<foo>
' """ _entity_re = re.compile(r"&([^;]+);") _entities = name2codepoint.copy() _entities["apos"] = 39 _empty_elements = { "area", "base", "basefont", "br", "col", "command", "embed", "frame", "hr", "img", "input", "keygen", "isindex", "link", "meta", "param", "source", "wbr", } _boolean_attributes = { "selected", "checked", "compact", "declare", "defer", "disabled", "ismap", "multiple", "nohref", "noresize", "noshade", "nowrap", } _plaintext_elements = {"textarea"} _c_like_cdata = {"script", "style"} def __init__(self, dialect): self._dialect = dialect def __call__(self, s): return escape(s) def __getattr__(self, tag): if tag[:2] == "__": raise AttributeError(tag) def proxy(*children, **arguments): buffer = "<" + tag for key, value in iteritems(arguments): if value is None: continue if key[-1] == "_": key = key[:-1] if key in self._boolean_attributes: if not value: continue if self._dialect == "xhtml": value = '="' + key + '"' else: value = "" else: value = '="' + escape(value) + '"' buffer += " " + key + value if not children and tag in self._empty_elements: if self._dialect == "xhtml": buffer += " />" else: buffer += ">" return buffer buffer += ">" children_as_string = "".join( [text_type(x) for x in children if x is not None] ) if children_as_string: if tag in self._plaintext_elements: children_as_string = escape(children_as_string) elif tag in self._c_like_cdata and self._dialect == "xhtml": children_as_string = ( "/**/" ) buffer += children_as_string + "" return buffer return proxy def __repr__(self): return "<%s for %r>" % (self.__class__.__name__, self._dialect) html = HTMLBuilder("html") xhtml = HTMLBuilder("xhtml") # https://cgit.freedesktop.org/xdg/shared-mime-info/tree/freedesktop.org.xml.in # https://www.iana.org/assignments/media-types/media-types.xhtml # Types listed in the XDG mime info that have a charset in the IANA registration. _charset_mimetypes = { "application/ecmascript", "application/javascript", "application/sql", "application/xml", "application/xml-dtd", "application/xml-external-parsed-entity", } def get_content_type(mimetype, charset): """Returns the full content type string with charset for a mimetype. If the mimetype represents text, the charset parameter will be appended, otherwise the mimetype is returned unchanged. :param mimetype: The mimetype to be used as content type. :param charset: The charset to be appended for text mimetypes. :return: The content type. .. verionchanged:: 0.15 Any type that ends with ``+xml`` gets a charset, not just those that start with ``application/``. Known text types such as ``application/javascript`` are also given charsets. """ if ( mimetype.startswith("text/") or mimetype in _charset_mimetypes or mimetype.endswith("+xml") ): mimetype += "; charset=" + charset return mimetype def detect_utf_encoding(data): """Detect which UTF encoding was used to encode the given bytes. The latest JSON standard (:rfc:`8259`) suggests that only UTF-8 is accepted. Older documents allowed 8, 16, or 32. 16 and 32 can be big or little endian. Some editors or libraries may prepend a BOM. :internal: :param data: Bytes in unknown UTF encoding. :return: UTF encoding name .. versionadded:: 0.15 """ head = data[:4] if head[:3] == codecs.BOM_UTF8: return "utf-8-sig" if b"\x00" not in head: return "utf-8" if head in (codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE): return "utf-32" if head[:2] in (codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE): return "utf-16" if len(head) == 4: if head[:3] == b"\x00\x00\x00": return "utf-32-be" if head[::2] == b"\x00\x00": return "utf-16-be" if head[1:] == b"\x00\x00\x00": return "utf-32-le" if head[1::2] == b"\x00\x00": return "utf-16-le" if len(head) == 2: return "utf-16-be" if head.startswith(b"\x00") else "utf-16-le" return "utf-8" def format_string(string, context): """String-template format a string: >>> format_string('$foo and ${foo}s', dict(foo=42)) '42 and 42s' This does not do any attribute lookup etc. For more advanced string formattings have a look at the `werkzeug.template` module. :param string: the format string. :param context: a dict with the variables to insert. """ def lookup_arg(match): x = context[match.group(1) or match.group(2)] if not isinstance(x, string_types): x = type(string)(x) return x return _format_re.sub(lookup_arg, string) def secure_filename(filename): r"""Pass it a filename and it will return a secure version of it. This filename can then safely be stored on a regular file system and passed to :func:`os.path.join`. The filename returned is an ASCII only string for maximum portability. On windows systems the function also makes sure that the file is not named after one of the special device files. >>> secure_filename("My cool movie.mov") 'My_cool_movie.mov' >>> secure_filename("../../../etc/passwd") 'etc_passwd' >>> secure_filename(u'i contain cool \xfcml\xe4uts.txt') 'i_contain_cool_umlauts.txt' The function might return an empty filename. It's your responsibility to ensure that the filename is unique and that you abort or generate a random filename if the function returned an empty one. .. versionadded:: 0.5 :param filename: the filename to secure """ if isinstance(filename, text_type): from unicodedata import normalize filename = normalize("NFKD", filename).encode("ascii", "ignore") if not PY2: filename = filename.decode("ascii") for sep in os.path.sep, os.path.altsep: if sep: filename = filename.replace(sep, " ") filename = str(_filename_ascii_strip_re.sub("", "_".join(filename.split()))).strip( "._" ) # on nt a couple of special files are present in each folder. We # have to ensure that the target file is not such a filename. In # this case we prepend an underline if ( os.name == "nt" and filename and filename.split(".")[0].upper() in _windows_device_files ): filename = "_" + filename return filename def escape(s, quote=None): """Replace special characters "&", "<", ">" and (") to HTML-safe sequences. There is a special handling for `None` which escapes to an empty string. .. versionchanged:: 0.9 `quote` is now implicitly on. :param s: the string to escape. :param quote: ignored. """ if s is None: return "" elif hasattr(s, "__html__"): return text_type(s.__html__()) elif not isinstance(s, string_types): s = text_type(s) if quote is not None: from warnings import warn warn( "The 'quote' parameter is no longer used as of version 0.9" " and will be removed in version 1.0.", DeprecationWarning, stacklevel=2, ) s = ( s.replace("&", "&") .replace("<", "<") .replace(">", ">") .replace('"', """) ) return s def unescape(s): """The reverse function of `escape`. This unescapes all the HTML entities, not only the XML entities inserted by `escape`. :param s: the string to unescape. """ def handle_match(m): name = m.group(1) if name in HTMLBuilder._entities: return unichr(HTMLBuilder._entities[name]) try: if name[:2] in ("#x", "#X"): return unichr(int(name[2:], 16)) elif name.startswith("#"): return unichr(int(name[1:])) except ValueError: pass return u"" return _entity_re.sub(handle_match, s) def redirect(location, code=302, Response=None): """Returns a response object (a WSGI application) that, if called, redirects the client to the target location. Supported codes are 301, 302, 303, 305, 307, and 308. 300 is not supported because it's not a real redirect and 304 because it's the answer for a request with a request with defined If-Modified-Since headers. .. versionadded:: 0.6 The location can now be a unicode string that is encoded using the :func:`iri_to_uri` function. .. versionadded:: 0.10 The class used for the Response object can now be passed in. :param location: the location the response should redirect to. :param code: the redirect status code. defaults to 302. :param class Response: a Response class to use when instantiating a response. The default is :class:`werkzeug.wrappers.Response` if unspecified. """ if Response is None: from .wrappers import Response display_location = escape(location) if isinstance(location, text_type): # Safe conversion is necessary here as we might redirect # to a broken URI scheme (for instance itms-services). from .urls import iri_to_uri location = iri_to_uri(location, safe_conversion=True) response = Response( '\n' "You should be redirected automatically to target URL: " '%s. If not click the link.' % (escape(location), display_location), code, mimetype="text/html", ) response.headers["Location"] = location return response def append_slash_redirect(environ, code=301): """Redirects to the same URL but with a slash appended. The behavior of this function is undefined if the path ends with a slash already. :param environ: the WSGI environment for the request that triggers the redirect. :param code: the status code for the redirect. """ new_path = environ["PATH_INFO"].strip("/") + "/" query_string = environ.get("QUERY_STRING") if query_string: new_path += "?" + query_string return redirect(new_path, code) def import_string(import_name, silent=False): """Imports an object based on a string. This is useful if you want to use import paths as endpoints or something similar. An import path can be specified either in dotted notation (``xml.sax.saxutils.escape``) or with a colon as object delimiter (``xml.sax.saxutils:escape``). If `silent` is True the return value will be `None` if the import fails. :param import_name: the dotted name for the object to import. :param silent: if set to `True` import errors are ignored and `None` is returned instead. :return: imported object """ # force the import name to automatically convert to strings # __import__ is not able to handle unicode strings in the fromlist # if the module is a package import_name = str(import_name).replace(":", ".") try: try: __import__(import_name) except ImportError: if "." not in import_name: raise else: return sys.modules[import_name] module_name, obj_name = import_name.rsplit(".", 1) module = __import__(module_name, globals(), locals(), [obj_name]) try: return getattr(module, obj_name) except AttributeError as e: raise ImportError(e) except ImportError as e: if not silent: reraise( ImportStringError, ImportStringError(import_name, e), sys.exc_info()[2] ) def find_modules(import_path, include_packages=False, recursive=False): """Finds all the modules below a package. This can be useful to automatically import all views / controllers so that their metaclasses / function decorators have a chance to register themselves on the application. Packages are not returned unless `include_packages` is `True`. This can also recursively list modules but in that case it will import all the packages to get the correct load path of that module. :param import_path: the dotted name for the package to find child modules. :param include_packages: set to `True` if packages should be returned, too. :param recursive: set to `True` if recursion should happen. :return: generator """ module = import_string(import_path) path = getattr(module, "__path__", None) if path is None: raise ValueError("%r is not a package" % import_path) basename = module.__name__ + "." for _importer, modname, ispkg in pkgutil.iter_modules(path): modname = basename + modname if ispkg: if include_packages: yield modname if recursive: for item in find_modules(modname, include_packages, True): yield item else: yield modname def validate_arguments(func, args, kwargs, drop_extra=True): """Checks if the function accepts the arguments and keyword arguments. Returns a new ``(args, kwargs)`` tuple that can safely be passed to the function without causing a `TypeError` because the function signature is incompatible. If `drop_extra` is set to `True` (which is the default) any extra positional or keyword arguments are dropped automatically. The exception raised provides three attributes: `missing` A set of argument names that the function expected but where missing. `extra` A dict of keyword arguments that the function can not handle but where provided. `extra_positional` A list of values that where given by positional argument but the function cannot accept. This can be useful for decorators that forward user submitted data to a view function:: from werkzeug.utils import ArgumentValidationError, validate_arguments def sanitize(f): def proxy(request): data = request.values.to_dict() try: args, kwargs = validate_arguments(f, (request,), data) except ArgumentValidationError: raise BadRequest('The browser failed to transmit all ' 'the data expected.') return f(*args, **kwargs) return proxy :param func: the function the validation is performed against. :param args: a tuple of positional arguments. :param kwargs: a dict of keyword arguments. :param drop_extra: set to `False` if you don't want extra arguments to be silently dropped. :return: tuple in the form ``(args, kwargs)``. """ parser = _parse_signature(func) args, kwargs, missing, extra, extra_positional = parser(args, kwargs)[:5] if missing: raise ArgumentValidationError(tuple(missing)) elif (extra or extra_positional) and not drop_extra: raise ArgumentValidationError(None, extra, extra_positional) return tuple(args), kwargs def bind_arguments(func, args, kwargs): """Bind the arguments provided into a dict. When passed a function, a tuple of arguments and a dict of keyword arguments `bind_arguments` returns a dict of names as the function would see it. This can be useful to implement a cache decorator that uses the function arguments to build the cache key based on the values of the arguments. :param func: the function the arguments should be bound for. :param args: tuple of positional arguments. :param kwargs: a dict of keyword arguments. :return: a :class:`dict` of bound keyword arguments. """ ( args, kwargs, missing, extra, extra_positional, arg_spec, vararg_var, kwarg_var, ) = _parse_signature(func)(args, kwargs) values = {} for (name, _has_default, _default), value in zip(arg_spec, args): values[name] = value if vararg_var is not None: values[vararg_var] = tuple(extra_positional) elif extra_positional: raise TypeError("too many positional arguments") if kwarg_var is not None: multikw = set(extra) & set([x[0] for x in arg_spec]) if multikw: raise TypeError( "got multiple values for keyword argument " + repr(next(iter(multikw))) ) values[kwarg_var] = extra elif extra: raise TypeError("got unexpected keyword argument " + repr(next(iter(extra)))) return values class ArgumentValidationError(ValueError): """Raised if :func:`validate_arguments` fails to validate""" def __init__(self, missing=None, extra=None, extra_positional=None): self.missing = set(missing or ()) self.extra = extra or {} self.extra_positional = extra_positional or [] ValueError.__init__( self, "function arguments invalid. (%d missing, %d additional)" % (len(self.missing), len(self.extra) + len(self.extra_positional)), ) class ImportStringError(ImportError): """Provides information about a failed :func:`import_string` attempt.""" #: String in dotted notation that failed to be imported. import_name = None #: Wrapped exception. exception = None def __init__(self, import_name, exception): self.import_name = import_name self.exception = exception msg = ( "import_string() failed for %r. Possible reasons are:\n\n" "- missing __init__.py in a package;\n" "- package or module path not included in sys.path;\n" "- duplicated package or module name taking precedence in " "sys.path;\n" "- missing module, class, function or variable;\n\n" "Debugged import:\n\n%s\n\n" "Original exception:\n\n%s: %s" ) name = "" tracked = [] for part in import_name.replace(":", ".").split("."): name += (name and ".") + part imported = import_string(name, silent=True) if imported: tracked.append((name, getattr(imported, "__file__", None))) else: track = ["- %r found in %r." % (n, i) for n, i in tracked] track.append("- %r not found." % name) msg = msg % ( import_name, "\n".join(track), exception.__class__.__name__, str(exception), ) break ImportError.__init__(self, msg) def __repr__(self): return "<%s(%r, %r)>" % ( self.__class__.__name__, self.import_name, self.exception, ) from werkzeug import _DeprecatedImportModule _DeprecatedImportModule( __name__, { ".datastructures": [ "CombinedMultiDict", "EnvironHeaders", "Headers", "MultiDict", ], ".http": ["dump_cookie", "parse_cookie"], }, "Werkzeug 1.0", ) del _DeprecatedImportModule