updated Dry Run feature

README.md

@@ -27,6 +27,7 @@ TwinTrim is a powerful and efficient tool designed to find and manage duplicate
 - **Multi-Threaded Processing**: Utilizes multi-threading to quickly scan and process large numbers of files concurrently.
 - **Deadlock Prevention**: Implements locks to prevent deadlocks during multi-threaded operations, ensuring smooth and safe execution.
 - **User-Friendly Interface**: Offers clear prompts and feedback via the command line, making the process straightforward and interactive.
+- **Dry Run**: Use the --dry-run option to simulate the process without making any changes, allowing you to review what will happen before executing.
 
 ## How It Works
 
@@ -46,7 +47,10 @@ TwinTrim is a powerful and efficient tool designed to find and manage duplicate
     - Duplicate files are identified by comparing their hashes.
     - Based on file modification time, the latest file is retained, and older duplicates are removed.
 
-5. **Deadlock Prevention**:
+5. **Dry Run Mode**:
+    - The --dry-run flag allows you to simulate the duplicate removal process without making any actual changes, giving you an opportunity to review potential actions before committing to them.
+
+6. **Deadlock Prevention**:
     - Uses locks within multi-threaded processes to ensure that resources are accessed safely, preventing deadlocks that could otherwise halt execution.
 
 ### Key Functions
@@ -74,6 +78,7 @@ python -m twinTrim.main <directory> [OPTIONS]
 - `--exclude`: Exclude specific files by name.
 - `--label-color`: Set the font color of the output label of the progress bar.
 - `--bar-color`: Set the color of the progress bar.
+- `--dry-run`: Simulate the duplicate removal process without making any changes.
 
 ### Examples
 
@@ -92,6 +97,12 @@ python -m twinTrim.main <directory> [OPTIONS]
     python -m twinTrim.main /path/to/directory --min-size "50kb" --max-size "500mb" --file-type "txt"
     ```
 
+4. **Dry Run Simulation**:
+
+   ```bash
+   python twinTrim.py /path/to/directory --dry-run
+   ```
+
 ## Dependencies
 
 - Python 3.6+

twinTrim/flagController.py

@@ -33,10 +33,6 @@ def handleAllFlag(directory,file_filter,pb_color,bar_color):
 
         # Update progress bar as files are processed
         for future in as_completed(futures):
-            try:
-                future.result()  # Ensures exception handling for each future
-            except Exception as e:
-                click.echo(click.style(f"Error processing file {futures[future]}: {str(e)}", fg='red'))
             progress_bar.update(1)
 
     click.echo(click.style("All files scanned and duplicates handled.", fg='green'))
@@ -50,7 +46,6 @@ def handleAllFlag(directory,file_filter,pb_color,bar_color):
 def find_duplicates(directory, file_filter, pb_color, bar_color):
     """Find duplicate files in the given directory and store them in normalStore."""
     # Collect all file paths first and apply filters
-    start_time=time.time()
     all_files = [os.path.join(root, file_name) for root, _, files in os.walk(directory) for file_name in files]
     all_files = [f for f in all_files if file_filter.filter_files(f)]  # Apply filters
 
@@ -65,14 +60,8 @@ def process_file(file_path):
         futures = {executor.submit(process_file, file_path): file_path for file_path in all_files}
 
         for future in as_completed(futures):
-            try:
-                future.result()  # Ensures exception handling for each future
-            except Exception as e:
-                click.echo(click.style(f"Error processing file {futures[future]}: {str(e)}", fg='red'))
-            progress_bar.update(1)
+            progress_bar.update(1) 
 
-    end_time=time.time()
-    click.echo(click.style(f"Time taken to find all duplicate files: {end_time-start_time:.2f} seconds.", fg='green'))
     duplicates = []
     for _, metadata in normalStore.items():
         if len(metadata.filepaths) > 1:
@@ -81,3 +70,5 @@ def process_file(file_path):
                 duplicates.append((original_path, duplicate_path))
 
     return duplicates
+
+

twinTrim/flags.py

@@ -1,20 +1,12 @@
 import os
 import click
 import time
-import logging
-import inquirer
 from collections import defaultdict
 from twinTrim.utils import handle_and_remove, parse_size
 from twinTrim.flagController import handleAllFlag, find_duplicates
+from beaupy import select_multiple
 from twinTrim.dataStructures.fileFilter import FileFilter
 
-# Setting up logging configuration
-logging.basicConfig (
-    filename='duplicate_file_manager.log',   
-    level = logging.INFO,                    
-    format = '%(asctime)s - %(levelname)s - %(message)s'                                  
-)
-
 @click.command()
 @click.argument("directory", type=click.Path(exists=True))
 @click.option("--all", is_flag=True, help="Delete duplicates automatically without asking.")
@@ -24,7 +16,8 @@
 @click.option("--exclude", multiple=True, help="Files to exclude by name.")
 @click.option("--label-color", default="yellow", type=str, help="Color of the label of progress bar.")
 @click.option("--bar-color", default='#aaaaaa', type=str, help="Color of the progress bar.")
-def cli(directory, all, min_size, max_size, file_type, exclude, label_color, bar_color):
+@click.option("--dry-run", is_flag=True, help="Simulate the process without deleting files.")
+def cli(directory, all, min_size, max_size, file_type, exclude, label_color, bar_color, dry_run):
     """Find and manage duplicate files in the specified DIRECTORY."""
 
     # Initialize the FileFilter object
@@ -36,27 +29,23 @@ def cli(directory, all, min_size, max_size, file_type, exclude, label_color, bar
         file_filter.addFileExclude(file_name)
 
     if all:
-        logging.info("Deleting all duplicate files without asking.")
-        handleAllFlag(directory, file_filter, label_color, bar_color)
+        if dry_run:
+            click.echo(click.style("Dry run mode enabled: Skipping actual deletion.", fg='yellow'))
+        handleAllFlag(directory, file_filter, label_color, bar_color, dry_run=dry_run)  # Modify handleAllFlag to support dry_run
         return
 
     start_time = time.time()
-    logging.info(f"Searching for duplicates in directory: {directory}")
+    duplicates = find_duplicates(directory, file_filter, label_color, bar_color)
 
-    try:
-        duplicates = find_duplicates(directory, file_filter, label_color, bar_color)
-    except Exception as e:
-        logging.error(f"Error finding duplicates: {str(e)}")
-        click.echo(click.style("Error while finding duplicates. Check the log for details.", fg='red'))
-        return
+    end_time = time.time()
+    time_taken = end_time - start_time
 
     if not duplicates:
         click.echo(click.style("No duplicate files found.", fg='green'))
-        logging.info("No duplicate files found.")
+        click.echo(click.style(f"Time taken: {time_taken:.2f} seconds.", fg='green'))
         return
 
     click.echo(click.style(f"Found {len(duplicates)} sets of duplicate files:", fg='yellow'))
-    logging.info(f"Found {len(duplicates)} set of duplicate files")
 
     duplicates_dict = defaultdict(list)
     for original, duplicate in duplicates:
@@ -66,42 +55,29 @@ def cli(directory, all, min_size, max_size, file_type, exclude, label_color, bar
     for original, duplicates_list in duplicates_dict.items():
         click.echo(click.style(f"Original file: \"{original}\"", fg='cyan'))
         click.echo(click.style(f"Number of duplicate files found: {len(duplicates_list)}", fg='cyan'))
-        logging.info(f"Original file: \"{original}\" with {len(duplicates_list)} duplicates")
-
         click.echo(click.style("They are:", fg='cyan'))
-
-        # Create file options with additional information
-        file_options = [
-            f"{idx + 1}) {duplicate} (Size: {os.path.getsize(duplicate)} bytes)" for idx, duplicate in enumerate(duplicates_list)
-        ]
-
-        answers = inquirer.prompt(
-        [
-            inquirer.Checkbox(
-                'files',
-                message="Select files to delete (Use space to select, enter to confirm, or ctr + c to cancel, arrow key to navigate.)",
-                choices=file_options,
-                validate=lambda answer, current: len(answer) > 0 or "You must choose at least one file.",
-            ),
-            inquirer.Confirm(
-                'confirm',
-                message="Are you sure you want to delete the selected files?",
-                default=True
-            )
-        ])
-
-
-        if answers and answers['confirm']:
-            selected_files = answers['files']
-            # Convert the selected options back to the original file paths
-            files_to_delete = [duplicates_list[int(option.split(")")[0]) - 1] for option in selected_files]
-
-            for file_path in files_to_delete:
+        file_options = [f"{idx + 1}) {duplicate}" for idx, duplicate in enumerate(duplicates_list)]
+
+        # Prompt user to select which files to delete
+        selected_indices = select_multiple(
+            file_options,  # List of files to choose from
+            ticked_indices=[],         # Default indices that are selected
+            maximal_count=len(file_options)  
+        )
+
+        # Convert the indices back to the original file paths
+        files_to_delete = [duplicates_list[int(option.split(")")[0]) - 1] for option in selected_indices]
+
+        for file_path in files_to_delete:
+            if dry_run:
+                click.echo(click.style(f"[Dry Run] Would delete: {file_path}", fg='yellow'))
+            else:
                 handle_and_remove(file_path)
-        else:
-            click.echo(click.style("File deletion canceled.", fg='yellow'))
 
-    end_time = time.time()
-    time_taken = end_time - start_time
+    if not dry_run:
+        click.echo(click.style("Selected duplicate files removed!", fg='green'))
+    else:
+        click.echo(click.style("Dry run completed. No files were actually deleted.", fg='yellow'))
+
     click.echo(click.style(f"Time taken: {time_taken:.2f} seconds.", fg='green'))
-    logging.info(f"Total time taken: {time_taken:.2f} seconds.")
+