"""Tests: Index-Bau (Chunking, FTS, Metadaten, Schema-Gates)."""
import sqlite3

import pytest

from agent.ingest import SCHEMA, build_index
from agent.kb import KbValidationError


def test_build_index_chunks_and_fts(mini_index):
    con = sqlite3.connect(mini_index.db_path)
    try:
        n_chunks = con.execute("SELECT COUNT(*) FROM chunks").fetchone()[0]
        n_fts = con.execute("SELECT COUNT(*) FROM chunks_fts").fetchone()[0]
        n_entries = con.execute(
            "SELECT COUNT(DISTINCT entry_id) FROM chunks"
        ).fetchone()[0]
        assert n_entries == 3
        assert n_chunks == n_fts and n_chunks >= 7
        row = con.execute(
            "SELECT entry_id, section, norm FROM chunks WHERE entry_id='lb-min-01' "
            "AND section LIKE 'Kernwerte%'"
        ).fetchone()
        assert row is not None
        # Umlaut-Folding im FTS-Text: "Lohnausgleich" normalisiert auffindbar
        assert "lohnausgleich" in row[2]
        meta = dict(con.execute("SELECT key, value FROM meta").fetchall())
        assert meta["n_entries"] == "3"
        assert meta["embed_model"] == ""  # embed_off=True
    finally:
        con.close()


def test_norm_contains_tags_and_legal_bases(mini_index):
    con = sqlite3.connect(mini_index.db_path)
    try:
        norm = con.execute(
            "SELECT norm FROM chunks WHERE entry_id='lb-min-01' "
            "AND section='Zusammenfassung'"
        ).fetchone()[0]
        assert "alvg" in norm  # legal_bases im FTS-Text
        assert "azg" in norm and "19e" in norm
    finally:
        con.close()


def test_rebuild_is_idempotent(mini_index):
    stats = build_index(mini_index)
    assert stats.n_entries == 3
    con = sqlite3.connect(mini_index.db_path)
    try:
        assert con.execute("SELECT COUNT(*) FROM chunks").fetchone()[0] == stats.n_chunks
    finally:
        con.close()


def test_build_index_aborts_on_gate_error(mini_cfg):
    """Gate-Fehler (Registry kaputt) bricht den Ingest ab — kein halber Index."""
    from pathlib import Path

    (Path(mini_cfg.kb_dir) / "kb.json").write_text(
        '{"n_entries": 0, "entries": []}', encoding="utf-8"
    )
    with pytest.raises(KbValidationError):
        build_index(mini_cfg)


def test_vectors_table_cached_across_rebuilds(mini_index):
    """Die Vektoren-Tabelle bleibt beim Rebuild erhalten (Cache-Garantie)."""
    con = sqlite3.connect(mini_index.db_path)
    try:
        con.execute(
            "INSERT INTO vectors(content_hash, model, dim, vec) "
            "VALUES ('deadbeef', 'bge-m3', 2, x'000000003f800000')"
        )  # 0.0, 1.0
        con.commit()
    finally:
        con.close()
    build_index(mini_index)
    con = sqlite3.connect(mini_index.db_path)
    try:
        assert con.execute(
            "SELECT COUNT(*) FROM vectors WHERE content_hash='deadbeef'"
        ).fetchone()[0] == 1
    finally:
        con.close()


def test_schema_creates_fts5(tmp_path):
    con = sqlite3.connect(tmp_path / "s.db")
    try:
        con.executescript(SCHEMA)
        con.execute("INSERT INTO chunks_fts(rowid, norm) VALUES (1, 'testtext')")
        hits = con.execute(
            "SELECT rowid FROM chunks_fts WHERE chunks_fts MATCH '\"testtext\"'"
        ).fetchall()
        assert hits == [(1,)]
    finally:
        con.close()