Support LicenseDetection models in load_inventory

Signed-off-by: Ayan Sinha Mahapatra <ayansmahapatra@gmail.com>

Author: AyanSinhaMahapatra

scanpipe/pipes/__init__.py

@@ -37,6 +37,7 @@
 from scanpipe.models import CodebaseResource
 from scanpipe.models import DiscoveredDependency
 from scanpipe.models import DiscoveredPackage
+from scanpipe.models import DiscoveredLicense
 from scanpipe.pipes import scancode
 
 logger = logging.getLogger("scanpipe.pipes")
@@ -245,6 +246,37 @@ def update_or_create_dependency(
     return dependency
 
 
+def update_or_create_license_detection(project, detection_data):
+    """
+    Get, update or create a DiscoveredLicense object then return it.
+    Use the `project` and `detection_data` mapping to lookup and creates the
+    DiscoveredLicense using its detection identifier as a unique key.
+    """
+    detection_identifier = detection_data["identifier"]
+
+    license_detection = project.discoveredlicenses.get_or_none(
+        identifier=detection_identifier,
+    )
+    detection_data = _clean_license_detection_data(detection_data)
+
+    if license_detection:
+        license_detection.update_from_data(detection_data)
+    else:
+        license_detection = DiscoveredLicense.create_from_data(
+            project,
+            detection_data,
+        )
+
+    return license_detection
+
+
+def _clean_license_detection_data(detection_data):
+    detection_data = detection_data.copy()
+    matches = detection_data.pop("sample_matches")
+    detection_data["matches"] = matches
+    return detection_data
+
+
 def get_or_create_relation(project, relation_data):
     """
     Get  or create a CodebaseRelation then return it.

scanpipe/pipes/input.py

@@ -35,6 +35,7 @@
 from scanpipe.models import CodebaseResource
 from scanpipe.models import DiscoveredDependency
 from scanpipe.models import DiscoveredPackage
+from scanpipe.models import DiscoveredLicense
 from scanpipe.pipes import scancode
 from scanpipe.pipes.output import mappings_key_by_fieldname
 
@@ -78,10 +79,11 @@ def is_archive(location):
 
 def load_inventory_from_toolkit_scan(project, input_location):
     """
-    Create packages, dependencies, and resources loaded from the ScanCode-toolkit scan
-    results located at ``input_location``.
+    Create license detections, packages, dependencies, and resources
+    loaded from the ScanCode-toolkit scan results located at ``input_location``.
     """
     scanned_codebase = scancode.get_virtual_codebase(project, input_location)
+    scancode.create_discovered_licenses(project, scanned_codebase)
     scancode.create_discovered_packages(project, scanned_codebase)
     scancode.create_codebase_resources(project, scanned_codebase)
     scancode.create_discovered_dependencies(
@@ -91,9 +93,12 @@ def load_inventory_from_toolkit_scan(project, input_location):
 
 def load_inventory_from_scanpipe(project, scan_data):
     """
-    Create packages, dependencies, resources, and relations loaded from a ScanCode.io
-    JSON output provided as ``scan_data``.
+    Create license detections, packages, dependencies, resources, and relations
+    loaded from a ScanCode.io JSON output provided as ``scan_data``.
     """
+    for detection_data in scan_data.get("license_detections", []):
+        pipes.update_or_create_license_detection(project, detection_data)
+
     for package_data in scan_data.get("packages", []):
         pipes.update_or_create_package(project, package_data)
 
@@ -110,12 +115,14 @@ def load_inventory_from_scanpipe(project, scan_data):
 model_to_object_maker_func = {
     DiscoveredPackage: pipes.update_or_create_package,
     DiscoveredDependency: pipes.update_or_create_dependency,
+    DiscoveredLicense: pipes.update_or_create_license_detection,
     CodebaseResource: pipes.update_or_create_resource,
     CodebaseRelation: pipes.get_or_create_relation,
 }
 
 worksheet_name_to_model = {
     "PACKAGES": DiscoveredPackage,
+    "LICENSE_DETECTIONS": DiscoveredLicense,
     "RESOURCES": CodebaseResource,
     "DEPENDENCIES": DiscoveredDependency,
     "RELATIONS": CodebaseRelation,

scanpipe/pipes/scancode.py

@@ -586,6 +586,14 @@ def create_codebase_resources(project, scanned_codebase):
                 discovered_package=package,
             )
 
+        license_detections = getattr(scanned_resource, "license_detections", [])
+        for detection_data in license_detections:
+            detection_identifier = detection_data.get("identifier")
+            license_detection = project.discoveredlicenses.get_or_none(
+                identifier=detection_identifier
+            )
+            logger.debug(f"Add {codebase_resource} to {license_detection}")
+
 
 def create_discovered_packages(project, scanned_codebase):
     """
@@ -620,6 +628,17 @@ def create_discovered_dependencies(
             )
 
 
+def create_discovered_licenses(project, scanned_codebase):
+    """
+    Save the license detections of a ScanCode `scanned_codebase`
+    scancode.resource.Codebase object to the database as a DiscoveredLicense of
+    `project`. 
+    """
+    if hasattr(scanned_codebase.attributes, "license_detections"):
+        for detection_data in scanned_codebase.attributes.license_detections:
+            pipes.update_or_create_license_detection(project, detection_data)
+
+
 def set_codebase_resource_for_package(codebase_resource, discovered_package):
     """
     Assign the `discovered_package` to the `codebase_resource` and set its