Python tornado.util.unicode_type() Examples

def url_unescape(value, encoding='utf-8', plus=True):
        """解码来自于URL 的给定值.

        该参数可以是一个字节或unicode 字符串.

        如果encoding 是None , 该结果将会是一个字节串. 否则, 该结果会是
        指定编码的unicode 字符串.

        如果 ``plus`` 是true (默认值), 加号将被解释为空格(文字加号必须被
        表示为"%2B"). 这是适用于查询字符串和form-encoded 的值, 但不是URL
        的路径组件. 注意该默认设置和Python 的urllib 模块是相反的.

        .. versionadded:: 3.1
           该 ``plus`` 参数
        """
        unquote = (urllib_parse.unquote_plus if plus else urllib_parse.unquote)
        if encoding is None:
            return unquote(utf8(value))
        else:
            return unicode_type(unquote(utf8(value)), encoding) 

def prepare(self):
        self.errors = {}

        self.check_type('status', self.get_status(), int)

        # get_argument is an exception from the general rule of using
        # type str for non-body data mainly for historical reasons.
        self.check_type('argument', self.get_argument('foo'), unicode_type)
        self.check_type('cookie_key', list(self.cookies.keys())[0], str)
        self.check_type('cookie_value', list(self.cookies.values())[0].value, str)

        # Secure cookies return bytes because they can contain arbitrary
        # data, but regular cookies are native strings.
        if list(self.cookies.keys()) != ['asdf']:
            raise Exception("unexpected values for cookie keys: %r" %
                            self.cookies.keys())
        self.check_type('get_secure_cookie', self.get_secure_cookie('asdf'), bytes_type)
        self.check_type('get_cookie', self.get_cookie('asdf'), str)

        self.check_type('xsrf_token', self.xsrf_token, bytes_type)
        self.check_type('xsrf_form_html', self.xsrf_form_html(), str)

        self.check_type('reverse_url', self.reverse_url('typecheck', 'foo'), str)

        self.check_type('request_summary', self._request_summary(), str) 

def get(self, *path_args):
        # Type checks: web.py interfaces convert argument values to
        # unicode strings (by default, but see also decode_argument).
        # In httpserver.py (i.e. self.request.arguments), they're left
        # as bytes.  Keys are always native strings.
        for key in self.request.arguments:
            if type(key) != str:
                raise Exception("incorrect type for key: %r" % type(key))
            for value in self.request.arguments[key]:
                if type(value) != bytes_type:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
            for value in self.get_arguments(key):
                if type(value) != unicode_type:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
        for arg in path_args:
            if type(arg) != unicode_type:
                raise Exception("incorrect type for path arg: %r" % type(arg))
        self.write(dict(path=self.request.path,
                        path_args=path_args,
                        args=recursive_unicode(self.request.arguments))) 

def prepare(self):
        self.errors = {}

        self.check_type('status', self.get_status(), int)

        # get_argument is an exception from the general rule of using
        # type str for non-body data mainly for historical reasons.
        self.check_type('argument', self.get_argument('foo'), unicode_type)
        self.check_type('cookie_key', list(self.cookies.keys())[0], str)
        self.check_type('cookie_value', list(self.cookies.values())[0].value, str)

        # Secure cookies return bytes because they can contain arbitrary
        # data, but regular cookies are native strings.
        if list(self.cookies.keys()) != ['asdf']:
            raise Exception("unexpected values for cookie keys: %r" %
                            self.cookies.keys())
        self.check_type('get_secure_cookie', self.get_secure_cookie('asdf'), bytes)
        self.check_type('get_cookie', self.get_cookie('asdf'), str)

        self.check_type('xsrf_token', self.xsrf_token, bytes)
        self.check_type('xsrf_form_html', self.xsrf_form_html(), str)

        self.check_type('reverse_url', self.reverse_url('typecheck', 'foo'), str)

        self.check_type('request_summary', self._request_summary(), str) 

def get(self, *path_args):
        # Type checks: web.py interfaces convert argument values to
        # unicode strings (by default, but see also decode_argument).
        # In httpserver.py (i.e. self.request.arguments), they're left
        # as bytes.  Keys are always native strings.
        for key in self.request.arguments:
            if type(key) != str:
                raise Exception("incorrect type for key: %r" % type(key))
            for value in self.request.arguments[key]:
                if type(value) != bytes:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
            for value in self.get_arguments(key):
                if type(value) != unicode_type:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
        for arg in path_args:
            if type(arg) != unicode_type:
                raise Exception("incorrect type for path arg: %r" % type(arg))
        self.write(dict(path=self.request.path,
                        path_args=path_args,
                        args=recursive_unicode(self.request.arguments))) 

def url_unescape(value, encoding='utf-8', plus=True):
        """Decodes the given value from a URL.

        The argument may be either a byte or unicode string.

        If encoding is None, the result will be a byte string.  Otherwise,
        the result is a unicode string in the specified encoding.

        If ``plus`` is true (the default), plus signs will be interpreted
        as spaces (literal plus signs must be represented as "%2B").  This
        is appropriate for query strings and form-encoded values but not
        for the path component of a URL.  Note that this default is the
        reverse of Python's urllib module.

        .. versionadded:: 3.1
           The ``plus`` argument
        """
        unquote = (urllib_parse.unquote_plus if plus else urllib_parse.unquote)
        if encoding is None:
            return unquote(utf8(value))
        else:
            return unicode_type(unquote(utf8(value)), encoding) 

def prepare(self):
        self.errors = {}

        self.check_type('status', self.get_status(), int)

        # get_argument is an exception from the general rule of using
        # type str for non-body data mainly for historical reasons.
        self.check_type('argument', self.get_argument('foo'), unicode_type)
        self.check_type('cookie_key', list(self.cookies.keys())[0], str)
        self.check_type('cookie_value', list(self.cookies.values())[0].value, str)

        # Secure cookies return bytes because they can contain arbitrary
        # data, but regular cookies are native strings.
        if list(self.cookies.keys()) != ['asdf']:
            raise Exception("unexpected values for cookie keys: %r" %
                            self.cookies.keys())
        self.check_type('get_secure_cookie', self.get_secure_cookie('asdf'), bytes_type)
        self.check_type('get_cookie', self.get_cookie('asdf'), str)

        self.check_type('xsrf_token', self.xsrf_token, bytes_type)
        self.check_type('xsrf_form_html', self.xsrf_form_html(), str)

        self.check_type('reverse_url', self.reverse_url('typecheck', 'foo'), str)

        self.check_type('request_summary', self._request_summary(), str) 

def get_arguments(self, name, strip=True):
        """Returns a list of the arguments with the given name.

        If the argument is not present, returns an empty list.

        The returned values are always unicode.
        """

        values = []
        for v in self.request.arguments.get(name, []):
            v = self.decode_argument(v, name=name)
            if isinstance(v, unicode_type):
                # Get rid of any weird control chars (unless decoding gave
                # us bytes, in which case leave it alone)
                v = RequestHandler._remove_control_chars_regex.sub(" ", v)
            if strip:
                v = v.strip()
            values.append(v)
        return values 

def url_unescape(value, encoding='utf-8', plus=True):
        """解码来自于URL 的给定值.

        该参数可以是一个字节或unicode 字符串.

        如果encoding 是None , 该结果将会是一个字节串. 否则, 该结果会是
        指定编码的unicode 字符串.

        如果 ``plus`` 是true (默认值), 加号将被解释为空格(文字加号必须被
        表示为"%2B"). 这是适用于查询字符串和form-encoded 的值, 但不是URL
        的路径组件. 注意该默认设置和Python 的urllib 模块是相反的.

        .. versionadded:: 3.1
           该 ``plus`` 参数
        """
        unquote = (urllib_parse.unquote_plus if plus else urllib_parse.unquote)
        if encoding is None:
            return unquote(utf8(value))
        else:
            return unicode_type(unquote(utf8(value)), encoding) 

def url_unescape(value, encoding='utf-8', plus=True):
        """Decodes the given value from a URL.

        The argument may be either a byte or unicode string.

        If encoding is None, the result will be a byte string.  Otherwise,
        the result is a unicode string in the specified encoding.

        If ``plus`` is true (the default), plus signs will be interpreted
        as spaces (literal plus signs must be represented as "%2B").  This
        is appropriate for query strings and form-encoded values but not
        for the path component of a URL.  Note that this default is the
        reverse of Python's urllib module.

        .. versionadded:: 3.1
           The ``plus`` argument
        """
        unquote = (urllib_parse.unquote_plus if plus else urllib_parse.unquote)
        if encoding is None:
            return unquote(utf8(value))
        else:
            return unicode_type(unquote(utf8(value)), encoding) 

def _convert_header_value(self, value):
        if isinstance(value, bytes_type):
            pass
        elif isinstance(value, unicode_type):
            value = value.encode('utf-8')
        elif isinstance(value, numbers.Integral):
            # return immediately since we know the converted value will be safe
            return str(value)
        elif isinstance(value, datetime.datetime):
            return httputil.format_timestamp(value)
        else:
            raise TypeError("Unsupported header value %r" % value)
        # If \n is allowed into the header, it is possible to inject
        # additional headers or split the request. Also cap length to
        # prevent obviously erroneous values.
        if (len(value) > 4000 or
                RequestHandler._INVALID_HEADER_CHAR_RE.search(value)):
            raise ValueError("Unsafe header value %r", value)
        return value 

def url_unescape(value, encoding='utf-8', plus=True):
        """Decodes the given value from a URL.

        The argument may be either a byte or unicode string.

        If encoding is None, the result will be a byte string.  Otherwise,
        the result is a unicode string in the specified encoding.

        If ``plus`` is true (the default), plus signs will be interpreted
        as spaces (literal plus signs must be represented as "%2B").  This
        is appropriate for query strings and form-encoded values but not
        for the path component of a URL.  Note that this default is the
        reverse of Python's urllib module.

        .. versionadded:: 3.1
           The ``plus`` argument
        """
        unquote = (urllib_parse.unquote_plus if plus else urllib_parse.unquote)
        if encoding is None:
            return unquote(utf8(value))
        else:
            return unicode_type(unquote(utf8(value)), encoding) 

def prepare(self):
        self.errors = {}

        self.check_type('status', self.get_status(), int)

        # get_argument is an exception from the general rule of using
        # type str for non-body data mainly for historical reasons.
        self.check_type('argument', self.get_argument('foo'), unicode_type)
        self.check_type('cookie_key', list(self.cookies.keys())[0], str)
        self.check_type('cookie_value', list(self.cookies.values())[0].value, str)

        # Secure cookies return bytes because they can contain arbitrary
        # data, but regular cookies are native strings.
        if list(self.cookies.keys()) != ['asdf']:
            raise Exception("unexpected values for cookie keys: %r" %
                            self.cookies.keys())
        self.check_type('get_secure_cookie', self.get_secure_cookie('asdf'), bytes)
        self.check_type('get_cookie', self.get_cookie('asdf'), str)

        self.check_type('xsrf_token', self.xsrf_token, bytes)
        self.check_type('xsrf_form_html', self.xsrf_form_html(), str)

        self.check_type('reverse_url', self.reverse_url('typecheck', 'foo'), str)

        self.check_type('request_summary', self._request_summary(), str) 

def get(self, *path_args):
        # Type checks: web.py interfaces convert argument values to
        # unicode strings (by default, but see also decode_argument).
        # In httpserver.py (i.e. self.request.arguments), they're left
        # as bytes.  Keys are always native strings.
        for key in self.request.arguments:
            if type(key) != str:
                raise Exception("incorrect type for key: %r" % type(key))
            for value in self.request.arguments[key]:
                if type(value) != bytes:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
            for value in self.get_arguments(key):
                if type(value) != unicode_type:
                    raise Exception("incorrect type for value: %r" %
                                    type(value))
        for arg in path_args:
            if type(arg) != unicode_type:
                raise Exception("incorrect type for path arg: %r" % type(arg))
        self.write(dict(path=self.request.path,
                        path_args=path_args,
                        args=recursive_unicode(self.request.arguments))) 

def get_arguments(self, name, strip=True):
        """Returns a list of the arguments with the given name.

        If the argument is not present, returns an empty list.

        The returned values are always unicode.
        """

        values = []
        for v in self.request.arguments.get(name, []):
            v = self.decode_argument(v, name=name)
            if isinstance(v, unicode_type):
                # Get rid of any weird control chars (unless decoding gave
                # us bytes, in which case leave it alone)
                v = RequestHandler._remove_control_chars_regex.sub(" ", v)
            if strip:
                v = v.strip()
            values.append(v)
        return values 

def post(self, path_component):
        self.check_type('path_component', path_component, unicode_type)
        self.write(self.errors) 

def utf8(value):
    """Converts a string argument to a byte string.

    If the argument is already a byte string or None, it is returned unchanged.
    Otherwise it must be a unicode string and is encoded as utf8.
    """
    if isinstance(value, _UTF8_TYPES):
        return value
    assert isinstance(value, unicode_type), \
        "Expected bytes, unicode, or None; got %r" % type(value)
    return value.encode("utf-8") 

def test_non_ascii_name(self):
        name = tornado.locale.LOCALE_NAMES['es_LA']['name']
        self.assertTrue(isinstance(name, unicode_type))
        self.assertEqual(name, u('Espa\u00f1ol'))
        self.assertEqual(utf8(name), b'Espa\xc3\xb1ol') 

def authenticate_redirect(self, callback_uri=None, cancel_uri=None,
                              extended_permissions=None, callback=None):
        """Authenticates/installs this app for the current user.

        .. versionchanged:: 3.1
           Returns a `.Future` and takes an optional callback.  These are
           not strictly necessary as this method is synchronous,
           but they are supplied for consistency with
           `OAuthMixin.authorize_redirect`.
        """
        self.require_setting("facebook_api_key", "Facebook Connect")
        callback_uri = callback_uri or self.request.uri
        args = {
            "api_key": self.settings["facebook_api_key"],
            "v": "1.0",
            "fbconnect": "true",
            "display": "page",
            "next": urlparse.urljoin(self.request.full_url(), callback_uri),
            "return_session": "true",
        }
        if cancel_uri:
            args["cancel_url"] = urlparse.urljoin(
                self.request.full_url(), cancel_uri)
        if extended_permissions:
            if isinstance(extended_permissions, (unicode_type, bytes_type)):
                extended_permissions = [extended_permissions]
            args["req_perms"] = ",".join(extended_permissions)
        self.redirect("http://www.facebook.com/login.php?" +
                      urllib_parse.urlencode(args))
        callback() 

def get(self, arg):
        def describe(s):
            if type(s) == bytes_type:
                return ["bytes", native_str(binascii.b2a_hex(s))]
            elif type(s) == unicode_type:
                return ["unicode", s]
            raise Exception("unknown type")
        self.write({'path': describe(arg),
                    'query': describe(self.get_argument("foo")),
                    }) 

def test_escape_return_types(self):
        # On python2 the escape methods should generally return the same
        # type as their argument
        self.assertEqual(type(xhtml_escape("foo")), str)
        self.assertEqual(type(xhtml_escape(u("foo"))), unicode_type) 

def test_non_ascii_name(self):
        name = tornado.locale.LOCALE_NAMES['es_LA']['name']
        self.assertTrue(isinstance(name, unicode_type))
        self.assertEqual(name, u('Espa\u00f1ol'))
        self.assertEqual(utf8(name), b'Espa\xc3\xb1ol') 

def get(self, arg):
        def describe(s):
            if type(s) == bytes_type:
                return ["bytes", native_str(binascii.b2a_hex(s))]
            elif type(s) == unicode_type:
                return ["unicode", s]
            raise Exception("unknown type")
        self.write({'path': describe(arg),
                    'query': describe(self.get_argument("foo")),
                    }) 

def get(self, path_component):
        # path_component uses type unicode instead of str for consistency
        # with get_argument()
        self.check_type('path_component', path_component, unicode_type)
        self.write(self.errors) 

def test_unicode_literal_expression(self):
        # Unicode literals should be usable in templates.  Note that this
        # test simulates unicode characters appearing directly in the
        # template file (with utf8 encoding), i.e. \u escapes would not
        # be used in the template file itself.
        if str is unicode_type:
            # python 3 needs a different version of this test since
            # 2to3 doesn't run on template internals
            template = Template(utf8(u('{{ "\u00e9" }}')))
        else:
            template = Template(utf8(u('{{ u"\u00e9" }}')))
        self.assertEqual(template.generate(), utf8(u("\u00e9"))) 

def generate(self, **kwargs):
        """Generate this template with the given arguments."""
        namespace = {
            "escape": escape.xhtml_escape,
            "xhtml_escape": escape.xhtml_escape,
            "url_escape": escape.url_escape,
            "json_encode": escape.json_encode,
            "squeeze": escape.squeeze,
            "linkify": escape.linkify,
            "datetime": datetime,
            "_tt_utf8": escape.utf8,  # for internal use
            "_tt_string_types": (unicode_type, bytes_type),
            # __name__ and __loader__ allow the traceback mechanism to find
            # the generated source code.
            "__name__": self.name.replace('.', '_'),
            "__loader__": ObjectDict(get_source=lambda name: self.code),
        }
        namespace.update(self.namespace)
        namespace.update(kwargs)
        exec_in(self.compiled, namespace)
        execute = namespace["_tt_execute"]
        # Clear the traceback module's cache of source data now that
        # we've generated a new template (mainly for this module's
        # unittests, where different tests reuse the same name).
        linecache.clearcache()
        return execute() 

def __init__(self, color=True, *args, **kwargs):
        logging.Formatter.__init__(self, *args, **kwargs)
        self._color = color and _stderr_supports_color()
        if self._color:
            # The curses module has some str/bytes confusion in
            # python3.  Until version 3.2.3, most methods return
            # bytes, but only accept strings.  In addition, we want to
            # output these strings with the logging module, which
            # works with unicode strings.  The explicit calls to
            # unicode() below are harmless in python2 but will do the
            # right conversion in python 3.
            fg_color = (curses.tigetstr("setaf") or
                        curses.tigetstr("setf") or "")
            if (3, 0) < sys.version_info < (3, 2, 3):
                fg_color = unicode_type(fg_color, "ascii")
            self._colors = {
                logging.DEBUG: unicode_type(curses.tparm(fg_color, 4),  # Blue
                                            "ascii"),
                logging.INFO: unicode_type(curses.tparm(fg_color, 2),  # Green
                                           "ascii"),
                logging.WARNING: unicode_type(curses.tparm(fg_color, 3),  # Yellow
                                              "ascii"),
                logging.ERROR: unicode_type(curses.tparm(fg_color, 1),  # Red
                                            "ascii"),
            }
            self._normal = unicode_type(curses.tigetstr("sgr0"), "ascii") 

def _oauth_escape(val):
    if isinstance(val, unicode_type):
        val = val.encode("utf-8")
    return urllib_parse.quote(val, safe="~") 

def _signature(self, args):
        parts = ["%s=%s" % (n, args[n]) for n in sorted(args.keys())]
        body = "".join(parts) + self.settings["facebook_secret"]
        if isinstance(body, unicode_type):
            body = body.encode("utf-8")
        return hashlib.md5(body).hexdigest() 

def reverse(self, *args):
        if self._path is None:
            raise ValueError("Cannot reverse url regex " + self.regex.pattern)
        assert len(args) == self._group_count, "required number of arguments " \
                                               "not found"
        if not len(args):
            return self._path
        converted_args = []
        for a in args:
            if not isinstance(a, (unicode_type, bytes)):
                a = str(a)
            converted_args.append(url_escape(utf8(a), plus=False))
        return self._path % tuple(converted_args)