From a6f73d64c5eb8939731e9262a335f201c117574c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marc-Andr=C3=A9=20Lemburg?= Date: Wed, 28 Jun 2000 16:41:23 +0000 Subject: Marc-Andre Lemburg : Added tests for the new Unicode character name support in the standard unicode-escape codec. --- Lib/test/test_unicode.py | 75 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 7c41534..304e672 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -408,3 +408,78 @@ assert (u"abc" "def") == u"abcdef" assert (u"abc" u"def" "ghi") == u"abcdefghi" assert ("abc" "def" u"ghi") == u"abcdefghi" print 'done.' + +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}" +assert s == u"The rEd fOx ate the sheep.", s +print "done." + +# misc. symbol testing +print "Testing misc. symbols for unicode character name expansion....", +assert u"\N{PILCROW SIGN}" == u"\u00b6" +assert u"\N{REPLACEMENT CHARACTER}" == u"\uFFFD" +assert u"\N{HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK}" == u"\uFF9F" +assert u"\N{FULLWIDTH LATIN SMALL LETTER A}" == u"\uFF41" +print "done." + + +# strict error testing: +print "Testing unicode character name expansion strict error handling....", +k_cchMaxUnicodeName = 83 + +s = "\N{" + "1" * (k_cchMaxUnicodeName + 2) + "}" +try: + unicode(s, 'unicode-escape', 'strict') +except UnicodeError: + pass +else: + raise AssertionError, "failed to raise an exception when presented " \ + "with a UCN > k_cchMaxUnicodeName" +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{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." + -- cgit v0.12