(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
-from test.test_support import verify, verbose
-
-print 'Testing General Unicode Character Name, and case insensitivity...',
-
-# General and case insensitivity test:
-try:
- # put all \N escapes inside exec'd raw strings, to make sure this
- # script runs even if the compiler chokes on \N escapes
- exec r"""
-s = u"\N{LATIN CAPITAL LETTER T}" \
- u"\N{LATIN SMALL LETTER H}" \
- u"\N{LATIN SMALL LETTER E}" \
- u"\N{SPACE}" \
- u"\N{LATIN SMALL LETTER R}" \
- u"\N{LATIN CAPITAL LETTER E}" \
- u"\N{LATIN SMALL LETTER D}" \
- u"\N{SPACE}" \
- u"\N{LATIN SMALL LETTER f}" \
- u"\N{LATIN CAPITAL LeTtEr o}" \
- u"\N{LATIN SMaLl LETTER x}" \
- u"\N{SPACE}" \
- u"\N{LATIN SMALL LETTER A}" \
- u"\N{LATIN SMALL LETTER T}" \
- u"\N{LATIN SMALL LETTER E}" \
- u"\N{SPACE}" \
- u"\N{LATIN SMALL LETTER T}" \
- u"\N{LATIN SMALL LETTER H}" \
- u"\N{LATIN SMALL LETTER E}" \
- u"\N{SpAcE}" \
- u"\N{LATIN SMALL LETTER S}" \
- u"\N{LATIN SMALL LETTER H}" \
- u"\N{LATIN SMALL LETTER E}" \
- u"\N{LATIN SMALL LETTER E}" \
- u"\N{LATIN SMALL LETTER P}" \
- u"\N{FULL STOP}"
-verify(s == u"The rEd fOx ate the sheep.", s)
-"""
-except UnicodeError, v:
- print v
-print "done."
-
-import unicodedata
-
-print "Testing name to code mapping....",
-for char in "SPAM":
- name = "LATIN SMALL LETTER %s" % char
- code = unicodedata.lookup(name)
- verify(unicodedata.name(code) == name)
-print "done."
-
-print "Testing hangul syllable names....",
-exec r"""
-verify(u"\N{HANGUL SYLLABLE GA}" == u"\uac00")
-verify(u"\N{HANGUL SYLLABLE GGWEOSS}" == u"\uafe8")
-verify(u"\N{HANGUL SYLLABLE DOLS}" == u"\ub3d0")
-verify(u"\N{HANGUL SYLLABLE RYAN}" == u"\ub7b8")
-verify(u"\N{HANGUL SYLLABLE MWIK}" == u"\ubba0")
-verify(u"\N{HANGUL SYLLABLE BBWAEM}" == u"\ubf88")
-verify(u"\N{HANGUL SYLLABLE SSEOL}" == u"\uc370")
-verify(u"\N{HANGUL SYLLABLE YI}" == u"\uc758")
-verify(u"\N{HANGUL SYLLABLE JJYOSS}" == u"\ucb40")
-verify(u"\N{HANGUL SYLLABLE KYEOLS}" == u"\ucf28")
-verify(u"\N{HANGUL SYLLABLE PAN}" == u"\ud310")
-verify(u"\N{HANGUL SYLLABLE HWEOK}" == u"\ud6f8")
-verify(u"\N{HANGUL SYLLABLE HIH}" == u"\ud7a3")
-"""
-try:
- unicodedata.name(u"\ud7a4")
-except ValueError:
- pass
-else:
- raise AssertionError, "Found name for U+D7A4"
-print "done."
-
-print "Testing names of CJK unified ideographs....",
-exec r"""
-verify(u"\N{CJK UNIFIED IDEOGRAPH-3400}" == u"\u3400")
-verify(u"\N{CJK UNIFIED IDEOGRAPH-4DB5}" == u"\u4db5")
-verify(u"\N{CJK UNIFIED IDEOGRAPH-4E00}" == u"\u4e00")
-verify(u"\N{CJK UNIFIED IDEOGRAPH-9FA5}" == u"\u9fa5")
-verify(u"\N{CJK UNIFIED IDEOGRAPH-20000}" == u"\U00020000")
-verify(u"\N{CJK UNIFIED IDEOGRAPH-2A6D6}" == u"\U0002a6d6")
-"""
-print "done."
-
-print "Testing code to name mapping for all BMP characters....",
-count = 0
-for code in range(0x10000):
- try:
- char = unichr(code)
- name = unicodedata.name(char)
- except (KeyError, ValueError):
- pass
- else:
- verify(unicodedata.lookup(name) == char)
- count += 1
-print "done."
-
-print "Found", count, "characters in the unicode name database"
-
-# misc. symbol testing
-print "Testing misc. symbols for unicode character name expansion....",
-exec r"""
-verify(u"\N{PILCROW SIGN}" == u"\u00b6")
-verify(u"\N{REPLACEMENT CHARACTER}" == u"\uFFFD")
-verify(u"\N{HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK}" == u"\uFF9F")
-verify(u"\N{FULLWIDTH LATIN SMALL LETTER A}" == u"\uFF41")
-"""
-print "done."
-
-# strict error testing:
-print "Testing unicode character name expansion strict error handling....",
-try:
- unicode("\N{blah}", 'unicode-escape', 'strict')
-except UnicodeError:
- pass
-else:
- raise AssertionError, "failed to raise an exception when given a bogus character name"
-
-try:
- unicode("\N{" + "x" * 100000 + "}", 'unicode-escape', 'strict')
-except UnicodeError:
- pass
-else:
- raise AssertionError, "failed to raise an exception when given a very " \
- "long bogus character name"
-
-try:
- unicode("\N{SPACE", 'unicode-escape', 'strict')
-except UnicodeError:
- pass
-else:
- raise AssertionError, "failed to raise an exception for a missing closing brace."
-
-try:
- unicode("\NSPACE", 'unicode-escape', 'strict')
-except UnicodeError:
- pass
-else:
- raise AssertionError, "failed to raise an exception for a missing opening brace."
-print "done."
+
+import unittest
+
+from test import test_support
+
+class UnicodeNamesTest(unittest.TestCase):
+
+ def checkletter(self, name, code):
+ # Helper that put all \N escapes inside eval'd raw strings,
+ # to make sure this script runs even if the compiler
+ # chokes on \N escapes
+ res = eval(ur'u"\N{%s}"' % name)
+ self.assertEqual(res, code)
+ return res
+
+ def test_general(self):
+ # General and case insensitivity test:
+ chars = [
+ "LATIN CAPITAL LETTER T",
+ "LATIN SMALL LETTER H",
+ "LATIN SMALL LETTER E",
+ "SPACE",
+ "LATIN SMALL LETTER R",
+ "LATIN CAPITAL LETTER E",
+ "LATIN SMALL LETTER D",
+ "SPACE",
+ "LATIN SMALL LETTER f",
+ "LATIN CAPITAL LeTtEr o",
+ "LATIN SMaLl LETTER x",
+ "SPACE",
+ "LATIN SMALL LETTER A",
+ "LATIN SMALL LETTER T",
+ "LATIN SMALL LETTER E",
+ "SPACE",
+ "LATIN SMALL LETTER T",
+ "LATIN SMALL LETTER H",
+ "LATIN SMALL LETTER E",
+ "SpAcE",
+ "LATIN SMALL LETTER S",
+ "LATIN SMALL LETTER H",
+ "LATIN small LETTER e",
+ "LATIN small LETTER e",
+ "LATIN SMALL LETTER P",
+ "FULL STOP"
+ ]
+ string = u"The rEd fOx ate the sheep."
+
+ self.assertEqual(
+ u"".join([self.checkletter(*args) for args in zip(chars, string)]),
+ string
+ )
+
+ def test_ascii_letters(self):
+ import unicodedata
+
+ for char in "".join(map(chr, xrange(ord("a"), ord("z")))):
+ name = "LATIN SMALL LETTER %s" % char.upper()
+ code = unicodedata.lookup(name)
+ self.assertEqual(unicodedata.name(code), name)
+
+ def test_hangul_syllables(self):
+ self.checkletter("HANGUL SYLLABLE GA", u"\uac00")
+ self.checkletter("HANGUL SYLLABLE GGWEOSS", u"\uafe8")
+ self.checkletter("HANGUL SYLLABLE DOLS", u"\ub3d0")
+ self.checkletter("HANGUL SYLLABLE RYAN", u"\ub7b8")
+ self.checkletter("HANGUL SYLLABLE MWIK", u"\ubba0")
+ self.checkletter("HANGUL SYLLABLE BBWAEM", u"\ubf88")
+ self.checkletter("HANGUL SYLLABLE SSEOL", u"\uc370")
+ self.checkletter("HANGUL SYLLABLE YI", u"\uc758")
+ self.checkletter("HANGUL SYLLABLE JJYOSS", u"\ucb40")
+ self.checkletter("HANGUL SYLLABLE KYEOLS", u"\ucf28")
+ self.checkletter("HANGUL SYLLABLE PAN", u"\ud310")
+ self.checkletter("HANGUL SYLLABLE HWEOK", u"\ud6f8")
+ self.checkletter("HANGUL SYLLABLE HIH", u"\ud7a3")
+
+ import unicodedata
+ self.assertRaises(ValueError, unicodedata.name, u"\ud7a4")
+
+ def test_cjk_unified_ideographs(self):
+ self.checkletter("CJK UNIFIED IDEOGRAPH-3400", u"\u3400")
+ self.checkletter("CJK UNIFIED IDEOGRAPH-4DB5", u"\u4db5")
+ self.checkletter("CJK UNIFIED IDEOGRAPH-4E00", u"\u4e00")
+ self.checkletter("CJK UNIFIED IDEOGRAPH-9FA5", u"\u9fa5")
+ self.checkletter("CJK UNIFIED IDEOGRAPH-20000", u"\U00020000")
+ self.checkletter("CJK UNIFIED IDEOGRAPH-2A6D6", u"\U0002a6d6")
+
+ def test_bmp_characters(self):
+ import unicodedata
+ count = 0
+ for code in xrange(0x10000):
+ char = unichr(code)
+ name = unicodedata.name(char, None)
+ if name is not None:
+ self.assertEqual(unicodedata.lookup(name), char)
+ count += 1
+
+ def test_misc_symbols(self):
+ self.checkletter("PILCROW SIGN", u"\u00b6")
+ self.checkletter("REPLACEMENT CHARACTER", u"\uFFFD")
+ self.checkletter("HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK", u"\uFF9F")
+ self.checkletter("FULLWIDTH LATIN SMALL LETTER A", u"\uFF41")
+
+ def test_errors(self):
+ import unicodedata
+ self.assertRaises(TypeError, unicodedata.name)
+ self.assertRaises(TypeError, unicodedata.name, u'xx')
+ self.assertRaises(TypeError, unicodedata.lookup)
+ self.assertRaises(KeyError, unicodedata.lookup, u'unknown')
+
+ def test_strict_eror_handling(self):
+ # bogus character name
+ self.assertRaises(
+ UnicodeError,
+ unicode, "\\N{blah}", 'unicode-escape', 'strict'
+ )
+ # long bogus character name
+ self.assertRaises(
+ UnicodeError,
+ unicode, "\\N{%s}" % ("x" * 100000), 'unicode-escape', 'strict'
+ )
+ # missing closing brace
+ self.assertRaises(
+ UnicodeError,
+ unicode, "\\N{SPACE", 'unicode-escape', 'strict'
+ )
+ # missing opening brace
+ self.assertRaises(
+ UnicodeError,
+ unicode, "\\NSPACE", 'unicode-escape', 'strict'
+ )
+
+def test_main():
+ suite = unittest.TestSuite()
+ suite.addTest(unittest.makeSuite(UnicodeNamesTest))
+ test_support.run_suite(suite)
+
+if __name__ == "__main__":
+ test_main()
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
-from test.test_support import verify, verbose
+import unittest, test.test_support
import sha
encoding = 'utf-8'
-def test_methods():
-
- h = sha.sha()
- for i in range(65536):
- char = unichr(i)
- data = [
-
- # Predicates (single char)
- char.isalnum() and u'1' or u'0',
- char.isalpha() and u'1' or u'0',
- char.isdecimal() and u'1' or u'0',
- char.isdigit() and u'1' or u'0',
- char.islower() and u'1' or u'0',
- char.isnumeric() and u'1' or u'0',
- char.isspace() and u'1' or u'0',
- char.istitle() and u'1' or u'0',
- char.isupper() and u'1' or u'0',
-
- # Predicates (multiple chars)
- (char + u'abc').isalnum() and u'1' or u'0',
- (char + u'abc').isalpha() and u'1' or u'0',
- (char + u'123').isdecimal() and u'1' or u'0',
- (char + u'123').isdigit() and u'1' or u'0',
- (char + u'abc').islower() and u'1' or u'0',
- (char + u'123').isnumeric() and u'1' or u'0',
- (char + u' \t').isspace() and u'1' or u'0',
- (char + u'abc').istitle() and u'1' or u'0',
- (char + u'ABC').isupper() and u'1' or u'0',
-
- # Mappings (single char)
- char.lower(),
- char.upper(),
- char.title(),
-
- # Mappings (multiple chars)
- (char + u'abc').lower(),
- (char + u'ABC').upper(),
- (char + u'abc').title(),
- (char + u'ABC').title(),
-
- ]
- h.update(u''.join(data).encode(encoding))
- return h.hexdigest()
-
-def test_unicodedata():
-
- h = sha.sha()
- for i in range(65536):
- char = unichr(i)
- data = [
- # Properties
- str(unicodedata.digit(char, -1)),
- str(unicodedata.numeric(char, -1)),
- str(unicodedata.decimal(char, -1)),
- unicodedata.category(char),
- unicodedata.bidirectional(char),
- unicodedata.decomposition(char),
- str(unicodedata.mirrored(char)),
- str(unicodedata.combining(char)),
- ]
- h.update(''.join(data))
- return h.hexdigest()
### Run tests
-print 'Testing Unicode Database...'
-print 'Methods:',
-print test_methods()
-
-# In case unicodedata is not available, this will raise an ImportError,
-# but still test the above cases...
-import unicodedata
-print 'Functions:',
-print test_unicodedata()
-
-# Some additional checks of the API:
-print 'API:',
-
-verify(unicodedata.digit(u'A',None) is None)
-verify(unicodedata.digit(u'9') == 9)
-verify(unicodedata.digit(u'\u215b',None) is None)
-verify(unicodedata.digit(u'\u2468') == 9)
-
-verify(unicodedata.numeric(u'A',None) is None)
-verify(unicodedata.numeric(u'9') == 9)
-verify(unicodedata.numeric(u'\u215b') == 0.125)
-verify(unicodedata.numeric(u'\u2468') == 9.0)
-
-verify(unicodedata.decimal(u'A',None) is None)
-verify(unicodedata.decimal(u'9') == 9)
-verify(unicodedata.decimal(u'\u215b',None) is None)
-verify(unicodedata.decimal(u'\u2468',None) is None)
-
-verify(unicodedata.category(u'\uFFFE') == 'Cn')
-verify(unicodedata.category(u'a') == 'Ll')
-verify(unicodedata.category(u'A') == 'Lu')
-
-verify(unicodedata.bidirectional(u'\uFFFE') == '')
-verify(unicodedata.bidirectional(u' ') == 'WS')
-verify(unicodedata.bidirectional(u'A') == 'L')
-
-verify(unicodedata.decomposition(u'\uFFFE') == '')
-verify(unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034')
-
-verify(unicodedata.mirrored(u'\uFFFE') == 0)
-verify(unicodedata.mirrored(u'a') == 0)
-verify(unicodedata.mirrored(u'\u2201') == 1)
-
-verify(unicodedata.combining(u'\uFFFE') == 0)
-verify(unicodedata.combining(u'a') == 0)
-verify(unicodedata.combining(u'\u20e1') == 230)
-
-print 'ok'
+class UnicodeMethodsTest(unittest.TestCase):
+
+ # update this, if the database changes
+ expectedchecksum = 'a37276dc2c158bef6dfd908ad34525c97180fad9'
+
+ def test_method_checksum(self):
+ h = sha.sha()
+ for i in range(65536):
+ char = unichr(i)
+ data = [
+ # Predicates (single char)
+ u"01"[char.isalnum()],
+ u"01"[char.isalpha()],
+ u"01"[char.isdecimal()],
+ u"01"[char.isdigit()],
+ u"01"[char.islower()],
+ u"01"[char.isnumeric()],
+ u"01"[char.isspace()],
+ u"01"[char.istitle()],
+ u"01"[char.isupper()],
+
+ # Predicates (multiple chars)
+ u"01"[(char + u'abc').isalnum()],
+ u"01"[(char + u'abc').isalpha()],
+ u"01"[(char + u'123').isdecimal()],
+ u"01"[(char + u'123').isdigit()],
+ u"01"[(char + u'abc').islower()],
+ u"01"[(char + u'123').isnumeric()],
+ u"01"[(char + u' \t').isspace()],
+ u"01"[(char + u'abc').istitle()],
+ u"01"[(char + u'ABC').isupper()],
+
+ # Mappings (single char)
+ char.lower(),
+ char.upper(),
+ char.title(),
+
+ # Mappings (multiple chars)
+ (char + u'abc').lower(),
+ (char + u'ABC').upper(),
+ (char + u'abc').title(),
+ (char + u'ABC').title(),
+
+ ]
+ h.update(u''.join(data).encode(encoding))
+ 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 = 'cfe20a967a450ebc82ca68c3e4eed344164e11af'
+
+ def test_function_checksum(self):
+ data = []
+ h = sha.sha()
+
+ for i in range(0x10000):
+ char = unichr(i)
+ data = [
+ # Properties
+ str(self.db.digit(char, -1)),
+ str(self.db.numeric(char, -1)),
+ str(self.db.decimal(char, -1)),
+ 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))
+ result = h.hexdigest()
+ self.assertEqual(result, self.expectedchecksum)
+
+ def test_digit(self):
+ self.assertEqual(self.db.digit(u'A', None), None)
+ self.assertEqual(self.db.digit(u'9'), 9)
+ self.assertEqual(self.db.digit(u'\u215b', None), None)
+ self.assertEqual(self.db.digit(u'\u2468'), 9)
+
+ self.assertRaises(TypeError, self.db.digit)
+ self.assertRaises(TypeError, self.db.digit, u'xx')
+ self.assertRaises(ValueError, self.db.digit, u'x')
+
+ def test_numeric(self):
+ self.assertEqual(self.db.numeric(u'A',None), None)
+ self.assertEqual(self.db.numeric(u'9'), 9)
+ self.assertEqual(self.db.numeric(u'\u215b'), 0.125)
+ self.assertEqual(self.db.numeric(u'\u2468'), 9.0)
+
+ self.assertRaises(TypeError, self.db.numeric)
+ self.assertRaises(TypeError, self.db.numeric, u'xx')
+ self.assertRaises(ValueError, self.db.numeric, u'x')
+
+ def test_decimal(self):
+ self.assertEqual(self.db.decimal(u'A',None), None)
+ self.assertEqual(self.db.decimal(u'9'), 9)
+ self.assertEqual(self.db.decimal(u'\u215b', None), None)
+ self.assertEqual(self.db.decimal(u'\u2468', None), None)
+
+ self.assertRaises(TypeError, self.db.decimal)
+ self.assertRaises(TypeError, self.db.decimal, u'xx')
+ self.assertRaises(ValueError, self.db.decimal, u'x')
+
+ def test_category(self):
+ self.assertEqual(self.db.category(u'\uFFFE'), 'Cn')
+ self.assertEqual(self.db.category(u'a'), 'Ll')
+ self.assertEqual(self.db.category(u'A'), 'Lu')
+
+ self.assertRaises(TypeError, self.db.category)
+ self.assertRaises(TypeError, self.db.category, u'xx')
+
+ def test_bidirectional(self):
+ self.assertEqual(self.db.bidirectional(u'\uFFFE'), '')
+ self.assertEqual(self.db.bidirectional(u' '), 'WS')
+ self.assertEqual(self.db.bidirectional(u'A'), 'L')
+
+ self.assertRaises(TypeError, self.db.bidirectional)
+ self.assertRaises(TypeError, self.db.bidirectional, u'xx')
+
+ def test_decomposition(self):
+ self.assertEqual(self.db.decomposition(u'\uFFFE'),'')
+ self.assertEqual(self.db.decomposition(u'\u00bc'), '<fraction> 0031 2044 0034')
+
+ self.assertRaises(TypeError, self.db.decomposition)
+ self.assertRaises(TypeError, self.db.decomposition, u'xx')
+
+ def test_mirrored(self):
+ self.assertEqual(self.db.mirrored(u'\uFFFE'), 0)
+ self.assertEqual(self.db.mirrored(u'a'), 0)
+ self.assertEqual(self.db.mirrored(u'\u2201'), 1)
+
+ self.assertRaises(TypeError, self.db.mirrored)
+ self.assertRaises(TypeError, self.db.mirrored, u'xx')
+
+ def test_combining(self):
+ self.assertEqual(self.db.combining(u'\uFFFE'), 0)
+ self.assertEqual(self.db.combining(u'a'), 0)
+ self.assertEqual(self.db.combining(u'\u20e1'), 230)
+
+ self.assertRaises(TypeError, self.db.combining)
+ self.assertRaises(TypeError, self.db.combining, u'xx')
+
+ def test_normalize(self):
+ self.assertRaises(TypeError, self.db.normalize)
+ self.assertRaises(ValueError, self.db.normalize, 'unknown', u'xx')
+ # The rest can be found in test_normalization.py
+ # which requires an external file.
+
+
+class UnicodeMiscTest(UnicodeDatabaseTest):
+
+ def test_decimal_numeric_consistent(self):
+ # Test that decimal and numeric are consistent,
+ # i.e. if a character has a decimal value,
+ # it's numeric value should be the same.
+ count = 0
+ for i in xrange(0x10000):
+ c = unichr(i)
+ dec = self.db.decimal(c, -1)
+ if dec != -1:
+ self.assertEqual(dec, self.db.numeric(c))
+ count += 1
+ self.assert_(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,
+ # it's numeric value should be the same.
+ count = 0
+ for i in xrange(0x10000):
+ c = unichr(i)
+ dec = self.db.digit(c, -1)
+ if dec != -1:
+ self.assertEqual(dec, self.db.numeric(c))
+ count += 1
+ self.assert_(count >= 10) # should have tested at least the ASCII digits
+
+def test_main():
+ suite = unittest.TestSuite()
+ suite.addTest(unittest.makeSuite(UnicodeMiscTest))
+ suite.addTest(unittest.makeSuite(UnicodeMethodsTest))
+ suite.addTest(unittest.makeSuite(UnicodeFunctionsTest))
+ test.test_support.run_suite(suite)
+
+if __name__ == "__main__":
+ test_main()
projects / python / commitdiff