log output

classify_pdfs.py

@@ -14,7 +14,7 @@ Kein LLM, keine Netzwerk. Reine lokale Analyse zum Planen.
 Aufruf:
   python3 classify_pdfs.py --src ~/data/S
 """
-import os, re, glob, argparse
+import os, re, glob, argparse, sys
 from collections import defaultdict
 from pypdf import PdfReader
 
@@ -45,6 +45,7 @@ def main():
     args = ap.parse_args()
 
     pdfs = sorted(glob.glob(os.path.join(args.src, "*.pdf")))
+    print(f"{len(pdfs)} PDFs (nur oberste Ebene) gefunden. Analysiere...\n")
     persons = defaultdict(list)
     for p in pdfs:
         persons[person_from_filename(p)].append(p)
@@ -55,6 +56,8 @@ def main():
     only_image_persons = []
     person_has_text = {}
 
+    processed = 0
+    total_files = len(pdfs)
     for person, files in persons.items():
         non_notes = [f for f in files if "notes" not in os.path.basename(f).lower()]
         notes = [f for f in files if "notes" in os.path.basename(f).lower()]
@@ -71,11 +74,19 @@ def main():
             else:
                 n_image += 1
 
-        # Person hat NUR Image-PDFs (oder nur Notes)?
+        # Fortschritt in EINER Zeile (mit \r ueberschreibend)
+        processed += len(files)
+        name_short = person[:40]
+        sys.stdout.write(f"\r  {processed}/{total_files} bearbeitet - {name_short:<42}")
+        sys.stdout.flush()
+
         if not has_any_text:
             only_image_persons.append(person)
         person_has_text[person] = has_any_text
 
+    sys.stdout.write("\r" + " " * 70 + "\r")  # Zeile loeschen
+    print("Analyse fertig.\n")
+
     print(f"=== Analyse: {args.src} ===")
     print(f"PDFs gesamt:              {len(pdfs)}")
     print(f"Distinkte Personen:       {total_persons}")