mirror of
https://github.com/pre-commit/pre-commit.git
synced 2026-04-14 17:41:45 +04:00
635912514d
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.
157 lines
4.5 KiB
Python
157 lines
4.5 KiB
Python
from __future__ import annotations
|
|
|
|
import sys
|
|
from unittest import mock
|
|
|
|
import pytest
|
|
|
|
from pre_commit.languages import pygrep
|
|
from testing.language_helpers import run_language
|
|
|
|
|
|
@pytest.fixture
|
|
def some_files(tmpdir):
|
|
tmpdir.join('f1').write_binary(b'foo\nbar\n')
|
|
tmpdir.join('f2').write_binary(b'[INFO] hi\n')
|
|
tmpdir.join('f3').write_binary(b"with'quotes\n")
|
|
tmpdir.join('f4').write_binary(b'foo\npattern\nbar\n')
|
|
tmpdir.join('f5').write_binary(b'[INFO] hi\npattern\nbar')
|
|
tmpdir.join('f6').write_binary(b"pattern\nbarwith'foo\n")
|
|
tmpdir.join('f7').write_binary(b"hello'hi\nworld\n")
|
|
tmpdir.join('f8').write_binary(b'foo\nbar\nbaz\n')
|
|
tmpdir.join('f9').write_binary(b'[WARN] hi\n')
|
|
with tmpdir.as_cwd():
|
|
yield
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
@pytest.mark.parametrize(
|
|
('pattern', 'expected_retcode', 'expected_out'),
|
|
(
|
|
('baz', 0, ''),
|
|
('foo', 1, 'f1:1:foo\n'),
|
|
('bar', 1, 'f1:2:bar\n'),
|
|
(r'(?i)\[info\]', 1, 'f2:1:[INFO] hi\n'),
|
|
("h'q", 1, "f3:1:with'quotes\n"),
|
|
),
|
|
)
|
|
def test_main(cap_out, pattern, expected_retcode, expected_out):
|
|
ret = pygrep.main((pattern, 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == expected_retcode
|
|
assert out == expected_out
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_line_no_match(cap_out):
|
|
ret = pygrep.main(('pattern\nbar', 'f4', 'f5', 'f6', '--negate'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f4\nf5\nf6\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_line_two_match(cap_out):
|
|
ret = pygrep.main(('foo', 'f4', 'f5', 'f6', '--negate'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f5\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_line_all_match(cap_out):
|
|
ret = pygrep.main(('pattern', 'f4', 'f5', 'f6', '--negate'))
|
|
out = cap_out.get()
|
|
assert ret == 0
|
|
assert out == ''
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_file_no_match(cap_out):
|
|
ret = pygrep.main(('baz', 'f4', 'f5', 'f6', '--negate', '--multiline'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f4\nf5\nf6\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_file_one_match(cap_out):
|
|
ret = pygrep.main(
|
|
('foo\npattern', 'f4', 'f5', 'f6', '--negate', '--multiline'),
|
|
)
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f5\nf6\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_negate_by_file_all_match(cap_out):
|
|
ret = pygrep.main(
|
|
('pattern\nbar', 'f4', 'f5', 'f6', '--negate', '--multiline'),
|
|
)
|
|
out = cap_out.get()
|
|
assert ret == 0
|
|
assert out == ''
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_ignore_case(cap_out):
|
|
ret = pygrep.main(('--ignore-case', 'info', 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f2:1:[INFO] hi\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_multiline(cap_out):
|
|
ret = pygrep.main(('--multiline', r'foo\nbar', 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f1:1:foo\nbar\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_multiline_line_number(cap_out):
|
|
ret = pygrep.main(('--multiline', r'ar', 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f1:2:bar\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_multiline_dotall_flag_is_enabled(cap_out):
|
|
ret = pygrep.main(('--multiline', r'o.*bar', 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f1:1:foo\nbar\n'
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_multiline_multiline_flag_is_enabled(cap_out):
|
|
ret = pygrep.main(('--multiline', r'foo$.*bar', 'f1', 'f2', 'f3'))
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f1:1:foo\nbar\n'
|
|
|
|
|
|
def test_grep_hook_matching(some_files, tmp_path):
|
|
ret = run_language(
|
|
tmp_path, pygrep, 'ello', file_args=('f7', 'f8', 'f9'),
|
|
)
|
|
assert ret == (1, b"f7:1:hello'hi\n")
|
|
|
|
|
|
@pytest.mark.usefixtures('some_files')
|
|
def test_main_reads_nul_delimited_filenames_from_stdin(cap_out):
|
|
with mock.patch.object(sys.stdin.buffer, 'read', return_value=b'f1\x00f2\x00'):
|
|
ret = pygrep.main(('foo',))
|
|
|
|
out = cap_out.get()
|
|
assert ret == 1
|
|
assert out == 'f1:1:foo\n'
|
|
|
|
|
|
@pytest.mark.parametrize('regex', ('nope', "foo'bar", r'^\[INFO\]'))
|
|
def test_grep_hook_not_matching(regex, some_files, tmp_path):
|
|
ret = run_language(tmp_path, pygrep, regex, file_args=('f7', 'f8', 'f9'))
|
|
assert ret == (0, b'')
|