dp-zp-agent/tools/rag/tests/test_rebuild_index.py

from __future__ import annotations

import multiprocessing
import subprocess
from pathlib import Path

import pytest

import tools.rag.rebuild_index as rebuild
import tools.sync.wiki_git as wiki_git


def hold_lock(lock_path: str, ready, release) -> None:
    with rebuild.acquire_reindex_lock(Path(lock_path)):
        ready.set()
        release.wait(timeout=10)


def test_only_one_process_can_reindex(tmp_path: Path) -> None:
    lock_file = tmp_path / "reindex.lock"
    context = multiprocessing.get_context("fork")
    ready = context.Event()
    release = context.Event()
    process = context.Process(
        target=hold_lock,
        args=(str(lock_file), ready, release),
    )
    process.start()

    try:
        assert ready.wait(timeout=5)

        with pytest.raises(
            rebuild.ReindexInProgressError,
            match="už prebieha",
        ):
            with rebuild.acquire_reindex_lock(lock_file):
                pass
    finally:
        release.set()
        process.join(timeout=5)

    assert process.exitcode == 0

    with rebuild.acquire_reindex_lock(lock_file):
        pass


def test_rebuild_runs_pipeline_in_correct_order(
    tmp_path: Path,
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    calls: list[str] = []

    monkeypatch.setattr(
        rebuild,
        "git_pull",
        lambda root: calls.append("git_pull"),
    )
    import tools.sync.sync_indexes as sync

    monkeypatch.setattr(
        sync,
        "synchronize_indexes",
        lambda wiki, data: calls.append("sqlite_and_neo4j")
        or {
            "documents_scanned": 1,
            "chunks_created": 1,
            "counts": {"fts_chunks": 1},
            "index_version": {"version": "both"},
        },
    )

    result = rebuild.rebuild_index(
        pull_git=True,
        wiki_root=tmp_path / "wiki",
        data_dir=tmp_path / "data",
        lock_file=tmp_path / "lock",
    )

    assert calls == ["git_pull", "sqlite_and_neo4j"]
    assert result["documents_scanned"] == 1
    assert result["chunks_created"] == 1
    assert result["counts"]["fts_chunks"] == 1
    assert result["index_version"] == {"version": "both"}


def test_rebuild_pulls_and_locks_the_requested_snapshot_paths(tmp_path, monkeypatch):
    import tools.sync.sync_indexes as sync

    wiki = tmp_path / "alternate-wiki"
    data = tmp_path / "alternate-data"
    seen = []
    monkeypatch.setattr(rebuild, "git_pull", lambda root: seen.append(("pull", root)))

    def synchronized(root, target):
        assert (data / ".reindex.lock").exists()
        seen.append(("sync", root, target))
        return {"index_version": {"version": "alternate"}}

    monkeypatch.setattr(sync, "synchronize_indexes", synchronized)
    result = rebuild.rebuild_index(pull_git=True, wiki_root=wiki, data_dir=data)
    assert seen == [("pull", wiki), ("sync", wiki, data)]
    assert result["index_version"]["version"] == "alternate"


def test_git_pull_uses_explicit_branch_and_fast_forward_only(tmp_path, monkeypatch):
    repo = tmp_path / "repo"
    (repo / ".git").mkdir(parents=True)
    captured = []

    def fake_run(args, **kwargs):
        captured.append((args, kwargs))
        output = {
            "remote": "git@git.example:KEMT/zpwiki.git",
            "branch": "master",
            "status": "",
        }.get(args[1], "")
        return subprocess.CompletedProcess(args, 0, stdout=output, stderr="")

    monkeypatch.setattr(wiki_git.subprocess, "run", fake_run)
    monkeypatch.setenv("EXPECTED_GITEA_BRANCH", "master")
    rebuild.git_pull(repo)
    assert captured[-2][0] == [
        "git",
        "fetch",
        "--no-tags",
        "--no-recurse-submodules",
        "origin",
        "refs/heads/master:refs/remotes/origin/master",
    ]
    assert captured[-1][0] == ["git", "merge", "--ff-only", "refs/remotes/origin/master"]
    assert all(
        kw["cwd"] == repo and kw["timeout"] == 120 and kw["env"]["GIT_TERMINAL_PROMPT"] == "0"
        for _, kw in captured
    )


def test_git_pull_rejects_non_repository(tmp_path: Path) -> None:
    directory = tmp_path / "not-repo"
    directory.mkdir()

    with pytest.raises(RuntimeError, match="Nie je to git repozitár"):
        rebuild.git_pull(directory)


def test_git_pull_reports_timeout(
    tmp_path: Path,
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    repo = tmp_path / "repo"
    (repo / ".git").mkdir(parents=True)

    def timeout(*args, **kwargs):
        raise subprocess.TimeoutExpired(cmd="git pull", timeout=120)

    monkeypatch.setattr(wiki_git.subprocess, "run", timeout)

    with pytest.raises(RuntimeError, match="prekročila limit"):
        rebuild.git_pull(repo)


def test_git_pull_reports_nonzero_exit(
    tmp_path: Path,
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    repo = tmp_path / "repo"
    (repo / ".git").mkdir(parents=True)

    monkeypatch.setattr(
        wiki_git.subprocess,
        "run",
        lambda *args, **kwargs: subprocess.CompletedProcess(
            args[0],
            1,
            stdout="",
            stderr="chyba",
        ),
    )

    with pytest.raises(RuntimeError, match="návratovým kódom 1"):
        rebuild.git_pull(repo)