FabledCurator/tests/test_backup_service.py

"""FC-3h: backup_service unit tests.

Subprocess calls (pg_dump, tar, psql) are monkeypatched so tests run
without external binaries. The real subprocess behavior is exercised
implicitly via the Celery task tests in test_tasks_backup.py.
"""
import json
import subprocess
from pathlib import Path

import pytest

from backend.app.services import backup_service

pytestmark = pytest.mark.integration


@pytest.fixture
def fake_subprocess(monkeypatch):
    """Fake both subprocess.run (restore path) AND subprocess.Popen (the
    bounded-kill backup path) so tests run without external binaries. Each
    writes the target sentinel and records the cmd in a shared list."""
    calls = []

    class _FakeProc:
        returncode = 0
        stdout = b""
        stderr = b""

    def _write_sentinel(cmd):
        if cmd[0] == "pg_dump":
            i = cmd.index("-f")
            Path(cmd[i + 1]).write_bytes(b"-- fake pg_dump\n")
        elif cmd[0] == "tar" and "-cf" in cmd:
            i = cmd.index("-cf")
            Path(cmd[i + 1]).write_bytes(b"fake tar payload")

    def _fake_run(cmd, **kwargs):
        calls.append(list(cmd))
        _write_sentinel(cmd)
        return _FakeProc()

    class _FakePopen:
        def __init__(self, cmd, **kwargs):
            calls.append(list(cmd))
            self.returncode = 0
            _write_sentinel(cmd)

        def communicate(self, timeout=None):
            return (b"", b"")

        def kill(self):
            self.returncode = -9

    monkeypatch.setattr("subprocess.run", _fake_run)
    monkeypatch.setattr("subprocess.Popen", _FakePopen)
    return calls


# --- backup_db -------------------------------------------------------


def test_backup_db_writes_sql_and_manifest(tmp_path, fake_subprocess):
    result = backup_service.backup_db(
        db_url="postgresql://test@x/db",
        images_root=tmp_path,
        tag="pre-cutover",
        triggered_by="manual",
    )
    sql = Path(result["sql_path"])
    manifest = Path(result["manifest_path"])
    assert sql.is_file() and sql.suffix == ".dump"
    assert manifest.is_file() and manifest.suffix == ".json"
    assert result["kind"] == "db"
    assert result["tar_path"] is None
    assert result["size_bytes"] == len(b"-- fake pg_dump\n")

    parsed = json.loads(manifest.read_text())
    assert parsed["kind"] == "db"
    assert parsed["tag"] == "pre-cutover"
    assert parsed["triggered_by"] == "manual"
    assert parsed["artifact_path"] == str(sql)


def test_backup_db_strips_sqlalchemy_psycopg_driver(tmp_path, fake_subprocess):
    backup_service.backup_db(
        db_url="postgresql+psycopg://u:p@h/d", images_root=tmp_path,
    )
    cmd = fake_subprocess[0]
    assert cmd[0] == "pg_dump"
    assert cmd[-1].startswith("postgresql://")
    assert "+psycopg" not in cmd[-1]


def test_backup_db_uses_compressed_custom_format(tmp_path, fake_subprocess):
    # -Fc → pg_restore-loadable, compressed dump (#739 backup polish).
    backup_service.backup_db(db_url="postgresql://u@h/d", images_root=tmp_path)
    assert "-Fc" in fake_subprocess[0]


def test_backup_db_strips_asyncpg_driver(tmp_path, fake_subprocess):
    backup_service.backup_db(
        db_url="postgresql+asyncpg://u:p@h/d", images_root=tmp_path,
    )
    assert "+asyncpg" not in fake_subprocess[0][-1]


def test_backup_db_default_tag_is_none(tmp_path, fake_subprocess):
    result = backup_service.backup_db(
        db_url="postgresql://u@h/d", images_root=tmp_path,
    )
    parsed = json.loads(Path(result["manifest_path"]).read_text())
    assert parsed["tag"] is None


# --- backup_images ---------------------------------------------------


def test_backup_images_writes_tar_and_manifest(tmp_path, fake_subprocess):
    result = backup_service.backup_images(
        images_root=tmp_path, tag="monthly", triggered_by="manual",
    )
    tar = Path(result["tar_path"])
    assert tar.is_file() and tar.name.endswith(".tar.zst")
    assert result["sql_path"] is None
    assert result["size_bytes"] == len(b"fake tar payload")


def test_backup_images_excludes_backups_and_quarantine(tmp_path, fake_subprocess):
    backup_service.backup_images(images_root=tmp_path)
    cmd = fake_subprocess[0]
    excludes = [arg for arg in cmd if arg.startswith("--exclude=")]
    assert any("_backups" in e for e in excludes)
    assert any("_quarantine" in e for e in excludes)


# --- restore_db ------------------------------------------------------


def test_restore_db_drops_schema_then_loads(tmp_path, fake_subprocess):
    dump_path = tmp_path / "fake.dump"
    dump_path.write_bytes(b"\x00fake custom dump")
    backup_service.restore_db(
        db_url="postgresql://u@h/d", sql_path=dump_path,
    )
    # Two calls: psql -c (DROP SCHEMA), then pg_restore -d (load the dump).
    assert len(fake_subprocess) == 2
    assert fake_subprocess[0][0] == "psql"
    assert "-c" in fake_subprocess[0]
    assert "DROP SCHEMA IF EXISTS public CASCADE" in fake_subprocess[0][-1]
    assert fake_subprocess[1][0] == "pg_restore"
    assert "-d" in fake_subprocess[1]
    assert str(dump_path) in fake_subprocess[1]


# --- restore_images --------------------------------------------------


def test_restore_images_untar_to_parent(tmp_path, fake_subprocess):
    tar_path = tmp_path / "fake.tar.zst"
    tar_path.write_bytes(b"fake")
    backup_service.restore_images(images_root=tmp_path, tar_path=tar_path)
    cmd = fake_subprocess[0]
    assert cmd[:3] == ["tar", "--zstd", "-xf"]
    assert str(tar_path) in cmd
    assert "-C" in cmd


# --- unlink ----------------------------------------------------------


def test_unlink_removes_present_files_and_reports(tmp_path):
    sql = tmp_path / "x.sql"
    sql.write_bytes(b"x")
    tar = tmp_path / "x.tar.zst"
    tar.write_bytes(b"x")
    manifest = tmp_path / "x.json"
    manifest.write_text("{}")
    result = backup_service.unlink_artifact_files(
        sql_path=str(sql), tar_path=str(tar), manifest_path=str(manifest),
    )
    assert result == {"sql": True, "tar": True, "manifest": True}
    assert not sql.exists() and not tar.exists() and not manifest.exists()


def test_unlink_missing_files_returns_true(tmp_path):
    """missing_ok semantics: a non-existent file isn't an error."""
    result = backup_service.unlink_artifact_files(
        sql_path=str(tmp_path / "nope.sql"),
        tar_path=None, manifest_path=None,
    )
    assert result == {"sql": True}


def test_unlink_skips_none_paths():
    """A None path is skipped — not added to the result dict."""
    result = backup_service.unlink_artifact_files(
        sql_path=None, tar_path=None, manifest_path=None,
    )
    assert result == {}


# --- helpers ---------------------------------------------------------


def test_libpq_url_strips_each_known_driver():
    assert backup_service._libpq_url(
        "postgresql+psycopg://u@h/d"
    ) == "postgresql://u@h/d"
    assert backup_service._libpq_url(
        "postgresql+asyncpg://u@h/d"
    ) == "postgresql://u@h/d"
    assert backup_service._libpq_url(
        "postgresql+psycopg2://u@h/d"
    ) == "postgresql://u@h/d"
    # Plain URL passes through unchanged.
    assert backup_service._libpq_url(
        "postgresql://u@h/d"
    ) == "postgresql://u@h/d"


def test_backups_dir_created_on_first_use(tmp_path):
    d = backup_service._backups_dir(tmp_path)
    assert d.is_dir()
    assert d.name == "_backups"


# --- bounded-kill + local-temp (FC #739) -----------------------------


def test_backup_db_dumps_to_local_temp_not_nfs_backups_dir(tmp_path, fake_subprocess):
    """pg_dump must target a LOCAL temp path, not the (NFS) _backups dir —
    so its long phase can't hang uninterruptibly on an NFS write."""
    backup_service.backup_db(db_url="postgresql://u@h/d", images_root=tmp_path)
    cmd = fake_subprocess[0]
    dump_target = cmd[cmd.index("-f") + 1]
    assert "_backups" not in dump_target
    # The finished file still ends up in _backups (moved there).
    result = backup_service.backup_db(
        db_url="postgresql://u@h/d", images_root=tmp_path,
    )
    assert "_backups" in result["sql_path"]


def test_run_bounded_fails_fast_when_unkillable(monkeypatch):
    """A child stuck in D-state (communicate keeps timing out even after kill)
    must NOT block the reaper — _run_bounded kills then re-raises promptly."""
    killed = {"n": 0}

    class _Hang:
        def __init__(self, cmd, **kwargs):
            pass

        def communicate(self, timeout=None):
            raise subprocess.TimeoutExpired(cmd="x", timeout=timeout or 0)

        def kill(self):
            killed["n"] += 1

    monkeypatch.setattr("subprocess.Popen", _Hang)
    with pytest.raises(subprocess.TimeoutExpired):
        backup_service._run_bounded(["pg_dump"], 1)
    assert killed["n"] == 1