feat: progress callbacks in analyzer, WebP support, HEIC dependency

- analyzer.py: progress_callback parameter with phase reporting
- analyzer.py: add .webp to SUPPORTED_EXTENSIONS
- requirements.txt: add pillow-heif==1.3.0 for HEIC/HEIF support

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

analyzer.py

@@ -89,7 +89,7 @@ def find_duplicates(paths: List[str], threshold: int = 8) -> List[List[str]]:
     return groups
 
 
-SUPPORTED_EXTENSIONS = {".jpg", ".jpeg", ".png"}
+SUPPORTED_EXTENSIONS = {".jpg", ".jpeg", ".png", ".webp"}
 
 
 def _analyze_with_ai(paths: List[str], api_key: str) -> dict:
@@ -152,21 +152,28 @@ def analyze_folder(
     dup_threshold: int = 8,
     use_ai: bool = False,
     api_key: Optional[str] = None,
+    progress_callback=None,  # callable(done: int, total: int, phase: str)
 ) -> List[dict]:
     """
     Analysiert alle Bilder im Ordner.
     Gibt Liste zurueck: [{"path": "/foo/bar.jpg", "reasons": ["unscharf"]}, ...]
     Nur Bilder mit mindestens einem Grund werden zurueckgegeben.
     """
+    def report(done, total, phase):
+        if progress_callback:
+            progress_callback(done, total, phase)
+
     paths = [
         os.path.join(folder, f)
         for f in os.listdir(folder)
         if os.path.splitext(f)[1].lower() in SUPPORTED_EXTENSIONS
     ]
+    total = len(paths)
 
     results: dict = {path: [] for path in paths}
 
-    for path in paths:
+    # Phase 1: Qualitätsanalyse pro Foto (macht ~70% der Arbeit aus)
+    for i, path in enumerate(paths):
         try:
             if is_blurry(path, blur_threshold):
                 results[path].append("unscharf")
@@ -175,8 +182,11 @@ def analyze_folder(
             if is_underexposed(path, under_threshold):
                 results[path].append("unterbelichtet")
         except Exception:
-            continue
+            pass
+        report(i + 1, total, "quality")
 
+    # Phase 2: Exakte Kopien (MD5)
+    report(total, total, "exact_copies")
     exact_copy_paths: set = set()
     exact_groups = find_exact_copies(paths)
     for group in exact_groups:
@@ -185,6 +195,8 @@ def analyze_folder(
             results[copy_path].append(f"exakte Kopie von {original}")
             exact_copy_paths.add(copy_path)
 
+    # Phase 3: Duplikate (pHash)
+    report(total, total, "duplicates")
     dup_paths = [p for p in paths if p not in exact_copy_paths]
     dup_groups = find_duplicates(dup_paths, dup_threshold)
     for group in dup_groups:
@@ -192,11 +204,14 @@ def analyze_folder(
         for dup_path in group[1:]:
             results[dup_path].append(f"Duplikat von {original}")
 
+    # Phase 4: KI-Analyse (optional)
     if use_ai and api_key:
+        report(total, total, "ai")
         ai_results = _analyze_with_ai(paths, api_key)
         for path, ai_reasons in ai_results.items():
             results[path].extend(ai_reasons)
 
+    report(total, total, "done")
     return [
         {"path": path, "reasons": reasons}
         for path, reasons in results.items()

requirements.txt

@@ -5,5 +5,6 @@ opencv-python-headless==4.13.0.92
 imagehash==4.3.1
 python-dotenv==1.0.1
 anthropic==0.89.0
+pillow-heif==1.3.0
 pytest==8.1.1
 httpx==0.27.0