#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import os
import shutil
import pymysql
import re
from pathlib import Path
from datetime import datetime
import time

# ==============================
# ⚙️ CONFIGURATION
# ==============================
DB_CONFIG = {
    "host": "192.168.1.76",
    "port": 3307,
    "user": "root",
    "password": "Vlado9674+",
    "database": "medevio",
    "charset": "utf8mb4",
}

BASE_DIR = Path(r"u:\Dropbox\Ordinace\Dokumentace_ke_zpracování\MP1")
BASE_DIR.mkdir(parents=True, exist_ok=True)


def sanitize_name(name: str) -> str:
    """Replace invalid filename characters with underscore."""
    return re.sub(r'[<>:"/\\|?*\x00-\x1F]', "_", name).strip()


# ==============================
# 🧹 DELETE UNEXPECTED FILES
# ==============================
def clean_folder(folder: Path, valid_files: set):
    """Remove all files in folder that are NOT present in valid_files."""
    if not folder.exists():
        return

    for f in folder.iterdir():
        if f.is_file():
            if sanitize_name(f.name) not in valid_files:
                print(f"🗑️ Removing unexpected file: {f.name}")
                try:
                    f.unlink()
                except Exception as e:
                    print(f"⚠️ Could not delete {f}: {e}")


# ==============================
# 📦 DB CONNECTION
# ==============================
conn = pymysql.connect(**DB_CONFIG)

cur_meta = conn.cursor(pymysql.cursors.DictCursor)
cur_blob = conn.cursor()

print("🔍 Loading metadata from DB (FAST)…")

cur_meta.execute("""
    SELECT d.id AS download_id,
           d.request_id,
           d.filename,
           d.created_at,
           p.updatedAt AS req_updated_at,
           p.pacient_jmeno AS jmeno,
           p.pacient_prijmeni AS prijmeni
    FROM medevio_downloads d
    JOIN pozadavky p ON d.request_id = p.id
    ORDER BY p.updatedAt DESC
""")

rows = cur_meta.fetchall()
print(f"📋 Found {len(rows)} attachment records.\n")

# ==============================
# 🧠 MAIN LOOP
# ==============================
processed_requests = set()

for r in rows:
    req_id = r["request_id"]

    if req_id in processed_requests:
        continue
    processed_requests.add(req_id)

    # ========== FETCH ALL VALID FILES FOR THIS REQUEST ==========
    cur_meta.execute(
        "SELECT filename FROM medevio_downloads WHERE request_id=%s",
        (req_id,)
    )
    valid_files = {sanitize_name(row["filename"]) for row in cur_meta.fetchall()}

    # ========== FOLDER NAME BASED ON UPDATEDAT ==========
    updated_at = r["req_updated_at"] or datetime.now()
    date_str = updated_at.strftime("%Y-%m-%d")

    prijmeni = sanitize_name(r["prijmeni"] or "Unknown")
    jmeno = sanitize_name(r["jmeno"] or "")

    folder_name = f"{date_str} {prijmeni}, {jmeno} {req_id}"
    folder_name = sanitize_name(folder_name)
    main_folder = BASE_DIR / folder_name

    # ========== FIND OLD FOLDER (DUPLICATE) ==========
    # Any folder that contains "_<req_id>" and is not main_folder is duplicate
    possible_dups = [
        f for f in BASE_DIR.iterdir()
        if f.is_dir() and req_id in f.name and f != main_folder
    ]

    # ========== MERGE DUPLICATES ==========
    for dup in possible_dups:
        print(f"♻️ Merging duplicate folder: {dup.name}")

        # 1) Clean unexpected files in dup
        clean_folder(dup, valid_files)

        # 2) Move files from dup to main folder
        main_folder.mkdir(parents=True, exist_ok=True)

        for f in dup.iterdir():
            if f.is_file():
                target = main_folder / f.name
                if not target.exists():
                    f.rename(target)

        # 3) Remove the duplicate folder
        try:
            shutil.rmtree(dup, ignore_errors=True)
        except Exception as e:
            print(f"⚠️ Could not delete duplicate folder {dup}: {e}")

    # ========== CLEAN MAIN FOLDER ==========
    clean_folder(main_folder, valid_files)

    # ========== DOWNLOAD MISSING FILES ==========
    main_folder.mkdir(parents=True, exist_ok=True)

    for filename in valid_files:
        dest = main_folder / filename
        if dest.exists():
            continue

        # fetch blob only now
        start = time.perf_counter()
        cur_blob.execute(
            "SELECT file_content FROM medevio_downloads "
            "WHERE request_id=%s AND filename=%s",
            (req_id, filename)
        )
        row = cur_blob.fetchone()
        if not row:
            continue
        end = time.perf_counter()
        print(f"⏱ Took {end - start:.4f} seconds")

        content = row[0]
        if not content:
            continue

        with open(dest, "wb") as f:
            f.write(content)

        print(f"💾 Wrote: {dest.relative_to(BASE_DIR)}")

print("\n🎯 Export complete.\n")

cur_blob.close()
cur_meta.close()
conn.close()