[KoCo-CVS] [Commit] cjkcodecs/tests test_multibytecodec_support.py

[Hye-Shik C. <pe...@us...>]

perky       03/05/26 08:08:49

  Modified:    tests    test_multibytecodec_support.py
  Log:
  Merge changes from iconv_codec.
  
  Revision  Changes    Path
  1.3       +66 -42    cjkcodecs/tests/test_multibytecodec_support.py
  
  Index: test_multibytecodec_support.py
  ===================================================================
  RCS file: /cvsroot/koco/cjkcodecs/tests/test_multibytecodec_support.py,v
  retrieving revision 1.2
  retrieving revision 1.3
  diff -u -r1.2 -r1.3
  --- test_multibytecodec_support.py	26 May 2003 11:40:41 -0000	1.2
  +++ test_multibytecodec_support.py	26 May 2003 15:08:49 -0000	1.3
  @@ -27,7 +27,7 @@
   # IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
   # POSSIBILITY OF SUCH DAMAGE.
   #
  -# $Id: test_multibytecodec_support.py,v 1.2 2003/05/26 11:40:41 perky Exp $
  +# $Id: test_multibytecodec_support.py,v 1.3 2003/05/26 15:08:49 perky Exp $
   #
   
   import sys, codecs
  @@ -68,47 +68,48 @@
               else:
                   self.assertRaises(UnicodeError, func, source, scheme)
   
  -    def test_xmlcharrefreplace(self):
  -        if self.has_iso10646:
  -            return
  -
  -        s = u"\u0b13\u0b23\u0b60 nd eggs"
  -        self.assertEqual(
  -            self.encode(s, "xmlcharrefreplace")[0],
  -            "ଓଣୠ nd eggs"
  -        )
  -
  -    def test_customreplace(self):
  -        if self.has_iso10646:
  -            return
  -
  -        import htmlentitydefs
  -
  -        names = {}
  -        for (key, value) in htmlentitydefs.entitydefs.items():
  -            if len(value)==1:
  -                names[value.decode('latin-1')] = self.decode(key)[0]
  -            else:
  -                names[unichr(int(value[2:-1]))] = self.decode(key)[0]
  -
  -        def xmlcharnamereplace(exc):
  -            if not isinstance(exc, UnicodeEncodeError):
  -                raise TypeError("don't know how to handle %r" % exc)
  -            l = []
  -            for c in exc.object[exc.start:exc.end]:
  -                try:
  -                    l.append(u"&%s;" % names[c])
  -                except KeyError:
  -                    l.append(u"&#%d;" % ord(c))
  -            return (u"".join(l), exc.end)
  -
  -        codecs.register_error(
  -            "test.xmlcharnamereplace", xmlcharnamereplace)
  -
  -        sin = u"\xab\u211c\xbb = \u2329\u1234\u232a"
  -        sout = "«ℜ» = ⟨ሴ⟩"
  -        self.assertEqual(self.encode(sin,
  -                                    "test.xmlcharnamereplace")[0], sout)
  +    if sys.hexversion >= 0x02030000:
  +        def test_xmlcharrefreplace(self):
  +            if self.has_iso10646:
  +                return
  +
  +            s = u"\u0b13\u0b23\u0b60 nd eggs"
  +            self.assertEqual(
  +                self.encode(s, "xmlcharrefreplace")[0],
  +                "ଓଣୠ nd eggs"
  +            )
  +
  +        def test_customreplace(self):
  +            if self.has_iso10646:
  +                return
  +
  +            import htmlentitydefs
  +
  +            names = {}
  +            for (key, value) in htmlentitydefs.entitydefs.items():
  +                if len(value)==1:
  +                    names[value.decode('latin-1')] = self.decode(key)[0]
  +                else:
  +                    names[unichr(int(value[2:-1]))] = self.decode(key)[0]
  +
  +            def xmlcharnamereplace(exc):
  +                if not isinstance(exc, UnicodeEncodeError):
  +                    raise TypeError("don't know how to handle %r" % exc)
  +                l = []
  +                for c in exc.object[exc.start:exc.end]:
  +                    try:
  +                        l.append(u"&%s;" % names[c])
  +                    except KeyError:
  +                        l.append(u"&#%d;" % ord(c))
  +                return (u"".join(l), exc.end)
  +
  +            codecs.register_error(
  +                "test.xmlcharnamereplace", xmlcharnamereplace)
  +
  +            sin = u"\xab\u211c\xbb = \u2329\u1234\u232a"
  +            sout = "«ℜ» = ⟨ሴ⟩"
  +            self.assertEqual(self.encode(sin,
  +                                        "test.xmlcharnamereplace")[0], sout)
   
       def test_streamreader(self):
           UTF8Writer = codecs.lookup('utf-8')[3]
  @@ -128,6 +129,29 @@
                           ostream.write(data)
   
                   self.assertEqual(ostream.getvalue(), self.tstring[1])
  +
  +    def test_streamwriter(self):
  +        # We can't test with the real utf-8 StreamReader here.
  +        # The standard SR.readline{,s} are mostly broken for multibyte seqs.
  +        #UTF8Reader = codecs.lookup('utf-8')[2]
  +        return
  +        UTF8Reader = iconv_codec.lookup('utf-8')[2]
  +        for name in ["read", "readline", "readlines"]:
  +            for sizehint in [None, -1] + range(1, 33) + \
  +                            [64, 128, 256, 512, 1024]:
  +                istream = UTF8Reader(StringIO(self.tstring[1]))
  +                ostream = self.writer(StringIO())
  +                func = getattr(istream, name)
  +                while 1:
  +                    data = func(sizehint)
  +                    if not data:
  +                        break
  +                    if name == "readlines":
  +                        ostream.writelines(data)
  +                    else:
  +                        ostream.write(data)
  +
  +                self.assertEqual(ostream.getvalue(), self.tstring[0])
   
   class TestBase_Mapping(unittest.TestCase):
       pass_enctest = []