forked from PyCQA/pycodestyle
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pycodestyle.py
executable file
·2732 lines (2386 loc) · 99.9 KB
/
pycodestyle.py
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
#!/usr/bin/env python
# pycodestyle.py - Check Python source code formatting, according to
# PEP 8
#
# Copyright (C) 2006-2009 Johann C. Rocholl <[email protected]>
# Copyright (C) 2009-2014 Florent Xicluna <[email protected]>
# Copyright (C) 2014-2016 Ian Lee <[email protected]>
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation files
# (the "Software"), to deal in the Software without restriction,
# including without limitation the rights to use, copy, modify, merge,
# publish, distribute, sublicense, and/or sell copies of the Software,
# and to permit persons to whom the Software is furnished to do so,
# subject to the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
r"""
Check Python source code formatting, according to PEP 8.
For usage and a list of options, try this:
$ python pycodestyle.py -h
This program and its regression test suite live here:
https://github.com/pycqa/pycodestyle
Groups of errors and warnings:
E errors
W warnings
100 indentation
200 whitespace
300 blank lines
400 imports
500 line length
600 deprecation
700 statements
900 syntax error
"""
import bisect
import configparser
import inspect
import io
import keyword
import os
import re
import sys
import time
import tokenize
import warnings
from fnmatch import fnmatch
from functools import lru_cache
from optparse import OptionParser
# this is a performance hack. see https://bugs.python.org/issue43014
if (
sys.version_info < (3, 10) and
callable(getattr(tokenize, '_compile', None))
): # pragma: no cover (<py310)
tokenize._compile = lru_cache()(tokenize._compile) # type: ignore
__version__ = '2.10.0'
DEFAULT_EXCLUDE = '.svn,CVS,.bzr,.hg,.git,__pycache__,.tox'
DEFAULT_IGNORE = 'E121,E123,E126,E226,E24,E704,W503,W504'
try:
if sys.platform == 'win32':
USER_CONFIG = os.path.expanduser(r'~\.pycodestyle')
else:
USER_CONFIG = os.path.join(
os.getenv('XDG_CONFIG_HOME') or os.path.expanduser('~/.config'),
'pycodestyle'
)
except ImportError:
USER_CONFIG = None
PROJECT_CONFIG = ('setup.cfg', 'tox.ini')
TESTSUITE_PATH = os.path.join(os.path.dirname(__file__), 'testsuite')
MAX_LINE_LENGTH = 79
# Number of blank lines between various code parts.
BLANK_LINES_CONFIG = {
# Top level class and function.
'top_level': 2,
# Methods and nested class and function.
'method': 1,
}
MAX_DOC_LENGTH = 72
INDENT_SIZE = 4
REPORT_FORMAT = {
'default': '%(path)s:%(row)d:%(col)d: %(code)s %(text)s',
'pylint': '%(path)s:%(row)d: [%(code)s] %(text)s',
}
PyCF_ONLY_AST = 1024
SINGLETONS = frozenset(['False', 'None', 'True'])
KEYWORDS = frozenset(keyword.kwlist + ['print', 'async']) - SINGLETONS
UNARY_OPERATORS = frozenset(['>>', '**', '*', '+', '-'])
ARITHMETIC_OP = frozenset(['**', '*', '/', '//', '+', '-', '@'])
WS_OPTIONAL_OPERATORS = ARITHMETIC_OP.union(['^', '&', '|', '<<', '>>', '%'])
ASSIGNMENT_EXPRESSION_OP = [':='] if sys.version_info >= (3, 8) else []
WS_NEEDED_OPERATORS = frozenset([
'**=', '*=', '/=', '//=', '+=', '-=', '!=', '<>', '<', '>',
'%=', '^=', '&=', '|=', '==', '<=', '>=', '<<=', '>>=', '=',
'and', 'in', 'is', 'or', '->'] +
ASSIGNMENT_EXPRESSION_OP)
WHITESPACE = frozenset(' \t\xa0')
NEWLINE = frozenset([tokenize.NL, tokenize.NEWLINE])
SKIP_TOKENS = NEWLINE.union([tokenize.INDENT, tokenize.DEDENT])
# ERRORTOKEN is triggered by backticks in Python 3
SKIP_COMMENTS = SKIP_TOKENS.union([tokenize.COMMENT, tokenize.ERRORTOKEN])
BENCHMARK_KEYS = ['directories', 'files', 'logical lines', 'physical lines']
INDENT_REGEX = re.compile(r'([ \t]*)')
ERRORCODE_REGEX = re.compile(r'\b[A-Z]\d{3}\b')
DOCSTRING_REGEX = re.compile(r'u?r?["\']')
EXTRANEOUS_WHITESPACE_REGEX = re.compile(r'[\[({][ \t]|[ \t][\]}),;:](?!=)')
WHITESPACE_AFTER_COMMA_REGEX = re.compile(r'[,;:]\s*(?: |\t)')
COMPARE_SINGLETON_REGEX = re.compile(r'(\bNone|\bFalse|\bTrue)?\s*([=!]=)'
r'\s*(?(1)|(None|False|True))\b')
COMPARE_NEGATIVE_REGEX = re.compile(r'\b(?<!is\s)(not)\s+[^][)(}{ ]+\s+'
r'(in|is)\s')
COMPARE_TYPE_REGEX = re.compile(r'(?:[=!]=|is(?:\s+not)?)\s+type(?:s.\w+Type'
r'|\s*\(\s*([^)]*[^ )])\s*\))')
KEYWORD_REGEX = re.compile(r'(\s*)\b(?:%s)\b(\s*)' % r'|'.join(KEYWORDS))
OPERATOR_REGEX = re.compile(r'(?:[^,\s])(\s*)(?:[-+*/|!<=>%&^]+|:=)(\s*)')
LAMBDA_REGEX = re.compile(r'\blambda\b')
HUNK_REGEX = re.compile(r'^@@ -\d+(?:,\d+)? \+(\d+)(?:,(\d+))? @@.*$')
STARTSWITH_DEF_REGEX = re.compile(r'^(async\s+def|def)\b')
STARTSWITH_TOP_LEVEL_REGEX = re.compile(r'^(async\s+def\s+|def\s+|class\s+|@)')
STARTSWITH_INDENT_STATEMENT_REGEX = re.compile(
r'^\s*({})\b'.format('|'.join(s.replace(' ', r'\s+') for s in (
'def', 'async def',
'for', 'async for',
'if', 'elif', 'else',
'try', 'except', 'finally',
'with', 'async with',
'class',
'while',
)))
)
DUNDER_REGEX = re.compile(r"^__([^\s]+)__(?::\s*[a-zA-Z.0-9_\[\]\"]+)? = ")
BLANK_EXCEPT_REGEX = re.compile(r"except\s*:")
_checks = {'physical_line': {}, 'logical_line': {}, 'tree': {}}
def _get_parameters(function):
return [parameter.name
for parameter
in inspect.signature(function).parameters.values()
if parameter.kind == parameter.POSITIONAL_OR_KEYWORD]
def register_check(check, codes=None):
"""Register a new check object."""
def _add_check(check, kind, codes, args):
if check in _checks[kind]:
_checks[kind][check][0].extend(codes or [])
else:
_checks[kind][check] = (codes or [''], args)
if inspect.isfunction(check):
args = _get_parameters(check)
if args and args[0] in ('physical_line', 'logical_line'):
if codes is None:
codes = ERRORCODE_REGEX.findall(check.__doc__ or '')
_add_check(check, args[0], codes, args)
elif inspect.isclass(check):
if _get_parameters(check.__init__)[:2] == ['self', 'tree']:
_add_check(check, 'tree', codes, None)
return check
########################################################################
# Plugins (check functions) for physical lines
########################################################################
@register_check
def tabs_or_spaces(physical_line, indent_char):
r"""Never mix tabs and spaces.
The most popular way of indenting Python is with spaces only. The
second-most popular way is with tabs only. Code indented with a
mixture of tabs and spaces should be converted to using spaces
exclusively. When invoking the Python command line interpreter with
the -t option, it issues warnings about code that illegally mixes
tabs and spaces. When using -tt these warnings become errors.
These options are highly recommended!
Okay: if a == 0:\n a = 1\n b = 1
E101: if a == 0:\n a = 1\n\tb = 1
"""
indent = INDENT_REGEX.match(physical_line).group(1)
for offset, char in enumerate(indent):
if char != indent_char:
return offset, "E101 indentation contains mixed spaces and tabs"
@register_check
def tabs_obsolete(physical_line):
r"""On new projects, spaces-only are strongly recommended over tabs.
Okay: if True:\n return
W191: if True:\n\treturn
"""
indent = INDENT_REGEX.match(physical_line).group(1)
if '\t' in indent:
return indent.index('\t'), "W191 indentation contains tabs"
@register_check
def trailing_whitespace(physical_line):
r"""Trailing whitespace is superfluous.
The warning returned varies on whether the line itself is blank,
for easier filtering for those who want to indent their blank lines.
Okay: spam(1)\n#
W291: spam(1) \n#
W293: class Foo(object):\n \n bang = 12
"""
physical_line = physical_line.rstrip('\n') # chr(10), newline
physical_line = physical_line.rstrip('\r') # chr(13), carriage return
physical_line = physical_line.rstrip('\x0c') # chr(12), form feed, ^L
stripped = physical_line.rstrip(' \t\v')
if physical_line != stripped:
if stripped:
return len(stripped), "W291 trailing whitespace"
else:
return 0, "W293 blank line contains whitespace"
@register_check
def trailing_blank_lines(physical_line, lines, line_number, total_lines):
r"""Trailing blank lines are superfluous.
Okay: spam(1)
W391: spam(1)\n
However the last line should end with a new line (warning W292).
"""
if line_number == total_lines:
stripped_last_line = physical_line.rstrip('\r\n')
if physical_line and not stripped_last_line:
return 0, "W391 blank line at end of file"
if stripped_last_line == physical_line:
return len(lines[-1]), "W292 no newline at end of file"
@register_check
def maximum_line_length(physical_line, max_line_length, multiline,
line_number, noqa):
r"""Limit all lines to a maximum of 79 characters.
There are still many devices around that are limited to 80 character
lines; plus, limiting windows to 80 characters makes it possible to
have several windows side-by-side. The default wrapping on such
devices looks ugly. Therefore, please limit all lines to a maximum
of 79 characters. For flowing long blocks of text (docstrings or
comments), limiting the length to 72 characters is recommended.
Reports error E501.
"""
line = physical_line.rstrip()
length = len(line)
if length > max_line_length and not noqa:
# Special case: ignore long shebang lines.
if line_number == 1 and line.startswith('#!'):
return
# Special case for long URLs in multi-line docstrings or
# comments, but still report the error when the 72 first chars
# are whitespaces.
chunks = line.split()
if ((len(chunks) == 1 and multiline) or
(len(chunks) == 2 and chunks[0] == '#')) and \
len(line) - len(chunks[-1]) < max_line_length - 7:
return
if length > max_line_length:
return (max_line_length, "E501 line too long "
"(%d > %d characters)" % (length, max_line_length))
########################################################################
# Plugins (check functions) for logical lines
########################################################################
def _is_one_liner(logical_line, indent_level, lines, line_number):
if not STARTSWITH_TOP_LEVEL_REGEX.match(logical_line):
return False
line_idx = line_number - 1
if line_idx < 1:
prev_indent = 0
else:
prev_indent = expand_indent(lines[line_idx - 1])
if prev_indent > indent_level:
return False
while line_idx < len(lines):
line = lines[line_idx].strip()
if not line.startswith('@') and STARTSWITH_TOP_LEVEL_REGEX.match(line):
break
else:
line_idx += 1
else:
return False # invalid syntax: EOF while searching for def/class
next_idx = line_idx + 1
while next_idx < len(lines):
if lines[next_idx].strip():
break
else:
next_idx += 1
else:
return True # line is last in the file
return expand_indent(lines[next_idx]) <= indent_level
@register_check
def blank_lines(logical_line, blank_lines, indent_level, line_number,
blank_before, previous_logical,
previous_unindented_logical_line, previous_indent_level,
lines):
r"""Separate top-level function and class definitions with two blank
lines.
Method definitions inside a class are separated by a single blank
line.
Extra blank lines may be used (sparingly) to separate groups of
related functions. Blank lines may be omitted between a bunch of
related one-liners (e.g. a set of dummy implementations).
Use blank lines in functions, sparingly, to indicate logical
sections.
Okay: def a():\n pass\n\n\ndef b():\n pass
Okay: def a():\n pass\n\n\nasync def b():\n pass
Okay: def a():\n pass\n\n\n# Foo\n# Bar\n\ndef b():\n pass
Okay: default = 1\nfoo = 1
Okay: classify = 1\nfoo = 1
E301: class Foo:\n b = 0\n def bar():\n pass
E302: def a():\n pass\n\ndef b(n):\n pass
E302: def a():\n pass\n\nasync def b(n):\n pass
E303: def a():\n pass\n\n\n\ndef b(n):\n pass
E303: def a():\n\n\n\n pass
E304: @decorator\n\ndef a():\n pass
E305: def a():\n pass\na()
E306: def a():\n def b():\n pass\n def c():\n pass
""" # noqa
top_level_lines = BLANK_LINES_CONFIG['top_level']
method_lines = BLANK_LINES_CONFIG['method']
if not previous_logical and blank_before < top_level_lines:
return # Don't expect blank lines before the first line
if previous_logical.startswith('@'):
if blank_lines:
yield 0, "E304 blank lines found after function decorator"
elif (blank_lines > top_level_lines or
(indent_level and blank_lines == method_lines + 1)
):
yield 0, "E303 too many blank lines (%d)" % blank_lines
elif STARTSWITH_TOP_LEVEL_REGEX.match(logical_line):
# allow a group of one-liners
if (
_is_one_liner(logical_line, indent_level, lines, line_number) and
blank_before == 0
):
return
if indent_level:
if not (blank_before == method_lines or
previous_indent_level < indent_level or
DOCSTRING_REGEX.match(previous_logical)
):
ancestor_level = indent_level
nested = False
# Search backwards for a def ancestor or tree root
# (top level).
for line in lines[line_number - top_level_lines::-1]:
if line.strip() and expand_indent(line) < ancestor_level:
ancestor_level = expand_indent(line)
nested = STARTSWITH_DEF_REGEX.match(line.lstrip())
if nested or ancestor_level == 0:
break
if nested:
yield 0, "E306 expected %s blank line before a " \
"nested definition, found 0" % (method_lines,)
else:
yield 0, "E301 expected {} blank line, found 0".format(
method_lines)
elif blank_before != top_level_lines:
yield 0, "E302 expected %s blank lines, found %d" % (
top_level_lines, blank_before)
elif (logical_line and
not indent_level and
blank_before != top_level_lines and
previous_unindented_logical_line.startswith(('def ', 'class '))
):
yield 0, "E305 expected %s blank lines after " \
"class or function definition, found %d" % (
top_level_lines, blank_before)
@register_check
def extraneous_whitespace(logical_line):
r"""Avoid extraneous whitespace.
Avoid extraneous whitespace in these situations:
- Immediately inside parentheses, brackets or braces.
- Immediately before a comma, semicolon, or colon.
Okay: spam(ham[1], {eggs: 2})
E201: spam( ham[1], {eggs: 2})
E201: spam(ham[ 1], {eggs: 2})
E201: spam(ham[1], { eggs: 2})
E202: spam(ham[1], {eggs: 2} )
E202: spam(ham[1 ], {eggs: 2})
E202: spam(ham[1], {eggs: 2 })
E203: if x == 4: print x, y; x, y = y , x
E203: if x == 4: print x, y ; x, y = y, x
E203: if x == 4 : print x, y; x, y = y, x
"""
line = logical_line
for match in EXTRANEOUS_WHITESPACE_REGEX.finditer(line):
text = match.group()
char = text.strip()
found = match.start()
if text[-1].isspace():
# assert char in '([{'
yield found + 1, "E201 whitespace after '%s'" % char
elif line[found - 1] != ',':
code = ('E202' if char in '}])' else 'E203') # if char in ',;:'
yield found, f"{code} whitespace before '{char}'"
@register_check
def whitespace_around_keywords(logical_line):
r"""Avoid extraneous whitespace around keywords.
Okay: True and False
E271: True and False
E272: True and False
E273: True and\tFalse
E274: True\tand False
"""
for match in KEYWORD_REGEX.finditer(logical_line):
before, after = match.groups()
if '\t' in before:
yield match.start(1), "E274 tab before keyword"
elif len(before) > 1:
yield match.start(1), "E272 multiple spaces before keyword"
if '\t' in after:
yield match.start(2), "E273 tab after keyword"
elif len(after) > 1:
yield match.start(2), "E271 multiple spaces after keyword"
@register_check
def missing_whitespace_after_keyword(logical_line, tokens):
r"""Keywords should be followed by whitespace.
Okay: from foo import (bar, baz)
E275: from foo import(bar, baz)
E275: from importable.module import(bar, baz)
E275: if(foo): bar
"""
for tok0, tok1 in zip(tokens, tokens[1:]):
# This must exclude the True/False/None singletons, which can
# appear e.g. as "if x is None:", and async/await, which were
# valid identifier names in old Python versions.
if (tok0.end == tok1.start and
keyword.iskeyword(tok0.string) and
tok0.string not in SINGLETONS and
tok0.string not in ('async', 'await') and
not (tok0.string == 'except' and tok1.string == '*') and
not (tok0.string == 'yield' and tok1.string == ')') and
tok1.string not in ':\n'):
yield tok0.end, "E275 missing whitespace after keyword"
@register_check
def missing_whitespace(logical_line):
r"""Each comma, semicolon or colon should be followed by whitespace.
Okay: [a, b]
Okay: (3,)
Okay: a[3,] = 1
Okay: a[1:4]
Okay: a[:4]
Okay: a[1:]
Okay: a[1:4:2]
E231: ['a','b']
E231: foo(bar,baz)
E231: [{'a':'b'}]
"""
line = logical_line
for index in range(len(line) - 1):
char = line[index]
next_char = line[index + 1]
if char in ',;:' and next_char not in WHITESPACE:
before = line[:index]
if char == ':' and before.count('[') > before.count(']') and \
before.rfind('{') < before.rfind('['):
continue # Slice syntax, no space required
if char == ',' and next_char in ')]':
continue # Allow tuple with only one element: (3,)
if char == ':' and next_char == '=' and sys.version_info >= (3, 8):
continue # Allow assignment expression
yield index, "E231 missing whitespace after '%s'" % char
@register_check
def indentation(logical_line, previous_logical, indent_char,
indent_level, previous_indent_level,
indent_size):
r"""Use indent_size (PEP8 says 4) spaces per indentation level.
For really old code that you don't want to mess up, you can continue
to use 8-space tabs.
Okay: a = 1
Okay: if a == 0:\n a = 1
E111: a = 1
E114: # a = 1
Okay: for item in items:\n pass
E112: for item in items:\npass
E115: for item in items:\n# Hi\n pass
Okay: a = 1\nb = 2
E113: a = 1\n b = 2
E116: a = 1\n # b = 2
"""
c = 0 if logical_line else 3
tmpl = "E11%d %s" if logical_line else "E11%d %s (comment)"
if indent_level % indent_size:
yield 0, tmpl % (
1 + c,
"indentation is not a multiple of " + str(indent_size),
)
indent_expect = previous_logical.endswith(':')
if indent_expect and indent_level <= previous_indent_level:
yield 0, tmpl % (2 + c, "expected an indented block")
elif not indent_expect and indent_level > previous_indent_level:
yield 0, tmpl % (3 + c, "unexpected indentation")
if indent_expect:
expected_indent_amount = 8 if indent_char == '\t' else 4
expected_indent_level = previous_indent_level + expected_indent_amount
if indent_level > expected_indent_level:
yield 0, tmpl % (7, 'over-indented')
@register_check
def continued_indentation(logical_line, tokens, indent_level, hang_closing,
indent_char, indent_size, noqa, verbose):
r"""Continuation lines indentation.
Continuation lines should align wrapped elements either vertically
using Python's implicit line joining inside parentheses, brackets
and braces, or using a hanging indent.
When using a hanging indent these considerations should be applied:
- there should be no arguments on the first line, and
- further indentation should be used to clearly distinguish itself
as a continuation line.
Okay: a = (\n)
E123: a = (\n )
Okay: a = (\n 42)
E121: a = (\n 42)
E122: a = (\n42)
E123: a = (\n 42\n )
E124: a = (24,\n 42\n)
E125: if (\n b):\n pass
E126: a = (\n 42)
E127: a = (24,\n 42)
E128: a = (24,\n 42)
E129: if (a or\n b):\n pass
E131: a = (\n 42\n 24)
"""
first_row = tokens[0][2][0]
nrows = 1 + tokens[-1][2][0] - first_row
if noqa or nrows == 1:
return
# indent_next tells us whether the next block is indented; assuming
# that it is indented by 4 spaces, then we should not allow 4-space
# indents on the final continuation line; in turn, some other
# indents are allowed to have an extra 4 spaces.
indent_next = logical_line.endswith(':')
row = depth = 0
valid_hangs = (indent_size,) if indent_char != '\t' \
else (indent_size, indent_size * 2)
# remember how many brackets were opened on each line
parens = [0] * nrows
# relative indents of physical lines
rel_indent = [0] * nrows
# for each depth, collect a list of opening rows
open_rows = [[0]]
# for each depth, memorize the hanging indentation
hangs = [None]
# visual indents
indent_chances = {}
last_indent = tokens[0][2]
visual_indent = None
last_token_multiline = False
# for each depth, memorize the visual indent column
indent = [last_indent[1]]
if verbose >= 3:
print(">>> " + tokens[0][4].rstrip())
for token_type, text, start, end, line in tokens:
newline = row < start[0] - first_row
if newline:
row = start[0] - first_row
newline = not last_token_multiline and token_type not in NEWLINE
if newline:
# this is the beginning of a continuation line.
last_indent = start
if verbose >= 3:
print("... " + line.rstrip())
# record the initial indent.
rel_indent[row] = expand_indent(line) - indent_level
# identify closing bracket
close_bracket = (token_type == tokenize.OP and text in ']})')
# is the indent relative to an opening bracket line?
for open_row in reversed(open_rows[depth]):
hang = rel_indent[row] - rel_indent[open_row]
hanging_indent = hang in valid_hangs
if hanging_indent:
break
if hangs[depth]:
hanging_indent = (hang == hangs[depth])
# is there any chance of visual indent?
visual_indent = (not close_bracket and hang > 0 and
indent_chances.get(start[1]))
if close_bracket and indent[depth]:
# closing bracket for visual indent
if start[1] != indent[depth]:
yield (start, "E124 closing bracket does not match "
"visual indentation")
elif close_bracket and not hang:
# closing bracket matches indentation of opening
# bracket's line
if hang_closing:
yield start, "E133 closing bracket is missing indentation"
elif indent[depth] and start[1] < indent[depth]:
if visual_indent is not True:
# visual indent is broken
yield (start, "E128 continuation line "
"under-indented for visual indent")
elif hanging_indent or (indent_next and
rel_indent[row] == 2 * indent_size):
# hanging indent is verified
if close_bracket and not hang_closing:
yield (start, "E123 closing bracket does not match "
"indentation of opening bracket's line")
hangs[depth] = hang
elif visual_indent is True:
# visual indent is verified
indent[depth] = start[1]
elif visual_indent in (text, str):
# ignore token lined up with matching one from a
# previous line
pass
else:
# indent is broken
if hang <= 0:
error = "E122", "missing indentation or outdented"
elif indent[depth]:
error = "E127", "over-indented for visual indent"
elif not close_bracket and hangs[depth]:
error = "E131", "unaligned for hanging indent"
else:
hangs[depth] = hang
if hang > indent_size:
error = "E126", "over-indented for hanging indent"
else:
error = "E121", "under-indented for hanging indent"
yield start, "%s continuation line %s" % error
# look for visual indenting
if (parens[row] and
token_type not in (tokenize.NL, tokenize.COMMENT) and
not indent[depth]):
indent[depth] = start[1]
indent_chances[start[1]] = True
if verbose >= 4:
print(f"bracket depth {depth} indent to {start[1]}")
# deal with implicit string concatenation
elif (token_type in (tokenize.STRING, tokenize.COMMENT) or
text in ('u', 'ur', 'b', 'br')):
indent_chances[start[1]] = str
# visual indent after assert/raise/with
elif not row and not depth and text in ["assert", "raise", "with"]:
indent_chances[end[1] + 1] = True
# special case for the "if" statement because len("if (") == 4
elif not indent_chances and not row and not depth and text == 'if':
indent_chances[end[1] + 1] = True
elif text == ':' and line[end[1]:].isspace():
open_rows[depth].append(row)
# keep track of bracket depth
if token_type == tokenize.OP:
if text in '([{':
depth += 1
indent.append(0)
hangs.append(None)
if len(open_rows) == depth:
open_rows.append([])
open_rows[depth].append(row)
parens[row] += 1
if verbose >= 4:
print("bracket depth %s seen, col %s, visual min = %s" %
(depth, start[1], indent[depth]))
elif text in ')]}' and depth > 0:
# parent indents should not be more than this one
prev_indent = indent.pop() or last_indent[1]
hangs.pop()
for d in range(depth):
if indent[d] > prev_indent:
indent[d] = 0
for ind in list(indent_chances):
if ind >= prev_indent:
del indent_chances[ind]
del open_rows[depth + 1:]
depth -= 1
if depth:
indent_chances[indent[depth]] = True
for idx in range(row, -1, -1):
if parens[idx]:
parens[idx] -= 1
break
assert len(indent) == depth + 1
if start[1] not in indent_chances:
# allow lining up tokens
indent_chances[start[1]] = text
last_token_multiline = (start[0] != end[0])
if last_token_multiline:
rel_indent[end[0] - first_row] = rel_indent[row]
if indent_next and expand_indent(line) == indent_level + indent_size:
pos = (start[0], indent[0] + indent_size)
if visual_indent:
code = "E129 visually indented line"
else:
code = "E125 continuation line"
yield pos, "%s with same indent as next logical line" % code
@register_check
def whitespace_before_parameters(logical_line, tokens):
r"""Avoid extraneous whitespace.
Avoid extraneous whitespace in the following situations:
- before the open parenthesis that starts the argument list of a
function call.
- before the open parenthesis that starts an indexing or slicing.
Okay: spam(1)
E211: spam (1)
Okay: dict['key'] = list[index]
E211: dict ['key'] = list[index]
E211: dict['key'] = list [index]
"""
prev_type, prev_text, __, prev_end, __ = tokens[0]
for index in range(1, len(tokens)):
token_type, text, start, end, __ = tokens[index]
if (
token_type == tokenize.OP and
text in '([' and
start != prev_end and
(prev_type == tokenize.NAME or prev_text in '}])') and
# Syntax "class A (B):" is allowed, but avoid it
(index < 2 or tokens[index - 2][1] != 'class') and
# Allow "return (a.foo for a in range(5))"
not keyword.iskeyword(prev_text) and
# 'match' and 'case' are only soft keywords
(
sys.version_info < (3, 9) or
not keyword.issoftkeyword(prev_text)
)
):
yield prev_end, "E211 whitespace before '%s'" % text
prev_type = token_type
prev_text = text
prev_end = end
@register_check
def whitespace_around_operator(logical_line):
r"""Avoid extraneous whitespace around an operator.
Okay: a = 12 + 3
E221: a = 4 + 5
E222: a = 4 + 5
E223: a = 4\t+ 5
E224: a = 4 +\t5
"""
for match in OPERATOR_REGEX.finditer(logical_line):
before, after = match.groups()
if '\t' in before:
yield match.start(1), "E223 tab before operator"
elif len(before) > 1:
yield match.start(1), "E221 multiple spaces before operator"
if '\t' in after:
yield match.start(2), "E224 tab after operator"
elif len(after) > 1:
yield match.start(2), "E222 multiple spaces after operator"
@register_check
def missing_whitespace_around_operator(logical_line, tokens):
r"""Surround operators with a single space on either side.
- Always surround these binary operators with a single space on
either side: assignment (=), augmented assignment (+=, -= etc.),
comparisons (==, <, >, !=, <=, >=, in, not in, is, is not),
Booleans (and, or, not).
- If operators with different priorities are used, consider adding
whitespace around the operators with the lowest priorities.
Okay: i = i + 1
Okay: submitted += 1
Okay: x = x * 2 - 1
Okay: hypot2 = x * x + y * y
Okay: c = (a + b) * (a - b)
Okay: foo(bar, key='word', *args, **kwargs)
Okay: alpha[:-i]
E225: i=i+1
E225: submitted +=1
E225: x = x /2 - 1
E225: z = x **y
E225: z = 1and 1
E226: c = (a+b) * (a-b)
E226: hypot2 = x*x + y*y
E227: c = a|b
E228: msg = fmt%(errno, errmsg)
"""
parens = 0
need_space = False
prev_type = tokenize.OP
prev_text = prev_end = None
operator_types = (tokenize.OP, tokenize.NAME)
for token_type, text, start, end, line in tokens:
if token_type in SKIP_COMMENTS:
continue
if text in ('(', 'lambda'):
parens += 1
elif text == ')':
parens -= 1
if need_space:
if start != prev_end:
# Found a (probably) needed space
if need_space is not True and not need_space[1]:
yield (need_space[0],
"E225 missing whitespace around operator")
need_space = False
elif text == '>' and prev_text in ('<', '-'):
# Tolerate the "<>" operator, even if running Python 3
# Deal with Python 3's annotated return value "->"
pass
elif (
# def f(a, /, b):
# ^
# def f(a, b, /):
# ^
# f = lambda a, /:
# ^
prev_text == '/' and text in {',', ')', ':'} or
# def f(a, b, /):
# ^
prev_text == ')' and text == ':'
):
# Tolerate the "/" operator in function definition
# For more info see PEP570
pass
else:
if need_space is True or need_space[1]:
# A needed trailing space was not found
yield prev_end, "E225 missing whitespace around operator"
elif prev_text != '**':
code, optype = 'E226', 'arithmetic'
if prev_text == '%':
code, optype = 'E228', 'modulo'
elif prev_text not in ARITHMETIC_OP:
code, optype = 'E227', 'bitwise or shift'
yield (need_space[0], "%s missing whitespace "
"around %s operator" % (code, optype))
need_space = False
elif token_type in operator_types and prev_end is not None:
if text == '=' and parens:
# Allow keyword args or defaults: foo(bar=None).
pass
elif text in WS_NEEDED_OPERATORS:
need_space = True
elif text in UNARY_OPERATORS:
# Check if the operator is used as a binary operator
# Allow unary operators: -123, -x, +1.
# Allow argument unpacking: foo(*args, **kwargs).
if prev_type == tokenize.OP and prev_text in '}])' or (
prev_type != tokenize.OP and
prev_text not in KEYWORDS and (
sys.version_info < (3, 9) or
not keyword.issoftkeyword(prev_text)
)
):
need_space = None
elif text in WS_OPTIONAL_OPERATORS:
need_space = None
if need_space is None:
# Surrounding space is optional, but ensure that
# trailing space matches opening space
need_space = (prev_end, start != prev_end)
elif need_space and start == prev_end:
# A needed opening space was not found
yield prev_end, "E225 missing whitespace around operator"
need_space = False
prev_type = token_type
prev_text = text
prev_end = end
@register_check
def whitespace_around_comma(logical_line):
r"""Avoid extraneous whitespace after a comma or a colon.
Note: these checks are disabled by default
Okay: a = (1, 2)
E241: a = (1, 2)
E242: a = (1,\t2)
"""
line = logical_line
for m in WHITESPACE_AFTER_COMMA_REGEX.finditer(line):
found = m.start() + 1
if '\t' in m.group():
yield found, "E242 tab after '%s'" % m.group()[0]
else:
yield found, "E241 multiple spaces after '%s'" % m.group()[0]
@register_check
def whitespace_around_named_parameter_equals(logical_line, tokens):
r"""Don't use spaces around the '=' sign in function arguments.
Don't use spaces around the '=' sign when used to indicate a
keyword argument or a default parameter value, except when
using a type annotation.
Okay: def complex(real, imag=0.0):
Okay: return magic(r=real, i=imag)
Okay: boolean(a == b)
Okay: boolean(a != b)
Okay: boolean(a <= b)
Okay: boolean(a >= b)
Okay: def foo(arg: int = 42):
Okay: async def foo(arg: int = 42):
E251: def complex(real, imag = 0.0):
E251: return magic(r = real, i = imag)
E252: def complex(real, image: float=0.0):
"""
parens = 0
no_space = False
require_space = False
prev_end = None
annotated_func_arg = False