402 lines
13 KiB
Python
402 lines
13 KiB
Python
#
|
|
# Copyright 2009 Facebook
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License"); you may
|
|
# not use this file except in compliance with the License. You may obtain
|
|
# a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
|
|
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
|
|
# License for the specific language governing permissions and limitations
|
|
# under the License.
|
|
|
|
"""Escaping/unescaping methods for HTML, JSON, URLs, and others.
|
|
|
|
Also includes a few other miscellaneous string manipulation functions that
|
|
have crept in over time.
|
|
"""
|
|
|
|
import html.entities
|
|
import json
|
|
import re
|
|
import urllib.parse
|
|
|
|
from tornado.util import unicode_type
|
|
|
|
import typing
|
|
from typing import Union, Any, Optional, Dict, List, Callable
|
|
|
|
|
|
_XHTML_ESCAPE_RE = re.compile("[&<>\"']")
|
|
_XHTML_ESCAPE_DICT = {
|
|
"&": "&",
|
|
"<": "<",
|
|
">": ">",
|
|
'"': """,
|
|
"'": "'",
|
|
}
|
|
|
|
|
|
def xhtml_escape(value: Union[str, bytes]) -> str:
|
|
"""Escapes a string so it is valid within HTML or XML.
|
|
|
|
Escapes the characters ``<``, ``>``, ``"``, ``'``, and ``&``.
|
|
When used in attribute values the escaped strings must be enclosed
|
|
in quotes.
|
|
|
|
.. versionchanged:: 3.2
|
|
|
|
Added the single quote to the list of escaped characters.
|
|
"""
|
|
return _XHTML_ESCAPE_RE.sub(
|
|
lambda match: _XHTML_ESCAPE_DICT[match.group(0)], to_basestring(value)
|
|
)
|
|
|
|
|
|
def xhtml_unescape(value: Union[str, bytes]) -> str:
|
|
"""Un-escapes an XML-escaped string."""
|
|
return re.sub(r"&(#?)(\w+?);", _convert_entity, _unicode(value))
|
|
|
|
|
|
# The fact that json_encode wraps json.dumps is an implementation detail.
|
|
# Please see https://github.com/tornadoweb/tornado/pull/706
|
|
# before sending a pull request that adds **kwargs to this function.
|
|
def json_encode(value: Any) -> str:
|
|
"""JSON-encodes the given Python object."""
|
|
# JSON permits but does not require forward slashes to be escaped.
|
|
# This is useful when json data is emitted in a <script> tag
|
|
# in HTML, as it prevents </script> tags from prematurely terminating
|
|
# the JavaScript. Some json libraries do this escaping by default,
|
|
# although python's standard library does not, so we do it here.
|
|
# http://stackoverflow.com/questions/1580647/json-why-are-forward-slashes-escaped
|
|
return json.dumps(value).replace("</", "<\\/")
|
|
|
|
|
|
def json_decode(value: Union[str, bytes]) -> Any:
|
|
"""Returns Python objects for the given JSON string.
|
|
|
|
Supports both `str` and `bytes` inputs.
|
|
"""
|
|
return json.loads(to_basestring(value))
|
|
|
|
|
|
def squeeze(value: str) -> str:
|
|
"""Replace all sequences of whitespace chars with a single space."""
|
|
return re.sub(r"[\x00-\x20]+", " ", value).strip()
|
|
|
|
|
|
def url_escape(value: Union[str, bytes], plus: bool = True) -> str:
|
|
"""Returns a URL-encoded version of the given value.
|
|
|
|
If ``plus`` is true (the default), spaces will be represented
|
|
as "+" instead of "%20". This is appropriate for query strings
|
|
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
|
|
"""
|
|
quote = urllib.parse.quote_plus if plus else urllib.parse.quote
|
|
return quote(utf8(value))
|
|
|
|
|
|
@typing.overload
|
|
def url_unescape(value: Union[str, bytes], encoding: None, plus: bool = True) -> bytes:
|
|
pass
|
|
|
|
|
|
@typing.overload # noqa: F811
|
|
def url_unescape(
|
|
value: Union[str, bytes], encoding: str = "utf-8", plus: bool = True
|
|
) -> str:
|
|
pass
|
|
|
|
|
|
def url_unescape( # noqa: F811
|
|
value: Union[str, bytes], encoding: Optional[str] = "utf-8", plus: bool = True
|
|
) -> Union[str, bytes]:
|
|
"""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
|
|
"""
|
|
if encoding is None:
|
|
if plus:
|
|
# unquote_to_bytes doesn't have a _plus variant
|
|
value = to_basestring(value).replace("+", " ")
|
|
return urllib.parse.unquote_to_bytes(value)
|
|
else:
|
|
unquote = urllib.parse.unquote_plus if plus else urllib.parse.unquote
|
|
return unquote(to_basestring(value), encoding=encoding)
|
|
|
|
|
|
def parse_qs_bytes(
|
|
qs: Union[str, bytes], keep_blank_values: bool = False, strict_parsing: bool = False
|
|
) -> Dict[str, List[bytes]]:
|
|
"""Parses a query string like urlparse.parse_qs,
|
|
but takes bytes and returns the values as byte strings.
|
|
|
|
Keys still become type str (interpreted as latin1 in python3!)
|
|
because it's too painful to keep them as byte strings in
|
|
python3 and in practice they're nearly always ascii anyway.
|
|
"""
|
|
# This is gross, but python3 doesn't give us another way.
|
|
# Latin1 is the universal donor of character encodings.
|
|
if isinstance(qs, bytes):
|
|
qs = qs.decode("latin1")
|
|
result = urllib.parse.parse_qs(
|
|
qs, keep_blank_values, strict_parsing, encoding="latin1", errors="strict"
|
|
)
|
|
encoded = {}
|
|
for k, v in result.items():
|
|
encoded[k] = [i.encode("latin1") for i in v]
|
|
return encoded
|
|
|
|
|
|
_UTF8_TYPES = (bytes, type(None))
|
|
|
|
|
|
@typing.overload
|
|
def utf8(value: bytes) -> bytes:
|
|
pass
|
|
|
|
|
|
@typing.overload # noqa: F811
|
|
def utf8(value: str) -> bytes:
|
|
pass
|
|
|
|
|
|
@typing.overload # noqa: F811
|
|
def utf8(value: None) -> None:
|
|
pass
|
|
|
|
|
|
def utf8(value: Union[None, str, bytes]) -> Optional[bytes]: # noqa: F811
|
|
"""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
|
|
if not isinstance(value, unicode_type):
|
|
raise TypeError("Expected bytes, unicode, or None; got %r" % type(value))
|
|
return value.encode("utf-8")
|
|
|
|
|
|
_TO_UNICODE_TYPES = (unicode_type, type(None))
|
|
|
|
|
|
@typing.overload
|
|
def to_unicode(value: str) -> str:
|
|
pass
|
|
|
|
|
|
@typing.overload # noqa: F811
|
|
def to_unicode(value: bytes) -> str:
|
|
pass
|
|
|
|
|
|
@typing.overload # noqa: F811
|
|
def to_unicode(value: None) -> None:
|
|
pass
|
|
|
|
|
|
def to_unicode(value: Union[None, str, bytes]) -> Optional[str]: # noqa: F811
|
|
"""Converts a string argument to a unicode string.
|
|
|
|
If the argument is already a unicode string or None, it is returned
|
|
unchanged. Otherwise it must be a byte string and is decoded as utf8.
|
|
"""
|
|
if isinstance(value, _TO_UNICODE_TYPES):
|
|
return value
|
|
if not isinstance(value, bytes):
|
|
raise TypeError("Expected bytes, unicode, or None; got %r" % type(value))
|
|
return value.decode("utf-8")
|
|
|
|
|
|
# to_unicode was previously named _unicode not because it was private,
|
|
# but to avoid conflicts with the built-in unicode() function/type
|
|
_unicode = to_unicode
|
|
|
|
# When dealing with the standard library across python 2 and 3 it is
|
|
# sometimes useful to have a direct conversion to the native string type
|
|
native_str = to_unicode
|
|
to_basestring = to_unicode
|
|
|
|
|
|
def recursive_unicode(obj: Any) -> Any:
|
|
"""Walks a simple data structure, converting byte strings to unicode.
|
|
|
|
Supports lists, tuples, and dictionaries.
|
|
"""
|
|
if isinstance(obj, dict):
|
|
return dict(
|
|
(recursive_unicode(k), recursive_unicode(v)) for (k, v) in obj.items()
|
|
)
|
|
elif isinstance(obj, list):
|
|
return list(recursive_unicode(i) for i in obj)
|
|
elif isinstance(obj, tuple):
|
|
return tuple(recursive_unicode(i) for i in obj)
|
|
elif isinstance(obj, bytes):
|
|
return to_unicode(obj)
|
|
else:
|
|
return obj
|
|
|
|
|
|
# I originally used the regex from
|
|
# http://daringfireball.net/2010/07/improved_regex_for_matching_urls
|
|
# but it gets all exponential on certain patterns (such as too many trailing
|
|
# dots), causing the regex matcher to never return.
|
|
# This regex should avoid those problems.
|
|
# Use to_unicode instead of tornado.util.u - we don't want backslashes getting
|
|
# processed as escapes.
|
|
_URL_RE = re.compile(
|
|
to_unicode(
|
|
r"""\b((?:([\w-]+):(/{1,3})|www[.])(?:(?:(?:[^\s&()]|&|")*(?:[^!"#$%&'()*+,.:;<=>?@\[\]^`{|}~\s]))|(?:\((?:[^\s&()]|&|")*\)))+)""" # noqa: E501
|
|
)
|
|
)
|
|
|
|
|
|
def linkify(
|
|
text: Union[str, bytes],
|
|
shorten: bool = False,
|
|
extra_params: Union[str, Callable[[str], str]] = "",
|
|
require_protocol: bool = False,
|
|
permitted_protocols: List[str] = ["http", "https"],
|
|
) -> str:
|
|
"""Converts plain text into HTML with links.
|
|
|
|
For example: ``linkify("Hello http://tornadoweb.org!")`` would return
|
|
``Hello <a href="http://tornadoweb.org">http://tornadoweb.org</a>!``
|
|
|
|
Parameters:
|
|
|
|
* ``shorten``: Long urls will be shortened for display.
|
|
|
|
* ``extra_params``: Extra text to include in the link tag, or a callable
|
|
taking the link as an argument and returning the extra text
|
|
e.g. ``linkify(text, extra_params='rel="nofollow" class="external"')``,
|
|
or::
|
|
|
|
def extra_params_cb(url):
|
|
if url.startswith("http://example.com"):
|
|
return 'class="internal"'
|
|
else:
|
|
return 'class="external" rel="nofollow"'
|
|
linkify(text, extra_params=extra_params_cb)
|
|
|
|
* ``require_protocol``: Only linkify urls which include a protocol. If
|
|
this is False, urls such as www.facebook.com will also be linkified.
|
|
|
|
* ``permitted_protocols``: List (or set) of protocols which should be
|
|
linkified, e.g. ``linkify(text, permitted_protocols=["http", "ftp",
|
|
"mailto"])``. It is very unsafe to include protocols such as
|
|
``javascript``.
|
|
"""
|
|
if extra_params and not callable(extra_params):
|
|
extra_params = " " + extra_params.strip()
|
|
|
|
def make_link(m: typing.Match) -> str:
|
|
url = m.group(1)
|
|
proto = m.group(2)
|
|
if require_protocol and not proto:
|
|
return url # not protocol, no linkify
|
|
|
|
if proto and proto not in permitted_protocols:
|
|
return url # bad protocol, no linkify
|
|
|
|
href = m.group(1)
|
|
if not proto:
|
|
href = "http://" + href # no proto specified, use http
|
|
|
|
if callable(extra_params):
|
|
params = " " + extra_params(href).strip()
|
|
else:
|
|
params = extra_params
|
|
|
|
# clip long urls. max_len is just an approximation
|
|
max_len = 30
|
|
if shorten and len(url) > max_len:
|
|
before_clip = url
|
|
if proto:
|
|
proto_len = len(proto) + 1 + len(m.group(3) or "") # +1 for :
|
|
else:
|
|
proto_len = 0
|
|
|
|
parts = url[proto_len:].split("/")
|
|
if len(parts) > 1:
|
|
# Grab the whole host part plus the first bit of the path
|
|
# The path is usually not that interesting once shortened
|
|
# (no more slug, etc), so it really just provides a little
|
|
# extra indication of shortening.
|
|
url = (
|
|
url[:proto_len]
|
|
+ parts[0]
|
|
+ "/"
|
|
+ parts[1][:8].split("?")[0].split(".")[0]
|
|
)
|
|
|
|
if len(url) > max_len * 1.5: # still too long
|
|
url = url[:max_len]
|
|
|
|
if url != before_clip:
|
|
amp = url.rfind("&")
|
|
# avoid splitting html char entities
|
|
if amp > max_len - 5:
|
|
url = url[:amp]
|
|
url += "..."
|
|
|
|
if len(url) >= len(before_clip):
|
|
url = before_clip
|
|
else:
|
|
# full url is visible on mouse-over (for those who don't
|
|
# have a status bar, such as Safari by default)
|
|
params += ' title="%s"' % href
|
|
|
|
return u'<a href="%s"%s>%s</a>' % (href, params, url)
|
|
|
|
# First HTML-escape so that our strings are all safe.
|
|
# The regex is modified to avoid character entites other than & so
|
|
# that we won't pick up ", etc.
|
|
text = _unicode(xhtml_escape(text))
|
|
return _URL_RE.sub(make_link, text)
|
|
|
|
|
|
def _convert_entity(m: typing.Match) -> str:
|
|
if m.group(1) == "#":
|
|
try:
|
|
if m.group(2)[:1].lower() == "x":
|
|
return chr(int(m.group(2)[1:], 16))
|
|
else:
|
|
return chr(int(m.group(2)))
|
|
except ValueError:
|
|
return "&#%s;" % m.group(2)
|
|
try:
|
|
return _HTML_UNICODE_MAP[m.group(2)]
|
|
except KeyError:
|
|
return "&%s;" % m.group(2)
|
|
|
|
|
|
def _build_unicode_map() -> Dict[str, str]:
|
|
unicode_map = {}
|
|
for name, value in html.entities.name2codepoint.items():
|
|
unicode_map[name] = chr(value)
|
|
return unicode_map
|
|
|
|
|
|
_HTML_UNICODE_MAP = _build_unicode_map()
|