add limit

find_duplicate_files/find_duplicate_files.py

@@ -17,7 +17,7 @@ import re
 
 class find_duplicate_files:
 
-    def __init__(self, debug_level, log_file, dummy, first_directory, second_directory, exclude):
+    def __init__(self, debug_level, log_file, dummy, first_directory, second_directory, exclude, limit):
         ''' Initial function called when object is created '''
         self.config = dict()
         self.config['debug_level'] = debug_level
@@ -30,6 +30,7 @@ class find_duplicate_files:
         self.first_directory = first_directory
         self.second_directory = second_directory
         self.exclude = exclude
+        self.limit = limit
 
         self._init_db_cache()
 
@@ -89,6 +90,8 @@ class find_duplicate_files:
         files = dict()
         try:
             for file in os.scandir(path):
+                if len(files) > self.limit:
+                    break
                 if not file.name.startswith('.'):
                     if not self._test_exclude(file.path):
                         if file.is_file():
@@ -155,9 +158,10 @@ class find_duplicate_files:
 @click.option('--first-directory', '-f', required=True, help='First directory to find files AND TO DELETE FILES FROM!!!')
 @click.option('--second-directory', '-s', required=True, help='Second directory to find files')
 @click.option('--exclude', '-e', multiple=True, help='Regular expression pattern to exclude from files and directories.')
+@click.option('--limit', '-l', default=None, help='Limit to a certain number of files to check.')
 @click_config_file.configuration_option()
-def __main__(debug_level, log_file, dummy, first_directory, second_directory, exclude):
-    return find_duplicate_files(debug_level, log_file, dummy, first_directory, second_directory, exclude)
+def __main__(debug_level, log_file, dummy, first_directory, second_directory, exclude, limit):
+    return find_duplicate_files(debug_level, log_file, dummy, first_directory, second_directory, exclude, limit)
 
 if __name__ == "__main__":
     __main__()