diff options
| author | Michael W. Hudson <mwh@python.net> | 2002-10-07 12:32:57 +0000 |
|---|---|---|
| committer | Michael W. Hudson <mwh@python.net> | 2002-10-07 12:32:57 +0000 |
| commit | d1bb75505fbb5b47f4f3d420e00964b38c24b203 (patch) | |
| tree | 301416738736d193214c3d6639c94682faf225af /Lib/test | |
| parent | b45532abd26a9752e42ca589b5b0e49552761811 (diff) | |
| download | cpython-git-d1bb75505fbb5b47f4f3d420e00964b38c24b203.tar.gz | |
Backport:
2002/08/11 12:23:04 lemburg Python/bltinmodule.c 2.262
2002/08/11 12:23:04 lemburg Objects/unicodeobject.c 2.162
2002/08/11 12:23:03 lemburg Misc/NEWS 1.461
2002/08/11 12:23:03 lemburg Lib/test/test_unicode.py 1.65
2002/08/11 12:23:03 lemburg Include/unicodeobject.h 2.39
Add C API PyUnicode_FromOrdinal() which exposes unichr() at C level.
u'%c' will now raise a ValueError in case the argument is an
integer outside the valid range of Unicode code point ordinals.
Closes SF bug #593581.
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/test_unicode.py | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 6125c92efc..d4209249b6 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -442,6 +442,14 @@ except KeyError: else: verify(value == u'abc, def') +for ordinal in (-100, 0x200000): + try: + u"%c" % ordinal + except ValueError: + pass + else: + print '*** formatting u"%%c" %% %i should give a ValueError' % ordinal + # formatting jobs delegated from the string implementation: verify('...%(foo)s...' % {'foo':u"abc"} == u'...abc...') verify('...%(foo)s...' % {'foo':"abc"} == '...abc...') @@ -737,6 +745,14 @@ for encoding in ( except ValueError,why: print '*** codec for "%s" failed: %s' % (encoding, why) +# UTF-8 must be roundtrip safe for all UCS-2 code points +# This excludes surrogates: in the full range, there would be +# a surrogate pair (\udbff\udc00), which gets converted back +# to a non-BMP character (\U0010fc00) +u = u''.join(map(unichr, range(0,0xd800)+range(0xe000,0x10000))) +for encoding in ('utf-8',): + verify(unicode(u.encode(encoding),encoding) == u) + print 'done.' print 'Testing Unicode string concatenation...', |