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.

pre_commit/languages/docker.py

@@ -165,6 +165,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:  # pragma: win32 no cover
     # Rebuild the docker image in case it has gone missing, as many people do
     # automated cleanup of docker images.
@@ -178,4 +179,5 @@ def run_hook(
         file_args,
         require_serial=require_serial,
         color=color,
+        pass_filenames_via_stdin=pass_filenames_via_stdin,
     )

pre_commit/languages/docker_image.py

@@ -22,6 +22,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:  # pragma: win32 no cover
     cmd = docker_cmd(color=color) + lang_base.hook_cmd(entry, args)
     return lang_base.run_xargs(
@@ -29,4 +30,5 @@ def run_hook(
         file_args,
         require_serial=require_serial,
         color=color,
+        pass_filenames_via_stdin=pass_filenames_via_stdin,
     )

pre_commit/languages/fail.py

@@ -21,6 +21,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:
     out = f'{entry}\n\n'.encode()
     out += b'\n'.join(f.encode() for f in file_args) + b'\n'

pre_commit/languages/julia.py

@@ -27,6 +27,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:
     # `entry` is a (hook-repo relative) file followed by (optional) args, e.g.
     # `bin/id.jl` or `bin/hook.jl --arg1 --arg2` so we
@@ -43,6 +44,7 @@ def run_hook(
         file_args,
         require_serial=require_serial,
         color=color,
+        pass_filenames_via_stdin=pass_filenames_via_stdin,
     )
 
 

pre_commit/languages/pygrep.py

@@ -96,8 +96,12 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:
     cmd = (sys.executable, '-m', __name__, *args, entry)
+    if pass_filenames_via_stdin:
+        stdin = lang_base.to_nul_delimited_filenames(file_args)
+        return xargs(cmd, (), color=color, input=stdin)
     return xargs(cmd, file_args, color=color)
 
 
@@ -116,6 +120,11 @@ def main(argv: Sequence[str] | None = None) -> int:
     parser.add_argument('filenames', nargs='*')
     args = parser.parse_args(argv)
 
+    if not args.filenames:
+        stdin = sys.stdin.buffer.read()
+        if stdin:
+            args.filenames = lang_base.from_nul_delimited_filenames(stdin)
+
     flags = re.IGNORECASE if args.ignore_case else 0
     if args.multiline:
         flags |= re.MULTILINE | re.DOTALL

pre_commit/languages/r.py

@@ -268,6 +268,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:
     cmd = _cmd_from_hook(prefix, entry, args, is_local=is_local)
     return lang_base.run_xargs(
@@ -275,4 +276,5 @@ def run_hook(
         file_args,
         require_serial=require_serial,
         color=color,
+        pass_filenames_via_stdin=pass_filenames_via_stdin,
     )

pre_commit/languages/unsupported_script.py

@@ -21,6 +21,7 @@ def run_hook(
         is_local: bool,
         require_serial: bool,
         color: bool,
+        pass_filenames_via_stdin: bool = False,
 ) -> tuple[int, bytes]:
     cmd = lang_base.hook_cmd(entry, args)
     cmd = (prefix.path(cmd[0]), *cmd[1:])
@@ -29,4 +30,5 @@ def run_hook(
         file_args,
         require_serial=require_serial,
         color=color,
+        pass_filenames_via_stdin=pass_filenames_via_stdin,
     )