"""Unit tests for search/aggregation.py"""
import sys
import os

_SEARCH_DIR = os.path.join(os.path.dirname(__file__), "..", "search")
sys.path.insert(0, _SEARCH_DIR)

os.environ.setdefault("EMBEDDINGS_DENSE_URL", "http://localhost/embed")
os.environ.setdefault("RERANKER_URL", "http://localhost/rerank")
os.environ.setdefault("QDRANT_URL", "http://localhost:6333")
os.environ.setdefault("API_KEY", "test-key")

from aggregation import aggregate_message_ids
from config import TOP_K


def _point(message_ids: list[str]):
    """Fake qdrant point with payload."""
    class FakePoint:
        payload = {"metadata": {"message_ids": message_ids}}
    return FakePoint()


class TestAggregateMessageIds:
    def test_empty_inputs(self):
        result = aggregate_message_ids([], [])
        assert result == []

    def test_basic_dedup(self):
        head = [_point(["m1", "m2"]), _point(["m2", "m3"])]
        result = aggregate_message_ids(head, [])
        assert result.count("m2") == 1

    def test_head_before_tail(self):
        head = [_point(["head_msg"])]
        tail = [_point(["tail_msg"])]
        result = aggregate_message_ids(head, tail)
        assert result.index("head_msg") < result.index("tail_msg")

    def test_top_k_limit(self):
        # Create enough points to exceed TOP_K
        points = [_point([f"m{i}"]) for i in range(TOP_K + 20)]
        result = aggregate_message_ids(points, [])
        assert len(result) <= TOP_K

    def test_cross_point_dedup(self):
        head = [_point(["shared"]), _point(["shared", "unique"])]
        result = aggregate_message_ids(head, [])
        assert result.count("shared") == 1
        assert "unique" in result

    def test_tail_fills_after_head(self):
        head = [_point(["h1"])]
        tail = [_point(["t1"]), _point(["t2"])]
        result = aggregate_message_ids(head, tail)
        assert "h1" in result
        assert "t1" in result
        assert "t2" in result