Ignore version control artifacts by default when scanning. #35

Author: pombredanne

src/scancode/cli.py

@@ -24,11 +24,14 @@
 
 from __future__ import print_function, absolute_import
 
+import os
+from functools import partial
 import json
 
 import click
 
 from commoncode.fileutils import file_iter
+from commoncode import ignore
 
 from scancode import __version__ as version
 from scancode.api import as_html
@@ -39,7 +42,6 @@
 from scancode.api import get_licenses
 from scancode.api import HtmlAppAssetCopyWarning
 from scancode.api import HtmlAppAssetCopyError
-import os
 
 
 info_text = '''
@@ -268,13 +270,16 @@ def scancode(ctx, input, output_file, extract, copyright, license, format, verbo
         click.secho('Scanning files...', fg='green')
         results = []
 
+        ignored = partial(ignore.is_ignored, ignores=ignore.ignores_VCS, unignores={})
+        files = file_iter(abs_input, ignored=ignored)
+
         if not verbose:
             # only display a progress bar
-            with click.progressbar(file_iter(abs_input), show_pos=True) as files:
+            with click.progressbar(files, show_pos=True) as files:
                 for input_file in files:
                     results.append(scan_one(input_file, copyright, license, verbose))
         else:
-            for input_file in file_iter(abs_input):
+            for input_file in file_iter(files):
                 results.append(scan_one(input_file, copyright, license, verbose))
 
         if format == 'html':

tests/commoncode/data/ignore/vcs.tgz

@@ -25,13 +25,15 @@
 from __future__ import absolute_import, print_function
 
 import os
+import json
 
 from click.testing import CliRunner
 
 from commoncode.testcase import FileBasedTesting
-from scancode import cli
 from commoncode.fileutils import as_posixpath
 
+from scancode import cli
+
 
 class TestCommandLine(FileBasedTesting):
     test_data_dir = os.path.join(os.path.dirname(__file__), 'data')
@@ -85,7 +87,7 @@ def test_extract_option_works_with_relative_paths(self):
         scancode_tmp = join(scancode_root, 'tmp')
         fileutils.create_dir(scancode_tmp)
         scancode_root_abs = abspath(scancode_root)
-        test_src_dir = tempfile.mkdtemp(dir=scancode_tmp).replace(scancode_root_abs,  '').strip('\\/')
+        test_src_dir = tempfile.mkdtemp(dir=scancode_tmp).replace(scancode_root_abs, '').strip('\\/')
         test_file = self.get_test_loc('extract_relative_path/basic.zip')
         shutil.copy(test_file, test_src_dir)
         test_src_file = join(test_src_dir, 'basic.zip')
@@ -98,8 +100,8 @@ def test_extract_option_works_with_relative_paths(self):
         assert not 'WARNING' in result.output
         assert not 'ERROR' in result.output
         expected = ['/c/a/a.txt', '/c/b/a.txt', '/c/c/a.txt']
-        file_result  = [as_posixpath(f.replace(test_tgt_dir, '')) for f in fileutils.file_iter(test_tgt_dir)]
-        assert sorted(expected)==sorted(file_result)
+        file_result = [as_posixpath(f.replace(test_tgt_dir, '')) for f in fileutils.file_iter(test_tgt_dir)]
+        assert sorted(expected) == sorted(file_result)
 
     def test_copyright_option_detects_copyrights(self):
         test_dir = self.get_test_loc('copyright', copy=True)
@@ -120,3 +122,15 @@ def test_license_option_detects_licenses(self):
         assert 'Scanning done' in result.output
         assert os.path.exists(output_json)
         assert len(open(output_json).read()) > 10
+
+    def test_scancode_skip_vcs_files_and_dirs_by_default(self):
+        test_dir = self.extract_test_tar('ignore/vcs.tgz')
+        runner = CliRunner()
+        output_json = self.get_temp_file('json')
+        result = runner.invoke(cli.scancode, ['--copyright', test_dir, output_json])
+        assert result.exit_code == 0
+        with open(output_json) as res:
+            scan_result = json.load(res)
+        # a single test.tst file that is not a VCS file should be listed
+        assert 1 == scan_result['count']
+        assert scan_result['results'][0]['location'].endswith('vcs.tgz/vcs/test.txt')