/usr/lib/python3.7/test/test_codeccallbacks.py is in libpython3.7-testsuite 3.7.0~b3-1.
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 | import codecs
import html.entities
import sys
import test.support
import unicodedata
import unittest
class PosReturn:
# this can be used for configurable callbacks
def __init__(self):
self.pos = 0
def handle(self, exc):
oldpos = self.pos
realpos = oldpos
if realpos<0:
realpos = len(exc.object) + realpos
# if we don't advance this time, terminate on the next call
# otherwise we'd get an endless loop
if realpos <= exc.start:
self.pos = len(exc.object)
return ("<?>", oldpos)
# A UnicodeEncodeError object with a bad start attribute
class BadStartUnicodeEncodeError(UnicodeEncodeError):
def __init__(self):
UnicodeEncodeError.__init__(self, "ascii", "", 0, 1, "bad")
self.start = []
# A UnicodeEncodeError object with a bad object attribute
class BadObjectUnicodeEncodeError(UnicodeEncodeError):
def __init__(self):
UnicodeEncodeError.__init__(self, "ascii", "", 0, 1, "bad")
self.object = []
# A UnicodeDecodeError object without an end attribute
class NoEndUnicodeDecodeError(UnicodeDecodeError):
def __init__(self):
UnicodeDecodeError.__init__(self, "ascii", bytearray(b""), 0, 1, "bad")
del self.end
# A UnicodeDecodeError object with a bad object attribute
class BadObjectUnicodeDecodeError(UnicodeDecodeError):
def __init__(self):
UnicodeDecodeError.__init__(self, "ascii", bytearray(b""), 0, 1, "bad")
self.object = []
# A UnicodeTranslateError object without a start attribute
class NoStartUnicodeTranslateError(UnicodeTranslateError):
def __init__(self):
UnicodeTranslateError.__init__(self, "", 0, 1, "bad")
del self.start
# A UnicodeTranslateError object without an end attribute
class NoEndUnicodeTranslateError(UnicodeTranslateError):
def __init__(self):
UnicodeTranslateError.__init__(self, "", 0, 1, "bad")
del self.end
# A UnicodeTranslateError object without an object attribute
class NoObjectUnicodeTranslateError(UnicodeTranslateError):
def __init__(self):
UnicodeTranslateError.__init__(self, "", 0, 1, "bad")
del self.object
class CodecCallbackTest(unittest.TestCase):
def test_xmlcharrefreplace(self):
# replace unencodable characters which numeric character entities.
# For ascii, latin-1 and charmaps this is completely implemented
# in C and should be reasonably fast.
s = "\u30b9\u30d1\u30e2 \xe4nd eggs"
self.assertEqual(
s.encode("ascii", "xmlcharrefreplace"),
b"スパモ änd eggs"
)
self.assertEqual(
s.encode("latin-1", "xmlcharrefreplace"),
b"スパモ \xe4nd eggs"
)
def test_xmlcharnamereplace(self):
# This time use a named character entity for unencodable
# characters, if one is available.
def xmlcharnamereplace(exc):
if not isinstance(exc, UnicodeEncodeError):
raise TypeError("don't know how to handle %r" % exc)
l = []
for c in exc.object[exc.start:exc.end]:
try:
l.append("&%s;" % html.entities.codepoint2name[ord(c)])
except KeyError:
l.append("&#%d;" % ord(c))
return ("".join(l), exc.end)
codecs.register_error(
"test.xmlcharnamereplace", xmlcharnamereplace)
sin = "\xab\u211c\xbb = \u2329\u1234\u20ac\u232a"
sout = b"«ℜ» = ⟨ሴ€⟩"
self.assertEqual(sin.encode("ascii", "test.xmlcharnamereplace"), sout)
sout = b"\xabℜ\xbb = ⟨ሴ€⟩"
self.assertEqual(sin.encode("latin-1", "test.xmlcharnamereplace"), sout)
sout = b"\xabℜ\xbb = ⟨ሴ\xa4⟩"
self.assertEqual(sin.encode("iso-8859-15", "test.xmlcharnamereplace"), sout)
def test_uninamereplace(self):
# We're using the names from the unicode database this time,
# and we're doing "syntax highlighting" here, i.e. we include
# the replaced text in ANSI escape sequences. For this it is
# useful that the error handler is not called for every single
# unencodable character, but for a complete sequence of
# unencodable characters, otherwise we would output many
# unnecessary escape sequences.
def uninamereplace(exc):
if not isinstance(exc, UnicodeEncodeError):
raise TypeError("don't know how to handle %r" % exc)
l = []
for c in exc.object[exc.start:exc.end]:
l.append(unicodedata.name(c, "0x%x" % ord(c)))
return ("\033[1m%s\033[0m" % ", ".join(l), exc.end)
codecs.register_error(
"test.uninamereplace", uninamereplace)
sin = "\xac\u1234\u20ac\u8000"
sout = b"\033[1mNOT SIGN, ETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("ascii", "test.uninamereplace"), sout)
sout = b"\xac\033[1mETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("latin-1", "test.uninamereplace"), sout)
sout = b"\xac\033[1mETHIOPIC SYLLABLE SEE\033[0m\xa4\033[1mCJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("iso-8859-15", "test.uninamereplace"), sout)
def test_backslashescape(self):
# Does the same as the "unicode-escape" encoding, but with different
# base encodings.
sin = "a\xac\u1234\u20ac\u8000\U0010ffff"
sout = b"a\\xac\\u1234\\u20ac\\u8000\\U0010ffff"
self.assertEqual(sin.encode("ascii", "backslashreplace"), sout)
sout = b"a\xac\\u1234\\u20ac\\u8000\\U0010ffff"
self.assertEqual(sin.encode("latin-1", "backslashreplace"), sout)
sout = b"a\xac\\u1234\xa4\\u8000\\U0010ffff"
self.assertEqual(sin.encode("iso-8859-15", "backslashreplace"), sout)
def test_nameescape(self):
# Does the same as backslashescape, but prefers ``\N{...}`` escape
# sequences.
sin = "a\xac\u1234\u20ac\u8000\U0010ffff"
sout = (b'a\\N{NOT SIGN}\\N{ETHIOPIC SYLLABLE SEE}\\N{EURO SIGN}'
b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff')
self.assertEqual(sin.encode("ascii", "namereplace"), sout)
sout = (b'a\xac\\N{ETHIOPIC SYLLABLE SEE}\\N{EURO SIGN}'
b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff')
self.assertEqual(sin.encode("latin-1", "namereplace"), sout)
sout = (b'a\xac\\N{ETHIOPIC SYLLABLE SEE}\xa4'
b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff')
self.assertEqual(sin.encode("iso-8859-15", "namereplace"), sout)
def test_decoding_callbacks(self):
# This is a test for a decoding callback handler
# that allows the decoding of the invalid sequence
# "\xc0\x80" and returns "\x00" instead of raising an error.
# All other illegal sequences will be handled strictly.
def relaxedutf8(exc):
if not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
if exc.object[exc.start:exc.start+2] == b"\xc0\x80":
return ("\x00", exc.start+2) # retry after two bytes
else:
raise exc
codecs.register_error("test.relaxedutf8", relaxedutf8)
# all the "\xc0\x80" will be decoded to "\x00"
sin = b"a\x00b\xc0\x80c\xc3\xbc\xc0\x80\xc0\x80"
sout = "a\x00b\x00c\xfc\x00\x00"
self.assertEqual(sin.decode("utf-8", "test.relaxedutf8"), sout)
# "\xc0\x81" is not valid and a UnicodeDecodeError will be raised
sin = b"\xc0\x80\xc0\x81"
self.assertRaises(UnicodeDecodeError, sin.decode,
"utf-8", "test.relaxedutf8")
def test_charmapencode(self):
# For charmap encodings the replacement string will be
# mapped through the encoding again. This means, that
# to be able to use e.g. the "replace" handler, the
# charmap has to have a mapping for "?".
charmap = dict((ord(c), bytes(2*c.upper(), 'ascii')) for c in "abcdefgh")
sin = "abc"
sout = b"AABBCC"
self.assertEqual(codecs.charmap_encode(sin, "strict", charmap)[0], sout)
sin = "abcA"
self.assertRaises(UnicodeError, codecs.charmap_encode, sin, "strict", charmap)
charmap[ord("?")] = b"XYZ"
sin = "abcDEF"
sout = b"AABBCCXYZXYZXYZ"
self.assertEqual(codecs.charmap_encode(sin, "replace", charmap)[0], sout)
charmap[ord("?")] = "XYZ" # wrong type in mapping
self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap)
def test_decodeunicodeinternal(self):
with test.support.check_warnings(('unicode_internal codec has been '
'deprecated', DeprecationWarning)):
self.assertRaises(
UnicodeDecodeError,
b"\x00\x00\x00\x00\x00".decode,
"unicode-internal",
)
if len('\0'.encode('unicode-internal')) == 4:
def handler_unicodeinternal(exc):
if not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
return ("\x01", 1)
self.assertEqual(
b"\x00\x00\x00\x00\x00".decode("unicode-internal", "ignore"),
"\u0000"
)
self.assertEqual(
b"\x00\x00\x00\x00\x00".decode("unicode-internal", "replace"),
"\u0000\ufffd"
)
self.assertEqual(
b"\x00\x00\x00\x00\x00".decode("unicode-internal", "backslashreplace"),
"\u0000\\x00"
)
codecs.register_error("test.hui", handler_unicodeinternal)
self.assertEqual(
b"\x00\x00\x00\x00\x00".decode("unicode-internal", "test.hui"),
"\u0000\u0001\u0000"
)
def test_callbacks(self):
def handler1(exc):
r = range(exc.start, exc.end)
if isinstance(exc, UnicodeEncodeError):
l = ["<%d>" % ord(exc.object[pos]) for pos in r]
elif isinstance(exc, UnicodeDecodeError):
l = ["<%d>" % exc.object[pos] for pos in r]
else:
raise TypeError("don't know how to handle %r" % exc)
return ("[%s]" % "".join(l), exc.end)
codecs.register_error("test.handler1", handler1)
def handler2(exc):
if not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
l = ["<%d>" % exc.object[pos] for pos in range(exc.start, exc.end)]
return ("[%s]" % "".join(l), exc.end+1) # skip one character
codecs.register_error("test.handler2", handler2)
s = b"\x00\x81\x7f\x80\xff"
self.assertEqual(
s.decode("ascii", "test.handler1"),
"\x00[<129>]\x7f[<128>][<255>]"
)
self.assertEqual(
s.decode("ascii", "test.handler2"),
"\x00[<129>][<128>]"
)
self.assertEqual(
b"\\u3042\\u3xxx".decode("unicode-escape", "test.handler1"),
"\u3042[<92><117><51>]xxx"
)
self.assertEqual(
b"\\u3042\\u3xx".decode("unicode-escape", "test.handler1"),
"\u3042[<92><117><51>]xx"
)
self.assertEqual(
codecs.charmap_decode(b"abc", "test.handler1", {ord("a"): "z"})[0],
"z[<98>][<99>]"
)
self.assertEqual(
"g\xfc\xdfrk".encode("ascii", "test.handler1"),
b"g[<252><223>]rk"
)
self.assertEqual(
"g\xfc\xdf".encode("ascii", "test.handler1"),
b"g[<252><223>]"
)
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace", "namereplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in ("x", "\u3042", "a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def check_exceptionobjectargs(self, exctype, args, msg):
# Test UnicodeError subclasses: construction, attribute assignment and __str__ conversion
# check with one missing argument
self.assertRaises(TypeError, exctype, *args[:-1])
# check with one argument too much
self.assertRaises(TypeError, exctype, *(args + ["too much"]))
# check with one argument of the wrong type
wrongargs = [ "spam", b"eggs", b"spam", 42, 1.0, None ]
for i in range(len(args)):
for wrongarg in wrongargs:
if type(wrongarg) is type(args[i]):
continue
# build argument array
callargs = []
for j in range(len(args)):
if i==j:
callargs.append(wrongarg)
else:
callargs.append(args[i])
self.assertRaises(TypeError, exctype, *callargs)
# check with the correct number and type of arguments
exc = exctype(*args)
self.assertEqual(str(exc), msg)
def test_unicodeencodeerror(self):
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "g\xfcrk", 1, 2, "ouch"],
"'ascii' codec can't encode character '\\xfc' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "g\xfcrk", 1, 4, "ouch"],
"'ascii' codec can't encode characters in position 1-3: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "\xfcx", 0, 1, "ouch"],
"'ascii' codec can't encode character '\\xfc' in position 0: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "\u0100x", 0, 1, "ouch"],
"'ascii' codec can't encode character '\\u0100' in position 0: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "\uffffx", 0, 1, "ouch"],
"'ascii' codec can't encode character '\\uffff' in position 0: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", "\U00010000x", 0, 1, "ouch"],
"'ascii' codec can't encode character '\\U00010000' in position 0: ouch"
)
def test_unicodedecodeerror(self):
self.check_exceptionobjectargs(
UnicodeDecodeError,
["ascii", bytearray(b"g\xfcrk"), 1, 2, "ouch"],
"'ascii' codec can't decode byte 0xfc in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeDecodeError,
["ascii", bytearray(b"g\xfcrk"), 1, 3, "ouch"],
"'ascii' codec can't decode bytes in position 1-2: ouch"
)
def test_unicodetranslateerror(self):
self.check_exceptionobjectargs(
UnicodeTranslateError,
["g\xfcrk", 1, 2, "ouch"],
"can't translate character '\\xfc' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeTranslateError,
["g\u0100rk", 1, 2, "ouch"],
"can't translate character '\\u0100' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeTranslateError,
["g\uffffrk", 1, 2, "ouch"],
"can't translate character '\\uffff' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeTranslateError,
["g\U00010000rk", 1, 2, "ouch"],
"can't translate character '\\U00010000' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeTranslateError,
["g\xfcrk", 1, 3, "ouch"],
"can't translate characters in position 1-2: ouch"
)
def test_badandgoodstrictexceptions(self):
# "strict" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.strict_errors,
42
)
# "strict" complains about the wrong exception type
self.assertRaises(
Exception,
codecs.strict_errors,
Exception("ouch")
)
# If the correct exception is passed in, "strict" raises it
self.assertRaises(
UnicodeEncodeError,
codecs.strict_errors,
UnicodeEncodeError("ascii", "\u3042", 0, 1, "ouch")
)
self.assertRaises(
UnicodeDecodeError,
codecs.strict_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")
)
self.assertRaises(
UnicodeTranslateError,
codecs.strict_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch")
)
def test_badandgoodignoreexceptions(self):
# "ignore" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.ignore_errors,
42
)
# "ignore" complains about the wrong exception type
self.assertRaises(
TypeError,
codecs.ignore_errors,
UnicodeError("ouch")
)
# If the correct exception is passed in, "ignore" returns an empty replacement
self.assertEqual(
codecs.ignore_errors(
UnicodeEncodeError("ascii", "a\u3042b", 1, 2, "ouch")),
("", 2)
)
self.assertEqual(
codecs.ignore_errors(
UnicodeDecodeError("ascii", bytearray(b"a\xffb"), 1, 2, "ouch")),
("", 2)
)
self.assertEqual(
codecs.ignore_errors(
UnicodeTranslateError("a\u3042b", 1, 2, "ouch")),
("", 2)
)
def test_badandgoodreplaceexceptions(self):
# "replace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.replace_errors,
42
)
# "replace" complains about the wrong exception type
self.assertRaises(
TypeError,
codecs.replace_errors,
UnicodeError("ouch")
)
self.assertRaises(
TypeError,
codecs.replace_errors,
BadObjectUnicodeEncodeError()
)
self.assertRaises(
TypeError,
codecs.replace_errors,
BadObjectUnicodeDecodeError()
)
# With the correct exception, "replace" returns an "?" or "\ufffd" replacement
self.assertEqual(
codecs.replace_errors(
UnicodeEncodeError("ascii", "a\u3042b", 1, 2, "ouch")),
("?", 2)
)
self.assertEqual(
codecs.replace_errors(
UnicodeDecodeError("ascii", bytearray(b"a\xffb"), 1, 2, "ouch")),
("\ufffd", 2)
)
self.assertEqual(
codecs.replace_errors(
UnicodeTranslateError("a\u3042b", 1, 2, "ouch")),
("\ufffd", 2)
)
def test_badandgoodxmlcharrefreplaceexceptions(self):
# "xmlcharrefreplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
42
)
# "xmlcharrefreplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeError("ouch")
)
# "xmlcharrefreplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch")
)
# Use the correct exception
cs = (0, 1, 9, 10, 99, 100, 999, 1000, 9999, 10000, 99999, 100000,
999999, 1000000)
cs += (0xd800, 0xdfff)
s = "".join(chr(c) for c in cs)
self.assertEqual(
codecs.xmlcharrefreplace_errors(
UnicodeEncodeError("ascii", "a" + s + "b",
1, 1 + len(s), "ouch")
),
("".join("&#%d;" % c for c in cs), 1 + len(s))
)
def test_badandgoodbackslashreplaceexceptions(self):
# "backslashreplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
42
)
# "backslashreplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
UnicodeError("ouch")
)
# Use the correct exception
tests = [
("\u3042", "\\u3042"),
("\n", "\\x0a"),
("a", "\\x61"),
("\x00", "\\x00"),
("\xff", "\\xff"),
("\u0100", "\\u0100"),
("\uffff", "\\uffff"),
("\U00010000", "\\U00010000"),
("\U0010ffff", "\\U0010ffff"),
# Lone surrogates
("\ud800", "\\ud800"),
("\udfff", "\\udfff"),
("\ud800\udfff", "\\ud800\\udfff"),
]
for s, r in tests:
with self.subTest(str=s):
self.assertEqual(
codecs.backslashreplace_errors(
UnicodeEncodeError("ascii", "a" + s + "b",
1, 1 + len(s), "ouch")),
(r, 1 + len(s))
)
self.assertEqual(
codecs.backslashreplace_errors(
UnicodeTranslateError("a" + s + "b",
1, 1 + len(s), "ouch")),
(r, 1 + len(s))
)
tests = [
(b"a", "\\x61"),
(b"\n", "\\x0a"),
(b"\x00", "\\x00"),
(b"\xff", "\\xff"),
]
for b, r in tests:
with self.subTest(bytes=b):
self.assertEqual(
codecs.backslashreplace_errors(
UnicodeDecodeError("ascii", bytearray(b"a" + b + b"b"),
1, 2, "ouch")),
(r, 2)
)
def test_badandgoodnamereplaceexceptions(self):
# "namereplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.namereplace_errors,
42
)
# "namereplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeError("ouch")
)
# "namereplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch")
)
# Use the correct exception
tests = [
("\u3042", "\\N{HIRAGANA LETTER A}"),
("\x00", "\\x00"),
("\ufbf9", "\\N{ARABIC LIGATURE UIGHUR KIRGHIZ YEH WITH "
"HAMZA ABOVE WITH ALEF MAKSURA ISOLATED FORM}"),
("\U000e007f", "\\N{CANCEL TAG}"),
("\U0010ffff", "\\U0010ffff"),
# Lone surrogates
("\ud800", "\\ud800"),
("\udfff", "\\udfff"),
("\ud800\udfff", "\\ud800\\udfff"),
]
for s, r in tests:
with self.subTest(str=s):
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "a" + s + "b",
1, 1 + len(s), "ouch")),
(r, 1 + len(s))
)
def test_badandgoodsurrogateescapeexceptions(self):
surrogateescape_errors = codecs.lookup_error('surrogateescape')
# "surrogateescape" complains about a non-exception passed in
self.assertRaises(
TypeError,
surrogateescape_errors,
42
)
# "surrogateescape" complains about the wrong exception types
self.assertRaises(
TypeError,
surrogateescape_errors,
UnicodeError("ouch")
)
# "surrogateescape" can not be used for translating
self.assertRaises(
TypeError,
surrogateescape_errors,
UnicodeTranslateError("\udc80", 0, 1, "ouch")
)
# Use the correct exception
for s in ("a", "\udc7f", "\udd00"):
with self.subTest(str=s):
self.assertRaises(
UnicodeEncodeError,
surrogateescape_errors,
UnicodeEncodeError("ascii", s, 0, 1, "ouch")
)
self.assertEqual(
surrogateescape_errors(
UnicodeEncodeError("ascii", "a\udc80b", 1, 2, "ouch")),
(b"\x80", 2)
)
self.assertRaises(
UnicodeDecodeError,
surrogateescape_errors,
UnicodeDecodeError("ascii", bytearray(b"a"), 0, 1, "ouch")
)
self.assertEqual(
surrogateescape_errors(
UnicodeDecodeError("ascii", bytearray(b"a\x80b"), 1, 2, "ouch")),
("\udc80", 2)
)
def test_badandgoodsurrogatepassexceptions(self):
surrogatepass_errors = codecs.lookup_error('surrogatepass')
# "surrogatepass" complains about a non-exception passed in
self.assertRaises(
TypeError,
surrogatepass_errors,
42
)
# "surrogatepass" complains about the wrong exception types
self.assertRaises(
TypeError,
surrogatepass_errors,
UnicodeError("ouch")
)
# "surrogatepass" can not be used for translating
self.assertRaises(
TypeError,
surrogatepass_errors,
UnicodeTranslateError("\ud800", 0, 1, "ouch")
)
# Use the correct exception
for enc in ("utf-8", "utf-16le", "utf-16be", "utf-32le", "utf-32be"):
with self.subTest(encoding=enc):
self.assertRaises(
UnicodeEncodeError,
surrogatepass_errors,
UnicodeEncodeError(enc, "a", 0, 1, "ouch")
)
self.assertRaises(
UnicodeDecodeError,
surrogatepass_errors,
UnicodeDecodeError(enc, "a".encode(enc), 0, 1, "ouch")
)
for s in ("\ud800", "\udfff", "\ud800\udfff"):
with self.subTest(str=s):
self.assertRaises(
UnicodeEncodeError,
surrogatepass_errors,
UnicodeEncodeError("ascii", s, 0, len(s), "ouch")
)
tests = [
("utf-8", "\ud800", b'\xed\xa0\x80', 3),
("utf-16le", "\ud800", b'\x00\xd8', 2),
("utf-16be", "\ud800", b'\xd8\x00', 2),
("utf-32le", "\ud800", b'\x00\xd8\x00\x00', 4),
("utf-32be", "\ud800", b'\x00\x00\xd8\x00', 4),
("utf-8", "\udfff", b'\xed\xbf\xbf', 3),
("utf-16le", "\udfff", b'\xff\xdf', 2),
("utf-16be", "\udfff", b'\xdf\xff', 2),
("utf-32le", "\udfff", b'\xff\xdf\x00\x00', 4),
("utf-32be", "\udfff", b'\x00\x00\xdf\xff', 4),
("utf-8", "\ud800\udfff", b'\xed\xa0\x80\xed\xbf\xbf', 3),
("utf-16le", "\ud800\udfff", b'\x00\xd8\xff\xdf', 2),
("utf-16be", "\ud800\udfff", b'\xd8\x00\xdf\xff', 2),
("utf-32le", "\ud800\udfff", b'\x00\xd8\x00\x00\xff\xdf\x00\x00', 4),
("utf-32be", "\ud800\udfff", b'\x00\x00\xd8\x00\x00\x00\xdf\xff', 4),
]
for enc, s, b, n in tests:
with self.subTest(encoding=enc, str=s, bytes=b):
self.assertEqual(
surrogatepass_errors(
UnicodeEncodeError(enc, "a" + s + "b",
1, 1 + len(s), "ouch")),
(b, 1 + len(s))
)
self.assertEqual(
surrogatepass_errors(
UnicodeDecodeError(enc, bytearray(b"a" + b[:n] + b"b"),
1, 1 + n, "ouch")),
(s[:1], 1 + n)
)
def test_badhandlerresults(self):
results = ( 42, "foo", (1,2,3), ("foo", 1, 3), ("foo", None), ("foo",), ("foo", 1, 3), ("foo", None), ("foo",) )
encs = ("ascii", "latin-1", "iso-8859-1", "iso-8859-15")
for res in results:
codecs.register_error("test.badhandler", lambda x: res)
for enc in encs:
self.assertRaises(
TypeError,
"\u3042".encode,
enc,
"test.badhandler"
)
for (enc, bytes) in (
("ascii", b"\xff"),
("utf-8", b"\xff"),
("utf-7", b"+x-"),
("unicode-internal", b"\x00"),
):
with test.support.check_warnings():
# unicode-internal has been deprecated
self.assertRaises(
TypeError,
bytes.decode,
enc,
"test.badhandler"
)
def test_lookup(self):
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(codecs.ignore_errors, codecs.lookup_error("ignore"))
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(
codecs.xmlcharrefreplace_errors,
codecs.lookup_error("xmlcharrefreplace")
)
self.assertEqual(
codecs.backslashreplace_errors,
codecs.lookup_error("backslashreplace")
)
self.assertEqual(
codecs.namereplace_errors,
codecs.lookup_error("namereplace")
)
def test_unencodablereplacement(self):
def unencrepl(exc):
if isinstance(exc, UnicodeEncodeError):
return ("\u4242", exc.end)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error("test.unencreplhandler", unencrepl)
for enc in ("ascii", "iso-8859-1", "iso-8859-15"):
self.assertRaises(
UnicodeEncodeError,
"\u4242".encode,
enc,
"test.unencreplhandler"
)
def test_badregistercall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::register_error()
# Python/codecs.c::PyCodec_RegisterError()
self.assertRaises(TypeError, codecs.register_error, 42)
self.assertRaises(TypeError, codecs.register_error, "test.dummy", 42)
def test_badlookupcall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(TypeError, codecs.lookup_error)
def test_unknownhandler(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(LookupError, codecs.lookup_error, "test.unknown")
def test_xmlcharrefvalues(self):
# enhance coverage of:
# Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
# and inline implementations
v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000, 100000,
500000, 1000000)
s = "".join([chr(x) for x in v])
codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
for enc in ("ascii", "iso-8859-15"):
for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
s.encode(enc, err)
def test_decodehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_decode_call_errorhandler()
# and callers
self.assertRaises(LookupError, b"\xff".decode, "ascii", "test.unknown")
def baddecodereturn1(exc):
return 42
codecs.register_error("test.baddecodereturn1", baddecodereturn1)
self.assertRaises(TypeError, b"\xff".decode, "ascii", "test.baddecodereturn1")
self.assertRaises(TypeError, b"\\".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, b"\\x0".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, b"\\x0y".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, b"\\Uffffeeee".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, b"\\uyyyy".decode, "raw-unicode-escape", "test.baddecodereturn1")
def baddecodereturn2(exc):
return ("?", None)
codecs.register_error("test.baddecodereturn2", baddecodereturn2)
self.assertRaises(TypeError, b"\xff".decode, "ascii", "test.baddecodereturn2")
handler = PosReturn()
codecs.register_error("test.posreturn", handler.handle)
# Valid negative position
handler.pos = -1
self.assertEqual(b"\xff0".decode("ascii", "test.posreturn"), "<?>0")
# Valid negative position
handler.pos = -2
self.assertEqual(b"\xff0".decode("ascii", "test.posreturn"), "<?><?>")
# Negative position out of bounds
handler.pos = -3
self.assertRaises(IndexError, b"\xff0".decode, "ascii", "test.posreturn")
# Valid positive position
handler.pos = 1
self.assertEqual(b"\xff0".decode("ascii", "test.posreturn"), "<?>0")
# Largest valid positive position (one beyond end of input)
handler.pos = 2
self.assertEqual(b"\xff0".decode("ascii", "test.posreturn"), "<?>")
# Invalid positive position
handler.pos = 3
self.assertRaises(IndexError, b"\xff0".decode, "ascii", "test.posreturn")
# Restart at the "0"
handler.pos = 6
self.assertEqual(b"\\uyyyy0".decode("raw-unicode-escape", "test.posreturn"), "<?>0")
class D(dict):
def __getitem__(self, key):
raise ValueError
self.assertRaises(UnicodeError, codecs.charmap_decode, b"\xff", "strict", {0xff: None})
self.assertRaises(ValueError, codecs.charmap_decode, b"\xff", "strict", D())
self.assertRaises(TypeError, codecs.charmap_decode, b"\xff", "strict", {0xff: sys.maxunicode+1})
def test_encodehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_encode_call_errorhandler()
# and callers
self.assertRaises(LookupError, "\xff".encode, "ascii", "test.unknown")
def badencodereturn1(exc):
return 42
codecs.register_error("test.badencodereturn1", badencodereturn1)
self.assertRaises(TypeError, "\xff".encode, "ascii", "test.badencodereturn1")
def badencodereturn2(exc):
return ("?", None)
codecs.register_error("test.badencodereturn2", badencodereturn2)
self.assertRaises(TypeError, "\xff".encode, "ascii", "test.badencodereturn2")
handler = PosReturn()
codecs.register_error("test.posreturn", handler.handle)
# Valid negative position
handler.pos = -1
self.assertEqual("\xff0".encode("ascii", "test.posreturn"), b"<?>0")
# Valid negative position
handler.pos = -2
self.assertEqual("\xff0".encode("ascii", "test.posreturn"), b"<?><?>")
# Negative position out of bounds
handler.pos = -3
self.assertRaises(IndexError, "\xff0".encode, "ascii", "test.posreturn")
# Valid positive position
handler.pos = 1
self.assertEqual("\xff0".encode("ascii", "test.posreturn"), b"<?>0")
# Largest valid positive position (one beyond end of input
handler.pos = 2
self.assertEqual("\xff0".encode("ascii", "test.posreturn"), b"<?>")
# Invalid positive position
handler.pos = 3
self.assertRaises(IndexError, "\xff0".encode, "ascii", "test.posreturn")
handler.pos = 0
class D(dict):
def __getitem__(self, key):
raise ValueError
for err in ("strict", "replace", "xmlcharrefreplace",
"backslashreplace", "namereplace", "test.posreturn"):
self.assertRaises(UnicodeError, codecs.charmap_encode, "\xff", err, {0xff: None})
self.assertRaises(ValueError, codecs.charmap_encode, "\xff", err, D())
self.assertRaises(TypeError, codecs.charmap_encode, "\xff", err, {0xff: 300})
def test_translatehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_encode_call_errorhandler()
# and callers
# (Unfortunately the errors argument is not directly accessible
# from Python, so we can't test that much)
class D(dict):
def __getitem__(self, key):
raise ValueError
#self.assertRaises(ValueError, "\xff".translate, D())
self.assertRaises(ValueError, "\xff".translate, {0xff: sys.maxunicode+1})
self.assertRaises(TypeError, "\xff".translate, {0xff: ()})
def test_bug828737(self):
charmap = {
ord("&"): "&",
ord("<"): "<",
ord(">"): ">",
ord('"'): """,
}
for n in (1, 10, 100, 1000):
text = 'abc<def>ghi'*n
text.translate(charmap)
def test_mutatingdecodehandler(self):
baddata = [
("ascii", b"\xff"),
("utf-7", b"++"),
("utf-8", b"\xff"),
("utf-16", b"\xff"),
("utf-32", b"\xff"),
("unicode-escape", b"\\u123g"),
("raw-unicode-escape", b"\\u123g"),
("unicode-internal", b"\xff"),
]
def replacing(exc):
if isinstance(exc, UnicodeDecodeError):
exc.object = 42
return ("\u4242", 0)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error("test.replacing", replacing)
with test.support.check_warnings():
# unicode-internal has been deprecated
for (encoding, data) in baddata:
with self.assertRaises(TypeError):
data.decode(encoding, "test.replacing")
def mutating(exc):
if isinstance(exc, UnicodeDecodeError):
exc.object = b""
return ("\u4242", 0)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error("test.mutating", mutating)
# If the decoder doesn't pick up the modified input the following
# will lead to an endless loop
with test.support.check_warnings():
# unicode-internal has been deprecated
for (encoding, data) in baddata:
self.assertEqual(data.decode(encoding, "test.mutating"), "\u4242")
# issue32583
def test_crashing_decode_handler(self):
# better generating one more character to fill the extra space slot
# so in debug build it can steadily fail
def forward_shorter_than_end(exc):
if isinstance(exc, UnicodeDecodeError):
# size one character, 0 < forward < exc.end
return ('\ufffd', exc.start+1)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error(
"test.forward_shorter_than_end", forward_shorter_than_end)
self.assertEqual(
b'\xd8\xd8\xd8\xd8\xd8\x00\x00\x00'.decode(
'utf-16-le', 'test.forward_shorter_than_end'),
'\ufffd\ufffd\ufffd\ufffd\xd8\x00'
)
self.assertEqual(
b'\xd8\xd8\xd8\xd8\x00\xd8\x00\x00'.decode(
'utf-16-be', 'test.forward_shorter_than_end'),
'\ufffd\ufffd\ufffd\ufffd\xd8\x00'
)
self.assertEqual(
b'\x11\x11\x11\x11\x11\x00\x00\x00\x00\x00\x00'.decode(
'utf-32-le', 'test.forward_shorter_than_end'),
'\ufffd\ufffd\ufffd\u1111\x00'
)
self.assertEqual(
b'\x11\x11\x11\x00\x00\x11\x11\x00\x00\x00\x00'.decode(
'utf-32-be', 'test.forward_shorter_than_end'),
'\ufffd\ufffd\ufffd\u1111\x00'
)
def replace_with_long(exc):
if isinstance(exc, UnicodeDecodeError):
exc.object = b"\x00" * 8
return ('\ufffd', exc.start)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error("test.replace_with_long", replace_with_long)
self.assertEqual(
b'\x00'.decode('utf-16', 'test.replace_with_long'),
'\ufffd\x00\x00\x00\x00'
)
self.assertEqual(
b'\x00'.decode('utf-32', 'test.replace_with_long'),
'\ufffd\x00\x00'
)
def test_fake_error_class(self):
handlers = [
codecs.strict_errors,
codecs.ignore_errors,
codecs.replace_errors,
codecs.backslashreplace_errors,
codecs.namereplace_errors,
codecs.xmlcharrefreplace_errors,
codecs.lookup_error('surrogateescape'),
codecs.lookup_error('surrogatepass'),
]
for cls in UnicodeEncodeError, UnicodeDecodeError, UnicodeTranslateError:
class FakeUnicodeError(str):
__class__ = cls
for handler in handlers:
with self.subTest(handler=handler, error_class=cls):
self.assertRaises(TypeError, handler, FakeUnicodeError())
class FakeUnicodeError(Exception):
__class__ = cls
for handler in handlers:
with self.subTest(handler=handler, error_class=cls):
with self.assertRaises((TypeError, FakeUnicodeError)):
handler(FakeUnicodeError())
if __name__ == "__main__":
unittest.main()
|