cpython/Lib/test/test_ucn.py

104 lines
2.8 KiB
Python
Raw Normal View History

2000-06-30 06:45:20 -03:00
""" Test script for the Unicode implementation.
Written by Bill Tutt.
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
from test_support import verify, verbose
2000-06-30 06:45:20 -03:00
print 'Testing General Unicode Character Name, and case insensitivity...',
# General and case insensitivity test:
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)
2001-01-19 07:13:46 -04:00
print "done."
import ucnhash
2001-01-19 07:13:46 -04:00
print "Testing name to code mapping....",
for char in "SPAM":
name = "LATIN SMALL LETTER %s" % char
code = ucnhash.getcode(name)
verify(ucnhash.getname(code) == name)
2001-01-19 07:13:46 -04:00
print "done."
2001-01-19 07:13:46 -04:00
print "Testing code to name mapping for all characters....",
count = 0
for code in range(65536):
try:
name = ucnhash.getname(code)
verify(ucnhash.getcode(name) == code)
2001-01-19 07:13:46 -04:00
count += 1
except ValueError:
pass
2000-06-30 06:45:20 -03:00
print "done."
2001-01-19 07:13:46 -04:00
print "Found", count, "characters in the unicode name database"
2000-06-30 06:45:20 -03:00
# misc. symbol testing
print "Testing misc. symbols for unicode character name expansion....",
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")
2000-06-30 06:45:20 -03:00
print "done."
# strict error testing:
print "Testing unicode character name expansion strict error handling....",
try:
unicode("\N{blah}", 'unicode-escape', 'strict')
2000-06-30 06:45:20 -03:00
except UnicodeError:
pass
2000-06-30 06:45:20 -03:00
else:
raise AssertionError, "failed to raise an exception when given a bogus character name"
2000-06-30 06:45:20 -03:00
try:
unicode("\N{" + "x" * 100000 + "}", 'unicode-escape', 'strict')
2000-06-30 06:45:20 -03:00
except UnicodeError:
pass
2000-06-30 06:45:20 -03:00
else:
raise AssertionError, "failed to raise an exception when given a very " \
"long bogus character name"
2000-06-30 06:45:20 -03:00
try:
unicode("\N{SPACE", 'unicode-escape', 'strict')
2000-06-30 06:45:20 -03:00
except UnicodeError:
pass
2000-06-30 06:45:20 -03:00
else:
raise AssertionError, "failed to raise an exception for a missing closing brace."
2000-06-30 06:45:20 -03:00
try:
unicode("\NSPACE", 'unicode-escape', 'strict')
2000-06-30 06:45:20 -03:00
except UnicodeError:
pass
2000-06-30 06:45:20 -03:00
else:
raise AssertionError, "failed to raise an exception for a missing opening brace."
2000-06-30 06:45:20 -03:00
print "done."