Lib/test/test_unicodedata.py

""" 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'


### Run tests

class UnicodeMethodsTest(unittest.TestCase):

    # update this, if the database changes
    expectedchecksum = 'b7db9b5f1d804976fa921d2009cbef6f025620c1'

    def test_method_checksum(self):
        h = hashlib.sha1()
        for i in range(65536):
            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))
        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 = '3136d5afd787dc2bcb1bdcac95e385349fbebbca'

    def test_function_checksum(self):
        data = []
        h = hashlib.sha1()

        for i in range(0x10000):
            char = chr(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).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('\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_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.assertTrue(error in popen.stderr.read().decode("ascii"))

    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.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,
        # 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.assert_(count >= 10) # should have tested at least the ASCII digits

    def test_bug_1704793(self):
        self.assertEquals(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.assert_(unicodedata.mirrored("\u0f3a"))
        self.assert_(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.assert_("a".upper()=='A')
        self.assert_("\u1d79".upper()=='\ua77d')
        self.assert_(".".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_main():
    test.support.run_unittest(
        UnicodeMiscTest,
        UnicodeMethodsTest,
        UnicodeFunctionsTest
    )

if __name__ == "__main__":
    test_main()