Add is_notice flag to the --classify option, issue aboutcode-org#3822

Signed-off-by: Aayush Kumar <[email protected]>
aayushkdev · Feb 11, 2025 · ba6181f · ba6181f
1 parent e795bc6
commit ba6181f
Show file tree

Hide file tree

Showing 51 changed files with 414 additions and 15 deletions.
diff --git a/docs/source/cli-reference/help-text-options.rst b/docs/source/cli-reference/help-text-options.rst
@@ -154,8 +154,8 @@ The Following Help Text is displayed, i.e. This is the help text for Scancode Ve
                                scans for key, top-level files. Key files are top-
                                level codebase files such as COPYING, README and
                                package manifests as reported by the --classify
-                               option "is_legal", "is_readme", "is_manifest" and
-                               "is_top_level" flags.
+                               option "is_legal", "is_readme", "is_manifest",
+                               "is_notice" and "is_top_level" flags.
       --tallies-with-details   Compute tallies of license, copyright and other scans
                                at the codebase level, keeping intermediate details
                                at the file and directory level.
@@ -639,7 +639,7 @@ The Following Text is displayed, i.e. This is the available plugins for Scancode
     required_plugins:
     options:
       help_group: post-scan, name: tallies_key_files: --tallies-key-files
-        help: Compute tallies for license, copyright and other scans for key, top-level files. Key files are top-level codebase files such as COPYING, README and package manifests as reported by the --classify option "is_legal", "is_readme", "is_manifest" and "is_top_level" flags.
+        help: Compute tallies for license, copyright and other scans for key, top-level files. Key files are top-level codebase files such as COPYING, README and package manifests as reported by the --classify option "is_legal", "is_readme", "is_manifest", "is_notice" and "is_top_level" flags.
     doc:
       Compute tallies of a scan at the codebase level for only key files.
 
@@ -669,7 +669,7 @@ The Following Text is displayed, i.e. This is the available plugins for Scancode
   --------------------------------------------
   Plugin: scancode_pre_scan:classify  class: summarycode.classify_plugin:FileClassifier
     codebase_attributes:
-    resource_attributes: is_legal, is_manifest, is_readme, is_top_level, is_key_file
+    resource_attributes: is_legal, is_manifest, is_readme, is_top_level, is_key_file, is_notice
     sort_order: 30
     required_plugins:
     options:

diff --git a/docs/source/cli-reference/scan-options-post.rst b/docs/source/cli-reference/scan-options-post.rst
@@ -1018,6 +1018,7 @@ To see all plugins available via command line help, use ``--plugins``.
         - "is_readme"
         - "is_top_level"
         - "is_key_file"
+        - "is_notice"
 
     A key-file is a top-level file, that is either a legal (LICENSE/COPYING etc), manifest or a
     readme file.
@@ -1087,6 +1088,7 @@ To see all plugins available via command line help, use ``--plugins``.
             "is_readme": false,
             "is_top_level": true,
             "is_key_file": false,
+            "is_notice": false,
             "tallies": {
               "detected_license_expression": [
                 {

diff --git a/docs/source/cli-reference/scan-options-pre.rst b/docs/source/cli-reference/scan-options-pre.rst
@@ -62,6 +62,7 @@ Pre-Scan Options
     - readme
     - top-level
     - manifest
+    - notice
 
         A manifest file in computing is a file containing metadata for a group of accompanying
         files that are part of a set or coherent unit.
@@ -80,6 +81,7 @@ Pre-Scan Options
         "is_readme": true,
         "is_top_level": true,
         "is_key_file": true
+        "is_notice": false,
       }
 
 ----

diff --git a/docs/source/rst_snippets/post_scan_options.rst b/docs/source/rst_snippets/post_scan_options.rst
@@ -53,9 +53,9 @@ All "Post-Scan" Options
                          for key, top-level files, with occurrence counts.
                          Key files are top-level codebase files such as
                          COPYING, README and package manifests as reported
-                         by the ``--classify`` option: "is_legal",
-                         "is_readme", "is_manifest" and "is_top_level"
-                         flags.
+                         by the ``--classify`` option: "is_legal"
+                         , "is_readme", "is_manifest", "is_notice" and
+                         "is_top_level" flags.
 
                          Sub-Option of: ``--classify`` and ``--summary``.
 

diff --git a/src/summarycode/classify.py b/src/summarycode/classify.py
@@ -91,6 +91,9 @@ def get_relative_path(root_path, path):
     'readme',
 )
 
+NOTICE_STARTS_ENDS = (
+    "notice",
+)
 
 def check_resource_name_start_and_end(resource, STARTS_ENDS):
     """
@@ -111,6 +114,7 @@ def set_classification_flags(resource,
     _LEGAL=LEGAL_STARTS_ENDS,
     _MANIF=MANIFEST_ENDS,
     _README=README_STARTS_ENDS,
+    _NOTICE=NOTICE_STARTS_ENDS,
 ):
     """
     Set classification flags on the `resource` Resource
@@ -119,8 +123,9 @@ def set_classification_flags(resource,
 
     resource.is_legal = is_legal = check_resource_name_start_and_end(resource, _LEGAL)
     resource.is_readme = is_readme = check_resource_name_start_and_end(resource, _README)
+    resource.is_notice = is_notice = check_resource_name_start_and_end(resource, _NOTICE)
     # FIXME: this will never be picked up as this is NOT available in a pre-scan plugin
     has_package_data = bool(getattr(resource, 'package_data', False))
     resource.is_manifest = is_manifest = path.endswith(_MANIF) or has_package_data
-    resource.is_key_file = (resource.is_top_level and (is_readme or is_legal or is_manifest))
+    resource.is_key_file = (resource.is_top_level and (is_readme or is_legal or is_manifest or is_notice))
     return resource
diff --git a/src/summarycode/classify_plugin.py b/src/summarycode/classify_plugin.py
@@ -75,7 +75,10 @@ class FileClassifier(PostScanPlugin):
 
         ('is_key_file',
          Boolean(help='True if this file is "top-level" file and either a '
-                      'legal, readme or manifest file.')),
+                      'legal, notice, readme or manifest file.')),
+
+        ('is_notice',
+        Boolean(help='True if this file is likely a notice file')),
 
 #         ('is_doc',
 #          Boolean(help='True if this file is likely a documentation file.')),

diff --git a/src/summarycode/tallies.py b/src/summarycode/tallies.py
@@ -304,7 +304,7 @@ class KeyFilesTallies(PostScanPlugin):
             help='Compute tallies for license, copyright and other scans for key, '
                  'top-level files. Key files are top-level codebase files such '
                  'as COPYING, README and package manifests as reported by the '
-                 '--classify option "is_legal", "is_readme", "is_manifest" '
+                 '--classify option "is_legal", "is_readme", "is_manifest", "is_notice" '
                  'and "is_top_level" flags.',
             help_group=POST_SCAN_GROUP,
             required_options=['classify', 'tallies']
@@ -334,7 +334,7 @@ def tally_codebase_key_files(codebase, field='tallies', **kwargs):
     # filter to get only key files
     key_files = (res for res in codebase.walk(topdown=True)
                  if (res.is_file and res.is_top_level
-                     and (res.is_readme or res.is_legal or res.is_manifest)))
+                     and (res.is_readme or res.is_legal or res.is_manifest or res.is_notice)))
 
     for resource in key_files:
         for key, values in talliable_values_by_key.items():

diff --git a/tests/formattedcode/data/common/manifests-expected.yaml b/tests/formattedcode/data/common/manifests-expected.yaml
@@ -1934,6 +1934,7 @@ files:
     is_readme: no
     is_top_level: yes
     is_key_file: no
+    is_notice: no
     detected_license_expression:
     detected_license_expression_spdx:
     license_detections: []
@@ -1974,6 +1975,7 @@ files:
     is_readme: no
     is_top_level: yes
     is_key_file: no
+    is_notice: no
     detected_license_expression:
     detected_license_expression_spdx:
     license_detections: []
@@ -2092,6 +2094,7 @@ files:
     is_readme: no
     is_top_level: no
     is_key_file: no
+    is_notice: no
     detected_license_expression: cddl-1.0
     detected_license_expression_spdx: CDDL-1.0
     license_detections:
@@ -2173,6 +2176,7 @@ files:
     is_readme: no
     is_top_level: yes
     is_key_file: no
+    is_notice: no
     detected_license_expression:
     detected_license_expression_spdx:
     license_detections: []
@@ -2390,6 +2394,7 @@ files:
     is_readme: no
     is_top_level: no
     is_key_file: no
+    is_notice: no
     detected_license_expression: apache-2.0
     detected_license_expression_spdx: Apache-2.0
     license_detections:
@@ -2481,6 +2486,7 @@ files:
     is_readme: no
     is_top_level: yes
     is_key_file: no
+    is_notice: no
     detected_license_expression:
     detected_license_expression_spdx:
     license_detections: []
@@ -2631,6 +2637,7 @@ files:
     is_readme: no
     is_top_level: no
     is_key_file: no
+    is_notice: no
     detected_license_expression: mit
     detected_license_expression_spdx: MIT
     license_detections:
@@ -2702,6 +2709,7 @@ files:
     is_readme: no
     is_top_level: yes
     is_key_file: no
+    is_notice: no
     detected_license_expression:
     detected_license_expression_spdx:
     license_detections: []
@@ -2935,6 +2943,7 @@ files:
     is_readme: no
     is_top_level: no
     is_key_file: no
+    is_notice: no
     detected_license_expression: lgpl-3.0
     detected_license_expression_spdx: LGPL-3.0-only
     license_detections: