Add --include --exclude to s3 ls

awscli/customizations/s3/subcommands.py

@@ -35,6 +35,7 @@
 from awscli.customizations.s3.syncstrategy.base import MissingFileSync, \
     SizeAndLastModifiedSync, NeverSync
 from awscli.customizations.s3 import transferconfig
+import fnmatch
 
 
 LOGGER = logging.getLogger(__name__)
@@ -461,7 +462,7 @@ class ListCommand(S3Command):
     USAGE = "<S3Uri> or NONE"
     ARG_TABLE = [{'name': 'paths', 'nargs': '?', 'default': 's3://',
                   'positional_arg': True, 'synopsis': USAGE}, RECURSIVE,
-                 PAGE_SIZE, HUMAN_READABLE, SUMMARIZE, REQUEST_PAYER]
+                 PAGE_SIZE, HUMAN_READABLE, SUMMARIZE, REQUEST_PAYER, INCLUDE, EXCLUDE]
 
     def _run_main(self, parsed_args, parsed_globals):
         super(ListCommand, self)._run_main(parsed_args, parsed_globals)
@@ -470,6 +471,8 @@ def _run_main(self, parsed_args, parsed_globals):
         self._size_accumulator = 0
         self._total_objects = 0
         self._human_readable = parsed_args.human_readable
+        self.filters = parsed_args.filters
+
         path = parsed_args.paths
         if path.startswith('s3://'):
             path = path[5:]
@@ -512,6 +515,27 @@ def _list_all_objects(self, bucket, key, page_size=None,
         for response_data in iterator:
             self._display_page(response_data)
 
+    def _is_match_pattern(self, pattern_type, path_pattern, file_path):
+        file_status = None 
+
+        is_match = fnmatch.fnmatch(file_path, path_pattern)
+        if is_match and pattern_type == 'include':
+            file_status = True
+            LOGGER.debug("%s matched include filter: %s",
+                        file_path, path_pattern)
+        elif is_match and pattern_type == 'exclude':
+            file_status = False
+            LOGGER.debug("%s matched exclude filter: %s",
+                        file_path, path_pattern)
+        else:
+            LOGGER.debug("%s did not match %s filter: %s",
+                        file_path, pattern_type, path_pattern)
+            if pattern_type == 'include':
+                file_status = False
+            else:
+                file_status = True
+        return file_status
+
     def _display_page(self, response_data, use_basename=True):
         common_prefixes = response_data.get('CommonPrefixes', [])
         contents = response_data.get('Contents', [])
@@ -523,20 +547,38 @@ def _display_page(self, response_data, use_basename=True):
             prefix = prefix_components[-2]
             pre_string = "PRE".rjust(30, " ")
             print_str = pre_string + ' ' + prefix + '/\n'
-            uni_print(print_str)
+
         for content in contents:
             last_mod_str = self._make_last_mod_str(content['LastModified'])
-            self._size_accumulator += int(content['Size'])
-            self._total_objects += 1
-            size_str = self._make_size_str(content['Size'])
+
             if use_basename:
                 filename_components = content['Key'].split('/')
                 filename = filename_components[-1]
             else:
                 filename = content['Key']
-            print_str = last_mod_str + ' ' + size_str + ' ' + \
-                filename + '\n'
-            uni_print(print_str)
+
+            file_status = None
+
+            if self.filters is not None:
+                for filter in self.filters:
+                    pattern_type = filter[0].lstrip('-')
+                    path_pattern = filter[1]
+                    file_status = self._is_match_pattern(pattern_type, path_pattern, filename)
+
+                if file_status is True:
+                    self._size_accumulator += int(content['Size'])
+                    self._total_objects += 1
+                    size_str = self._make_size_str(content['Size'])
+                    print_str = last_mod_str + ' ' + size_str + ' ' + \
+                        filename + '\n'
+                    uni_print(print_str)
+            else:
+                self._size_accumulator += int(content['Size'])
+                self._total_objects += 1
+                size_str = self._make_size_str(content['Size'])
+                print_str = last_mod_str + ' ' + size_str + ' ' + \
+                        filename + '\n'
+                uni_print(print_str)
         self._at_first_page = False
 
     def _list_all_buckets(self):

awscli/examples/s3/ls.rst

@@ -8,7 +8,7 @@ Output::
 
     2013-07-11 17:08:50 mybucket
     2013-07-24 14:55:44 mybucket2
-    
+
 **Example 2: Listing all prefixes and objects in a bucket**
 
 The following ``ls`` command lists objects and common prefixes under a specified bucket and prefix.  In this example, the user owns the bucket ``mybucket`` with the objects ``test.txt`` and ``somePrefix/test.txt``.  The ``LastWriteTime`` and ``Length`` are arbitrary. Note that since the ``ls`` command has no interaction with the local filesystem, the ``s3://`` URI scheme is not required to resolve ambiguity and may be omitted::
@@ -29,7 +29,7 @@ The following ``ls`` command lists objects and common prefixes under a specified
 Output::
 
     None
-    
+
 **Example 4: Recursively listing all prefixes and objects in a bucket**
 
 The following ``ls`` command will recursively list objects in a bucket.  Rather than showing ``PRE dirname/`` in the output, all the content in a bucket will be listed in order::
@@ -69,7 +69,21 @@ Output::
     2013-09-02 21:32:57  398 Bytes z.txt
 
     Total Objects: 10
-       Total Size: 2.9 MiB
+    Total Size: 2.9 MiB
+
+You can combine ``--exclude`` and ``--include`` options to list only objects that match a pattern, excluding all others::
+
+   aws s3 ls s3://mybucket --recursive --human-readable --summarize --exclude "*" --include "*.txt"
+
+Output::
+
+   2013-09-02 21:37:53   10 Bytes a.txt
+   2013-09-02 21:32:57  398 Bytes z.txt
+
+   Total Objects: 2
+   Total Size: 408 Bytes
+
+**Listing from an S3 access point**
 
 **Example 6: Listing from an S3 access point**
 

tests/unit/customizations/s3/test_subcommands.py

@@ -95,7 +95,7 @@ def test_ls_command_for_bucket(self):
         ls_command = ListCommand(self.session)
         parsed_args = FakeArgs(paths='s3://mybucket/', dir_op=False,
                                page_size='5', human_readable=False,
-                               summarize=False, request_payer=None)
+                               summarize=False, request_payer=None, filters=None)
         parsed_globals = mock.Mock()
         ls_command._run_main(parsed_args, parsed_globals)
         call = self.session.create_client.return_value.list_objects_v2
@@ -118,7 +118,7 @@ def test_ls_command_with_no_args(self):
                                  verify_ssl=None)
         parsed_args = FakeArgs(dir_op=False, paths='s3://',
                                human_readable=False, summarize=False,
-                               request_payer=None)
+                               request_payer=None, filters=None)
         ls_command._run_main(parsed_args, parsed_global)
         # We should only be a single call.
         call = self.session.create_client.return_value.list_buckets
@@ -139,7 +139,7 @@ def test_ls_with_verify_argument(self):
                                  verify_ssl=False)
         parsed_args = FakeArgs(paths='s3://', dir_op=False,
                                human_readable=False, summarize=False,
-                               request_payer=None)
+                               request_payer=None, filters=None)
         ls_command._run_main(parsed_args, parsed_global)
         # Verify get_client
         get_client = self.session.create_client
@@ -152,7 +152,7 @@ def test_ls_with_requester_pays(self):
         ls_command = ListCommand(self.session)
         parsed_args = FakeArgs(paths='s3://mybucket/', dir_op=False,
                                human_readable=False, summarize=False,
-                               request_payer='requester', page_size='5')
+                               request_payer='requester', page_size='5', filters=None)
         parsed_globals = mock.Mock()
         ls_command._run_main(parsed_args, parsed_globals)
         call = self.session.create_client.return_value.list_objects
@@ -171,6 +171,48 @@ def test_ls_with_requester_pays(self):
 
         paginate.assert_called_with(**ref_call_args)
 
+    def test_ls_with_filters(self):
+        ls_command = ListCommand(self.session)
+        parsed_args = FakeArgs(paths='s3://mybucket/', dir_op=False,
+                               page_size='5', human_readable=False,
+                               summarize=False, request_payer=None, filters=[['--include', '*', '--exclude', '*']])
+        parsed_globals = mock.Mock()
+        ls_command._run_main(parsed_args, parsed_globals)
+        call = self.session.create_client.return_value.list_objects_v2
+        paginate = self.session.create_client.return_value.get_paginator\
+            .return_value.paginate
+        # We should make no operation calls.
+        self.assertEqual(call.call_count, 0)
+        # And only a single pagination call to ListObjectsV2.
+        self.session.create_client.return_value.get_paginator.\
+            assert_called_with('list_objects_v2')
+        ref_call_args = {'Bucket': u'mybucket', 'Delimiter': '/',
+                         'Prefix': u'',
+                         'PaginationConfig': {'PageSize': u'5'}}
+
+        paginate.assert_called_with(**ref_call_args)
+
+    def test_ls_is_match_pattern(self):
+        ls_command = ListCommand(self.session)
+        # Match with Include
+        ls_command._is_match_pattern = MagicMock(return_value=True)
+        file_status = ls_command._is_match_pattern('include', '*.txt', '/foo/bar.txt', is_match=True)
+        self.assertEqual(file_status, True)
+
+        # Match with Exclude
+        ls_command._is_match_pattern = MagicMock(return_value=False)
+        file_status = ls_command._is_match_pattern('exclude', '*.txt', '/foo/bar.txt', is_match=True)
+        self.assertEqual(file_status, False)
+
+        # Not match with Include 
+        ls_command._is_match_pattern = MagicMock(return_value=False)
+        file_status = ls_command._is_match_pattern('include', '*.zip', '/foo/bar.txt', is_match=False)
+        self.assertEqual(file_status, False)
+
+        # Not match with Exclude
+        ls_command._is_match_pattern = MagicMock(return_value=True)
+        file_status = ls_command._is_match_pattern('exclude', '*.zip', '/foo/bar.txt', is_match=False)
+        self.assertEqual(file_status, True)
 
 class CommandArchitectureTest(BaseAWSCommandParamsTest):
     def setUp(self):