Rewriten as class Sweeper with code improvements and optimizations.

README.rst

@@ -10,28 +10,31 @@ Print duplicates
 
 .. code:: python
 
-    from sweeper import file_dups
-    dups = file_dups(['images1', 'images2'])
+    from sweeper import Sweeper
+    swp = Sweeper(['images1', 'images2'])
+    dups = swp.file_dups()
     print(dups)
 
 Remove duplicate files
 
 .. code:: python
 
-    from sweeper import rm_file_dups
-    rm_file_dups(['images'])
+    from sweeper import Sweeper
+    swp = Sweeper(['images1', 'images2'])
+    swp.rm()
 
 Perform custom action
 
 .. code:: python
 
-    from sweeper import iter_file_dups
-    for f, h, dups in iter_file_dups(['images']):
+    from sweeper import Sweeper
+    swp = Sweeper(['images'])
+    for f, h, dups in swp:
         print('encountered {} which duplicates with already found duplicate files {} with hash {}'.format(f, dups, h))
 
 As script::
 
-    python sweeper.py --help
+    python -m sweeper/sweeper --help
 
 As installed console script::
     

TODO

-* Play it safe and add byte by byte comparison option for hash dup files?
-  Or use one more, different, hash algorithm?

sweeper/__init__.py

 from __future__ import absolute_import
-from .sweeper import file_dups, mv_file_dups, rm_file_dups, iter_file_dups
+from .sweeper import Sweeper
 
-__all__ = ['file_dups', 'mv_file_dups', 'rm_file_dups', 'iter_file_dups']
+__all__ = ['Sweeper']

test/test_sweeper.py

@@ -3,7 +3,7 @@
 # License: GPLv3
 
 import unittest
-from sweeper import file_dups, iter_file_dups
+from sweeper import Sweeper
 import os
 
 mydir = os.path.dirname(os.path.realpath(__file__))
@@ -11,7 +11,8 @@ mydir = os.path.dirname(os.path.realpath(__file__))
 
 class TestSweeper(unittest.TestCase):
     def test_file_dups_dups(self):
-        dups = file_dups([os.path.join(mydir, 'testfiles_dups')])
+        swp = Sweeper(topdirs=[os.path.join(mydir, 'testfiles_dups')])
+        dups = swp.file_dups()
         dups_exist = False
         for h, flist in dups.items():
             if len(flist) > 1:
@@ -19,24 +20,26 @@ class TestSweeper(unittest.TestCase):
         self.assertTrue(dups_exist)
 
     def test_file_dups_nodups(self):
-        dups = file_dups([os.path.join(mydir, 'testfiles_nodups')])
+        swp = Sweeper(topdirs=[os.path.join(mydir, 'testfiles_nodups')])
+        dups = swp.file_dups()
         for h, flist in dups.items():
             self.assertTrue(len(flist) == 1)
 
     # does not actually test safe_mode, we would need to find
     # hash collision
     def test_file_dups_safe_mode(self):
-        dups = file_dups([os.path.join(mydir, 'testfiles_dups')],
-                         safe_mode=True)
+        swp = Sweeper(topdirs=[os.path.join(mydir, 'testfiles_dups')],
+                      safe_mode=True)
+        dups = swp.file_dups()
         for h, flist in dups.items():
             if len(flist) > 1:
                 dups_exist = True
         self.assertTrue(dups_exist)
 
     def test_iter_file_dups_dups(self):
-        it = iter_file_dups([os.path.join(mydir, 'testfiles_dups')])
+        swp = Sweeper(topdirs=[os.path.join(mydir, 'testfiles_dups')])
         dups_exist = False
-        for x in it:
+        for x in swp:
             dups_exist = True
             filepath, h, dups = x
             self.assertNotIn(filepath, dups)
@@ -44,9 +47,9 @@ class TestSweeper(unittest.TestCase):
         self.assertTrue(dups_exist)
 
     def test_iter_file_dups_nodups(self):
-        it = iter_file_dups([os.path.join(mydir, 'testfiles_nodups')])
+        swp = Sweeper([os.path.join(mydir, 'testfiles_nodups')])
         dups_exist = False
-        for x in it:
+        for x in swp:
             dups_exist = True
             break
         self.assertFalse(dups_exist)