"""Under `pipefail`, an early-exiting `head` must not void the output it kept (#4042).

The hooks run with `set -uo pipefail`. `hits=$(git grep -l … | head -4) ||
hits=""` lost its four hits whenever git grep was still writing when head
exited: SIGPIPE, a failed substitution, and the fallback wiped the result. It
only showed on big outputs, so the by-name duplicate arm went silent for
exactly the most-duplicated names.

Two halves: the real function on a repo big enough to overflow the pipe, and
the check_plugin pattern that keeps the shape out of every hook (shown able to
fail, rule #167).
"""
from __future__ import annotations

import os
import shutil
import subprocess
from pathlib import Path

import pytest

ROOT = Path(__file__).resolve().parents[1]
DEFS = ROOT / "plugin" / "hooks" / "scribe_defs.sh"


def test_the_duplicate_arm_still_names_a_name_defined_in_thousands_of_files(tmp_path):
    for tool in ("git", "bash"):
        if shutil.which(tool) is None:
            pytest.skip(f"{tool!r} not installed")
    env = {"PATH": os.environ["PATH"], "HOME": str(tmp_path),
           "GIT_AUTHOR_NAME": "t", "GIT_AUTHOR_EMAIL": "t@x",
           "GIT_COMMITTER_NAME": "t", "GIT_COMMITTER_EMAIL": "t@x"}
    repo = tmp_path / "repo"
    repo.mkdir()
    subprocess.run(["git", "init", "-q"], cwd=repo, check=True, env=env)
    # ~3000 × ~60 bytes of `git grep -l` output: well past a 64 KiB pipe buffer,
    # so git grep is still writing when head has its four lines.
    for i in range(3000):
        (repo / f"module_with_a_fairly_long_descriptive_name_{i}.py").write_text("def slug(t):\n    return t\n")
    subprocess.run(["git", "add", "."], cwd=repo, check=True, env=env)
    subprocess.run(["git", "commit", "-q", "-m", "base"], cwd=repo, check=True, env=env)

    script = f'set -uo pipefail\n. "{DEFS}"\nprintf "sym\\tslug\\n" | scribe_local_dups "{repo}" new.py\n'
    out = subprocess.run(["bash", "-c", script], capture_output=True, text=True, env=env, timeout=60)
    assert out.returncode == 0, out.stderr
    assert "`slug` is already defined in 4 other file(s)" in out.stdout


def test_the_lint_pattern_catches_the_shape_and_passes_the_fix():
    from scripts.check_plugin import PATTERNS

    pattern = next(p for p, label, _why in PATTERNS if label.startswith("early-exit consumer"))
    for bad in ('hits=$(git grep -l x | head -4) || hits=""',
                "    | grep -m1 -v '^[[:space:]]*$') || old_first=\"\"",
                'x=$(a | grep -q b) || x=""'):
        assert pattern.search(bad), bad
    for good in ('hits=$(git grep -l x | head -4 || true)',
                 'ln=$(grep -nF -m1 -- "$a" "$f" | cut -d: -f1) || ln=""'):
        assert not pattern.search(good), good