``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is
decomposed before parsing, no error will be raised.
+ .. warning::
+
+ :func:`urlparse` does not perform validation. See :ref:`URL parsing
+ security <url-parsing-security>` for details.
+
.. versionchanged:: 3.2
Added IPv6 URL parsing capabilities.
``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is
decomposed before parsing, no error will be raised.
+ Following some of the `WHATWG spec`_ that updates RFC 3986, leading C0
+ control and space characters are stripped from the URL. ``\n``,
+ ``\r`` and tab ``\t`` characters are removed from the URL at any position.
+
+ .. warning::
+
+ :func:`urlsplit` does not perform validation. See :ref:`URL parsing
+ security <url-parsing-security>` for details.
+
.. versionchanged:: 3.6
Out-of-range port numbers now raise :exc:`ValueError`, instead of
returning :const:`None`.
Characters that affect netloc parsing under NFKC normalization will
now raise :exc:`ValueError`.
+ .. versionchanged:: 3.7.17
+ Leading WHATWG C0 control and space characters are stripped from the URL.
+
+
.. function:: urlunsplit(parts)
.. versionchanged:: 3.2
Result is a structured object rather than a simple 2-tuple.
+.. _url-parsing-security:
+
+URL parsing security
+--------------------
+
+The :func:`urlsplit` and :func:`urlparse` APIs do not perform **validation** of
+inputs. They may not raise errors on inputs that other applications consider
+invalid. They may also succeed on some inputs that might not be considered
+URLs elsewhere. Their purpose is for practical functionality rather than
+purity.
+
+Instead of raising an exception on unusual input, they may instead return some
+component parts as empty strings. Or components may contain more than perhaps
+they should.
+
+We recommend that users of these APIs where the values may be used anywhere
+with security implications code defensively. Do some verification within your
+code before trusting a returned component part. Does that ``scheme`` make
+sense? Is that a sensible ``path``? Is there anything strange about that
+``hostname``? etc.
+
.. _parsing-ascii-encoded-bytes:
Parsing ASCII Encoded Bytes
for port in ("foo", "1.5", "-1", "0x10"):
with self.subTest(bytes=bytes, parse=parse, port=port):
netloc = "www.example.net:" + port
- url = "http://" + netloc
+ url = "http://" + netloc + "/"
if bytes:
netloc = netloc.encode("ascii")
url = url.encode("ascii")
else:
self.assertEqual(p.scheme, "")
+ def test_urlsplit_strip_url(self):
+ noise = bytes(range(0, 0x20 + 1))
+ base_url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
+
+ url = noise.decode("utf-8") + base_url
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, "http")
+ self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query=yes")
+ self.assertEqual(p.fragment, "frag")
+ self.assertEqual(p.username, "User")
+ self.assertEqual(p.password, "Pass")
+ self.assertEqual(p.hostname, "www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url)
+
+ url = noise + base_url.encode("utf-8")
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"User:Pass@www.python.org:080")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"query=yes")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, b"User")
+ self.assertEqual(p.password, b"Pass")
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url.encode("utf-8"))
+
+ # Test that trailing space is preserved as some applications rely on
+ # this within query strings.
+ query_spaces_url = "https://www.python.org:88/doc/?query= "
+ p = urllib.parse.urlsplit(noise.decode("utf-8") + query_spaces_url)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.netloc, "www.python.org:88")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query= ")
+ self.assertEqual(p.port, 88)
+ self.assertEqual(p.geturl(), query_spaces_url)
+
+ p = urllib.parse.urlsplit("www.pypi.org ")
+ # That "hostname" gets considered a "path" due to the
+ # trailing space and our existing logic... YUCK...
+ # and re-assembles via geturl aka unurlsplit into the original.
+ # django.core.validators.URLValidator (at least through v3.2) relies on
+ # this, for better or worse, to catch it in a ValidationError via its
+ # regular expressions.
+ # Here we test the basic round trip concept of such a trailing space.
+ self.assertEqual(urllib.parse.urlunsplit(p), "www.pypi.org ")
+
+ # with scheme as cache-key
+ url = "//www.python.org/"
+ scheme = noise.decode("utf-8") + "https" + noise.decode("utf-8")
+ for _ in range(2):
+ p = urllib.parse.urlsplit(url, scheme=scheme)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.geturl(), "https://www.python.org/")
+
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
+
+The WHATWG URL Parser spec should also be considered. We are not compliant with
+it either due to existing user code API behavior expectations (Hyrum's Law).
+It serves as a useful guide when making changes.
"""
import re
'0123456789'
'+-.')
+# Leading and trailing C0 control and space to be stripped per WHATWG spec.
+# == "".join([chr(i) for i in range(0, 0x20 + 1)])
+_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '
+
+
# XXX: Consider replacing with functools.lru_cache
MAX_CACHE_SIZE = 20
_parse_cache = {}
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
+ # Only lstrip url as some applications rely on preserving trailing space.
+ # (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both)
+ url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)
+ scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
projects / platform / upstream / python3.git / commitdiff