Return package details in summary #2717

CHANGELOG.rst

@@ -64,12 +64,30 @@ Outputs:
 
 
 
+30.1.0 - 2021-09-25
+--------------------
+
+This is a bug fix release for these bugs:
+
+- https://github.com/nexB/scancode-toolkit/issues/2717
+
+We now return the package in the summaries as before.
+
+There is also a minor API change: we no longer return a count of "null" empty
+values in the summaries for license, copyrights, etc.
+
+
+Thank you to:
+- Thomas Druez @tdruez 
+
+
+
 30.0.1 - 2021-09-24
 --------------------
 
 This is a minor bug fix release for these bugs:
 
-- https://github.com/nexB/scancode-toolkit/issues/2713
+- https://github.com/nexB/commoncode/issues/31
 - https://github.com/nexB/scancode-toolkit/issues/2713
 
 We now correctly work with all supported Click versions. 

setup-mini.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = scancode-toolkit-mini
-version = 30.0.1
+version = 30.1.0
 license = Apache-2.0 AND CC-BY-4.0 AND LicenseRef-scancode-other-permissive AND LicenseRef-scancode-other-copyleft
 
 description = ScanCode is a tool to scan code for license, copyright, package and their documented dependencies and other interesting facts. scancode-toolkit-mini is a special build that does not come with pre-built binary dependencies by default. These are instead installed separately or with the extra_requires scancode-toolkit-mini[full]

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = scancode-toolkit
-version = 30.0.1
+version = 30.1.0
 license = Apache-2.0 AND CC-BY-4.0 AND LicenseRef-scancode-other-permissive AND LicenseRef-scancode-other-copyleft
 
 description = ScanCode is a tool to scan code for license, copyright, package and their documented dependencies and other interesting facts.

src/scancode_config.py

@@ -77,7 +77,7 @@ def _create_dir(location):
 
 # in case package is not installed or we do not have setutools/pkg_resources
 # on hand fall back to this version
-__version__ = '30.0.1'
+__version__ = '30.1.0'
 
 # used to warn user when the version is out of date
 __release_date__ = datetime.datetime(2021, 9, 24)

src/summarycode/summarizer.py

@@ -40,49 +40,7 @@ def logger_debug(*args):
         return logger.debug(' '.join(isinstance(a, str) and a or repr(a) for a in args))
 
 """
-top_level:
-    - license_expressions:
-        - count: 1
-          value: gpl-2.0
-    - holders:
-        - count: 1
-          value: RedHat Inc.
-
-by_facet:
-    facet: core
-        - license_expressions:
-            - count: 10
-              value: gpl-2.0 or bsd-new
-            - count: 2
-              value: mit
-        - programming_language:
-            - count: 10
-              value: java
-        - holders:
-            - count: 10
-              value: RedHat Inc.
-    facet: dev
-        - license_expressions:
-            - count: 23
-              value: gpl-2.0
-        - holders:
-            - count: 20
-              value: RedHat Inc.
-            - count: 10
-              value: none
-        - programming_languages:
-            - count: 34
-              value: java
-all:
-    - license_expressions:
-        - count: 10
-          value: gpl-2.0 or bsd-new
-    - programming_language:
-        - count: 10
-          value: java
-    - holders:
-        - count: 10
-          value: RedHat Inc.
+Create summarized scan data.
 """
 
 
@@ -205,8 +163,10 @@ def license_summarizer(resource, children, keep_details=False):
         child_summaries = get_resource_summary(child, key=LIC_EXP, as_attribute=keep_details) or []
         for child_summary in child_summaries:
             # TODO: review this: this feels rather weird
-            values = [child_summary['value']] * child_summary['count']
-            license_expressions.extend(values)
+            child_sum_val = child_summary.get('value')
+            if child_sum_val:
+                values = [child_sum_val] * child_summary['count']
+                license_expressions.extend(values)
 
     # summarize proper
     licenses_counter = summarize_licenses(license_expressions)
@@ -245,8 +205,10 @@ def language_summarizer(resource, children, keep_details=False):
     for child in children:
         child_summaries = get_resource_summary(child, key=PROG_LANG, as_attribute=keep_details) or []
         for child_summary in child_summaries:
-            values = [child_summary['value']] * child_summary['count']
-            languages.extend(values)
+            child_sum_val = child_summary.get('value')
+            if child_sum_val:
+                values = [child_sum_val] * child_summary['count']
+                languages.extend(values)
 
     # summarize proper
     languages_counter = summarize_languages(languages)
@@ -264,11 +226,23 @@ def summarize_languages(languages):
     return Counter(languages)
 
 
+SUMMARIZABLE_ATTRS = set([
+    'license_expressions',
+    'copyrights',
+    'holders',
+    'authors',
+    'programming_language',
+    # 'packages',
+])
+
+
 def summarize_values(values, attribute):
     """
     Given a list of `values` for a given `attribute`, return a mapping of
     {value: count of occurences} using a summarization specific to the attribute.
     """
+    if attribute not in SUMMARIZABLE_ATTRS:
+        return {}
     from summarycode.copyright_summary import summarize_holders
     from summarycode.copyright_summary import summarize_copyrights
 
@@ -278,7 +252,6 @@ def summarize_values(values, attribute):
         holders=summarize_holders,
         authors=summarize_holders,
         programming_language=summarize_languages,
-        packages=summarize_packages,
     )
     return value_summarizers_by_attr[attribute](values)
 
@@ -317,23 +290,14 @@ def summarize_codebase_key_files(codebase, **kwargs):
     """
     Summarize codebase key files.
     """
-    summarizable_attributes = codebase.attributes.summary.keys()
-    if TRACE: logger_debug('summarizable_attributes:', summarizable_attributes)
-
-    # TODO: we cannot summarize packages with "key files for now
-    really_summarizable_attributes = set([
-        'license_expressions',
-        'copyrights',
-        'holders',
-        'authors',
-        'programming_language',
-        # 'packages',
-    ])
-    summarizable_attributes = [k for k in summarizable_attributes
-        if k in really_summarizable_attributes]
+    summarizables = codebase.attributes.summary.keys()
+    if TRACE: logger_debug('summarizables:', summarizables)
+
+    # TODO: we cannot summarize packages with "key files" for now
+    summarizables = [k for k in summarizables if k in SUMMARIZABLE_ATTRS]
 
     # create one counter for each summarized attribute
-    summarizable_values_by_key = dict([(key, []) for key in summarizable_attributes])
+    summarizable_values_by_key = dict([(key, []) for key in summarizables])
 
     # filter to get only key files
     key_files = (res for res in codebase.walk(topdown=True)
@@ -347,10 +311,14 @@ def summarize_codebase_key_files(codebase, **kwargs):
             res_summaries = get_resource_summary(resource, key=key, as_attribute=False) or []
             for summary in res_summaries:
                 # each summary is a mapping with value/count: we transform back to values
-                values.extend([summary['value']] * summary['count'])
+                sum_value = summary.get('value')
+                if sum_value:
+                    values.extend([sum_value] * summary['count'])
 
     summary_counters = []
     for key, values in summarizable_values_by_key.items():
+        if key not in SUMMARIZABLE_ATTRS:
+            continue
         summarized = summarize_values(values, key)
         summary_counters.append((key, summarized))
 
@@ -394,13 +362,13 @@ def summarize_codebase_by_facet(codebase, **kwargs):
     """
     from summarycode import facet as facet_module
 
-    summarizable_attributes = codebase.attributes.summary.keys()
+    summarizable = codebase.attributes.summary.keys()
     if TRACE:
-        logger_debug('summarize_codebase_by_facet for attributes:', summarizable_attributes)
+        logger_debug('summarize_codebase_by_facet for attributes:', summarizable)
 
     # create one group of by-facet values lists for each summarized attribute
     summarizable_values_by_key_by_facet = dict([
-        (facet, dict([(key, []) for key in summarizable_attributes]))
+        (facet, dict([(key, []) for key in summarizable]))
         for facet in facet_module.FACETS
     ])
 
@@ -417,7 +385,9 @@ def summarize_codebase_by_facet(codebase, **kwargs):
                 res_summaries = get_resource_summary(resource, key=key, as_attribute=False) or []
                 for summary in res_summaries:
                     # each summary is a mapping with value/count: we transform back to discrete values
-                    values.extend([summary['value']] * summary['count'])
+                    sum_value = summary.get('value')
+                    if sum_value:
+                        values.extend([sum_value] * summary['count'])
 
     final_summaries = []
     for facet, summarizable_values_by_key in summarizable_values_by_key_by_facet.items():
@@ -480,28 +450,11 @@ def package_summarizer(resource, children, keep_details=False):
         logger_debug('package_summarizer: for:', resource,
                      'packages are:', packs)
 
-    package_urls = []
-    for package in packages:
-        purl = package.get('purl')
-        if purl:
-            package_urls.append(purl)
+    # Collect direct children packages summary
+    for child in children:
+        child_summaries = get_resource_summary(child, key='packages', as_attribute=False) or []
+        packages.extend(child_summaries)
 
     # summarize proper
-    packages_counter = summarize_packages(package_urls)
-    summarized = sorted_counter(packages_counter)
-    set_resource_summary(
-        resource=resource,
-        key='packages',
-        value=summarized,
-        as_attribute=keep_details,
-    )
-
-    return summarized
-
-
-def summarize_packages(package_urls):
-    """
-    Given a list of package urls, return a mapping of {expression: count
-    of occurences}
-    """
-    return Counter(package_urls)
+    set_resource_summary(resource, key='packages', value=packages, as_attribute=False)
+    return packages

tests/summarycode/data/classify/cli.expected.json

@@ -9,6 +9,7 @@
         "--json-pp": "<file>"
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {

tests/summarycode/data/copyright_summary/summary.expected.json

@@ -9,6 +9,7 @@
         "--summary": true
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {

tests/summarycode/data/copyright_summary/summary2.expected.json

@@ -9,6 +9,7 @@
         "--summary": true
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {

tests/summarycode/data/copyright_summary/summary_details.expected.json

@@ -9,6 +9,7 @@
         "--summary-with-details": true
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {

tests/summarycode/data/copyright_summary/summary_details.expected2.json

@@ -9,6 +9,7 @@
         "--summary-with-details": true
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {

tests/summarycode/data/copyright_summary/summary_key_files.expected.json

@@ -12,6 +12,7 @@
         "--summary-key-files": true
       },
       "notice": "Generated with ScanCode and provided on an \"AS IS\" BASIS, WITHOUT WARRANTIES\nOR CONDITIONS OF ANY KIND, either express or implied. No content created from\nScanCode should be considered or used as legal advice. Consult an Attorney\nfor any legal advice.\nScanCode is a free software code scanning tool from nexB Inc. and others.\nVisit https://github.com/nexB/scancode-toolkit/ for support and download.",
+      "output_format_version": "1.0.0",
       "message": null,
       "errors": [],
       "extra_data": {
@@ -148,10 +149,6 @@
         "value": "Java",
         "count": 7
       },
-      {
-        "value": null,
-        "count": 2
-      },
       {
         "value": "C#",
         "count": 2
@@ -163,30 +160,10 @@
     ]
   },
   "summary_of_key_files": {
-    "copyrights": [
-      {
-        "value": null,
-        "count": 1
-      }
-    ],
-    "holders": [
-      {
-        "value": null,
-        "count": 1
-      }
-    ],
-    "authors": [
-      {
-        "value": null,
-        "count": 1
-      }
-    ],
-    "programming_language": [
-      {
-        "value": null,
-        "count": 1
-      }
-    ]
+    "copyrights": [],
+    "holders": [],
+    "authors": [],
+    "programming_language": []
   },
   "files": [
     {