diff options
Diffstat (limited to 'Lib/test/test_unicodedata.py')
| -rw-r--r-- | Lib/test/test_unicodedata.py | 400 |
1 files changed, 160 insertions, 240 deletions
diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py index 4b5c892..11f2cda 100644 --- a/Lib/test/test_unicodedata.py +++ b/Lib/test/test_unicodedata.py @@ -1,4 +1,4 @@ -""" Tests for the unicodedata module. +""" Test script for the unicodedata module. Written by Marc-Andre Lemburg (mal@lemburg.com). @@ -6,46 +6,48 @@ """ -import hashlib -from http.client import HTTPException import sys -import unicodedata import unittest -from test.support import open_urlresource, requires_resource, script_helper +import hashlib +import subprocess +import test.test_support + +encoding = 'utf-8' + +### Run tests class UnicodeMethodsTest(unittest.TestCase): # update this, if the database changes - expectedchecksum = 'e728278035eb76cf92d86f07852266b0433f16a5' + expectedchecksum = '4504dffd035baea02c5b9de82bebc3d65e0e0baf' - @requires_resource('cpu') def test_method_checksum(self): h = hashlib.sha1() - for i in range(sys.maxunicode + 1): - char = chr(i) + for i in range(0x10000): + char = unichr(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()], + 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) - "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()], + 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(), @@ -53,175 +55,180 @@ class UnicodeMethodsTest(unittest.TestCase): char.title(), # Mappings (multiple chars) - (char + 'abc').lower(), - (char + 'ABC').upper(), - (char + 'abc').title(), - (char + 'ABC').title(), + (char + u'abc').lower(), + (char + u'ABC').upper(), + (char + u'abc').title(), + (char + u'ABC').title(), ] - h.update(''.join(data).encode('utf-8', 'surrogatepass')) + h.update(u''.join(data).encode(encoding)) result = h.hexdigest() self.assertEqual(result, self.expectedchecksum) class UnicodeDatabaseTest(unittest.TestCase): - db = unicodedata + + 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. Make sure to do a full rebuild - # (e.g. 'make distclean && make') to get the correct checksum. - expectedchecksum = '4bcbf9df344114b1ebc95b904f4352dd250dff7e' + # update this, if the database changes + expectedchecksum = '6ccf1b1a36460d2694f9b0b0f0324942fe70ede6' - @requires_resource('cpu') def test_function_checksum(self): data = [] h = hashlib.sha1() - for i in range(sys.maxunicode + 1): - char = chr(i) + for i in range(0x10000): + char = unichr(i) data = [ # Properties - format(self.db.digit(char, -1), '.12g'), - format(self.db.numeric(char, -1), '.12g'), - format(self.db.decimal(char, -1), '.12g'), + 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).encode("ascii")) + h.update(''.join(data)) 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.assertEqual(self.db.digit('\U0001D7FD'), 7) + 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.assertEqual(self.db.digit(u'\U00020000', None), None) self.assertRaises(TypeError, self.db.digit) - self.assertRaises(TypeError, self.db.digit, 'xx') - self.assertRaises(ValueError, self.db.digit, 'x') + 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('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) + 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.assertEqual(self.db.numeric(u'\ua627'), 7.0) + self.assertEqual(self.db.numeric(u'\U00020000', None), None) self.assertRaises(TypeError, self.db.numeric) - self.assertRaises(TypeError, self.db.numeric, 'xx') - self.assertRaises(ValueError, self.db.numeric, 'x') + 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('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.assertEqual(self.db.decimal('\U0001D7FD'), 7) + 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.assertEqual(self.db.decimal(u'\U00020000', None), None) self.assertRaises(TypeError, self.db.decimal) - self.assertRaises(TypeError, self.db.decimal, 'xx') - self.assertRaises(ValueError, self.db.decimal, 'x') + 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('\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') + 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.assertEqual(self.db.category(u'\U00020000'), 'Lo') self.assertRaises(TypeError, self.db.category) - self.assertRaises(TypeError, self.db.category, 'xx') + self.assertRaises(TypeError, self.db.category, u'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.assertEqual(self.db.bidirectional(u'\uFFFE'), '') + self.assertEqual(self.db.bidirectional(u' '), 'WS') + self.assertEqual(self.db.bidirectional(u'A'), 'L') + self.assertEqual(self.db.bidirectional(u'\U00020000'), 'L') self.assertRaises(TypeError, self.db.bidirectional) - self.assertRaises(TypeError, self.db.bidirectional, 'xx') + self.assertRaises(TypeError, self.db.bidirectional, u'xx') def test_decomposition(self): - self.assertEqual(self.db.decomposition('\uFFFE'),'') - self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034') + 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, 'xx') + self.assertRaises(TypeError, self.db.decomposition, u'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.assertEqual(self.db.mirrored(u'\uFFFE'), 0) + self.assertEqual(self.db.mirrored(u'a'), 0) + self.assertEqual(self.db.mirrored(u'\u2201'), 1) + self.assertEqual(self.db.mirrored(u'\U00020000'), 0) self.assertRaises(TypeError, self.db.mirrored) - self.assertRaises(TypeError, self.db.mirrored, 'xx') + self.assertRaises(TypeError, self.db.mirrored, u'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.assertEqual(self.db.combining(u'\uFFFE'), 0) + self.assertEqual(self.db.combining(u'a'), 0) + self.assertEqual(self.db.combining(u'\u20e1'), 230) + self.assertEqual(self.db.combining(u'\U00020000'), 0) self.assertRaises(TypeError, self.db.combining) - self.assertRaises(TypeError, self.db.combining, 'xx') + 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') + self.assertEqual(self.db.normalize('NFKC', u''), u'') + # 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') + composed = (u"\u0b47\u0300\u0b3e", u"\u1100\u0300\u1161", + u'Li\u030dt-s\u1e73\u0301', + u'\u092e\u093e\u0930\u094d\u0915 \u091c\u093c' + + u'\u0941\u0915\u0947\u0930\u092c\u0930\u094d\u0917', + u'\u0915\u093f\u0930\u094d\u0917\u093f\u091c\u093c' + + 'u\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' + a = u'C\u0338' * 20 + u'C\u0327' + b = u'C\u0338' * 20 + u'\xC7' self.assertEqual(self.db.normalize('NFC', a), b) def test_issue29456(self): # Fix #29456 - u1176_str_a = '\u1100\u1176\u11a8' - u1176_str_b = '\u1100\u1176\u11a8' - u11a7_str_a = '\u1100\u1175\u11a7' - u11a7_str_b = '\uae30\u11a7' - u11c3_str_a = '\u1100\u1175\u11c3' - u11c3_str_b = '\uae30\u11c3' + u1176_str_a = u'\u1100\u1176\u11a8' + u1176_str_b = u'\u1100\u1176\u11a8' + u11a7_str_a = u'\u1100\u1175\u11a7' + u11a7_str_b = u'\uae30\u11a7' + u11c3_str_a = u'\u1100\u1175\u11c3' + u11c3_str_b = u'\uae30\u11c3' self.assertEqual(self.db.normalize('NFC', u1176_str_a), u1176_str_b) self.assertEqual(self.db.normalize('NFC', u11a7_str_a), u11a7_str_b) self.assertEqual(self.db.normalize('NFC', u11c3_str_a), u11c3_str_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') - - 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') + self.assertRaises(TypeError, eaw, 'a') + self.assertRaises(TypeError, eaw, u'') + self.assertRaises(TypeError, eaw, u'ra') + self.assertEqual(eaw(u'\x1e'), 'N') + self.assertEqual(eaw(u'\x20'), 'Na') + self.assertEqual(eaw(u'\uC894'), 'W') + self.assertEqual(eaw(u'\uFF66'), 'H') + self.assertEqual(eaw(u'\uFF1F'), 'F') + self.assertEqual(eaw(u'\u2010'), 'A') + self.assertEqual(eaw(u'\U00020000'), 'W') class UnicodeMiscTest(UnicodeDatabaseTest): @@ -233,21 +240,24 @@ class UnicodeMiscTest(UnicodeDatabaseTest): # This program should raise a SyntaxError in the eval. code = "import sys;" \ "sys.modules['unicodedata'] = None;" \ - """eval("'\\\\N{SOFT HYPHEN}'")""" - # We use a separate process because the unicodedata module may already - # have been loaded in this process. - result = script_helper.assert_python_failure("-c", code) - error = "SyntaxError: (unicode error) \\N escapes not supported " \ + """eval("u'\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, result.err.decode("ascii")) + self.assertIn(error, popen.stderr.read()) 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) + for i in xrange(0x10000): + c = unichr(i) dec = self.db.decimal(c, -1) if dec != -1: self.assertEqual(dec, self.db.numeric(c)) @@ -259,8 +269,8 @@ class UnicodeMiscTest(UnicodeDatabaseTest): # 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 i in xrange(0x10000): + c = unichr(i) dec = self.db.digit(c, -1) if dec != -1: self.assertEqual(dec, self.db.numeric(c)) @@ -268,39 +278,39 @@ class UnicodeMiscTest(UnicodeDatabaseTest): 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') + self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), u'\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")) + self.assertTrue(unicodedata.mirrored(u"\u0f3a")) + self.assertTrue(not unicodedata.ucd_3_2_0.mirrored(u"\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()=='.') + self.assertTrue(u"a".upper()==u'A') + self.assertTrue(u"\u1d79".upper()==u'\ua77d') + self.assertTrue(u".".upper()==u".") def test_bug_5828(self): - self.assertEqual("\u1d79".lower(), "\u1d79") + self.assertEqual(u"\u1d79".lower(), u"\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() + if u"\x00" in unichr(c).lower()+unichr(c).upper()+unichr(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") + self.assertEqual(u"\u01c4".title(), u"\u01c5") + self.assertEqual(u"\u01c5".title(), u"\u01c5") + self.assertEqual(u"\u01c6".title(), u"\u01c5") def test_linebreak_7643(self): for i in range(0x10000): - lines = (chr(i) + 'A').splitlines() + lines = (unichr(i) + u'A').splitlines() if i in (0x0a, 0x0b, 0x0c, 0x0d, 0x85, 0x1c, 0x1d, 0x1e, 0x2028, 0x2029): self.assertEqual(len(lines), 2, @@ -309,102 +319,12 @@ class UnicodeMiscTest(UnicodeDatabaseTest): self.assertEqual(len(lines), 1, r"\u%.4x should not be a linebreak" % i) -class NormalizationTest(unittest.TestCase): - @staticmethod - def check_version(testfile): - hdr = testfile.readline() - return unicodedata.unidata_version in hdr - - @staticmethod - def unistr(data): - data = [int(x, 16) for x in data.split(" ")] - return "".join([chr(x) for x in data]) - - def test_normalization(self): - TESTDATAFILE = "NormalizationTest.txt" - TESTDATAURL = f"http://www.pythontest.net/unicode/{unicodedata.unidata_version}/{TESTDATAFILE}" - - # Hit the exception early - try: - testdata = open_urlresource(TESTDATAURL, encoding="utf-8", - check=self.check_version) - except PermissionError: - self.skipTest(f"Permission error when downloading {TESTDATAURL} " - f"into the test data directory") - except (OSError, HTTPException): - self.fail(f"Could not retrieve {TESTDATAURL}") - - with testdata: - self.run_normalization_tests(testdata) - - def run_normalization_tests(self, testdata): - part = None - part1_data = {} - - 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) - - for line in testdata: - if '#' in line: - line = line.split('#')[0] - line = line.strip() - if not line: - continue - if line.startswith("@Part"): - part = line.split()[0] - continue - c1,c2,c3,c4,c5 = [self.unistr(x) for x in line.split(';')[:-1]] - - # Perform tests - self.assertTrue(c2 == NFC(c1) == NFC(c2) == NFC(c3), line) - self.assertTrue(c4 == NFC(c4) == NFC(c5), line) - self.assertTrue(c3 == NFD(c1) == NFD(c2) == NFD(c3), line) - self.assertTrue(c5 == NFD(c4) == NFD(c5), line) - self.assertTrue(c4 == NFKC(c1) == NFKC(c2) == \ - NFKC(c3) == NFKC(c4) == NFKC(c5), - line) - self.assertTrue(c5 == NFKD(c1) == NFKD(c2) == \ - NFKD(c3) == NFKD(c4) == NFKD(c5), - line) - - self.assertTrue(unicodedata.is_normalized("NFC", c2)) - self.assertTrue(unicodedata.is_normalized("NFC", c4)) - - self.assertTrue(unicodedata.is_normalized("NFD", c3)) - self.assertTrue(unicodedata.is_normalized("NFD", c5)) - - self.assertTrue(unicodedata.is_normalized("NFKC", c4)) - self.assertTrue(unicodedata.is_normalized("NFKD", c5)) - - # Record part 1 data - if part == "@Part1": - part1_data[c1] = 1 - - # Perform tests for all other data - for c in range(sys.maxunicode+1): - X = chr(c) - if X in part1_data: - continue - self.assertTrue(X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X), c) - - def test_edge_cases(self): - self.assertRaises(TypeError, unicodedata.normalize) - self.assertRaises(ValueError, unicodedata.normalize, 'unknown', 'xx') - self.assertEqual(unicodedata.normalize('NFKC', ''), '') - - def test_bug_834676(self): - # Check for bug 834676 - unicodedata.normalize('NFC', '\ud55c\uae00') - +def test_main(): + test.test_support.run_unittest( + UnicodeMiscTest, + UnicodeMethodsTest, + UnicodeFunctionsTest + ) if __name__ == "__main__": - unittest.main() + test_main() |