Skip to content
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.

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

Avoid normalizing child paths when there are no dots in the path #1248

Merged
merged 5 commits into from
Oct 13, 2024
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
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
1 change: 1 addition & 0 deletions CHANGES/1248.misc.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Improved performance of :meth:`URL.joinpath() <yarl.URL.joinpath> -- by :user:`bdraco`.
bdraco marked this conversation as resolved.
Show resolved Hide resolved
18 changes: 18 additions & 0 deletions tests/test_url.py
Original file line number Diff line number Diff line change
Expand Up @@ -955,6 +955,16 @@ def test_joinpath(base, to_join, expected):
pytest.param("path", "a/", "path/a/", id="default_trailing-empty-segment"),
pytest.param("path", "a//", "path/a//", id="default_trailing-empty-segments"),
pytest.param("path", "a//b", "path/a//b", id="default_embedded-empty-segment"),
pytest.param(
"path/a/b/c/d/e", "a/../../../../../../c", "path/c", id="long-backtrack"
),
pytest.param(
"path/a/b/c/d/e",
"a/../../../././../../../c",
"path/c",
id="long-backtrack-with-dots",
),
pytest.param("path/a/../../d/e", "a/../c", "d/e/c", id="backtrack-in-both"),
],
)
def test_joinpath_empty_segments(base, to_join, expected):
Expand All @@ -965,6 +975,14 @@ def test_joinpath_empty_segments(base, to_join, expected):
)


def test_joinpath_backtrack_to_base():
url = URL("http://example.com/../../c")
new_url = url.joinpath("../../..")
assert str(new_url) == "http://example.com"
assert new_url.path == "/"
assert new_url.raw_path == "/"


def test_joinpath_single_empty_segments():
"""joining standalone empty segments does not create empty segments"""
a = URL("/1//2///3")
Expand Down
4 changes: 3 additions & 1 deletion yarl/_url.py
Original file line number Diff line number Diff line change
Expand Up @@ -949,6 +949,7 @@ def _make_child(self, paths: "Sequence[str]", encoded: bool = False) -> "URL":
keep existing, but do not create new, empty segments
"""
parsed: List[str] = []
needs_normalize: bool = False
for idx, path in enumerate(reversed(paths)):
# empty segment of last is not removed
last = idx == 0
Expand All @@ -957,6 +958,7 @@ def _make_child(self, paths: "Sequence[str]", encoded: bool = False) -> "URL":
f"Appending path {path!r} starting from slash is forbidden"
)
path = path if encoded else self._PATH_QUOTER(path)
needs_normalize |= "." in path
segments = list(reversed(path.split("/")))
bdraco marked this conversation as resolved.
Show resolved Hide resolved
# remove trailing empty segment for all but the last path
segment_slice_start = int(not last and segments[0] == "")
Expand All @@ -968,7 +970,7 @@ def _make_child(self, paths: "Sequence[str]", encoded: bool = False) -> "URL":
parsed = [*old_path_segments[:old_path_cutoff], *parsed]

if self.absolute:
parsed = _normalize_path_segments(parsed)
parsed = _normalize_path_segments(parsed) if needs_normalize else parsed
if parsed and parsed[0] != "":
# inject a leading slash when adding a path to an absolute URL
# where there was none before
Expand Down
Loading