# 项目文件：crawler_project/src/catalogcrawl/state.py
# 页任务、详情任务与结果放进同一个 SQLite 文件，提交后才把任务标为完成。
import json
from pathlib import Path
import sqlite3

from bookdata.models import Book

from .errors import CrawlError
from .models import CollectedBook

SCHEMA = """
CREATE TABLE IF NOT EXISTS meta(key TEXT PRIMARY KEY, value TEXT NOT NULL);
CREATE TABLE IF NOT EXISTS pages(
    seq INTEGER PRIMARY KEY, url TEXT NOT NULL UNIQUE,
    done INTEGER NOT NULL DEFAULT 0 CHECK(done IN (0, 1)));
CREATE TABLE IF NOT EXISTS jobs(
    seq INTEGER PRIMARY KEY, url TEXT NOT NULL UNIQUE,
    done INTEGER NOT NULL DEFAULT 0 CHECK(done IN (0, 1)));
CREATE TABLE IF NOT EXISTS items(
    source_id TEXT PRIMARY KEY, title TEXT NOT NULL,
    finished INTEGER NOT NULL CHECK(finished IN (0, 1)),
    tags TEXT NOT NULL, source_url TEXT NOT NULL);
"""


class CrawlState:
    def __init__(self, path: Path, start_url=None):
        if start_url is None and not path.is_file():
            raise FileNotFoundError(f"还没有采集进度：{path}")
        path.parent.mkdir(parents=True, exist_ok=True)
        self.connection = sqlite3.connect(path)
        self.connection.row_factory = sqlite3.Row
        try:
            self.connection.executescript(SCHEMA)
            if start_url is not None:
                with self.connection:
                    row = self.connection.execute(
                        "SELECT value FROM meta WHERE key='start_url'"
                    ).fetchone()
                    if row is not None and row["value"] != start_url:
                        raise CrawlError(
                            "这份进度属于另一个目录入口，请为新目录选择新的进度文件"
                        )
                    self.connection.execute(
                        "INSERT OR IGNORE INTO meta VALUES ('start_url', ?)",
                        (start_url,),
                    )
                    self.connection.execute(
                        "INSERT OR IGNORE INTO pages(url) VALUES (?)", (start_url,)
                    )
        except BaseException:
            self.connection.close()
            raise

    def __enter__(self):
        return self

    def __exit__(self, *error):
        self.connection.close()