"""Reusable vectors keyed by the exact input and model fingerprint."""
import hashlib
import json
import sqlite3
from contextlib import closing
from pathlib import Path

import numpy as np


def cache_key(profile: dict, text: str) -> str:
    return hashlib.sha256(json.dumps({'profile': profile['fingerprint'], 'text': text},
        ensure_ascii=False, sort_keys=True).encode()).hexdigest()


class EmbeddingCache:
    def __init__(self, path: Path):
        self.path = Path(path)
        self.path.parent.mkdir(parents=True, exist_ok=True)
        with closing(sqlite3.connect(self.path)) as conn, conn:
            conn.execute('''CREATE TABLE IF NOT EXISTS embeddings (
                key TEXT PRIMARY KEY, dimensions INTEGER NOT NULL, vector BLOB NOT NULL,
                vector_sha256 TEXT NOT NULL)''')

    def load(self, keys: list[str]) -> dict[str, np.ndarray]:
        found = {}
        with closing(sqlite3.connect(self.path)) as conn:
            for key in set(keys):
                row = conn.execute('SELECT dimensions,vector,vector_sha256 FROM embeddings WHERE key=?', (key,)).fetchone()
                if not row or hashlib.sha256(row[1]).hexdigest() != row[2]:
                    continue
                vector = np.frombuffer(row[1], dtype=np.float32)
                if len(vector) == row[0] and np.isfinite(vector).all() and np.linalg.norm(vector) > 0:
                    found[key] = vector.copy()
        return found

    def save(self, vectors: dict[str, np.ndarray]):
        with closing(sqlite3.connect(self.path)) as conn, conn:
            for key, vector in vectors.items():
                blob = np.asarray(vector, dtype=np.float32).tobytes()
                conn.execute('INSERT OR REPLACE INTO embeddings VALUES(?,?,?,?)',
                    (key, len(vector), blob, hashlib.sha256(blob).hexdigest()))