diff options
| author | Martin v. Löwis <martin@v.loewis.de> | 2002-11-23 18:01:32 (GMT) |
|---|---|---|
| committer | Martin v. Löwis <martin@v.loewis.de> | 2002-11-23 18:01:32 (GMT) |
| commit | ef7fe2e8137824248cf45d316535b76dae302b5a (patch) | |
| tree | 01a0b67fae5af758f8c8cc18459266756f4e1074 /Lib | |
| parent | 8579efc86c18b7b824ec080582f032674e2f8a5e (diff) | |
| download | cpython-ef7fe2e8137824248cf45d316535b76dae302b5a.zip cpython-ef7fe2e8137824248cf45d316535b76dae302b5a.tar.gz cpython-ef7fe2e8137824248cf45d316535b76dae302b5a.tar.bz2 | |
Implement names for CJK unified ideographs. Add name to KeyError output.
Verify that the lookup for an existing name succeeds.
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/test/output/test_ucn | 5 | ||||
| -rw-r--r-- | Lib/test/test_ucn.py | 20 |
2 files changed, 19 insertions, 6 deletions
diff --git a/Lib/test/output/test_ucn b/Lib/test/output/test_ucn index 1006c07..c41017b 100644 --- a/Lib/test/output/test_ucn +++ b/Lib/test/output/test_ucn @@ -2,7 +2,8 @@ test_ucn Testing General Unicode Character Name, and case insensitivity... done. Testing name to code mapping.... done. Testing hangul syllable names.... done. -Testing code to name mapping for all characters.... done. -Found 22728 characters in the unicode name database +Testing names of CJK unified ideographs.... done. +Testing code to name mapping for all BMP characters.... done. +Found 50212 characters in the unicode name database Testing misc. symbols for unicode character name expansion.... done. Testing unicode character name expansion strict error handling.... done. diff --git a/Lib/test/test_ucn.py b/Lib/test/test_ucn.py index 6f2b022..e7b8bbd 100644 --- a/Lib/test/test_ucn.py +++ b/Lib/test/test_ucn.py @@ -80,16 +80,28 @@ else: raise AssertionError, "Found name for U+D7A4" print "done." -print "Testing code to name mapping for all characters....", +print "Testing names of CJK unified ideographs....", +exec r""" +verify(u"\N{CJK UNIFIED IDEOGRAPH-3400}" == u"\u3400") +verify(u"\N{CJK UNIFIED IDEOGRAPH-4DB5}" == u"\u4db5") +verify(u"\N{CJK UNIFIED IDEOGRAPH-4E00}" == u"\u4e00") +verify(u"\N{CJK UNIFIED IDEOGRAPH-9FA5}" == u"\u9fa5") +verify(u"\N{CJK UNIFIED IDEOGRAPH-20000}" == u"\U00020000") +verify(u"\N{CJK UNIFIED IDEOGRAPH-2A6D6}" == u"\U0002a6d6") +""" +print "done." + +print "Testing code to name mapping for all BMP characters....", count = 0 -for code in range(65536): +for code in range(0x10000): try: char = unichr(code) name = unicodedata.name(char) - verify(unicodedata.lookup(name) == char) - count += 1 except (KeyError, ValueError): pass + else: + verify(unicodedata.lookup(name) == char) + count += 1 print "done." print "Found", count, "characters in the unicode name database" |