/usr/lib/python3/dist-packages/sixer.py is in sixer 1.6-2.
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 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 | #!/usr/bin/env python3
import collections
import functools
import optparse
import os
import re
import sys
import tokenize
# Maximum range which creates a list on Python 2. For example, xrange(10) can
# be replaced with range(10) without "from six.moves import range".
MAX_RANGE = 1024
# Modules of the Python standard library
STDLIB_MODULES = set((
"StringIO",
"copy",
"csv",
"datetime",
"glob",
"heapq",
"importlib",
"itertools",
"json",
"logging",
"os",
"re",
"socket",
"string",
"sys",
"textwrap",
"traceback",
"types",
"unittest",
"urlparse",
))
# Name of third-party modules
THIRD_PARTY_MODULES = [
"django",
"eventlet",
"iso8601",
"keystoneclient",
"numpy",
"mock",
"mox3",
"oslo_concurrency",
"oslo_config",
"oslo_db",
"oslo_i18n",
"oslo_log",
"oslo_messaging",
"oslo_middleware",
"oslo_rootwrap",
"oslo_serialization",
"oslo_utils",
"oslotest",
"selenium",
"six",
"subunit",
"testtools",
"webob",
"wsme",
]
# Modules of the application
APPLICATION_MODULES = set((
"ceilometer",
"cinder",
"congress",
"glance",
"glance_store",
"horizon",
"neutron",
"nova",
"openstack_dashboard",
"swift",
))
# Ugly regular expressions because I'm too lazy to write a real parser,
# and Match objects are convinient to modify code in-place
def import_regex(name):
# 'import test\n', 'import test\n\n'
# but not ony match 'import test\n' in 'import test\n\nimport test\n'
# (don't match the second newline if it's followed by an import)
regex = r"^import %s\n(?:\n(?!from|import))?" % name
return re.compile(regex, re.MULTILINE)
def from_import_regex(module, symbol):
# 'from test import symbol\n', 'from test import symbol\n\n'
# but not ony match 'from test import symbol\n' in 'from test import symbol\n\nimport test2'
# (don't match the second newline if it's followed by an import)
regex = r"^from %s import %s\n(?:\n(?!from|import))?" % (module, symbol)
return re.compile(regex, re.MULTILINE)
# 'identifier', 'var3', 'NameCamelCase'
IDENTIFIER_REGEX = r'[a-zA-Z_][a-zA-Z0-9_]*'
# 'name', 'module.name'
QUALNAME_REGEX = r'%s(?:\.%s)*' % (IDENTIFIER_REGEX, IDENTIFIER_REGEX)
# '[0]'
GETITEM_REGEX = r'\[[^]]+\]'
# '()' or '(obj, {})', don't support nested calls: 'f(g())'
CALL_REGEX = r'\([^()]*\)'
# '[0]' or '(obj, {})' or '()[key]'
SUFFIX_REGEX = r'(?:%s|%s)' % (GETITEM_REGEX, CALL_REGEX)
# 'var' or 'var[0]' or 'func()' or 'func()[0]'
SUBEXPR_REGEX = r'%s(?:%s)*' % (IDENTIFIER_REGEX, SUFFIX_REGEX)
# 'inst' or 'self.attr' or 'self.attr[0]'
EXPR_REGEX = r'%s(?:\.%s)*' % (SUBEXPR_REGEX, SUBEXPR_REGEX)
# '"hello"', "'hello'"
_QUOTE1_STRING_REGEX = r'"(?:[^"\\]|\\[tn"])*"'
_QUOTE2_STRING_REGEX = r"'(?:[^'\\]|\\[tn'])*'"
STRING_REGEX = r'(?:%s|%s)' % (_QUOTE1_STRING_REGEX, _QUOTE2_STRING_REGEX)
_EXPR_STRING_REGEX = '(?:%s|%s)' % (EXPR_REGEX, STRING_REGEX)
# [a, b, c]
LIST_REGEX = (r'\[ *%s *(?:, *%s *)*\]'
% (_EXPR_STRING_REGEX,
_EXPR_STRING_REGEX))
# (a,)
_TUPLE1_REGEX = r'\( *%s *, *\)' % _EXPR_STRING_REGEX
# (a, b, c)
_TUPLEN_REGEX = (r'\( *%s *(?:, *%s *)+\)'
% (_EXPR_STRING_REGEX, _EXPR_STRING_REGEX))
# expr, 'string', (a, b, c), [a, b, c]
EXPR_STRING_REGEX = ('(?:%s)'
% '|'.join((EXPR_REGEX, STRING_REGEX, LIST_REGEX,
_TUPLE1_REGEX, _TUPLEN_REGEX)))
# '(...)'
SUBPARENT_REGEX= r'\([^()]+\)'
# '(...)' or '(...(...)...)' (max: 1 level of nested parenthesis)
PARENT_REGEX = r'\([^()]*(?:%s)?[^()]*\)' % SUBPARENT_REGEX
IMPORT_GROUP_REGEX = re.compile(r"^(?:import|from) .*\n(?:(?:import|from) .*\n)*\n*",
re.MULTILINE)
IMPORT_NAME_REGEX = re.compile(r"^(?:import|from) (%s)" % IDENTIFIER_REGEX,
re.MULTILINE)
# 'abc', 'sym1, sym2'
FROM_IMPORT_SYMBOLS_REGEX = r"%s(?:, %s)*" % (IDENTIFIER_REGEX, IDENTIFIER_REGEX)
def parse_import_groups(content):
pos = 0
import_groups = []
while True:
match = IMPORT_GROUP_REGEX.search(content, pos)
if not match:
break
import_group = match.group(0)
imports = [match.group(1)
for match in IMPORT_NAME_REGEX.finditer(import_group)]
import_groups.append((match.start(), match.end(), set(imports)))
pos = match.end()
return import_groups
def parse_import(line):
line = line.strip()
if line.startswith("import "):
return line[7:].split(".")
elif line.startswith("from "):
pos = 5
pos2 = line.find(" import ", pos)
names = line[pos:pos2].split(".")
names.append(line[pos2+len(" import "):])
return names
else:
raise SyntaxError("unable to parse import %r" % line)
def get_line(content, pos):
eol = content.find("\n", pos)
return content[pos:eol + 1]
class Operation:
NAME = "<name>"
DOC = "<doc>"
def __init__(self, patcher):
self.patcher = patcher
self.options = patcher.options
def patch(self, content):
raise NotImplementedError
def check(self, content):
raise NotImplementedError
def warning(self, message):
message = ("[%s] %s: %s"
% (self.NAME, self.patcher.current_file, message))
self.patcher.warning(message)
def warn_line(self, line):
self.warning(line.strip())
class Iteritems(Operation):
NAME = "iteritems"
DOC = "replace dict.iteritems() with six.iteritems(dict)"
REGEX = re.compile(r"(%s)\.iteritems\(\)" % EXPR_REGEX)
CHECK_REGEX = re.compile(r"^.*\biteritems *\(.*$", re.MULTILINE)
def replace(self, regs):
return 'six.iteritems(%s)' % regs.group(1)
def patch(self, content):
new_content = self.REGEX.sub(self.replace, content)
if new_content == content:
return content
return self.patcher.add_import_six(new_content)
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
if "six.iteritems" not in line:
self.warn_line(line)
class Itervalues(Operation):
NAME = "itervalues"
DOC = "replace dict.itervalues() with six.itervalues(dict)"
REGEX = re.compile(r"(%s)\.itervalues\(\)" % EXPR_REGEX)
CHECK_REGEX = re.compile(r"^.*\bitervalues *\(.*$", re.MULTILINE)
def replace(self, regs):
return 'six.itervalues(%s)' % regs.group(1)
def patch(self, content):
new_content = self.REGEX.sub(self.replace, content)
if new_content == content:
return content
return self.patcher.add_import_six(new_content)
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
if "six.itervalues" not in line:
self.warn_line(line)
class HasKey(Operation):
NAME = "has_key"
DOC = "replace dict.has_key(key) with 'key in dict'"
REGEX = re.compile(r"(%s)\.has_key\((%s)\)" % (EXPR_REGEX, EXPR_REGEX))
CHECK_REGEX = re.compile(r"^.*\.has_key", re.MULTILINE)
def replace(self, regs):
return '%s in %s' % (regs.group(2), regs.group(1))
def patch(self, content):
return self.REGEX.sub(self.replace, content)
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
if "six.iterkeys" not in line:
self.warn_line(line)
class Iterkeys(Operation):
NAME = "iterkeys"
DOC = ("replace 'for key in dict.iterkeys():' with 'for key in dict:',"
"replace dict.iterkeys() with six.iterkeys(dict)")
FOR_REGEX = re.compile(r"(for %s in %s)\.iterkeys\(\):"
% (EXPR_REGEX, EXPR_REGEX))
REGEX = re.compile(r"(%s)\.iterkeys\(\)" % EXPR_REGEX)
CHECK_REGEX = re.compile(r"^.*\biterkeys *\(.*$", re.MULTILINE)
def replace_for(self, regs):
return '%s:' % regs.group(1)
def replace(self, regs):
return 'six.iterkeys(%s)' % regs.group(1)
def patch(self, content):
content = self.FOR_REGEX.sub(self.replace_for, content)
new_content = self.REGEX.sub(self.replace, content)
if new_content != content:
content = self.patcher.add_import_six(new_content)
return content
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
if "six.iterkeys" not in line:
self.warn_line(line)
class Next(Operation):
NAME = "next"
DOC = "replace it.next() with next(it)"
# Match 'gen.next()' and '(...).next()'
REGEX = re.compile(r"(%s|%s)\.next\(\)" % (EXPR_REGEX, PARENT_REGEX))
# '.next(' but not 'six.next('
CHECK_REGEX = re.compile(r"^.*(?<!six)\.next *\(.*$", re.MULTILINE)
# 'def next('
DEF_NEXT_LINE_REGEX = re.compile(r"^.*def next *\(.*$", re.MULTILINE)
def replace(self, regs):
expr = regs.group(1)
if expr.startswith('(') and expr.endswith(')'):
expr = expr[1:-1]
return 'next(%s)' % expr
def patch(self, content):
return self.REGEX.sub(self.replace, content)
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
self.warn_line(match.group(0))
for match in self.DEF_NEXT_LINE_REGEX.finditer(content):
self.warn_line(match.group(0))
class Long(Operation):
NAME = "long"
DOC = ("replace 123L with 123, "
"replace (int, long) with six.integer_types, "
"replace long(1) with 1")
# (int, long)
INT_LONG_REGEX = re.compile(r'\(int, *long\)')
# '123L', '0xFFL' but not '0123L'
REGEX_INT_L = re.compile(r"\b([1-9][0-9]*|0x[0-9A-Fa-f]+|0)[lL]")
# '0123L', '0600l'
OCTAL_REGEX = re.compile(r"\b0([0-9]*)[lL]")
# '0123L', '0600l'
LONG_INT_REGEX = re.compile(r"\blong *\(([0-9]*)\)")
# '123L', '123l', '0123L'
CHECK_REGEX = re.compile(r"^.*\b(?:Ox)?[0-9]+[lL].*$", re.MULTILINE)
def replace_int_l(self, regs):
return regs.group(1)
def replace_octal(self, regs):
return '0o%s' % regs.group(1)
def replace_long_int(self, regs):
return regs.group(1)
def patch(self, content):
content = self.REGEX_INT_L.sub(self.replace_int_l, content)
content = self.OCTAL_REGEX.sub(self.replace_octal, content)
content = self.LONG_INT_REGEX.sub(self.replace_long_int, content)
new_content = self.INT_LONG_REGEX.sub('six.integer_types', content)
if new_content != content:
content = self.patcher.add_import_six(new_content)
return content
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
self.warn_line(match.group(0))
class Unicode(Operation):
NAME = "unicode"
DOC = ("replace unicode with six.text_type,"
"replace (str, unicode) with six.string_types")
UNICODE_REGEX = re.compile(r'\bunicode\b')
STR_UNICODE_REGEX = re.compile(r'\(str, *unicode\)')
DEF_REGEX = re.compile(r'^ *def +%s *\(' % IDENTIFIER_REGEX, re.MULTILINE)
def _patch_line(self, line, start, end):
result = None
while True:
match = self.UNICODE_REGEX.search(line, start, end)
if not match:
return result
line = line[:match.start()] + "six.text_type" + line[match.end():]
result = line
start = match.start() + len("six.text_type")
end += len("six.text_type") - len("unicode")
def patch_unicode(self, content):
# replace unicode with six.text_type
lines = content.splitlines(True)
for index, line in enumerate(lines):
# Ugly heuristic to exclude "import ...", "from ... import ...",
# function name in "def ...(", comments and strings
# declared with """
if line.startswith(("import ", "from ")):
continue
start = 0
end = line.find("#")
if end < 0:
end = len(line)
pos = line.find('"""', start, end)
if pos != -1:
end = pos
match = self.DEF_REGEX.search(line, start, end)
if match:
start = match.end()
new_line = self._patch_line(line, start, end)
if new_line is not None:
lines[index] = new_line
return ''.join(lines)
def patch(self, content):
old_content = content
content = self.STR_UNICODE_REGEX.sub('six.string_types', content)
content = self.patch_unicode(content)
if content != old_content:
content = self.patcher.add_import_six(content)
return content
def check(self, content):
for line in content.splitlines():
end = line.find("#")
if end >= 0:
match = self.UNICODE_REGEX.search(line, 0, end)
else:
match = self.UNICODE_REGEX.search(line, 0)
if match:
self.warn_line(line)
class Xrange(Operation):
NAME = "xrange"
DOC = "replace xrange() with range() using 'from six import range'"
# 'xrange(' but not 'moves.xrange(' or 'from six.moves import xrange'
XRANGE_REGEX = re.compile("(?<!moves\.)xrange *\(")
# 'xrange(2)'
XRANGE1_REGEX = re.compile(r"(?<!moves\.)xrange\(([0-9]+)\)")
# 'xrange(1, 6)'
XRANGE2_REGEX = re.compile(r"(?<!moves\.)xrange\(([0-9]+), ([0-9]+)\)")
def patch(self, content):
need_six = False
def xrange1_replace(regs):
nonlocal need_six
end = int(regs.group(1))
if end > self.options.max_range:
need_six = True
return 'range(%s)' % end
def xrange2_replace(regs):
nonlocal need_six
start = int(regs.group(1))
end = int(regs.group(2))
if (end - start) > self.options.max_range:
need_six = True
return 'range(%s, %s)' % (start, end)
new_content = self.XRANGE1_REGEX.sub(xrange1_replace, content)
new_content = self.XRANGE2_REGEX.sub(xrange2_replace, new_content)
new_content2 = self.XRANGE_REGEX.sub("range(", new_content)
if new_content2 != new_content:
need_six = True
new_content = new_content2
if need_six:
new_content = self.patcher.add_import(new_content, 'from six.moves import range')
return new_content
def check(self, content):
for line in content.splitlines():
if self.XRANGE_REGEX.search(line):
self.warn_line(line)
class Basestring(Operation):
NAME = "basestring"
DOC = "replace basestring with six.string_types"
# match 'basestring' word
BASESTRING_REGEX = re.compile(r"\bbasestring\b")
def patch(self, content):
new_content = self.BASESTRING_REGEX.sub('six.string_types', content)
if new_content == content:
return content
return self.patcher.add_import_six(new_content)
def check(self, content):
for line in content.splitlines():
if 'basestring' in line:
self.warn_line(line)
class StringIO(Operation):
NAME = "stringio"
DOC = ("replace StringIO.StringIO with six.StringIO"
" and cStringIO.StringIO with six.moves.cStringIO")
# 'import StringIO'
IMPORT_STRINGIO_REGEX = import_regex(r"StringIO")
# 'from StringIO import StringIO'
FROM_IMPORT_STRINGIO_REGEX = from_import_regex(r"StringIO", r"StringIO")
# 'from StringIO import StringIO'
FROM_IMPORT_CSTRINGIO_REGEX = from_import_regex(r"cStringIO", r"StringIO")
# 'import cStringIO'
IMPORT_CSTRINGIO_REGEX = import_regex(r"cStringIO")
# 'import cStringIO as StringIO'
IMPORT_CSTRINGIO_AS_REGEX = import_regex(r"cStringIO as StringIO")
# 'StringIO.', 'cStringIO.', but not 'six.StringIO' or 'six.cStringIO'
CSTRINGIO_REGEX = re.compile(r'(?<!six\.)\bc?StringIO\.')
def _patch_stringio1(self, content):
# Replace 'from StringIO import StringIO'
# with 'from six import StringIO'
new_content = self.FROM_IMPORT_STRINGIO_REGEX.sub('', content)
if new_content == content:
return content
return self.patcher.add_import(new_content, 'from six import StringIO')
def _patch_stringio2(self, content):
# Replace 'import StringIO' + 'StringIO.StringIO'
# with 'import six' + 'six.StringIO'
new_content = self.IMPORT_STRINGIO_REGEX.sub('', content)
if new_content == content:
return content
new_content = self.patcher.add_import_six(new_content)
return new_content.replace("StringIO.StringIO", "six.StringIO")
def _patch_cstringio1(self, content):
# Replace 'from cStringIO import StringIO'
# with 'from six.moves import cStringIO as StringIO'
new_content = self.FROM_IMPORT_CSTRINGIO_REGEX.sub('', content)
if new_content == content:
return content
new_content = self.patcher.add_import(new_content,
"from six.moves import cStringIO as StringIO")
return new_content
def _patch_cstringio2(self, content):
# Replace 'import cStringIO' + 'cStringIO.StringIO'
# with 'from six import moves' + 'moves.cStringIO'
new_content = self.IMPORT_CSTRINGIO_REGEX.sub('', content)
if new_content == content:
return content
new_content = self.patcher.add_import(new_content, "from six import moves")
return new_content.replace("cStringIO.StringIO", "moves.cStringIO")
def _patch_cstringio3(self, content):
# Replace 'import cStringIO as StringIO' + 'StringIO.StringIO'
# with 'from six import moves' + 'moves.cStringIO'
new_content = self.IMPORT_CSTRINGIO_AS_REGEX.sub('', content)
if new_content == content:
return content
new_content = self.patcher.add_import(new_content, "from six import moves")
return new_content.replace("StringIO.StringIO", "moves.cStringIO")
def patch(self, content):
content = self._patch_stringio1(content)
content = self._patch_stringio2(content)
content = self._patch_cstringio1(content)
content = self._patch_cstringio2(content)
content = self._patch_cstringio3(content)
return content
def check(self, content):
for line in content.splitlines():
if 'StringIO.StringIO' in line or self.CSTRINGIO_REGEX.search(line):
self.warn_line(line)
class Urllib(Operation):
NAME = "urllib"
DOC = "replace urllib, urllib2 and urlparse with six.moves.urllib"
# 'import urllib', 'import urllib2', 'import urlparse'
IMPORT_URLLIB_REGEX = import_regex(r"\b(?:urllib2?|urlparse)\b")
# 'from urlparse import symbol, symbol2'
FROM_IMPORT_REGEX = from_import_regex('(urllib2?|urlparse)',
'(%s)' % FROM_IMPORT_SYMBOLS_REGEX)
# 'from urlparse import'
FROM_IMPORT_WARN_REGEX = re.compile(r"^from (?:urllib2?|urlparse) import",
re.MULTILINE)
# 'urllib.attr'
# 'urllib2.urlparse.attr'
# 'urllib2.attr'
# 'urlparse.attr'
URLLIB_ATTR_REGEX = re.compile(r"\b(?:urllib|urllib2(?:\.(?:urllib|urlparse))?|urlparse)\.(%s)"
% IDENTIFIER_REGEX)
SIX_MOVES_URLLIB = {
# six.moves.urllib submodule => Python 2 urllib/urllib2 symbols
'error': (
'HTTPError',
'URLError',
),
'request': (
'HTTPBasicAuthHandler',
'HTTPCookieProcessor',
'HTTPPasswordMgrWithDefaultRealm',
'HTTPSHandler',
'OpenerDirector',
'ProxyHandler',
'Request',
'build_opener',
'install_opener',
'pathname2url',
'urlopen',
),
'parse': (
'parse_qs',
'parse_qsl',
'quote',
'quote_plus',
'unquote',
'urlencode',
'urljoin',
'urlparse',
'urlsplit',
'urlunparse',
'urlunsplit',
),
}
URLLIB = {}
for submodule, symbols in SIX_MOVES_URLLIB.items():
for symbol in symbols:
URLLIB[symbol] = submodule
# 'urllib.error', 'urllib.parse', 'urllib.request'
URLLIB_UNCHANGED = set('urllib.%s' % submodule
for submodule in SIX_MOVES_URLLIB)
def replace(self, regs):
text = regs.group(0)
if text in self.URLLIB_UNCHANGED:
return text
name = regs.group(1)
if name == 'parse_http_list':
# six has no helper for parse_http_list() yet
return text
try:
submodule = self.URLLIB[name]
except KeyError:
self.warning("Unknown urllib symbol: %s" % text)
return text
return 'urllib.%s.%s' % (submodule, name)
def replace_import_from(self, add_imports, regs):
module = regs.group(1)
symbols = regs.group(2)
if 'parse_http_list' in symbols:
# six has no helper for parse_http_list() yet
return regs.group(0)
imports = collections.defaultdict(list)
for symbol in symbols.split(','):
name = symbol.strip()
try:
submodule = self.URLLIB[name]
except KeyError:
raise Exception("unknown urllib symbol: %s.%s"
% (module, name))
imports[submodule].append(name)
for submodule, names in imports.items():
line = ('from six.moves.urllib.%s import %s'
% (submodule, ', '.join(names)))
add_imports.add(line)
return ''
def patch_import(self, content):
new_content = self.IMPORT_URLLIB_REGEX.sub('', content)
if new_content == content:
return content
content = new_content
content = self.URLLIB_ATTR_REGEX.sub(self.replace, content)
return self.patcher.add_import(content,
"from six.moves import urllib")
def patch_from_import(self, content, add_imports):
replace_cb = functools.partial(self.replace_import_from, add_imports)
content = self.FROM_IMPORT_REGEX.sub(replace_cb, content)
return content
def patch(self, content):
add_imports = set()
content = self.patch_import(content)
content = self.patch_from_import(content, add_imports)
for line in sorted(add_imports):
content = self.patcher.add_import(content, line)
return content
def check(self, content):
for line in content.splitlines():
if 'urllib2.parse_http_list' in line:
self.warn_line(line)
elif self.FROM_IMPORT_WARN_REGEX.search(line):
self.warn_line(line)
class Raise(Operation):
NAME = "raise"
DOC = ("replace 'raise exc, msg' with 'raise exc(msg)'"
" and replace 'raise a, b, c' with 'six.reraise(a, b, c)'")
# 'raise a, b, c' expr
RAISE3_REGEX = re.compile(r"raise (%s), *(%s), *(%s)"
% (EXPR_REGEX, EXPR_REGEX, EXPR_REGEX))
# 'raise a, b' expr
RAISE2_REGEX = re.compile(r'''raise (%s), *(%s|'[^']+'|"[^"]+")$'''
% (EXPR_REGEX, EXPR_REGEX), re.MULTILINE)
# 'raise a,' line
RAISE_LINE_REGEX = re.compile(r"^.*raise %s,.*$" % EXPR_REGEX,
re.MULTILINE)
def raise2_replace(self, regs):
return 'raise %s(%s)' % (regs.group(1), regs.group(2))
def raise3_replace(self, regs):
exc_type = regs.group(1)
exc_value = regs.group(2)
exc_tb = regs.group(3)
# 'raise exc_info[0], exc_info[1], exc_inf[2]'
# => 'six.reraise(*exc_info)'
if (exc_type.endswith('[0]')
and exc_value.endswith('[1]')
and exc_tb.endswith('[2]')):
return ('six.reraise(*%s)' % exc_type[:-3])
return ('six.reraise(%s, %s, %s)'
% (exc_type, exc_value, exc_tb))
def patch(self, content):
old_content = content
content = self.RAISE2_REGEX.sub(self.raise2_replace, content)
new_content = self.RAISE3_REGEX.sub(self.raise3_replace, content)
if new_content != content:
content = self.patcher.add_import_six(new_content)
return content
def check(self, content):
for match in self.RAISE_LINE_REGEX.finditer(content):
self.warn_line(match.group(0))
class Except(Operation):
NAME = "except"
DOC = ("replace 'except ValueError, exc:' with "
"'except ValueError as exc:', replace "
"'except (TypeError, ValueError), exc:' with "
"'except (TypeError, ValueError) as exc:'.")
# 'except ValueError, exc:'
EXCEPT_REGEX = re.compile(r"except (%s), *(%s):"
% (QUALNAME_REGEX, IDENTIFIER_REGEX))
# 'except (ValueError, TypeError), exc:'
EXCEPT2_REGEX = re.compile(r"except (\(%s(?:, *%s)*\)), *(%s):"
% (QUALNAME_REGEX, IDENTIFIER_REGEX,
IDENTIFIER_REGEX))
EXCEPT_WARN_REGEX = re.compile(r"except [^,()]+, *[^:]+:")
EXCEPT_WARN2_REGEX = re.compile(r"except \([^()]+\), *[^:]+:")
def except_replace(self, regs):
return 'except %s as %s:' % (regs.group(1), regs.group(2))
def patch(self, content):
content = self.EXCEPT_REGEX.sub(self.except_replace, content)
return self.EXCEPT2_REGEX.sub(self.except_replace, content)
def check(self, content):
for line in content.splitlines():
if (self.EXCEPT_WARN_REGEX.search(line)
or self.EXCEPT_WARN2_REGEX.search(line)):
self.warn_line(line)
class SixMoves(Operation):
NAME = "six_moves"
DOC = ("replace Python 2 imports with six and six.moves imports")
SIX_MODULE_MOVES = {
# Python 2 import => six.moves import
'BaseHTTPServer': 'BaseHTTPServer',
'ConfigParser': 'configparser',
'Cookie': 'http_cookies',
'HTMLParser': 'html_parser',
'Queue': 'queue',
'SimpleHTTPServer': 'SimpleHTTPServer',
'SimpleXMLRPCServer': 'xmlrpc_server',
'__builtin__': 'builtins',
'cPickle': 'cPickle',
'cookielib': 'http_cookiejar',
'htmlentitydefs': 'html_entities',
'httplib': 'http_client',
'repr': 'reprlib',
# 'thread': '_thread',
'xmlrpclib': 'xmlrpc_client',
}
# 'BaseHTTPServer', '__builtin__', 'repr', ...
SIX_MOVES_REGEX = sorted(map(re.escape, SIX_MODULE_MOVES.keys()))
SIX_MOVES_REGEX = ("(?:%s)" % '|'.join(SIX_MOVES_REGEX))
# 'import BaseHTTPServer', 'import repr as reprlib'
IMPORT_REGEX = import_regex(r"(%s)( as %s)?"
% (SIX_MOVES_REGEX, IDENTIFIER_REGEX))
# 'from BaseHTTPServer import ...'
FROM_IMPORT_REGEX = from_import_regex(r"(%s)" % SIX_MOVES_REGEX,
r"(%s)" % FROM_IMPORT_SYMBOLS_REGEX)
# "patch('__builtin__."
MOCK_REGEX = re.compile(r"""(patch\(['"])(%s)\."""
% SIX_MOVES_REGEX, re.MULTILINE)
SIX_BUILTIN_MOVES = {
# Python 2 builtin function => six.moves import
'raw_input': 'input',
'reduce': 'reduce',
'reload': 'reload_module',
}
SIX_FUNCTIONS = {
# Python 2 builtin function => six function
'unichr': 'unichr',
}
# 'reduce(', 'reload('
# but not '.reduce(' (exclude 'moves.reduce(...)')
BUILTIN_REGEX = re.compile(r'(?<!\.)\b(%s)\b( *\()'
% '|'.join(SIX_BUILTIN_MOVES))
# 'unichr('
# but not '.unichr('
FUNCTION_REGEX = re.compile(r'(?<!\.)\b(%s)\b( *\()'
% '|'.join(SIX_FUNCTIONS))
def replace_mock(self, regs):
name = regs.group(2)
new_name = self.SIX_MODULE_MOVES[name]
return '%ssix.moves.%s.' % (regs.group(1), new_name)
def replace_import(self, add_imports, replace_names, regs):
name = regs.group(1)
as_name = regs.group(2)
new_name = self.SIX_MODULE_MOVES[name]
line = 'from six.moves import %s' % new_name
if as_name:
line += as_name
add_imports.add(line)
replace_names.add((name, new_name))
return ''
def replace_from(self, add_imports, regs):
new_name = self.SIX_MODULE_MOVES[regs.group(1)]
symbols = regs.group(2)
line = 'from six.moves.%s import %s' % (new_name, symbols)
add_imports.add(line)
return ''
def replace_builtin(self, add_imports, regs):
new_name = self.SIX_BUILTIN_MOVES[regs.group(1)]
suffix = regs.group(2)
line = 'from six.moves import %s' % new_name
add_imports.add(line)
return new_name + suffix
def replace_all_builtins(self, add_imports, content):
six_builtin_moves = dict(self.SIX_BUILTIN_MOVES)
for regs in self.BUILTIN_REGEX.finditer(content):
name = regs.group(1)
if name not in six_builtin_moves:
# already removed
continue
new_name = six_builtin_moves[name]
pattern = 'from six.moves import %s\n' % new_name
if pattern in content:
# the symbol comes from six.moves, no need to patch it
del six_builtin_moves[name]
builtin_regex2 = re.compile(r'(?<!\.)\b(%s)\b( *\()'
% '|'.join(six_builtin_moves))
replace_cb = functools.partial(self.replace_builtin, add_imports)
return builtin_regex2.sub(replace_cb, content)
def replace_function(self, add_imports, regs):
new_name = self.SIX_FUNCTIONS[regs.group(1)]
suffix = regs.group(2)
add_imports.add('import six')
return 'six.%s%s' % (new_name, suffix)
def replace_all_functions(self, add_imports, content):
replace_cb = functools.partial(self.replace_function, add_imports)
return self.FUNCTION_REGEX.sub(replace_cb, content)
def patch(self, content):
add_imports = set()
replace_names = set()
replace_cb = functools.partial(self.replace_import,
add_imports, replace_names)
content = self.IMPORT_REGEX.sub(replace_cb, content)
replace_cb = functools.partial(self.replace_from, add_imports)
content = self.FROM_IMPORT_REGEX.sub(replace_cb, content)
content = self.replace_all_builtins(add_imports, content)
content = self.replace_all_functions(add_imports, content)
for old_name, new_name in replace_names:
# Only match words
regex = r'\b(?<!\.)%s\b' % re.escape(old_name)
content = re.sub(regex, new_name, content)
for line in sorted(add_imports):
names = parse_import(line)
content = self.patcher.add_import_names(content, line, names)
content = self.MOCK_REGEX.sub(self.replace_mock, content)
return content
def check(self, content):
pass
class Itertools(Operation):
NAME = "itertools"
DOC = ("replace itertools.ifilter with six.moves.filter, "
"similar change for ifilterfalse, imap, izip and izip_longest")
FUNCTIONS = {
# itertools function => six.moves function
'ifilter': 'filter',
'ifilterfalse': 'filterfalse',
'imap': 'map',
'izip': 'zip',
'izip_longest': 'zip_longest',
}
FUNCTIONS_REGEX = '(?:%s)' % '|'.join(FUNCTIONS)
# 'from itertools import imap'
IFUNC_IMPORT_REGEX = from_import_regex(r"itertools", FUNCTIONS_REGEX)
# 'imap', 'ifilter'
IFUNC_REGEX = re.compile(r'\b(%s)\b' % FUNCTIONS_REGEX)
# 'itertools.imap'
ITERTOOLS_IFUNC_REGEX = re.compile(r'\bitertools\.(%s)\b' % FUNCTIONS_REGEX)
# 'itertools.'
ITERTOOLS_REGEX = re.compile(r'\bitertools\.')
# 'import itertools'
IMPORT_ITERTOOLS_REGEX = import_regex(r"itertools")
def replace(self, regs):
func = regs.group(1)
six_func = self.FUNCTIONS[func]
return 'six.moves.%s' % six_func
def patch_from_import(self, content):
# Replace itertools.imap with six.moves.map
new_content = self.IFUNC_IMPORT_REGEX.sub('', content)
if new_content == content:
return content
content = self.patcher.add_import_six(new_content)
content = self.IFUNC_REGEX.sub(self.replace, content)
return content
def patch_import(self, content):
# Replace itertools.imap with six.moves.map
new_content = self.ITERTOOLS_IFUNC_REGEX.sub(self.replace, content)
if new_content == content:
return content
content = new_content
if not self.ITERTOOLS_REGEX.search(content):
# itertools is no more used, remove it
content = self.IMPORT_ITERTOOLS_REGEX.sub('', content)
return self.patcher.add_import_six(content)
def patch(self, content):
content = self.patch_from_import(content)
content = self.patch_import(content)
return content
def check(self, content):
for line in content.splitlines():
if 'imap' in line:
self.warn_line(line)
class Dict0(Operation):
NAME = "dict0"
DOC = ("replace dict.keys()[0] with list(dict.keys())[0], "
"same for dict.values()[0] and dict.items()[0]")
EXPR_REGEX = re.compile(r'(%s\.(?:keys|values|items)\(\))\[([0-9]+)\]'
% EXPR_REGEX)
CHECK_REGEX = re.compile(r'\.(?:keys|values|items)\(\)\[[0-9]+\]')
def replace(self, regs):
return 'list(%s)[%s]' % (regs.group(1), regs.group(2))
def patch(self, content):
return self.EXPR_REGEX.sub(self.replace, content)
def check(self, content):
for line in content.splitlines():
if self.CHECK_REGEX.search(line):
self.warn_line(line)
class DictAdd(Operation):
NAME = "dict_add"
DOC = ('replace "dict.keys() + list2" with "list(dict.keys()) + list2", '
'same for "dict.values() + list2" and "dict.items() + list2"')
EXPR_REGEX = re.compile(r'(%s\.(?:keys|values|items)\(\))( *\+)'
% EXPR_REGEX)
CHECK_REGEX = re.compile(r'\.(?:keys|values|items)\(\) *\+')
def replace(self, regs):
return 'list(%s)%s' % (regs.group(1), regs.group(2))
def patch(self, content):
return self.EXPR_REGEX.sub(self.replace, content)
def check(self, content):
for line in content.splitlines():
if self.CHECK_REGEX.search(line):
self.warn_line(line)
class Print(Operation):
NAME = "print"
DOC = ('replace "print msg" with "print(msg)", '
'replace "print msg," with "print(msg, end=\' \')", '
'replace "print" with "print()"')
# 'print msg', 'print "hello"'
# but don't match: 'print msg,'
REGEX_ARG = re.compile(r"\bprint ( *)(%s)(?! *,)$"
% EXPR_STRING_REGEX ,
re.MULTILINE)
# 'print', 'print # comment'
# but don't match: 'print msg'
REGEX = re.compile(r"\bprint( *(?:#.*)?)$", re.MULTILINE)
# 'print >>file, arg'
# but don't match 'print >>file, arg,' (trailing comma)
REGEX_INTO = re.compile(r"\bprint ?( *)>>(%s), *(%s)(?! *,)$"
% (EXPR_REGEX, EXPR_STRING_REGEX),
re.MULTILINE)
# 'print msg,', 'print "hello",'
REGEX_COMMA = re.compile(r"\bprint ( *)(%s) *,$"
% EXPR_STRING_REGEX ,
re.MULTILINE)
CHECK_REGEX = re.compile(r"^.*\bprint\b *[^( ].*$", re.MULTILINE)
def replace_arg(self, regs):
return 'print%s(%s)' % (regs.group(1), regs.group(2))
def replace(self, regs):
return 'print()%s' % regs.group(1)
def replace_into(self, regs):
return 'print%s(%s, file=%s)' % (regs.group(1), regs.group(3), regs.group(2))
def replace_comma(self, regs):
return "print%s(%s, end=' ')" % (regs.group(1), regs.group(2))
def patch(self, content):
content = self.REGEX_ARG.sub(self.replace_arg, content)
new_content = self.REGEX_INTO.sub(self.replace_into, content)
new_content = self.REGEX.sub(self.replace, new_content)
new_content = self.REGEX_COMMA.sub(self.replace_comma, new_content)
if new_content != content:
content = self.patcher.add_import(new_content, 'from __future__ import print_function')
return content
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
self.warn_line(line)
class String(Operation):
NAME = "string"
DOC = 'replace string.func(str, ...) with text.func(...)'
# Deprecated functions of the Python 2 string module
FUNCTIONS = '|'.join((
'lower',
'upper',
'swapcase',
'strip',
'lstrip',
'rstrip',
'split',
'splitfields',
'rsplit',
'join',
'joinfields',
'index',
'rindex',
'count',
'find',
'rfind',
'ljust',
'rjust',
'center',
'zfill',
'expandtabs',
# FIXME: translate, maketrans
'capitalize',
'replace',
))
# 'string.upper("ABC")', 'string.lower(x)'
REGEX = re.compile(r"\bstring\.(%s)\((%s)\)"
% (FUNCTIONS, EXPR_STRING_REGEX))
# 'string.split("ABC", maxsplit=2)'
REGEX_ARGS = re.compile(r"\bstring\.(%s)\((%s), *([^)]+)\)"
% (FUNCTIONS, EXPR_STRING_REGEX))
# string.atof(str) => float(str)
ATOX = {
'atof': 'float',
'atoi': 'int',
'atol': 'int',
}
# 'string.atof("1.2")'
REGEX_ATOX = re.compile(r"\bstring\.(%s)\((%s)\)"
% ('|'.join(ATOX), EXPR_STRING_REGEX))
# match 'string.letters',
# don't match 'string.ascii_letters'
CHECK_REGEX = re.compile(r"^.*\bstring\.(?!ascii_letters).*$", re.MULTILINE)
def replace(self, regs):
return '%s.%s()' % (regs.group(2), regs.group(1))
def replace_args(self, regs):
return '%s.%s(%s)' % (regs.group(2), regs.group(1), regs.group(3))
def replace_atox(self, regs):
new_name = self.ATOX[regs.group(1)]
return '%s(%s)' % (new_name, regs.group(2))
def patch(self, content):
old_content = content
content = self.REGEX.sub(self.replace, content)
content = self.REGEX_ARGS.sub(self.replace_args, content)
content = self.REGEX_ATOX.sub(self.replace_atox, content)
if content != old_content:
if 'string.' not in content:
# Remove 'import string'
content = import_regex(r"string").sub('', content)
return content
def check(self, content):
for match in self.CHECK_REGEX.finditer(content):
line = match.group(0)
self.warn_line(line)
class All(Operation):
NAME = "all"
DOC = "apply all available operations"
def patch(self, content):
# All is a virtual operation, it's implemented in Patcher.__init__
return content
def check(self, content):
# All is a virtual operation, it's implemented in Patcher.__init__
pass
OPERATIONS = (
Iteritems,
Itervalues,
Iterkeys,
HasKey,
Next,
Long,
Unicode,
Xrange,
Basestring,
StringIO,
Urllib,
Raise,
Except,
SixMoves,
Itertools,
Dict0,
DictAdd,
Print,
String,
All,
)
OPERATION_NAMES = set(operation.NAME for operation in OPERATIONS)
OPERATION_BY_NAME = {operation.NAME: operation for operation in OPERATIONS}
class Patcher:
IMPORT_SIX_REGEX = re.compile(r"^import six$", re.MULTILINE)
def __init__(self, operations, options=None):
self.exitcode = 0
self.warnings = []
self.current_file = None
self.options = options
self.applied_operations = set()
self.application_modules = set(APPLICATION_MODULES)
self.third_party_modules = set(THIRD_PARTY_MODULES)
if options.third_party:
names = options.third_party.split(',')
names = set(name.strip() for name in names)
self.third_party_modules |= names
if options.app:
self.application_modules.add(options.app)
self.third_party_modules.discard(options.app)
operations = set(operations)
if All.NAME in operations:
operations |= set(OPERATION_NAMES)
operations.discard(All.NAME)
discard = [operation for operation in operations
if operation.startswith('-')]
for name in discard:
operations.discard(name)
operations.discard(name[1:])
self.operations = [OPERATION_BY_NAME[name](self)
for name in operations]
def _walk_dir(self, path):
for dirpath, dirnames, filenames in os.walk(path):
# Don't walk into .tox
try:
dirnames.remove(".tox")
except ValueError:
pass
for filename in filenames:
if filename.endswith(".py"):
yield os.path.join(dirpath, filename)
def walk(self, paths):
for path in paths:
if os.path.isfile(path):
yield path
else:
empty = True
for filename in self._walk_dir(path):
yield filename
empty = False
if empty:
if os.path.isdir(path):
self.warning("Directory %s doesn't contain any "
".py file" % path)
self.exitcode = 1
else:
self.warning("Path %s doesn't exist" % path)
self.exitcode = 1
def add_import_names(self, content, import_line, import_names):
import_line = import_line.rstrip() + '\n'
create_new_import_group = None
import_groups = parse_import_groups(content)
if not import_groups:
if content:
return import_line + '\n\n' + content
else:
return import_line
add_future = (import_names[0] == '__future__')
if not add_future and import_groups[0][2] == {'__future__'}:
# Ignore the first import group: from __future__ import ...
del import_groups[0]
if len(import_groups) == 3:
import_group = import_groups[1]
else:
# Heuristic to locate the import group of third-party modules
seen_stdlib_group = False
for import_group in import_groups:
start, end, imports = import_group
if any(name.split('.', 1)[0] in self.third_party_modules
for name in imports):
break
if any(name in self.application_modules for name in imports):
# application import, add import six before in a new group
create_new_import_group = (start, False)
break
if any(name in STDLIB_MODULES for name in imports):
seen_stdlib_group = True
if add_future:
# stdlib imports, add future imports before in a new group
create_new_import_group = (start, False)
break
if add_future and any(name == '__future__' for name in imports):
break
else:
create_new_import_group = (end, True)
if not seen_stdlib_group:
self.warning("%s: Failed to find the best place to add %r: "
"put it at the end. Use --app and "
"--third-party options."
% (self.current_file, import_line.rstrip()))
if create_new_import_group is not None:
pos, last_group = create_new_import_group
part1 = content[:pos]
if not part1 or part1.endswith('\n\n'):
newline1 = ''
else:
newline1 = '\n'
if last_group:
newline2 = '\n\n'
else:
newline2 = '\n'
return part1 + newline1 + import_line + newline2 + content[pos:]
start, end, imports = import_group
pos = start
while pos < end:
line = get_line(content, pos)
if line == "\n":
break
try:
names = parse_import(line)
except SyntaxError:
pass
else:
if import_names < names:
break
pos += len(line)
return content[:pos] + import_line + content[pos:]
def add_import(self, content, line):
regex = r"^%s *(?:#.*)?$" % re.escape(line)
if re.search(regex, content, flags=re.MULTILINE):
return content
names = parse_import(line)
return self.add_import_names(content, line, names)
def add_import_six(self, content):
return self.add_import(content, 'import six')
def _display_warning(self, msg):
print("WARNING: %s" % msg, file=sys.stderr, flush=True)
def warning(self, msg):
self._display_warning(msg)
self.warnings.append(msg)
def check(self, content):
for operation in self.operations:
operation.check(content)
def write_stdout(self, content):
for line in content.splitlines():
print(line)
sys.stdout.flush()
def patch(self, filename):
self.current_file = filename
with tokenize.open(filename) as fp:
content = fp.read()
modified = set()
for operation in self.operations:
new_content = operation.patch(content)
if new_content == content:
continue
modified.add(operation.NAME)
content = new_content
if not modified:
# no change
self.check(content)
if self.options.to_stdout:
self.write_stdout(content)
return False
if not self.options.quiet:
self.applied_operations |= modified
print("Patch %s with %s" % (filename, ', '.join(sorted(modified))),
flush=True)
if not self.options.to_stdout:
if self.options.write:
with open(filename, "rb") as fp:
encoding, _ = tokenize.detect_encoding(fp.readline)
with open(filename, "w", encoding=encoding) as fp:
fp.write(content)
else:
self.write_stdout(content)
self.check(content)
return True
@staticmethod
def usage(parser):
parser.print_help()
print()
print("operations:")
for name in sorted(OPERATION_NAMES):
operation = OPERATION_BY_NAME[name]
print("- %s: %s" % (name, operation.DOC))
print()
print("If a directory is passed, sixer finds .py files in subdirectories.")
print()
print("<operation> can be a list of operations separated by commas")
print("Example: six_moves,urllib")
@staticmethod
def parse_options():
parser = optparse.OptionParser(
description=("sixer is a tool adding Python 3 support "
"to a Python 2 project"),
usage="%prog [options] <operation> <file1> <file2> <...>")
parser.add_option(
'-c', '--to-stdout', action="store_true",
help='Write output into stdout instead of modify files in-place '
'(imply --quiet option)')
parser.add_option(
'-w', '--write', action="store_true",
help='Really modify files in place')
parser.add_option(
'--app', type="str",
help='Name of the application module, used to sort and group '
'imports')
parser.add_option(
'--third-party', type="str",
help='Comma separated list of third-party modules, used to sort '
'and group imports (ex: --third-party=django,eventlet)')
parser.add_option(
'-q', '--quiet', action="store_true",
help='Be quiet')
parser.add_option(
'--max-range', type="int",
help=("Don't use six.moves.xrange for ranges smaller than "
"MAX_RANGE items (default: %s)" % MAX_RANGE),
default=MAX_RANGE)
options, args = parser.parse_args()
if len(args) < 2:
Patcher.usage(parser)
sys.exit(1)
if options.to_stdout:
options.quiet = True
operations = args[0].split(',')
paths = args[1:]
for operation in operations:
if operation.startswith("-"):
operation = operation[1:]
if operation not in OPERATION_NAMES:
print("invalid operation: %r" % operation)
print()
Patcher.usage(parser)
sys.exit(1)
return options, operations, paths
def main(self, paths):
if not self.options.write and not self.options.quiet:
print("(Dry run: don't modify files)", file=sys.stderr)
print(file=sys.stderr)
nfiles = 0
for filename in self.walk(paths):
try:
self.patch(filename)
except Exception:
print("ERROR while patching %s" % filename)
raise
nfiles += 1
print()
if not self.options.quiet:
print("Scanned %s files" % nfiles)
if self.applied_operations:
operations = sorted(self.applied_operations)
print("Applied operations (%s): %s"
% (len(self.applied_operations), ', '.join(operations)))
if self.warnings:
print(file=sys.stderr)
print("Warnings:", file=sys.stderr)
for msg in self.warnings:
self._display_warning(msg)
if not self.options.write and not self.options.quiet:
print(file=sys.stderr)
print("Now retry with --write option to really modify files "
"inplace", file=sys.stderr)
sys.exit(self.exitcode)
def main():
options, operations, paths = Patcher.parse_options()
Patcher(operations, options).main(paths)
if __name__ == "__main__":
main()
|