225 lines
6.0 KiB
Python
225 lines
6.0 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
import os
|
|
import shutil
|
|
import pymysql
|
|
import re
|
|
from pathlib import Path
|
|
from datetime import datetime
|
|
from collections import defaultdict
|
|
|
|
# ==============================
|
|
# ⚙️ 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\MP")
|
|
BASE_DIR.mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
# ==============================
|
|
# 🔧 HELPERS
|
|
# ==============================
|
|
|
|
def sanitize_name(name: str) -> str:
|
|
"""Replace invalid Windows filename characters."""
|
|
return re.sub(r'[<>:"/\\|?*\x00-\x1F]', "_", name).strip()
|
|
|
|
|
|
def make_abbrev(title: str) -> str:
|
|
"""Create abbreviation from title."""
|
|
if not title:
|
|
return ""
|
|
words = re.findall(r"[A-Za-zÁ-Žá-ž0-9]+", title)
|
|
abbr = ""
|
|
for w in words:
|
|
if w.isdigit():
|
|
abbr += w
|
|
else:
|
|
abbr += w[0]
|
|
return abbr.upper()
|
|
|
|
|
|
def clean_folder(folder: Path, valid_files: set):
|
|
"""Remove unexpected files except ▲ files."""
|
|
if not folder.exists():
|
|
return
|
|
|
|
for f in folder.iterdir():
|
|
if f.is_file():
|
|
if f.name.startswith("▲"):
|
|
continue
|
|
sanitized = sanitize_name(f.name)
|
|
if sanitized 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 only requests with NEW attachments…")
|
|
|
|
cur_meta.execute("""
|
|
SELECT
|
|
p.id AS request_id,
|
|
p.displayTitle,
|
|
p.pacient_jmeno,
|
|
p.pacient_prijmeni,
|
|
p.updatedAt,
|
|
p.attachmentsProcessed,
|
|
d.filename,
|
|
d.created_at
|
|
FROM pozadavky p
|
|
JOIN medevio_downloads d ON d.request_id = p.id
|
|
LEFT JOIN (
|
|
SELECT request_id, MAX(created_at) AS last_attachment_ts
|
|
FROM medevio_downloads
|
|
GROUP BY request_id
|
|
) x ON x.request_id = p.id
|
|
WHERE p.attachmentsProcessed IS NULL
|
|
OR p.attachmentsProcessed < x.last_attachment_ts
|
|
ORDER BY p.updatedAt DESC;
|
|
""")
|
|
|
|
rows = cur_meta.fetchall()
|
|
print(f"📋 Found {len(rows)} attachment rows belonging to requests needing processing.\n")
|
|
|
|
# ==============================
|
|
# 🧠 PREPARE REQUEST GROUPING
|
|
# ==============================
|
|
|
|
grouped = defaultdict(list)
|
|
for r in rows:
|
|
grouped[r["request_id"]].append(r)
|
|
|
|
unique_request_ids = list(grouped.keys())
|
|
total_requests = len(unique_request_ids)
|
|
|
|
print(f"🔄 Processing {total_requests} requests needing updates…\n")
|
|
|
|
# ==============================
|
|
# 🧠 MAIN LOOP
|
|
# ==============================
|
|
|
|
index = 0
|
|
|
|
for req_id in unique_request_ids:
|
|
index += 1
|
|
pct = (index / total_requests) * 100
|
|
|
|
print(f"\n[ {pct:5.1f}% ] Processing request {index}/{total_requests} → {req_id}")
|
|
|
|
req_rows = grouped[req_id]
|
|
first = req_rows[0]
|
|
|
|
# Build folder name
|
|
updated_at = first["updatedAt"] or datetime.now()
|
|
date_str = updated_at.strftime("%Y-%m-%d")
|
|
|
|
prijmeni = sanitize_name(first["pacient_prijmeni"] or "Unknown")
|
|
jmeno = sanitize_name(first["pacient_jmeno"] or "")
|
|
abbr = make_abbrev(first["displayTitle"])
|
|
|
|
desired_folder_name = sanitize_name(f"{date_str} {prijmeni}, {jmeno} [{abbr}] {req_id}")
|
|
|
|
# Detect existing folder for request
|
|
main_folder = None
|
|
for f in BASE_DIR.iterdir():
|
|
if f.is_dir() and req_id in f.name:
|
|
main_folder = f
|
|
break
|
|
|
|
if not main_folder:
|
|
main_folder = BASE_DIR / desired_folder_name
|
|
|
|
main_folder.mkdir(parents=True, exist_ok=True)
|
|
|
|
# Build valid filename set
|
|
valid_files = {sanitize_name(r["filename"]) for r in req_rows}
|
|
|
|
# Clean unexpected non-▲ files
|
|
clean_folder(main_folder, valid_files)
|
|
|
|
# Track if ANY new files were downloaded
|
|
added_new_file = False
|
|
|
|
# DOWNLOAD MISSING FILES
|
|
for r in req_rows:
|
|
filename = sanitize_name(r["filename"])
|
|
dest_plain = main_folder / filename
|
|
dest_flag = main_folder / ("▲" + filename)
|
|
|
|
# Skip if file already exists (plain or ▲)
|
|
if dest_plain.exists() or dest_flag.exists():
|
|
continue
|
|
|
|
# Fetch content
|
|
cur_blob.execute("""
|
|
SELECT file_content
|
|
FROM medevio_downloads
|
|
WHERE request_id=%s AND filename=%s
|
|
""", (req_id, r["filename"]))
|
|
|
|
row = cur_blob.fetchone()
|
|
if not row or not row[0]:
|
|
continue
|
|
|
|
with open(dest_plain, "wb") as f:
|
|
f.write(row[0])
|
|
|
|
print(f"💾 Wrote: {dest_plain.relative_to(BASE_DIR)}")
|
|
added_new_file = True
|
|
|
|
# ------------------------------------
|
|
# 🟦 FOLDER ▲ LOGIC (IMPORTANT)
|
|
# ------------------------------------
|
|
if added_new_file:
|
|
# If folder contains ▲ in its name → remove it
|
|
if "▲" in main_folder.name:
|
|
new_name = main_folder.name.replace("▲", "").strip()
|
|
new_path = main_folder.parent / new_name
|
|
|
|
try:
|
|
main_folder.rename(new_path)
|
|
print(f"🔄 Folder flag ▲ removed → {new_name}")
|
|
main_folder = new_path
|
|
except Exception as e:
|
|
print(f"⚠️ Could not rename folder: {e}")
|
|
else:
|
|
# NO new files → NEVER rename folder
|
|
pass
|
|
|
|
# Mark request as processed
|
|
cur_meta.execute(
|
|
"UPDATE pozadavky SET attachmentsProcessed = NOW() WHERE id=%s",
|
|
(req_id,)
|
|
)
|
|
conn.commit()
|
|
|
|
# ==============================
|
|
# 🏁 DONE
|
|
# ==============================
|
|
|
|
print("\n🎯 Export complete.\n")
|
|
cur_blob.close()
|
|
cur_meta.close()
|
|
conn.close()
|