"""Check if article_date also has YYYY-01-01 issue"""
import asyncio, httpx, lxml.etree as ET
from datetime import date
from sqlalchemy import text
from sqlalchemy.ext.asyncio import create_async_engine

DATABASE_URL = 'postgresql+asyncpg://scilit:scilit_prod_2026@postgres:5432/scilit'

async def main():
    engine = create_async_engine(DATABASE_URL)
    async with engine.connect() as conn:
        # 1. Count article_date YYYY-01-01
        r = await conn.execute(text("""
            SELECT COUNT(*) FROM global_literature WHERE article_date IS NOT NULL 
            AND EXTRACT(MONTH FROM article_date)=1 AND EXTRACT(DAY FROM article_date)=1
        """))
        ad_jan01 = r.scalar()
        r = await conn.execute(text("SELECT COUNT(*) FROM global_literature WHERE article_date IS NOT NULL"))
        ad_total = r.scalar()
        print(f'article_date Jan-01: {ad_jan01} / {ad_total} total ({(ad_jan01/ad_total*100) if ad_total else 0:.1f}%)')
        
        # 2. Count records where pub_date is YYYY-01-01 but article_date is not
        r = await conn.execute(text("""
            SELECT COUNT(*) FROM global_literature 
            WHERE EXTRACT(MONTH FROM pub_date)=1 AND EXTRACT(DAY FROM pub_date)=1
            AND article_date IS NOT NULL 
            AND NOT (EXTRACT(MONTH FROM article_date)=1 AND EXTRACT(DAY FROM article_date)=1)
        """))
        fixed_but_ad_not = r.scalar()
        print(f'pub_date Jan-01 but article_date has real date: {fixed_but_ad_not}')
        
        # 3. Count by year for article_date Jan-01
        r = await conn.execute(text("""
            SELECT EXTRACT(YEAR FROM article_date) as y, COUNT(*) as c FROM global_literature
            WHERE article_date IS NOT NULL AND EXTRACT(MONTH FROM article_date)=1 AND EXTRACT(DAY FROM article_date)=1
            GROUP BY y ORDER BY y DESC LIMIT 10
        """))
        print('\narticle_date Jan-01 by year:')
        for row in r:
            print(f'  {int(row.y)}: {row.c}')
        
        # 4. Check for any pub_date that's not YYYY-01-01 but pub_year differs from EXTRACT(YEAR FROM pub_date)
        r = await conn.execute(text("""
            SELECT COUNT(*) FROM global_literature
            WHERE pub_date IS NOT NULL AND pub_year IS NOT NULL
            AND pub_year != EXTRACT(YEAR FROM pub_date)
        """))
        year_mismatch = r.scalar()
        print(f'\npub_year != EXTRACT(YEAR FROM pub_date): {year_mismatch}')
        
        # 5. Check for orphan feeds (articles that don't exist)
        r = await conn.execute(text("""
            SELECT COUNT(*) FROM user_feed uf 
            LEFT JOIN global_literature gl ON uf.literature_id = gl.id
            WHERE gl.id IS NULL
        """))
        orphan_feeds = r.scalar()
        print(f'Orphan feeds (no matching literature): {orphan_feeds}')
        
        # 6. Check the articles that were backfilled (2018-2023) - do they have proper dates now?
        r = await conn.execute(text("""
            SELECT EXTRACT(YEAR FROM pub_date) as y, COUNT(*) as c FROM global_literature
            WHERE EXTRACT(YEAR FROM pub_date) BETWEEN 2018 AND 2023
            AND EXTRACT(MONTH FROM pub_date)=1 AND EXTRACT(DAY FROM pub_date)=1
            GROUP BY y ORDER BY y DESC
        """))
        print('\nBackfill years (2018-2023) still Jan-01:')
        for row in r:
            print(f'  {int(row.y)}: {row.c}')
        
    await engine.dispose()

asyncio.run(main())