Merge pull request #52 from sgibson91/list-files

Add functionality to list duplicated files

README.md

@@ -124,7 +124,7 @@ deduplify compare          # Compare the filenames again. The code should return
 **Command line usage:**
 
 ```bash
-usage: deduplify compare [-h] [-c COUNT] [-v] [-f INFILE] [--purge]
+usage: deduplify compare [-h] [-c COUNT] [-v] [-f INFILE] [--list-files] [--purge]
 
 optional arguments:
   -h, --help            show this help message and exit
@@ -133,6 +133,7 @@ optional arguments:
   -v, --verbose         Print logging messages to the console
   -f INFILE, --infile INFILE
                         Database to analyse. Must be a JSON file. Default: file_hashes.json
+  --list-files          List duplicated files. Default: False
   --purge               Deletes duplicated files. Default: False
   ```
 

deduplify/_version.py

@@ -7,5 +7,5 @@
 
 from incremental import Version
 
-__version__ = Version("deduplify", 0, 4, 2)
+__version__ = Version("deduplify", 0, 5, 0)
 __all__ = ["__version__"]

deduplify/cli.py

@@ -109,6 +109,11 @@ def parse_args(args):
         default="file_hashes.json",
         help="Database to analyse. Must be a JSON file. Default: file_hashes.json",
     )
+    parser_compare.add_argument(
+        "--list-files",
+        action="store_true",
+        help="List duplicated files. Default: False",
+    )
     parser_compare.add_argument(
         "--purge", action="store_true", help="Deletes duplicated files. Default: False"
     )

deduplify/compare_files.py

@@ -8,9 +8,9 @@
 files.
 
 Python version: >= 3.7 (developed with 3.8)
-Packages: tqdm
+Packages: tqdm, rich
 
->>> pip install tqdm
+>>> pip install tqdm rich
 """
 
 import logging
@@ -20,6 +20,7 @@
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 import jmespath
+from rich import print_json
 from tinydb import TinyDB, where
 from tqdm import tqdm
 
@@ -100,11 +101,12 @@ def delete_files(files: list, workers: int):
     logger.info("Deletion complete!")
 
 
-def run_compare(infile: str, purge: bool, count: int, **kwargs):
+def run_compare(infile: str, list_files: bool, purge: bool, count: int, **kwargs):
     """Compare files for duplicated hashes
 
     Args:
         infile (str): JSON location of filepaths and hashes
+        list_files (bool): Print list of duplicated files to the console
         purge (bool): Delete duplicated files
         count (int): Number of threads to parallelise over
     """
@@ -123,5 +125,9 @@ def run_compare(infile: str, purge: bool, count: int, **kwargs):
 
     logger.info("Number of files that can be safely deleted: %s" % len(files_to_delete))
 
+    if list_files:
+        print("Duplicated files:")
+        print_json(data=files_to_delete)
+
     if purge:
         delete_files(files_to_delete, count)

requirements.txt

@@ -1,5 +1,6 @@
 incremental
 jmespath==1.0.0
+rich==12.2.0
 tinydb==4.7.0
 tqdm
 twisted

tests/test_compare.py

@@ -43,7 +43,7 @@ def test_run_compare_and_purge(mock):
         call("path/to/test/file.txt"),
     ]
 
-    run_compare(infile, True, 1)
+    run_compare(infile, False, True, 1)
 
     assert mock.call_count == 2
     mock.assert_has_calls(test_calls)