diff options
Diffstat (limited to 'Lib/test/test_unicode.py')
| -rw-r--r-- | Lib/test/test_unicode.py | 54 |
1 files changed, 42 insertions, 12 deletions
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 5efbe3e..3fcb590 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -8,6 +8,7 @@ Written by Marc-Andre Lemburg (mal@lemburg.com). import _string import codecs import itertools +import operator import struct import sys import unittest @@ -315,6 +316,7 @@ class UnicodeTest(string_tests.CommonTest, {ord('a'): None, ord('b'): ''}) self.checkequalnofix('xyyx', 'xzx', 'translate', {ord('z'): 'yy'}) + # this needs maketrans() self.checkequalnofix('abababc', 'abababc', 'translate', {'b': '<i>'}) @@ -324,6 +326,33 @@ class UnicodeTest(string_tests.CommonTest, tbl = self.type2test.maketrans('abc', 'xyz', 'd') self.checkequalnofix('xyzzy', 'abdcdcbdddd', 'translate', tbl) + # various tests switching from ASCII to latin1 or the opposite; + # same length, remove a letter, or replace with a longer string. + self.assertEqual("[a]".translate(str.maketrans('a', 'X')), + "[X]") + self.assertEqual("[a]".translate(str.maketrans({'a': 'X'})), + "[X]") + self.assertEqual("[a]".translate(str.maketrans({'a': None})), + "[]") + self.assertEqual("[a]".translate(str.maketrans({'a': 'XXX'})), + "[XXX]") + self.assertEqual("[a]".translate(str.maketrans({'a': '\xe9'})), + "[\xe9]") + self.assertEqual("[a]".translate(str.maketrans({'a': '<\xe9>'})), + "[<\xe9>]") + self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': 'a'})), + "[a]") + self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': None})), + "[]") + + # invalid Unicode characters + invalid_char = 0x10ffff+1 + for before in "a\xe9\u20ac\U0010ffff": + mapping = str.maketrans({before: invalid_char}) + text = "[%s]" % before + self.assertRaises(ValueError, text.translate, mapping) + + # errors self.assertRaises(TypeError, self.type2test.maketrans) self.assertRaises(ValueError, self.type2test.maketrans, 'abc', 'defg') self.assertRaises(TypeError, self.type2test.maketrans, 2, 'def') @@ -1306,20 +1335,20 @@ class UnicodeTest(string_tests.CommonTest, self.assertEqual('%.2s' % "a\xe9\u20ac", 'a\xe9') #issue 19995 - class PsuedoInt: + class PseudoInt: def __init__(self, value): self.value = int(value) def __int__(self): return self.value def __index__(self): return self.value - class PsuedoFloat: + class PseudoFloat: def __init__(self, value): self.value = float(value) def __int__(self): return int(self.value) - pi = PsuedoFloat(3.1415) - letter_m = PsuedoInt(109) + pi = PseudoFloat(3.1415) + letter_m = PseudoInt(109) self.assertEqual('%x' % 42, '2a') self.assertEqual('%X' % 15, 'F') self.assertEqual('%o' % 9, '11') @@ -1328,11 +1357,11 @@ class UnicodeTest(string_tests.CommonTest, self.assertEqual('%X' % letter_m, '6D') self.assertEqual('%o' % letter_m, '155') self.assertEqual('%c' % letter_m, 'm') - self.assertWarns(DeprecationWarning, '%x'.__mod__, pi), - self.assertWarns(DeprecationWarning, '%x'.__mod__, 3.14), - self.assertWarns(DeprecationWarning, '%X'.__mod__, 2.11), - self.assertWarns(DeprecationWarning, '%o'.__mod__, 1.79), - self.assertWarns(DeprecationWarning, '%c'.__mod__, pi), + self.assertRaisesRegex(TypeError, '%x format: an integer is required, not float', operator.mod, '%x', 3.14), + self.assertRaisesRegex(TypeError, '%X format: an integer is required, not float', operator.mod, '%X', 2.11), + self.assertRaisesRegex(TypeError, '%o format: an integer is required, not float', operator.mod, '%o', 1.79), + self.assertRaisesRegex(TypeError, '%x format: an integer is required, not PseudoFloat', operator.mod, '%x', pi), + self.assertRaises(TypeError, operator.mod, '%c', pi), def test_formatting_with_enum(self): # issue18780 @@ -2052,7 +2081,8 @@ class UnicodeTest(string_tests.CommonTest, 'cp863', 'cp865', 'cp866', 'cp1125', 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15', 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6', - 'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1', + 'iso8859_7', 'iso8859_9', + 'koi8_r', 'koi8_t', 'koi8_u', 'kz1048', 'latin_1', 'mac_cyrillic', 'mac_latin2', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', @@ -2080,14 +2110,14 @@ class UnicodeTest(string_tests.CommonTest, 'cp863', 'cp865', 'cp866', 'cp1125', 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15', 'iso8859_2', 'iso8859_4', 'iso8859_5', - 'iso8859_9', 'koi8_r', 'latin_1', + 'iso8859_9', 'koi8_r', 'koi8_u', 'latin_1', 'mac_cyrillic', 'mac_latin2', ### These have undefined mappings: #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', #'cp1256', 'cp1257', 'cp1258', #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874', - #'iso8859_3', 'iso8859_6', 'iso8859_7', + #'iso8859_3', 'iso8859_6', 'iso8859_7', 'koi8_t', 'kz1048', #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish', ### These fail the round-trip: |