1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
|
/*
An implementation of Text I/O as defined by PEP 3116 - "New I/O"
Classes defined here: TextIOBase, IncrementalNewlineDecoder, TextIOWrapper.
Written by Amaury Forgeot d'Arc and Antoine Pitrou
*/
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "structmember.h"
#include "_iomodule.h"
/* TextIOBase */
PyDoc_STRVAR(textiobase_doc,
"Base class for text I/O.\n"
"\n"
"This class provides a character and line based interface to stream\n"
"I/O. There is no readinto method because Python's character strings\n"
"are immutable. There is no public constructor.\n"
);
static PyObject *
_unsupported(const char *message)
{
PyErr_SetString(_PyIO_unsupported_operation, message);
return NULL;
}
PyDoc_STRVAR(textiobase_detach_doc,
"Separate the underlying buffer from the TextIOBase and return it.\n"
"\n"
"After the underlying buffer has been detached, the TextIO is in an\n"
"unusable state.\n"
);
static PyObject *
textiobase_detach(PyObject *self)
{
return _unsupported("detach");
}
PyDoc_STRVAR(textiobase_read_doc,
"Read at most n characters from stream.\n"
"\n"
"Read from underlying buffer until we have n characters or we hit EOF.\n"
"If n is negative or omitted, read until EOF.\n"
);
static PyObject *
textiobase_read(PyObject *self, PyObject *args)
{
return _unsupported("read");
}
PyDoc_STRVAR(textiobase_readline_doc,
"Read until newline or EOF.\n"
"\n"
"Returns an empty string if EOF is hit immediately.\n"
);
static PyObject *
textiobase_readline(PyObject *self, PyObject *args)
{
return _unsupported("readline");
}
PyDoc_STRVAR(textiobase_write_doc,
"Write string to stream.\n"
"Returns the number of characters written (which is always equal to\n"
"the length of the string).\n"
);
static PyObject *
textiobase_write(PyObject *self, PyObject *args)
{
return _unsupported("write");
}
PyDoc_STRVAR(textiobase_encoding_doc,
"Encoding of the text stream.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_encoding_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
PyDoc_STRVAR(textiobase_newlines_doc,
"Line endings translated so far.\n"
"\n"
"Only line endings translated during reading are considered.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_newlines_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
PyDoc_STRVAR(textiobase_errors_doc,
"The error setting of the decoder or encoder.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_errors_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
static PyMethodDef textiobase_methods[] = {
{"detach", (PyCFunction)textiobase_detach, METH_NOARGS, textiobase_detach_doc},
{"read", textiobase_read, METH_VARARGS, textiobase_read_doc},
{"readline", textiobase_readline, METH_VARARGS, textiobase_readline_doc},
{"write", textiobase_write, METH_VARARGS, textiobase_write_doc},
{NULL, NULL}
};
static PyGetSetDef textiobase_getset[] = {
{"encoding", (getter)textiobase_encoding_get, NULL, textiobase_encoding_doc},
{"newlines", (getter)textiobase_newlines_get, NULL, textiobase_newlines_doc},
{"errors", (getter)textiobase_errors_get, NULL, textiobase_errors_doc},
{NULL}
};
PyTypeObject PyTextIOBase_Type = {
PyVarObject_HEAD_INIT(NULL, 0)
"_io._TextIOBase", /*tp_name*/
0, /*tp_basicsize*/
0, /*tp_itemsize*/
0, /*tp_dealloc*/
0, /*tp_print*/
0, /*tp_getattr*/
0, /*tp_setattr*/
0, /*tp_compare */
0, /*tp_repr*/
0, /*tp_as_number*/
0, /*tp_as_sequence*/
0, /*tp_as_mapping*/
0, /*tp_hash */
0, /*tp_call*/
0, /*tp_str*/
0, /*tp_getattro*/
0, /*tp_setattro*/
0, /*tp_as_buffer*/
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /*tp_flags*/
textiobase_doc, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
textiobase_methods, /* tp_methods */
0, /* tp_members */
textiobase_getset, /* tp_getset */
&PyIOBase_Type, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
0, /* tp_init */
0, /* tp_alloc */
0, /* tp_new */
};
/* IncrementalNewlineDecoder */
PyDoc_STRVAR(incrementalnewlinedecoder_doc,
"Codec used when reading a file in universal newlines mode. It wraps\n"
"another incremental decoder, translating \\r\\n and \\r into \\n. It also\n"
"records the types of newlines encountered. When used with\n"
"translate=False, it ensures that the newline sequence is returned in\n"
"one piece. When used with decoder=None, it expects unicode strings as\n"
"decode input and translates newlines without first invoking an external\n"
"decoder.\n"
);
typedef struct {
PyObject_HEAD
PyObject *decoder;
PyObject *errors;
signed int pendingcr: 1;
signed int translate: 1;
unsigned int seennl: 3;
} nldecoder_object;
static int
incrementalnewlinedecoder_init(nldecoder_object *self,
PyObject *args, PyObject *kwds)
{
PyObject *decoder;
int translate;
PyObject *errors = NULL;
char *kwlist[] = {"decoder", "translate", "errors", NULL};
if (!PyArg_ParseTupleAndKeywords(args, kwds, "Oi|O:IncrementalNewlineDecoder",
kwlist, &decoder, &translate, &errors))
return -1;
self->decoder = decoder;
Py_INCREF(decoder);
if (errors == NULL) {
self->errors = PyUnicode_FromString("strict");
if (self->errors == NULL)
return -1;
}
else {
Py_INCREF(errors);
self->errors = errors;
}
self->translate = translate;
self->seennl = 0;
self->pendingcr = 0;
return 0;
}
static void
incrementalnewlinedecoder_dealloc(nldecoder_object *self)
{
Py_CLEAR(self->decoder);
Py_CLEAR(self->errors);
Py_TYPE(self)->tp_free((PyObject *)self);
}
static int
check_decoded(PyObject *decoded)
{
if (decoded == NULL)
return -1;
if (!PyUnicode_Check(decoded)) {
PyErr_Format(PyExc_TypeError,
"decoder should return a string result, not '%.200s'",
Py_TYPE(decoded)->tp_name);
Py_DECREF(decoded);
return -1;
}
return 0;
}
#define SEEN_CR 1
#define SEEN_LF 2
#define SEEN_CRLF 4
#define SEEN_ALL (SEEN_CR | SEEN_LF | SEEN_CRLF)
PyObject *
_PyIncrementalNewlineDecoder_decode(PyObject *_self,
PyObject *input, int final)
{
PyObject *output;
Py_ssize_t output_len;
nldecoder_object *self = (nldecoder_object *) _self;
if (self->decoder == NULL) {
PyErr_SetString(PyExc_ValueError,
"IncrementalNewlineDecoder.__init__ not called");
return NULL;
}
/* decode input (with the eventual \r from a previous pass) */
if (self->decoder != Py_None) {
output = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_decode, input, final ? Py_True : Py_False, NULL);
}
else {
output = input;
Py_INCREF(output);
}
if (check_decoded(output) < 0)
return NULL;
output_len = PyUnicode_GET_SIZE(output);
if (self->pendingcr && (final || output_len > 0)) {
Py_UNICODE *out;
PyObject *modified = PyUnicode_FromUnicode(NULL, output_len + 1);
if (modified == NULL)
goto error;
out = PyUnicode_AS_UNICODE(modified);
out[0] = '\r';
memcpy(out + 1, PyUnicode_AS_UNICODE(output),
output_len * sizeof(Py_UNICODE));
Py_DECREF(output);
output = modified;
self->pendingcr = 0;
output_len++;
}
/* retain last \r even when not translating data:
* then readline() is sure to get \r\n in one pass
*/
if (!final) {
if (output_len > 0
&& PyUnicode_AS_UNICODE(output)[output_len - 1] == '\r') {
if (Py_REFCNT(output) == 1) {
if (PyUnicode_Resize(&output, output_len - 1) < 0)
goto error;
}
else {
PyObject *modified = PyUnicode_FromUnicode(
PyUnicode_AS_UNICODE(output),
output_len - 1);
if (modified == NULL)
goto error;
Py_DECREF(output);
output = modified;
}
self->pendingcr = 1;
}
}
/* Record which newlines are read and do newline translation if desired,
all in one pass. */
{
Py_UNICODE *in_str;
Py_ssize_t len;
int seennl = self->seennl;
int only_lf = 0;
in_str = PyUnicode_AS_UNICODE(output);
len = PyUnicode_GET_SIZE(output);
if (len == 0)
return output;
/* If, up to now, newlines are consistently \n, do a quick check
for the \r *byte* with the libc's optimized memchr.
*/
if (seennl == SEEN_LF || seennl == 0) {
only_lf = (memchr(in_str, '\r', len * sizeof(Py_UNICODE)) == NULL);
}
if (only_lf) {
/* If not already seen, quick scan for a possible "\n" character.
(there's nothing else to be done, even when in translation mode)
*/
if (seennl == 0 &&
memchr(in_str, '\n', len * sizeof(Py_UNICODE)) != NULL) {
Py_UNICODE *s, *end;
s = in_str;
end = in_str + len;
for (;;) {
Py_UNICODE c;
/* Fast loop for non-control characters */
while (*s > '\n')
s++;
c = *s++;
if (c == '\n') {
seennl |= SEEN_LF;
break;
}
if (s > end)
break;
}
}
/* Finished: we have scanned for newlines, and none of them
need translating */
}
else if (!self->translate) {
Py_UNICODE *s, *end;
/* We have already seen all newline types, no need to scan again */
if (seennl == SEEN_ALL)
goto endscan;
s = in_str;
end = in_str + len;
for (;;) {
Py_UNICODE c;
/* Fast loop for non-control characters */
while (*s > '\r')
s++;
c = *s++;
if (c == '\n')
seennl |= SEEN_LF;
else if (c == '\r') {
if (*s == '\n') {
seennl |= SEEN_CRLF;
s++;
}
else
seennl |= SEEN_CR;
}
if (s > end)
break;
if (seennl == SEEN_ALL)
break;
}
endscan:
;
}
else {
PyObject *translated = NULL;
Py_UNICODE *out_str;
Py_UNICODE *in, *out, *end;
if (Py_REFCNT(output) != 1) {
/* We could try to optimize this so that we only do a copy
when there is something to translate. On the other hand,
most decoders should only output non-shared strings, i.e.
translation is done in place. */
translated = PyUnicode_FromUnicode(NULL, len);
if (translated == NULL)
goto error;
assert(Py_REFCNT(translated) == 1);
memcpy(PyUnicode_AS_UNICODE(translated),
PyUnicode_AS_UNICODE(output),
len * sizeof(Py_UNICODE));
}
else {
translated = output;
}
out_str = PyUnicode_AS_UNICODE(translated);
in = in_str;
out = out_str;
end = in_str + len;
for (;;) {
Py_UNICODE c;
/* Fast loop for non-control characters */
while ((c = *in++) > '\r')
*out++ = c;
if (c == '\n') {
*out++ = c;
seennl |= SEEN_LF;
continue;
}
if (c == '\r') {
if (*in == '\n') {
in++;
seennl |= SEEN_CRLF;
}
else
seennl |= SEEN_CR;
*out++ = '\n';
continue;
}
if (in > end)
break;
*out++ = c;
}
if (translated != output) {
Py_DECREF(output);
output = translated;
}
if (out - out_str != len) {
if (PyUnicode_Resize(&output, out - out_str) < 0)
goto error;
}
}
self->seennl |= seennl;
}
return output;
error:
Py_DECREF(output);
return NULL;
}
static PyObject *
incrementalnewlinedecoder_decode(nldecoder_object *self,
PyObject *args, PyObject *kwds)
{
char *kwlist[] = {"input", "final", NULL};
PyObject *input;
int final = 0;
if (!PyArg_ParseTupleAndKeywords(args, kwds, "O|i:IncrementalNewlineDecoder",
kwlist, &input, &final))
return NULL;
return _PyIncrementalNewlineDecoder_decode((PyObject *) self, input, final);
}
static PyObject *
incrementalnewlinedecoder_getstate(nldecoder_object *self, PyObject *args)
{
PyObject *buffer;
unsigned PY_LONG_LONG flag;
if (self->decoder != Py_None) {
PyObject *state = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_getstate, NULL);
if (state == NULL)
return NULL;
if (!PyArg_Parse(state, "(OK)", &buffer, &flag)) {
Py_DECREF(state);
return NULL;
}
Py_INCREF(buffer);
Py_DECREF(state);
}
else {
buffer = PyBytes_FromString("");
flag = 0;
}
flag <<= 1;
if (self->pendingcr)
flag |= 1;
return Py_BuildValue("NK", buffer, flag);
}
static PyObject *
incrementalnewlinedecoder_setstate(nldecoder_object *self, PyObject *state)
{
PyObject *buffer;
unsigned PY_LONG_LONG flag;
if (!PyArg_Parse(state, "(OK)", &buffer, &flag))
return NULL;
self->pendingcr = (int) flag & 1;
flag >>= 1;
if (self->decoder != Py_None)
return PyObject_CallMethod(self->decoder,
"setstate", "((OK))", buffer, flag);
else
Py_RETURN_NONE;
}
static PyObject *
incrementalnewlinedecoder_reset(nldecoder_object *self, PyObject *args)
{
self->seennl = 0;
self->pendingcr = 0;
if (self->decoder != Py_None)
return PyObject_CallMethodObjArgs(self->decoder, _PyIO_str_reset, NULL);
else
Py_RETURN_NONE;
}
static PyObject *
incrementalnewlinedecoder_newlines_get(nldecoder_object *self, void *context)
{
switch (self->seennl) {
case SEEN_CR:
return PyUnicode_FromString("\r");
case SEEN_LF:
return PyUnicode_FromString("\n");
case SEEN_CRLF:
return PyUnicode_FromString("\r\n");
case SEEN_CR | SEEN_LF:
return Py_BuildValue("ss", "\r", "\n");
case SEEN_CR | SEEN_CRLF:
return Py_BuildValue("ss", "\r", "\r\n");
case SEEN_LF | SEEN_CRLF:
return Py_BuildValue("ss", "\n", "\r\n");
case SEEN_CR | SEEN_LF | SEEN_CRLF:
return Py_BuildValue("sss", "\r", "\n", "\r\n");
default:
Py_RETURN_NONE;
}
}
static PyMethodDef incrementalnewlinedecoder_methods[] = {
{"decode", (PyCFunction)incrementalnewlinedecoder_decode, METH_VARARGS|METH_KEYWORDS},
{"getstate", (PyCFunction)incrementalnewlinedecoder_getstate, METH_NOARGS},
{"setstate", (PyCFunction)incrementalnewlinedecoder_setstate, METH_O},
{"reset", (PyCFunction)incrementalnewlinedecoder_reset, METH_NOARGS},
{NULL}
};
static PyGetSetDef incrementalnewlinedecoder_getset[] = {
{"newlines", (getter)incrementalnewlinedecoder_newlines_get, NULL, NULL},
{NULL}
};
PyTypeObject PyIncrementalNewlineDecoder_Type = {
PyVarObject_HEAD_INIT(NULL, 0)
"_io.IncrementalNewlineDecoder", /*tp_name*/
sizeof(nldecoder_object), /*tp_basicsize*/
0, /*tp_itemsize*/
(destructor)incrementalnewlinedecoder_dealloc, /*tp_dealloc*/
0, /*tp_print*/
0, /*tp_getattr*/
0, /*tp_setattr*/
0, /*tp_compare */
0, /*tp_repr*/
0, /*tp_as_number*/
0, /*tp_as_sequence*/
0, /*tp_as_mapping*/
0, /*tp_hash */
0, /*tp_call*/
0, /*tp_str*/
0, /*tp_getattro*/
0, /*tp_setattro*/
0, /*tp_as_buffer*/
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /*tp_flags*/
incrementalnewlinedecoder_doc, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /*tp_weaklistoffset*/
0, /* tp_iter */
0, /* tp_iternext */
incrementalnewlinedecoder_methods, /* tp_methods */
0, /* tp_members */
incrementalnewlinedecoder_getset, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc)incrementalnewlinedecoder_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
/* TextIOWrapper */
PyDoc_STRVAR(textiowrapper_doc,
"Character and line based layer over a BufferedIOBase object, buffer.\n"
"\n"
"encoding gives the name of the encoding that the stream will be\n"
"decoded or encoded with. It defaults to locale.getpreferredencoding.\n"
"\n"
"errors determines the strictness of encoding and decoding (see the\n"
"codecs.register) and defaults to \"strict\".\n"
"\n"
"newline controls how line endings are handled. It can be None, '',\n"
"'\\n', '\\r', and '\\r\\n'. It works as follows:\n"
"\n"
"* On input, if newline is None, universal newlines mode is\n"
" enabled. Lines in the input can end in '\\n', '\\r', or '\\r\\n', and\n"
" these are translated into '\\n' before being returned to the\n"
" caller. If it is '', universal newline mode is enabled, but line\n"
" endings are returned to the caller untranslated. If it has any of\n"
" the other legal values, input lines are only terminated by the given\n"
" string, and the line ending is returned to the caller untranslated.\n"
"\n"
"* On output, if newline is None, any '\\n' characters written are\n"
" translated to the system default line separator, os.linesep. If\n"
" newline is '', no translation takes place. If newline is any of the\n"
" other legal values, any '\\n' characters written are translated to\n"
" the given string.\n"
"\n"
"If line_buffering is True, a call to flush is implied when a call to\n"
"write contains a newline character."
);
typedef PyObject *
(*encodefunc_t)(PyObject *, PyObject *);
typedef struct
{
PyObject_HEAD
int ok; /* initialized? */
int detached;
Py_ssize_t chunk_size;
PyObject *buffer;
PyObject *encoding;
PyObject *encoder;
PyObject *decoder;
PyObject *readnl;
PyObject *errors;
const char *writenl; /* utf-8 encoded, NULL stands for \n */
char line_buffering;
char readuniversal;
char readtranslate;
char writetranslate;
char seekable;
char telling;
/* Specialized encoding func (see below) */
encodefunc_t encodefunc;
/* Whether or not it's the start of the stream */
char encoding_start_of_stream;
/* Reads and writes are internally buffered in order to speed things up.
However, any read will first flush the write buffer if itsn't empty.
Please also note that text to be written is first encoded before being
buffered. This is necessary so that encoding errors are immediately
reported to the caller, but it unfortunately means that the
IncrementalEncoder (whose encode() method is always written in Python)
becomes a bottleneck for small writes.
*/
PyObject *decoded_chars; /* buffer for text returned from decoder */
Py_ssize_t decoded_chars_used; /* offset into _decoded_chars for read() */
PyObject *pending_bytes; /* list of bytes objects waiting to be
written, or NULL */
Py_ssize_t pending_bytes_count;
PyObject *snapshot;
/* snapshot is either None, or a tuple (dec_flags, next_input) where
* dec_flags is the second (integer) item of the decoder state and
* next_input is the chunk of input bytes that comes next after the
* snapshot point. We use this to reconstruct decoder states in tell().
*/
/* Cache raw object if it's a FileIO object */
PyObject *raw;
PyObject *weakreflist;
PyObject *dict;
} textio;
/* A couple of specialized cases in order to bypass the slow incremental
encoding methods for the most popular encodings. */
static PyObject *
ascii_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeASCII(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors));
}
static PyObject *
utf16be_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeUTF16(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), 1);
}
static PyObject *
utf16le_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeUTF16(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), -1);
}
static PyObject *
utf16_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if defined(WORDS_BIGENDIAN)
return utf16be_encode(self, text);
#else
return utf16le_encode(self, text);
#endif
}
return PyUnicode_EncodeUTF16(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), 0);
}
static PyObject *
utf32be_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeUTF32(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), 1);
}
static PyObject *
utf32le_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeUTF32(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), -1);
}
static PyObject *
utf32_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if defined(WORDS_BIGENDIAN)
return utf32be_encode(self, text);
#else
return utf32le_encode(self, text);
#endif
}
return PyUnicode_EncodeUTF32(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors), 0);
}
static PyObject *
utf8_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors));
}
static PyObject *
latin1_encode(textio *self, PyObject *text)
{
return PyUnicode_EncodeLatin1(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text),
PyBytes_AS_STRING(self->errors));
}
/* Map normalized encoding names onto the specialized encoding funcs */
typedef struct {
const char *name;
encodefunc_t encodefunc;
} encodefuncentry;
static encodefuncentry encodefuncs[] = {
{"ascii", (encodefunc_t) ascii_encode},
{"iso8859-1", (encodefunc_t) latin1_encode},
{"utf-8", (encodefunc_t) utf8_encode},
{"utf-16-be", (encodefunc_t) utf16be_encode},
{"utf-16-le", (encodefunc_t) utf16le_encode},
{"utf-16", (encodefunc_t) utf16_encode},
{"utf-32-be", (encodefunc_t) utf32be_encode},
{"utf-32-le", (encodefunc_t) utf32le_encode},
{"utf-32", (encodefunc_t) utf32_encode},
{NULL, NULL}
};
static int
textiowrapper_init(textio *self, PyObject *args, PyObject *kwds)
{
char *kwlist[] = {"buffer", "encoding", "errors",
"newline", "line_buffering",
NULL};
PyObject *buffer, *raw;
char *encoding = NULL;
char *errors = NULL;
char *newline = NULL;
int line_buffering = 0;
PyObject *res;
int r;
self->ok = 0;
self->detached = 0;
if (!PyArg_ParseTupleAndKeywords(args, kwds, "O|zzzi:fileio",
kwlist, &buffer, &encoding, &errors,
&newline, &line_buffering))
return -1;
if (newline && newline[0] != '\0'
&& !(newline[0] == '\n' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\n' && newline[2] == '\0')) {
PyErr_Format(PyExc_ValueError,
"illegal newline value: %s", newline);
return -1;
}
Py_CLEAR(self->buffer);
Py_CLEAR(self->encoding);
Py_CLEAR(self->encoder);
Py_CLEAR(self->decoder);
Py_CLEAR(self->readnl);
Py_CLEAR(self->decoded_chars);
Py_CLEAR(self->pending_bytes);
Py_CLEAR(self->snapshot);
Py_CLEAR(self->errors);
Py_CLEAR(self->raw);
self->decoded_chars_used = 0;
self->pending_bytes_count = 0;
self->encodefunc = NULL;
self->writenl = NULL;
if (encoding == NULL && self->encoding == NULL) {
if (_PyIO_locale_module == NULL) {
_PyIO_locale_module = PyImport_ImportModule("locale");
if (_PyIO_locale_module == NULL)
goto catch_ImportError;
else
goto use_locale;
}
else {
use_locale:
self->encoding = PyObject_CallMethod(
_PyIO_locale_module, "getpreferredencoding", NULL);
if (self->encoding == NULL) {
catch_ImportError:
/*
Importing locale can raise a ImportError because of
_functools, and locale.getpreferredencoding can raise a
ImportError if _locale is not available. These will happen
during module building.
*/
if (PyErr_ExceptionMatches(PyExc_ImportError)) {
PyErr_Clear();
self->encoding = PyString_FromString("ascii");
}
else
goto error;
}
else if (!PyString_Check(self->encoding))
Py_CLEAR(self->encoding);
}
}
if (self->encoding != NULL)
encoding = PyString_AsString(self->encoding);
else if (encoding != NULL) {
self->encoding = PyString_FromString(encoding);
if (self->encoding == NULL)
goto error;
}
else {
PyErr_SetString(PyExc_IOError,
"could not determine default encoding");
}
if (errors == NULL)
errors = "strict";
self->errors = PyBytes_FromString(errors);
if (self->errors == NULL)
goto error;
self->chunk_size = 8192;
self->readuniversal = (newline == NULL || newline[0] == '\0');
self->line_buffering = line_buffering;
self->readtranslate = (newline == NULL);
if (newline) {
self->readnl = PyString_FromString(newline);
if (self->readnl == NULL)
return -1;
}
self->writetranslate = (newline == NULL || newline[0] != '\0');
if (!self->readuniversal && self->writetranslate) {
self->writenl = PyString_AsString(self->readnl);
if (!strcmp(self->writenl, "\n"))
self->writenl = NULL;
}
#ifdef MS_WINDOWS
else
self->writenl = "\r\n";
#endif
/* Build the decoder object */
res = PyObject_CallMethod(buffer, "readable", NULL);
if (res == NULL)
goto error;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
goto error;
if (r == 1) {
self->decoder = PyCodec_IncrementalDecoder(
encoding, errors);
if (self->decoder == NULL)
goto error;
if (self->readuniversal) {
PyObject *incrementalDecoder = PyObject_CallFunction(
(PyObject *)&PyIncrementalNewlineDecoder_Type,
"Oi", self->decoder, (int)self->readtranslate);
if (incrementalDecoder == NULL)
goto error;
Py_CLEAR(self->decoder);
self->decoder = incrementalDecoder;
}
}
/* Build the encoder object */
res = PyObject_CallMethod(buffer, "writable", NULL);
if (res == NULL)
goto error;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
goto error;
if (r == 1) {
PyObject *ci;
self->encoder = PyCodec_IncrementalEncoder(
encoding, errors);
if (self->encoder == NULL)
goto error;
/* Get the normalized named of the codec */
ci = _PyCodec_Lookup(encoding);
if (ci == NULL)
goto error;
res = PyObject_GetAttrString(ci, "name");
Py_DECREF(ci);
if (res == NULL) {
if (PyErr_ExceptionMatches(PyExc_AttributeError))
PyErr_Clear();
else
goto error;
}
else if (PyString_Check(res)) {
encodefuncentry *e = encodefuncs;
while (e->name != NULL) {
if (!strcmp(PyString_AS_STRING(res), e->name)) {
self->encodefunc = e->encodefunc;
break;
}
e++;
}
}
Py_XDECREF(res);
}
self->buffer = buffer;
Py_INCREF(buffer);
if (Py_TYPE(buffer) == &PyBufferedReader_Type ||
Py_TYPE(buffer) == &PyBufferedWriter_Type ||
Py_TYPE(buffer) == &PyBufferedRandom_Type) {
raw = PyObject_GetAttrString(buffer, "raw");
/* Cache the raw FileIO object to speed up 'closed' checks */
if (raw == NULL) {
if (PyErr_ExceptionMatches(PyExc_AttributeError))
PyErr_Clear();
else
goto error;
}
else if (Py_TYPE(raw) == &PyFileIO_Type)
self->raw = raw;
else
Py_DECREF(raw);
}
res = PyObject_CallMethod(buffer, "seekable", NULL);
if (res == NULL)
goto error;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r < 0)
goto error;
self->seekable = self->telling = r;
self->encoding_start_of_stream = 0;
if (self->seekable && self->encoder) {
PyObject *cookieObj;
int cmp;
self->encoding_start_of_stream = 1;
cookieObj = PyObject_CallMethodObjArgs(buffer, _PyIO_str_tell, NULL);
if (cookieObj == NULL)
goto error;
cmp = PyObject_RichCompareBool(cookieObj, _PyIO_zero, Py_EQ);
Py_DECREF(cookieObj);
if (cmp < 0) {
goto error;
}
if (cmp == 0) {
self->encoding_start_of_stream = 0;
res = PyObject_CallMethodObjArgs(self->encoder, _PyIO_str_setstate,
_PyIO_zero, NULL);
if (res == NULL)
goto error;
Py_DECREF(res);
}
}
self->ok = 1;
return 0;
error:
return -1;
}
static int
_textiowrapper_clear(textio *self)
{
if (self->ok && _PyIOBase_finalize((PyObject *) self) < 0)
return -1;
self->ok = 0;
Py_CLEAR(self->buffer);
Py_CLEAR(self->encoding);
Py_CLEAR(self->encoder);
Py_CLEAR(self->decoder);
Py_CLEAR(self->readnl);
Py_CLEAR(self->decoded_chars);
Py_CLEAR(self->pending_bytes);
Py_CLEAR(self->snapshot);
Py_CLEAR(self->errors);
Py_CLEAR(self->raw);
return 0;
}
static void
textiowrapper_dealloc(textio *self)
{
if (_textiowrapper_clear(self) < 0)
return;
_PyObject_GC_UNTRACK(self);
if (self->weakreflist != NULL)
PyObject_ClearWeakRefs((PyObject *)self);
Py_CLEAR(self->dict);
Py_TYPE(self)->tp_free((PyObject *)self);
}
static int
textiowrapper_traverse(textio *self, visitproc visit, void *arg)
{
Py_VISIT(self->buffer);
Py_VISIT(self->encoding);
Py_VISIT(self->encoder);
Py_VISIT(self->decoder);
Py_VISIT(self->readnl);
Py_VISIT(self->decoded_chars);
Py_VISIT(self->pending_bytes);
Py_VISIT(self->snapshot);
Py_VISIT(self->errors);
Py_VISIT(self->raw);
Py_VISIT(self->dict);
return 0;
}
static int
textiowrapper_clear(textio *self)
{
if (_textiowrapper_clear(self) < 0)
return -1;
Py_CLEAR(self->dict);
return 0;
}
static PyObject *
textiowrapper_closed_get(textio *self, void *context);
/* This macro takes some shortcuts to make the common case faster. */
#define CHECK_CLOSED(self) \
do { \
int r; \
PyObject *_res; \
if (Py_TYPE(self) == &PyTextIOWrapper_Type) { \
if (self->raw != NULL) \
r = _PyFileIO_closed(self->raw); \
else { \
_res = textiowrapper_closed_get(self, NULL); \
if (_res == NULL) \
return NULL; \
r = PyObject_IsTrue(_res); \
Py_DECREF(_res); \
if (r < 0) \
return NULL; \
} \
if (r > 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on closed file."); \
return NULL; \
} \
} \
else if (_PyIOBase_check_closed((PyObject *)self, Py_True) == NULL) \
return NULL; \
} while (0)
#define CHECK_INITIALIZED(self) \
if (self->ok <= 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on uninitialized object"); \
return NULL; \
}
#define CHECK_ATTACHED(self) \
CHECK_INITIALIZED(self); \
if (self->detached) { \
PyErr_SetString(PyExc_ValueError, \
"underlying buffer has been detached"); \
return NULL; \
}
#define CHECK_ATTACHED_INT(self) \
if (self->ok <= 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on uninitialized object"); \
return -1; \
} else if (self->detached) { \
PyErr_SetString(PyExc_ValueError, \
"underlying buffer has been detached"); \
return -1; \
}
static PyObject *
textiowrapper_detach(textio *self)
{
PyObject *buffer, *res;
CHECK_ATTACHED(self);
res = PyObject_CallMethodObjArgs((PyObject *)self, _PyIO_str_flush, NULL);
if (res == NULL)
return NULL;
Py_DECREF(res);
buffer = self->buffer;
self->buffer = NULL;
self->detached = 1;
return buffer;
}
Py_LOCAL_INLINE(const Py_UNICODE *)
findchar(const Py_UNICODE *s, Py_ssize_t size, Py_UNICODE ch)
{
/* like wcschr, but doesn't stop at NULL characters */
while (size-- > 0) {
if (*s == ch)
return s;
s++;
}
return NULL;
}
/* Flush the internal write buffer. This doesn't explicitly flush the
underlying buffered object, though. */
static int
_textiowrapper_writeflush(textio *self)
{
PyObject *pending, *b, *ret;
if (self->pending_bytes == NULL)
return 0;
pending = self->pending_bytes;
Py_INCREF(pending);
self->pending_bytes_count = 0;
Py_CLEAR(self->pending_bytes);
b = _PyBytes_Join(_PyIO_empty_bytes, pending);
Py_DECREF(pending);
if (b == NULL)
return -1;
ret = NULL;
do {
ret = PyObject_CallMethodObjArgs(self->buffer,
_PyIO_str_write, b, NULL);
} while (ret == NULL && _PyIO_trap_eintr());
Py_DECREF(b);
if (ret == NULL)
return -1;
Py_DECREF(ret);
return 0;
}
static PyObject *
textiowrapper_write(textio *self, PyObject *args)
{
PyObject *ret;
PyObject *text; /* owned reference */
PyObject *b;
Py_ssize_t textlen;
int haslf = 0;
int needflush = 0;
CHECK_ATTACHED(self);
if (!PyArg_ParseTuple(args, "U:write", &text)) {
return NULL;
}
CHECK_CLOSED(self);
if (self->encoder == NULL) {
PyErr_SetString(PyExc_IOError, "not writable");
return NULL;
}
Py_INCREF(text);
textlen = PyUnicode_GetSize(text);
if ((self->writetranslate && self->writenl != NULL) || self->line_buffering)
if (findchar(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text), '\n'))
haslf = 1;
if (haslf && self->writetranslate && self->writenl != NULL) {
PyObject *newtext = PyObject_CallMethod(
text, "replace", "ss", "\n", self->writenl);
Py_DECREF(text);
if (newtext == NULL)
return NULL;
text = newtext;
}
if (self->line_buffering &&
(haslf ||
findchar(PyUnicode_AS_UNICODE(text),
PyUnicode_GET_SIZE(text), '\r')))
needflush = 1;
/* XXX What if we were just reading? */
if (self->encodefunc != NULL) {
b = (*self->encodefunc)((PyObject *) self, text);
self->encoding_start_of_stream = 0;
}
else
b = PyObject_CallMethodObjArgs(self->encoder,
_PyIO_str_encode, text, NULL);
Py_DECREF(text);
if (b == NULL)
return NULL;
if (self->pending_bytes == NULL) {
self->pending_bytes = PyList_New(0);
if (self->pending_bytes == NULL) {
Py_DECREF(b);
return NULL;
}
self->pending_bytes_count = 0;
}
if (PyList_Append(self->pending_bytes, b) < 0) {
Py_DECREF(b);
return NULL;
}
self->pending_bytes_count += PyBytes_GET_SIZE(b);
Py_DECREF(b);
if (self->pending_bytes_count > self->chunk_size || needflush) {
if (_textiowrapper_writeflush(self) < 0)
return NULL;
}
if (needflush) {
ret = PyObject_CallMethodObjArgs(self->buffer, _PyIO_str_flush, NULL);
if (ret == NULL)
return NULL;
Py_DECREF(ret);
}
Py_CLEAR(self->snapshot);
if (self->decoder) {
ret = PyObject_CallMethod(self->decoder, "reset", NULL);
if (ret == NULL)
return NULL;
Py_DECREF(ret);
}
return PyLong_FromSsize_t(textlen);
}
/* Steal a reference to chars and store it in the decoded_char buffer;
*/
static void
textiowrapper_set_decoded_chars(textio *self, PyObject *chars)
{
Py_CLEAR(self->decoded_chars);
self->decoded_chars = chars;
self->decoded_chars_used = 0;
}
static PyObject *
textiowrapper_get_decoded_chars(textio *self, Py_ssize_t n)
{
PyObject *chars;
Py_ssize_t avail;
if (self->decoded_chars == NULL)
return PyUnicode_FromStringAndSize(NULL, 0);
avail = (PyUnicode_GET_SIZE(self->decoded_chars)
- self->decoded_chars_used);
assert(avail >= 0);
if (n < 0 || n > avail)
n = avail;
if (self->decoded_chars_used > 0 || n < avail) {
chars = PyUnicode_FromUnicode(
PyUnicode_AS_UNICODE(self->decoded_chars)
+ self->decoded_chars_used, n);
if (chars == NULL)
return NULL;
}
else {
chars = self->decoded_chars;
Py_INCREF(chars);
}
self->decoded_chars_used += n;
return chars;
}
/* Read and decode the next chunk of data from the BufferedReader.
*/
static int
textiowrapper_read_chunk(textio *self)
{
PyObject *dec_buffer = NULL;
PyObject *dec_flags = NULL;
PyObject *input_chunk = NULL;
PyObject *decoded_chars, *chunk_size;
int eof;
/* The return value is True unless EOF was reached. The decoded string is
* placed in self._decoded_chars (replacing its previous value). The
* entire input chunk is sent to the decoder, though some of it may remain
* buffered in the decoder, yet to be converted.
*/
if (self->decoder == NULL) {
PyErr_SetString(PyExc_IOError, "not readable");
return -1;
}
if (self->telling) {
/* To prepare for tell(), we need to snapshot a point in the file
* where the decoder's input buffer is empty.
*/
PyObject *state = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_getstate, NULL);
if (state == NULL)
return -1;
/* Given this, we know there was a valid snapshot point
* len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
*/
if (PyArg_Parse(state, "(OO)", &dec_buffer, &dec_flags) < 0) {
Py_DECREF(state);
return -1;
}
Py_INCREF(dec_buffer);
Py_INCREF(dec_flags);
Py_DECREF(state);
}
/* Read a chunk, decode it, and put the result in self._decoded_chars. */
chunk_size = PyLong_FromSsize_t(self->chunk_size);
if (chunk_size == NULL)
goto fail;
input_chunk = PyObject_CallMethodObjArgs(self->buffer,
_PyIO_str_read1, chunk_size, NULL);
Py_DECREF(chunk_size);
if (input_chunk == NULL)
goto fail;
if (!PyBytes_Check(input_chunk)) {
PyErr_Format(PyExc_TypeError,
"underlying read1() should have returned a bytes object, "
"not '%.200s'", Py_TYPE(input_chunk)->tp_name);
goto fail;
}
eof = (PyBytes_Size(input_chunk) == 0);
if (Py_TYPE(self->decoder) == &PyIncrementalNewlineDecoder_Type) {
decoded_chars = _PyIncrementalNewlineDecoder_decode(
self->decoder, input_chunk, eof);
}
else {
decoded_chars = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_decode, input_chunk, eof ? Py_True : Py_False, NULL);
}
if (check_decoded(decoded_chars) < 0)
goto fail;
textiowrapper_set_decoded_chars(self, decoded_chars);
if (PyUnicode_GET_SIZE(decoded_chars) > 0)
eof = 0;
if (self->telling) {
/* At the snapshot point, len(dec_buffer) bytes before the read, the
* next input to be decoded is dec_buffer + input_chunk.
*/
PyObject *next_input = PyNumber_Add(dec_buffer, input_chunk);
if (next_input == NULL)
goto fail;
if (!PyBytes_Check(next_input)) {
PyErr_Format(PyExc_TypeError,
"decoder getstate() should have returned a bytes "
"object, not '%.200s'",
Py_TYPE(next_input)->tp_name);
Py_DECREF(next_input);
goto fail;
}
Py_DECREF(dec_buffer);
Py_CLEAR(self->snapshot);
self->snapshot = Py_BuildValue("NN", dec_flags, next_input);
}
Py_DECREF(input_chunk);
return (eof == 0);
fail:
Py_XDECREF(dec_buffer);
Py_XDECREF(dec_flags);
Py_XDECREF(input_chunk);
return -1;
}
static PyObject *
textiowrapper_read(textio *self, PyObject *args)
{
Py_ssize_t n = -1;
PyObject *result = NULL, *chunks = NULL;
CHECK_ATTACHED(self);
if (!PyArg_ParseTuple(args, "|O&:read", &_PyIO_ConvertSsize_t, &n))
return NULL;
CHECK_CLOSED(self);
if (self->decoder == NULL) {
PyErr_SetString(PyExc_IOError, "not readable");
return NULL;
}
if (_textiowrapper_writeflush(self) < 0)
return NULL;
if (n < 0) {
/* Read everything */
PyObject *bytes = PyObject_CallMethod(self->buffer, "read", NULL);
PyObject *decoded, *final;
if (bytes == NULL)
goto fail;
decoded = PyObject_CallMethodObjArgs(self->decoder, _PyIO_str_decode,
bytes, Py_True, NULL);
Py_DECREF(bytes);
if (check_decoded(decoded) < 0)
goto fail;
result = textiowrapper_get_decoded_chars(self, -1);
if (result == NULL) {
Py_DECREF(decoded);
return NULL;
}
final = PyUnicode_Concat(result, decoded);
Py_DECREF(result);
Py_DECREF(decoded);
if (final == NULL)
goto fail;
Py_CLEAR(self->snapshot);
return final;
}
else {
int res = 1;
Py_ssize_t remaining = n;
result = textiowrapper_get_decoded_chars(self, n);
if (result == NULL)
goto fail;
remaining -= PyUnicode_GET_SIZE(result);
/* Keep reading chunks until we have n characters to return */
while (remaining > 0) {
res = textiowrapper_read_chunk(self);
if (res < 0) {
/* NOTE: PyErr_SetFromErrno() calls PyErr_CheckSignals()
when EINTR occurs so we needn't do it ourselves. */
if (_PyIO_trap_eintr()) {
continue;
}
goto fail;
}
if (res == 0) /* EOF */
break;
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto fail;
}
if (PyList_Append(chunks, result) < 0)
goto fail;
Py_DECREF(result);
result = textiowrapper_get_decoded_chars(self, remaining);
if (result == NULL)
goto fail;
remaining -= PyUnicode_GET_SIZE(result);
}
if (chunks != NULL) {
if (result != NULL && PyList_Append(chunks, result) < 0)
goto fail;
Py_CLEAR(result);
result = PyUnicode_Join(_PyIO_empty_str, chunks);
if (result == NULL)
goto fail;
Py_CLEAR(chunks);
}
return result;
}
fail:
Py_XDECREF(result);
Py_XDECREF(chunks);
return NULL;
}
/* NOTE: `end` must point to the real end of the Py_UNICODE storage,
that is to the NUL character. Otherwise the function will produce
incorrect results. */
static Py_UNICODE *
find_control_char(Py_UNICODE *start, Py_UNICODE *end, Py_UNICODE ch)
{
Py_UNICODE *s = start;
for (;;) {
while (*s > ch)
s++;
if (*s == ch)
return s;
if (s == end)
return NULL;
s++;
}
}
Py_ssize_t
_PyIO_find_line_ending(
int translated, int universal, PyObject *readnl,
Py_UNICODE *start, Py_UNICODE *end, Py_ssize_t *consumed)
{
Py_ssize_t len = end - start;
if (translated) {
/* Newlines are already translated, only search for \n */
Py_UNICODE *pos = find_control_char(start, end, '\n');
if (pos != NULL)
return pos - start + 1;
else {
*consumed = len;
return -1;
}
}
else if (universal) {
/* Universal newline search. Find any of \r, \r\n, \n
* The decoder ensures that \r\n are not split in two pieces
*/
Py_UNICODE *s = start;
for (;;) {
Py_UNICODE ch;
/* Fast path for non-control chars. The loop always ends
since the Py_UNICODE storage is NUL-terminated. */
while (*s > '\r')
s++;
if (s >= end) {
*consumed = len;
return -1;
}
ch = *s++;
if (ch == '\n')
return s - start;
if (ch == '\r') {
if (*s == '\n')
return s - start + 1;
else
return s - start;
}
}
}
else {
/* Non-universal mode. */
Py_ssize_t readnl_len = PyString_GET_SIZE(readnl);
unsigned char *nl = (unsigned char *) PyString_AS_STRING(readnl);
if (readnl_len == 1) {
Py_UNICODE *pos = find_control_char(start, end, nl[0]);
if (pos != NULL)
return pos - start + 1;
*consumed = len;
return -1;
}
else {
Py_UNICODE *s = start;
Py_UNICODE *e = end - readnl_len + 1;
Py_UNICODE *pos;
if (e < s)
e = s;
while (s < e) {
Py_ssize_t i;
Py_UNICODE *pos = find_control_char(s, end, nl[0]);
if (pos == NULL || pos >= e)
break;
for (i = 1; i < readnl_len; i++) {
if (pos[i] != nl[i])
break;
}
if (i == readnl_len)
return pos - start + readnl_len;
s = pos + 1;
}
pos = find_control_char(e, end, nl[0]);
if (pos == NULL)
*consumed = len;
else
*consumed = pos - start;
return -1;
}
}
}
static PyObject *
_textiowrapper_readline(textio *self, Py_ssize_t limit)
{
PyObject *line = NULL, *chunks = NULL, *remaining = NULL;
Py_ssize_t start, endpos, chunked, offset_to_buffer;
int res;
CHECK_CLOSED(self);
if (_textiowrapper_writeflush(self) < 0)
return NULL;
chunked = 0;
while (1) {
Py_UNICODE *ptr;
Py_ssize_t line_len;
Py_ssize_t consumed = 0;
/* First, get some data if necessary */
res = 1;
while (!self->decoded_chars ||
!PyUnicode_GET_SIZE(self->decoded_chars)) {
res = textiowrapper_read_chunk(self);
if (res < 0) {
/* NOTE: PyErr_SetFromErrno() calls PyErr_CheckSignals()
when EINTR occurs so we needn't do it ourselves. */
if (_PyIO_trap_eintr()) {
continue;
}
goto error;
}
if (res == 0)
break;
}
if (res == 0) {
/* end of file */
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
start = endpos = offset_to_buffer = 0;
break;
}
if (remaining == NULL) {
line = self->decoded_chars;
start = self->decoded_chars_used;
offset_to_buffer = 0;
Py_INCREF(line);
}
else {
assert(self->decoded_chars_used == 0);
line = PyUnicode_Concat(remaining, self->decoded_chars);
start = 0;
offset_to_buffer = PyUnicode_GET_SIZE(remaining);
Py_CLEAR(remaining);
if (line == NULL)
goto error;
}
ptr = PyUnicode_AS_UNICODE(line);
line_len = PyUnicode_GET_SIZE(line);
endpos = _PyIO_find_line_ending(
self->readtranslate, self->readuniversal, self->readnl,
ptr + start, ptr + line_len, &consumed);
if (endpos >= 0) {
endpos += start;
if (limit >= 0 && (endpos - start) + chunked >= limit)
endpos = start + limit - chunked;
break;
}
/* We can put aside up to `endpos` */
endpos = consumed + start;
if (limit >= 0 && (endpos - start) + chunked >= limit) {
/* Didn't find line ending, but reached length limit */
endpos = start + limit - chunked;
break;
}
if (endpos > start) {
/* No line ending seen yet - put aside current data */
PyObject *s;
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto error;
}
s = PyUnicode_FromUnicode(ptr + start, endpos - start);
if (s == NULL)
goto error;
if (PyList_Append(chunks, s) < 0) {
Py_DECREF(s);
goto error;
}
chunked += PyUnicode_GET_SIZE(s);
Py_DECREF(s);
}
/* There may be some remaining bytes we'll have to prepend to the
next chunk of data */
if (endpos < line_len) {
remaining = PyUnicode_FromUnicode(
ptr + endpos, line_len - endpos);
if (remaining == NULL)
goto error;
}
Py_CLEAR(line);
/* We have consumed the buffer */
textiowrapper_set_decoded_chars(self, NULL);
}
if (line != NULL) {
/* Our line ends in the current buffer */
self->decoded_chars_used = endpos - offset_to_buffer;
if (start > 0 || endpos < PyUnicode_GET_SIZE(line)) {
if (start == 0 && Py_REFCNT(line) == 1) {
if (PyUnicode_Resize(&line, endpos) < 0)
goto error;
}
else {
PyObject *s = PyUnicode_FromUnicode(
PyUnicode_AS_UNICODE(line) + start, endpos - start);
Py_CLEAR(line);
if (s == NULL)
goto error;
line = s;
}
}
}
if (remaining != NULL) {
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto error;
}
if (PyList_Append(chunks, remaining) < 0)
goto error;
Py_CLEAR(remaining);
}
if (chunks != NULL) {
if (line != NULL && PyList_Append(chunks, line) < 0)
goto error;
Py_CLEAR(line);
line = PyUnicode_Join(_PyIO_empty_str, chunks);
if (line == NULL)
goto error;
Py_DECREF(chunks);
}
if (line == NULL)
line = PyUnicode_FromStringAndSize(NULL, 0);
return line;
error:
Py_XDECREF(chunks);
Py_XDECREF(remaining);
Py_XDECREF(line);
return NULL;
}
static PyObject *
textiowrapper_readline(textio *self, PyObject *args)
{
PyObject *limitobj = NULL;
Py_ssize_t limit = -1;
CHECK_ATTACHED(self);
if (!PyArg_ParseTuple(args, "|O:readline", &limitobj)) {
return NULL;
}
if (limitobj) {
if (!PyNumber_Check(limitobj)) {
PyErr_Format(PyExc_TypeError,
"integer argument expected, got '%.200s'",
Py_TYPE(limitobj)->tp_name);
return NULL;
}
limit = PyNumber_AsSsize_t(limitobj, PyExc_OverflowError);
if (limit == -1 && PyErr_Occurred())
return NULL;
}
return _textiowrapper_readline(self, limit);
}
/* Seek and Tell */
typedef struct {
Py_off_t start_pos;
int dec_flags;
int bytes_to_feed;
int chars_to_skip;
char need_eof;
} cookie_type;
/*
To speed up cookie packing/unpacking, we store the fields in a temporary
string and call _PyLong_FromByteArray() or _PyLong_AsByteArray (resp.).
The following macros define at which offsets in the intermediary byte
string the various CookieStruct fields will be stored.
*/
#define COOKIE_BUF_LEN (sizeof(Py_off_t) + 3 * sizeof(int) + sizeof(char))
#if defined(WORDS_BIGENDIAN)
# define IS_LITTLE_ENDIAN 0
/* We want the least significant byte of start_pos to also be the least
significant byte of the cookie, which means that in big-endian mode we
must copy the fields in reverse order. */
# define OFF_START_POS (sizeof(char) + 3 * sizeof(int))
# define OFF_DEC_FLAGS (sizeof(char) + 2 * sizeof(int))
# define OFF_BYTES_TO_FEED (sizeof(char) + sizeof(int))
# define OFF_CHARS_TO_SKIP (sizeof(char))
# define OFF_NEED_EOF 0
#else
# define IS_LITTLE_ENDIAN 1
/* Little-endian mode: the least significant byte of start_pos will
naturally end up the least significant byte of the cookie. */
# define OFF_START_POS 0
# define OFF_DEC_FLAGS (sizeof(Py_off_t))
# define OFF_BYTES_TO_FEED (sizeof(Py_off_t) + sizeof(int))
# define OFF_CHARS_TO_SKIP (sizeof(Py_off_t) + 2 * sizeof(int))
# define OFF_NEED_EOF (sizeof(Py_off_t) + 3 * sizeof(int))
#endif
static int
textiowrapper_parse_cookie(cookie_type *cookie, PyObject *cookieObj)
{
unsigned char buffer[COOKIE_BUF_LEN];
PyLongObject *cookieLong = (PyLongObject *)PyNumber_Long(cookieObj);
if (cookieLong == NULL)
return -1;
if (_PyLong_AsByteArray(cookieLong, buffer, sizeof(buffer),
IS_LITTLE_ENDIAN, 0) < 0) {
Py_DECREF(cookieLong);
return -1;
}
Py_DECREF(cookieLong);
memcpy(&cookie->start_pos, buffer + OFF_START_POS, sizeof(cookie->start_pos));
memcpy(&cookie->dec_flags, buffer + OFF_DEC_FLAGS, sizeof(cookie->dec_flags));
memcpy(&cookie->bytes_to_feed, buffer + OFF_BYTES_TO_FEED, sizeof(cookie->bytes_to_feed));
memcpy(&cookie->chars_to_skip, buffer + OFF_CHARS_TO_SKIP, sizeof(cookie->chars_to_skip));
memcpy(&cookie->need_eof, buffer + OFF_NEED_EOF, sizeof(cookie->need_eof));
return 0;
}
static PyObject *
textiowrapper_build_cookie(cookie_type *cookie)
{
unsigned char buffer[COOKIE_BUF_LEN];
memcpy(buffer + OFF_START_POS, &cookie->start_pos, sizeof(cookie->start_pos));
memcpy(buffer + OFF_DEC_FLAGS, &cookie->dec_flags, sizeof(cookie->dec_flags));
memcpy(buffer + OFF_BYTES_TO_FEED, &cookie->bytes_to_feed, sizeof(cookie->bytes_to_feed));
memcpy(buffer + OFF_CHARS_TO_SKIP, &cookie->chars_to_skip, sizeof(cookie->chars_to_skip));
memcpy(buffer + OFF_NEED_EOF, &cookie->need_eof, sizeof(cookie->need_eof));
return _PyLong_FromByteArray(buffer, sizeof(buffer), IS_LITTLE_ENDIAN, 0);
}
#undef IS_LITTLE_ENDIAN
static int
_textiowrapper_decoder_setstate(textio *self, cookie_type *cookie)
{
PyObject *res;
/* When seeking to the start of the stream, we call decoder.reset()
rather than decoder.getstate().
This is for a few decoders such as utf-16 for which the state value
at start is not (b"", 0) but e.g. (b"", 2) (meaning, in the case of
utf-16, that we are expecting a BOM).
*/
if (cookie->start_pos == 0 && cookie->dec_flags == 0)
res = PyObject_CallMethodObjArgs(self->decoder, _PyIO_str_reset, NULL);
else
res = PyObject_CallMethod(self->decoder, "setstate",
"((si))", "", cookie->dec_flags);
if (res == NULL)
return -1;
Py_DECREF(res);
return 0;
}
static int
_textiowrapper_encoder_setstate(textio *self, cookie_type *cookie)
{
PyObject *res;
/* Same as _textiowrapper_decoder_setstate() above. */
if (cookie->start_pos == 0 && cookie->dec_flags == 0) {
res = PyObject_CallMethodObjArgs(self->encoder, _PyIO_str_reset, NULL);
self->encoding_start_of_stream = 1;
}
else {
res = PyObject_CallMethodObjArgs(self->encoder, _PyIO_str_setstate,
_PyIO_zero, NULL);
self->encoding_start_of_stream = 0;
}
if (res == NULL)
return -1;
Py_DECREF(res);
return 0;
}
static PyObject *
textiowrapper_seek(textio *self, PyObject *args)
{
PyObject *cookieObj, *posobj;
cookie_type cookie;
int whence = 0;
PyObject *res;
int cmp;
CHECK_ATTACHED(self);
if (!PyArg_ParseTuple(args, "O|i:seek", &cookieObj, &whence))
return NULL;
CHECK_CLOSED(self);
Py_INCREF(cookieObj);
if (!self->seekable) {
PyErr_SetString(PyExc_IOError,
"underlying stream is not seekable");
goto fail;
}
if (whence == 1) {
/* seek relative to current position */
cmp = PyObject_RichCompareBool(cookieObj, _PyIO_zero, Py_EQ);
if (cmp < 0)
goto fail;
if (cmp == 0) {
PyErr_SetString(PyExc_IOError,
"can't do nonzero cur-relative seeks");
goto fail;
}
/* Seeking to the current position should attempt to
* sync the underlying buffer with the current position.
*/
Py_DECREF(cookieObj);
cookieObj = PyObject_CallMethod((PyObject *)self, "tell", NULL);
if (cookieObj == NULL)
goto fail;
}
else if (whence == 2) {
/* seek relative to end of file */
cmp = PyObject_RichCompareBool(cookieObj, _PyIO_zero, Py_EQ);
if (cmp < 0)
goto fail;
if (cmp == 0) {
PyErr_SetString(PyExc_IOError,
"can't do nonzero end-relative seeks");
goto fail;
}
res = PyObject_CallMethod((PyObject *)self, "flush", NULL);
if (res == NULL)
goto fail;
Py_DECREF(res);
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
if (self->decoder) {
res = PyObject_CallMethod(self->decoder, "reset", NULL);
if (res == NULL)
goto fail;
Py_DECREF(res);
}
res = PyObject_CallMethod(self->buffer, "seek", "ii", 0, 2);
Py_XDECREF(cookieObj);
return res;
}
else if (whence != 0) {
PyErr_Format(PyExc_ValueError,
"invalid whence (%d, should be 0, 1 or 2)", whence);
goto fail;
}
cmp = PyObject_RichCompareBool(cookieObj, _PyIO_zero, Py_LT);
if (cmp < 0)
goto fail;
if (cmp == 1) {
PyObject *repr = PyObject_Repr(cookieObj);
if (repr != NULL) {
PyErr_Format(PyExc_ValueError,
"negative seek position %s",
PyString_AS_STRING(repr));
Py_DECREF(repr);
}
goto fail;
}
res = PyObject_CallMethodObjArgs((PyObject *)self, _PyIO_str_flush, NULL);
if (res == NULL)
goto fail;
Py_DECREF(res);
/* The strategy of seek() is to go back to the safe start point
* and replay the effect of read(chars_to_skip) from there.
*/
if (textiowrapper_parse_cookie(&cookie, cookieObj) < 0)
goto fail;
/* Seek back to the safe start point. */
posobj = PyLong_FromOff_t(cookie.start_pos);
if (posobj == NULL)
goto fail;
res = PyObject_CallMethodObjArgs(self->buffer,
_PyIO_str_seek, posobj, NULL);
Py_DECREF(posobj);
if (res == NULL)
goto fail;
Py_DECREF(res);
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
/* Restore the decoder to its state from the safe start point. */
if (self->decoder) {
if (_textiowrapper_decoder_setstate(self, &cookie) < 0)
goto fail;
}
if (cookie.chars_to_skip) {
/* Just like _read_chunk, feed the decoder and save a snapshot. */
PyObject *input_chunk = PyObject_CallMethod(
self->buffer, "read", "i", cookie.bytes_to_feed);
PyObject *decoded;
if (input_chunk == NULL)
goto fail;
if (!PyBytes_Check(input_chunk)) {
PyErr_Format(PyExc_TypeError,
"underlying read() should have returned a bytes "
"object, not '%.200s'",
Py_TYPE(input_chunk)->tp_name);
Py_DECREF(input_chunk);
goto fail;
}
self->snapshot = Py_BuildValue("iN", cookie.dec_flags, input_chunk);
if (self->snapshot == NULL) {
Py_DECREF(input_chunk);
goto fail;
}
decoded = PyObject_CallMethod(self->decoder, "decode",
"Oi", input_chunk, (int)cookie.need_eof);
if (check_decoded(decoded) < 0)
goto fail;
textiowrapper_set_decoded_chars(self, decoded);
/* Skip chars_to_skip of the decoded characters. */
if (PyUnicode_GetSize(self->decoded_chars) < cookie.chars_to_skip) {
PyErr_SetString(PyExc_IOError, "can't restore logical file position");
goto fail;
}
self->decoded_chars_used = cookie.chars_to_skip;
}
else {
self->snapshot = Py_BuildValue("is", cookie.dec_flags, "");
if (self->snapshot == NULL)
goto fail;
}
/* Finally, reset the encoder (merely useful for proper BOM handling) */
if (self->encoder) {
if (_textiowrapper_encoder_setstate(self, &cookie) < 0)
goto fail;
}
return cookieObj;
fail:
Py_XDECREF(cookieObj);
return NULL;
}
static PyObject *
textiowrapper_tell(textio *self, PyObject *args)
{
PyObject *res;
PyObject *posobj = NULL;
cookie_type cookie = {0,0,0,0,0};
PyObject *next_input;
Py_ssize_t chars_to_skip, chars_decoded;
PyObject *saved_state = NULL;
char *input, *input_end;
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
if (!self->seekable) {
PyErr_SetString(PyExc_IOError,
"underlying stream is not seekable");
goto fail;
}
if (!self->telling) {
PyErr_SetString(PyExc_IOError,
"telling position disabled by next() call");
goto fail;
}
if (_textiowrapper_writeflush(self) < 0)
return NULL;
res = PyObject_CallMethod((PyObject *)self, "flush", NULL);
if (res == NULL)
goto fail;
Py_DECREF(res);
posobj = PyObject_CallMethod(self->buffer, "tell", NULL);
if (posobj == NULL)
goto fail;
if (self->decoder == NULL || self->snapshot == NULL) {
assert (self->decoded_chars == NULL || PyUnicode_GetSize(self->decoded_chars) == 0);
return posobj;
}
#if defined(HAVE_LARGEFILE_SUPPORT)
cookie.start_pos = PyLong_AsLongLong(posobj);
#else
cookie.start_pos = PyLong_AsLong(posobj);
#endif
if (PyErr_Occurred())
goto fail;
/* Skip backward to the snapshot point (see _read_chunk). */
if (!PyArg_Parse(self->snapshot, "(iO)", &cookie.dec_flags, &next_input))
goto fail;
assert (PyBytes_Check(next_input));
cookie.start_pos -= PyBytes_GET_SIZE(next_input);
/* How many decoded characters have been used up since the snapshot? */
if (self->decoded_chars_used == 0) {
/* We haven't moved from the snapshot point. */
Py_DECREF(posobj);
return textiowrapper_build_cookie(&cookie);
}
chars_to_skip = self->decoded_chars_used;
/* Starting from the snapshot position, we will walk the decoder
* forward until it gives us enough decoded characters.
*/
saved_state = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_getstate, NULL);
if (saved_state == NULL)
goto fail;
/* Note our initial start point. */
if (_textiowrapper_decoder_setstate(self, &cookie) < 0)
goto fail;
/* Feed the decoder one byte at a time. As we go, note the
* nearest "safe start point" before the current location
* (a point where the decoder has nothing buffered, so seek()
* can safely start from there and advance to this location).
*/
chars_decoded = 0;
input = PyBytes_AS_STRING(next_input);
input_end = input + PyBytes_GET_SIZE(next_input);
while (input < input_end) {
PyObject *state;
char *dec_buffer;
Py_ssize_t dec_buffer_len;
int dec_flags;
PyObject *decoded = PyObject_CallMethod(
self->decoder, "decode", "s#", input, (Py_ssize_t)1);
if (check_decoded(decoded) < 0)
goto fail;
chars_decoded += PyUnicode_GET_SIZE(decoded);
Py_DECREF(decoded);
cookie.bytes_to_feed += 1;
state = PyObject_CallMethodObjArgs(self->decoder,
_PyIO_str_getstate, NULL);
if (state == NULL)
goto fail;
if (!PyArg_Parse(state, "(s#i)", &dec_buffer, &dec_buffer_len, &dec_flags)) {
Py_DECREF(state);
goto fail;
}
Py_DECREF(state);
if (dec_buffer_len == 0 && chars_decoded <= chars_to_skip) {
/* Decoder buffer is empty, so this is a safe start point. */
cookie.start_pos += cookie.bytes_to_feed;
chars_to_skip -= chars_decoded;
cookie.dec_flags = dec_flags;
cookie.bytes_to_feed = 0;
chars_decoded = 0;
}
if (chars_decoded >= chars_to_skip)
break;
input++;
}
if (input == input_end) {
/* We didn't get enough decoded data; signal EOF to get more. */
PyObject *decoded = PyObject_CallMethod(
self->decoder, "decode", "si", "", /* final = */ 1);
if (check_decoded(decoded) < 0)
goto fail;
chars_decoded += PyUnicode_GET_SIZE(decoded);
Py_DECREF(decoded);
cookie.need_eof = 1;
if (chars_decoded < chars_to_skip) {
PyErr_SetString(PyExc_IOError,
"can't reconstruct logical file position");
goto fail;
}
}
/* finally */
Py_XDECREF(posobj);
res = PyObject_CallMethod(self->decoder, "setstate", "(O)", saved_state);
Py_DECREF(saved_state);
if (res == NULL)
return NULL;
Py_DECREF(res);
/* The returned cookie corresponds to the last safe start point. */
cookie.chars_to_skip = Py_SAFE_DOWNCAST(chars_to_skip, Py_ssize_t, int);
return textiowrapper_build_cookie(&cookie);
fail:
Py_XDECREF(posobj);
if (saved_state) {
PyObject *type, *value, *traceback;
PyErr_Fetch(&type, &value, &traceback);
res = PyObject_CallMethod(self->decoder, "setstate", "(O)", saved_state);
_PyErr_ReplaceException(type, value, traceback);
Py_DECREF(saved_state);
Py_XDECREF(res);
}
return NULL;
}
static PyObject *
textiowrapper_truncate(textio *self, PyObject *args)
{
PyObject *pos = Py_None;
PyObject *res;
CHECK_ATTACHED(self)
if (!PyArg_ParseTuple(args, "|O:truncate", &pos)) {
return NULL;
}
res = PyObject_CallMethodObjArgs((PyObject *) self, _PyIO_str_flush, NULL);
if (res == NULL)
return NULL;
Py_DECREF(res);
return PyObject_CallMethodObjArgs(self->buffer, _PyIO_str_truncate, pos, NULL);
}
static PyObject *
textiowrapper_repr(textio *self)
{
PyObject *nameobj, *res;
PyObject *namerepr = NULL, *encrepr = NULL;
CHECK_INITIALIZED(self);
nameobj = PyObject_GetAttrString((PyObject *) self, "name");
if (nameobj == NULL) {
if (PyErr_ExceptionMatches(PyExc_Exception))
PyErr_Clear();
else
goto error;
encrepr = PyObject_Repr(self->encoding);
res = PyString_FromFormat("<_io.TextIOWrapper encoding=%s>",
PyString_AS_STRING(encrepr));
}
else {
encrepr = PyObject_Repr(self->encoding);
namerepr = PyObject_Repr(nameobj);
res = PyString_FromFormat("<_io.TextIOWrapper name=%s encoding=%s>",
PyString_AS_STRING(namerepr),
PyString_AS_STRING(encrepr));
Py_DECREF(nameobj);
}
Py_XDECREF(namerepr);
Py_XDECREF(encrepr);
return res;
error:
Py_XDECREF(namerepr);
Py_XDECREF(encrepr);
return NULL;
}
/* Inquiries */
static PyObject *
textiowrapper_fileno(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
return PyObject_CallMethod(self->buffer, "fileno", NULL);
}
static PyObject *
textiowrapper_seekable(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
return PyObject_CallMethod(self->buffer, "seekable", NULL);
}
static PyObject *
textiowrapper_readable(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
return PyObject_CallMethod(self->buffer, "readable", NULL);
}
static PyObject *
textiowrapper_writable(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
return PyObject_CallMethod(self->buffer, "writable", NULL);
}
static PyObject *
textiowrapper_isatty(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
return PyObject_CallMethod(self->buffer, "isatty", NULL);
}
static PyObject *
textiowrapper_flush(textio *self, PyObject *args)
{
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
self->telling = self->seekable;
if (_textiowrapper_writeflush(self) < 0)
return NULL;
return PyObject_CallMethod(self->buffer, "flush", NULL);
}
static PyObject *
textiowrapper_close(textio *self, PyObject *args)
{
PyObject *res;
int r;
CHECK_ATTACHED(self);
res = textiowrapper_closed_get(self, NULL);
if (res == NULL)
return NULL;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r < 0)
return NULL;
if (r > 0) {
Py_RETURN_NONE; /* stream already closed */
}
else {
PyObject *exc = NULL, *val, *tb;
res = PyObject_CallMethod((PyObject *)self, "flush", NULL);
if (res == NULL)
PyErr_Fetch(&exc, &val, &tb);
else
Py_DECREF(res);
res = PyObject_CallMethod(self->buffer, "close", NULL);
if (exc != NULL) {
_PyErr_ReplaceException(exc, val, tb);
Py_CLEAR(res);
}
return res;
}
}
static PyObject *
textiowrapper_iternext(textio *self)
{
PyObject *line;
CHECK_ATTACHED(self);
self->telling = 0;
if (Py_TYPE(self) == &PyTextIOWrapper_Type) {
/* Skip method call overhead for speed */
line = _textiowrapper_readline(self, -1);
}
else {
line = PyObject_CallMethodObjArgs((PyObject *)self,
_PyIO_str_readline, NULL);
if (line && !PyUnicode_Check(line)) {
PyErr_Format(PyExc_IOError,
"readline() should have returned an str object, "
"not '%.200s'", Py_TYPE(line)->tp_name);
Py_DECREF(line);
return NULL;
}
}
if (line == NULL)
return NULL;
if (PyUnicode_GET_SIZE(line) == 0) {
/* Reached EOF or would have blocked */
Py_DECREF(line);
Py_CLEAR(self->snapshot);
self->telling = self->seekable;
return NULL;
}
return line;
}
static PyObject *
textiowrapper_name_get(textio *self, void *context)
{
CHECK_ATTACHED(self);
return PyObject_GetAttrString(self->buffer, "name");
}
static PyObject *
textiowrapper_closed_get(textio *self, void *context)
{
CHECK_ATTACHED(self);
return PyObject_GetAttr(self->buffer, _PyIO_str_closed);
}
static PyObject *
textiowrapper_newlines_get(textio *self, void *context)
{
PyObject *res;
CHECK_ATTACHED(self);
if (self->decoder == NULL)
Py_RETURN_NONE;
res = PyObject_GetAttr(self->decoder, _PyIO_str_newlines);
if (res == NULL) {
if (PyErr_ExceptionMatches(PyExc_AttributeError)) {
PyErr_Clear();
Py_RETURN_NONE;
}
else {
return NULL;
}
}
return res;
}
static PyObject *
textiowrapper_errors_get(textio *self, void *context)
{
CHECK_INITIALIZED(self);
Py_INCREF(self->errors);
return self->errors;
}
static PyObject *
textiowrapper_chunk_size_get(textio *self, void *context)
{
CHECK_ATTACHED(self);
return PyLong_FromSsize_t(self->chunk_size);
}
static int
textiowrapper_chunk_size_set(textio *self, PyObject *arg, void *context)
{
Py_ssize_t n;
CHECK_ATTACHED_INT(self);
n = PyNumber_AsSsize_t(arg, PyExc_TypeError);
if (n == -1 && PyErr_Occurred())
return -1;
if (n <= 0) {
PyErr_SetString(PyExc_ValueError,
"a strictly positive integer is required");
return -1;
}
self->chunk_size = n;
return 0;
}
static PyMethodDef textiowrapper_methods[] = {
{"detach", (PyCFunction)textiowrapper_detach, METH_NOARGS},
{"write", (PyCFunction)textiowrapper_write, METH_VARARGS},
{"read", (PyCFunction)textiowrapper_read, METH_VARARGS},
{"readline", (PyCFunction)textiowrapper_readline, METH_VARARGS},
{"flush", (PyCFunction)textiowrapper_flush, METH_NOARGS},
{"close", (PyCFunction)textiowrapper_close, METH_NOARGS},
{"fileno", (PyCFunction)textiowrapper_fileno, METH_NOARGS},
{"seekable", (PyCFunction)textiowrapper_seekable, METH_NOARGS},
{"readable", (PyCFunction)textiowrapper_readable, METH_NOARGS},
{"writable", (PyCFunction)textiowrapper_writable, METH_NOARGS},
{"isatty", (PyCFunction)textiowrapper_isatty, METH_NOARGS},
{"seek", (PyCFunction)textiowrapper_seek, METH_VARARGS},
{"tell", (PyCFunction)textiowrapper_tell, METH_NOARGS},
{"truncate", (PyCFunction)textiowrapper_truncate, METH_VARARGS},
{NULL, NULL}
};
static PyMemberDef textiowrapper_members[] = {
{"encoding", T_OBJECT, offsetof(textio, encoding), READONLY},
{"buffer", T_OBJECT, offsetof(textio, buffer), READONLY},
{"line_buffering", T_BOOL, offsetof(textio, line_buffering), READONLY},
{NULL}
};
static PyGetSetDef textiowrapper_getset[] = {
{"name", (getter)textiowrapper_name_get, NULL, NULL},
{"closed", (getter)textiowrapper_closed_get, NULL, NULL},
/* {"mode", (getter)TextIOWrapper_mode_get, NULL, NULL},
*/
{"newlines", (getter)textiowrapper_newlines_get, NULL, NULL},
{"errors", (getter)textiowrapper_errors_get, NULL, NULL},
{"_CHUNK_SIZE", (getter)textiowrapper_chunk_size_get,
(setter)textiowrapper_chunk_size_set, NULL},
{NULL}
};
PyTypeObject PyTextIOWrapper_Type = {
PyVarObject_HEAD_INIT(NULL, 0)
"_io.TextIOWrapper", /*tp_name*/
sizeof(textio), /*tp_basicsize*/
0, /*tp_itemsize*/
(destructor)textiowrapper_dealloc, /*tp_dealloc*/
0, /*tp_print*/
0, /*tp_getattr*/
0, /*tps_etattr*/
0, /*tp_compare */
(reprfunc)textiowrapper_repr,/*tp_repr*/
0, /*tp_as_number*/
0, /*tp_as_sequence*/
0, /*tp_as_mapping*/
0, /*tp_hash */
0, /*tp_call*/
0, /*tp_str*/
0, /*tp_getattro*/
0, /*tp_setattro*/
0, /*tp_as_buffer*/
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE
| Py_TPFLAGS_HAVE_GC, /*tp_flags*/
textiowrapper_doc, /* tp_doc */
(traverseproc)textiowrapper_traverse, /* tp_traverse */
(inquiry)textiowrapper_clear, /* tp_clear */
0, /* tp_richcompare */
offsetof(textio, weakreflist), /*tp_weaklistoffset*/
0, /* tp_iter */
(iternextfunc)textiowrapper_iternext, /* tp_iternext */
textiowrapper_methods, /* tp_methods */
textiowrapper_members, /* tp_members */
textiowrapper_getset, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
offsetof(textio, dict), /*tp_dictoffset*/
(initproc)textiowrapper_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
|