mirror of
https://github.com/pre-commit/pre-commit.git
synced 2026-04-15 18:11:48 +04:00
add pass_filenames_via_stdin for large changesets
pre-commit currently passes selected filenames to hooks via argv.
For large changesets (or --all-files), argv length limits are hit and
filenames are partitioned, causing multiple hook invocations.
This means there is currently no built-in way to pass filenames to an
underlying hook in one shot without chunking / re-running. The only practical
workaround is to set pass_filenames: false and run custom git operations in
hook code to reconstruct the file set, which is expensive and duplicates
pre-commit's own file-selection logic.
This change adds a hook option:
pass_filenames_via_stdin: true
When enabled, pre-commit sends filenames as NUL-delimited bytes on stdin and
runs the hook in a single invocation (no argv chunking).
Why NUL-delimited stdin:
- safe for filenames containing spaces/newlines
- matches established -0 conventions in unix tooling
Usage for hook authors:
- shell:
while IFS= read -r -d '' filename; do
...
done
- python:
data = sys.stdin.buffer.read()
filenames = [os.fsdecode(p) for p in data.split(b'\0') if p]
Behavior notes:
- default remains argv-based passing
- pass_filenames: false still disables filename passing entirely
Implementation includes schema/runtime wiring, shared NUL encode/decode
helpers, and tests covering defaulting and runtime behavior.
This commit is contained in:
parent
8416413a0e
commit
635912514d
18 changed files with 147 additions and 2 deletions
|
|
@ -1,6 +1,7 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import os.path
|
||||
import shlex
|
||||
import sys
|
||||
from unittest import mock
|
||||
|
||||
|
|
@ -166,6 +167,42 @@ def test_basic_run_hook(tmp_path):
|
|||
assert out == b'hi hello file file file\n'
|
||||
|
||||
|
||||
def test_basic_run_hook_passes_filenames_via_stdin(tmp_path):
|
||||
ret, out = lang_base.basic_run_hook(
|
||||
Prefix(tmp_path),
|
||||
(
|
||||
f'{shlex.quote(sys.executable)} -c '
|
||||
'\'import sys; '
|
||||
'print(repr(sys.argv[1:])); '
|
||||
'print(repr(sys.stdin.buffer.read()))\''
|
||||
),
|
||||
(),
|
||||
['file1', 'file2'],
|
||||
is_local=False,
|
||||
require_serial=False,
|
||||
color=False,
|
||||
pass_filenames_via_stdin=True,
|
||||
)
|
||||
assert ret == 0
|
||||
out = out.replace(b'\r\n', b'\n')
|
||||
assert out == b"[]\nb'file1\\x00file2\\x00'\n"
|
||||
|
||||
|
||||
def test_to_nul_delimited_filenames():
|
||||
ret = lang_base.to_nul_delimited_filenames(('file1', 'file2'))
|
||||
assert ret == b'file1\x00file2\x00'
|
||||
|
||||
|
||||
def test_to_nul_delimited_filenames_empty():
|
||||
ret = lang_base.to_nul_delimited_filenames(())
|
||||
assert ret == b''
|
||||
|
||||
|
||||
def test_from_nul_delimited_filenames():
|
||||
ret = lang_base.from_nul_delimited_filenames(b'file1\x00file2\x00')
|
||||
assert ret == ['file1', 'file2']
|
||||
|
||||
|
||||
def test_hook_cmd():
|
||||
assert lang_base.hook_cmd('echo hi', ()) == ('echo', 'hi')
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue