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
|
"""
The io module provides the Python interfaces to stream handling. The
builtin open function is defined in this module.
At the top of the I/O hierarchy is the abstract base class IOBase. It
defines the basic interface to a stream. Note, however, that there is no
separation between reading and writing to streams; implementations are
allowed to throw an IOError if they do not support a given operation.
Extending IOBase is RawIOBase which deals simply with the reading and
writing of raw bytes to a stream. FileIO subclasses RawIOBase to provide
an interface to OS files.
BufferedIOBase deals with buffering on a raw byte stream (RawIOBase). Its
subclasses, BufferedWriter, BufferedReader, and BufferedRWPair buffer
streams that are readable, writable, and both respectively.
BufferedRandom provides a buffered interface to random access
streams. BytesIO is a simple stream of in-memory bytes.
Another IOBase subclass, TextIOBase, deals with the encoding and decoding
of streams into text. TextIOWrapper, which extends it, is a buffered text
interface to a buffered raw stream (`BufferedIOBase`). Finally, StringIO
is a in-memory stream for text.
Argument names are not part of the specification, and only the arguments
of open() are intended to be used as keyword arguments.
data:
DEFAULT_BUFFER_SIZE
An int containing the default buffer size used by the module's buffered
I/O classes. open() uses the file's blksize (as obtained by os.stat) if
possible.
"""
# New I/O library conforming to PEP 3116.
# This is a prototype; hopefully eventually some of this will be
# reimplemented in C.
# XXX edge cases when switching between reading/writing
# XXX need to support 1 meaning line-buffered
# XXX whenever an argument is None, use the default value
# XXX read/write ops should check readable/writable
# XXX buffered readinto should work with arbitrary buffer objects
# XXX use incremental encoder for text output, at least for UTF-16 and UTF-8-SIG
# XXX check writable, readable and seekable in appropriate places
from __future__ import print_function
from __future__ import unicode_literals
__author__ = ("Guido van Rossum <guido@python.org>, "
"Mike Verdone <mike.verdone@gmail.com>, "
"Mark Russell <mark.russell@zen.co.uk>")
__all__ = ["BlockingIOError", "open", "IOBase", "RawIOBase", "FileIO",
"BytesIO", "StringIO", "BufferedIOBase",
"BufferedReader", "BufferedWriter", "BufferedRWPair",
"BufferedRandom", "TextIOBase", "TextIOWrapper"]
import os
import abc
import codecs
import _fileio
import threading
# open() uses st_blksize whenever we can
DEFAULT_BUFFER_SIZE = 8 * 1024 # bytes
# py3k has only new style classes
__metaclass__ = type
class BlockingIOError(IOError):
"""Exception raised when I/O would block on a non-blocking I/O stream."""
def __init__(self, errno, strerror, characters_written=0):
IOError.__init__(self, errno, strerror)
self.characters_written = characters_written
def open(file, mode="r", buffering=None, encoding=None, errors=None,
newline=None, closefd=True):
r"""Open file and return a stream. If the file cannot be opened, an IOError is
raised.
file is either a string giving the name (and the path if the file
isn't in the current working directory) of the file to be opened or an
integer file descriptor of the file to be wrapped. (If a file
descriptor is given, it is closed when the returned I/O object is
closed, unless closefd is set to False.)
mode is an optional string that specifies the mode in which the file
is opened. It defaults to 'r' which means open for reading in text
mode. Other common values are 'w' for writing (truncating the file if
it already exists), and 'a' for appending (which on some Unix systems,
means that all writes append to the end of the file regardless of the
current seek position). In text mode, if encoding is not specified the
encoding used is platform dependent. (For reading and writing raw
bytes use binary mode and leave encoding unspecified.) The available
modes are:
========= ===============================================================
Character Meaning
--------- ---------------------------------------------------------------
'r' open for reading (default)
'w' open for writing, truncating the file first
'a' open for writing, appending to the end of the file if it exists
'b' binary mode
't' text mode (default)
'+' open a disk file for updating (reading and writing)
'U' universal newline mode (for backwards compatibility; unneeded
for new code)
========= ===============================================================
The default mode is 'rt' (open for reading text). For binary random
access, the mode 'w+b' opens and truncates the file to 0 bytes, while
'r+b' opens the file without truncation.
Python distinguishes between files opened in binary and text modes,
even when the underlying operating system doesn't. Files opened in
binary mode (appending 'b' to the mode argument) return contents as
bytes objects without any decoding. In text mode (the default, or when
't' is appended to the mode argument), the contents of the file are
returned as strings, the bytes having been first decoded using a
platform-dependent encoding or using the specified encoding if given.
buffering is an optional integer used to set the buffering policy. By
default full buffering is on. Pass 0 to switch buffering off (only
allowed in binary mode), 1 to set line buffering, and an integer > 1
for full buffering.
encoding is the name of the encoding used to decode or encode the
file. This should only be used in text mode. The default encoding is
platform dependent, but any encoding supported by Python can be
passed. See the codecs module for the list of supported encodings.
errors is an optional string that specifies how encoding errors are to
be handled---this argument should not be used in binary mode. Pass
'strict' to raise a ValueError exception if there is an encoding error
(the default of None has the same effect), or pass 'ignore' to ignore
errors. (Note that ignoring encoding errors can lead to data loss.)
See the documentation for codecs.register for a list of the permitted
encoding error strings.
newline controls how universal newlines works (it only applies to text
mode). It can be None, '', '\n', '\r', and '\r\n'. It works as
follows:
* On input, if newline is None, universal newlines mode is
enabled. Lines in the input can end in '\n', '\r', or '\r\n', and
these are translated into '\n' before being returned to the
caller. If it is '', universal newline mode is enabled, but line
endings are returned to the caller untranslated. If it has any of
the other legal values, input lines are only terminated by the given
string, and the line ending is returned to the caller untranslated.
* On output, if newline is None, any '\n' characters written are
translated to the system default line separator, os.linesep. If
newline is '', no translation takes place. If newline is any of the
other legal values, any '\n' characters written are translated to
the given string.
If closefd is False, the underlying file descriptor will be kept open
when the file is closed. This does not work when a file name is given
and must be True in that case.
open() returns a file object whose type depends on the mode, and
through which the standard file operations such as reading and writing
are performed. When open() is used to open a file in a text mode ('w',
'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open
a file in a binary mode, the returned class varies: in read binary
mode, it returns a BufferedReader; in write binary and append binary
modes, it returns a BufferedWriter, and in read/write mode, it returns
a BufferedRandom.
It is also possible to use a string or bytearray as a file for both
reading and writing. For strings StringIO can be used like a file
opened in a text mode, and for bytes a BytesIO can be used like a file
opened in a binary mode.
"""
if not isinstance(file, (basestring, int)):
raise TypeError("invalid file: %r" % file)
if not isinstance(mode, basestring):
raise TypeError("invalid mode: %r" % mode)
if buffering is not None and not isinstance(buffering, int):
raise TypeError("invalid buffering: %r" % buffering)
if encoding is not None and not isinstance(encoding, basestring):
raise TypeError("invalid encoding: %r" % encoding)
if errors is not None and not isinstance(errors, basestring):
raise TypeError("invalid errors: %r" % errors)
modes = set(mode)
if modes - set("arwb+tU") or len(mode) > len(modes):
raise ValueError("invalid mode: %r" % mode)
reading = "r" in modes
writing = "w" in modes
appending = "a" in modes
updating = "+" in modes
text = "t" in modes
binary = "b" in modes
if "U" in modes:
if writing or appending:
raise ValueError("can't use U and writing mode at once")
reading = True
if text and binary:
raise ValueError("can't have text and binary mode at once")
if reading + writing + appending > 1:
raise ValueError("can't have read/write/append mode at once")
if not (reading or writing or appending):
raise ValueError("must have exactly one of read/write/append mode")
if binary and encoding is not None:
raise ValueError("binary mode doesn't take an encoding argument")
if binary and errors is not None:
raise ValueError("binary mode doesn't take an errors argument")
if binary and newline is not None:
raise ValueError("binary mode doesn't take a newline argument")
raw = FileIO(file,
(reading and "r" or "") +
(writing and "w" or "") +
(appending and "a" or "") +
(updating and "+" or ""),
closefd)
if buffering is None:
buffering = -1
line_buffering = False
if buffering == 1 or buffering < 0 and raw.isatty():
buffering = -1
line_buffering = True
if buffering < 0:
buffering = DEFAULT_BUFFER_SIZE
try:
bs = os.fstat(raw.fileno()).st_blksize
except (os.error, AttributeError):
pass
else:
if bs > 1:
buffering = bs
if buffering < 0:
raise ValueError("invalid buffering size")
if buffering == 0:
if binary:
return raw
raise ValueError("can't have unbuffered text I/O")
if updating:
buffer = BufferedRandom(raw, buffering)
elif writing or appending:
buffer = BufferedWriter(raw, buffering)
elif reading:
buffer = BufferedReader(raw, buffering)
else:
raise ValueError("unknown mode: %r" % mode)
if binary:
return buffer
text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
text.mode = mode
return text
class _DocDescriptor:
"""Helper for builtins.open.__doc__
"""
def __get__(self, obj, typ):
return (
"open(file, mode='r', buffering=None, encoding=None, "
"errors=None, newline=None, closefd=True)\n\n" +
open.__doc__)
class OpenWrapper:
"""Wrapper for builtins.open
Trick so that open won't become a bound method when stored
as a class variable (as dumbdbm does).
See initstdio() in Python/pythonrun.c.
"""
__doc__ = _DocDescriptor()
def __new__(cls, *args, **kwargs):
return open(*args, **kwargs)
class UnsupportedOperation(ValueError, IOError):
pass
class IOBase(object):
"""The abstract base class for all I/O classes, acting on streams of
bytes. There is no public constructor.
This class provides dummy implementations for many methods that
derived classes can override selectively; the default implementations
represent a file that cannot be read, written or seeked.
Even though IOBase does not declare read, readinto, or write because
their signatures will vary, implementations and clients should
consider those methods part of the interface. Also, implementations
may raise a IOError when operations they do not support are called.
The basic type used for binary data read from or written to a file is
bytes. bytearrays are accepted too, and in some cases (such as
readinto) needed. Text I/O classes work with str data.
Note that calling any method (even inquiries) on a closed stream is
undefined. Implementations may raise IOError in this case.
IOBase (and its subclasses) support the iterator protocol, meaning
that an IOBase object can be iterated over yielding the lines in a
stream.
IOBase also supports the :keyword:`with` statement. In this example,
fp is closed after the suite of the with statment is complete:
with open('spam.txt', 'r') as fp:
fp.write('Spam and eggs!')
"""
__metaclass__ = abc.ABCMeta
### Internal ###
def _unsupported(self, name):
"""Internal: raise an exception for unsupported operations."""
raise UnsupportedOperation("%s.%s() not supported" %
(self.__class__.__name__, name))
### Positioning ###
def seek(self, pos, whence = 0):
"""Change stream position.
Change the stream position to byte offset offset. offset is
interpreted relative to the position indicated by whence. Values
for whence are:
* 0 -- start of stream (the default); offset should be zero or positive
* 1 -- current stream position; offset may be negative
* 2 -- end of stream; offset is usually negative
Return the new absolute position.
"""
self._unsupported("seek")
def tell(self):
"""Return current stream position."""
return self.seek(0, 1)
def truncate(self, pos = None):
"""Truncate file to size bytes.
Size defaults to the current IO position as reported by tell(). Return
the new size.
"""
self._unsupported("truncate")
### Flush and close ###
def flush(self):
"""Flush write buffers, if applicable.
This is not implemented for read-only and non-blocking streams.
"""
# XXX Should this return the number of bytes written???
__closed = False
def close(self):
"""Flush and close the IO object.
This method has no effect if the file is already closed.
"""
if not self.__closed:
try:
self.flush()
except IOError:
pass # If flush() fails, just give up
self.__closed = True
def __del__(self):
"""Destructor. Calls close()."""
# The try/except block is in case this is called at program
# exit time, when it's possible that globals have already been
# deleted, and then the close() call might fail. Since
# there's nothing we can do about such failures and they annoy
# the end users, we suppress the traceback.
try:
self.close()
except:
pass
### Inquiries ###
def seekable(self):
"""Return whether object supports random access.
If False, seek(), tell() and truncate() will raise IOError.
This method may need to do a test seek().
"""
return False
def _checkSeekable(self, msg=None):
"""Internal: raise an IOError if file is not seekable
"""
if not self.seekable():
raise IOError("File or stream is not seekable."
if msg is None else msg)
def readable(self):
"""Return whether object was opened for reading.
If False, read() will raise IOError.
"""
return False
def _checkReadable(self, msg=None):
"""Internal: raise an IOError if file is not readable
"""
if not self.readable():
raise IOError("File or stream is not readable."
if msg is None else msg)
def writable(self):
"""Return whether object was opened for writing.
If False, write() and truncate() will raise IOError.
"""
return False
def _checkWritable(self, msg=None):
"""Internal: raise an IOError if file is not writable
"""
if not self.writable():
raise IOError("File or stream is not writable."
if msg is None else msg)
@property
def closed(self):
"""closed: bool. True iff the file has been closed.
For backwards compatibility, this is a property, not a predicate.
"""
return self.__closed
def _checkClosed(self, msg=None):
"""Internal: raise an ValueError if file is closed
"""
if self.closed:
raise ValueError("I/O operation on closed file."
if msg is None else msg)
### Context manager ###
def __enter__(self):
"""Context management protocol. Returns self."""
self._checkClosed()
return self
def __exit__(self, *args):
"""Context management protocol. Calls close()"""
self.close()
### Lower-level APIs ###
# XXX Should these be present even if unimplemented?
def fileno(self):
"""Returns underlying file descriptor if one exists.
An IOError is raised if the IO object does not use a file descriptor.
"""
self._unsupported("fileno")
def isatty(self):
"""Return whether this is an 'interactive' stream.
Return False if it can't be determined.
"""
self._checkClosed()
return False
### Readline[s] and writelines ###
def readline(self, limit = -1):
r"""Read and return a line from the stream.
If limit is specified, at most limit bytes will be read.
The line terminator is always b'\n' for binary files; for text
files, the newlines argument to open can be used to select the line
terminator(s) recognized.
"""
self._checkClosed()
if hasattr(self, "peek"):
def nreadahead():
readahead = self.peek(1)
if not readahead:
return 1
n = (readahead.find(b"\n") + 1) or len(readahead)
if limit >= 0:
n = min(n, limit)
return n
else:
def nreadahead():
return 1
if limit is None:
limit = -1
if not isinstance(limit, (int, long)):
raise TypeError("limit must be an integer")
res = bytearray()
while limit < 0 or len(res) < limit:
b = self.read(nreadahead())
if not b:
break
res += b
if res.endswith(b"\n"):
break
return bytes(res)
def __iter__(self):
self._checkClosed()
return self
def next(self):
line = self.readline()
if not line:
raise StopIteration
return line
def readlines(self, hint=None):
"""Return a list of lines from the stream.
hint can be specified to control the number of lines read: no more
lines will be read if the total size (in bytes/characters) of all
lines so far exceeds hint.
"""
if hint is None:
hint = -1
if not isinstance(hint, (int, long)):
raise TypeError("hint must be an integer")
if hint <= 0:
return list(self)
n = 0
lines = []
for line in self:
lines.append(line)
n += len(line)
if n >= hint:
break
return lines
def writelines(self, lines):
self._checkClosed()
for line in lines:
self.write(line)
class RawIOBase(IOBase):
"""Base class for raw binary I/O."""
# The read() method is implemented by calling readinto(); derived
# classes that want to support read() only need to implement
# readinto() as a primitive operation. In general, readinto() can be
# more efficient than read().
# (It would be tempting to also provide an implementation of
# readinto() in terms of read(), in case the latter is a more suitable
# primitive operation, but that would lead to nasty recursion in case
# a subclass doesn't implement either.)
def read(self, n = -1):
"""Read and return up to n bytes.
Returns an empty bytes array on EOF, or None if the object is
set not to block and has no data to read.
"""
if n is None:
n = -1
if n < 0:
return self.readall()
b = bytearray(n.__index__())
n = self.readinto(b)
del b[n:]
return bytes(b)
def readall(self):
"""Read until EOF, using multiple read() call."""
res = bytearray()
while True:
data = self.read(DEFAULT_BUFFER_SIZE)
if not data:
break
res += data
return bytes(res)
def readinto(self, b):
"""Read up to len(b) bytes into b.
Returns number of bytes read (0 for EOF), or None if the object
is set not to block as has no data to read.
"""
self._unsupported("readinto")
def write(self, b):
"""Write the given buffer to the IO stream.
Returns the number of bytes written, which may be less than len(b).
"""
self._unsupported("write")
class FileIO(_fileio._FileIO, RawIOBase):
"""Raw I/O implementation for OS files."""
# This multiply inherits from _FileIO and RawIOBase to make
# isinstance(io.FileIO(), io.RawIOBase) return True without requiring
# that _fileio._FileIO inherits from io.RawIOBase (which would be hard
# to do since _fileio.c is written in C).
def __init__(self, name, mode="r", closefd=True):
_fileio._FileIO.__init__(self, name, mode, closefd)
self._name = name
def close(self):
_fileio._FileIO.close(self)
RawIOBase.close(self)
@property
def name(self):
return self._name
class BufferedIOBase(IOBase):
"""Base class for buffered IO objects.
The main difference with RawIOBase is that the read() method
supports omitting the size argument, and does not have a default
implementation that defers to readinto().
In addition, read(), readinto() and write() may raise
BlockingIOError if the underlying raw stream is in non-blocking
mode and not ready; unlike their raw counterparts, they will never
return None.
A typical implementation should not inherit from a RawIOBase
implementation, but wrap one.
"""
def read(self, n = None):
"""Read and return up to n bytes.
If the argument is omitted, None, or negative, reads and
returns all data until EOF.
If the argument is positive, and the underlying raw stream is
not 'interactive', multiple raw reads may be issued to satisfy
the byte count (unless EOF is reached first). But for
interactive raw streams (XXX and for pipes?), at most one raw
read will be issued, and a short result does not imply that
EOF is imminent.
Returns an empty bytes array on EOF.
Raises BlockingIOError if the underlying raw stream has no
data at the moment.
"""
self._unsupported("read")
def readinto(self, b):
"""Read up to len(b) bytes into b.
Like read(), this may issue multiple reads to the underlying raw
stream, unless the latter is 'interactive'.
Returns the number of bytes read (0 for EOF).
Raises BlockingIOError if the underlying raw stream has no
data at the moment.
"""
# XXX This ought to work with anything that supports the buffer API
data = self.read(len(b))
n = len(data)
try:
b[:n] = data
except TypeError as err:
import array
if not isinstance(b, array.array):
raise err
b[:n] = array.array(b'b', data)
return n
def write(self, b):
"""Write the given buffer to the IO stream.
Return the number of bytes written, which is never less than
len(b).
Raises BlockingIOError if the buffer is full and the
underlying raw stream cannot accept more data at the moment.
"""
self._unsupported("write")
class _BufferedIOMixin(BufferedIOBase):
"""A mixin implementation of BufferedIOBase with an underlying raw stream.
This passes most requests on to the underlying raw stream. It
does *not* provide implementations of read(), readinto() or
write().
"""
def __init__(self, raw):
self.raw = raw
### Positioning ###
def seek(self, pos, whence=0):
return self.raw.seek(pos, whence)
def tell(self):
return self.raw.tell()
def truncate(self, pos=None):
# Flush the stream. We're mixing buffered I/O with lower-level I/O,
# and a flush may be necessary to synch both views of the current
# file state.
self.flush()
if pos is None:
pos = self.tell()
# XXX: Should seek() be used, instead of passing the position
# XXX directly to truncate?
return self.raw.truncate(pos)
### Flush and close ###
def flush(self):
self.raw.flush()
def close(self):
if not self.closed:
try:
self.flush()
except IOError:
pass # If flush() fails, just give up
self.raw.close()
### Inquiries ###
def seekable(self):
return self.raw.seekable()
def readable(self):
return self.raw.readable()
def writable(self):
return self.raw.writable()
@property
def closed(self):
return self.raw.closed
@property
def name(self):
return self.raw.name
@property
def mode(self):
return self.raw.mode
### Lower-level APIs ###
def fileno(self):
return self.raw.fileno()
def isatty(self):
return self.raw.isatty()
class _BytesIO(BufferedIOBase):
"""Buffered I/O implementation using an in-memory bytes buffer."""
# XXX More docs
def __init__(self, initial_bytes=None):
buf = bytearray()
if initial_bytes is not None:
buf += bytearray(initial_bytes)
self._buffer = buf
self._pos = 0
def getvalue(self):
"""Return the bytes value (contents) of the buffer
"""
if self.closed:
raise ValueError("getvalue on closed file")
return bytes(self._buffer)
def read(self, n=None):
if self.closed:
raise ValueError("read from closed file")
if n is None:
n = -1
if not isinstance(n, (int, long)):
raise TypeError("argument must be an integer")
if n < 0:
n = len(self._buffer)
if len(self._buffer) <= self._pos:
return b""
newpos = min(len(self._buffer), self._pos + n)
b = self._buffer[self._pos : newpos]
self._pos = newpos
return bytes(b)
def read1(self, n):
"""this is the same as read.
"""
return self.read(n)
def write(self, b):
if self.closed:
raise ValueError("write to closed file")
if isinstance(b, unicode):
raise TypeError("can't write unicode to binary stream")
n = len(b)
if n == 0:
return 0
pos = self._pos
if pos > len(self._buffer):
# Inserts null bytes between the current end of the file
# and the new write position.
padding = b'\x00' * (pos - len(self._buffer))
self._buffer += padding
self._buffer[pos:pos + n] = b
self._pos += n
return n
def seek(self, pos, whence=0):
if self.closed:
raise ValueError("seek on closed file")
try:
pos = pos.__index__()
except AttributeError as err:
raise TypeError("an integer is required") # from err
if whence == 0:
if pos < 0:
raise ValueError("negative seek position %r" % (pos,))
self._pos = pos
elif whence == 1:
self._pos = max(0, self._pos + pos)
elif whence == 2:
self._pos = max(0, len(self._buffer) + pos)
else:
raise ValueError("invalid whence value")
return self._pos
def tell(self):
if self.closed:
raise ValueError("tell on closed file")
return self._pos
def truncate(self, pos=None):
if self.closed:
raise ValueError("truncate on closed file")
if pos is None:
pos = self._pos
elif pos < 0:
raise ValueError("negative truncate position %r" % (pos,))
del self._buffer[pos:]
return self.seek(pos)
def readable(self):
return True
def writable(self):
return True
def seekable(self):
return True
# Use the faster implementation of BytesIO if available
try:
import _bytesio
class BytesIO(_bytesio._BytesIO, BufferedIOBase):
__doc__ = _bytesio._BytesIO.__doc__
except ImportError:
BytesIO = _BytesIO
class BufferedReader(_BufferedIOMixin):
"""BufferedReader(raw[, buffer_size])
A buffer for a readable, sequential BaseRawIO object.
The constructor creates a BufferedReader for the given readable raw
stream and buffer_size. If buffer_size is omitted, DEFAULT_BUFFER_SIZE
is used.
"""
def __init__(self, raw, buffer_size=DEFAULT_BUFFER_SIZE):
"""Create a new buffered reader using the given readable raw IO object.
"""
raw._checkReadable()
_BufferedIOMixin.__init__(self, raw)
self.buffer_size = buffer_size
self._reset_read_buf()
self._read_lock = threading.Lock()
def _reset_read_buf(self):
self._read_buf = b""
self._read_pos = 0
def read(self, n=None):
"""Read n bytes.
Returns exactly n bytes of data unless the underlying raw IO
stream reaches EOF or if the call would block in non-blocking
mode. If n is negative, read until EOF or until read() would
block.
"""
with self._read_lock:
return self._read_unlocked(n)
def _read_unlocked(self, n=None):
nodata_val = b""
empty_values = (b"", None)
buf = self._read_buf
pos = self._read_pos
# Special case for when the number of bytes to read is unspecified.
if n is None or n == -1:
self._reset_read_buf()
chunks = [buf[pos:]] # Strip the consumed bytes.
current_size = 0
while True:
# Read until EOF or until read() would block.
chunk = self.raw.read()
if chunk in empty_values:
nodata_val = chunk
break
current_size += len(chunk)
chunks.append(chunk)
return b"".join(chunks) or nodata_val
# The number of bytes to read is specified, return at most n bytes.
avail = len(buf) - pos # Length of the available buffered data.
if n <= avail:
# Fast path: the data to read is fully buffered.
self._read_pos += n
return buf[pos:pos+n]
# Slow path: read from the stream until enough bytes are read,
# or until an EOF occurs or until read() would block.
chunks = [buf[pos:]]
wanted = max(self.buffer_size, n)
while avail < n:
chunk = self.raw.read(wanted)
if chunk in empty_values:
nodata_val = chunk
break
avail += len(chunk)
chunks.append(chunk)
# n is more then avail only when an EOF occurred or when
# read() would have blocked.
n = min(n, avail)
out = b"".join(chunks)
self._read_buf = out[n:] # Save the extra data in the buffer.
self._read_pos = 0
return out[:n] if out else nodata_val
def peek(self, n=0):
"""Returns buffered bytes without advancing the position.
The argument indicates a desired minimal number of bytes; we
do at most one raw read to satisfy it. We never return more
than self.buffer_size.
"""
with self._read_lock:
return self._peek_unlocked(n)
def _peek_unlocked(self, n=0):
want = min(n, self.buffer_size)
have = len(self._read_buf) - self._read_pos
if have < want:
to_read = self.buffer_size - have
current = self.raw.read(to_read)
if current:
self._read_buf = self._read_buf[self._read_pos:] + current
self._read_pos = 0
return self._read_buf[self._read_pos:]
def read1(self, n):
"""Reads up to n bytes, with at most one read() system call."""
# Returns up to n bytes. If at least one byte is buffered, we
# only return buffered bytes. Otherwise, we do one raw read.
if n <= 0:
return b""
with self._read_lock:
self._peek_unlocked(1)
return self._read_unlocked(
min(n, len(self._read_buf) - self._read_pos))
def tell(self):
return self.raw.tell() - len(self._read_buf) + self._read_pos
def seek(self, pos, whence=0):
with self._read_lock:
if whence == 1:
pos -= len(self._read_buf) - self._read_pos
pos = self.raw.seek(pos, whence)
self._reset_read_buf()
return pos
class BufferedWriter(_BufferedIOMixin):
"""A buffer for a writeable sequential RawIO object.
The constructor creates a BufferedWriter for the given writeable raw
stream. If the buffer_size is not given, it defaults to
DEAFULT_BUFFER_SIZE. If max_buffer_size is omitted, it defaults to
twice the buffer size.
"""
def __init__(self, raw,
buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
raw._checkWritable()
_BufferedIOMixin.__init__(self, raw)
self.buffer_size = buffer_size
self.max_buffer_size = (2*buffer_size
if max_buffer_size is None
else max_buffer_size)
self._write_buf = bytearray()
self._write_lock = threading.Lock()
def write(self, b):
if self.closed:
raise ValueError("write to closed file")
if isinstance(b, unicode):
raise TypeError("can't write unicode to binary stream")
with self._write_lock:
# XXX we can implement some more tricks to try and avoid
# partial writes
if len(self._write_buf) > self.buffer_size:
# We're full, so let's pre-flush the buffer
try:
self._flush_unlocked()
except BlockingIOError as e:
# We can't accept anything else.
# XXX Why not just let the exception pass through?
raise BlockingIOError(e.errno, e.strerror, 0)
before = len(self._write_buf)
self._write_buf.extend(b)
written = len(self._write_buf) - before
if len(self._write_buf) > self.buffer_size:
try:
self._flush_unlocked()
except BlockingIOError as e:
if len(self._write_buf) > self.max_buffer_size:
# We've hit max_buffer_size. We have to accept a
# partial write and cut back our buffer.
overage = len(self._write_buf) - self.max_buffer_size
self._write_buf = self._write_buf[:self.max_buffer_size]
raise BlockingIOError(e.errno, e.strerror, overage)
return written
def truncate(self, pos=None):
with self._write_lock:
self._flush_unlocked()
if pos is None:
pos = self.raw.tell()
return self.raw.truncate(pos)
def flush(self):
with self._write_lock:
self._flush_unlocked()
def _flush_unlocked(self):
if self.closed:
raise ValueError("flush of closed file")
written = 0
try:
while self._write_buf:
n = self.raw.write(self._write_buf)
del self._write_buf[:n]
written += n
except BlockingIOError as e:
n = e.characters_written
del self._write_buf[:n]
written += n
raise BlockingIOError(e.errno, e.strerror, written)
def tell(self):
return self.raw.tell() + len(self._write_buf)
def seek(self, pos, whence=0):
with self._write_lock:
self._flush_unlocked()
return self.raw.seek(pos, whence)
class BufferedRWPair(BufferedIOBase):
"""A buffered reader and writer object together.
A buffered reader object and buffered writer object put together to
form a sequential IO object that can read and write. This is typically
used with a socket or two-way pipe.
reader and writer are RawIOBase objects that are readable and
writeable respectively. If the buffer_size is omitted it defaults to
DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered writer)
defaults to twice the buffer size.
"""
# XXX The usefulness of this (compared to having two separate IO
# objects) is questionable.
def __init__(self, reader, writer,
buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
"""Constructor.
The arguments are two RawIO instances.
"""
reader._checkReadable()
writer._checkWritable()
self.reader = BufferedReader(reader, buffer_size)
self.writer = BufferedWriter(writer, buffer_size, max_buffer_size)
def read(self, n=None):
if n is None:
n = -1
return self.reader.read(n)
def readinto(self, b):
return self.reader.readinto(b)
def write(self, b):
return self.writer.write(b)
def peek(self, n=0):
return self.reader.peek(n)
def read1(self, n):
return self.reader.read1(n)
def readable(self):
return self.reader.readable()
def writable(self):
return self.writer.writable()
def flush(self):
return self.writer.flush()
def close(self):
self.writer.close()
self.reader.close()
def isatty(self):
return self.reader.isatty() or self.writer.isatty()
@property
def closed(self):
return self.writer.closed
class BufferedRandom(BufferedWriter, BufferedReader):
"""A buffered interface to random access streams.
The constructor creates a reader and writer for a seekable stream,
raw, given in the first argument. If the buffer_size is omitted it
defaults to DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered
writer) defaults to twice the buffer size.
"""
def __init__(self, raw,
buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
raw._checkSeekable()
BufferedReader.__init__(self, raw, buffer_size)
BufferedWriter.__init__(self, raw, buffer_size, max_buffer_size)
def seek(self, pos, whence=0):
self.flush()
# First do the raw seek, then empty the read buffer, so that
# if the raw seek fails, we don't lose buffered data forever.
pos = self.raw.seek(pos, whence)
with self._read_lock:
self._reset_read_buf()
return pos
def tell(self):
if self._write_buf:
return self.raw.tell() + len(self._write_buf)
else:
return BufferedReader.tell(self)
def truncate(self, pos=None):
if pos is None:
pos = self.tell()
# Use seek to flush the read buffer.
self.seek(pos)
return BufferedWriter.truncate(self)
def read(self, n=None):
if n is None:
n = -1
self.flush()
return BufferedReader.read(self, n)
def readinto(self, b):
self.flush()
return BufferedReader.readinto(self, b)
def peek(self, n=0):
self.flush()
return BufferedReader.peek(self, n)
def read1(self, n):
self.flush()
return BufferedReader.read1(self, n)
def write(self, b):
if self._read_buf:
# Undo readahead
with self._read_lock:
self.raw.seek(self._read_pos - len(self._read_buf), 1)
self._reset_read_buf()
return BufferedWriter.write(self, b)
class TextIOBase(IOBase):
"""Base class for text I/O.
This class provides a character and line based interface to stream
I/O. There is no readinto method because Python's character strings
are immutable. There is no public constructor.
"""
def read(self, n = -1):
"""Read at most n characters from stream.
Read from underlying buffer until we have n characters or we hit EOF.
If n is negative or omitted, read until EOF.
"""
self._unsupported("read")
def write(self, s):
"""Write string s to stream."""
self._unsupported("write")
def truncate(self, pos = None):
"""Truncate size to pos."""
self._unsupported("truncate")
def readline(self):
"""Read until newline or EOF.
Returns an empty string if EOF is hit immediately.
"""
self._unsupported("readline")
@property
def encoding(self):
"""Subclasses should override."""
return None
@property
def newlines(self):
"""Line endings translated so far.
Only line endings translated during reading are considered.
Subclasses should override.
"""
return None
class IncrementalNewlineDecoder(codecs.IncrementalDecoder):
"""Codec used when reading a file in universal newlines mode.
It wraps another incremental decoder, translating \\r\\n and \\r into \\n.
It also records the types of newlines encountered.
When used with translate=False, it ensures that the newline sequence is
returned in one piece.
"""
def __init__(self, decoder, translate, errors='strict'):
codecs.IncrementalDecoder.__init__(self, errors=errors)
self.translate = translate
self.decoder = decoder
self.seennl = 0
self.pendingcr = False
def decode(self, input, final=False):
# decode input (with the eventual \r from a previous pass)
output = self.decoder.decode(input, final=final)
if self.pendingcr and (output or final):
output = "\r" + output
self.pendingcr = False
# retain last \r even when not translating data:
# then readline() is sure to get \r\n in one pass
if output.endswith("\r") and not final:
output = output[:-1]
self.pendingcr = True
# Record which newlines are read
crlf = output.count('\r\n')
cr = output.count('\r') - crlf
lf = output.count('\n') - crlf
self.seennl |= (lf and self._LF) | (cr and self._CR) \
| (crlf and self._CRLF)
if self.translate:
if crlf:
output = output.replace("\r\n", "\n")
if cr:
output = output.replace("\r", "\n")
return output
def getstate(self):
buf, flag = self.decoder.getstate()
flag <<= 1
if self.pendingcr:
flag |= 1
return buf, flag
def setstate(self, state):
buf, flag = state
self.pendingcr = bool(flag & 1)
self.decoder.setstate((buf, flag >> 1))
def reset(self):
self.seennl = 0
self.pendingcr = False
self.decoder.reset()
_LF = 1
_CR = 2
_CRLF = 4
@property
def newlines(self):
return (None,
"\n",
"\r",
("\r", "\n"),
"\r\n",
("\n", "\r\n"),
("\r", "\r\n"),
("\r", "\n", "\r\n")
)[self.seennl]
class TextIOWrapper(TextIOBase):
r"""Character and line based layer over a BufferedIOBase object, buffer.
encoding gives the name of the encoding that the stream will be
decoded or encoded with. It defaults to locale.getpreferredencoding.
errors determines the strictness of encoding and decoding (see the
codecs.register) and defaults to "strict".
newline can be None, '', '\n', '\r', or '\r\n'. It controls the
handling of line endings. If it is None, universal newlines is
enabled. With this enabled, on input, the lines endings '\n', '\r',
or '\r\n' are translated to '\n' before being returned to the
caller. Conversely, on output, '\n' is translated to the system
default line separator, os.linesep. If newline is any other of its
legal values, that newline becomes the newline when the file is read
and it is returned untranslated. On output, '\n' is converted to the
newline.
If line_buffering is True, a call to flush is implied when a call to
write contains a newline character.
"""
_CHUNK_SIZE = 128
def __init__(self, buffer, encoding=None, errors=None, newline=None,
line_buffering=False):
if newline not in (None, "", "\n", "\r", "\r\n"):
raise ValueError("illegal newline value: %r" % (newline,))
if encoding is None:
try:
encoding = os.device_encoding(buffer.fileno())
except (AttributeError, UnsupportedOperation):
pass
if encoding is None:
try:
import locale
except ImportError:
# Importing locale may fail if Python is being built
encoding = "ascii"
else:
encoding = locale.getpreferredencoding()
if not isinstance(encoding, basestring):
raise ValueError("invalid encoding: %r" % encoding)
if errors is None:
errors = "strict"
else:
if not isinstance(errors, basestring):
raise ValueError("invalid errors: %r" % errors)
self.buffer = buffer
self._line_buffering = line_buffering
self._encoding = encoding
self._errors = errors
self._readuniversal = not newline
self._readtranslate = newline is None
self._readnl = newline
self._writetranslate = newline != ''
self._writenl = newline or os.linesep
self._encoder = None
self._decoder = None
self._decoded_chars = '' # buffer for text returned from decoder
self._decoded_chars_used = 0 # offset into _decoded_chars for read()
self._snapshot = None # info for reconstructing decoder state
self._seekable = self._telling = self.buffer.seekable()
# self._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().
# Naming convention:
# - "bytes_..." for integer variables that count input bytes
# - "chars_..." for integer variables that count decoded characters
@property
def encoding(self):
return self._encoding
@property
def errors(self):
return self._errors
@property
def line_buffering(self):
return self._line_buffering
def seekable(self):
return self._seekable
def readable(self):
return self.buffer.readable()
def writable(self):
return self.buffer.writable()
def flush(self):
self.buffer.flush()
self._telling = self._seekable
def close(self):
try:
self.flush()
except:
pass # If flush() fails, just give up
self.buffer.close()
@property
def closed(self):
return self.buffer.closed
@property
def name(self):
return self.buffer.name
def fileno(self):
return self.buffer.fileno()
def isatty(self):
return self.buffer.isatty()
def write(self, s):
if self.closed:
raise ValueError("write to closed file")
if not isinstance(s, unicode):
raise TypeError("can't write %s to text stream" %
s.__class__.__name__)
length = len(s)
haslf = (self._writetranslate or self._line_buffering) and "\n" in s
if haslf and self._writetranslate and self._writenl != "\n":
s = s.replace("\n", self._writenl)
encoder = self._encoder or self._get_encoder()
# XXX What if we were just reading?
b = encoder.encode(s)
self.buffer.write(b)
if self._line_buffering and (haslf or "\r" in s):
self.flush()
self._snapshot = None
if self._decoder:
self._decoder.reset()
return length
def _get_encoder(self):
make_encoder = codecs.getincrementalencoder(self._encoding)
self._encoder = make_encoder(self._errors)
return self._encoder
def _get_decoder(self):
make_decoder = codecs.getincrementaldecoder(self._encoding)
decoder = make_decoder(self._errors)
if self._readuniversal:
decoder = IncrementalNewlineDecoder(decoder, self._readtranslate)
self._decoder = decoder
return decoder
# The following three methods implement an ADT for _decoded_chars.
# Text returned from the decoder is buffered here until the client
# requests it by calling our read() or readline() method.
def _set_decoded_chars(self, chars):
"""Set the _decoded_chars buffer."""
self._decoded_chars = chars
self._decoded_chars_used = 0
def _get_decoded_chars(self, n=None):
"""Advance into the _decoded_chars buffer."""
offset = self._decoded_chars_used
if n is None:
chars = self._decoded_chars[offset:]
else:
chars = self._decoded_chars[offset:offset + n]
self._decoded_chars_used += len(chars)
return chars
def _rewind_decoded_chars(self, n):
"""Rewind the _decoded_chars buffer."""
if self._decoded_chars_used < n:
raise AssertionError("rewind decoded_chars out of bounds")
self._decoded_chars_used -= n
def _read_chunk(self):
"""
Read and decode the next chunk of data from the BufferedReader.
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 is None:
raise ValueError("no decoder")
if self._telling:
# To prepare for tell(), we need to snapshot a point in the
# file where the decoder's input buffer is empty.
dec_buffer, dec_flags = self._decoder.getstate()
# Given this, we know there was a valid snapshot point
# len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
# Read a chunk, decode it, and put the result in self._decoded_chars.
input_chunk = self.buffer.read1(self._CHUNK_SIZE)
eof = not input_chunk
self._set_decoded_chars(self._decoder.decode(input_chunk, eof))
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.
self._snapshot = (dec_flags, dec_buffer + input_chunk)
return not eof
def _pack_cookie(self, position, dec_flags=0,
bytes_to_feed=0, need_eof=0, chars_to_skip=0):
# The meaning of a tell() cookie is: seek to position, set the
# decoder flags to dec_flags, read bytes_to_feed bytes, feed them
# into the decoder with need_eof as the EOF flag, then skip
# chars_to_skip characters of the decoded result. For most simple
# decoders, tell() will often just give a byte offset in the file.
return (position | (dec_flags<<64) | (bytes_to_feed<<128) |
(chars_to_skip<<192) | bool(need_eof)<<256)
def _unpack_cookie(self, bigint):
rest, position = divmod(bigint, 1<<64)
rest, dec_flags = divmod(rest, 1<<64)
rest, bytes_to_feed = divmod(rest, 1<<64)
need_eof, chars_to_skip = divmod(rest, 1<<64)
return position, dec_flags, bytes_to_feed, need_eof, chars_to_skip
def tell(self):
if not self._seekable:
raise IOError("underlying stream is not seekable")
if not self._telling:
raise IOError("telling position disabled by next() call")
self.flush()
position = self.buffer.tell()
decoder = self._decoder
if decoder is None or self._snapshot is None:
if self._decoded_chars:
# This should never happen.
raise AssertionError("pending decoded text")
return position
# Skip backward to the snapshot point (see _read_chunk).
dec_flags, next_input = self._snapshot
position -= len(next_input)
# How many decoded characters have been used up since the snapshot?
chars_to_skip = self._decoded_chars_used
if chars_to_skip == 0:
# We haven't moved from the snapshot point.
return self._pack_cookie(position, dec_flags)
# Starting from the snapshot position, we will walk the decoder
# forward until it gives us enough decoded characters.
saved_state = decoder.getstate()
try:
# Note our initial start point.
decoder.setstate((b'', dec_flags))
start_pos = position
start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
need_eof = 0
# 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).
for next_byte in next_input:
bytes_fed += 1
chars_decoded += len(decoder.decode(next_byte))
dec_buffer, dec_flags = decoder.getstate()
if not dec_buffer and chars_decoded <= chars_to_skip:
# Decoder buffer is empty, so this is a safe start point.
start_pos += bytes_fed
chars_to_skip -= chars_decoded
start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
if chars_decoded >= chars_to_skip:
break
else:
# We didn't get enough decoded data; signal EOF to get more.
chars_decoded += len(decoder.decode(b'', final=True))
need_eof = 1
if chars_decoded < chars_to_skip:
raise IOError("can't reconstruct logical file position")
# The returned cookie corresponds to the last safe start point.
return self._pack_cookie(
start_pos, start_flags, bytes_fed, need_eof, chars_to_skip)
finally:
decoder.setstate(saved_state)
def truncate(self, pos=None):
self.flush()
if pos is None:
pos = self.tell()
self.seek(pos)
return self.buffer.truncate()
def seek(self, cookie, whence=0):
if self.closed:
raise ValueError("tell on closed file")
if not self._seekable:
raise IOError("underlying stream is not seekable")
if whence == 1: # seek relative to current position
if cookie != 0:
raise IOError("can't do nonzero cur-relative seeks")
# Seeking to the current position should attempt to
# sync the underlying buffer with the current position.
whence = 0
cookie = self.tell()
if whence == 2: # seek relative to end of file
if cookie != 0:
raise IOError("can't do nonzero end-relative seeks")
self.flush()
position = self.buffer.seek(0, 2)
self._set_decoded_chars('')
self._snapshot = None
if self._decoder:
self._decoder.reset()
return position
if whence != 0:
raise ValueError("invalid whence (%r, should be 0, 1 or 2)" %
(whence,))
if cookie < 0:
raise ValueError("negative seek position %r" % (cookie,))
self.flush()
# The strategy of seek() is to go back to the safe start point
# and replay the effect of read(chars_to_skip) from there.
start_pos, dec_flags, bytes_to_feed, need_eof, chars_to_skip = \
self._unpack_cookie(cookie)
# Seek back to the safe start point.
self.buffer.seek(start_pos)
self._set_decoded_chars('')
self._snapshot = None
# Restore the decoder to its state from the safe start point.
if self._decoder or dec_flags or chars_to_skip:
self._decoder = self._decoder or self._get_decoder()
self._decoder.setstate((b'', dec_flags))
self._snapshot = (dec_flags, b'')
if chars_to_skip:
# Just like _read_chunk, feed the decoder and save a snapshot.
input_chunk = self.buffer.read(bytes_to_feed)
self._set_decoded_chars(
self._decoder.decode(input_chunk, need_eof))
self._snapshot = (dec_flags, input_chunk)
# Skip chars_to_skip of the decoded characters.
if len(self._decoded_chars) < chars_to_skip:
raise IOError("can't restore logical file position")
self._decoded_chars_used = chars_to_skip
return cookie
def read(self, n=None):
if n is None:
n = -1
decoder = self._decoder or self._get_decoder()
if n < 0:
# Read everything.
result = (self._get_decoded_chars() +
decoder.decode(self.buffer.read(), final=True))
self._set_decoded_chars('')
self._snapshot = None
return result
else:
# Keep reading chunks until we have n characters to return.
eof = False
result = self._get_decoded_chars(n)
while len(result) < n and not eof:
eof = not self._read_chunk()
result += self._get_decoded_chars(n - len(result))
return result
def next(self):
self._telling = False
line = self.readline()
if not line:
self._snapshot = None
self._telling = self._seekable
raise StopIteration
return line
def readline(self, limit=None):
if self.closed:
raise ValueError("read from closed file")
if limit is None:
limit = -1
if not isinstance(limit, (int, long)):
raise TypeError("limit must be an integer")
# Grab all the decoded text (we will rewind any extra bits later).
line = self._get_decoded_chars()
start = 0
decoder = self._decoder or self._get_decoder()
pos = endpos = None
while True:
if self._readtranslate:
# Newlines are already translated, only search for \n
pos = line.find('\n', start)
if pos >= 0:
endpos = pos + 1
break
else:
start = len(line)
elif self._readuniversal:
# Universal newline search. Find any of \r, \r\n, \n
# The decoder ensures that \r\n are not split in two pieces
# In C we'd look for these in parallel of course.
nlpos = line.find("\n", start)
crpos = line.find("\r", start)
if crpos == -1:
if nlpos == -1:
# Nothing found
start = len(line)
else:
# Found \n
endpos = nlpos + 1
break
elif nlpos == -1:
# Found lone \r
endpos = crpos + 1
break
elif nlpos < crpos:
# Found \n
endpos = nlpos + 1
break
elif nlpos == crpos + 1:
# Found \r\n
endpos = crpos + 2
break
else:
# Found \r
endpos = crpos + 1
break
else:
# non-universal
pos = line.find(self._readnl)
if pos >= 0:
endpos = pos + len(self._readnl)
break
if limit >= 0 and len(line) >= limit:
endpos = limit # reached length limit
break
# No line ending seen yet - get more data
more_line = ''
while self._read_chunk():
if self._decoded_chars:
break
if self._decoded_chars:
line += self._get_decoded_chars()
else:
# end of file
self._set_decoded_chars('')
self._snapshot = None
return line
if limit >= 0 and endpos > limit:
endpos = limit # don't exceed limit
# Rewind _decoded_chars to just after the line ending we found.
self._rewind_decoded_chars(len(line) - endpos)
return line[:endpos]
@property
def newlines(self):
return self._decoder.newlines if self._decoder else None
class StringIO(TextIOWrapper):
"""An in-memory stream for text. The initial_value argument sets the
value of object. The other arguments are like those of TextIOWrapper's
constructor.
"""
def __init__(self, initial_value="", encoding="utf-8",
errors="strict", newline="\n"):
super(StringIO, self).__init__(BytesIO(),
encoding=encoding,
errors=errors,
newline=newline)
if initial_value:
if not isinstance(initial_value, unicode):
initial_value = unicode(initial_value)
self.write(initial_value)
self.seek(0)
def getvalue(self):
self.flush()
return self.buffer.getvalue().decode(self._encoding, self._errors)
|