Python _internal._decode_unicode函数代码示例

def uri_to_iri(uri, charset = 'utf-8', errors = 'ignore'):
    uri = url_fix(str(uri), charset)
    scheme, auth, hostname, port, path, query, fragment = _uri_split(uri)
    scheme = _decode_unicode(scheme, 'ascii', errors)
    try:
        hostname = hostname.decode('idna')
    except UnicodeError:
        if errors not in ('ignore', 'replace'):
            raise
        hostname = hostname.decode('ascii', errors)

    if auth:
        if ':' in auth:
            auth, password = auth.split(':', 1)
        else:
            password = None
        auth = _decode_unicode(_unquote(auth), charset, errors)
        if password:
            auth += u':' + _decode_unicode(_unquote(password), charset, errors)
        hostname = auth + u'@' + hostname
    if port:
        hostname += u':' + port.decode(charset, errors)
    path = _decode_unicode(_unquote(path, '/;?'), charset, errors)
    query = _decode_unicode(_unquote(query, ';/?:@&=+,$'), charset, errors)
    return urlparse.urlunsplit([scheme,
     hostname,
     path,
     query,
     fragment])

def uri_to_iri(uri, charset='utf-8', errors='replace'):
    r"""Converts a URI in a given charset to a IRI.

    Examples for URI versus IRI

    >>> uri_to_iri('http://xn--n3h.net/')
    u'http://\u2603.net/'
    >>> uri_to_iri('http://%C3%BCser:p%C3%[email protected]/p%C3%A5th')
    u'http://\xfcser:p\[email protected]\u2603.net/p\xe5th'

    Query strings are left unchanged:

    >>> uri_to_iri('/?foo=24&x=%26%2f')
    u'/?foo=24&x=%26%2f'

    .. versionadded:: 0.6

    :param uri: the URI to convert
    :param charset: the charset of the URI
    :param errors: the error handling on decode
    """
    uri = url_fix(str(uri), charset)
    scheme, auth, hostname, port, path, query, fragment = _uri_split(uri)

    scheme = _decode_unicode(scheme, 'ascii', errors)

    try:
        hostname = hostname.decode('idna')
    except UnicodeError:
        # dammit, that codec raised an error.  Because it does not support
        # any error handling we have to fake it.... badly
        if errors not in ('ignore', 'replace'):
            raise
        hostname = hostname.decode('ascii', errors)

    if ':' in hostname:
        hostname = '[' + hostname + ']'

    if auth:
        if ':' in auth:
            auth, password = auth.split(':', 1)
        else:
            password = None
        auth = _decode_unicode(_unquote(auth), charset, errors)
        if password:
            auth += u':' + _decode_unicode(_unquote(password),
                                           charset, errors)
        hostname = auth + u'@' + hostname
    if port:
        # port should be numeric, but you never know...
        hostname += u':' + port.decode(charset, errors)

    path = _decode_unicode(_unquote(path, '/;?'), charset, errors)
    query = _decode_unicode(_unquote(query, ';/?:@&=+,$'),
                            charset, errors)

    return urlparse.urlunsplit([scheme, hostname, path, query, fragment])

    def from_file(cls, file, charset='utf-8', errors='strict',
                  unicode_mode=True, encoding=None):
        """Load a template from a file.

        .. versionchanged:: 0.5
            The encoding parameter was renamed to charset.

        :param file: a filename or file object to load the template from.
        :param charset: the charset of the template to load.
        :param errors: the error behavior of the charset decoding.
        :param unicode_mode: set to `False` to disable unicode mode.
        :return: a template
        """
        if encoding is not None:
            from warnings import warn
            warn(DeprecationWarning('the encoding parameter is deprecated. '
                                    'use charset instead.'), stacklevel=2)
            charset = encoding
        close = False
        if isinstance(file, basestring):
            f = open(file, 'r')
            close = True
        try:
            data = _decode_unicode(f.read(), charset, errors)
        finally:
            if close:
                f.close()
        return cls(data, getattr(f, 'name', '<template>'), charset,
                   errors, unicode_mode)

def parse_cookie(header, charset="utf-8", errors="replace", cls=None):
    """Parse a cookie.  Either from a string or WSGI environ.

    Per default encoding errors are ignored.  If you want a different behavior
    you can set `errors` to ``'replace'`` or ``'strict'``.  In strict mode a
    :exc:`HTTPUnicodeError` is raised.

    .. versionchanged:: 0.5
       This function now returns a :class:`TypeConversionDict` instead of a
       regular dict.  The `cls` parameter was added.

    :param header: the header to be used to parse the cookie.  Alternatively
                   this can be a WSGI environment.
    :param charset: the charset for the cookie values.
    :param errors: the error behavior for the charset decoding.
    :param cls: an optional dict class to use.  If this is not specified
                       or `None` the default :class:`TypeConversionDict` is
                       used.
    """
    if isinstance(header, dict):
        header = header.get("HTTP_COOKIE", "")
    if cls is None:
        cls = TypeConversionDict
    cookie = _ExtendedCookie()
    cookie.load(header)
    result = {}

    # decode to unicode and skip broken items.  Our extended morsel
    # and extended cookie will catch CookieErrors and convert them to
    # `None` items which we have to skip here.
    for key, value in cookie.iteritems():
        if value.value is not None:
            result[key] = _decode_unicode(unquote_header_value(value.value), charset, errors)

    return cls(result)

 def path(self):
     """Requested path as unicode.  This works a bit like the regular path
     info in the WSGI environment but will always include a leading slash,
     even if the URL root is accessed.
     """
     path = '/' + (self.environ.get('PATH_INFO') or '').lstrip('/')
     return _decode_unicode(path, self.charset, self.encoding_errors)

    def from_file(cls, file, charset='utf-8', errors='strict',
                  unicode_mode=True):
        """Load a template from a file.

        .. versionchanged:: 0.5
            The encoding parameter was renamed to charset.

        :param file: a filename or file object to load the template from.
        :param charset: the charset of the template to load.
        :param errors: the error behavior of the charset decoding.
        :param unicode_mode: set to `False` to disable unicode mode.
        :return: a template
        """
        close = False
        f = file
        if isinstance(file, basestring):
            f = open(file, 'r')
            close = True
        try:
            data = _decode_unicode(f.read(), charset, errors)
        finally:
            if close:
                f.close()
        return cls(data, getattr(f, 'name', '<template>'), charset,
                   errors, unicode_mode)

 def __init__(self, source, filename = '<template>', charset = 'utf-8', errors = 'strict', unicode_mode = True):
     if isinstance(source, str):
         source = _decode_unicode(source, charset, errors)
     if isinstance(filename, unicode):
         filename = filename.encode('utf-8')
     node = Parser(tokenize(u'\n'.join(source.splitlines()), filename), filename).parse()
     self.code = TemplateCodeGenerator(node, filename).getCode()
     self.filename = filename
     self.charset = charset
     self.errors = errors
     self.unicode_mode = unicode_mode

 def start_file_streaming(self, filename, headers, total_content_length):
     filename = _decode_unicode(filename, self.charset, self.errors)
     filename = self._fix_ie_filename(filename)
     content_type = headers.get('content-type')
     try:
         content_length = int(headers['content-length'])
     except (KeyError, ValueError):
         content_length = 0
     container = self.stream_factory(total_content_length, content_type,
                                     filename, content_length)
     return filename, container

 def __init__(self, source, filename="<template>", charset="utf-8", errors="strict", unicode_mode=True):
     if isinstance(source, str):
         source = _decode_unicode(source, charset, errors)
     if isinstance(filename, unicode):
         filename = filename.encode("utf-8")
     node = Parser(tokenize(u"\n".join(source.splitlines()), filename), filename).parse()
     self.code = TemplateCodeGenerator(node, filename).getCode()
     self.filename = filename
     self.charset = charset
     self.errors = errors
     self.unicode_mode = unicode_mode

    def from_file(cls, file, charset = 'utf-8', errors = 'strict', unicode_mode = True):
        close = False
        if isinstance(file, basestring):
            f = open(file, 'r')
            close = True
        try:
            data = _decode_unicode(f.read(), charset, errors)
        finally:
            if close:
                f.close()

        return cls(data, getattr(f, 'name', '<template>'), charset, errors, unicode_mode)

def parse_cookie(header, charset = 'utf-8', errors = 'ignore', cls = None):
    if isinstance(header, dict):
        header = header.get('HTTP_COOKIE', '')
    if cls is None:
        cls = TypeConversionDict
    cookie = _ExtendedCookie()
    cookie.load(header)
    result = {}
    for key, value in cookie.iteritems():
        if value.value is not None:
            result[key] = _decode_unicode(unquote_header_value(value.value), charset, errors)

    return cls(result)

def url_unquote_plus(s, charset='utf-8', errors='ignore'):
    """URL decode a single string with the given decoding and decode
    a "+" to whitespace.

    Per default encoding errors are ignored.  If you want a different behavior
    you can set `errors` to ``'replace'`` or ``'strict'``.  In strict mode a
    `HTTPUnicodeError` is raised.

    :param s: the string to unquote.
    :param charset: the charset to be used.
    :param errors: the error handling for the charset decoding.
    """
    return _decode_unicode(_unquote_plus(s), charset, errors)

def url_unquote(s, charset='utf-8', errors='replace'):
    """URL decode a single string with a given decoding.

    Per default encoding errors are ignored.  If you want a different behavior
    you can set `errors` to ``'replace'`` or ``'strict'``.  In strict mode a
    `HTTPUnicodeError` is raised.

    :param s: the string to unquote.
    :param charset: the charset to be used.
    :param errors: the error handling for the charset decoding.
    """
    if isinstance(s, unicode):
        s = s.encode(charset)
    return _decode_unicode(_unquote(s), charset, errors)

def _url_decode_impl(pair_iter, charset, decode_keys, include_empty,
                     errors):
    for pair in pair_iter:
        if not pair:
            continue
        if '=' in pair:
            key, value = pair.split('=', 1)
        else:
            if not include_empty:
                continue
            key = pair
            value = ''
        key = _unquote_plus(key)
        if decode_keys:
            key = _decode_unicode(key, charset, errors)
        yield key, url_unquote_plus(value, charset, errors)

def url_decode(s, charset='utf-8', decode_keys=False, include_empty=True,
               errors='ignore', separator='&', cls=None):
    """Parse a querystring and return it as :class:`MultiDict`.  Per default
    only values are decoded into unicode strings.  If `decode_keys` is set to
    `True` the same will happen for keys.

    Per default a missing value for a key will default to an empty key.  If
    you don't want that behavior you can set `include_empty` to `False`.

    Per default encoding errors are ignored.  If you want a different behavior
    you can set `errors` to ``'replace'`` or ``'strict'``.  In strict mode a
    `HTTPUnicodeError` is raised.

    .. versionchanged:: 0.5
       In previous versions ";" and "&" could be used for url decoding.
       This changed in 0.5 where only "&" is supported.  If you want to
       use ";" instead a different `separator` can be provided.

       The `cls` parameter was added.

    :param s: a string with the query string to decode.
    :param charset: the charset of the query string.
    :param decode_keys: set to `True` if you want the keys to be decoded
                        as well.
    :param include_empty: Set to `False` if you don't want empty values to
                          appear in the dict.
    :param errors: the decoding error behavior.
    :param separator: the pair separator to be used, defaults to ``&``
    :param cls: an optional dict class to use.  If this is not specified
                       or `None` the default :class:`MultiDict` is used.
    """
    if cls is None:
        cls = MultiDict
    result = []
    for pair in str(s).split(separator):
        if not pair:
            continue
        if '=' in pair:
            key, value = pair.split('=', 1)
        else:
            key = pair
            value = ''
        key = _unquote_plus(key)
        if decode_keys:
            key = _decode_unicode(key, charset, errors)
        result.append((key, url_unquote_plus(value, charset, errors)))
    return cls(result)