/usr/share/pyshared/ninja_ide/dependencies/pep8mod.py is in ninja-ide 2.3-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #!/usr/bin/env python
# pep8.py - Check Python source code formatting, according to PEP 8
# Copyright (C) 2006 Johann C. Rocholl <johann@rocholl.net>
#
# 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:
http://www.python.org/dev/peps/pep-0008/
For usage and a list of options, try this:
$ python pep8.py -h
This program and its regression test suite live here:
http://github.com/jcrocholl/pep8
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
You can add checks to this program by writing plugins. Each plugin is
a simple function that is called for each line of source code, either
physical or logical.
Physical line:
- Raw line of text from the input file.
Logical line:
- Multi-line statements converted to a single line.
- Stripped left and right.
- Contents of strings replaced with 'xxx' of same length.
- Comments removed.
The check function requests physical or logical lines by the name of
the first argument:
def maximum_line_length(physical_line)
def extraneous_whitespace(logical_line)
def blank_lines(logical_line, blank_lines, indent_level, line_number)
The last example above demonstrates how check plugins can request
additional information with extra arguments. All attributes of the
Checker object are available. Some examples:
lines: a list of the raw lines from the input file
tokens: the tokens that contribute to this logical line
line_number: line number in the input file
blank_lines: blank lines before this one
indent_char: first indentation character in this file (' ' or '\t')
indent_level: indentation (with tabs expanded to multiples of 8)
previous_indent_level: indentation on previous line
previous_logical: previous logical line
The docstring of each check function shall be the relevant part of
text from PEP 8. It is printed if the user enables --show-pep8.
Several docstrings contain examples directly from the PEP 8 document.
Okay: spam(ham[1], {eggs: 2})
E201: spam( ham[1], {eggs: 2})
These examples are verified automatically when pep8.py is run with the
--doctest option. You can add examples for your own check functions.
The format is simple: "Okay" or error/warning code followed by colon
and space, the rest of the line is example source code. If you put 'r'
before the docstring, you can use \n for newline, \t for tab and \s
for space.
"""
from __future__ import unicode_literals
__version__ = '1.3.4a0'
import os
import sys
import re
import inspect
import keyword
import tokenize
from ninja_ide import resources
DEFAULT_EXCLUDE = '.svn,CVS,.bzr,.hg,.git'
DEFAULT_IGNORE = 'E24'
if sys.platform == 'win32':
DEFAULT_CONFIG = os.path.join(resources.HOME_PATH, r'.pep8')
else:
DEFAULT_CONFIG = os.path.join(os.getenv('XDG_CONFIG_HOME') or
os.path.join(
resources.HOME_PATH, '.config'), 'pep8')
MAX_LINE_LENGTH = 79
REPORT_FORMAT = {
'default': '%(path)s:%(row)d:%(col)d: %(code)s %(text)s',
'pylint': '%(path)s:%(row)d: [%(code)s] %(text)s',
}
SINGLETONS = frozenset(['False', 'None', 'True'])
KEYWORDS = frozenset(keyword.kwlist + ['print']) - SINGLETONS
BINARY_OPERATORS = frozenset([
'**=', '*=', '+=', '-=', '!=', '<>',
'%=', '^=', '&=', '|=', '==', '/=', '//=', '<=', '>=', '<<=', '>>=',
'%', '^', '&', '|', '=', '/', '//', '<', '>', '<<'])
UNARY_OPERATORS = frozenset(['>>', '**', '*', '+', '-'])
OPERATORS = BINARY_OPERATORS | UNARY_OPERATORS
WHITESPACE = frozenset(' \t')
SKIP_TOKENS = frozenset([tokenize.COMMENT, tokenize.NL, tokenize.NEWLINE,
tokenize.INDENT, tokenize.DEDENT])
BENCHMARK_KEYS = ['directories', 'files', 'logical lines', 'physical lines']
INDENT_REGEX = re.compile(r'([ \t]*)')
RAISE_COMMA_REGEX = re.compile(r'raise\s+\w+\s*(,)')
RERAISE_COMMA_REGEX = re.compile(r'raise\s+\w+\s*,\s*\w+\s*,\s*\w+')
SELFTEST_REGEX = re.compile(r'(Okay|[EW]\d{3}):\s(.*)')
ERRORCODE_REGEX = re.compile(r'[EW]\d{3}')
DOCSTRING_REGEX = re.compile(r'u?r?["\']')
EXTRANEOUS_WHITESPACE_REGEX = re.compile(r'[[({] | []}),;:]')
WHITESPACE_AFTER_COMMA_REGEX = re.compile(r'[,;:]\s*(?: |\t)')
COMPARE_SINGLETON_REGEX = re.compile(r'([=!]=)\s*(None|False|True)')
COMPARE_TYPE_REGEX = re.compile(r'([=!]=|is|is\s+not)\s*type(?:s\.(\w+)Type'
r'|\(\s*(\(\s*\)|[^)]*[^ )])\s*\))')
KEYWORD_REGEX = re.compile(r'(?:[^\s])(\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+) @@.*$')
# Work around Python < 2.6 behaviour, which does not generate NL after
# a comment which is on a line by itself.
COMMENT_WITH_NL = tokenize.generate_tokens(['#\n'].pop).send(None)[1] == '#\n'
#Define instance options to set options to be analized
class Options:
pass
options = Options()
#Set the options to be analized
options.show_source = True
options.repeat = True
options.show_pep8 = False
options.messages = {}
options.select = []
options.ignore = []
options.verbose = 0
options.quiet = 0
options.max_line_length = MAX_LINE_LENGTH
options.ignore_continuation_indentation = True
##############################################################################
# Plugins (check functions) for physical lines
##############################################################################
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"
def tabs_obsolete(physical_line):
r"""
For new projects, spaces-only are strongly recommended over tabs. Most
editors have features that make this easy to do.
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"
def trailing_whitespace(physical_line):
r"""
JCR: Trailing whitespace is superfluous.
FBM: Except when it occurs as part of a blank line (i.e. the line is
nothing but whitespace). According to Python docs[1] a line with only
whitespace is considered a blank line, and is to be ignored. However,
matching a blank line to its indentation level avoids mistakenly
terminating a multi-line statement (e.g. class declaration) when
pasting code into the standard Python interpreter.
[1] http://docs.python.org/reference/lexical_analysis.html#blank-lines
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)
W291: spam(1)\s
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"
def trailing_blank_lines(physical_line, lines, line_number):
r"""
JCR: Trailing blank lines are superfluous.
Okay: spam(1)
W391: spam(1)\n
"""
if not physical_line.rstrip() and line_number == len(lines):
return 0, "W391 blank line at end of file"
def missing_newline(physical_line):
"""
JCR: The last line should have a newline.
Reports warning W292.
"""
if physical_line.rstrip() == physical_line:
return len(physical_line), "W292 no newline at end of file"
def maximum_line_length(physical_line, max_line_length):
"""
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:
if hasattr(line, 'decode'): # Python 2
# The line could contain multi-byte characters
try:
length = len(line.decode('utf-8'))
except UnicodeError:
pass
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 blank_lines(logical_line, blank_lines, indent_level, line_number,
previous_logical, previous_indent_level):
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\n# Foo\n# Bar\n\ndef b():\n pass
E301: class Foo:\n b = 0\n def bar():\n pass
E302: def a():\n pass\n\ndef 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
"""
if line_number == 1:
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 > 2 or (indent_level and blank_lines == 2):
yield 0, "E303 too many blank lines (%d)" % blank_lines
elif logical_line.startswith(('def ', 'class ', '@')):
if indent_level:
if not (blank_lines or previous_indent_level < indent_level or
DOCSTRING_REGEX.match(previous_logical)):
yield 0, "E301 expected 1 blank line, found 0"
elif blank_lines != 2:
yield 0, "E302 expected 2 blank lines, found %d" % blank_lines
def extraneous_whitespace(logical_line):
"""
Avoid extraneous whitespace in the following 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 == char + ' ':
# 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, "%s whitespace before '%s'" % (code, char)
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"
def missing_whitespace(logical_line):
"""
JCR: Each comma, semicolon or colon should be followed by whitespace.
Okay: [a, b]
Okay: (3,)
Okay: a[1:4]
Okay: a[:4]
Okay: a[1:]
Okay: a[1:4:2]
E231: ['a','b']
E231: foo(bar,baz)
"""
line = logical_line
for index in range(len(line) - 1):
char = line[index]
if char in ',;:' and line[index + 1] not in WHITESPACE:
before = line[:index]
if char == ':' and before.count('[') > before.count(']'):
continue # Slice syntax, no space required
if char == ',' and line[index + 1] == ')':
continue # Allow tuple with only one element: (3,)
yield index, "E231 missing whitespace after '%s'" % char
def indentation(logical_line, previous_logical, indent_char,
indent_level, previous_indent_level):
r"""
Use 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
Okay: for item in items:\n pass
E112: for item in items:\npass
Okay: a = 1\nb = 2
E113: a = 1\n b = 2
"""
if indent_char == ' ' and indent_level % 4:
yield 0, "E111 indentation is not a multiple of four"
indent_expect = previous_logical.endswith(':')
if indent_expect and indent_level <= previous_indent_level:
yield 0, "E112 expected an indented block"
if indent_level > previous_indent_level and not indent_expect:
yield 0, "E113 unexpected indentation"
def continuation_line_indentation(logical_line, tokens, indent_level, verbose):
r"""
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 the following 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 (a or\n b):\n pass
E126: a = (\n 42)
E127: a = (24,\n 42)
E128: a = (24,\n 42)
"""
if options.ignore_continuation_indentation:
return
first_row = tokens[0][2][0]
nrows = 1 + tokens[-1][2][0] - first_row
if 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
# remember how many brackets were opened on each line
parens = [0] * nrows
# relative indents of physical lines
rel_indent = [0] * nrows
# visual indents
indent = [indent_level]
indent_chances = {}
last_indent = tokens[0][2]
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 (tokenize.NL, tokenize.NEWLINE))
if newline:
# this is the beginning of a continuation line.
last_indent = start
# record the initial indent.
rel_indent[row] = start[1] - indent_level
if depth:
# a bracket expression in a continuation line.
# find the line that it was opened on
for open_row in range(row - 1, -1, -1):
if parens[open_row]:
break
else:
# an unbracketed continuation line (ie, backslash)
open_row = 0
hang = rel_indent[row] - rel_indent[open_row]
visual_indent = indent_chances.get(start[1])
if token_type == tokenize.OP and text in ']})':
# this line starts with a closing bracket
if indent[depth]:
if start[1] != indent[depth]:
yield (start, 'E124 closing bracket does not match '
'visual indentation')
elif hang:
yield (start, 'E123 closing bracket does not match '
'indentation of opening bracket\'s line')
elif visual_indent is True:
# visual indent is verified
if not indent[depth]:
indent[depth] = start[1]
elif visual_indent in (text, str):
# ignore token lined up with matching one from a previous line
pass
elif indent[depth] and start[1] < indent[depth]:
# visual indent is broken
yield (start, 'E128 continuation line '
'under-indented for visual indent')
elif hang == 4 or (indent_next and rel_indent[row] == 8):
# hanging indent is verified
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 hang % 4:
error = 'E121', 'indentation is not a multiple of four'
else:
error = 'E126', 'over-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
# deal with implicit string concatenation
elif token_type == tokenize.STRING or text in ('u', 'ur', 'b', 'br'):
indent_chances[start[1]] = str
# keep track of bracket depth
if token_type == tokenize.OP:
if text in '([{':
depth += 1
indent.append(0)
parens[row] += 1
elif text in ')]}' and depth > 0:
# parent indents should not be more than this one
prev_indent = indent.pop() or last_indent[1]
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]
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 to line up tokens
indent_chances[start[1]] = text
last_token_multiline = (start[0] != end[0])
if indent_next and rel_indent[-1] == 4:
yield (last_indent, "E125 continuation line does not distinguish "
"itself from next logical line")
def whitespace_before_parameters(logical_line, tokens):
"""
Avoid extraneous whitespace in the following situations:
- Immediately before the open parenthesis that starts the argument
list of a function call.
- Immediately 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 = tokens[0][0]
prev_text = tokens[0][1]
prev_end = tokens[0][3]
for index in range(1, len(tokens)):
token_type, text, start, end, line = 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)):
yield prev_end, "E211 whitespace before '%s'" % text
prev_type = token_type
prev_text = text
prev_end = end
def whitespace_around_operator(logical_line):
r"""
Avoid extraneous whitespace in the following situations:
- More than one space around an assignment (or other) operator to
align it with another.
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"
def missing_whitespace_around_operator(logical_line, tokens):
r"""
- 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).
- Use spaces around arithmetic operators.
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: baz(**kwargs)
Okay: negative = -1
Okay: spam(-1)
Okay: alpha[:-i]
Okay: if not -5 < x < +5:\n pass
Okay: lambda *args, **kw: (args, kw)
E225: i=i+1
E225: submitted +=1
E225: x = x*2 - 1
E225: hypot2 = x*x + y*y
E225: c = (a+b) * (a-b)
E225: c = alpha -4
E225: z = x **y
"""
parens = 0
need_space = False
prev_type = tokenize.OP
prev_text = prev_end = None
for token_type, text, start, end, line in tokens:
if token_type in (tokenize.NL, tokenize.NEWLINE, tokenize.ERRORTOKEN):
# ERRORTOKEN is triggered by backticks in Python 3000
continue
if text in ('(', 'lambda'):
parens += 1
elif text == ')':
parens -= 1
if need_space:
if start != prev_end:
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
else:
yield prev_end, "E225 missing whitespace around operator"
need_space = False
elif token_type == tokenize.OP and prev_end is not None:
if text == '=' and parens:
# Allow keyword args or defaults: foo(bar=None).
pass
elif text in BINARY_OPERATORS:
need_space = True
elif text in UNARY_OPERATORS:
# Allow unary operators: -123, -x, +1.
# Allow argument unpacking: foo(*args, **kwargs).
if prev_type == tokenize.OP:
if prev_text in '}])':
need_space = True
elif prev_type == tokenize.NAME:
if prev_text not in KEYWORDS:
need_space = True
elif prev_type not in SKIP_TOKENS:
need_space = True
if need_space and start == prev_end:
yield prev_end, "E225 missing whitespace around operator"
need_space = False
prev_type = token_type
prev_text = text
prev_end = end
def whitespace_around_comma(logical_line):
r"""
Avoid extraneous whitespace in the following situations:
- More than one space around an assignment (or other) operator to
align it with another.
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]
def whitespace_around_named_parameter_equals(logical_line, tokens):
"""
Don't use spaces around the '=' sign when used to indicate a
keyword argument or a default parameter value.
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)
E251: def complex(real, imag = 0.0):
E251: return magic(r = real, i = imag)
"""
parens = 0
no_space = False
prev_end = None
for token_type, text, start, end, line in tokens:
if no_space:
no_space = False
if start != prev_end:
yield (prev_end,
"E251 no spaces around keyword / parameter equals")
elif token_type == tokenize.OP:
if text == '(':
parens += 1
elif text == ')':
parens -= 1
elif parens and text == '=':
no_space = True
if start != prev_end:
yield (prev_end,
"E251 no spaces around keyword / parameter equals")
prev_end = end
def whitespace_before_inline_comment(logical_line, tokens):
"""
Separate inline comments by at least two spaces.
An inline comment is a comment on the same line as a statement. Inline
comments should be separated by at least two spaces from the statement.
They should start with a # and a single space.
Okay: x = x + 1 # Increment x
Okay: x = x + 1 # Increment x
E261: x = x + 1 # Increment x
E262: x = x + 1 #Increment x
E262: x = x + 1 # Increment x
"""
prev_end = (0, 0)
for token_type, text, start, end, line in tokens:
if token_type == tokenize.COMMENT:
if not line[:start[1]].strip():
continue
if prev_end[0] == start[0] and start[1] < prev_end[1] + 2:
yield (prev_end,
"E261 at least two spaces before inline comment")
if text.startswith('# ') or not text.startswith('# '):
yield start, "E262 inline comment should start with '# '"
elif token_type != tokenize.NL:
prev_end = end
def imports_on_separate_lines(logical_line):
r"""
Imports should usually be on separate lines.
Okay: import os\nimport sys
E401: import sys, os
Okay: from subprocess import Popen, PIPE
Okay: from myclas import MyClass
Okay: from foo.bar.yourclass import YourClass
Okay: import myclass
Okay: import foo.bar.yourclass
"""
line = logical_line
if line.startswith('import '):
found = line.find(',')
if -1 < found and ';' not in line[:found]:
yield found, "E401 multiple imports on one line"
def compound_statements(logical_line):
r"""
Compound statements (multiple statements on the same line) are
generally discouraged.
While sometimes it's okay to put an if/for/while with a small body
on the same line, never do this for multi-clause statements. Also
avoid folding such long lines!
Okay: if foo == 'blah':\n do_blah_thing()
Okay: do_one()
Okay: do_two()
Okay: do_three()
E701: if foo == 'blah': do_blah_thing()
E701: for x in lst: total += x
E701: while t < 10: t = delay()
E701: if foo == 'blah': do_blah_thing()
E701: else: do_non_blah_thing()
E701: try: something()
E701: finally: cleanup()
E701: if foo == 'blah': one(); two(); three()
E702: do_one(); do_two(); do_three()
"""
line = logical_line
found = line.find(':')
if -1 < found < len(line) - 1:
before = line[:found]
if (before.count('{') <= before.count('}') and # {'a': 1} (dict)
before.count('[') <= before.count(']') and # [1:2] (slice)
before.count('(') <= before.count(')') and # (Python 3 annotation)
not LAMBDA_REGEX.search(before)): # lambda x: x
yield found, "E701 multiple statements on one line (colon)"
found = line.find(';')
if -1 < found:
yield found, "E702 multiple statements on one line (semicolon)"
def explicit_line_join(logical_line, tokens):
r"""
Avoid explicit line join between brackets.
The preferred way of wrapping long lines is by using Python's implied line
continuation inside parentheses, brackets and braces. Long lines can be
broken over multiple lines by wrapping expressions in parentheses. These
should be used in preference to using a backslash for line continuation.
E502: aaa = [123, \\n 123]
E502: aaa = ("bbb " \\n "ccc")
Okay: aaa = [123,\n 123]
Okay: aaa = ("bbb "\n "ccc")
Okay: aaa = "bbb " \\n "ccc"
"""
prev_start = prev_end = parens = 0
for token_type, text, start, end, line in tokens:
if start[0] != prev_start and parens and backslash:
yield backslash, "E502 the backslash is redundant between brackets"
if end[0] != prev_end:
if line.rstrip('\r\n').endswith('\\'):
backslash = (end[0], len(line.splitlines()[-1]) - 1)
else:
backslash = None
prev_start = prev_end = end[0]
else:
prev_start = start[0]
if token_type == tokenize.OP:
if text in '([{':
parens += 1
elif text in ')]}':
parens -= 1
def comparison_to_singleton(logical_line):
"""
Comparisons to singletons like None should always be done
with "is" or "is not", never the equality operators.
Okay: if arg is not None:
E711: if arg != None:
E712: if arg == True:
Also, beware of writing if x when you really mean if x is not None --
e.g. when testing whether a variable or argument that defaults to None was
set to some other value. The other value might have a type (such as a
container) that could be false in a boolean context!
"""
match = COMPARE_SINGLETON_REGEX.search(logical_line)
if match:
same = (match.group(1) == '==')
singleton = match.group(2)
msg = "'if cond is %s:'" % (('' if same else 'not ') + singleton)
if singleton in ('None',):
code = 'E711'
else:
code = 'E712'
nonzero = ((singleton == 'True' and same) or
(singleton == 'False' and not same))
msg += " or 'if %scond:'" % ('' if nonzero else 'not ')
yield match.start(1), ("%s comparison to %s should be %s" %
(code, singleton, msg))
def comparison_type(logical_line):
"""
Object type comparisons should always use isinstance() instead of
comparing types directly.
Okay: if isinstance(obj, int):
E721: if type(obj) is type(1):
When checking if an object is a string, keep in mind that it might be a
unicode string too! In Python 2.3, str and unicode have a common base
class, basestring, so you can do:
Okay: if isinstance(obj, basestring):
Okay: if type(a1) is type(b1):
"""
match = COMPARE_TYPE_REGEX.search(logical_line)
if match:
inst = match.group(3)
if inst and isidentifier(inst) and inst not in SINGLETONS:
return # Allow comparison for types which are not obvious
yield match.start(1), "E721 do not compare types, use 'isinstance()'"
def python_3000_has_key(logical_line):
r"""
The {}.has_key() method will be removed in the future version of
Python. Use the 'in' operation instead.
Okay: if "alph" in d:\n print d["alph"]
W601: assert d.has_key('alph')
"""
pos = logical_line.find('.has_key(')
if pos > -1:
yield pos, "W601 .has_key() is deprecated, use 'in'"
def python_3000_raise_comma(logical_line):
"""
When raising an exception, use "raise ValueError('message')"
instead of the older form "raise ValueError, 'message'".
The paren-using form is preferred because when the exception arguments
are long or include string formatting, you don't need to use line
continuation characters thanks to the containing parentheses. The older
form will be removed in Python 3000.
Okay: raise DummyError("Message")
W602: raise DummyError, "Message"
"""
match = RAISE_COMMA_REGEX.match(logical_line)
if match and not RERAISE_COMMA_REGEX.match(logical_line):
yield match.start(1), "W602 deprecated form of raising exception"
def python_3000_not_equal(logical_line):
"""
!= can also be written <>, but this is an obsolete usage kept for
backwards compatibility only. New code should always use !=.
The older syntax is removed in Python 3000.
Okay: if a != 'no':
W603: if a <> 'no':
"""
pos = logical_line.find('<>')
if pos > -1:
yield pos, "W603 '<>' is deprecated, use '!='"
def python_3000_backticks(logical_line):
"""
Backticks are removed in Python 3000.
Use repr() instead.
Okay: val = repr(1 + 2)
W604: val = `1 + 2`
"""
pos = logical_line.find('`')
if pos > -1:
yield pos, "W604 backticks are deprecated, use 'repr()'"
##############################################################################
# Helper functions
##############################################################################
if '' == ''.encode():
# Python 2: implicit encoding.
isidentifier = re.compile(r'[a-zA-Z_]\w*').match
else:
# Python 3
isidentifier = str.isidentifier
def expand_indent(line):
r"""
Return the amount of indentation.
Tabs are expanded to the next multiple of 8.
>>> expand_indent(' ')
4
>>> expand_indent('\t')
8
>>> expand_indent(' \t')
8
>>> expand_indent(' \t')
8
>>> expand_indent(' \t')
16
"""
if '\t' not in line:
return len(line) - len(line.lstrip())
result = 0
for char in line:
if char == '\t':
result = result // 8 * 8 + 8
elif char == ' ':
result += 1
else:
break
return result
def mute_string(text):
"""
Replace contents with 'xxx' to prevent syntax matching.
>>> mute_string('"abc"')
'"xxx"'
>>> mute_string("'''abc'''")
"'''xxx'''"
>>> mute_string("r'abc'")
"r'xxx'"
"""
# String modifiers (e.g. u or r)
start = text.index(text[-1]) + 1
end = len(text) - 1
# Triple quotes
if text[-3:] in ('"""', "'''"): # '''
start += 2
end -= 2
return text[:start] + 'x' * (end - start) + text[end:]
##############################################################################
# Framework to run all checks
##############################################################################
def find_checks(argument_name):
"""
Find all globally visible functions where the first argument name
starts with argument_name.
"""
checks = []
for name, function in list(globals().items()):
if not inspect.isfunction(function):
continue
args = inspect.getargspec(function)[0]
if args and args[0].startswith(argument_name):
codes = ERRORCODE_REGEX.findall(function.__doc__ or '')
# yield name, codes, function, args
for code in codes or ['']:
if not code or not ignore_code(code):
checks.append((name, function, args))
break
checks.sort()
return checks
def ignore_code(code):
"""
Check if options.ignore contains a prefix of the error code.
If options.select contains a prefix of the error code, do not ignore it.
"""
for select in options.select:
if code.startswith(select):
return False
for ignore in options.ignore:
if code.startswith(ignore):
return True
#Set Physical and Logical check functions
options.physical_checks = find_checks('physical_line')
options.logical_checks = find_checks('logical_line')
def refresh_checks():
#Refresh the Physical and Logical check functions
options.physical_checks = find_checks('physical_line')
options.logical_checks = find_checks('logical_line')
class Checker(object):
"""
Load a Python source file, tokenize it, check coding style.
"""
def __init__(self, filename, lines=None):
self._physical_checks = options.physical_checks
self._logical_checks = options.logical_checks
self.max_line_length = options.max_line_length
self.verbose = options.verbose
self.filename = filename
self.lines = lines
self.results = []
def readline(self):
"""
Get the next line from the input buffer.
"""
self.line_number += 1
if self.line_number > len(self.lines):
return ''
return self.lines[self.line_number - 1]
def readline_check_physical(self):
"""
Check and return the next physical line. This method can be
used to feed tokenize.generate_tokens.
"""
line = self.readline()
if line:
self.check_physical(line)
return line
def run_check(self, check, argument_names):
"""
Run a check plugin.
"""
arguments = []
for name in argument_names:
arguments.append(getattr(self, name))
return check(*arguments)
def check_physical(self, line):
"""
Run all physical checks on a raw input line.
"""
self.physical_line = line
if self.indent_char is None and line[:1] in WHITESPACE:
self.indent_char = line[0]
for name, check, argument_names in self._physical_checks:
result = self.run_check(check, argument_names)
if result is not None:
offset, text = result
self.report_error(self.line_number, offset, text, check)
def build_tokens_line(self):
"""
Build a logical line from tokens.
"""
self.mapping = []
logical = []
length = 0
previous = None
for token in self.tokens:
token_type, text = token[0:2]
if token_type in SKIP_TOKENS:
continue
if token_type == tokenize.STRING:
text = mute_string(text)
if previous:
end_row, end = previous[3]
start_row, start = token[2]
if end_row != start_row: # different row
prev_text = self.lines[end_row - 1][end - 1]
if prev_text == ',' or (prev_text not in '{[('
and text not in '}])'):
logical.append(' ')
length += 1
elif end != start: # different column
fill = self.lines[end_row - 1][end:start]
logical.append(fill)
length += len(fill)
self.mapping.append((length, token))
logical.append(text)
length += len(text)
previous = token
self.logical_line = ''.join(logical)
assert self.logical_line.strip() == self.logical_line
def check_logical(self):
"""
Build a line from tokens and run all logical checks on it.
"""
self.build_tokens_line()
first_line = self.lines[self.mapping[0][1][2][0] - 1]
indent = first_line[:self.mapping[0][1][2][1]]
self.previous_indent_level = self.indent_level
self.indent_level = expand_indent(indent)
for name, check, argument_names in self._logical_checks:
for result in self.run_check(check, argument_names):
offset, text = result
if isinstance(offset, tuple):
orig_number, orig_offset = offset
else:
for token_offset, token in self.mapping:
if offset >= token_offset:
orig_number = token[2][0]
orig_offset = (token[2][1] + offset - token_offset)
self.report_error(orig_number, orig_offset, text, check)
self.previous_logical = self.logical_line
def generate_tokens(self):
tokengen = tokenize.generate_tokens(self.readline_check_physical)
try:
for token in tokengen:
yield token
except (SyntaxError, tokenize.TokenError):
exc_type, exc = sys.exc_info()[:2]
offset = exc.args[1]
if len(offset) > 2:
offset = offset[1:3]
self.report_error(offset[0], offset[1],
'E901 %s: %s' % (exc_type.__name__, exc.args[0]),
self.generate_tokens)
generate_tokens.__doc__ = " Check if the syntax is valid."
def check_all(self, expected=None, line_offset=0):
"""
Run all checks on the input file.
"""
self.line_number = 0
self.line_offset = line_offset
self.indent_char = None
self.indent_level = 0
self.previous_logical = ''
self.tokens = []
self.blank_lines = blank_lines_before_comment = 0
parens = 0
for token in self.generate_tokens():
self.tokens.append(token)
token_type, text = token[0:2]
if self.verbose >= 3:
if token[2][0] == token[3][0]:
pos = '[%s:%s]' % (token[2][1] or '', token[3][1])
else:
pos = 'l.%s' % token[3][0]
if token_type == tokenize.OP:
if text in '([{':
parens += 1
elif text in '}])':
parens -= 1
elif not parens:
if token_type == tokenize.NEWLINE:
if self.blank_lines < blank_lines_before_comment:
self.blank_lines = blank_lines_before_comment
self.check_logical()
self.tokens = []
self.blank_lines = blank_lines_before_comment = 0
elif token_type == tokenize.NL:
if len(self.tokens) == 1:
# The physical line contains only this token.
self.blank_lines += 1
self.tokens = []
elif token_type == tokenize.COMMENT and len(self.tokens) == 1:
if blank_lines_before_comment < self.blank_lines:
blank_lines_before_comment = self.blank_lines
self.blank_lines = 0
if COMMENT_WITH_NL:
# The comment also ends a physical line
self.tokens = []
return self.results
def report_error(self, line_number, offset, text, check):
"""
Report an error, according to options.
"""
if options.repeat:
self.results.append("%s:%s:%d: %s" %
(self.filename, self.line_offset + line_number,
offset + 1, text))
if options.show_source and len(self.lines) >= line_number:
line = self.lines[line_number - 1]
self.results.append(line.rstrip())
self.results.append(' ' * offset + '^')
if options.show_pep8:
self.results.append(check.__doc__.lstrip('\n').rstrip())
def run_check(fileName, source):
"""
Parse options and run checks on Python source.
"""
try:
lines = ['%s\n' % line for line in source.splitlines()]
return Checker(fileName, lines).check_all()
except Exception as reason:
print(('pep8mod couldn\'t parse file: {0}'.format(fileName)))
print(reason)
raise
return []
|