Python codecs 模块，lookup() 实例源码

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def search_function(name):
    name = encodings.normalize_encoding(name) # Rather undocumented...
    if name in _extended_encodings:
        if name not in _cache:
            base_encoding, mapping = _extended_encodings[name]
            assert(name[-4:] == "_ttx")
            # Python 2 didn't have any of the encodings that we are implementing
            # in this file.  Python 3 added aliases for the East Asian ones, mapping
            # them "temporarily" to the same base encoding as us, with a comment
            # suggesting that full implementation will appear some time later.
            # As such, try the Python version of the x_mac_... first, if that is found,
            # use *that* as our base encoding.  This would make our encoding upgrade
            # to the full encoding when and if Python finally implements that.
            # http://bugs.python.org/issue24041
            base_encodings = [name[:-4], base_encoding]
            for base_encoding in base_encodings:
                try:
                    codecs.lookup(base_encoding)
                except LookupError:
                    continue
                _cache[name] = ExtendCodec(name, base_encoding, mapping)
                break
        return _cache[name].info

    return None

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = chr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def get_news(id):
    sys.stdout = codecs.lookup('utf_8')[-1](sys.stdout)
    try:
        news = id_news(id)
    except Exception as e:
        log.exception(e)
    if news is not False:
        if news is not 0:
            try:
                update = news.up_date.decode('utf-8')
                detail = news.detail.decode('utf-8')
                if len(news.link) is not 0:
                    link_ = news.link.decode('utf-8')
                    return u"???:%s\n??:%s\n???:%s" % (update, detail, link_)
                else:
                    return u"???: %s\n??: %s" % (update, detail)
            except Exception as e:
                log.exception(e)
        else:
            return u"?????????????????????"

    else:
        return u"DB????????????????????"

def get_info(id):
    sys.stdout = codecs.lookup('utf_8')[-1](sys.stdout)
    try:
        info = id_info(id)
    except Exception as e:
        log.exception(e)
    if info is not False:
        if info is not 0:
            try:
                subject = info.subject.decode('utf-8')
                teacher = info.teacher.decode('utf-8')
                week = info.week.decode('utf-8')
                period = info.period.decode('utf-8')
                detail = info.detail.decode('utf-8')
                return u"????%s\n????%s\n???%s, %s\n???%s" % (subject, teacher, week, period, detail)
            except Exception as e:
                log.exception(e)
        else:
            return u"?????????????????????????"

    else:
        return u"DB????????????????????"

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = chr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def execute_process_work_item(self):
        try:
            from subprocess import Popen, PIPE, STDOUT
            import codecs
            out_codec = codecs.lookup(sys.stdout.encoding)

            proc = Popen(
                '"%s" %s' % (self.current_code, self.current_args),
                stdout=PIPE,
                stderr=STDOUT,
                bufsize=0,
            )

            for line in proc.stdout:
                print(out_codec.decode(line, 'replace')[0].rstrip('\r\n'))
        except Exception:
            traceback.print_exc()

def execute_process_work_item(self):
        try:
            from subprocess import Popen, PIPE, STDOUT
            import codecs
            out_codec = codecs.lookup(sys.stdout.encoding)

            proc = Popen(
                '"%s" %s' % (self.current_code, self.current_args),
                stdout=PIPE,
                stderr=STDOUT,
                bufsize=0,
            )

            for line in proc.stdout:
                print(out_codec.decode(line, 'replace')[0].rstrip('\r\n'))
        except Exception:
            traceback.print_exc()

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = chr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = chr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def __transform_4suite(self, file, xsl_file, output, params):

        import codecs
        from Ft.Xml import InputSource
        from Ft.Xml.Xslt.Processor import Processor

        document = InputSource.DefaultFactory.fromUri(file)
        stylesheet = InputSource.DefaultFactory.fromUri(xsl_file)
            # there's also a fromString() method

        processor = Processor()
        processor.appendStylesheet(stylesheet)  
        result = processor.run(document, topLevelParams=params)
        (utf8_encode, utf8_decode, utf8_reader, utf8_writer) = codecs.lookup("utf-8")
        write_obj = utf8_writer(open(output, 'w'))
        write_obj.write(result)
        write_obj.close()
        return result, ''

def __output_xml(self, in_file, out_file):
        """

        output the ill-formed xml file

        """

        (utf8_encode, utf8_decode, utf8_reader, utf8_writer) = codecs.lookup("utf-8")
        write_obj = utf8_writer(open(out_file, 'w'))
        write_obj = open(out_file, 'w')
        read_obj = utf8_writer(open(in_file, 'r'))
        read_obj = open(in_file, 'r')
        line = 1
        while line:
            line = read_obj.readline()
            if isinstance(line, type(u"")):
                line = line.encode("utf-8")
            write_obj.write(line)

        read_obj.close()
        write_obj.close()

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = chr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def __init__(self, file, encoding=None):
        """
        @param file A file-like object holding your input. Only the read()
           method must be implemented.

        @param encoding If you set the optional encoding argument, then the
           data will be decoded on the fly.

        """

        if encoding is not None:
            # wrap input in a decoding reader
            reader = codecs.lookup(encoding)[2]
            file = reader(file)

        data = file.read()

        ANTLRStringStream.__init__(self, data)


# I guess the ANTLR prefix exists only to avoid a name clash with some Java
# mumbojumbo. A plain "StringStream" looks better to me, which should be
# the preferred name in Python.

def __init__(self, file, encoding=None):
        """
        @param file A file-like object holding your input. Only the read()
           method must be implemented.

        @param encoding If you set the optional encoding argument, then the
           data will be decoded on the fly.

        """

        if encoding is not None:
            # wrap input in a decoding reader
            reader = codecs.lookup(encoding)[2]
            file = reader(file)

        data = file.read()

        ANTLRStringStream.__init__(self, data)


# I guess the ANTLR prefix exists only to avoid a name clash with some Java
# mumbojumbo. A plain "StringStream" looks better to me, which should be
# the preferred name in Python.

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def __init__(self, file, encoding=None):
        """
        @param file A file-like object holding your input. Only the read()
           method must be implemented.

        @param encoding If you set the optional encoding argument, then the
           data will be decoded on the fly.

        """

        if encoding is not None:
            # wrap input in a decoding reader
            reader = codecs.lookup(encoding)[2]
            file = reader(file)

        data = file.read()

        ANTLRStringStream.__init__(self, data)


# I guess the ANTLR prefix exists only to avoid a name clash with some Java
# mumbojumbo. A plain "StringStream" looks better to me, which should be
# the preferred name in Python.

def __init__(self, file, encoding=None):
        """
        @param file A file-like object holding your input. Only the read()
           method must be implemented.

        @param encoding If you set the optional encoding argument, then the
           data will be decoded on the fly.

        """

        if encoding is not None:
            # wrap input in a decoding reader
            reader = codecs.lookup(encoding)[2]
            file = reader(file)

        data = file.read()

        ANTLRStringStream.__init__(self, data)


# I guess the ANTLR prefix exists only to avoid a name clash with some Java
# mumbojumbo. A plain "StringStream" looks better to me, which should be
# the preferred name in Python.

def _get_encoding(encoding_or_label):
    """
    Accept either an encoding object or label.

    :param encoding: An :class:`Encoding` object or a label string.
    :returns: An :class:`Encoding` object.
    :raises: :exc:`~exceptions.LookupError` for an unknown label.

    """
    if hasattr(encoding_or_label, 'codec_info'):
        return encoding_or_label

    encoding = lookup(encoding_or_label)
    if encoding is None:
        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
    return encoding

def _populate_class_variables():
        lookup = {}
        reverse_lookup = {}
        characters_for_re = []
        for codepoint, name in list(codepoint2name.items()):
            character = unichr(codepoint)
            if codepoint != 34:
                # There's no point in turning the quotation mark into
                # ", unless it happens within an attribute value, which
                # is handled elsewhere.
                characters_for_re.append(character)
                lookup[character] = name
            # But we do want to turn " into the quotation mark.
            reverse_lookup[name] = character
        re_definition = "[%s]" % "".join(characters_for_re)
        return lookup, reverse_lookup, re.compile(re_definition)

def aliasmbcs():
    """On Windows, some default encodings are not provided by Python,
    while they are always available as "mbcs" in each locale. Make
    them usable by aliasing to "mbcs" in such a case."""
    if sys.platform == 'win32':
        import locale, codecs
        enc = locale.getdefaultlocale()[1]
        if enc.startswith('cp'):            # "cp***" ?
            try:
                codecs.lookup(enc)
            except LookupError:
                import encodings
                encodings._cache[enc] = encodings._unknown
                encodings.aliases.aliases[enc] = 'mbcs'

def lookup(label):
    """
    Look for an encoding by its label.
    This is the spec’s `get an encoding
    <http://encoding.spec.whatwg.org/#concept-encoding-get>`_ algorithm.
    Supported labels are listed there.

    :param label: A string.
    :returns:
        An :class:`Encoding` object, or :obj:`None` for an unknown label.

    """
    # Only strip ASCII whitespace: U+0009, U+000A, U+000C, U+000D, and U+0020.
    label = ascii_lower(label.strip('\t\n\f\r '))
    name = LABELS.get(label)
    if name is None:
        return None
    encoding = CACHE.get(name)
    if encoding is None:
        if name == 'x-user-defined':
            from .x_user_defined import codec_info
        else:
            python_name = PYTHON_NAMES.get(name, name)
            # Any python_name value that gets to here should be valid.
            codec_info = codecs.lookup(python_name)
        encoding = Encoding(name, codec_info)
        CACHE[name] = encoding
    return encoding

def aliasmbcs():
    """On Windows, some default encodings are not provided by Python,
    while they are always available as "mbcs" in each locale. Make
    them usable by aliasing to "mbcs" in such a case."""
    if sys.platform == 'win32':
        import locale, codecs
        enc = locale.getdefaultlocale()[1]
        if enc.startswith('cp'):            # "cp***" ?
            try:
                codecs.lookup(enc)
            except LookupError:
                import encodings
                encodings._cache[enc] = encodings._unknown
                encodings.aliases.aliases[enc] = 'mbcs'

def lookup(label):
    """
    Look for an encoding by its label.
    This is the spec’s `get an encoding
    <http://encoding.spec.whatwg.org/#concept-encoding-get>`_ algorithm.
    Supported labels are listed there.

    :param label: A string.
    :returns:
        An :class:`Encoding` object, or :obj:`None` for an unknown label.

    """
    # Only strip ASCII whitespace: U+0009, U+000A, U+000C, U+000D, and U+0020.
    label = ascii_lower(label.strip('\t\n\f\r '))
    name = LABELS.get(label)
    if name is None:
        return None
    encoding = CACHE.get(name)
    if encoding is None:
        if name == 'x-user-defined':
            from .x_user_defined import codec_info
        else:
            python_name = PYTHON_NAMES.get(name, name)
            # Any python_name value that gets to here should be valid.
            codec_info = codecs.lookup(python_name)
        encoding = Encoding(name, codec_info)
        CACHE[name] = encoding
    return encoding

def aliasmbcs():
    """On Windows, some default encodings are not provided by Python,
    while they are always available as "mbcs" in each locale. Make
    them usable by aliasing to "mbcs" in such a case."""
    if sys.platform == 'win32':
        import locale, codecs
        enc = locale.getdefaultlocale()[1]
        if enc.startswith('cp'):            # "cp***" ?
            try:
                codecs.lookup(enc)
            except LookupError:
                import encodings
                encodings._cache[enc] = encodings._unknown
                encodings.aliases.aliases[enc] = 'mbcs'

def __init__(self, input_charset=DEFAULT_CHARSET):
        # RFC 2046, $4.1.2 says charsets are not case sensitive.  We coerce to
        # unicode because its .lower() is locale insensitive.  If the argument
        # is already a unicode, we leave it at that, but ensure that the
        # charset is ASCII, as the standard (RFC XXX) requires.
        try:
            if isinstance(input_charset, unicode):
                input_charset.encode('ascii')
            else:
                input_charset = unicode(input_charset, 'ascii')
        except UnicodeError:
            raise errors.CharsetError(input_charset)
        input_charset = input_charset.lower().encode('ascii')
        # Set the input charset after filtering through the aliases and/or codecs
        if not (input_charset in ALIASES or input_charset in CHARSETS):
            try:
                input_charset = codecs.lookup(input_charset).name
            except LookupError:
                pass
        self.input_charset = ALIASES.get(input_charset, input_charset)
        # We can try to guess which encoding and conversion to use by the
        # charset_map dictionary.  Try that first, but let the user override
        # it.
        henc, benc, conv = CHARSETS.get(self.input_charset,
                                        (SHORTEST, BASE64, None))
        if not conv:
            conv = self.input_charset
        # Set the attributes, allowing the arguments to override the default.
        self.header_encoding = henc
        self.body_encoding = benc
        self.output_charset = ALIASES.get(conv, conv)
        # Now set the codecs.  If one isn't defined for input_charset,
        # guess and try a Unicode codec with the same name as input_codec.
        self.input_codec = CODEC_MAP.get(self.input_charset,
                                         self.input_charset)
        self.output_codec = CODEC_MAP.get(self.output_charset,
                                          self.output_charset)

def toprettyxml(self, indent="\t", newl="\n", encoding = None):
        # indent = the indentation string to prepend, per level
        # newl = the newline string to append
        writer = _get_StringIO()
        if encoding is not None:
            import codecs
            # Can't use codecs.getwriter to preserve 2.0 compatibility
            writer = codecs.lookup(encoding)[3](writer)
        if self.nodeType == Node.DOCUMENT_NODE:
            # Can pass encoding only to document, to put it into XML header
            self.writexml(writer, "", indent, newl, encoding)
        else:
            self.writexml(writer, "", indent, newl)
        return writer.getvalue()

def codec_search(name):
        if name == 'cp65001':
            return codecs.lookup('utf-8')
        return None

def _codec(self, charset):
        if not charset: return charset
        codec = None
        try:
            codecs.lookup(charset)
            codec = charset
        except (LookupError, ValueError):
            pass
        return codec

def get_eci_assignment_number(encoding):
    """\
    Returns the ECI number for the provided encoding.

    :param str encoding: A encoding name
    :return str: The ECI number.
    """
    try:
        return consts.ECI_ASSIGNMENT_NUM[codecs.lookup(encoding).name]
    except KeyError:
        raise QRCodeError('Unknown ECI assignment number for encoding "{0}".'
                          .format(encoding))

def _codec(self, charset):
        if not charset:
            return charset
        codec = None
        try:
            codecs.lookup(charset)
            codec = charset
        except (LookupError, ValueError):
            pass
        return codec

def _codec(self, charset):
        if not charset:
            return charset
        codec = None
        try:
            codecs.lookup(charset)
            codec = charset
        except (LookupError, ValueError):
            pass
        return codec


    # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.

def __getitem__(self, key):
        """Besides index lookup (getting item n) you can also pass it a string
        to get the quality for the item.  If the item is not in the list, the
        returned quality is ``0``.
        """
        if isinstance(key, string_types):
            return self.quality(key)
        return list.__getitem__(self, key)

def quality(self, key):
        """Returns the quality of the key.

        .. versionadded:: 0.6
           In previous versions you had to use the item-lookup syntax
           (eg: ``obj[key]`` instead of ``obj.quality(key)``)
        """
        for item, quality in self:
            if self._value_matches(key, item):
                return quality
        return 0