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.
61 lines
1.5 KiB
Python
61 lines
1.5 KiB
Python
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import Sequence
|
|
from typing import Any
|
|
from typing import NamedTuple
|
|
|
|
from pre_commit.prefix import Prefix
|
|
|
|
logger = logging.getLogger('pre_commit')
|
|
|
|
|
|
class Hook(NamedTuple):
|
|
src: str
|
|
prefix: Prefix
|
|
id: str
|
|
name: str
|
|
entry: str
|
|
language: str
|
|
alias: str
|
|
files: str
|
|
exclude: str
|
|
types: Sequence[str]
|
|
types_or: Sequence[str]
|
|
exclude_types: Sequence[str]
|
|
additional_dependencies: Sequence[str]
|
|
args: Sequence[str]
|
|
always_run: bool
|
|
fail_fast: bool
|
|
pass_filenames: bool
|
|
pass_filenames_via_stdin: bool
|
|
description: str
|
|
language_version: str
|
|
log_file: str
|
|
minimum_pre_commit_version: str
|
|
require_serial: bool
|
|
stages: Sequence[str]
|
|
verbose: bool
|
|
|
|
@property
|
|
def install_key(self) -> tuple[Prefix, str, str, tuple[str, ...]]:
|
|
return (
|
|
self.prefix,
|
|
self.language,
|
|
self.language_version,
|
|
tuple(self.additional_dependencies),
|
|
)
|
|
|
|
@classmethod
|
|
def create(cls, src: str, prefix: Prefix, dct: dict[str, Any]) -> Hook:
|
|
# TODO: have cfgv do this (?)
|
|
extra_keys = set(dct) - _KEYS
|
|
if extra_keys:
|
|
logger.warning(
|
|
f'Unexpected key(s) present on {src} => {dct["id"]}: '
|
|
f'{", ".join(sorted(extra_keys))}',
|
|
)
|
|
return cls(src=src, prefix=prefix, **{k: dct[k] for k in _KEYS})
|
|
|
|
|
|
_KEYS = frozenset(set(Hook._fields) - {'src', 'prefix'})
|