Visitar URL original
fix: bound actor and date parsing by Byron · Pull Request #2253 · gitpython-developers/GitPython · GitHub
Skip to content

fix: bound actor and date parsing #2253

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
Byron merged 1 commit into from
Sep 27, 2026
+54 −3
Merged

fix: bound actor and date parsing #2253

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 doc/source/changes.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@ Changelog
Security fixes for

* https://github.com/gitpython-developers/GitPython/security/advisories/GHSA-w8jc-g24h-crhw
* https://github.com/gitpython-developers/GitPython/security/advisories/GHSA-m64x-33q8-m5h7
Comment thread
Byron marked this conversation as resolved.

3.2.0
=====
Expand Down
7 changes: 4 additions & 3 deletions git/objects/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,9 +318,10 @@ def parse_date(string_date: Union[str, datetime]) -> Tuple[int, int]:
# END handle exceptions


# Precompiled regexes
_re_actor_epoch = re.compile(r"^.+? (.*) (\d+) ([+-]\d+).*$")
_re_only_actor = re.compile(r"^.+? (.*)$")
# Check the line ending once, before parsing fields, to avoid repeated backtracking.
# Keep the field name from consuming spaces belonging to the actor.
_re_actor_epoch = re.compile(r"^(?=[^\n]*$).[^ \n]* (.*) (\d+) ([+-]\d+)")
_re_only_actor = re.compile(r"^.[^ \n]* (.*)$")


def parse_actor_and_date(line: str) -> Tuple[Actor, int, int]:
Expand Down
49 changes: 49 additions & 0 deletions test/test_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
from git.objects.util import (
altz_to_utctz_str,
from_timestamp,
parse_actor_and_date,
parse_date,
tzoffset,
utctz_to_altz,
Expand Down Expand Up @@ -571,6 +572,54 @@ def test_actor_from_string(self):
Actor("name last another", "some-very-long-email@example.com"),
)

@ddt.data(
("", Actor("", None), 0, 0),
("author", Actor("author", None), 0, 0),
("author Name <email> 42 -0700", Actor("Name", "email"), 42, 25200),
("committer Name <email> 42 +0530\n", Actor("Name", "email"), 42, -19800),
("tagger Name <email> 42 +0000\r\n", Actor("Name", "email"), 42, 0),
("author Name <email> 42 -0700 trailing", Actor("Name", "email"), 42, 25200),
("author Name <email> 1 +0 42 -0700", Actor("Name", "email"), 42, 25200),
("author Name <email> invalid -0700", Actor("Name", "email"), 0, 0),
("author Name <email> 42 invalid", Actor("Name", "email"), 0, 0),
("author 42 -0700", Actor("42 -0700", None), 0, 0),
("author 42 -0700", Actor("", None), 42, 25200),
(" author Name <email> 42 -0700", Actor("Name", "email"), 42, 25200),
("author Näme <email> ١ +٠١٣٠", Actor("Näme", "email"), 1, -5400),
("author\nName <email> 42 -0700", Actor("author\nName <email> 42 -0700", None), 0, 0),
Comment thread
Byron marked this conversation as resolved.
("author Name <email> 42 -0700\nextra", Actor("author Name", "email"), 0, 0),
)
@ddt.unpack
def test_parse_actor_and_date(self, line, actor, epoch, offset):
self.assertEqual(parse_actor_and_date(line), (actor, epoch, offset))

def test_parse_actor_and_date_long_malformed_lines(self):
padding = " " * 64_000
for field in ("author", "committer", "tagger"):
for tail in ("", "<unterminated", "invalid -0700", "42", "-0700", "42 invalid", "42 +"):
actor_text = padding + tail
start = time.process_time()
result = parse_actor_and_date(f"{field} {actor_text}")
elapsed = time.process_time() - start
# Leave ample CPU time for slow runners, but catch excessive backtracking.
self.assertLess(elapsed, 1.0, (field, tail))
self.assertEqual(result, (Actor(actor_text, None), 0, 0))

name = "Long name " * 6_400
self.assertEqual(
parse_actor_and_date(f"{field} {name}<email> 42 -0700"),
(Actor(name.rstrip(), "email"), 42, 25200),
)

def test_parse_actor_and_date_long_multiline_input(self):
for field in ("author", "committer", "tagger"):
line = f"{field} Name <email> 42 +" + "0" * 64_000 + "\nextra"
start = time.process_time()
result = parse_actor_and_date(line)
elapsed = time.process_time() - start
self.assertLess(elapsed, 1.0, field)
self.assertEqual(result, (Actor(f"{field} Name", "email"), 0, 0))

@ddt.data(
("name", ""),
("name", "prefix_"),
Expand Down
Loading