Implement parallel processing for optimization steps using ThreadPoolExecutor.

- Improved documentation with optimization levels
- Updated version history
- Fixed aspect ratio in PDF output

README.md

@@ -10,10 +10,11 @@ A command-line tool for processing and cleaning scanned musical score PDFs. This
 - **PNG Optimization**: Optimize PNG files using optipng (if installed)
 - **Modular Processing**: Process your files step by step or all at once
 - **High Quality Output**: Preserve image quality throughout the process
+- **Professional PDF Output**: Generate A4-sized PDFs with proper borders and centered content
 
 ## Installation
 
-1. Ensure you have Python 3.8+ installed
+1. Ensure you have Python 3.12+ installed
 2. Install uv (recommended) or pip
 3. Clone this repository:
    ```bash
@@ -55,15 +56,20 @@ Automatically detects and corrects page rotation by analyzing staff lines.
 
 ### Optimize Pages
 ```bash
-./pdf_cleaner.py optimize
+./pdf_cleaner.py optimize [--level {1,2,3}]
 ```
-Trims excess white space and optionally runs PNG optimization (requires optipng).
+Processes pages with different optimization levels:
+- Level 1: Only trims excess white space
+- Level 2: Trims white space and converts to 1-bit monochrome
+- Level 3: All optimizations + PNG optimization (requires optipng)
+
+Default level is 1 if not specified.
 
 ### Create Final PDF
 ```bash
 ./pdf_cleaner.py finalize output.pdf
 ```
-Combines all processed pages into a final PDF and cleans up temporary files.
+Combines all processed pages into a final PDF with proper A4 sizing, borders, and centered content.
 
 ### Typical Workflow
 ```bash
@@ -83,7 +89,10 @@ Combines all processed pages into a final PDF and cleans up temporary files.
 3. **Optimization**:
    - Detects content boundaries and removes excess white space
    - Optionally runs optipng for additional file size reduction
-4. **Finalization**: Combines processed images back into a PDF using img2pdf
+4. **Finalization**: 
+   - Combines processed images into a professional A4-sized PDF
+   - Adds configurable borders around content
+   - Centers content on each page while maintaining aspect ratio
 
 ## Dependencies
 
@@ -100,4 +109,15 @@ Contributions are welcome! Please feel free to submit a Pull Request.
 
 ## License
 
-[Insert chosen license here]
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Version History
+
+- v0.9rc2: Second release candidate
+  - Improved documentation
+  - Added optimization level descriptions
+  - Fixed aspect ratio in PDF output
+- v0.9rc1: First release candidate with full functionality
+  - Professional PDF output with A4 sizing and borders
+  - Complete image processing pipeline
+  - Configurable settings

pdf_cleaner.py

@@ -15,6 +15,7 @@ from pdf2image import convert_from_path
 import settings
 from settings import OptimizationLevel
 from PIL import Image
+import concurrent.futures
 
 class Settings:
     TRIM_PADDING_PIXELS = 20
@@ -323,40 +324,53 @@ def optimize(level):
     
     print(f"Processing {total_files} images at optimization level {level}...")
     
-    # Step 1: Always trim whitespace
-    print("\nTrimming whitespace from images...")
-    for i, file_path in enumerate(temp_files, 1):
-        print(f"[{i}/{total_files}] Processing {os.path.basename(file_path)}...", end='', flush=True)
-        # Only optimize if this is the final step (level 1)
-        if trim_whitespace(file_path, is_final=(opt_level == OptimizationLevel.TRIM)):
-            successful['trim'] += 1
-            print(" ")
-        else:
-            print(" ")
-    
-    # Step 2: Convert to monochrome if level >= 2
+    # Step 1: Convert to monochrome if level >= 2
     if int(opt_level) >= int(OptimizationLevel.MONOCHROME):
         print("\nConverting to monochrome...")
-        for i, file_path in enumerate(temp_files, 1):
-            print(f"[{i}/{total_files}] Converting {os.path.basename(file_path)}...", end='', flush=True)
-            # Only optimize if this is the final step (level 2)
-            if convert_to_monochrome(file_path, is_final=(opt_level == OptimizationLevel.MONOCHROME)):
-                successful['monochrome'] += 1
-                print(" ")
-            else:
-                print(" ")
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            futures = {executor.submit(convert_to_monochrome, file_path, (opt_level == OptimizationLevel.MONOCHROME)): file_path for file_path in temp_files}
+            for future in concurrent.futures.as_completed(futures):
+                file_path = futures[future]
+                try:
+                    if future.result():
+                        successful['monochrome'] += 1
+                        print(f"Converted {os.path.basename(file_path)}")
+                    else:
+                        print(f"Failed to convert {os.path.basename(file_path)}")
+                except Exception as exc:
+                    print(f"{os.path.basename(file_path)} generated an exception: {exc}")
+    
+    # Step 2: Always trim whitespace
+    print("\nTrimming whitespace from images...")
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        futures = {executor.submit(trim_whitespace, file_path, (opt_level == OptimizationLevel.TRIM)): file_path for file_path in temp_files}
+        for future in concurrent.futures.as_completed(futures):
+            file_path = futures[future]
+            try:
+                if future.result():
+                    successful['trim'] += 1
+                    print(f"Trimmed {os.path.basename(file_path)}")
+                else:
+                    print(f"Failed to trim {os.path.basename(file_path)}")
+            except Exception as exc:
+                print(f"{os.path.basename(file_path)} generated an exception: {exc}")
     
     # Step 3: Run optipng if level = 3
     if opt_level == OptimizationLevel.FULL:
         if check_optipng_installed():
             print("\nOptimizing PNG files with optipng...")
-            for i, file_path in enumerate(temp_files, 1):
-                print(f"[{i}/{total_files}] Optimizing {os.path.basename(file_path)}...", end='', flush=True)
-                if run_optipng(file_path):
-                    successful['optipng'] += 1
-                    print(" ")
-                else:
-                    print(" ")
+            with concurrent.futures.ThreadPoolExecutor() as executor:
+                futures = {executor.submit(run_optipng, file_path): file_path for file_path in temp_files}
+                for future in concurrent.futures.as_completed(futures):
+                    file_path = futures[future]
+                    try:
+                        if future.result():
+                            successful['optipng'] += 1
+                            print(f"Optimized {os.path.basename(file_path)}")
+                        else:
+                            print(f"Failed to optimize {os.path.basename(file_path)}")
+                    except Exception as exc:
+                        print(f"{os.path.basename(file_path)} generated an exception: {exc}")
         else:
             print("\nNote: optipng not found. Skipping PNG optimization.")
     

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "notes-cleaner"
-version = "0.9rc1"
+version = "0.9rc2"
 description = "Add your description here"
 readme = "README.md"
 license = "MIT"

uv.lock

@@ -33,7 +33,7 @@ wheels = [
 
 [[package]]
 name = "notes-cleaner"
-version = "0.1.0"
+version = "0.9rc2"
 source = { virtual = "." }
 dependencies = [
     { name = "click" },