improve the OCR pipeline processing and outputs formatting

src/ocr_pipeline/cli.py

@@ -44,6 +44,8 @@ def run(
     engine: str | None = typer.Option(
         None, "--engine", "-e", help="OCR engine (paddleocr/tesseract/auto)"
     ),
+    exclude: list[str] = typer.Option([], "--exclude", help="Glob pattern to exclude; repeatable"),
+    force: bool = typer.Option(False, "--force", help="Reprocess files already recorded as processed"),
 ):
     """Run OCR pipeline on all screenshots"""
     if input_dir:
@@ -54,6 +56,10 @@ def run(
         settings.processing.workers = workers
     if engine:
         settings.ocr.engine = engine
+    if exclude:
+        settings.input.exclude_patterns = exclude
+    if force:
+        settings.processing.skip_existing = False
 
     pipeline = OCRPipeline()
     result = pipeline.process_all()
@@ -136,7 +142,7 @@ def status():
 def stats(days: int = typer.Option(30, "--days", "-d", help="Number of days to analyze")):
     """Show processing statistics"""
     pipeline = OCRPipeline()
-    stats = pipeline.get_stats()
+    stats = pipeline.get_stats(days)
 
     table = Table(title=f"Statistics (last {days} days)")
     table.add_column("Metric", style="cyan")