# -*- coding: utf-8 -*-
"""查询 ODS schema 的表、索引、关键列现状，输出到控制台。"""
import os
import sys
from pathlib import Path
from dotenv import load_dotenv
import psycopg2

# 加载 ETL .env
env_path = Path(__file__).resolve().parents[2] / "apps" / "etl" / "pipelines" / "feiqiu" / ".env"
load_dotenv(env_path)

dsn = os.environ.get("PG_DSN")
if not dsn:
    print("ERROR: PG_DSN 未配置")
    sys.exit(1)

conn = psycopg2.connect(dsn, connect_timeout=10)
cur = conn.cursor()

print("=" * 80)
print("1. ODS 所有表及行数")
print("=" * 80)
cur.execute("""
    SELECT t.tablename,
           pg_stat_user_tables.n_live_tup AS approx_rows
    FROM pg_tables t
    LEFT JOIN pg_stat_user_tables
        ON pg_stat_user_tables.schemaname = t.schemaname
        AND pg_stat_user_tables.relname = t.tablename
    WHERE t.schemaname = 'ods'
    ORDER BY t.tablename
""")
tables = cur.fetchall()
for tbl, rows in tables:
    print(f"  {tbl:50s}  ~{rows or 0} rows")

print(f"\n  共 {len(tables)} 张表")

print("\n" + "=" * 80)
print("2. ODS 所有索引")
print("=" * 80)
cur.execute("""
    SELECT tablename, indexname, indexdef
    FROM pg_indexes
    WHERE schemaname = 'ods'
    ORDER BY tablename, indexname
""")
indexes = cur.fetchall()
for tbl, idx_name, idx_def in indexes:
    print(f"  [{tbl}] {idx_name}")
    print(f"    {idx_def}")

print(f"\n  共 {len(indexes)} 个索引")

print("\n" + "=" * 80)
print("3. 各表是否有 id / fetched_at / is_delete / content_hash 列")
print("=" * 80)
cur.execute("""
    SELECT table_name, column_name
    FROM information_schema.columns
    WHERE table_schema = 'ods'
      AND column_name IN ('id', 'fetched_at', 'is_delete', 'content_hash')
    ORDER BY table_name, column_name
""")
col_rows = cur.fetchall()
# 按表聚合
from collections import defaultdict
col_map = defaultdict(set)
for tbl, col in col_rows:
    col_map[tbl].add(col)

check_cols = ['id', 'fetched_at', 'is_delete', 'content_hash']
print(f"  {'表名':50s} {'id':5s} {'fetched_at':12s} {'is_delete':10s} {'content_hash':13s}")
print(f"  {'-'*50} {'-'*5} {'-'*12} {'-'*10} {'-'*13}")
for tbl, _ in tables:
    cols = col_map.get(tbl, set())
    flags = [('✓' if c in cols else '✗') for c in check_cols]
    print(f"  {tbl:50s} {flags[0]:5s} {flags[1]:12s} {flags[2]:10s} {flags[3]:13s}")

print("\n" + "=" * 80)
print("4. 各表主键定义")
print("=" * 80)
cur.execute("""
    SELECT tc.table_name,
           string_agg(kcu.column_name, ', ' ORDER BY kcu.ordinal_position) AS pk_cols
    FROM information_schema.table_constraints tc
    JOIN information_schema.key_column_usage kcu
        ON tc.constraint_name = kcu.constraint_name
        AND tc.table_schema = kcu.table_schema
    WHERE tc.table_schema = 'ods'
      AND tc.constraint_type = 'PRIMARY KEY'
    GROUP BY tc.table_name
    ORDER BY tc.table_name
""")
pk_rows = cur.fetchall()
for tbl, pk_cols in pk_rows:
    print(f"  {tbl:50s} PK: ({pk_cols})")

cur.close()
conn.close()
print("\n完成。")