Python codecs.c方法代码示例

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_xmlcharnamereplace(self):
        # This time use a named character entity for unencodable
        # characters, if one is available.

        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;" % htmlentitydefs.codepoint2name[ord(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\u20ac\u232a"
        sout = "«ℜ» = ⟨ሴ€⟩"
        self.assertEqual(sin.encode("ascii", "test.xmlcharnamereplace"), sout)
        sout = "\xabℜ\xbb = ⟨ሴ€⟩"
        self.assertEqual(sin.encode("latin-1", "test.xmlcharnamereplace"), sout)
        sout = "\xabℜ\xbb = ⟨ሴ\xa4⟩"
        self.assertEqual(sin.encode("iso-8859-15", "test.xmlcharnamereplace"), sout) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_charmapencode(self):
        # For charmap encodings the replacement string will be
        # mapped through the encoding again. This means, that
        # to be able to use e.g. the "replace" handler, the
        # charmap has to have a mapping for "?".
        charmap = dict([ (ord(c), 2*c.upper()) for c in "abcdefgh"])
        sin = u"abc"
        sout = "AABBCC"
        self.assertEqual(codecs.charmap_encode(sin, "strict", charmap)[0], sout)

        sin = u"abcA"
        self.assertRaises(UnicodeError, codecs.charmap_encode, sin, "strict", charmap)

        charmap[ord("?")] = "XYZ"
        sin = u"abcDEF"
        sout = "AABBCCXYZXYZXYZ"
        self.assertEqual(codecs.charmap_encode(sin, "replace", charmap)[0], sout)

        charmap[ord("?")] = u"XYZ"
        self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap)

        charmap[ord("?")] = u"XYZ"
        self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_xmlcharnamereplace(self):
        # This time use a named character entity for unencodable
        # characters, if one is available.

        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("&%s;" % html.entities.codepoint2name[ord(c)])
                except KeyError:
                    l.append("&#%d;" % ord(c))
            return ("".join(l), exc.end)

        codecs.register_error(
            "test.xmlcharnamereplace", xmlcharnamereplace)

        sin = "\xab\u211c\xbb = \u2329\u1234\u20ac\u232a"
        sout = b"«ℜ» = ⟨ሴ€⟩"
        self.assertEqual(sin.encode("ascii", "test.xmlcharnamereplace"), sout)
        sout = b"\xabℜ\xbb = ⟨ሴ€⟩"
        self.assertEqual(sin.encode("latin-1", "test.xmlcharnamereplace"), sout)
        sout = b"\xabℜ\xbb = ⟨ሴ\xa4⟩"
        self.assertEqual(sin.encode("iso-8859-15", "test.xmlcharnamereplace"), sout) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_charmapencode(self):
        # For charmap encodings the replacement string will be
        # mapped through the encoding again. This means, that
        # to be able to use e.g. the "replace" handler, the
        # charmap has to have a mapping for "?".
        charmap = dict((ord(c), bytes(2*c.upper(), 'ascii')) for c in "abcdefgh")
        sin = "abc"
        sout = b"AABBCC"
        self.assertEqual(codecs.charmap_encode(sin, "strict", charmap)[0], sout)

        sin = "abcA"
        self.assertRaises(UnicodeError, codecs.charmap_encode, sin, "strict", charmap)

        charmap[ord("?")] = b"XYZ"
        sin = "abcDEF"
        sout = b"AABBCCXYZXYZXYZ"
        self.assertEqual(codecs.charmap_encode(sin, "replace", charmap)[0], sout)

        charmap[ord("?")] = "XYZ" # wrong type in mapping
        self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def replace_surrogate_encode(mystring):
    """
    Returns a (unicode) string, not the more logical bytes, because the codecs
    register_error functionality expects this.
    """
    decoded = []
    for ch in mystring:
        # if utils.PY3:
        #     code = ch
        # else:
        code = ord(ch)

        # The following magic comes from Py3.3's Python/codecs.c file:
        if not 0xD800 <= code <= 0xDCFF:
            # Not a surrogate. Fail with the original exception.
            raise exc
        # mybytes = [0xe0 | (code >> 12),
        #            0x80 | ((code >> 6) & 0x3f),
        #            0x80 | (code & 0x3f)]
        # Is this a good idea?
        if 0xDC00 <= code <= 0xDC7F:
            decoded.append(_unichr(code - 0xDC00))
        elif code <= 0xDCFF:
            decoded.append(_unichr(code - 0xDC00))
        else:
            raise NotASurrogateError
    return str().join(decoded) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def replace_surrogate_encode(mystring):
    """
    Returns a (unicode) string, not the more logical bytes, because the codecs
    register_error functionality expects this.
    """
    decoded = []
    for ch in mystring:
        # if utils.PY3:
        #     code = ch
        # else:
        code = ord(ch)

        # The following magic comes from Py3.3's Python/codecs.c file:
        if not 0xD800 <= code <= 0xDCFF:
            # Not a surrogate. Fail with the original exception.
            raise NotASurrogateError
        # mybytes = [0xe0 | (code >> 12),
        #            0x80 | ((code >> 6) & 0x3f),
        #            0x80 | (code & 0x3f)]
        # Is this a good idea?
        if 0xDC00 <= code <= 0xDC7F:
            decoded.append(_unichr(code - 0xDC00))
        elif code <= 0xDCFF:
            decoded.append(_unichr(code - 0xDC00))
        else:
            raise NotASurrogateError
    return str().join(decoded) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_uninamereplace(self):
        # We're using the names from the unicode database this time,
        # and we're doing "syntax highlighting" here, i.e. we include
        # the replaced text in ANSI escape sequences. For this it is
        # useful that the error handler is not called for every single
        # unencodable character, but for a complete sequence of
        # unencodable characters, otherwise we would output many
        # unnecessary escape sequences.

        def uninamereplace(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]:
                l.append(unicodedata.name(c, u"0x%x" % ord(c)))
            return (u"\033[1m%s\033[0m" % u", ".join(l), exc.end)

        codecs.register_error(
            "test.uninamereplace", uninamereplace)

        sin = u"\xac\u1234\u20ac\u8000"
        sout = "\033[1mNOT SIGN, ETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
        self.assertEqual(sin.encode("ascii", "test.uninamereplace"), sout)

        sout = "\xac\033[1mETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
        self.assertEqual(sin.encode("latin-1", "test.uninamereplace"), sout)

        sout = "\xac\033[1mETHIOPIC SYLLABLE SEE\033[0m\xa4\033[1mCJK UNIFIED IDEOGRAPH-8000\033[0m"
        self.assertEqual(sin.encode("iso-8859-15", "test.uninamereplace"), sout) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_badandgoodxmlcharrefreplaceexceptions(self):
        # "xmlcharrefreplace" complains about a non-exception passed in
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           42
        )
        # "xmlcharrefreplace" complains about the wrong exception types
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           UnicodeError("ouch")
        )
        # "xmlcharrefreplace" can only be used for encoding
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
        )
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
        )
        # Use the correct exception
        cs = (0, 1, 9, 10, 99, 100, 999, 1000, 9999, 10000)
        cs += (0xdfff, 0xd800)
        s = u"".join(unichr(c) for c in cs)
        s += u"\U0001869f\U000186a0\U000f423f\U000f4240"
        cs += (99999, 100000, 999999, 1000000)
        self.assertEqual(
            codecs.xmlcharrefreplace_errors(
                UnicodeEncodeError("ascii", u"a" + s + u"b",
                                   1, 1 + len(s), "ouch")
            ),
            (u"".join(u"&#%d;" % c for c in cs), 1 + len(s))
        ) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_badregistercall(self):
        # enhance coverage of:
        # Modules/_codecsmodule.c::register_error()
        # Python/codecs.c::PyCodec_RegisterError()
        self.assertRaises(TypeError, codecs.register_error, 42)
        self.assertRaises(TypeError, codecs.register_error, "test.dummy", 42) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_unknownhandler(self):
        # enhance coverage of:
        # Modules/_codecsmodule.c::lookup_error()
        self.assertRaises(LookupError, codecs.lookup_error, "test.unknown") 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_xmlcharrefvalues(self):
        # enhance coverage of:
        # Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
        # and inline implementations
        v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000)
        if sys.maxunicode>=100000:
            v += (100000, 500000, 1000000)
        s = u"".join([unichr(x) for x in v])
        codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
        for enc in ("ascii", "iso-8859-15"):
            for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
                s.encode(enc, err) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_translatehelper(self):
        # enhance coverage of:
        # Objects/unicodeobject.c::unicode_encode_call_errorhandler()
        # and callers
        # (Unfortunately the errors argument is not directly accessible
        # from Python, so we can't test that much)
        class D(dict):
            def __getitem__(self, key):
                raise ValueError
        self.assertRaises(ValueError, u"\xff".translate, D())
        self.assertRaises(TypeError, u"\xff".translate, {0xff: sys.maxunicode+1})
        self.assertRaises(TypeError, u"\xff".translate, {0xff: ()}) 

# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import c [as 别名]
def test_badandgoodxmlcharrefreplaceexceptions(self):
        # "xmlcharrefreplace" complains about a non-exception passed in
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           42
        )
        # "xmlcharrefreplace" complains about the wrong exception types
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           UnicodeError("ouch")
        )
        # "xmlcharrefreplace" can only be used for encoding
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
        )
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
        )
        # Use the correct exception
        cs = (0, 1, 9, 10, 99, 100, 999, 1000, 9999, 10000, 0x3042)
        s = "".join(unichr(c) for c in cs)
        self.assertEqual(
            codecs.xmlcharrefreplace_errors(
                UnicodeEncodeError("ascii", s, 0, len(s), "ouch")
            ),
            (u"".join(u"&#%d;" % ord(c) for c in s), len(s))
        )