Skip to content

make tarfile creation reproducible #1915

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
asottile merged 1 commit into from
May 18, 2021
Merged

make tarfile creation reproducible #1915

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
Binary file modified pre_commit/resources/rbenv.tar.gz
View file
Open in desktop
Binary file not shown.
Binary file modified pre_commit/resources/ruby-build.tar.gz
View file
Open in desktop
Binary file not shown.
Binary file modified pre_commit/resources/ruby-download.tar.gz
View file
Open in desktop
Binary file not shown.
36 changes: 26 additions & 10 deletions testing/make-archives
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
#!/usr/bin/env python3
import argparse
import gzip
import os.path
import shutil
import subprocess
Expand All @@ -24,15 +25,14 @@ REPOS = (
)


def reset(tarinfo: tarfile.TarInfo) -> tarfile.TarInfo:
tarinfo.uid = tarinfo.gid = 0
tarinfo.uname = tarinfo.gname = 'root'
tarinfo.mtime = 0
return tarinfo


def make_archive(name: str, repo: str, ref: str, destdir: str) -> str:
"""Makes an archive of a repository in the given destdir.

:param text name: Name to give the archive. For instance foo. The file
that is created will be called foo.tar.gz.
:param text repo: Repository to clone.
:param text ref: Tag/SHA/branch to check out.
:param text destdir: Directory to place archives in.
"""
output_path = os.path.join(destdir, f'{name}.tar.gz')
with tempfile.TemporaryDirectory() as tmpdir:
# this ensures that the root directory has umask permissions
Expand All @@ -47,8 +47,24 @@ def make_archive(name: str, repo: str, ref: str, destdir: str) -> str:
# runtime
shutil.rmtree(os.path.join(gitdir, '.git'))

with tarfile.open(output_path, 'w|gz') as tf:
tf.add(gitdir, name)
arcs = [(name, gitdir)]
for root, dirs, filenames in os.walk(gitdir):
for filename in dirs + filenames:
abspath = os.path.abspath(os.path.join(root, filename))
relpath = os.path.relpath(abspath, gitdir)
arcs.append((os.path.join(name, relpath), abspath))
arcs.sort()

with gzip.GzipFile(output_path, 'wb', mtime=0) as gzipf:
# https://github.com/python/typeshed/issues/5491
with tarfile.open(fileobj=gzipf, mode='w') as tf: # type: ignore
for arcname, abspath in arcs:
tf.add(
abspath,
arcname=arcname,
recursive=False,
filter=reset,
)

return output_path

Expand Down