cpython/Lib/test/test_ucn.py

145 lines
4.9 KiB
Python
Raw Normal View History

2000-06-30 06:45:20 -03:00
""" Test script for the Unicode implementation.
Written by Bill Tutt.
Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
2000-06-30 06:45:20 -03:00
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
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,
2003-03-07 13:30:48 -04:00
# to make sure this script runs even if the compiler
# chokes on \N escapes
res = eval(r'"\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 = "The rEd fOx ate the sheep."
self.assertEqual(
"".join([self.checkletter(*args) for args in zip(chars, string)]),
string
)
def test_ascii_letters(self):
import unicodedata
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for char in "".join(map(chr, range(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", "\uac00")
self.checkletter("HANGUL SYLLABLE GGWEOSS", "\uafe8")
self.checkletter("HANGUL SYLLABLE DOLS", "\ub3d0")
self.checkletter("HANGUL SYLLABLE RYAN", "\ub7b8")
self.checkletter("HANGUL SYLLABLE MWIK", "\ubba0")
self.checkletter("HANGUL SYLLABLE BBWAEM", "\ubf88")
self.checkletter("HANGUL SYLLABLE SSEOL", "\uc370")
self.checkletter("HANGUL SYLLABLE YI", "\uc758")
self.checkletter("HANGUL SYLLABLE JJYOSS", "\ucb40")
self.checkletter("HANGUL SYLLABLE KYEOLS", "\ucf28")
self.checkletter("HANGUL SYLLABLE PAN", "\ud310")
self.checkletter("HANGUL SYLLABLE HWEOK", "\ud6f8")
self.checkletter("HANGUL SYLLABLE HIH", "\ud7a3")
import unicodedata
self.assertRaises(ValueError, unicodedata.name, "\ud7a4")
def test_cjk_unified_ideographs(self):
self.checkletter("CJK UNIFIED IDEOGRAPH-3400", "\u3400")
self.checkletter("CJK UNIFIED IDEOGRAPH-4DB5", "\u4db5")
self.checkletter("CJK UNIFIED IDEOGRAPH-4E00", "\u4e00")
self.checkletter("CJK UNIFIED IDEOGRAPH-9FA5", "\u9fa5")
self.checkletter("CJK UNIFIED IDEOGRAPH-20000", "\U00020000")
self.checkletter("CJK UNIFIED IDEOGRAPH-2A6D6", "\U0002a6d6")
def test_bmp_characters(self):
import unicodedata
count = 0
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for code in range(0x10000):
char = chr(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", "\u00b6")
self.checkletter("REPLACEMENT CHARACTER", "\uFFFD")
self.checkletter("HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK", "\uFF9F")
self.checkletter("FULLWIDTH LATIN SMALL LETTER A", "\uFF41")
def test_errors(self):
import unicodedata
self.assertRaises(TypeError, unicodedata.name)
self.assertRaises(TypeError, unicodedata.name, 'xx')
self.assertRaises(TypeError, unicodedata.lookup)
self.assertRaises(KeyError, unicodedata.lookup, 'unknown')
def test_strict_error_handling(self):
# bogus character name
self.assertRaises(
UnicodeError,
str, b"\\N{blah}", 'unicode-escape', 'strict'
)
# long bogus character name
self.assertRaises(
UnicodeError,
str, bytes("\\N{%s}" % ("x" * 100000)), 'unicode-escape', 'strict'
)
# missing closing brace
self.assertRaises(
UnicodeError,
str, b"\\N{SPACE", 'unicode-escape', 'strict'
)
# missing opening brace
self.assertRaises(
UnicodeError,
str, b"\\NSPACE", 'unicode-escape', 'strict'
)
def test_main():
test_support.run_unittest(UnicodeNamesTest)
if __name__ == "__main__":
test_main()