"""Index-Bau: Layer-2-Einträge -> SQLite (FTS5-BM25 + Dense-Vektoren).

Chunking: H2-Sektion je Eintrag (Parent-Child: Retrieval auf Sektion,
Kontext = Sektion + Metadatenkopf). Die Vektoren-Tabelle ist ein Cache
(Content-Hash) und überlebt Rebuilds — ein Reindex bettet nur Neues ein.
"""
from __future__ import annotations

import hashlib
import json
import sqlite3
import time
from dataclasses import asdict, dataclass
from datetime import datetime, timezone
from pathlib import Path

import numpy as np

from .config import Config
from .kb import KBEntry, Section, load_kb
from .normalize import normalize_text

SCHEMA_VERSION = 1
EMBED_BATCH = 32

SCHEMA = """
CREATE TABLE IF NOT EXISTS meta (key TEXT PRIMARY KEY, value TEXT);
CREATE TABLE IF NOT EXISTS chunks (
    chunk_id INTEGER PRIMARY KEY,
    entry_id TEXT NOT NULL,
    section TEXT NOT NULL,
    text TEXT NOT NULL,
    norm TEXT NOT NULL,
    content_hash TEXT NOT NULL,
    title TEXT, work TEXT, chapter TEXT, topic TEXT,
    stand TEXT, batch INTEGER,
    tags TEXT, legal_bases TEXT, cross_refs TEXT,
    source_pdf TEXT, source_text TEXT
);
CREATE INDEX IF NOT EXISTS idx_chunks_entry ON chunks(entry_id);
CREATE VIRTUAL TABLE IF NOT EXISTS chunks_fts USING fts5(norm);
CREATE TABLE IF NOT EXISTS vectors (
    content_hash TEXT NOT NULL,
    model TEXT NOT NULL,
    dim INTEGER NOT NULL,
    vec BLOB NOT NULL,
    PRIMARY KEY (content_hash, model)
);
"""


@dataclass
class IndexStats:
    n_entries: int = 0
    n_chunks: int = 0
    n_embedded: int = 0
    embed_error: str | None = None
    duration_s: float = 0.0
    kb_dir: str = ""
    db_path: str = ""
    schema_version: int = SCHEMA_VERSION

    def as_dict(self) -> dict:
        return asdict(self)


def embed_text(title: str, section_title: str, text: str) -> str:
    """Einheitlicher Embedding-Input (Title + Abschnitt + Body)."""
    return f"{title}\n{section_title}\n\n{text}"


def content_hash_for(title: str, section_title: str, text: str) -> str:
    return hashlib.sha256(
        embed_text(title, section_title, text).encode("utf-8")
    ).hexdigest()


def norm_text_for(entry: KBEntry, section: Section) -> str:
    """FTS-Text: Titel + Abschnitt + Tags + Rechtsgrundlagen + Kapitel + Body."""
    parts = [
        entry.title,
        section.title,
        " ".join(entry.tags),
        " ".join(entry.legal_bases),
        entry.chapter,
        section.text,
    ]
    return normalize_text("\n".join(p for p in parts if p))


def _insert_chunk(con: sqlite3.Connection, entry: KBEntry, section: Section) -> int:
    h = content_hash_for(entry.title, section.title, section.text)
    cur = con.execute(
        """INSERT INTO chunks (
            entry_id, section, text, norm, content_hash,
            title, work, chapter, topic, stand, batch,
            tags, legal_bases, cross_refs, source_pdf, source_text
        ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
        (
            entry.id, section.title, section.text, norm_text_for(entry, section), h,
            entry.title, entry.work, entry.chapter, entry.topic, entry.stand,
            entry.batch,
            json.dumps(entry.tags, ensure_ascii=False),
            json.dumps(entry.legal_bases, ensure_ascii=False),
            json.dumps(entry.cross_refs, ensure_ascii=False),
            entry.source.get("pdf", ""), entry.source.get("text", ""),
        ),
    )
    chunk_id = cur.lastrowid
    con.execute(
        "INSERT INTO chunks_fts(rowid, norm) VALUES (?, ?)",
        (chunk_id, norm_text_for(entry, section)),
    )
    return chunk_id


def _embed_missing(cfg: Config, con: sqlite3.Connection, client) -> tuple[int, str | None]:
    """Bettet alle Chunk-Hashes ein, die für cfg.embed_model fehlen."""
    rows = con.execute(
        "SELECT DISTINCT content_hash, title, section, text FROM chunks"
    ).fetchall()
    unique: dict[str, str] = {}
    for h, title, section, text in rows:
        if h not in unique:
            unique[h] = embed_text(title, section, text)
    have = {
        r[0] for r in con.execute(
            "SELECT content_hash FROM vectors WHERE model = ?",
            (cfg.embed_model,),
        ).fetchall()
    }
    todo = [h for h in unique if h not in have]
    if not todo:
        return 0, None
    n = 0
    for i in range(0, len(todo), EMBED_BATCH):
        batch = todo[i:i + EMBED_BATCH]
        texts = [unique[h] for h in batch]
        try:
            embs = client.embed(cfg.embed_model, texts)
        except Exception as e:  # httpx/Ollama-Fehler -> BM25-only weiterlaufen
            return n, f"embedding failed at batch {i // EMBED_BATCH + 1}: {e}"
        for h, vec in zip(batch, embs):
            arr = np.asarray(vec, dtype=np.float32)
            con.execute(
                "INSERT OR REPLACE INTO vectors(content_hash, model, dim, vec) "
                "VALUES (?, ?, ?, ?)",
                (h, cfg.embed_model, int(arr.shape[0]), arr.tobytes()),
            )
            n += 1
    return n, None


def build_index(cfg: Config, client=None) -> IndexStats:
    """Vollständiger Rebuild von chunks/FTS; Vektoren-Cache bleibt erhalten."""
    t0 = time.perf_counter()
    entries = load_kb(cfg.kb_dir, verify_registry=True)
    db_path = Path(cfg.db_path)
    db_path.parent.mkdir(parents=True, exist_ok=True)
    stats = IndexStats(kb_dir=str(cfg.kb_dir), db_path=str(db_path))
    con = sqlite3.connect(db_path)
    try:
        con.executescript(SCHEMA)
        con.execute("DELETE FROM chunks")
        con.execute("DELETE FROM chunks_fts")
        con.execute("DELETE FROM meta")
        for entry in entries:
            for section in entry.sections:
                _insert_chunk(con, entry, section)
        con.commit()
        stats.n_entries = len(entries)
        stats.n_chunks = con.execute("SELECT COUNT(*) FROM chunks").fetchone()[0]

        if not cfg.embed_off:
            if client is None:
                from .ollama_client import OllamaClient
                client = OllamaClient(
                    cfg.ollama_url,
                    embed_timeout_s=cfg.embed_timeout_s,
                    chat_timeout_s=cfg.chat_timeout_s,
                )
            try:
                stats.n_embedded, stats.embed_error = _embed_missing(cfg, con, client)
            except Exception as e:
                stats.embed_error = f"{type(e).__name__}: {e}"

        con.executemany(
            "INSERT OR REPLACE INTO meta(key, value) VALUES (?, ?)",
            [
                ("schema_version", str(SCHEMA_VERSION)),
                ("built_at", datetime.now(timezone.utc).isoformat()),
                ("kb_dir", str(cfg.kb_dir)),
                ("embed_model", "" if cfg.embed_off else cfg.embed_model),
                ("n_entries", str(stats.n_entries)),
                ("n_chunks", str(stats.n_chunks)),
            ],
        )
        con.commit()
    finally:
        con.close()
    stats.duration_s = round(time.perf_counter() - t0, 2)
    return stats