searxng-use-cli/tests/test_research_mode.py

"""Tests for v2.1.0 --research mode.

Covers:
  * expand_research_queries — topic → [(angle, query), ...] expansion
  * --research CLI flag     — mutex with --query/--queries-file, --stream
  * --research end-to-end   — subprocess with real CLI (stubbed at search_multi)
"""
import json
import os
import subprocess
import sys
from pathlib import Path

import pytest

sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "scripts"))

from search import expand_research_queries, _RESEARCH_ANGLES

PROJECT_ROOT = Path(__file__).resolve().parent.parent


# ===== expand_research_queries =====

class TestExpandResearchQueries:
    def test_basic_topic(self):
        queries = expand_research_queries("Python")
        assert len(queries) == 5
        # First angle is overview (no suffix)
        assert queries[0] == ("overview", "Python")
        # Each query starts with the topic
        for angle, q in queries:
            assert q.startswith("Python")

    def test_chinese_topic(self):
        queries = expand_research_queries("七森莉莉")
        assert len(queries) == 5
        assert queries[0] == ("overview", "七森莉莉")
        assert queries[1] == ("profile", "七森莉莉 简介")
        assert queries[2] == ("background", "七森莉莉 经历")
        assert queries[3] == ("works", "七森莉莉 作品")
        assert queries[4] == ("review", "七森莉莉 评价")

    def test_angles_match_definition(self):
        queries = expand_research_queries("test")
        angles = [a for a, _ in queries]
        assert angles == [a for a, _ in _RESEARCH_ANGLES]

    def test_empty_topic_returns_empty(self):
        assert expand_research_queries("") == []

    def test_whitespace_topic_returns_empty(self):
        assert expand_research_queries("   ") == []

    def test_topic_is_stripped(self):
        queries = expand_research_queries("  Python  ")
        assert queries[0] == ("overview", "Python")

    def test_deterministic(self):
        """Same topic always produces same queries (no randomness)."""
        q1 = expand_research_queries("Rust async")
        q2 = expand_research_queries("Rust async")
        assert q1 == q2

    def test_multi_word_topic(self):
        queries = expand_research_queries("Python asyncio tutorial")
        assert queries[0] == ("overview", "Python asyncio tutorial")
        assert "简介" in queries[1][1]


# ===== --research CLI mutex checks =====

def _run_cli(*args, env=None):
    """Run scripts/search.py as a real subprocess."""
    full_env = {**os.environ, **(env or {})}
    cmd = [sys.executable, str(PROJECT_ROOT / "scripts" / "search.py")] + list(args)
    return subprocess.run(
        cmd, cwd=str(PROJECT_ROOT),
        capture_output=True, text=True, encoding="utf-8", timeout=30,
        env=full_env,
    )


class TestResearchCLIMutex:
    def test_research_with_query_errors(self):
        """--research + --query → E_INPUT error."""
        r = _run_cli("--research", "topic", "-q", "query", "-i", "https://x.com")
        assert r.returncode != 0
        # Error goes to stdout in json mode, stderr in other modes
        combined = r.stdout + r.stderr
        assert "--research cannot be used with --query" in combined

    def test_research_with_queries_file_errors(self, tmp_path):
        """--research + --queries-file → E_INPUT error."""
        qf = tmp_path / "queries.txt"
        qf.write_text("test\n", encoding="utf-8")
        r = _run_cli("--research", "topic", "--queries-file", str(qf),
                     "-i", "https://x.com")
        assert r.returncode != 0
        combined = r.stdout + r.stderr
        assert "--research cannot be used with --queries-file" in combined

    def test_research_with_stream_errors(self):
        """--research + --stream → E_INPUT error."""
        r = _run_cli("--research", "topic", "--stream", "-i", "https://x.com")
        assert r.returncode != 0
        combined = r.stdout + r.stderr
        assert "--stream cannot be used with --research" in combined

    def test_research_alone_without_instance_errors(self):
        """--research without -i or config → E_CONFIG (instance required).

        Uses SEARXNG_INSTANCE= (empty) + a non-existent HOME to prevent
        config file auto-discovery from finding the project's searxng.toml.
        """
        r = _run_cli("--research", "topic",
                     env={"SEARXNG_INSTANCE": "",
                          "USERPROFILE": "/nonexistent",
                          "HOME": "/nonexistent"})
        assert r.returncode != 0


# ===== --research end-to-end (stubbed) =====

class TestResearchExpandOutput:
    """Verify that expand_research_queries produces the expected output shape
    that the CLI relies on."""

    def test_output_is_list_of_tuples(self):
        queries = expand_research_queries("test")
        assert isinstance(queries, list)
        for item in queries:
            assert isinstance(item, tuple)
            assert len(item) == 2
            assert isinstance(item[0], str)  # angle
            assert isinstance(item[1], str)  # query

    def test_all_angles_present(self):
        queries = expand_research_queries("test")
        angles = {a for a, _ in queries}
        assert angles == {"overview", "profile", "background", "works", "review"}

    def test_overview_has_no_suffix(self):
        """The overview angle should be just the topic itself."""
        queries = expand_research_queries("my topic")
        assert queries[0][1] == "my topic"