Skip to content

Do not decode # in URL paths during canonicalization #141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Mar 5, 2021
Merged

Do not decode # in URL paths during canonicalization #141

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b8c753f
fix: preservation of url encoded hash signs.
jvanasco May 9, 2019
bad299a
Remove # only from path-specific safe characters
Gallaecio Oct 18, 2019
a26dd48
Text # quoting in safe_url_string
Gallaecio Oct 18, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 26 additions & 0 deletions tests/test_url.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,6 +219,17 @@ def test_safe_url_port_number(self):
safe_url_string(u"http://www.example.com:/résumé?q=résumé"),
"http://www.example.com/r%C3%A9sum%C3%A9?q=r%C3%A9sum%C3%A9")

def test_safe_url_string_preserve_nonfragment_hash(self):
# don't decode `%23` to `#`
self.assertEqual(safe_url_string("http://www.example.com/path/to/%23/foo/bar"),
"http://www.example.com/path/to/%23/foo/bar")
self.assertEqual(safe_url_string("http://www.example.com/path/to/%23/foo/bar#frag"),
"http://www.example.com/path/to/%23/foo/bar#frag")
self.assertEqual(safe_url_string("http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2Fpath%2Fto%2F%23%2Fbar%2Ffoo"),
"http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2Fpath%2Fto%2F%23%2Fbar%2Ffoo")
self.assertEqual(safe_url_string("http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo#frag"),
"http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo#frag")

def test_safe_download_url(self):
self.assertEqual(safe_download_url('http://www.example.org'),
'http://www.example.org/')
Expand Down Expand Up @@ -650,6 +661,21 @@ def test_canonicalize_url_idna_exceptions(self):
"http://www.{label}.com/r%C3%A9sum%C3%A9?q=r%C3%A9sum%C3%A9".format(
label=u"example"*11))

def test_preserve_nonfragment_hash(self):
# don't decode `%23` to `#`
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar"),
"http://www.example.com/path/to/%23/foo/bar")
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar#frag"),
"http://www.example.com/path/to/%23/foo/bar")
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar#frag", keep_fragments=True),
"http://www.example.com/path/to/%23/foo/bar#frag")
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2Fpath%2Fto%2F%23%2Fbar%2Ffoo"),
"http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2Fpath%2Fto%2F%23%2Fbar%2Ffoo")
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo#frag"),
"http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo")
self.assertEqual(canonicalize_url("http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo#frag", keep_fragments=True),
"http://www.example.com/path/to/%23/foo/bar?url=http%3A%2F%2Fwww.example.com%2F%2Fpath%2Fto%2F%23%2Fbar%2Ffoo#frag")


class DataURITests(unittest.TestCase):

Expand Down
7 changes: 4 additions & 3 deletions w3lib/url.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ def _quote_byte(error):
EXTRA_SAFE_CHARS = b'|' # see https://github.com/scrapy/w3lib/pull/25

_safe_chars = RFC3986_RESERVED + RFC3986_UNRESERVED + EXTRA_SAFE_CHARS + b'%'
_path_safe_chars = _safe_chars.replace(b'#', b'')

_ascii_tab_newline_re = re.compile(r'[\t\n\r]') # see https://infra.spec.whatwg.org/#ascii-tab-or-newline

Expand Down Expand Up @@ -74,7 +75,7 @@ def safe_url_string(url, encoding='utf8', path_encoding='utf8', quote_path=True)

# default encoding for path component SHOULD be UTF-8
if quote_path:
path = quote(to_bytes(parts.path, path_encoding), _safe_chars)
path = quote(to_bytes(parts.path, path_encoding), _path_safe_chars)
else:
path = to_native_str(parts.path)

Expand Down Expand Up @@ -414,7 +415,7 @@ def _safe_ParseResult(parts, encoding='utf8', path_encoding='utf8'):
to_native_str(netloc),

# default encoding for path component SHOULD be UTF-8
quote(to_bytes(parts.path, path_encoding), _safe_chars),
quote(to_bytes(parts.path, path_encoding), _path_safe_chars),
quote(to_bytes(parts.params, path_encoding), _safe_chars),

# encoding of query and fragment follows page encoding
Expand Down Expand Up @@ -502,7 +503,7 @@ def canonicalize_url(url, keep_blank_values=True, keep_fragments=False,
# 2. decode percent-encoded sequences in path as UTF-8 (or keep raw bytes)
# and percent-encode path again (this normalizes to upper-case %XX)
uqp = _unquotepath(path)
path = quote(uqp, _safe_chars) or '/'
path = quote(uqp, _path_safe_chars) or '/'

fragment = '' if not keep_fragments else fragment

Expand Down