mirror of
https://github.com/RustPython/RustPython.git
synced 2026-10-28 18:59:04 +08:00
Update test_unicodedata.py to 3.14.4 (#7750)
* Update `test_unicodedata.py` to 3.14.4 * Add test asset * Mark failing tests * Add `expectedSuccess` docorator * Add support for nee decorator in patch_spec * Reapply patches
This commit is contained in:
Shahar Naveh authored and GitHub committed
1 parent
c0005f744b
commit
b1df45bd09
4 files changed
+17551
-90
No files matched your search
Vendored
+17035
File diff suppressed because it is too large.
Load diff
Vendored
+506
-88
@@ -6,6 +6,7 @@
|
||||
|
||||
"""
|
||||
|
||||
from functools import partial
|
||||
import hashlib
|
||||
from http.client import HTTPException
|
||||
import sys
|
||||
@@ -18,21 +19,32 @@ from test.support import (
|
||||
cpython_only,
|
||||
check_disallow_instantiation,
|
||||
force_not_colorized,
|
||||
is_resource_enabled,
|
||||
findfile,
|
||||
)
|
||||
|
||||
|
||||
quicktest = not is_resource_enabled('cpu')
|
||||
|
||||
def iterallchars():
|
||||
maxunicode = 0xffff if quicktest else sys.maxunicode
|
||||
return map(chr, range(maxunicode + 1))
|
||||
|
||||
class UnicodeMethodsTest(unittest.TestCase):
|
||||
|
||||
# update this, if the database changes
|
||||
expectedchecksum = '9e43ee3929471739680c0e705482b4ae1c4122e4'
|
||||
expectedchecksum = ('486bf97d506d0ccf0e463fd1f40c51029805af5a'
|
||||
if quicktest else
|
||||
'9e43ee3929471739680c0e705482b4ae1c4122e4')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; + 9e43ee3929471739680c0e705482b4ae1c4122e4
|
||||
@requires_resource('cpu')
|
||||
def test_method_checksum(self):
|
||||
h = hashlib.sha1()
|
||||
for i in range(sys.maxunicode + 1):
|
||||
char = chr(i)
|
||||
data = [
|
||||
for char in iterallchars():
|
||||
s1 = char + 'abc'
|
||||
s2 = char + 'ABC'
|
||||
s3 = char + '123'
|
||||
data = (
|
||||
# Predicates (single char)
|
||||
"01"[char.isalnum()],
|
||||
"01"[char.isalpha()],
|
||||
@@ -45,15 +57,15 @@ class UnicodeMethodsTest(unittest.TestCase):
|
||||
"01"[char.isupper()],
|
||||
|
||||
# Predicates (multiple chars)
|
||||
"01"[(char + 'abc').isalnum()],
|
||||
"01"[(char + 'abc').isalpha()],
|
||||
"01"[(char + '123').isdecimal()],
|
||||
"01"[(char + '123').isdigit()],
|
||||
"01"[(char + 'abc').islower()],
|
||||
"01"[(char + '123').isnumeric()],
|
||||
"01"[s1.isalnum()],
|
||||
"01"[s1.isalpha()],
|
||||
"01"[s3.isdecimal()],
|
||||
"01"[s3.isdigit()],
|
||||
"01"[s1.islower()],
|
||||
"01"[s3.isnumeric()],
|
||||
"01"[(char + ' \t').isspace()],
|
||||
"01"[(char + 'abc').istitle()],
|
||||
"01"[(char + 'ABC').isupper()],
|
||||
"01"[s1.istitle()],
|
||||
"01"[s2.isupper()],
|
||||
|
||||
# Mappings (single char)
|
||||
char.lower(),
|
||||
@@ -61,55 +73,106 @@ class UnicodeMethodsTest(unittest.TestCase):
|
||||
char.title(),
|
||||
|
||||
# Mappings (multiple chars)
|
||||
(char + 'abc').lower(),
|
||||
(char + 'ABC').upper(),
|
||||
(char + 'abc').title(),
|
||||
(char + 'ABC').title(),
|
||||
s1.lower(),
|
||||
s2.upper(),
|
||||
s1.title(),
|
||||
s2.title(),
|
||||
|
||||
]
|
||||
)
|
||||
h.update(''.join(data).encode('utf-8', 'surrogatepass'))
|
||||
result = h.hexdigest()
|
||||
self.assertEqual(result, self.expectedchecksum)
|
||||
|
||||
class UnicodeDatabaseTest(unittest.TestCase):
|
||||
db = unicodedata
|
||||
|
||||
class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
class UnicodeFunctionsTest(unittest.TestCase):
|
||||
db = unicodedata
|
||||
old = False
|
||||
|
||||
# Update this if the database changes. Make sure to do a full rebuild
|
||||
# (e.g. 'make distclean && make') to get the correct checksum.
|
||||
expectedchecksum = '23ab09ed4abdf93db23b97359108ed630dd8311d'
|
||||
expectedchecksum = ('1ba453ec456896f1190d849b6e9b7c2e1a4128e0'
|
||||
if quicktest else
|
||||
'46ca89d9fe34881d0be3a4a4b29f5aa8c019640c')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AttributeError: module 'unicodedata' has no attribute 'digit'
|
||||
@requires_resource('cpu')
|
||||
def test_function_checksum(self):
|
||||
db = self.db
|
||||
data = []
|
||||
h = hashlib.sha1()
|
||||
|
||||
for i in range(sys.maxunicode + 1):
|
||||
char = chr(i)
|
||||
data = [
|
||||
for char in iterallchars():
|
||||
data = "%.12g%.12g%.12g%s%s%s%s%s%s%s" % (
|
||||
# Properties
|
||||
format(self.db.digit(char, -1), '.12g'),
|
||||
format(self.db.numeric(char, -1), '.12g'),
|
||||
format(self.db.decimal(char, -1), '.12g'),
|
||||
self.db.category(char),
|
||||
self.db.bidirectional(char),
|
||||
self.db.decomposition(char),
|
||||
str(self.db.mirrored(char)),
|
||||
str(self.db.combining(char)),
|
||||
unicodedata.east_asian_width(char),
|
||||
self.db.name(char, ""),
|
||||
]
|
||||
h.update(''.join(data).encode("ascii"))
|
||||
db.digit(char, -1),
|
||||
db.numeric(char, -1),
|
||||
db.decimal(char, -1),
|
||||
db.category(char),
|
||||
db.bidirectional(char),
|
||||
db.decomposition(char),
|
||||
db.mirrored(char),
|
||||
db.combining(char),
|
||||
db.east_asian_width(char),
|
||||
db.name(char, ""),
|
||||
)
|
||||
h.update(data.encode("ascii"))
|
||||
result = h.hexdigest()
|
||||
self.assertEqual(result, self.expectedchecksum)
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: None != 'EGYPTIAN HIEROGLYPH-13460'
|
||||
def test_name(self):
|
||||
name = self.db.name
|
||||
self.assertRaises(ValueError, name, '\0')
|
||||
self.assertRaises(ValueError, name, '\n')
|
||||
self.assertRaises(ValueError, name, '\x1F')
|
||||
self.assertRaises(ValueError, name, '\x7F')
|
||||
self.assertRaises(ValueError, name, '\x9F')
|
||||
self.assertRaises(ValueError, name, '\uFFFE')
|
||||
self.assertRaises(ValueError, name, '\uFFFF')
|
||||
self.assertRaises(ValueError, name, '\U0010FFFF')
|
||||
self.assertEqual(name('\U0010FFFF', 42), 42)
|
||||
|
||||
self.assertEqual(name(' '), 'SPACE')
|
||||
self.assertEqual(name('1'), 'DIGIT ONE')
|
||||
self.assertEqual(name('A'), 'LATIN CAPITAL LETTER A')
|
||||
self.assertEqual(name('\xA0'), 'NO-BREAK SPACE')
|
||||
self.assertEqual(name('\u0221', None), None if self.old else
|
||||
'LATIN SMALL LETTER D WITH CURL')
|
||||
self.assertEqual(name('\u3400'), 'CJK UNIFIED IDEOGRAPH-3400')
|
||||
self.assertEqual(name('\u9FA5'), 'CJK UNIFIED IDEOGRAPH-9FA5')
|
||||
self.assertEqual(name('\uAC00'), 'HANGUL SYLLABLE GA')
|
||||
self.assertEqual(name('\uD7A3'), 'HANGUL SYLLABLE HIH')
|
||||
self.assertEqual(name('\uF900'), 'CJK COMPATIBILITY IDEOGRAPH-F900')
|
||||
self.assertEqual(name('\uFA6A'), 'CJK COMPATIBILITY IDEOGRAPH-FA6A')
|
||||
self.assertEqual(name('\uFBF9'),
|
||||
'ARABIC LIGATURE UIGHUR KIRGHIZ YEH WITH HAMZA '
|
||||
'ABOVE WITH ALEF MAKSURA ISOLATED FORM')
|
||||
self.assertEqual(name('\U00013460', None), None if self.old else
|
||||
'EGYPTIAN HIEROGLYPH-13460')
|
||||
self.assertEqual(name('\U000143FA', None), None if self.old else
|
||||
'EGYPTIAN HIEROGLYPH-143FA')
|
||||
self.assertEqual(name('\U00018B00', None), None if self.old else
|
||||
'KHITAN SMALL SCRIPT CHARACTER-18B00')
|
||||
self.assertEqual(name('\U00018CD5', None), None if self.old else
|
||||
'KHITAN SMALL SCRIPT CHARACTER-18CD5')
|
||||
self.assertEqual(name('\U00018CFF', None), None if self.old else
|
||||
'KHITAN SMALL SCRIPT CHARACTER-18CFF')
|
||||
self.assertEqual(name('\U0001B170', None), None if self.old else
|
||||
'NUSHU CHARACTER-1B170')
|
||||
self.assertEqual(name('\U0001B2FB', None), None if self.old else
|
||||
'NUSHU CHARACTER-1B2FB')
|
||||
self.assertEqual(name('\U0001FBA8', None), None if self.old else
|
||||
'BOX DRAWINGS LIGHT DIAGONAL UPPER CENTRE TO '
|
||||
'MIDDLE LEFT AND MIDDLE RIGHT TO LOWER CENTRE')
|
||||
self.assertEqual(name('\U0002A6D6'), 'CJK UNIFIED IDEOGRAPH-2A6D6')
|
||||
self.assertEqual(name('\U0002FA1D'), 'CJK COMPATIBILITY IDEOGRAPH-2FA1D')
|
||||
self.assertEqual(name('\U000323AF', None), None if self.old else
|
||||
'CJK UNIFIED IDEOGRAPH-323AF')
|
||||
|
||||
@requires_resource('cpu')
|
||||
def test_name_inverse_lookup(self):
|
||||
for i in range(sys.maxunicode + 1):
|
||||
char = chr(i)
|
||||
if looked_name := self.db.name(char, None):
|
||||
for char in iterallchars():
|
||||
looked_name = self.db.name(char, None)
|
||||
if looked_name is not None:
|
||||
self.assertEqual(self.db.lookup(looked_name), char)
|
||||
|
||||
def test_no_names_in_pua(self):
|
||||
@@ -120,6 +183,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
char = chr(i)
|
||||
self.assertRaises(ValueError, self.db.name, char)
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: KeyError not raised by lookup
|
||||
def test_lookup_nonexistant(self):
|
||||
# just make sure that lookup can fail
|
||||
for nonexistent in [
|
||||
@@ -129,9 +193,21 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
"HANDBUG",
|
||||
"MODIFIER LETTER CYRILLIC SMALL QUESTION MARK",
|
||||
"???",
|
||||
"CJK UNIFIED IDEOGRAPH-03400",
|
||||
"CJK UNIFIED IDEOGRAPH-020000",
|
||||
"CJK UNIFIED IDEOGRAPH-33FF",
|
||||
"CJK UNIFIED IDEOGRAPH-F900",
|
||||
"CJK UNIFIED IDEOGRAPH-13460",
|
||||
"CJK UNIFIED IDEOGRAPH-17000",
|
||||
"CJK UNIFIED IDEOGRAPH-18B00",
|
||||
"CJK UNIFIED IDEOGRAPH-1B170",
|
||||
"CJK COMPATIBILITY IDEOGRAPH-3400",
|
||||
"TANGUT IDEOGRAPH-3400",
|
||||
"HANGUL SYLLABLE AC00",
|
||||
]:
|
||||
self.assertRaises(KeyError, self.db.lookup, nonexistent)
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: None != 9
|
||||
def test_digit(self):
|
||||
self.assertEqual(self.db.digit('A', None), None)
|
||||
self.assertEqual(self.db.digit('9'), 9)
|
||||
@@ -140,23 +216,51 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
self.assertEqual(self.db.digit('\U00020000', None), None)
|
||||
self.assertEqual(self.db.digit('\U0001D7FD'), 7)
|
||||
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.digit('\U0001fbf9', None), 9)
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.digit('\U00016ac9', None), 9)
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.digit('\U0001e4f9', None), 9)
|
||||
|
||||
self.assertRaises(TypeError, self.db.digit)
|
||||
self.assertRaises(TypeError, self.db.digit, 'xx')
|
||||
self.assertRaises(ValueError, self.db.digit, 'x')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON
|
||||
def test_numeric(self):
|
||||
self.assertEqual(self.db.numeric('A',None), None)
|
||||
self.assertEqual(self.db.numeric('9'), 9)
|
||||
self.assertEqual(self.db.numeric('\u215b'), 0.125)
|
||||
self.assertEqual(self.db.numeric('\u2468'), 9.0)
|
||||
self.assertEqual(self.db.numeric('\ua627'), 7.0)
|
||||
self.assertEqual(self.db.numeric('\U00020000', None), None)
|
||||
self.assertEqual(self.db.numeric('\U0001012A'), 9000)
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.numeric('\U0001012A', None), None if self.old else 9000)
|
||||
# Changed in 4.1.0
|
||||
self.assertEqual(self.db.numeric('\u5793', None), 1e20 if self.old else None)
|
||||
# New in 5.0.0
|
||||
self.assertEqual(self.db.numeric('\u07c0', None), None if self.old else 0.0)
|
||||
# New in 5.1.0
|
||||
self.assertEqual(self.db.numeric('\ua627', None), None if self.old else 7.0)
|
||||
# Changed in 5.2.0
|
||||
self.assertEqual(self.db.numeric('\u09f6'), 3.0 if self.old else 3/16)
|
||||
# New in 6.0.0
|
||||
self.assertEqual(self.db.numeric('\u0b72', None), None if self.old else 0.25)
|
||||
# New in 12.0.0
|
||||
self.assertEqual(self.db.numeric('\U0001ed3c', None), None if self.old else 0.5)
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.numeric('\U0001fbf9', None), None if self.old else 9)
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.numeric('\U00016ac9', None), None if self.old else 9)
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.numeric('\U0001e4f9', None), None if self.old else 9)
|
||||
|
||||
self.assertRaises(TypeError, self.db.numeric)
|
||||
self.assertRaises(TypeError, self.db.numeric, 'xx')
|
||||
self.assertRaises(ValueError, self.db.numeric, 'x')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: None != 2
|
||||
def test_decimal(self):
|
||||
self.assertEqual(self.db.decimal('A',None), None)
|
||||
self.assertEqual(self.db.decimal('9'), 9)
|
||||
@@ -165,16 +269,43 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
self.assertEqual(self.db.decimal('\U00020000', None), None)
|
||||
self.assertEqual(self.db.decimal('\U0001D7FD'), 7)
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.decimal('\xb2', None), 2 if self.old else None)
|
||||
self.assertEqual(self.db.decimal('\u1369', None), 1 if self.old else None)
|
||||
# New in 5.0.0
|
||||
self.assertEqual(self.db.decimal('\u07c0', None), None if self.old else 0)
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.decimal('\U0001fbf9', None), None if self.old else 9)
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.decimal('\U00016ac9', None), None if self.old else 9)
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.decimal('\U0001e4f9', None), None if self.old else 9)
|
||||
|
||||
self.assertRaises(TypeError, self.db.decimal)
|
||||
self.assertRaises(TypeError, self.db.decimal, 'xx')
|
||||
self.assertRaises(ValueError, self.db.decimal, 'x')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: 'Cn' != 'Mn'
|
||||
def test_category(self):
|
||||
self.assertEqual(self.db.category('\uFFFE'), 'Cn')
|
||||
self.assertEqual(self.db.category('a'), 'Ll')
|
||||
self.assertEqual(self.db.category('A'), 'Lu')
|
||||
self.assertEqual(self.db.category('\U00020000'), 'Lo')
|
||||
self.assertEqual(self.db.category('\U0001012A'), 'No')
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.category('\U0001012A'), 'Cn' if self.old else 'No')
|
||||
self.assertEqual(self.db.category('\U000e01ef'), 'Cn' if self.old else 'Mn')
|
||||
# New in 5.1.0
|
||||
self.assertEqual(self.db.category('\u0374'), 'Sk' if self.old else 'Lm')
|
||||
# Changed in 13.0.0
|
||||
self.assertEqual(self.db.category('\u0b55'), 'Cn' if self.old else 'Mn')
|
||||
self.assertEqual(self.db.category('\U0003134a'), 'Cn' if self.old else 'Lo')
|
||||
# Changed in 14.0.0
|
||||
self.assertEqual(self.db.category('\u061d'), 'Cn' if self.old else 'Po')
|
||||
self.assertEqual(self.db.category('\U0002b738'), 'Cn' if self.old else 'Lo')
|
||||
# Changed in 15.0.0
|
||||
self.assertEqual(self.db.category('\u0cf3'), 'Cn' if self.old else 'Mc')
|
||||
self.assertEqual(self.db.category('\U000323af'), 'Cn' if self.old else 'Lo')
|
||||
|
||||
self.assertRaises(TypeError, self.db.category)
|
||||
self.assertRaises(TypeError, self.db.category, 'xx')
|
||||
@@ -186,34 +317,262 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
self.assertEqual(self.db.bidirectional('A'), 'L')
|
||||
self.assertEqual(self.db.bidirectional('\U00020000'), 'L')
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.bidirectional('+'), 'ET' if self.old else 'ES')
|
||||
self.assertEqual(self.db.bidirectional('\u0221'), '' if self.old else 'L')
|
||||
self.assertEqual(self.db.bidirectional('\U000e01ef'), '' if self.old else 'NSM')
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.bidirectional('\u0b55'), '' if self.old else 'NSM')
|
||||
self.assertEqual(self.db.bidirectional('\U0003134a'), '' if self.old else 'L')
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.bidirectional('\u061d'), '' if self.old else 'AL')
|
||||
self.assertEqual(self.db.bidirectional('\U0002b738'), '' if self.old else 'L')
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.bidirectional('\u0cf3'), '' if self.old else 'L')
|
||||
self.assertEqual(self.db.bidirectional('\U000323af'), '' if self.old else 'L')
|
||||
# New in 16.0.0
|
||||
self.assertEqual(self.db.bidirectional('\u0897'), '' if self.old else 'NSM')
|
||||
self.assertEqual(self.db.bidirectional('\U0001fbef'), '' if self.old else 'ON')
|
||||
|
||||
self.assertRaises(TypeError, self.db.bidirectional)
|
||||
self.assertRaises(TypeError, self.db.bidirectional, 'xx')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: 'D4CC 11B6' != '1111 1171 11B6'
|
||||
def test_decomposition(self):
|
||||
self.assertEqual(self.db.decomposition('\uFFFE'),'')
|
||||
self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034')
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.decomposition('\u03f9'), '' if self.old else '<compat> 03A3')
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.decomposition('\uab69'), '' if self.old else '<super> 028D')
|
||||
self.assertEqual(self.db.decomposition('\U00011938'), '' if self.old else '11935 11930')
|
||||
self.assertEqual(self.db.decomposition('\U0001fbf9'), '' if self.old else '<font> 0039')
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.decomposition('\ua7f2'), '' if self.old else '<super> 0043')
|
||||
self.assertEqual(self.db.decomposition('\U000107ba'), '' if self.old else '<super> 1DF1E')
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.decomposition('\U0001e06d'), '' if self.old else '<super> 04B1')
|
||||
# New in 16.0.0
|
||||
self.assertEqual(self.db.decomposition('\U0001CCD6'), '' if self.old else '<font> 0041')
|
||||
|
||||
# Hangul characters
|
||||
self.assertEqual(self.db.decomposition('\uAC00'), '1100 1161')
|
||||
self.assertEqual(self.db.decomposition('\uD4DB'), '1111 1171 11B6')
|
||||
self.assertEqual(self.db.decomposition('\uC2F8'), '110A 1161')
|
||||
self.assertEqual(self.db.decomposition('\uD7A3'), '1112 1175 11C2')
|
||||
|
||||
self.assertRaises(TypeError, self.db.decomposition)
|
||||
self.assertRaises(TypeError, self.db.decomposition, 'xx')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: 1 != 0
|
||||
def test_mirrored(self):
|
||||
self.assertEqual(self.db.mirrored('\uFFFE'), 0)
|
||||
self.assertEqual(self.db.mirrored('a'), 0)
|
||||
self.assertEqual(self.db.mirrored('\u2201'), 1)
|
||||
self.assertEqual(self.db.mirrored('\U00020000'), 0)
|
||||
|
||||
# New in 5.0.0
|
||||
self.assertEqual(self.db.mirrored('\u0f3a'), 0 if self.old else 1)
|
||||
self.assertEqual(self.db.mirrored('\U0001d7c3'), 0 if self.old else 1)
|
||||
# New in 11.0.0
|
||||
self.assertEqual(self.db.mirrored('\u29a1'), 1 if self.old else 0)
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.mirrored('\u2e5c'), 0 if self.old else 1)
|
||||
# New in 16.0.0
|
||||
self.assertEqual(self.db.mirrored('\u226D'), 0 if self.old else 1)
|
||||
|
||||
self.assertRaises(TypeError, self.db.mirrored)
|
||||
self.assertRaises(TypeError, self.db.mirrored, 'xx')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: 0 != 220
|
||||
def test_combining(self):
|
||||
self.assertEqual(self.db.combining('\uFFFE'), 0)
|
||||
self.assertEqual(self.db.combining('a'), 0)
|
||||
self.assertEqual(self.db.combining('\u20e1'), 230)
|
||||
self.assertEqual(self.db.combining('\U00020000'), 0)
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.combining('\u0350'), 0 if self.old else 230)
|
||||
# New in 9.0.0
|
||||
self.assertEqual(self.db.combining('\U0001e94a'), 0 if self.old else 7)
|
||||
# New in 13.0.0
|
||||
self.assertEqual(self.db.combining('\u1abf'), 0 if self.old else 220)
|
||||
self.assertEqual(self.db.combining('\U00016ff1'), 0 if self.old else 6)
|
||||
# New in 14.0.0
|
||||
self.assertEqual(self.db.combining('\u0c3c'), 0 if self.old else 7)
|
||||
self.assertEqual(self.db.combining('\U0001e2ae'), 0 if self.old else 230)
|
||||
# New in 15.0.0
|
||||
self.assertEqual(self.db.combining('\U00010efd'), 0 if self.old else 220)
|
||||
# New in 16.0.0
|
||||
self.assertEqual(self.db.combining('\u0897'), 0 if self.old else 230)
|
||||
|
||||
self.assertRaises(TypeError, self.db.combining)
|
||||
self.assertRaises(TypeError, self.db.combining, 'xx')
|
||||
|
||||
def test_normalization(self):
|
||||
# Test normalize() and is_normalized()
|
||||
def check(ch, expected):
|
||||
if isinstance(expected, str):
|
||||
expected = [expected]*4
|
||||
forms = ('NFC', 'NFD', 'NFKC', 'NFKD')
|
||||
result = [self.db.normalize(form, ch) for form in forms]
|
||||
self.assertEqual(ascii(result), ascii(list(expected)))
|
||||
self.assertEqual([self.db.is_normalized(form, ch) for form in forms],
|
||||
[ch == y for x, y in zip(result, expected)])
|
||||
|
||||
check('', '')
|
||||
check('A', 'A')
|
||||
check(' ', ' ')
|
||||
check('\U0010ffff', '\U0010ffff')
|
||||
check('abc', 'abc')
|
||||
# Broken in 4.0.0
|
||||
check('\u0340', '\u0300')
|
||||
check('\u0300', '\u0300')
|
||||
check('\U0002fa1d', '\U0002a600')
|
||||
check('\U0002a600', '\U0002a600')
|
||||
check('\u0344', '\u0308\u0301')
|
||||
check('\u0308\u0301', '\u0308\u0301')
|
||||
# Broken in 4.0.0 and 4.0.1
|
||||
check('\U0001d1bc', '\U0001d1ba\U0001d165')
|
||||
check('\U0001d1ba\U0001d165', '\U0001d1ba\U0001d165')
|
||||
check('\ufb2c', '\u05e9\u05bc\u05c1')
|
||||
check('\u05e9\u05bc\u05c1', '\u05e9\u05bc\u05c1')
|
||||
check('\U0001d1c0', '\U0001d1ba\U0001d165\U0001d16f')
|
||||
check('\U0001d1ba\U0001d165\U0001d16f', '\U0001d1ba\U0001d165\U0001d16f')
|
||||
|
||||
# Broken in 4.0.0
|
||||
check('\xa0', ['\xa0', '\xa0', ' ', ' '])
|
||||
check('\u2003', ['\u2003', '\u2003', ' ', ' '])
|
||||
check('\U0001d7ff', ['\U0001d7ff', '\U0001d7ff', '9', '9'])
|
||||
|
||||
check('\xa8', ['\xa8', '\xa8', ' \u0308', ' \u0308'])
|
||||
check(' \u0308', ' \u0308')
|
||||
|
||||
check('\xc0', ['\xc0', 'A\u0300']*2)
|
||||
check('A\u0300', ['\xc0', 'A\u0300']*2)
|
||||
|
||||
check('\ud7a3', ['\ud7a3', '\u1112\u1175\u11c2']*2)
|
||||
check('\u1112\u1175\u11c2', ['\ud7a3', '\u1112\u1175\u11c2']*2)
|
||||
|
||||
check('\xb4', ['\xb4', '\xb4', ' \u0301', ' \u0301'])
|
||||
check('\u1ffd', ['\xb4', '\xb4', ' \u0301', ' \u0301'])
|
||||
check(' \u0301', ' \u0301')
|
||||
|
||||
check('\xc5', ['\xc5', 'A\u030a']*2)
|
||||
check('\u212b', ['\xc5', 'A\u030a']*2)
|
||||
check('A\u030a', ['\xc5', 'A\u030a']*2)
|
||||
|
||||
check('\u1f71', ['\u03ac', '\u03b1\u0301']*2)
|
||||
check('\u03ac', ['\u03ac', '\u03b1\u0301']*2)
|
||||
check('\u03b1\u0301', ['\u03ac', '\u03b1\u0301']*2)
|
||||
|
||||
check('\u01c4', ['\u01c4', '\u01c4', 'D\u017d', 'DZ\u030c'])
|
||||
check('D\u017d', ['D\u017d', 'DZ\u030c']*2)
|
||||
check('DZ\u030c', ['D\u017d', 'DZ\u030c']*2)
|
||||
|
||||
check('\u1fed', ['\u1fed', '\xa8\u0300', ' \u0308\u0300', ' \u0308\u0300'])
|
||||
check('\xa8\u0300', ['\u1fed', '\xa8\u0300', ' \u0308\u0300', ' \u0308\u0300'])
|
||||
check(' \u0308\u0300', ' \u0308\u0300')
|
||||
|
||||
check('\u326e', ['\u326e', '\u326e', '\uac00', '\u1100\u1161'])
|
||||
check('\u320e', ['\u320e', '\u320e', '(\uac00)', '(\u1100\u1161)'])
|
||||
check('(\uac00)', ['(\uac00)', '(\u1100\u1161)']*2)
|
||||
check('(\u1100\u1161)', ['(\uac00)', '(\u1100\u1161)']*2)
|
||||
|
||||
check('\u0385', ['\u0385', '\xa8\u0301', ' \u0308\u0301', ' \u0308\u0301'])
|
||||
check('\u1fee', ['\u0385', '\xa8\u0301', ' \u0308\u0301', ' \u0308\u0301'])
|
||||
check('\xa8\u0301', ['\u0385', '\xa8\u0301', ' \u0308\u0301', ' \u0308\u0301'])
|
||||
check(' \u0308\u0301', ' \u0308\u0301')
|
||||
|
||||
check('\u1fdf', ['\u1fdf', '\u1ffe\u0342', ' \u0314\u0342', ' \u0314\u0342'])
|
||||
check('\u1ffe\u0342', ['\u1fdf', '\u1ffe\u0342', ' \u0314\u0342', ' \u0314\u0342'])
|
||||
check('\u1ffe', ['\u1ffe', '\u1ffe', ' \u0314', ' \u0314'])
|
||||
check(' \u0314\u0342', ' \u0314\u0342')
|
||||
|
||||
check('\u03d3', ['\u03d3', '\u03d2\u0301', '\u038e', '\u03a5\u0301'])
|
||||
check('\u03d2\u0301', ['\u03d3', '\u03d2\u0301', '\u038e', '\u03a5\u0301'])
|
||||
check('\u038e', ['\u038e', '\u03a5\u0301']*2)
|
||||
check('\u1feb', ['\u038e', '\u03a5\u0301']*2)
|
||||
check('\u03a5\u0301', ['\u038e', '\u03a5\u0301']*2)
|
||||
|
||||
check('\u0626', ['\u0626', '\u064a\u0654']*2)
|
||||
check('\u064a\u0654', ['\u0626', '\u064a\u0654']*2)
|
||||
check('\ufe89', ['\ufe89', '\ufe89', '\u0626', '\u064a\u0654'])
|
||||
check('\ufe8a', ['\ufe8a', '\ufe8a', '\u0626', '\u064a\u0654'])
|
||||
check('\ufe8b', ['\ufe8b', '\ufe8b', '\u0626', '\u064a\u0654'])
|
||||
check('\ufe8c', ['\ufe8c', '\ufe8c', '\u0626', '\u064a\u0654'])
|
||||
|
||||
check('\ufef9', ['\ufef9', '\ufef9', '\u0644\u0625', '\u0644\u0627\u0655'])
|
||||
check('\ufefa', ['\ufefa', '\ufefa', '\u0644\u0625', '\u0644\u0627\u0655'])
|
||||
check('\ufefb', ['\ufefb', '\ufefb', '\u0644\u0627', '\u0644\u0627'])
|
||||
check('\ufefc', ['\ufefc', '\ufefc', '\u0644\u0627', '\u0644\u0627'])
|
||||
check('\u0644\u0625', ['\u0644\u0625', '\u0644\u0627\u0655']*2)
|
||||
check('\u0644\u0627\u0655', ['\u0644\u0625', '\u0644\u0627\u0655']*2)
|
||||
check('\u0644\u0627', '\u0644\u0627')
|
||||
|
||||
# Broken in 4.0.0
|
||||
check('\u327c', '\u327c' if self.old else
|
||||
['\u327c', '\u327c', '\ucc38\uace0', '\u110e\u1161\u11b7\u1100\u1169'])
|
||||
check('\ucc38\uace0', ['\ucc38\uace0', '\u110e\u1161\u11b7\u1100\u1169']*2)
|
||||
check('\ucc38', ['\ucc38', '\u110e\u1161\u11b7']*2)
|
||||
check('\u110e\u1161\u11b7\u1100\u1169',
|
||||
['\ucc38\uace0', '\u110e\u1161\u11b7\u1100\u1169']*2)
|
||||
check('\u110e\u1161\u11b7\u1100',
|
||||
['\ucc38\u1100', '\u110e\u1161\u11b7\u1100']*2)
|
||||
check('\u110e\u1161\u11b7',
|
||||
['\ucc38', '\u110e\u1161\u11b7']*2)
|
||||
check('\u110e\u1161',
|
||||
['\ucc28', '\u110e\u1161']*2)
|
||||
check('\u110e', '\u110e')
|
||||
# Broken in 4.0.0-12.0.0
|
||||
check('\U00011938', '\U00011938' if self.old else
|
||||
['\U00011938', '\U00011935\U00011930']*2)
|
||||
check('\U00011935\U00011930', ['\U00011938', '\U00011935\U00011930']*2)
|
||||
# New in 4.0.1
|
||||
check('\u321d', '\u321d' if self.old else
|
||||
['\u321d', '\u321d', '(\uc624\uc804)', '(\u110b\u1169\u110c\u1165\u11ab)'])
|
||||
check('(\uc624\uc804)',
|
||||
['(\uc624\uc804)', '(\u110b\u1169\u110c\u1165\u11ab)']*2)
|
||||
check('(\u110b\u1169\u110c\u1165\u11ab)',
|
||||
['(\uc624\uc804)', '(\u110b\u1169\u110c\u1165\u11ab)']*2)
|
||||
check('\u4d57', '\u4d57')
|
||||
check('\u45d7', '\u45d7' if self.old else '\u45d7')
|
||||
check('\U0002f9bf', '\u4d57' if self.old else '\u45d7')
|
||||
# New in 4.1.0
|
||||
check('\u03a3', '\u03a3')
|
||||
check('\u03f9', '\u03f9' if self.old else
|
||||
['\u03f9', '\u03f9', '\u03a3', '\u03a3'])
|
||||
# New in 5.0.0
|
||||
check('\u1b06', '\u1b06' if self.old else ['\u1b06', '\u1b05\u1b35']*2)
|
||||
# New in 5.2.0
|
||||
check('\U0001f213', '\U0001f213' if self.old else
|
||||
['\U0001f213', '\U0001f213', '\u30c7', '\u30c6\u3099'])
|
||||
# New in 6.1.0
|
||||
check('\ufa2e', '\ufa2e' if self.old else '\u90de')
|
||||
# New in 13.0.0
|
||||
check('\U00011938', '\U00011938' if self.old else
|
||||
['\U00011938', '\U00011935\U00011930', '\U00011938', '\U00011935\U00011930'])
|
||||
check('\U0001fbf9', '\U0001fbf9' if self.old else
|
||||
['\U0001fbf9', '\U0001fbf9', '9', '9'])
|
||||
# New in 14.0.0
|
||||
check('\U000107ba', '\U000107ba' if self.old else
|
||||
['\U000107ba', '\U000107ba', '\U0001df1e', '\U0001df1e'])
|
||||
# New in 15.0.0
|
||||
check('\U0001e06d', '\U0001e06d' if self.old else
|
||||
['\U0001e06d', '\U0001e06d', '\u04b1', '\u04b1'])
|
||||
# New in 16.0.0
|
||||
check('\U0001ccd6', '\U0001ccd6' if self.old else
|
||||
['\U0001ccd6', '\U0001ccd6', 'A', 'A'])
|
||||
|
||||
self.assertRaises(TypeError, self.db.normalize)
|
||||
self.assertRaises(TypeError, self.db.normalize, 'NFC')
|
||||
self.assertRaises(ValueError, self.db.normalize, 'SPAM', 'A')
|
||||
|
||||
self.assertRaises(TypeError, self.db.is_normalized)
|
||||
self.assertRaises(TypeError, self.db.is_normalized, 'NFC')
|
||||
self.assertRaises(ValueError, self.db.is_normalized, 'SPAM', 'A')
|
||||
|
||||
def test_pr29(self):
|
||||
# https://www.unicode.org/review/pr-29.html
|
||||
# See issues #1054943 and #10254.
|
||||
@@ -228,6 +587,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
|
||||
def test_issue10254(self):
|
||||
# Crash reported in #10254
|
||||
# New in 4.1.0
|
||||
a = 'C\u0338' * 20 + 'C\u0327'
|
||||
b = 'C\u0338' * 20 + '\xC7'
|
||||
self.assertEqual(self.db.normalize('NFC', a), b)
|
||||
@@ -241,9 +601,11 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
u11c3_str_a = '\u1100\u1175\u11c3'
|
||||
u11c3_str_b = '\uae30\u11c3'
|
||||
self.assertEqual(self.db.normalize('NFC', u1176_str_a), u1176_str_b)
|
||||
# New in 4.1.0
|
||||
self.assertEqual(self.db.normalize('NFC', u11a7_str_a), u11a7_str_b)
|
||||
self.assertEqual(self.db.normalize('NFC', u11c3_str_a), u11c3_str_b)
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: 'W' != 'N'
|
||||
def test_east_asian_width(self):
|
||||
eaw = self.db.east_asian_width
|
||||
self.assertRaises(TypeError, eaw, b'a')
|
||||
@@ -258,6 +620,32 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
self.assertEqual(eaw('\u2010'), 'A')
|
||||
self.assertEqual(eaw('\U00020000'), 'W')
|
||||
|
||||
# New in 4.1.0
|
||||
self.assertEqual(eaw('\u0350'), 'N' if self.old else 'A')
|
||||
self.assertEqual(eaw('\U000e01ef'), 'N' if self.old else 'A')
|
||||
# New in 5.2.0
|
||||
self.assertEqual(eaw('\u115a'), 'N' if self.old else 'W')
|
||||
# New in 9.0.0
|
||||
self.assertEqual(eaw('\u231a'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\u2614'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0001f19a'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0001f991'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0001f9c0'), 'N' if self.old else 'W')
|
||||
# New in 12.0.0
|
||||
self.assertEqual(eaw('\u32ff'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0001fa95'), 'N' if self.old else 'W')
|
||||
# New in 13.0.0
|
||||
self.assertEqual(eaw('\u31bb'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0003134a'), 'N' if self.old else 'W')
|
||||
# New in 14.0.0
|
||||
self.assertEqual(eaw('\u9ffd'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0002b738'), 'N' if self.old else 'W')
|
||||
# New in 15.0.0
|
||||
self.assertEqual(eaw('\U000323af'), 'N' if self.old else 'W')
|
||||
# New in 16.0.0
|
||||
self.assertEqual(eaw('\u2630'), 'N' if self.old else 'W')
|
||||
self.assertEqual(eaw('\U0001FAE9'), 'N' if self.old else 'W')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; + W
|
||||
def test_east_asian_width_unassigned(self):
|
||||
eaw = self.db.east_asian_width
|
||||
@@ -267,7 +655,8 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
self.assertIs(self.db.name(char, None), None)
|
||||
|
||||
# unassigned but reserved for CJK
|
||||
for char in '\uFA6E\uFADA\U0002A6E0\U0002FA20\U0003134B\U0003FFFD':
|
||||
for char in ('\U0002A6E0\U0002FA20\U0003134B\U0003FFFD'
|
||||
'\uFA6E\uFADA'): # New in 5.2.0
|
||||
self.assertEqual(eaw(char), 'W')
|
||||
self.assertIs(self.db.name(char, None), None)
|
||||
|
||||
@@ -278,10 +667,31 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; + N
|
||||
def test_east_asian_width_9_0_changes(self):
|
||||
self.assertEqual(self.db.ucd_3_2_0.east_asian_width('\u231a'), 'N')
|
||||
self.assertEqual(self.db.east_asian_width('\u231a'), 'W')
|
||||
return super().test_east_asian_width_9_0_changes()
|
||||
|
||||
class UnicodeMiscTest(UnicodeDatabaseTest):
|
||||
|
||||
class Unicode_3_2_0_FunctionsTest(UnicodeFunctionsTest):
|
||||
db = unicodedata.ucd_3_2_0
|
||||
old = True
|
||||
expectedchecksum = ('883824cb6c0ccf994e4451ebf281e2d6d479af47'
|
||||
if quicktest else
|
||||
'caf1a7f2f380f927461837f1901ef20683f98683')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON
|
||||
def test_normalization(self):
|
||||
return super().test_normalization()
|
||||
|
||||
@unittest.expectedSuccess # TODO: RUSTPYTHON
|
||||
def test_combining(self):
|
||||
return super().test_combining()
|
||||
|
||||
@unittest.expectedSuccess # TODO: RUSTPYTHON
|
||||
def test_name(self):
|
||||
return super().test_name()
|
||||
|
||||
|
||||
class UnicodeMiscTest(unittest.TestCase):
|
||||
db = unicodedata
|
||||
|
||||
@cpython_only
|
||||
def test_disallow_instantiation(self):
|
||||
@@ -311,33 +721,40 @@ class UnicodeMiscTest(UnicodeDatabaseTest):
|
||||
# i.e. if a character has a decimal value,
|
||||
# its numeric value should be the same.
|
||||
count = 0
|
||||
for i in range(0x10000):
|
||||
c = chr(i)
|
||||
for c in iterallchars():
|
||||
dec = self.db.decimal(c, -1)
|
||||
if dec != -1:
|
||||
self.assertEqual(dec, self.db.numeric(c))
|
||||
count += 1
|
||||
self.assertTrue(count >= 10) # should have tested at least the ASCII digits
|
||||
self.assertTrue(count >= 10, count) # should have tested at least the ASCII digits
|
||||
|
||||
def test_digit_numeric_consistent(self):
|
||||
# Test that digit and numeric are consistent,
|
||||
# i.e. if a character has a digit value,
|
||||
# its numeric value should be the same.
|
||||
count = 0
|
||||
for i in range(0x10000):
|
||||
c = chr(i)
|
||||
for c in iterallchars():
|
||||
dec = self.db.digit(c, -1)
|
||||
if dec != -1:
|
||||
self.assertEqual(dec, self.db.numeric(c))
|
||||
count += 1
|
||||
self.assertTrue(count >= 10) # should have tested at least the ASCII digits
|
||||
self.assertTrue(count >= 10, count) # should have tested at least the ASCII digits
|
||||
|
||||
def test_normalize_consistent(self):
|
||||
allchars = list(iterallchars())
|
||||
for form in ('NFC', 'NFD', 'NFKC', 'NFKD'):
|
||||
for c in allchars:
|
||||
norm = self.db.normalize(form, c)
|
||||
self.assertEqual(self.db.is_normalized(form, c), norm == c)
|
||||
if norm != c:
|
||||
self.assertEqual(self.db.normalize(form, norm), norm)
|
||||
self.assertTrue(self.db.is_normalized(form, norm))
|
||||
|
||||
def test_bug_1704793(self):
|
||||
self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), '\U00010346')
|
||||
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: False is not true
|
||||
def test_ucd_510(self):
|
||||
import unicodedata
|
||||
# In UCD 5.1.0, a mirrored property changed wrt. UCD 3.2.0
|
||||
self.assertTrue(unicodedata.mirrored("\u0f3a"))
|
||||
self.assertTrue(not unicodedata.ucd_3_2_0.mirrored("\u0f3a"))
|
||||
@@ -353,10 +770,10 @@ class UnicodeMiscTest(UnicodeDatabaseTest):
|
||||
# Only U+0000 should have U+0000 as its upper/lower/titlecase variant
|
||||
self.assertEqual(
|
||||
[
|
||||
c for c in range(sys.maxunicode+1)
|
||||
if "\x00" in chr(c).lower()+chr(c).upper()+chr(c).title()
|
||||
c for c in iterallchars()
|
||||
if "\x00" in (c.lower(), c.upper(), c.title())
|
||||
],
|
||||
[0]
|
||||
["\x00"]
|
||||
)
|
||||
|
||||
def test_bug_4971(self):
|
||||
@@ -366,15 +783,16 @@ class UnicodeMiscTest(UnicodeDatabaseTest):
|
||||
self.assertEqual("\u01c6".title(), "\u01c5")
|
||||
|
||||
def test_linebreak_7643(self):
|
||||
for i in range(0x10000):
|
||||
lines = (chr(i) + 'A').splitlines()
|
||||
if i in (0x0a, 0x0b, 0x0c, 0x0d, 0x85,
|
||||
0x1c, 0x1d, 0x1e, 0x2028, 0x2029):
|
||||
for c in iterallchars():
|
||||
lines = (c + 'A').splitlines()
|
||||
if c in ('\x0a', '\x0b', '\x0c', '\x0d', '\x85',
|
||||
'\x1c', '\x1d', '\x1e', '\u2028', '\u2029'):
|
||||
self.assertEqual(len(lines), 2,
|
||||
r"\u%.4x should be a linebreak" % i)
|
||||
r"%a should be a linebreak" % c)
|
||||
else:
|
||||
self.assertEqual(len(lines), 1,
|
||||
r"\u%.4x should not be a linebreak" % i)
|
||||
r"%a should not be a linebreak" % c)
|
||||
|
||||
|
||||
class NormalizationTest(unittest.TestCase):
|
||||
@staticmethod
|
||||
@@ -405,23 +823,24 @@ class NormalizationTest(unittest.TestCase):
|
||||
self.skipTest(f"Failed to download {TESTDATAURL}: {exc}")
|
||||
|
||||
with testdata:
|
||||
self.run_normalization_tests(testdata)
|
||||
self.run_normalization_tests(testdata, unicodedata)
|
||||
|
||||
def run_normalization_tests(self, testdata):
|
||||
@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: False is not true : 2F868;2136A;2136A;2136A;2136A
|
||||
@requires_resource('cpu')
|
||||
def test_normalization_3_2_0(self):
|
||||
testdatafile = findfile('NormalizationTest-3.2.0.txt')
|
||||
with open(testdatafile, encoding='utf-8') as testdata:
|
||||
self.run_normalization_tests(testdata, unicodedata.ucd_3_2_0)
|
||||
|
||||
def run_normalization_tests(self, testdata, ucd):
|
||||
part = None
|
||||
part1_data = {}
|
||||
part1_data = set()
|
||||
|
||||
def NFC(str):
|
||||
return unicodedata.normalize("NFC", str)
|
||||
|
||||
def NFKC(str):
|
||||
return unicodedata.normalize("NFKC", str)
|
||||
|
||||
def NFD(str):
|
||||
return unicodedata.normalize("NFD", str)
|
||||
|
||||
def NFKD(str):
|
||||
return unicodedata.normalize("NFKD", str)
|
||||
NFC = partial(ucd.normalize, "NFC")
|
||||
NFKC = partial(ucd.normalize, "NFKC")
|
||||
NFD = partial(ucd.normalize, "NFD")
|
||||
NFKD = partial(ucd.normalize, "NFKD")
|
||||
is_normalized = ucd.is_normalized
|
||||
|
||||
for line in testdata:
|
||||
if '#' in line:
|
||||
@@ -446,25 +865,24 @@ class NormalizationTest(unittest.TestCase):
|
||||
NFKD(c3) == NFKD(c4) == NFKD(c5),
|
||||
line)
|
||||
|
||||
self.assertTrue(unicodedata.is_normalized("NFC", c2))
|
||||
self.assertTrue(unicodedata.is_normalized("NFC", c4))
|
||||
self.assertTrue(is_normalized("NFC", c2))
|
||||
self.assertTrue(is_normalized("NFC", c4))
|
||||
|
||||
self.assertTrue(unicodedata.is_normalized("NFD", c3))
|
||||
self.assertTrue(unicodedata.is_normalized("NFD", c5))
|
||||
self.assertTrue(is_normalized("NFD", c3))
|
||||
self.assertTrue(is_normalized("NFD", c5))
|
||||
|
||||
self.assertTrue(unicodedata.is_normalized("NFKC", c4))
|
||||
self.assertTrue(unicodedata.is_normalized("NFKD", c5))
|
||||
self.assertTrue(is_normalized("NFKC", c4))
|
||||
self.assertTrue(is_normalized("NFKD", c5))
|
||||
|
||||
# Record part 1 data
|
||||
if part == "@Part1":
|
||||
part1_data[c1] = 1
|
||||
part1_data.add(c1)
|
||||
|
||||
# Perform tests for all other data
|
||||
for c in range(sys.maxunicode+1):
|
||||
X = chr(c)
|
||||
for X in iterallchars():
|
||||
if X in part1_data:
|
||||
continue
|
||||
self.assertTrue(X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X), c)
|
||||
self.assertTrue(X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X), ord(X))
|
||||
|
||||
def test_edge_cases(self):
|
||||
self.assertRaises(TypeError, unicodedata.normalize)
|
||||
|
||||
Vendored
+8
-1
@@ -109,4 +109,11 @@ def expectedFailureIf(condition, reason):
|
||||
# Even more useful because most of them are windows only.
|
||||
def expectedFailureIfWindows(reason):
|
||||
import sys
|
||||
return expectedFailureIf(sys.platform == 'win32', reason)
|
||||
return expectedFailureIf(sys.platform == 'win32', reason)
|
||||
|
||||
# XXX: RUSTPYTHON
|
||||
# For a rare case when the parent class test fails but the child pass.
|
||||
def expectedSuccess(test_item):
|
||||
test_item.__unittest_expecting_failure__ = False
|
||||
return test_item
|
||||
|
||||
@@ -32,7 +32,7 @@ class UtMethod(enum.StrEnum):
|
||||
return name[0].lower() + name[1:]
|
||||
|
||||
def has_args(self) -> bool:
|
||||
return self != self.ExpectedFailure
|
||||
return self not in (self.ExpectedFailure, self.ExpectedSuccess)
|
||||
|
||||
def has_cond(self) -> bool:
|
||||
return self.endswith(("If", "Unless"))
|
||||
@@ -40,6 +40,7 @@ class UtMethod(enum.StrEnum):
|
||||
ExpectedFailure = enum.auto()
|
||||
ExpectedFailureIf = enum.auto()
|
||||
ExpectedFailureIfWindows = enum.auto()
|
||||
ExpectedSuccess = enum.auto()
|
||||
Skip = enum.auto()
|
||||
SkipIf = enum.auto()
|
||||
SkipUnless = enum.auto()
|
||||
|
||||
Reference in new issue
Block a user