Python codecs.getencoder() Examples

def test_all(self):
        api = (
            "encode", "decode",
            "register", "CodecInfo", "Codec", "IncrementalEncoder",
            "IncrementalDecoder", "StreamReader", "StreamWriter", "lookup",
            "getencoder", "getdecoder", "getincrementalencoder",
            "getincrementaldecoder", "getreader", "getwriter",
            "register_error", "lookup_error",
            "strict_errors", "replace_errors", "ignore_errors",
            "xmlcharrefreplace_errors", "backslashreplace_errors",
            "namereplace_errors",
            "open", "EncodedFile",
            "iterencode", "iterdecode",
            "BOM", "BOM_BE", "BOM_LE",
            "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_BE", "BOM_UTF16_LE",
            "BOM_UTF32", "BOM_UTF32_BE", "BOM_UTF32_LE",
            "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",  # Undocumented
            "StreamReaderWriter", "StreamRecoder",
        )
        self.assertCountEqual(api, codecs.__all__)
        for api in codecs.__all__:
            getattr(codecs, api) 

def header_check(self, content):
        """Special HTML encoding check."""

        encode = None

        # Look for meta charset
        m = RE_HTML_ENCODE.search(content)
        if m:
            enc = m.group(1).decode('ascii')

            try:
                codecs.getencoder(enc)
                encode = enc
            except LookupError:
                pass
        else:
            encode = self._has_xml_encode(content)
        return encode 

def str_encode(arr, encoding, errors="strict"):
    """
    Encode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.encode`.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    encoded : Series/Index of objects
    """
    if encoding in _cpython_optimized_encoders:
        # CPython optimized implementation
        f = lambda x: x.encode(encoding, errors)
    else:
        encoder = codecs.getencoder(encoding)
        f = lambda x: encoder(x, errors)[0]
    return _na_map(f, arr) 

def alpha_encode(data: Any, metadata: 'XMetadata', field_metadata: 'XField') -> bytes:
    """Encode alpha or alphanumeric data.
    metadata has encoding.
    field_metadata is not used.

    Mock metadata objects
    >>> import types
    >>> meta = types.SimpleNamespace(encoding='ebcdic')
    >>> meta.encode = codecs.getencoder(meta.encoding)
    >>> field_meta = types.SimpleNamespace(length=6)

    >>> data = '98765-'
    >>> actual = alpha_encode(data, meta, field_meta)
    >>> repr(actual)
    "b'\\\\xf9\\\\xf8\\\\xf7\\\\xf6\\\\xf5`'"
    >>> actual == bytes([0xf9, 0xf8, 0xf7, 0xf6, 0xf5, 0x60])
    True

    """
    bytes, _ = metadata.encode("{:<{size}s}".format(data, size=field_metadata.length))
    return bytes


# Encoder for numeric USAGE DISPLAY, trailing sign. 

def test_all(self):
        api = (
            "encode", "decode",
            "register", "CodecInfo", "Codec", "IncrementalEncoder",
            "IncrementalDecoder", "StreamReader", "StreamWriter", "lookup",
            "getencoder", "getdecoder", "getincrementalencoder",
            "getincrementaldecoder", "getreader", "getwriter",
            "register_error", "lookup_error",
            "strict_errors", "replace_errors", "ignore_errors",
            "xmlcharrefreplace_errors", "backslashreplace_errors",
            "open", "EncodedFile",
            "iterencode", "iterdecode",
            "BOM", "BOM_BE", "BOM_LE",
            "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_BE", "BOM_UTF16_LE",
            "BOM_UTF32", "BOM_UTF32_BE", "BOM_UTF32_LE",
            "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",  # Undocumented
            "StreamReaderWriter", "StreamRecoder",
        )
        self.assertCountEqual(api, codecs.__all__)
        for api in codecs.__all__:
            getattr(codecs, api) 

def test_all(self):
        api = (
            "encode", "decode",
            "register", "CodecInfo", "Codec", "IncrementalEncoder",
            "IncrementalDecoder", "StreamReader", "StreamWriter", "lookup",
            "getencoder", "getdecoder", "getincrementalencoder",
            "getincrementaldecoder", "getreader", "getwriter",
            "register_error", "lookup_error",
            "strict_errors", "replace_errors", "ignore_errors",
            "xmlcharrefreplace_errors", "backslashreplace_errors",
            "namereplace_errors",
            "open", "EncodedFile",
            "iterencode", "iterdecode",
            "BOM", "BOM_BE", "BOM_LE",
            "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_BE", "BOM_UTF16_LE",
            "BOM_UTF32", "BOM_UTF32_BE", "BOM_UTF32_LE",
            "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",  # Undocumented
            "StreamReaderWriter", "StreamRecoder",
        )
        self.assertCountEqual(api, codecs.__all__)
        for api in codecs.__all__:
            getattr(codecs, api) 

def _filter_encode(self, data, encoding):
		if its.py_v3 and isinstance(data, str):
			data = data.encode('utf-8')
		encoding = encoding.lower()
		encoding = re.sub(r'^(base|rot)-(\d\d)$', r'\1\2', encoding)

		if encoding == 'base16' or encoding == 'hex':
			data = base64.b16encode(data)
		elif encoding == 'base32':
			data = base64.b32encode(data)
		elif encoding == 'base64':
			data = base64.b64encode(data)
		elif encoding == 'rot13':
			data = codecs.getencoder('rot-13')(data.decode('utf-8'))[0]
		else:
			raise ValueError('Unknown encoding type: ' + encoding)
		if its.py_v3 and isinstance(data, bytes):
			data = data.decode('utf-8')
		return data 

def str_encode(arr, encoding, errors="strict"):
    """
    Encode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.encode`.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    encoded : Series/Index of objects
    """
    if encoding in _cpython_optimized_encoders:
        # CPython optimized implementation
        f = lambda x: x.encode(encoding, errors)
    else:
        encoder = codecs.getencoder(encoding)
        f = lambda x: encoder(x, errors)[0]
    return _na_map(f, arr) 

def str_encode(arr, encoding, errors="strict"):
    """
    Encode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.encode`.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    encoded : Series/Index of objects
    """
    if encoding in _cpython_optimized_encoders:
        # CPython optimized implementation
        f = lambda x: x.encode(encoding, errors)
    else:
        encoder = codecs.getencoder(encoding)
        f = lambda x: encoder(x, errors)[0]
    return _na_map(f, arr) 

def test_all(self):
        api = (
            "encode", "decode",
            "register", "CodecInfo", "Codec", "IncrementalEncoder",
            "IncrementalDecoder", "StreamReader", "StreamWriter", "lookup",
            "getencoder", "getdecoder", "getincrementalencoder",
            "getincrementaldecoder", "getreader", "getwriter",
            "register_error", "lookup_error",
            "strict_errors", "replace_errors", "ignore_errors",
            "xmlcharrefreplace_errors", "backslashreplace_errors",
            "open", "EncodedFile",
            "iterencode", "iterdecode",
            "BOM", "BOM_BE", "BOM_LE",
            "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_BE", "BOM_UTF16_LE",
            "BOM_UTF32", "BOM_UTF32_BE", "BOM_UTF32_LE",
            "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",  # Undocumented
            "StreamReaderWriter", "StreamRecoder",
        )
        self.assertEqual(sorted(api), sorted(codecs.__all__))
        for api in codecs.__all__:
            getattr(codecs, api) 

def str_encode(arr, encoding, errors="strict"):
    """
    Encode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.encode`.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    encoded : Series/Index of objects
    """
    if encoding in _cpython_optimized_encoders:
        # CPython optimized implementation
        f = lambda x: x.encode(encoding, errors)
    else:
        encoder = codecs.getencoder(encoding)
        f = lambda x: encoder(x, errors)[0]
    return _na_map(f, arr) 

def bind_processor(self, dialect):
        if self.convert_unicode or dialect.convert_unicode:
            if dialect.supports_unicode_binds and \
                    self.convert_unicode != 'force':
                if self._warn_on_bytestring:
                    def process(value):
                        if isinstance(value, util.binary_type):
                            util.warn_limited(
                                "Unicode type received non-unicode "
                                "bind param value %r.",
                                (util.ellipses_string(value),))
                        return value
                    return process
                else:
                    return None
            else:
                encoder = codecs.getencoder(dialect.encoding)
                warn_on_bytestring = self._warn_on_bytestring

                def process(value):
                    if isinstance(value, util.text_type):
                        return encoder(value, self.unicode_error)[0]
                    elif warn_on_bytestring and value is not None:
                        util.warn_limited(
                            "Unicode type received non-unicode bind "
                            "param value %r.",
                            (util.ellipses_string(value),))
                    return value
            return process
        else:
            return None 

def bind_processor(self, dialect):
        if self.convert_unicode or dialect.convert_unicode:
            if dialect.supports_unicode_binds and \
                    self.convert_unicode != 'force':
                if self._warn_on_bytestring:
                    def process(value):
                        if isinstance(value, util.binary_type):
                            util.warn("Unicode type received non-unicode"
                                      "bind param value.")
                        return value
                    return process
                else:
                    return None
            else:
                encoder = codecs.getencoder(dialect.encoding)
                warn_on_bytestring = self._warn_on_bytestring

                def process(value):
                    if isinstance(value, util.text_type):
                        return encoder(value, self.unicode_error)[0]
                    elif warn_on_bytestring and value is not None:
                        util.warn("Unicode type received non-unicode bind "
                                  "param value")
                    return value
            return process
        else:
            return None 

def hexencode(b):
    if sys.version_info[0] < 3:
        return b.encode('hex')
    else:
        import codecs
        coder = codecs.getencoder('hex_codec')
        return coder(b)[0] 

def iter(self, fields, files):
        """
        :param fields: sequence of (name, value) elements for regular form fields
        :param files: sequence of (name, filename, contenttype, filedata) elements for data to be uploaded as files
        :return:
        """
        encoder = codecs.getencoder('utf-8')
        for (key, value) in fields:
            key = self.u(key)
            yield encoder('--{}\r\n'.format(self.boundary))
            yield encoder(self.u('Content-Disposition: form-data; name="{}"\r\n').format(key))
            yield encoder('\r\n')
            if isinstance(value, (int, float)):
                value = str(value)
            yield encoder(self.u(value))
            yield encoder('\r\n')
        for (key, filename, contenttype, fd) in files:
            key = self.u(key)
            filename = self.u(filename)
            yield encoder('--{}\r\n'.format(self.boundary))
            yield encoder(self.u('Content-Disposition: form-data; name="{}"; filename="{}"\r\n').format(key, filename))
            yield encoder('Content-Type: {}\r\n'.format(
                contenttype or mimetypes.guess_type(filename)[0] or 'application/octet-stream'))
            yield encoder('Content-Transfer-Encoding: binary\r\n')
            yield encoder('\r\n')
            yield (fd, len(fd))
            yield encoder('\r\n')
        yield encoder('--{}--\r\n'.format(self.boundary)) 

def iter(self, fields, files):
        """
        :param fields: sequence of (name, value) elements for regular form fields
        :param files: sequence of (name, filename, contenttype, filedata) elements for data to be uploaded as files
        :return:
        """
        encoder = codecs.getencoder('utf-8')
        for (key, value) in fields:
            key = self.u(key)
            yield encoder('--{}\r\n'.format(self.boundary))
            yield encoder(self.u('Content-Disposition: form-data; name="{}"\r\n').format(key))
            yield encoder('\r\n')
            if isinstance(value, (int, float)):
                value = str(value)
            yield encoder(self.u(value))
            yield encoder('\r\n')
        for (key, filename, contenttype, fd) in files:
            key = self.u(key)
            filename = self.u(filename)
            yield encoder('--{}\r\n'.format(self.boundary))
            yield encoder(self.u('Content-Disposition: form-data; name="{}"; filename="{}"\r\n').format(key, filename))
            yield encoder('Content-Type: {}\r\n'.format(
                contenttype or mimetypes.guess_type(filename)[0] or 'application/octet-stream'))
            yield encoder('Content-Transfer-Encoding: binary\r\n')
            yield encoder('\r\n')
            yield (fd, len(fd))
            yield encoder('\r\n')
        yield encoder('--{}--\r\n'.format(self.boundary)) 

def __init__(self, stream, fieldnames, encoding='utf-8', **kwds):
    """Initialzer.

    Args:
      stream: Stream to write to.
      fieldnames: Fieldnames to pass to the DictWriter.
      encoding: Desired encoding.
      kwds: Additional arguments to pass to the DictWriter.
    """

    writer = codecs.getwriter(encoding)



    if (writer is encodings.utf_8.StreamWriter or
        writer is encodings.ascii.StreamWriter or
        writer is encodings.latin_1.StreamWriter or
        writer is encodings.cp1252.StreamWriter):
      self.no_recoding = True
      self.encoder = codecs.getencoder(encoding)
      self.writer = csv.DictWriter(stream, fieldnames, **kwds)
    else:
      self.no_recoding = False
      self.encoder = codecs.getencoder('utf-8')
      self.queue = cStringIO.StringIO()
      self.writer = csv.DictWriter(self.queue, fieldnames, **kwds)
      self.stream = writer(stream) 

def test_getencoder(self):
        self.assertRaises(TypeError, codecs.getencoder)
        self.assertRaises(LookupError, codecs.getencoder, "__spam__") 

def test_encode_length(self):
        with support.check_warnings(('unicode_internal codec has been '
                                     'deprecated', DeprecationWarning)):
            # Issue 3739
            encoder = codecs.getencoder("unicode_internal")
            self.assertEqual(encoder("a")[1], 1)
            self.assertEqual(encoder("\xe9\u0142")[1], 2)

            self.assertEqual(codecs.escape_encode(br'\x00')[1], 4)

# From http://www.gnu.org/software/libidn/draft-josefsson-idn-test-vectors.html 

def test_bad_encode_args(self):
        for encoding in all_unicode_encodings:
            encoder = codecs.getencoder(encoding)
            with support.check_warnings():
                # unicode-internal has been deprecated
                self.assertRaises(TypeError, encoder) 

def quote_value(self, value):
        # The backend "mostly works" without this function and there are use
        # cases for compiling Python without the sqlite3 libraries (e.g.
        # security hardening).
        try:
            import sqlite3
            value = sqlite3.adapt(value)
        except ImportError:
            pass
        except sqlite3.ProgrammingError:
            pass
        # Manual emulation of SQLite parameter quoting
        if isinstance(value, type(True)):
            return str(int(value))
        elif isinstance(value, (Decimal, float)):
            return str(value)
        elif isinstance(value, six.integer_types):
            return str(value)
        elif isinstance(value, six.string_types):
            return "'%s'" % six.text_type(value).replace("\'", "\'\'")
        elif value is None:
            return "NULL"
        elif isinstance(value, (bytes, bytearray, six.memoryview)):
            # Bytes are only allowed for BLOB fields, encoded as string
            # literals containing hexadecimal data and preceded by a single "X"
            # character:
            # value = b'\x01\x02' => value_hex = b'0102' => return X'0102'
            value = bytes(value)
            hex_encoder = codecs.getencoder('hex_codec')
            value_hex, _length = hex_encoder(value)
            # Use 'ascii' encoding for b'01' => '01', no need to use force_text here.
            return "X'%s'" % value_hex.decode('ascii')
        else:
            raise ValueError("Cannot quote parameter value %r of type %s" % (value, type(value))) 

def encoder(self, val):
        _ = codecs.getencoder(val)
        self._encoder = val 

def quote_value(self, value):
        # The backend "mostly works" without this function and there are use
        # cases for compiling Python without the sqlite3 libraries (e.g.
        # security hardening).
        import sqlite3
        try:
            value = sqlite3.adapt(value)
        except sqlite3.ProgrammingError:
            pass
        # Manual emulation of SQLite parameter quoting
        if isinstance(value, type(True)):
            return str(int(value))
        elif isinstance(value, (Decimal, float)):
            return str(value)
        elif isinstance(value, six.integer_types):
            return str(value)
        elif isinstance(value, six.string_types):
            return "'%s'" % six.text_type(value).replace("\'", "\'\'")
        elif value is None:
            return "NULL"
        elif isinstance(value, (bytes, bytearray, six.memoryview)):
            # Bytes are only allowed for BLOB fields, encoded as string
            # literals containing hexadecimal data and preceded by a single "X"
            # character:
            # value = b'\x01\x02' => value_hex = b'0102' => return X'0102'
            value = bytes(value)
            hex_encoder = codecs.getencoder('hex_codec')
            value_hex, _length = hex_encoder(value)
            # Use 'ascii' encoding for b'01' => '01', no need to use force_text here.
            return "X'%s'" % value_hex.decode('ascii')
        else:
            raise ValueError("Cannot quote parameter value %r of type %s" % (value, type(value))) 

def bind_processor(self, dialect):
        if self.convert_unicode or dialect.convert_unicode:
            if dialect.supports_unicode_binds and \
                    self.convert_unicode != 'force':
                if self._warn_on_bytestring:
                    def process(value):
                        if isinstance(value, util.binary_type):
                            util.warn_limited(
                                "Unicode type received non-unicode "
                                "bind param value %r.",
                                (util.ellipses_string(value),))
                        return value
                    return process
                else:
                    return None
            else:
                encoder = codecs.getencoder(dialect.encoding)
                warn_on_bytestring = self._warn_on_bytestring

                def process(value):
                    if isinstance(value, util.text_type):
                        return encoder(value, self.unicode_error)[0]
                    elif warn_on_bytestring and value is not None:
                        util.warn_limited(
                            "Unicode type received non-unicode bind "
                            "param value %r.",
                            (util.ellipses_string(value),))
                    return value
            return process
        else:
            return None 

def new_client_id(self, _server):
        client_id = codecs.getencoder('hex')(os.urandom(16))[0].decode("ascii")
        if not hasattr(_server, "next_method"):
            _server.next_method = {}
        if not hasattr(_server, "lifetimes"):
            _server.lifetimes = []

        _server.next_method[client_id] = "Start"
        _server.lifetimes.append((time.time(), client_id))
        return client_id 

def quote_value(self, value):
        # The backend "mostly works" without this function and there are use
        # cases for compiling Python without the sqlite3 libraries (e.g.
        # security hardening).
        try:
            import sqlite3
            value = sqlite3.adapt(value)
        except ImportError:
            pass
        except sqlite3.ProgrammingError:
            pass
        # Manual emulation of SQLite parameter quoting
        if isinstance(value, type(True)):
            return str(int(value))
        elif isinstance(value, (Decimal, float)):
            return str(value)
        elif isinstance(value, six.integer_types):
            return str(value)
        elif isinstance(value, six.string_types):
            return "'%s'" % six.text_type(value).replace("\'", "\'\'")
        elif value is None:
            return "NULL"
        elif isinstance(value, (bytes, bytearray, six.memoryview)):
            # Bytes are only allowed for BLOB fields, encoded as string
            # literals containing hexadecimal data and preceded by a single "X"
            # character:
            # value = b'\x01\x02' => value_hex = b'0102' => return X'0102'
            value = bytes(value)
            hex_encoder = codecs.getencoder('hex_codec')
            value_hex, _length = hex_encoder(value)
            # Use 'ascii' encoding for b'01' => '01', no need to use force_text here.
            return "X'%s'" % value_hex.decode('ascii')
        else:
            raise ValueError("Cannot quote parameter value %r of type %s" % (value, type(value))) 

def __init__(self, cmd):
        self.encoder = getencoder('utf8')
        self.decoder = getincrementaldecoder('utf8')()
        self.popen = Popen(cmd, bufsize=1,
            stderr=subprocess.STDOUT, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
        if POSIX:
            flags = fcntl.fcntl(self.popen.stdout, fcntl.F_GETFL)
            fcntl.fcntl(self.popen.stdout, fcntl.F_SETFL, flags | os.O_NONBLOCK) 

def test_basics(self):
        binput = bytes(range(256))
        for encoding in bytes_transform_encodings:
            with self.subTest(encoding=encoding):
                # generic codecs interface
                (o, size) = codecs.getencoder(encoding)(binput)
                self.assertEqual(size, len(binput))
                (i, size) = codecs.getdecoder(encoding)(o)
                self.assertEqual(size, len(o))
                self.assertEqual(i, binput) 

def test_bad_encode_args(self):
        for encoding in all_unicode_encodings:
            encoder = codecs.getencoder(encoding)
            with support.check_warnings():
                # unicode-internal has been deprecated
                self.assertRaises(TypeError, encoder) 

def test_getencoder(self):
        self.assertRaises(TypeError, codecs.getencoder)
        self.assertRaises(LookupError, codecs.getencoder, "__spam__")