#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""probe_constituent.py — 单元3 前置: 探查成份股两源 schema (写 migrate 前必须看清)。

1. bs_index_constituent (DB, baostock 300/500/50 历史): cols/rows/distinct index_code/抽样
2. data/index_const_hist/*.parquet (akshare cni 深证 union): 文件列表 + 每个 shape/cols/抽样
"""
import glob
import os
import sqlite3

import pandas as pd

DB = r"C:\sanguo_vnpy_v2\data\quant_trading.db"
HIST = r"C:\sanguo_vnpy_v2\data\index_const_hist"

c = sqlite3.connect(DB, timeout=60)
c.execute("PRAGMA busy_timeout = 60000")
cols = [r[1] for r in c.execute("PRAGMA table_info(bs_index_constituent)")]
print("[bs_index_constituent] cols:", cols)
print("  rows:", c.execute("SELECT COUNT(*) FROM bs_index_constituent").fetchone()[0])
idx = [r[0] for r in c.execute(
    "SELECT DISTINCT index_code FROM bs_index_constituent ORDER BY index_code")]
print("  distinct index_code:", idx)
print("  distinct updateDate count:", c.execute(
    "SELECT COUNT(DISTINCT updateDate) FROM bs_index_constituent").fetchone()[0])
print("  sample rows:", c.execute(
    "SELECT * FROM bs_index_constituent LIMIT 3").fetchall())
c.close()

print("\n[index_const_hist parquets]")
files = sorted(glob.glob(os.path.join(HIST, "*.parquet")))
print("files:", [os.path.basename(f) for f in files])
for f in files:
    df = pd.read_parquet(f)
    print(f"  {os.path.basename(f)}: shape={df.shape} cols={list(df.columns)}")
    print(f"    head:\n{df.head(2).to_string()}")