mirror of
https://github.com/python/cpython.git
synced 2025-08-01 15:43:13 +00:00
f60560626c
errors aren't that helpful), or doesn't contain what's expected from it. Also tweaked the test script so it compiles even if ucnhash is missing.
112 lines
3 KiB
Python
112 lines
3 KiB
Python
""" Test script for the Unicode implementation.
|
|
|
|
Written by Bill Tutt.
|
|
|
|
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|
|
|
"""#"
|
|
from 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 ucnhash
|
|
|
|
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)
|
|
print "done."
|
|
|
|
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)
|
|
count += 1
|
|
except ValueError:
|
|
pass
|
|
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."
|