FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

fix(tag): split tag object headers at line feeds only by Keerthana-64 · Pull Request #2290 · gitpython-developers/GitPython · GitHub

Repository navigation

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension .py  (2) All 1 file type selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
11 changes: 10 additions & 1 deletion git/objects/tag.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,16 @@ def _set_cache_(self, attr: str) -> None:
"""Cache all our attributes at once."""
if attr in TagObject.__slots__:
ostream = self.repo.odb.stream(self.binsha)
lines: List[str] = ostream.read().decode(defenc, "replace").splitlines()
# Git ends a header only at a line feed, but str.splitlines() also
# breaks at "\r", "\v", "\f", U+2028 and similar. Splitting a tag
# object that way lets an untrusted "tag" header containing such a
# character shift every later header by a line. Split at "\n" only,
# and drop the trailing empty element so tags that use line feeds
# parse exactly as before.
data = ostream.read().decode(defenc, "replace")
lines: List[str] = data.split("\n")
if lines and lines[-1] == "":
lines.pop()

_obj, hexsha = lines[0].split(" ")
_type_token, type_name = lines[1].split(" ")
Expand Down
27 changes: 27 additions & 0 deletions test/test_refs.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -7,10 +7,12 @@
import os.path as osp
import tempfile
import unittest
from io import BytesIO
from itertools import chain
from pathlib import Path
from unittest.mock import patch

from gitdb import IStream
from gitdb.exc import BadName

import git.refs as refs
Expand Down Expand Up @@ -139,6 +141,31 @@ def test_tags_author(self):
tagger_name = tagobj.tagger.name
assert tagger_name == "Michael Trier"

def test_tag_headers_split_at_line_feeds_only(self):
# A "tag" header value carrying a U+2028 (or any separator that
# str.splitlines() honors but git does not) must not shift the later
# headers. Git ends a header only at "\n", so GitPython must read the
# whole value as the tag name and the following line as the tagger,
# exactly as "git cat-file tag" does. See the TagObject parsing fix.
with tempfile.TemporaryDirectory() as tmp_dir:
with self._repo_with_initial_commit(Path(tmp_dir)) as repo:
commit_hexsha = repo.head.commit.hexsha
payload = (
f"object {commit_hexsha}\n"
"type commit\n"
"tag v1
tagger Linus Torvalds <torvalds@linux-foundation.org> 1700000000 +0000\n"
"tagger Mallory <m@evil.example> 1700000001 +0000\n"
"\n"
"release\n"
).encode("utf-8")
istream = repo.odb.store(IStream("tag", len(payload), BytesIO(payload)))
tagobj = TagObject(repo, istream.binsha)

assert tagobj.tag == "v1
tagger Linus Torvalds <torvalds@linux-foundation.org> 1700000000 +0000"
assert tagobj.tagger.name == "Mallory"
assert tagobj.tagger.email == "m@evil.example"
assert tagobj.message == "release"

def test_tags(self):
# Tag refs can point to tag objects or to commits.
s = set()
Expand Down
Loading

Back | FazBrowse Home | New Git URL