Merge pull request #2244 from nexB/2208-yaml-output

Add basic YAML output plugin #2208

Author: pombredanne

setup.cfg

@@ -192,6 +192,7 @@ scancode_output =
     jsonlines = formattedcode.output_jsonlines:JsonLinesOutput
     template = formattedcode.output_html:CustomTemplateOutput
     debian = formattedcode.output_debian:DebianCopyrightOutput
+    yaml = formattedcode.output_yaml:YamlOutput
 
 
 [tool:pytest]

src/formattedcode/output_json.py

@@ -98,7 +98,12 @@ def write_results(codebase, output_file, pretty=False, **kwargs):
         close_fd = True
 
     # Begin wri'w' JSON to `output_file`
-    with jsonstreams.Stream(jsonstreams.Type.object, fd=output_file, close_fd=close_fd, **jsonstreams_kwargs) as s:
+    with jsonstreams.Stream(
+        jsonstreams.Type.object,
+        fd=output_file,
+        close_fd=close_fd,
+        **jsonstreams_kwargs
+    ) as s:
         # Write headers
         codebase.add_files_count_to_current_header()
         codebase_headers = codebase.get_headers()

src/formattedcode/output_yaml.py

@@ -0,0 +1,50 @@
+#
+# Copyright (c) nexB Inc. and others. All rights reserved.
+    # ScanCode is a trademark of nexB Inc.
+# SPDX-License-Identifier: Apache-2.0
+# See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
+# See https://github.com/nexB/scancode-toolkit for support or download.
+# See https://aboutcode.org for more information about nexB OSS projects.
+#
+
+import saneyaml
+
+from commoncode.cliutils import PluggableCommandLineOption
+from commoncode.cliutils import OUTPUT_GROUP
+from formattedcode import FileOptionType
+from formattedcode import output_json
+from plugincode.output import output_impl
+from plugincode.output import OutputPlugin
+
+"""
+Output plugin to write scan results as YAML.
+"""
+
+
+@output_impl
+class YamlOutput(OutputPlugin):
+
+    options = [
+        PluggableCommandLineOption(('--yaml', 'output_yaml',),
+            type=FileOptionType(mode='w', encoding='utf-8', lazy=True),
+            metavar='FILE',
+            help='Write scan output as YAML to FILE.',
+            help_group=OUTPUT_GROUP,
+            sort_order=20
+        ),
+    ]
+
+    def is_enabled(self, output_yaml, **kwargs):
+        return output_yaml
+
+    def process_codebase(self, codebase, output_yaml, **kwargs):
+        results = output_json.get_results(codebase, as_list=True, **kwargs)
+        write_yaml(results, output_file=output_yaml, pretty=False)
+
+
+def write_yaml(results, output_file, **kwargs):
+    """
+    Write `results` to the `output_file` opened file-like object.
+    """
+    output_file.write(saneyaml.dump(results, indent=4))
+    output_file.write('\n')

src/scancode/cli_test_utils.py

@@ -17,11 +17,11 @@
 
 
 def run_scan_plain(
-    options, 
-    cwd=None, 
-    test_mode=True, 
-    expected_rc=0, 
-    env=None, 
+    options,
+    cwd=None,
+    test_mode=True,
+    expected_rc=0,
+    env=None,
     retry=True,
 ):
     """
@@ -229,6 +229,22 @@ def load_json_result_from_string(string, remove_file_date=False):
     return scan_results
 
 
+def cleanup_scan(scan_results, remove_file_date=False):
+    """
+    Cleanup in place the ``scan_results`` mapping for dates, headers and
+    other variable data that break tests otherwise.
+    """
+    # clean new headers attributes
+    streamline_headers(scan_results.get('headers', []))
+    # clean file_level attributes
+    for scanned_file in scan_results['files']:
+        streamline_scanned_file(scanned_file, remove_file_date)
+
+    # TODO: remove sort, this should no longer be needed
+    scan_results['files'].sort(key=lambda x: x['path'])
+    return scan_results
+
+
 def streamline_errors(errors):
     """
     Modify the `errors` list in place to make it easier to test