mirror of
https://github.com/python/cpython.git
synced 2024-12-26 02:04:24 +08:00
18f6b1987f
svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r87442 | alexander.belopolsky | 2010-12-22 21:27:37 -0500 (Wed, 22 Dec 2010) | 1 line Issue #10254: Fixed a crash and a regression introduced by the implementation of PRI 29. ........
328 lines
12 KiB
Python
328 lines
12 KiB
Python
""" Test script for the unicodedata module.
|
|
|
|
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
|
|
|
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|
|
|
"""
|
|
|
|
import sys
|
|
import unittest
|
|
import hashlib
|
|
import subprocess
|
|
import test.support
|
|
|
|
encoding = 'utf-8'
|
|
errors = 'surrogatepass'
|
|
|
|
|
|
### Run tests
|
|
|
|
class UnicodeMethodsTest(unittest.TestCase):
|
|
|
|
# update this, if the database changes
|
|
expectedchecksum = '21b90f1aed00081b81ca7942b22196af090015a0'
|
|
|
|
def test_method_checksum(self):
|
|
h = hashlib.sha1()
|
|
for i in range(0x10000):
|
|
char = chr(i)
|
|
data = [
|
|
# Predicates (single char)
|
|
"01"[char.isalnum()],
|
|
"01"[char.isalpha()],
|
|
"01"[char.isdecimal()],
|
|
"01"[char.isdigit()],
|
|
"01"[char.islower()],
|
|
"01"[char.isnumeric()],
|
|
"01"[char.isspace()],
|
|
"01"[char.istitle()],
|
|
"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"[(char + ' \t').isspace()],
|
|
"01"[(char + 'abc').istitle()],
|
|
"01"[(char + 'ABC').isupper()],
|
|
|
|
# Mappings (single char)
|
|
char.lower(),
|
|
char.upper(),
|
|
char.title(),
|
|
|
|
# Mappings (multiple chars)
|
|
(char + 'abc').lower(),
|
|
(char + 'ABC').upper(),
|
|
(char + 'abc').title(),
|
|
(char + 'ABC').title(),
|
|
|
|
]
|
|
h.update(''.join(data).encode(encoding, errors))
|
|
result = h.hexdigest()
|
|
self.assertEqual(result, self.expectedchecksum)
|
|
|
|
class UnicodeDatabaseTest(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
# In case unicodedata is not available, this will raise an ImportError,
|
|
# but the other test cases will still be run
|
|
import unicodedata
|
|
self.db = unicodedata
|
|
|
|
def tearDown(self):
|
|
del self.db
|
|
|
|
class UnicodeFunctionsTest(UnicodeDatabaseTest):
|
|
|
|
# update this, if the database changes
|
|
expectedchecksum = 'c23dfc0b5eaf3ca2aad32d733de96bb182ccda50'
|
|
def test_function_checksum(self):
|
|
data = []
|
|
h = hashlib.sha1()
|
|
|
|
for i in range(0x10000):
|
|
char = chr(i)
|
|
data = [
|
|
# 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)),
|
|
]
|
|
h.update(''.join(data).encode("ascii"))
|
|
result = h.hexdigest()
|
|
self.assertEqual(result, self.expectedchecksum)
|
|
|
|
def test_digit(self):
|
|
self.assertEqual(self.db.digit('A', None), None)
|
|
self.assertEqual(self.db.digit('9'), 9)
|
|
self.assertEqual(self.db.digit('\u215b', None), None)
|
|
self.assertEqual(self.db.digit('\u2468'), 9)
|
|
self.assertEqual(self.db.digit('\U00020000', None), None)
|
|
|
|
self.assertRaises(TypeError, self.db.digit)
|
|
self.assertRaises(TypeError, self.db.digit, 'xx')
|
|
self.assertRaises(ValueError, self.db.digit, 'x')
|
|
|
|
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.assertRaises(TypeError, self.db.numeric)
|
|
self.assertRaises(TypeError, self.db.numeric, 'xx')
|
|
self.assertRaises(ValueError, self.db.numeric, 'x')
|
|
|
|
def test_decimal(self):
|
|
self.assertEqual(self.db.decimal('A',None), None)
|
|
self.assertEqual(self.db.decimal('9'), 9)
|
|
self.assertEqual(self.db.decimal('\u215b', None), None)
|
|
self.assertEqual(self.db.decimal('\u2468', None), None)
|
|
self.assertEqual(self.db.decimal('\U00020000', None), None)
|
|
|
|
self.assertRaises(TypeError, self.db.decimal)
|
|
self.assertRaises(TypeError, self.db.decimal, 'xx')
|
|
self.assertRaises(ValueError, self.db.decimal, 'x')
|
|
|
|
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.assertRaises(TypeError, self.db.category)
|
|
self.assertRaises(TypeError, self.db.category, 'xx')
|
|
|
|
def test_bidirectional(self):
|
|
self.assertEqual(self.db.bidirectional('\uFFFE'), '')
|
|
self.assertEqual(self.db.bidirectional(' '), 'WS')
|
|
self.assertEqual(self.db.bidirectional('A'), 'L')
|
|
self.assertEqual(self.db.bidirectional('\U00020000'), 'L')
|
|
|
|
self.assertRaises(TypeError, self.db.bidirectional)
|
|
self.assertRaises(TypeError, self.db.bidirectional, 'xx')
|
|
|
|
def test_decomposition(self):
|
|
self.assertEqual(self.db.decomposition('\uFFFE'),'')
|
|
self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034')
|
|
|
|
self.assertRaises(TypeError, self.db.decomposition)
|
|
self.assertRaises(TypeError, self.db.decomposition, 'xx')
|
|
|
|
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)
|
|
|
|
self.assertRaises(TypeError, self.db.mirrored)
|
|
self.assertRaises(TypeError, self.db.mirrored, 'xx')
|
|
|
|
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)
|
|
|
|
self.assertRaises(TypeError, self.db.combining)
|
|
self.assertRaises(TypeError, self.db.combining, 'xx')
|
|
|
|
def test_normalize(self):
|
|
self.assertRaises(TypeError, self.db.normalize)
|
|
self.assertRaises(ValueError, self.db.normalize, 'unknown', 'xx')
|
|
self.assertEqual(self.db.normalize('NFKC', ''), '')
|
|
# The rest can be found in test_normalization.py
|
|
# which requires an external file.
|
|
|
|
def test_pr29(self):
|
|
# http://www.unicode.org/review/pr-29.html
|
|
# See issues #1054943 and #10254.
|
|
composed = ("\u0b47\u0300\u0b3e", "\u1100\u0300\u1161",
|
|
'Li\u030dt-s\u1e73\u0301',
|
|
'\u092e\u093e\u0930\u094d\u0915 \u091c\u093c'
|
|
+ '\u0941\u0915\u0947\u0930\u092c\u0930\u094d\u0917',
|
|
'\u0915\u093f\u0930\u094d\u0917\u093f\u091c\u093c'
|
|
+ '\u0938\u094d\u0924\u093e\u0928')
|
|
for text in composed:
|
|
self.assertEqual(self.db.normalize('NFC', text), text)
|
|
|
|
def test_issue10254(self):
|
|
# Crash reported in #10254
|
|
a = 'C\u0338' * 20 + 'C\u0327'
|
|
b = 'C\u0338' * 20 + '\xC7'
|
|
self.assertEqual(self.db.normalize('NFC', a), b)
|
|
|
|
def test_east_asian_width(self):
|
|
eaw = self.db.east_asian_width
|
|
self.assertRaises(TypeError, eaw, b'a')
|
|
self.assertRaises(TypeError, eaw, bytearray())
|
|
self.assertRaises(TypeError, eaw, '')
|
|
self.assertRaises(TypeError, eaw, 'ra')
|
|
self.assertEqual(eaw('\x1e'), 'N')
|
|
self.assertEqual(eaw('\x20'), 'Na')
|
|
self.assertEqual(eaw('\uC894'), 'W')
|
|
self.assertEqual(eaw('\uFF66'), 'H')
|
|
self.assertEqual(eaw('\uFF1F'), 'F')
|
|
self.assertEqual(eaw('\u2010'), 'A')
|
|
self.assertEqual(eaw('\U00020000'), 'W')
|
|
|
|
class UnicodeMiscTest(UnicodeDatabaseTest):
|
|
|
|
def test_failed_import_during_compiling(self):
|
|
# Issue 4367
|
|
# Decoding \N escapes requires the unicodedata module. If it can't be
|
|
# imported, we shouldn't segfault.
|
|
|
|
# This program should raise a SyntaxError in the eval.
|
|
code = "import sys;" \
|
|
"sys.modules['unicodedata'] = None;" \
|
|
"""eval("'\\\\N{SOFT HYPHEN}'")"""
|
|
args = [sys.executable, "-c", code]
|
|
# We use a subprocess because the unicodedata module may already have
|
|
# been loaded in this process.
|
|
popen = subprocess.Popen(args, stderr=subprocess.PIPE)
|
|
popen.wait()
|
|
self.assertEqual(popen.returncode, 1)
|
|
error = "SyntaxError: (unicode error) \\N escapes not supported " \
|
|
"(can't load unicodedata module)"
|
|
self.assertIn(error, popen.stderr.read().decode("ascii"))
|
|
popen.stderr.close()
|
|
|
|
def test_decimal_numeric_consistent(self):
|
|
# Test that decimal and numeric are consistent,
|
|
# 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)
|
|
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
|
|
|
|
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)
|
|
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
|
|
|
|
def test_bug_1704793(self):
|
|
self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), '\U00010346')
|
|
|
|
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"))
|
|
# Also, we now have two ways of representing
|
|
# the upper-case mapping: as delta, or as absolute value
|
|
self.assertTrue("a".upper()=='A')
|
|
self.assertTrue("\u1d79".upper()=='\ua77d')
|
|
self.assertTrue(".".upper()=='.')
|
|
|
|
def test_bug_5828(self):
|
|
self.assertEqual("\u1d79".lower(), "\u1d79")
|
|
# 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()
|
|
],
|
|
[0]
|
|
)
|
|
|
|
def test_bug_4971(self):
|
|
# LETTER DZ WITH CARON: DZ, Dz, dz
|
|
self.assertEqual("\u01c4".title(), "\u01c5")
|
|
self.assertEqual("\u01c5".title(), "\u01c5")
|
|
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):
|
|
self.assertEqual(len(lines), 2,
|
|
r"\u%.4x should be a linebreak" % i)
|
|
else:
|
|
self.assertEqual(len(lines), 1,
|
|
r"\u%.4x should not be a linebreak" % i)
|
|
|
|
def test_UCS4(self):
|
|
# unicodedata should work with code points outside the BMP
|
|
# even on a narrow Unicode build
|
|
self.assertEqual(self.db.category("\U0001012A"), "No")
|
|
self.assertEqual(self.db.numeric("\U0001012A"), 9000)
|
|
self.assertEqual(self.db.decimal("\U0001D7FD"), 7)
|
|
self.assertEqual(self.db.digit("\U0001D7FD"), 7)
|
|
|
|
def test_main():
|
|
test.support.run_unittest(
|
|
UnicodeMiscTest,
|
|
UnicodeMethodsTest,
|
|
UnicodeFunctionsTest
|
|
)
|
|
|
|
if __name__ == "__main__":
|
|
test_main()
|