|
|
|
@@ -8,12 +8,29 @@ import re
|
|
|
|
from pathlib import Path
|
|
|
|
from pathlib import Path
|
|
|
|
from datetime import datetime
|
|
|
|
from datetime import datetime
|
|
|
|
import time
|
|
|
|
import time
|
|
|
|
|
|
|
|
import sys
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
|
|
|
|
# 🛡 SAFE PRINT FOR CP1250 / EMOJI
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
|
|
|
|
def safe_print(text: str = ""):
|
|
|
|
|
|
|
|
enc = sys.stdout.encoding or ""
|
|
|
|
|
|
|
|
if not enc.lower().startswith("utf"):
|
|
|
|
|
|
|
|
# Strip emoji and characters outside BMP for Task Scheduler
|
|
|
|
|
|
|
|
text = ''.join(ch for ch in text if ord(ch) < 65536)
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
|
|
|
print(text)
|
|
|
|
|
|
|
|
except UnicodeEncodeError:
|
|
|
|
|
|
|
|
# ASCII fallback
|
|
|
|
|
|
|
|
text = ''.join(ch for ch in text if ord(ch) < 128)
|
|
|
|
|
|
|
|
print(text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
# ⚙️ CONFIGURATION
|
|
|
|
# ⚙️ CONFIGURATION
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
DB_CONFIG = {
|
|
|
|
DB_CONFIG = {
|
|
|
|
"host": "127.0.0.1",
|
|
|
|
"host": "192.168.1.76",
|
|
|
|
"port": 3307,
|
|
|
|
"port": 3307,
|
|
|
|
"user": "root",
|
|
|
|
"user": "root",
|
|
|
|
"password": "Vlado9674+",
|
|
|
|
"password": "Vlado9674+",
|
|
|
|
@@ -31,24 +48,15 @@ def sanitize_name(name: str) -> str:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def make_abbrev(title: str) -> str:
|
|
|
|
def make_abbrev(title: str) -> str:
|
|
|
|
"""
|
|
|
|
|
|
|
|
Create abbreviation from displayTitle:
|
|
|
|
|
|
|
|
- First letter of each word
|
|
|
|
|
|
|
|
- Keep digits together
|
|
|
|
|
|
|
|
- Uppercase
|
|
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
if not title:
|
|
|
|
if not title:
|
|
|
|
return ""
|
|
|
|
return ""
|
|
|
|
|
|
|
|
|
|
|
|
words = re.findall(r"[A-Za-zÁ-Žá-ž0-9]+", title)
|
|
|
|
words = re.findall(r"[A-Za-zÁ-Žá-ž0-9]+", title)
|
|
|
|
|
|
|
|
|
|
|
|
abbr = ""
|
|
|
|
abbr = ""
|
|
|
|
for w in words:
|
|
|
|
for w in words:
|
|
|
|
if w.isdigit():
|
|
|
|
if w.isdigit():
|
|
|
|
abbr += w
|
|
|
|
abbr += w
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
abbr += w[0]
|
|
|
|
abbr += w[0]
|
|
|
|
|
|
|
|
|
|
|
|
return abbr.upper()
|
|
|
|
return abbr.upper()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -56,28 +64,20 @@ def make_abbrev(title: str) -> str:
|
|
|
|
# 🧹 DELETE UNEXPECTED FILES
|
|
|
|
# 🧹 DELETE UNEXPECTED FILES
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
def clean_folder(folder: Path, valid_files: set):
|
|
|
|
def clean_folder(folder: Path, valid_files: set):
|
|
|
|
"""
|
|
|
|
|
|
|
|
Remove unexpected files.
|
|
|
|
|
|
|
|
RULE:
|
|
|
|
|
|
|
|
- Files starting with `▲` are ALWAYS kept.
|
|
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
if not folder.exists():
|
|
|
|
if not folder.exists():
|
|
|
|
return
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
|
|
for f in folder.iterdir():
|
|
|
|
for f in folder.iterdir():
|
|
|
|
if f.is_file():
|
|
|
|
if f.is_file():
|
|
|
|
|
|
|
|
|
|
|
|
# zpracované soubory (▲filename.pdf) nikdy nemažeme
|
|
|
|
|
|
|
|
if f.name.startswith("▲"):
|
|
|
|
if f.name.startswith("▲"):
|
|
|
|
continue
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
|
|
sanitized = sanitize_name(f.name)
|
|
|
|
sanitized = sanitize_name(f.name)
|
|
|
|
if sanitized not in valid_files:
|
|
|
|
if sanitized not in valid_files:
|
|
|
|
print(f"🗑️ Removing unexpected file: {f.name}")
|
|
|
|
safe_print(f"🗑️ Removing unexpected file: {f.name}")
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
f.unlink()
|
|
|
|
f.unlink()
|
|
|
|
except Exception as e:
|
|
|
|
except Exception as e:
|
|
|
|
print(f"⚠️ Could not delete {f}: {e}")
|
|
|
|
safe_print(f"⚠️ Could not delete {f}: {e}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
@@ -88,30 +88,30 @@ conn = pymysql.connect(**DB_CONFIG)
|
|
|
|
cur_meta = conn.cursor(pymysql.cursors.DictCursor)
|
|
|
|
cur_meta = conn.cursor(pymysql.cursors.DictCursor)
|
|
|
|
cur_blob = conn.cursor()
|
|
|
|
cur_blob = conn.cursor()
|
|
|
|
|
|
|
|
|
|
|
|
print("🔍 Loading metadata from DB (FAST)…")
|
|
|
|
safe_print("🔍 Loading metadata from DB (FAST)…")
|
|
|
|
|
|
|
|
|
|
|
|
cur_meta.execute("""
|
|
|
|
cur_meta.execute("""
|
|
|
|
SELECT d.id AS download_id,
|
|
|
|
SELECT d.id AS download_id,
|
|
|
|
d.request_id,
|
|
|
|
d.request_id,
|
|
|
|
d.filename,
|
|
|
|
d.filename,
|
|
|
|
d.created_at,
|
|
|
|
d.created_at,
|
|
|
|
p.updatedAt AS req_updated_at,
|
|
|
|
p.updatedAt AS req_updated_at,
|
|
|
|
p.pacient_jmeno AS jmeno,
|
|
|
|
p.pacient_jmeno AS jmeno,
|
|
|
|
p.pacient_prijmeni AS prijmeni,
|
|
|
|
p.pacient_prijmeni AS prijmeni,
|
|
|
|
p.displayTitle
|
|
|
|
p.displayTitle
|
|
|
|
FROM medevio_downloads d
|
|
|
|
FROM medevio_downloads d
|
|
|
|
JOIN pozadavky p ON d.request_id = p.id
|
|
|
|
JOIN pozadavky p ON d.request_id = p.id
|
|
|
|
ORDER BY p.updatedAt DESC
|
|
|
|
WHERE d.downloaded_at IS NULL
|
|
|
|
|
|
|
|
ORDER BY p.updatedAt DESC
|
|
|
|
""")
|
|
|
|
""")
|
|
|
|
|
|
|
|
|
|
|
|
rows = cur_meta.fetchall()
|
|
|
|
rows = cur_meta.fetchall()
|
|
|
|
print(f"📋 Found {len(rows)} attachment records.\n")
|
|
|
|
safe_print(f"📋 Found {len(rows)} attachment records.\n")
|
|
|
|
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
# 🧠 MAIN LOOP WITH PROGRESS
|
|
|
|
# 🧠 MAIN LOOP WITH PROGRESS
|
|
|
|
# ==============================
|
|
|
|
# ==============================
|
|
|
|
|
|
|
|
|
|
|
|
# list of unique request_ids in order
|
|
|
|
|
|
|
|
unique_request_ids = []
|
|
|
|
unique_request_ids = []
|
|
|
|
seen = set()
|
|
|
|
seen = set()
|
|
|
|
for r in rows:
|
|
|
|
for r in rows:
|
|
|
|
@@ -121,7 +121,7 @@ for r in rows:
|
|
|
|
seen.add(req_id)
|
|
|
|
seen.add(req_id)
|
|
|
|
|
|
|
|
|
|
|
|
total_requests = len(unique_request_ids)
|
|
|
|
total_requests = len(unique_request_ids)
|
|
|
|
print(f"🔄 Processing {total_requests} unique requests...\n")
|
|
|
|
safe_print(f"🔄 Processing {total_requests} unique requests...\n")
|
|
|
|
|
|
|
|
|
|
|
|
processed_requests = set()
|
|
|
|
processed_requests = set()
|
|
|
|
current_index = 0
|
|
|
|
current_index = 0
|
|
|
|
@@ -136,17 +136,16 @@ for r in rows:
|
|
|
|
current_index += 1
|
|
|
|
current_index += 1
|
|
|
|
percent = (current_index / total_requests) * 100
|
|
|
|
percent = (current_index / total_requests) * 100
|
|
|
|
|
|
|
|
|
|
|
|
print(f"\n[ {percent:5.1f}% ] Processing request {current_index} / {total_requests} → {req_id}")
|
|
|
|
safe_print(f"\n[ {percent:5.1f}% ] Processing request {current_index} / {total_requests} → {req_id}")
|
|
|
|
|
|
|
|
|
|
|
|
# ========== FETCH ALL VALID FILES FOR THIS REQUEST ==========
|
|
|
|
# ========== FETCH VALID FILENAMES ==========
|
|
|
|
cur_meta.execute(
|
|
|
|
cur_meta.execute(
|
|
|
|
"SELECT filename FROM medevio_downloads WHERE request_id=%s",
|
|
|
|
"SELECT filename FROM medevio_downloads WHERE request_id=%s",
|
|
|
|
(req_id,)
|
|
|
|
(req_id,)
|
|
|
|
)
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
valid_files = {sanitize_name(row["filename"]) for row in cur_meta.fetchall()}
|
|
|
|
valid_files = {sanitize_name(row["filename"]) for row in cur_meta.fetchall()}
|
|
|
|
|
|
|
|
|
|
|
|
# ========== FOLDER NAME BASED ON UPDATEDAT ==========
|
|
|
|
# ========== BUILD FOLDER NAME ==========
|
|
|
|
updated_at = r["req_updated_at"] or datetime.now()
|
|
|
|
updated_at = r["req_updated_at"] or datetime.now()
|
|
|
|
date_str = updated_at.strftime("%Y-%m-%d")
|
|
|
|
date_str = updated_at.strftime("%Y-%m-%d")
|
|
|
|
|
|
|
|
|
|
|
|
@@ -159,17 +158,14 @@ for r in rows:
|
|
|
|
f"{date_str} {prijmeni}, {jmeno} [{abbr}] {req_id}"
|
|
|
|
f"{date_str} {prijmeni}, {jmeno} [{abbr}] {req_id}"
|
|
|
|
)
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
# ========== DETECT EXISTING FOLDER (WITH OR WITHOUT ▲) ==========
|
|
|
|
# ========== DETECT EXISTING FOLDER ==========
|
|
|
|
existing_folder = None
|
|
|
|
existing_folder = None
|
|
|
|
folder_has_flag = False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
for f in BASE_DIR.iterdir():
|
|
|
|
for f in BASE_DIR.iterdir():
|
|
|
|
if f.is_dir() and req_id in f.name:
|
|
|
|
if f.is_dir() and req_id in f.name:
|
|
|
|
existing_folder = f
|
|
|
|
existing_folder = f
|
|
|
|
folder_has_flag = ("▲" in f.name)
|
|
|
|
|
|
|
|
break
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
|
|
# pokud složka existuje → pracujeme v ní
|
|
|
|
|
|
|
|
main_folder = existing_folder if existing_folder else BASE_DIR / clean_folder_name
|
|
|
|
main_folder = existing_folder if existing_folder else BASE_DIR / clean_folder_name
|
|
|
|
|
|
|
|
|
|
|
|
# ========== MERGE DUPLICATES ==========
|
|
|
|
# ========== MERGE DUPLICATES ==========
|
|
|
|
@@ -179,14 +175,13 @@ for r in rows:
|
|
|
|
]
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
for dup in possible_dups:
|
|
|
|
for dup in possible_dups:
|
|
|
|
print(f"♻️ Merging duplicate folder: {dup.name}")
|
|
|
|
safe_print(f"♻️ Merging duplicate folder: {dup.name}")
|
|
|
|
|
|
|
|
|
|
|
|
clean_folder(dup, valid_files)
|
|
|
|
clean_folder(dup, valid_files)
|
|
|
|
main_folder.mkdir(parents=True, exist_ok=True)
|
|
|
|
main_folder.mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
|
|
|
|
|
|
for f in dup.iterdir():
|
|
|
|
for f in dup.iterdir():
|
|
|
|
if f.is_file():
|
|
|
|
if f.is_file():
|
|
|
|
# prostě přesuneme, ▲ případně zůstane v názvu
|
|
|
|
|
|
|
|
target = main_folder / f.name
|
|
|
|
target = main_folder / f.name
|
|
|
|
if not target.exists():
|
|
|
|
if not target.exists():
|
|
|
|
f.rename(target)
|
|
|
|
f.rename(target)
|
|
|
|
@@ -204,11 +199,9 @@ for r in rows:
|
|
|
|
dest_plain = main_folder / filename
|
|
|
|
dest_plain = main_folder / filename
|
|
|
|
dest_marked = main_folder / ("▲" + filename)
|
|
|
|
dest_marked = main_folder / ("▲" + filename)
|
|
|
|
|
|
|
|
|
|
|
|
# soubor už existuje (buď filename, nebo ▲filename)
|
|
|
|
|
|
|
|
if dest_plain.exists() or dest_marked.exists():
|
|
|
|
if dest_plain.exists() or dest_marked.exists():
|
|
|
|
continue
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
|
|
# stáhneme nový soubor → znamená že se má odstranit ▲ složky
|
|
|
|
|
|
|
|
added_new_file = True
|
|
|
|
added_new_file = True
|
|
|
|
|
|
|
|
|
|
|
|
cur_blob.execute(
|
|
|
|
cur_blob.execute(
|
|
|
|
@@ -227,31 +220,22 @@ for r in rows:
|
|
|
|
with open(dest_plain, "wb") as f:
|
|
|
|
with open(dest_plain, "wb") as f:
|
|
|
|
f.write(content)
|
|
|
|
f.write(content)
|
|
|
|
|
|
|
|
|
|
|
|
print(f"💾 Wrote: {dest_plain.relative_to(BASE_DIR)}")
|
|
|
|
safe_print(f"💾 Wrote: {dest_plain.relative_to(BASE_DIR)}")
|
|
|
|
|
|
|
|
|
|
|
|
# ==============================
|
|
|
|
# ========== REMOVE ▲ FLAG IF NEW FILES ADDED ==========
|
|
|
|
# 🔵 REMOVE FOLDER-LEVEL ▲ ONLY IF NEW FILE ADDED
|
|
|
|
if added_new_file and "▲" in main_folder.name:
|
|
|
|
# ==============================
|
|
|
|
new_name = main_folder.name.replace("▲", "").strip()
|
|
|
|
if added_new_file:
|
|
|
|
new_path = main_folder.parent / new_name
|
|
|
|
# složka se má přejmenovat bez ▲
|
|
|
|
|
|
|
|
if "▲" in main_folder.name:
|
|
|
|
|
|
|
|
new_name = main_folder.name.replace("▲", "")
|
|
|
|
|
|
|
|
new_name = new_name.strip() # pro jistotu
|
|
|
|
|
|
|
|
new_path = main_folder.parent / new_name
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if new_path != main_folder:
|
|
|
|
if new_path != main_folder:
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
main_folder.rename(new_path)
|
|
|
|
main_folder.rename(new_path)
|
|
|
|
print(f"🔄 Folder flag ▲ removed → {new_name}")
|
|
|
|
safe_print(f"🔄 Folder flag ▲ removed → {new_name}")
|
|
|
|
main_folder = new_path
|
|
|
|
main_folder = new_path
|
|
|
|
except Exception as e:
|
|
|
|
except Exception as e:
|
|
|
|
print(f"⚠️ Could not rename folder: {e}")
|
|
|
|
safe_print(f"⚠️ Could not rename folder: {e}")
|
|
|
|
else:
|
|
|
|
|
|
|
|
# žádné nové soubory → NIKDY nesahat na název složky
|
|
|
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
safe_print("\n🎯 Export complete.\n")
|
|
|
|
print("\n🎯 Export complete.\n")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cur_blob.close()
|
|
|
|
cur_blob.close()
|
|
|
|
cur_meta.close()
|
|
|
|
cur_meta.close()
|
|
|
|
|