From c90069a19bfba9d3d9ced0b8e911358b73ef8a5b Mon Sep 17 00:00:00 2001
From: Varsha U N <varshamaddur2006@gmail.com>
Date: Sat, 16 Nov 2024 11:26:20 +0530
Subject: [PATCH] addded support to parse labels in dockerfile

Signed-off-by: Varsha U N <varshamaddur2006@gmail.com>
---
 src/packagedcode/__init__.py        |  2 +
 src/packagedcode/dockerfileLABEL.py | 72 +++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)
 create mode 100644 src/packagedcode/dockerfileLABEL.py

diff --git a/src/packagedcode/__init__.py b/src/packagedcode/__init__.py
index 6692087aa4..dc9cde4589 100644
--- a/src/packagedcode/__init__.py
+++ b/src/packagedcode/__init__.py
@@ -20,6 +20,7 @@
 from packagedcode import debian
 from packagedcode import debian_copyright
 from packagedcode import distro
+from packagedcode import dockerfileLABEL
 from packagedcode import conda
 from packagedcode import conan
 from packagedcode import cocoapods
@@ -97,6 +98,7 @@
     debian.DebianSourcePackageTarballHandler,
 
     distro.EtcOsReleaseHandler,
+    dockerfileLABEL.DockerfileHandler,
 
     freebsd.CompactManifestHandler,
 
diff --git a/src/packagedcode/dockerfileLABEL.py b/src/packagedcode/dockerfileLABEL.py
new file mode 100644
index 0000000000..b9e46dddc2
--- /dev/null
+++ b/src/packagedcode/dockerfileLABEL.py
@@ -0,0 +1,72 @@
+#
+# 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 io
+from pathlib import Path
+from dockerfile_parse import DockerfileParser  
+from packagedcode import models
+from packagedcode import utils
+
+
+class DockerfileHandler(models.DatafileHandler):
+    datasource_id = 'dockerfile'
+    default_package_type = 'docker-image'
+    path_patterns = ('Dockerfile', 'containerfile', '*.dockerfile')  
+    description = 'Dockerfile (OCI) metadata handler'
+    documentation_url = 'https://docs.docker.com/engine/reference/builder/'
+
+    @classmethod
+    def parse(cls, location, package_only=False):
+        """
+        Parse a Dockerfile and yield one or more PackageData objects with OCI labels and metadata.
+        """
+        labels = cls.extract_oci_labels_from_dockerfile(location)
+
+       
+        package_data = {
+            'datasource_id': cls.datasource_id,
+            'type': cls.default_package_type,
+            'name': labels.get('name', 'unknown'),  
+            'version': labels.get('version', 'unknown'),  
+            'license_expression': labels.get('license', 'unknown'),
+            'labels': labels,  
+        }
+
+        yield models.PackageData.from_data(package_data, package_only)
+
+    @classmethod
+    def extract_oci_labels_from_dockerfile(cls, dockerfile_path):
+        """
+        Extract OCI labels from the Dockerfile using container-inspector.
+        """
+        labels = {}
+        parser = DockerfileParser()
+        parser.parse(dockerfile_path)
+        labels = parser.labels
+        return labels
+
+    @classmethod
+    def assemble(cls, package_data, resource, codebase, package_adder):
+        """
+        Assemble a Package from the parsed Dockerfile data.
+        """
+        if package_data.purl:
+            package = models.Package.from_package_data(package_data=package_data, datafile_path=resource.path)
+
+           
+            package.populate_license_fields()
+
+            yield package
+
+           
+            package_adder(package.package_uid, resource, codebase)
+
+        yield resource