searxng-use-cli/tests/test_instance_resolution.py

"""Tests for scripts/search.py — instance resolution chain.

Covers:
  * ``_load_toml`` — TOML file loading (Python 3.11+ tomllib / 3.8-3.10 tomli)
  * ``_read_instance_file`` — config file parsing (.toml single/list/table,
    .txt per-line / comments / comma-separated / blanks, missing file,
    corrupted toml)
  * ``resolve_instances`` — priority chain (CLI > env > config file > empty)
    and config-file auto-discovery (cwd/home, .toml before .txt)

Tests are hermetic: cwd and home are redirected to ``tmp_path`` via
monkeypatch so the real user environment never interferes.
"""
import pytest
from pathlib import Path

from search import _load_toml, _read_instance_file, resolve_instances


# ----- _load_toml -----

def test_load_toml_valid_file(tmp_path):
    f = tmp_path / "test.toml"
    f.write_text('key = "value"\nnumber = 42\n', encoding="utf-8")
    data = _load_toml(f)
    assert data["key"] == "value"
    assert data["number"] == 42


def test_load_toml_returns_dict(tmp_path):
    f = tmp_path / "test.toml"
    f.write_text('instance = "https://x.example.com"\n', encoding="utf-8")
    data = _load_toml(f)
    assert isinstance(data, dict)


# ----- _read_instance_file: .toml -----

def test_read_toml_single_instance(tmp_path):
    """Top-level instance = "url" → parse_instances single URL."""
    f = tmp_path / "searxng.toml"
    f.write_text('instance = "https://x.example.com"\n', encoding="utf-8")
    assert _read_instance_file(f) == ["https://x.example.com"]


def test_read_toml_instances_list(tmp_path):
    """Top-level instances = ["a", "b"] → normalized list."""
    f = tmp_path / "searxng.toml"
    f.write_text('instances = ["a.com", "b.com"]\n', encoding="utf-8")
    assert _read_instance_file(f) == ["https://a.com", "https://b.com"]


def test_read_toml_searxng_table_instance(tmp_path):
    """Instance under [searxng] table is read correctly."""
    f = tmp_path / "searxng.toml"
    f.write_text('[searxng]\ninstance = "https://t.example.com"\n',
                 encoding="utf-8")
    assert _read_instance_file(f) == ["https://t.example.com"]


def test_read_corrupted_toml_returns_empty(tmp_path):
    """Corrupted (unparseable) toml → empty list, no exception raised."""
    f = tmp_path / "bad.toml"
    f.write_text("[searxng\ninstance = broken\n", encoding="utf-8")
    assert _read_instance_file(f) == []


# ----- _read_instance_file: .txt -----

def test_read_txt_one_url_per_line(tmp_path):
    f = tmp_path / "instances.txt"
    f.write_text("https://a.com\nhttps://b.com\n", encoding="utf-8")
    assert _read_instance_file(f) == ["https://a.com", "https://b.com"]


def test_read_txt_skips_comments(tmp_path):
    f = tmp_path / "instances.txt"
    f.write_text("# comment\nhttps://a.com\n# another\nhttps://b.com\n",
                 encoding="utf-8")
    assert _read_instance_file(f) == ["https://a.com", "https://b.com"]


def test_read_txt_comma_separated(tmp_path):
    """Comma-separated URLs on one line are split."""
    f = tmp_path / "instances.txt"
    f.write_text("a.com,b.com\n", encoding="utf-8")
    assert _read_instance_file(f) == ["https://a.com", "https://b.com"]


def test_read_txt_skips_blank_lines(tmp_path):
    f = tmp_path / "instances.txt"
    f.write_text("https://a.com\n\n\nhttps://b.com\n", encoding="utf-8")
    assert _read_instance_file(f) == ["https://a.com", "https://b.com"]


# ----- _read_instance_file: edge cases -----

def test_read_nonexistent_file_returns_empty(tmp_path):
    """Missing file → empty list (FileNotFoundError caught internally)."""
    f = tmp_path / "nonexistent.toml"
    assert _read_instance_file(f) == []


# ----- resolve_instances: priority chain -----

def test_resolve_cli_arg_takes_priority_over_env(monkeypatch, tmp_path):
    """CLI arg wins even when SEARXNG_INSTANCE env var is set."""
    monkeypatch.setenv("SEARXNG_INSTANCE", "https://env.example.com")
    assert resolve_instances("https://cli.example.com") == ["https://cli.example.com"]


def test_resolve_env_takes_priority_over_config_file(monkeypatch, tmp_path):
    """Env var wins over a present config file."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    (tmp_path / "searxng.toml").write_text(
        'instance = "https://file.example.com"\n', encoding="utf-8")
    monkeypatch.setenv("SEARXNG_INSTANCE", "https://env.example.com")
    assert resolve_instances(None) == ["https://env.example.com"]


def test_resolve_no_source_returns_empty(monkeypatch, tmp_path):
    """No CLI, no env, no config file → empty list."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    assert resolve_instances(None) == []


def test_resolve_cli_none_falls_back_to_env(monkeypatch, tmp_path):
    """cli_arg=None → use SEARXNG_INSTANCE env var."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.setenv("SEARXNG_INSTANCE", "https://env.example.com")
    assert resolve_instances(None) == ["https://env.example.com"]


def test_resolve_no_env_falls_back_to_config_file(monkeypatch, tmp_path):
    """No CLI, no env → fall back to config file."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    (tmp_path / "searxng.toml").write_text(
        'instance = "https://file.example.com"\n', encoding="utf-8")
    assert resolve_instances(None) == ["https://file.example.com"]


# ----- resolve_instances: config file discovery -----

def test_resolve_discovers_cwd_searxng_toml(monkeypatch, tmp_path):
    """./searxng.toml is auto-discovered."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    (tmp_path / "searxng.toml").write_text(
        'instance = "https://cwd.example.com"\n', encoding="utf-8")
    assert resolve_instances(None) == ["https://cwd.example.com"]


def test_resolve_discovers_home_searxng_toml(monkeypatch, tmp_path):
    """~/.config/searxng-cli/searxng.toml is auto-discovered."""
    monkeypatch.chdir(tmp_path)  # cwd has no config file
    home = tmp_path / "fake_home"
    cfg_dir = home / ".config" / "searxng-cli"
    cfg_dir.mkdir(parents=True)
    (cfg_dir / "searxng.toml").write_text(
        'instance = "https://home.example.com"\n', encoding="utf-8")
    monkeypatch.setattr(Path, "home", lambda: home)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    assert resolve_instances(None) == ["https://home.example.com"]


def test_resolve_discovers_cwd_instances_txt(monkeypatch, tmp_path):
    """./instances.txt is auto-discovered when no .toml present."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    (tmp_path / "instances.txt").write_text("https://txt.example.com\n",
                                            encoding="utf-8")
    assert resolve_instances(None) == ["https://txt.example.com"]


def test_resolve_prefers_toml_over_txt(monkeypatch, tmp_path):
    """When both ./searxng.toml and ./instances.txt exist, .toml wins."""
    monkeypatch.chdir(tmp_path)
    monkeypatch.setattr(Path, "home", lambda: tmp_path)
    monkeypatch.delenv("SEARXNG_INSTANCE", raising=False)
    (tmp_path / "searxng.toml").write_text(
        'instance = "https://toml.example.com"\n', encoding="utf-8")
    (tmp_path / "instances.txt").write_text("https://txt.example.com\n",
                                            encoding="utf-8")
    result = resolve_instances(None)
    assert result == ["https://toml.example.com"]