRING_END (-2)
/* Convert an UTF-16 or UTF-32 code point to a return value that can be
distinguished from a single-byte return value. */
#define UNICODE(code) (0x100 + (code))
/* Test a return value of phase7_getuc whether it designates an UTF-16 or
UTF-32 code point. */
#define IS_UNICODE(p7_result) ((p7_result) >= 0x100)
/* Extract the UTF-16 or UTF-32 code of a return value that satisfies
IS_UNICODE. */
#define UNICODE_VALUE(p7_result) ((p7_result) - 0x100)
/* ========================== Reading of tokens. ========================== */
enum token_type_ty
{
token_type_eof,
token_type_lparen, /* ( */
token_type_rparen, /* ) */
token_type_comma, /* , */
token_type_lbracket, /* [ */
token_type_rbracket, /* ] */
token_type_string, /* "abc", 'abc', """abc""", '''abc''' */
token_type_symbol, /* symbol, number */
token_type_plus, /* + */
token_type_other /* misc. operator */
};
typedef enum token_type_ty token_type_ty;
typedef struct token_ty token_ty;
struct token_ty
{
token_type_ty type;
char *string; /* for token_type_string, token_type_symbol */
refcounted_string_list_ty *comment; /* for token_type_string */
int line_number;
};
/* Free the memory pointed to by a 'struct token_ty'. */
static inline void
free_token (token_ty *tp)
{
if (tp->type == token_type_string || tp->type == token_type_symbol)
free (tp->string);
if (tp->type == token_type_string)
drop_reference (tp->comment);
}
/* There are two different input syntaxes for strings, "abc" and r"abc",
and two different input syntaxes for Unicode strings, u"abc" and ur"abc".
Which escape sequences are understood, i.e. what is interpreted specially
after backslash?
"abc" \<nl> \\ \' \" \a\b\f\n\r\t\v \ooo \xnn
r"abc"
u"abc" \<nl> \\ \' \" \a\b\f\n\r\t\v \ooo \xnn \unnnn \Unnnnnnnn \N{...}
ur"abc" \unnnn
The \unnnn values are UTF-16 values; a single \Unnnnnnnn can expand to two
\unnnn items. The \ooo and \xnn values are in the current source encoding
for byte strings, and Unicode code points for Unicode strings.
*/
static int
phase7_getuc (int quote_char,
bool triple, bool interpret_ansic, bool interpret_unicode,
unsigned int *backslash_counter)
{
int c;
for (;;)
{
/* Use phase 2, because phase 3 elides comments. */
c = phase2_getc ();
if (c == UEOF)
return P7_EOF;
if (c == quote_char && (interpret_ansic || (*backslash_counter & 1) == 0))
{
if (triple)
{
int c1 = phase2_getc ();
if (c1 == quote_char)
{
int c2 = phase2_getc ();
if (c2 == quote_char)
return P7_STRING_END;
phase2_ungetc (c2);
}
phase2_ungetc (c1);
return UNICODE (c);
}
else
return P7_STRING_END;
}
if (c == '\n')
{
if (triple)
{
*backslash_counter = 0;
return UNICODE ('\n');
}
/* In r"..." and ur"..." strings, newline is only allowed
immediately after an odd number of backslashes (although the
backslashes are not interpreted!). */
if (!(interpret_ansic || (*backslash_counter & 1) == 0))
{
*backslash_counter = 0;
return UNICODE ('\n');
}
phase2_ungetc (c);
error_with_progname = false;
error (0, 0, _("%s:%d: warning: unterminated string"),
logical_file_name, line_number);
error_with_progname = true;
return P7_STRING_END;
}
if (c != '\\')
{
*backslash_counter = 0;
return UNICODE (c);
}
/* Backslash handling. */
if (!interpret_ansic && !interpret_unicode)
{
++*backslash_counter;
return UNICODE ('\\');
}
/* Dispatch according to the character following the backslash. */
c = phase2_getc ();
if (c == UEOF)
{
++*backslash_counter;
return UNICODE ('\\');
}
if (interpret_ansic)
switch (c)
{
case '\n':
continue;
case '\\':
++*backslash_counter;
return UNICODE (c);
case '\'': case '"':
*backslash_counter = 0;
return UNICODE (c);
case 'a':
*backslash_counter = 0;
return UNICODE ('\a');
case 'b':
*backslash_counter = 0;
return UNICODE ('\b');
case 'f':
*backslash_counter = 0;
return UNICODE ('\f');
case 'n':
*backslash_counter = 0;
return UNICODE ('\n');
case 'r':
*backslash_counter = 0;
return UNICODE ('\r');
case 't':
*backslash_counter = 0;
return UNICODE ('\t');
case 'v':
*backslash_counter = 0;
return UNICODE ('\v');
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7':
{
int n = c - '0';
c = phase2_getc ();
if (c != UEOF)
{
if (c >= '0' && c <= '7')
{
n = (n << 3) + (c - '0');
c = phase2_getc ();
if (c != UEOF)
{
if (c >= '0' && c <= '7')
n = (n << 3) + (c - '0');
else
phase2_ungetc (c);
}
}
else
phase2_ungetc (c);
}
*backslash_counter = 0;
if (interpret_unicode)
return UNICODE (n);
else
return (unsigned char) n;
}
case 'x':
{
int c1 = phase2_getc ();
int n1;
if (c1 >= '0' && c1 <= '9')
n1 = c1 - '0';
else if (c1 >= 'A' && c1 <= 'F')
n1 = c1 - 'A' + 10;
else if (c1 >= 'a' && c1 <= 'f')
n1 = c1 - 'a' + 10;
else
n1 = -1;
if (n1 >= 0)
{
int c2 = phase2_getc ();
int n2;
if (c2 >= '0' && c2 <= '9')
n2 = c2 - '0';
else if (c2 >= 'A' && c2 <= 'F')
n2 = c2 - 'A' + 10;
else if (c2 >= 'a' && c2 <= 'f')
n2 = c2 - 'a' + 10;
else
n2 = -1;
if (n2 >= 0)
{
int n = (n1 << 4) + n2;
*backslash_counter = 0;
if (interpret_unicode)
return UNICODE (n);
else
return (unsigned char) n;
}
phase2_ungetc (c2);
}
phase2_ungetc (c1);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
}
if (interpret_unicode)
{
if (c == 'u')
{
unsigned char buf[4];
unsigned int n = 0;
int i;
for (i = 0; i < 4; i++)
{
int c1 = phase2_getc ();
if (c1 >= '0' && c1 <= '9')
n = (n << 4) + (c1 - '0');
else if (c1 >= 'A' && c1 <= 'F')
n = (n << 4) + (c1 - 'A' + 10);
else if (c1 >= 'a' && c1 <= 'f')
n = (n << 4) + (c1 - 'a' + 10);
else
{
phase2_ungetc (c1);
while (--i >= 0)
phase2_ungetc (buf[i]);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
buf[i] = c1;
}
*backslash_counter = 0;
return UNICODE (n);
}
if (interpret_ansic)
{
if (c == 'U')
{
unsigned char buf[8];
unsigned int n = 0;
int i;
for (i = 0; i < 8; i++)
{
int c1 = phase2_getc ();
if (c1 >= '0' && c1 <= '9')
n = (n << 4) + (c1 - '0');
else if (c1 >= 'A' && c1 <= 'F')
n = (n << 4) + (c1 - 'A' + 10);
else if (c1 >= 'a' && c1 <= 'f')
n = (n << 4) + (c1 - 'a' + 10);
else
{
phase2_ungetc (c1);
while (--i >= 0)
phase2_ungetc (buf[i]);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
buf[i] = c1;
}
if (n < 0x110000)
{
*backslash_counter = 0;
return UNICODE (n);
}
error_with_progname = false;
error (0, 0, _("%s:%d: warning: invalid Unicode character"),
logical_file_name, line_number);
error_with_progname = true;
while (--i >= 0)
phase2_ungetc (buf[i]);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
if (c == 'N')
{
int c1 = phase2_getc ();
if (c1 == '{')
{
unsigned char buf[UNINAME_MAX + 1];
int i;
unsigned int n;
for (i = 0; i < UNINAME_MAX; i++)
{
int c2 = phase2_getc ();
if (!(c2 >= ' ' && c2 <= '~'))
{
phase2_ungetc (c2);
while (--i >= 0)
phase2_ungetc (buf[i]);
phase2_ungetc (c1);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
if (c2 == '}')
break;
buf[i] = c2;
}
buf[i] = '\0';
n = unicode_name_character ((char *) buf);
if (n != UNINAME_INVALID)
{
*backslash_counter = 0;
return UNICODE (n);
}
phase2_ungetc ('}');
while (--i >= 0)
phase2_ungetc (buf[i]);
}
phase2_ungetc (c1);
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
}
}
phase2_ungetc (c);
++*backslash_counter;
return UNICODE ('\\');
}
}
/* Combine characters into tokens. Discard whitespace except newlines at
the end of logical lines. */
/* Number of pending open parentheses/braces/brackets. */
static int open_pbb;
static token_ty phase5_pushback[2];
static int phase5_pushback_length;
static void
phase5_get (token_ty *tp)
{
int c;
if (phase5_pushback_length)
{
*tp = phase5_pushback[--phase5_pushback_length];
return;
}
for (;;)
{
tp->line_number = line_number;
c = phase3_getc ();
switch (c)
{
case UEOF:
tp->type = token_type_eof;
return;
case ' ':
case '\t':
case '\f':
/* Ignore whitespace and comments. */
continue;
case '\n':
if (last_non_comment_line > last_comment_line)
savable_comment_reset ();
/* Ignore newline if and only if it is used for implicit line
joining. */
if (open_pbb > 0)
continue;
tp->type = token_type_other;
return;
}
last_non_comment_line = tp->line_number;
switch (c)
{
case '.':
{
int c1 = phase3_getc ();
phase3_ungetc (c1);
if (!(c1 >= '0' && c1 <= '9'))
{
tp->type = token_type_other;
return;
}
}
/* FALLTHROUGH */
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q':
case 'S': case 'T': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '_':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q':
case 's': case 't': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
symbol:
/* Symbol, or part of a number. */
{
static char *buffer;
static int bufmax;
int bufpos;
bufpos = 0;
for (;;)
{
if (bufpos >= bufmax)
{
bufmax = 2 * bufmax + 10;
buffer = xrealloc (buffer, bufmax);
}
buffer[bufpos++] = c;
c = phase3_getc ();
switch (c)
{
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '_':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
continue;
default:
phase3_ungetc (c);
break;
}
break;
}
if (bufpos >= bufmax)
{
bufmax = 2 * bufmax + 10;
buffer = xrealloc (buffer, bufmax);
}
buffer[bufpos] = '\0';
tp->string = xstrdup (buffer);
tp->type = token_type_symbol;
return;
}
/* Strings. */
{
struct mixed_string_buffer *bp;
int quote_char;
bool interpret_ansic;
bool interpret_unicode;
bool triple;
unsigned int backslash_counter;
case 'R': case 'r':
{
int c1 = phase2_getc ();
if (c1 == '"' || c1 == '\'')
{
quote_char = c1;
interpret_ansic = false;
interpret_unicode = false;
goto string;
}
phase2_ungetc (c1);
goto symbol;
}
case 'U': case 'u':
{
int c1 = phase2_getc ();
if (c1 == '"' || c1 == '\'')
{
quote_char = c1;
interpret_ansic = true;
interpret_unicode = true;
goto string;
}
if (c1 == 'R' || c1 == 'r')
{
int c2 = phase2_getc ();
if (c2 == '"' || c2 == '\'')
{
quote_char = c2;
interpret_ansic = false;
interpret_unicode = true;
goto string;
}
phase2_ungetc (c2);
}
phase2_ungetc (c1);
goto symbol;
}
case '"': case '\'':
quote_char = c;
interpret_ansic = true;
interpret_unicode = false;
string:
triple = false;
lexical_context = lc_string;
{
int c1 = phase2_getc ();
if (c1 == quote_char)
{
int c2 = phase2_getc ();
if (c2 == quote_char)
triple = true;
else
{
phase2_ungetc (c2);
phase2_ungetc (c1);
}
}
else
phase2_ungetc (c1);
}
backslash_counter = 0;
/* Start accumulating the string. */
bp = mixed_string_buffer_alloc (lexical_context,
logical_file_name,
line_number);
for (;;)
{
int uc = phase7_getuc (quote_char, triple, interpret_ansic,
interpret_unicode, &backslash_counter);
bp->line_number = line_number;
if (uc == P7_EOF || uc == P7_STRING_END)
break;
if (IS_UNICODE (uc))
{
assert (UNICODE_VALUE (uc) >= 0
&& UNICODE_VALUE (uc) < 0x110000);
mixed_string_buffer_append_unicode (bp,
UNICODE_VALUE (uc));
}
else
mixed_string_buffer_append_char (bp, uc);
}
tp->string = xstrdup (mixed_string_buffer_done (bp));
tp->comment = add_reference (savable_comment);
lexical_context = lc_outside;
tp->type = token_type_string;
return;
}
case '(':
open_pbb++;
tp->type = token_type_lparen;
return;
case ')':
if (open_pbb > 0)
open_pbb--;
tp->type = token_type_rparen;
return;
case ',':
tp->type = token_type_comma;
return;
case '[': case '{':
open_pbb++;
tp->type = (c == '[' ? token_type_lbracket : token_type_other);
return;
case ']': case '}':
if (open_pbb > 0)
open_pbb--;
tp->type = (c == ']' ? token_type_rbracket : token_type_other);
return;
case '+':
tp->type = token_type_plus;
return;
default:
/* We could carefully recognize each of the 2 and 3 character
operators, but it is not necessary, as we only need to recognize
gettext invocations. Don't bother. */
tp->type = token_type_other;
return;
}
}
}
/* Supports only one pushback token. */
static void
phase5_unget (token_ty *tp)
{
if (tp->type != token_type_eof)
{
if (phase5_pushback_length == SIZEOF (phase5_pushback))
abort ();
phase5_pushback[phase5_pushback_length++] = *tp;
}
}
/* Combine adjacent strings to form a single string. Note that the end
of a logical line appears as a token of its own, therefore strings that
belong to different logical lines will not be concatenated. */
static void
x_python_lex (token_ty *tp)
{
phase5_get (tp);
if (tp->type == token_type_string)
{
char *sum = tp->string;
size_t sum_len = strlen (sum);
for (;;)
{
token_ty token2, *tp2 = NULL;
phase5_get (&token2);
switch (token2.type)
{
case token_type_plus:
{
token_ty token3;
phase5_get (&token3);
if (token3.type == token_type_string)
{
free_token (&token2);
tp2 = &token3;
}
else
phase5_unget (&token3);
}
break;
case token_type_string:
tp2 = &token2;
break;
default:
break;
}
if (tp2)
{
char *addend = tp2->string;
size_t addend_len = strlen (addend);
sum = (char *) xrealloc (sum, sum_len + addend_len + 1);
memcpy (sum + sum_len, addend, addend_len + 1);
sum_len += addend_len;
free_token (tp2);
continue;
}
phase5_unget (&token2);
break;
}
tp->string = sum;
}
}
/* ========================= Extracting strings. ========================== */
/* Context lookup table. */
static flag_context_list_table_ty *flag_context_list_table;
/* The file is broken into tokens. Scan the token stream, looking for
a keyword, followed by a left paren, followed by a string. When we
see this sequence, we have something to remember. We assume we are
looking at a valid C or C++ program, and leave the complaints about
the grammar to the compiler.
Normal handling: Look for
keyword ( ... msgid ... )
Plural handling: Look for
keyword ( ... msgid ... msgid_plural ... )
We use recursion because the arguments before msgid or between msgid
and msgid_plural can contain subexpressions of the same form. */
/* Extract messages until the next balanced closing parenthesis or bracket.
Extracted messages are added to MLP.
DELIM can be either token_type_rparen or token_type_rbracket, or
token_type_eof to accept both.
Return true upon eof, false upon closing parenthesis or bracket. */
static bool
extract_balanced (message_list_ty *mlp,
token_type_ty delim,
flag_context_ty outer_context,
flag_context_list_iterator_ty context_iter,
struct arglist_parser *argparser)
{
/* Current argument number. */
int arg = 1;
/* 0 when no keyword has been seen. 1 right after a keyword is seen. */
int state;
/* Parameters of the keyword just seen. Defined only in state 1. */
const struct callshapes *next_shapes = NULL;
/* Context iterator that will be used if the next token is a '('. */
flag_context_list_iterator_ty next_context_iter =
passthrough_context_list_iterator;
/* Current context. */
flag_context_ty inner_context =
inherited_context (outer_context,
flag_context_list_iterator_advance (&context_iter));
/* Start state is 0. */
state = 0;
for (;;)
{
token_ty token;
x_python_lex (&token);
switch (token.type)
{
case token_type_symbol:
{
void *keyword_value;
if (hash_find_entry (&keywords, token.string, strlen (token.string),
&keyword_value)
== 0)
{
next_shapes = (const struct callshapes *) keyword_value;
state = 1;
}
else
state = 0;
}
next_context_iter =
flag_context_list_iterator (
flag_context_list_table_lookup (
flag_context_list_table,
token.string, strlen (token.string)));
free (token.string);
continue;
case token_type_lparen:
if (extract_balanced (mlp, token_type_rparen,
inner_context, next_context_iter,
arglist_parser_alloc (mlp,
state ? next_shapes : NULL)))
{
xgettext_current_source_encoding = po_charset_utf8;
arglist_parser_done (argparser, arg);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
return true;
}
next_context_iter = null_context_list_iterator;
state = 0;
continue;
case token_type_rparen:
if (delim == token_type_rparen || delim == token_type_eof)
{
xgettext_current_source_encoding = po_charset_utf8;
arglist_parser_done (argparser, arg);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
return false;
}
next_context_iter = null_context_list_iterator;
state = 0;
continue;
case token_type_comma:
arg++;
inner_context =
inherited_context (outer_context,
flag_context_list_iterator_advance (
&context_iter));
next_context_iter = passthrough_context_list_iterator;
state = 0;
continue;
case token_type_lbracket:
if (extract_balanced (mlp, token_type_rbracket,
null_context, null_context_list_iterator,
arglist_parser_alloc (mlp, NULL)))
{
xgettext_current_source_encoding = po_charset_utf8;
arglist_parser_done (argparser, arg);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
return true;
}
next_context_iter = null_context_list_iterator;
state = 0;
continue;
case token_type_rbracket:
if (delim == token_type_rbracket || delim == token_type_eof)
{
xgettext_current_source_encoding = po_charset_utf8;
arglist_parser_done (argparser, arg);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
return false;
}
next_context_iter = null_context_list_iterator;
state = 0;
continue;
case token_type_string:
{
lex_pos_ty pos;
pos.file_name = logical_file_name;
pos.line_number = token.line_number;
xgettext_current_source_encoding = po_charset_utf8;
if (extract_all)
remember_a_message (mlp, NULL, token.string, inner_context,
&pos, NULL, token.comment);
else
arglist_parser_remember (argparser, arg, token.string,
inner_context,
pos.file_name, pos.line_number,
token.comment);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
}
drop_reference (token.comment);
next_context_iter = null_context_list_iterator;
state = 0;
continue;
case token_type_eof:
xgettext_current_source_encoding = po_charset_utf8;
arglist_parser_done (argparser, arg);
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
return true;
case token_type_plus:
case token_type_other:
next_context_iter = null_context_list_iterator;
state = 0;
continue;
default:
abort ();
}
}
}
void
extract_python (FILE *f,
const char *real_filename, const char *logical_filename,
flag_context_list_table_ty *flag_table,
msgdomain_list_ty *mdlp)
{
message_list_ty *mlp = mdlp->item[0]->messages;
fp = f;
real_file_name = real_filename;
logical_file_name = xstrdup (logical_filename);
line_number = 1;
lexical_context = lc_outside;
last_comment_line = -1;
last_non_comment_line = -1;
xgettext_current_file_source_encoding = xgettext_global_source_encoding;
#if HAVE_ICONV
xgettext_current_file_source_iconv = xgettext_global_source_iconv;
#endif
xgettext_current_source_encoding = xgettext_current_file_source_encoding;
#if HAVE_ICONV
xgettext_current_source_iconv = xgettext_current_file_source_iconv;
#endif
continuation_or_nonblank_line = false;
open_pbb = 0;
flag_context_list_table = flag_table;
init_keywords ();
/* Eat tokens until eof is seen. When extract_balanced returns
due to an unbalanced closing parenthesis, just restart it. */
while (!extract_balanced (mlp, token_type_eof,
null_context, null_context_list_iterator,
arglist_parser_alloc (mlp, NULL)))
;
fp = NULL;
real_file_name = NULL;
logical_file_name = NULL;
line_number = 0;
}
|