Merge remote-tracking branch 'origin/master'

AdobeFlatten/10 FlattenAdobe.py

@@ -0,0 +1,45 @@
+import fitz
+from pathlib import Path
+
+BASE_DIR = Path(r"z:\Dropbox\Ordinace\Dokumentace_ke_zpracování\AdobeFlattenStamp")
+
+def flatten_pdf_rasterize(input_pdf: Path):
+    print(f"Processing: {input_pdf.name}")
+    doc = fitz.open(input_pdf)
+
+    # Create a new empty PDF
+    new_doc = fitz.open()
+
+    for page in doc:
+        # Render each page to a high-resolution image
+        pix = page.get_pixmap(dpi=400)
+
+        # Create a new PDF page with same size
+        new_page = new_doc.new_page(width=page.rect.width, height=page.rect.height)
+
+        # Insert the rasterized image
+        new_page.insert_image(new_page.rect, pixmap=pix)
+
+    # Save output
+    output_pdf = input_pdf.with_name(input_pdf.stem + "_flatten.pdf")
+    new_doc.save(output_pdf, deflate=True)
+    new_doc.close()
+    doc.close()
+
+    print(f"   ✔ Saved: {output_pdf.name}")
+
+
+def main():
+    pdfs = list(BASE_DIR.glob("*.pdf"))
+    if not pdfs:
+        print("No PDF files found.")
+        return
+
+    for pdf in pdfs:
+        flatten_pdf_rasterize(pdf)
+
+    print("\nAll files processed.")
+
+
+if __name__ == "__main__":
+    main()

ECG/20 ECG test2.py

@@ -26,9 +26,22 @@ def ocr_page(page):
 
 
 def extract_rodne_cislo(text):
-    """Extract 10-digit rodné číslo (no slash)."""
+    """
-    m = re.search(r"\b\d{9,10}\b", text)
+    Extract rodné číslo in formats:
-    return m.group(0) if m else None
+    - 6 digits + slash + 4 digits  → 655527/1910
+    - 6 digits + slash + 3 digits  → 655527/910
+    - 10 digits without slash      → 6555271910
+
+    Always returns 10 digits without slash.
+    """
+    m = re.search(r"\b(\d{6})/?(\d{3,4})\b", text)
+    if not m:
+        return None
+
+    left = m.group(1)
+    right = m.group(2).zfill(4)  # ensure 4 digits
+
+    return left + right
 
 
 def extract_date(text):

MedevioPřílohykontroly/05 SpočítejMD5ZpracoveneALAB.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import hashlib
+import json
+from pathlib import Path
+import time
+
+# === ZDE JEN PŘIDÁVEJ ADRESÁŘE ===
+DIRECTORIES = [
+    Path(r"U:\Dropbox\Ordinace\Dokumentace_zpracovaná"),
+    Path(r"U:\Dropbox\Ordinace\LAB-PDF"),
+]
+
+CHUNK = 65536
+
+
+def md5_file(path: Path) -> str:
+    h = hashlib.md5()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(CHUNK), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def load_db(db_path: Path) -> dict:
+    if db_path.exists():
+        with db_path.open("r", encoding="utf-8") as f:
+            return json.load(f)
+    return {}
+
+
+def save_db(db: dict, db_path: Path):
+    with db_path.open("w", encoding="utf-8") as f:
+        json.dump(db, f, ensure_ascii=False, indent=2)
+
+
+def process_directory(root: Path):
+    print("\n===========================================")
+    print(f"📁 ZPRACOVÁVÁM ADRESÁŘ: {root}")
+    print("===========================================\n")
+
+    db_path = root / "processed_files.json"
+
+    # Načíst databázi
+    db = load_db(db_path)
+    print(f"Načteno z DB: {len(db)} záznamů")
+
+    # Projít souborový systém
+    files_in_fs = {}
+    start_scan = time.time()
+
+    for f in root.rglob("*"):
+        if f.is_file() and f.suffix.lower() != ".json":
+            stat = f.stat()
+            files_in_fs[f.name] = {
+                "size": stat.st_size,
+                "mtime": int(stat.st_mtime),
+                "path": str(f)
+            }
+
+    print(f"Nalezeno v FS: {len(files_in_fs)} souborů")
+    print(f"Čas skenu: {time.time() - start_scan:.2f} s\n")
+
+    new_files = 0
+    changed_files = 0
+
+    for fname, info in files_in_fs.items():
+
+        size = info["size"]
+        mtime = info["mtime"]
+
+        # nový soubor?
+        if fname not in db:
+            print(f"Nový soubor → MD5: {fname}")
+            new_files += 1
+            db[fname] = {
+                "size": size,
+                "mtime": mtime,
+                "md5": md5_file(Path(info["path"]))
+            }
+            continue
+
+        # změněný soubor?
+        if db[fname]["size"] != size or db[fname]["mtime"] != mtime:
+            print(f"Změněný soubor → MD5: {fname}")
+            changed_files += 1
+            db[fname] = {
+                "size": size,
+                "mtime": mtime,
+                "md5": md5_file(Path(info["path"]))
+            }
+
+    # uložit databázi
+    save_db(db, db_path)
+
+    print("\n=== Výsledky ===")
+    print(f" Nové soubory:     {new_files}")
+    print(f" Změněné soubory:  {changed_files}")
+    print(f" Celkem v DB:      {len(db)}")
+    print(f" Databáze:         {db_path}")
+    print("=============================\n")
+
+
+def main():
+    for directory in DIRECTORIES:
+        process_directory(directory)
+
+
+if __name__ == "__main__":
+    main()

MedevioPřílohykontroly/10 spočítejMD5AoznačsouboryAadresáře.py

@@ -0,0 +1,158 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import hashlib
+import json
+from pathlib import Path
+import time
+import traceback
+
+
+# ======= CONFIG =======
+
+MP_DIR = Path(r"U:\Dropbox\Ordinace\Dokumentace_ke_zpracování\MP")
+
+JSON_PATHS = [
+    Path(r"U:\Dropbox\Ordinace\LAB-PDF\processed_files.json"),
+    Path(r"U:\Dropbox\Ordinace\Dokumentace_zpracovaná\processed_files.json"),
+]
+
+CHUNK = 65536
+PRINT_EVERY = 50
+# ======================
+
+
+def try_rename(old_path: Path, new_path: Path, retries: int = 5, delay: int = 5):
+    """Try rename with retry mechanism."""
+    for attempt in range(1, retries + 1):
+        try:
+            old_path.rename(new_path)
+            return True
+        except Exception as e:
+            print(f"⚠ Rename failed ({attempt}/{retries}): {e}")
+            if attempt < retries:
+                print(f"   Waiting {delay}s before retry...")
+                time.sleep(delay)
+            else:
+                print("   ❌ Maximum retries reached. Skipping.")
+                traceback.print_exc()
+                return False
+
+
+def md5_file(path: Path) -> str:
+    h = hashlib.md5()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(CHUNK), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def load_all_md5(json_paths):
+    """Načte MD5 ze všech JSONů a vrátí množinu."""
+    md5_set = set()
+    for jp in json_paths:
+        if not jp.exists():
+            print(f"⚠ JSON nenalezen: {jp}")
+            continue
+        try:
+            with jp.open("r", encoding="utf-8") as f:
+                db = json.load(f)
+                for _, info in db.items():
+                    md5_set.add(info["md5"])
+            print(f"Načteno {len(db)} záznamů z {jp}")
+        except Exception as e:
+            print(f"❌ Chyba při čtení {jp}: {e}")
+    print(f"➡ Celkem MD5 hashů: {len(md5_set)}\n")
+    return md5_set
+
+
+def mark_folders_if_all_marked(root: Path, dryrun: bool):
+    print("\n=== KONTROLA ADRESÁŘŮ — OZNAČENÍ PLNĚ HOTOVÝCH ===")
+
+    for folder in sorted(root.rglob("*")):
+        if not folder.is_dir():
+            continue
+
+        files = [f for f in folder.iterdir() if f.is_file()]
+        if not files:
+            continue
+
+        # všechny soubory označené?
+        if not all(f.name.startswith("▲") for f in files):
+            continue
+
+        # adresář už označen?
+        if len(folder.name) > 10 and folder.name[10] == "▲":
+            continue
+
+        # vložení ▲ na 11. pozici
+        insert_pos = 10
+        name = folder.name
+
+        if len(name) <= insert_pos:
+            new_name = name + "▲"
+        else:
+            new_name = name[:insert_pos] + "▲" + name[insert_pos:]
+
+        new_path = folder.parent / new_name
+
+        print(f"✔ Adresář označen: {folder.name} → {new_name}")
+
+        if not dryrun:
+            try_rename(folder, new_path)
+
+
+def run_matcher(dryrun: bool = True):
+    print("\n=== MATCHER V3 — SOUBORY + ADRESÁŘE ===")
+    print(f"Režim: {'DRYRUN (simulace)' if dryrun else 'OSTRÝ'}\n")
+
+    all_md5 = load_all_md5(JSON_PATHS)
+
+    counter = 0
+    renamed = 0
+    start = time.time()
+
+    for file in MP_DIR.rglob("*"):
+        if not file.is_file():
+            continue
+
+        counter += 1
+
+        if counter % PRINT_EVERY == 0:
+            speed = counter / (time.time() - start)
+            print(f"  {counter} soub. ({speed:.1f}/s)")
+
+        md5 = md5_file(file)
+
+        if md5 in all_md5:
+
+            if file.name.startswith("▲"):
+                continue
+
+            new_name = "▲" + file.name
+            new_path = file.parent / new_name
+
+            if dryrun:
+                print(f"[DRYRUN] Označil bych: {file.name} → {new_name}")
+            else:
+                # === RETRY RENAME (soubory) ===
+                success = try_rename(file, new_path)
+                if success:
+                    renamed += 1
+                    print(f"✔ {file.name} → {new_name}")
+
+    # označit adresáře
+    mark_folders_if_all_marked(MP_DIR, dryrun)
+
+    total_time = time.time() - start
+    speed = 0 if counter == 0 or total_time == 0 else counter / total_time
+
+    print("\n=== MATCHER HOTOVO ===")
+    print(f" Zkontrolováno: {counter} souborů")
+    print(f" Označeno:     {renamed}")
+    print(f" Rychlost:     {speed:.1f} soub./s")
+    print(f" Režim:        {'DRYRUN' if dryrun else 'OSTRÝ'}\n")
+
+
+if __name__ == "__main__":
+    run_matcher(dryrun=False)