From a1ce146b574ae12ae4da0e4e8f7d96a2d7b7f9ab Mon Sep 17 00:00:00 2001
From: tdruez <489057+tdruez@users.noreply.github.com>
Date: Fri, 21 Mar 2025 13:06:42 +0400
Subject: [PATCH 1/6] Refine the scan_single_package pipeline to work on git
 inputs #1376 (#1636)

Signed-off-by: tdruez <tdruez@nexb.com>
Signed-off-by: Model Monster <van@modelmonster.ai>
---
 CHANGELOG.rst                             |   3 +
 scanpipe/pipelines/scan_single_package.py |   6 +-
 scanpipe/tests/pipes/test_d2d.py          |   1 +
 scanpipe/tests/pipes/test_fetch.py        |   4 +-
 scanpipe/tests/test_pipelines.py          | 150 +++++++++++++---------
 5 files changed, 99 insertions(+), 65 deletions(-)

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 9ae1ecf47..1d0d83fac 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -29,6 +29,9 @@ v34.9.6 (unreleased)
 - Add support for "Permission denied" file access in make_codebase_resource.
   https://github.com/aboutcode-org/scancode.io/issues/1630
 
+- Refine the ``scan_single_package`` pipeline to work on git fetched inputs.
+  https://github.com/aboutcode-org/scancode.io/issues/1376
+
 v34.9.5 (2025-02-19)
 --------------------
 
diff --git a/scanpipe/pipelines/scan_single_package.py b/scanpipe/pipelines/scan_single_package.py
index 1c9eee2ee..c2e077a3f 100644
--- a/scanpipe/pipelines/scan_single_package.py
+++ b/scanpipe/pipelines/scan_single_package.py
@@ -69,10 +69,12 @@ def steps(cls):
 
     def get_package_input(self):
         """Locate the package input in the project's input/ directory."""
-        input_files = self.project.input_files
+        # Using the input_sources model property as it includes input sources instances
+        # as well as any files manually copied into the input/ directory.
+        input_sources = self.project.input_sources
         inputs = list(self.project.inputs("*"))
 
-        if len(inputs) != 1 or len(input_files) != 1:
+        if len(inputs) != 1 or len(input_sources) != 1:
             raise Exception("Only 1 input file supported")
 
         self.input_path = inputs[0]
diff --git a/scanpipe/tests/pipes/test_d2d.py b/scanpipe/tests/pipes/test_d2d.py
index 0eacbee6e..a60cd864b 100644
--- a/scanpipe/tests/pipes/test_d2d.py
+++ b/scanpipe/tests/pipes/test_d2d.py
@@ -1629,6 +1629,7 @@ def test_scanpipe_pipes_d2d_match_purldb_resources_post_process_with_special_cha
         except DataError:
             self.fail("DataError was raised, but it should not occur.")
 
+    @skipIf(sys.platform == "darwin", "Test is failing on macOS")
     def test_scanpipe_pipes_d2d_map_javascript_symbols(self):
         to_dir = self.project1.codebase_path / "to/project.tar.zst-extract/"
         to_resource_file = (
diff --git a/scanpipe/tests/pipes/test_fetch.py b/scanpipe/tests/pipes/test_fetch.py
index 35f3f33c9..15e32a3c2 100644
--- a/scanpipe/tests/pipes/test_fetch.py
+++ b/scanpipe/tests/pipes/test_fetch.py
@@ -38,7 +38,7 @@ def test_scanpipe_pipes_fetch_get_fetcher(self):
         self.assertEqual(fetch.fetch_http, fetch.get_fetcher("http://a.b/f.z"))
         self.assertEqual(fetch.fetch_http, fetch.get_fetcher("https://a.b/f.z"))
         self.assertEqual(fetch.fetch_docker_image, fetch.get_fetcher("docker://image"))
-        git_http_url = "https://github.com/nexB/scancode.io.git"
+        git_http_url = "https://github.com/aboutcode-org/scancode.io.git"
         self.assertEqual(fetch.fetch_git_repo, fetch.get_fetcher(git_http_url))
         self.assertEqual(fetch.fetch_git_repo, fetch.get_fetcher(git_http_url + "/"))
 
@@ -229,7 +229,7 @@ def test_scanpipe_pipes_fetch_get_request_session(self):
     @mock.patch("git.repo.base.Repo.clone_from")
     def test_scanpipe_pipes_fetch_git_repo(self, mock_clone_from):
         mock_clone_from.return_value = None
-        url = "https://github.com/nexB/scancode.io.git"
+        url = "https://github.com/aboutcode-org/scancode.io.git"
         download = fetch.fetch_git_repo(url)
 
         self.assertEqual(url, download.uri)
diff --git a/scanpipe/tests/test_pipelines.py b/scanpipe/tests/test_pipelines.py
index 03a4547bb..248da6379 100644
--- a/scanpipe/tests/test_pipelines.py
+++ b/scanpipe/tests/test_pipelines.py
@@ -40,7 +40,6 @@
 from scanpipe import pipes
 from scanpipe.models import CodebaseResource
 from scanpipe.models import DiscoveredPackage
-from scanpipe.models import Project
 from scanpipe.pipelines import CommonStepsMixin
 from scanpipe.pipelines import InputFilesError
 from scanpipe.pipelines import Pipeline
@@ -55,6 +54,7 @@
 from scanpipe.pipes.input import copy_input
 from scanpipe.tests import FIXTURES_REGEN
 from scanpipe.tests import make_package
+from scanpipe.tests import make_project
 from scanpipe.tests import package_data1
 from scanpipe.tests.pipelines.do_nothing import DoNothing
 from scanpipe.tests.pipelines.download_inputs import DownloadInput
@@ -69,7 +69,7 @@ class ScanPipePipelinesTest(TestCase):
     data = Path(__file__).parent / "data"
 
     def test_scanpipe_pipeline_class_pipeline_name_attribute(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline_instance = DoNothing(run)
         self.assertEqual("do_nothing", pipeline_instance.pipeline_name)
@@ -104,7 +104,7 @@ def test_scanpipe_pipeline_class_get_summary(self):
         self.assertEqual(expected, ProfileStep.get_summary())
 
     def test_scanpipe_pipeline_class_log(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
         pipeline.log("Event1")
@@ -115,7 +115,7 @@ def test_scanpipe_pipeline_class_log(self):
         self.assertIn("Event2", run.log)
 
     def test_scanpipe_pipeline_class_execute(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
@@ -132,7 +132,7 @@ def test_scanpipe_pipeline_class_execute(self):
         self.assertIn("Pipeline completed", run.log)
 
     def test_scanpipe_pipeline_class_execute_with_exception(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("raise_exception")
         pipeline = run.make_pipeline_instance()
 
@@ -158,7 +158,7 @@ def test_scanpipe_pipeline_class_execute_with_selected_steps(self, step2, step1)
         step2.__name__ = "step2"
         step2.groups = []
 
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         run.update(selected_steps=["step2", "not_existing_step"])
         pipeline = run.make_pipeline_instance()
@@ -178,7 +178,7 @@ def test_scanpipe_pipeline_class_execute_with_selected_steps(self, step2, step1)
         self.assertIn("Pipeline completed", run.log)
 
     def test_scanpipe_pipeline_class_download_inputs_attribute(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("download_inputs")
         pipeline = run.make_pipeline_instance()
         self.assertTrue(pipeline.download_inputs)
@@ -197,7 +197,7 @@ def test_scanpipe_pipeline_class_download_inputs_attribute(self):
 
     @mock.patch("requests.sessions.Session.get")
     def test_scanpipe_pipeline_class_download_missing_inputs(self, mock_get):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
@@ -239,7 +239,7 @@ def test_scanpipe_pipeline_class_download_missing_inputs(self, mock_get):
 
     @mock.patch("scanpipe.models.InputSource.fetch")
     def test_scanpipe_pipeline_class_download_fetch_exception(self, mock_fetch):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
@@ -262,30 +262,31 @@ def test_scanpipe_pipeline_class_download_fetch_exception(self, mock_fetch):
 
     @mock.patch("git.repo.base.Repo.clone_from")
     def test_scanpipe_pipeline_class_download_missing_inputs_git_repo(self, mock_clone):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
-        download_url = "https://github.com/nexB/scancode.io.git"
+        download_url = "https://github.com/aboutcode-org/scancode.io.git"
         input_source = project1.add_input_source(download_url=download_url)
 
         def mock_make_to_path(**kwargs):
             to_path = kwargs.get("to_path")
-            to_path.touch()
+            to_path.mkdir()
 
         mock_clone.side_effect = mock_make_to_path
         mock_clone.return_value = None
 
         pipeline.download_missing_inputs()
         self.assertIn(
-            "Fetching input from https://github.com/nexB/scancode.io.git", run.log
+            "Fetching input from https://github.com/aboutcode-org/scancode.io.git",
+            run.log,
         )
         input_source.refresh_from_db()
         self.assertEqual("scancode.io.git", input_source.filename)
         self.assertTrue(input_source.exists())
 
     def test_scanpipe_pipeline_class_save_errors_context_manager(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
         self.assertEqual(project1, pipeline.project)
@@ -323,7 +324,7 @@ def test_scanpipe_pipeline_class_get_graph(self):
         self.assertEqual(expected, DoNothing.get_graph())
 
     def test_scanpipe_pipelines_profile_decorator(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("profile_step")
         pipeline_instance = run.make_pipeline_instance()
 
@@ -376,7 +377,7 @@ def test_scanpipe_pipeline_class_get_available_groups(self):
         self.assertEqual([], DoNothing.get_available_groups())
 
     def test_scanpipe_pipeline_class_env_loaded_from_config_file(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
         self.assertEqual({}, pipeline.env)
@@ -391,7 +392,7 @@ def test_scanpipe_pipeline_class_env_loaded_from_config_file(self):
         self.assertEqual({"product_name": "Product"}, pipeline.env)
 
     def test_scanpipe_pipeline_class_env_reloaded_after_extraction(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "settings" / "archived-scancode-config.zip"
         project1.copy_input_from(input_location)
@@ -412,7 +413,7 @@ def test_scanpipe_pipeline_class_env_reloaded_after_extraction(self):
         self.assertEqual(expected, pipeline.env)
 
     def test_scanpipe_pipeline_class_flag_ignored_resources(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
         self.assertIsNone(pipeline.env.get("ignored_patterns"))
@@ -428,7 +429,7 @@ def test_scanpipe_pipeline_class_flag_ignored_resources(self):
         mock_flag.assert_called_with(project1, patterns=patterns_args)
 
     def test_scanpipe_pipeline_class_extract_archive(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
@@ -446,7 +447,7 @@ def test_scanpipe_pipeline_class_extract_archive(self):
         self.assertEqual("", project_error.traceback)
 
     def test_scanpipe_pipeline_class_extract_archives(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("do_nothing")
         pipeline = run.make_pipeline_instance()
 
@@ -468,7 +469,7 @@ def test_scanpipe_pipeline_class_extract_archives(self):
 
 class RootFSPipelineTest(TestCase):
     def test_scanpipe_rootfs_pipeline_extract_input_files_errors(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("analyze_root_filesystem_or_vm_image")
         pipeline_instance = analyze_root_filesystem.RootFS(run)
 
@@ -659,7 +660,7 @@ def assertPipelineResultEqual(
     @skipIf(from_docker_image, "Random failure in the Docker context.")
     def test_scanpipe_scan_package_pipeline_integration(self):
         pipeline_name = "scan_single_package"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "scancode" / "is-npm-1.0.0.tgz"
         project1.copy_input_from(input_location)
@@ -695,7 +696,7 @@ def test_scanpipe_scan_package_pipeline_integration(self):
     @skipIf(from_docker_image, "Random failure in the Docker context.")
     def test_scanpipe_scan_package_pipeline_integration_multiple_packages(self):
         pipeline_name = "scan_single_package"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "scancode" / "multiple-is-npm-1.0.0.tar.gz"
         project1.copy_input_from(input_location)
@@ -727,7 +728,7 @@ def test_scanpipe_scan_package_pipeline_integration_multiple_packages(self):
     def test_scanpipe_scan_package_single_extract_input_to_codebase_directory(
         self, mock_is_archive
     ):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("scan_single_package")
         pipeline_instance = scan_single_package.ScanSinglePackage(run)
 
@@ -751,7 +752,7 @@ def test_scanpipe_scan_package_single_extract_input_to_codebase_directory(
 
     def test_scanpipe_scan_package_single_file(self):
         pipeline_name = "scan_single_package"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "manifests" / "openpdf-parent-1.3.11.pom.xml"
         project1.copy_input_from(input_location)
@@ -772,9 +773,36 @@ def test_scanpipe_scan_package_single_file(self):
         )
         self.assertPipelineResultEqual(expected_file, scancode_file)
 
+    @mock.patch("git.repo.base.Repo.clone_from")
+    def test_scanpipe_scan_package_single_package_git_repo(self, mock_clone):
+        pipeline_name = "scan_single_package"
+        project1 = make_project()
+
+        download_url = "https://github.com/aboutcode-org/scancode.io.git"
+        project1.add_input_source(download_url=download_url)
+
+        run = project1.add_pipeline(pipeline_name)
+        pipeline = run.make_pipeline_instance()
+
+        # Create the "fetched" git directory content
+        def mock_make_git_directory(**kwargs):
+            to_path = kwargs.get("to_path")  # scancode.io.git
+            to_path.mkdir()
+            file_location = self.data / "aboutcode" / "notice.NOTICE"
+            copy_input(file_location, to_path)
+
+        mock_clone.side_effect = mock_make_git_directory
+        mock_clone.return_value = None
+
+        exitcode, out = pipeline.execute()
+        self.assertEqual(0, exitcode, msg=out)
+
+        self.assertEqual(2, project1.codebaseresources.count())
+        self.assertEqual(0, project1.discoveredpackages.count())
+
     def test_scanpipe_scan_codebase_pipeline_integration(self):
         pipeline_name = "scan_codebase"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "is-npm-1.0.0.tgz"
         input_location = self.data / "scancode" / filename
@@ -797,7 +825,7 @@ def test_scanpipe_scan_codebase_pipeline_integration(self):
 
     def test_scanpipe_inspect_packages_creates_packages_npm(self):
         pipeline_name = "inspect_packages"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "is-npm-1.0.0.tgz"
         input_location = self.data / "scancode" / filename
@@ -828,7 +856,7 @@ def test_scanpipe_inspect_packages_creates_packages_npm(self):
 
     def test_scanpipe_inspect_packages_creates_packages_pypi(self):
         pipeline_name = "inspect_packages"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "manifests" / "python-inspector-0.10.0.zip"
         project1.copy_input_from(input_location)
@@ -845,7 +873,7 @@ def test_scanpipe_inspect_packages_creates_packages_pypi(self):
     @skipIf(sys.platform == "darwin", "Not supported on macOS")
     def test_scanpipe_inspect_packages_with_resolved_dependencies_npm(self):
         pipeline_name = "inspect_packages"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "dependencies" / "resolved_dependencies_npm.zip"
         project1.copy_input_from(input_location)
@@ -873,7 +901,7 @@ def test_scanpipe_inspect_packages_with_resolved_dependencies_npm(self):
     @skipIf(sys.platform == "darwin", "Not supported on macOS")
     def test_scanpipe_inspect_packages_with_resolved_dependencies_poetry(self):
         pipeline_name = "inspect_packages"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "dependencies" / "resolved_dependencies_poetry.zip"
         project1.copy_input_from(input_location)
@@ -900,7 +928,7 @@ def test_scanpipe_inspect_packages_with_resolved_dependencies_poetry(self):
 
     def test_scanpipe_resolved_dependencies_cocoapods(self):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = (
             self.data / "dependencies" / "resolved_dependencies_cocoapods.zip"
@@ -929,7 +957,7 @@ def test_scanpipe_resolved_dependencies_cocoapods(self):
 
     def test_scanpipe_resolved_dependencies_pip_inspect(self):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "dependencies" / "resolved_dependencies_pip.zip"
         project1.copy_input_from(input_location)
@@ -955,7 +983,7 @@ def test_scanpipe_resolved_dependencies_pip_inspect(self):
 
     def test_scanpipe_resolved_dependencies_nuget(self):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "dependencies" / "resolved_dependencies_nuget.zip"
         project1.copy_input_from(input_location)
@@ -982,7 +1010,7 @@ def test_scanpipe_resolved_dependencies_nuget(self):
 
     def test_scanpipe_scan_codebase_can_process_wheel(self):
         pipeline_name = "scan_codebase"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "daglib-0.6.0-py3-none-any.whl"
         input_location = self.data / "scancode" / filename
@@ -1008,7 +1036,7 @@ def test_scanpipe_scan_codebase_can_process_wheel(self):
     @skipIf(sys.platform != "linux", "Expected results are inconsistent across OS")
     def test_scanpipe_docker_pipeline_alpine_integration(self):
         pipeline_name = "analyze_docker_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "alpine_3_15_4.tar.gz"
         input_location = self.data / "docker" / filename
@@ -1031,7 +1059,7 @@ def test_scanpipe_docker_pipeline_alpine_integration(self):
 
     def test_scanpipe_docker_pipeline_does_not_report_errors_for_broken_symlinks(self):
         pipeline_name = "analyze_docker_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "minitag.tar"
         input_location = self.data / "image-with-symlinks" / filename
@@ -1058,7 +1086,7 @@ def test_scanpipe_docker_pipeline_does_not_report_errors_for_broken_symlinks(sel
     @skipIf(sys.platform != "linux", "RPM related features only supported on Linux.")
     def test_scanpipe_docker_pipeline_rpm_integration(self):
         pipeline_name = "analyze_docker_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "centos.tar.gz"
         input_location = self.data / "docker" / filename
@@ -1081,7 +1109,7 @@ def test_scanpipe_docker_pipeline_rpm_integration(self):
 
     def test_scanpipe_docker_pipeline_debian_integration(self):
         pipeline_name = "analyze_docker_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "debian.tar.gz"
         input_location = self.data / "docker" / filename
@@ -1104,7 +1132,7 @@ def test_scanpipe_docker_pipeline_debian_integration(self):
 
     def test_scanpipe_docker_pipeline_distroless_debian_integration(self):
         pipeline_name = "analyze_docker_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         filename = "gcr_io_distroless_base.tar.gz"
         input_location = self.data / "docker" / filename
@@ -1129,7 +1157,7 @@ def test_scanpipe_docker_pipeline_distroless_debian_integration(self):
 
     def test_scanpipe_rootfs_pipeline_integration(self):
         pipeline_name = "analyze_root_filesystem_or_vm_image"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "rootfs" / "basic-rootfs.tar.gz"
         project1.copy_input_from(input_location)
@@ -1150,7 +1178,7 @@ def test_scanpipe_rootfs_pipeline_integration(self):
 
     def test_scanpipe_load_inventory_pipeline_integration(self):
         pipeline_name = "load_inventory"
-        project1 = Project.objects.create(name="Tool: scancode-toolkit")
+        project1 = make_project()
 
         input_location = self.data / "asgiref" / "asgiref-3.3.0_toolkit_scan.json"
         project1.copy_input_from(input_location)
@@ -1172,7 +1200,7 @@ def test_scanpipe_load_inventory_pipeline_integration(self):
         self.assertPipelineResultEqual(expected_file, result_file)
 
         # Using the ScanCode.io JSON output as the input
-        project2 = Project.objects.create(name="Tool: scanpipe")
+        project2 = make_project()
 
         input_location = self.data / "asgiref" / "asgiref-3.3.0_scanpipe_output.json"
         project2.copy_input_from(input_location)
@@ -1194,7 +1222,7 @@ def test_scanpipe_find_vulnerabilities_pipeline_integration(
         self, mock_bulk_search_by_purl, mock_is_configured, mock_is_available
     ):
         pipeline_name = "find_vulnerabilities"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         package1 = DiscoveredPackage.create_from_data(project1, package_data1)
 
         run = project1.add_pipeline(pipeline_name)
@@ -1240,7 +1268,7 @@ def test_scanpipe_find_vulnerabilities_pipeline_integration(
 
     def test_scanpipe_resolve_dependencies_pipeline_integration(self):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         selected_groups = ["DynamicResolver"]
 
         run = project1.add_pipeline(
@@ -1258,7 +1286,7 @@ def test_scanpipe_resolve_dependencies_pipeline_integration(self):
 
     def test_scanpipe_resolve_dependencies_pipeline_integration_empty_manifest(self):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         selected_groups = ["DynamicResolver"]
 
         run = project1.add_pipeline(
@@ -1279,7 +1307,7 @@ def test_scanpipe_resolve_dependencies_pipeline_integration_misc(
         self, mock_resolve_dependencies
     ):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         selected_groups = ["DynamicResolver"]
 
         input_location = self.data / "manifests" / "requirements.txt"
@@ -1300,7 +1328,7 @@ def test_scanpipe_resolve_dependencies_pipeline_pypi_integration(
         self, mock_resolve_dependencies
     ):
         pipeline_name = "resolve_dependencies"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         selected_groups = ["DynamicResolver"]
 
         run = project1.add_pipeline(
@@ -1322,7 +1350,7 @@ def test_scanpipe_resolve_dependencies_pipeline_pypi_integration(
 
     def test_scanpipe_load_sbom_pipeline_aboutfile_integration(self):
         pipeline_name = "load_sbom"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "manifests" / "Django-4.0.8-py3-none-any.whl.ABOUT"
         project1.copy_input_from(input_location)
@@ -1342,7 +1370,7 @@ def test_scanpipe_load_sbom_pipeline_aboutfile_integration(self):
 
     def test_scanpipe_load_sbom_pipeline_spdx_integration(self):
         pipeline_name = "load_sbom"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "manifests" / "toml.spdx.json"
         project1.copy_input_from(input_location)
@@ -1364,7 +1392,7 @@ def test_scanpipe_load_sbom_pipeline_spdx_integration(self):
 
     def test_scanpipe_load_sbom_pipeline_cyclonedx_integration(self):
         pipeline_name = "load_sbom"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "cyclonedx" / "nested.cdx.json"
         project1.copy_input_from(input_location)
@@ -1439,7 +1467,7 @@ def test_scanpipe_load_sbom_pipeline_cyclonedx_integration(self):
 
     def test_scanpipe_load_sbom_pipeline_cyclonedx_with_dependencies_integration(self):
         pipeline_name = "load_sbom"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         input_location = self.data / "cyclonedx" / "laravel-7.12.0" / "bom.1.4.json"
         project1.copy_input_from(input_location)
@@ -1464,7 +1492,7 @@ def test_scanpipe_deploy_to_develop_pipeline_integration(
         mock_uuid4.return_value = forced_uuid
         mock_request.return_value = None
         pipeline_name = "map_deploy_to_develop"
-        project1 = Project.objects.create(name="Analysis", uuid=forced_uuid)
+        project1 = make_project(name="Analysis", uuid=forced_uuid)
         selected_groups = ["Java"]
 
         jar_location = self.data / "d2d" / "jars"
@@ -1489,7 +1517,7 @@ def test_scanpipe_deploy_to_develop_pipeline_integration(
         self.assertPipelineResultEqual(expected_file, result_file)
 
     def test_scanpipe_deploy_to_develop_pipeline_extract_input_files_errors(self):
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         run = project1.add_pipeline("map_deploy_to_develop")
         pipeline_instance = deploy_to_develop.DeployToDevelop(run)
 
@@ -1528,7 +1556,7 @@ def test_scanpipe_deploy_to_develop_pipeline_with_about_file(
         mock_uuid4.return_value = forced_uuid
         mock_request.return_value = None
         pipeline_name = "map_deploy_to_develop"
-        project1 = Project.objects.create(name="Analysis", uuid=forced_uuid)
+        project1 = make_project(name="Analysis", uuid=forced_uuid)
         selected_groups = ["Java"]
 
         data_dir = self.data / "d2d" / "about_files"
@@ -1567,7 +1595,7 @@ def test_scanpipe_populate_purldb_pipeline_integration(
     ):
         pipeline_name1 = "load_inventory"
         pipeline_name2 = "populate_purldb"
-        project1 = Project.objects.create(name="Utility: PurlDB")
+        project1 = make_project()
 
         input_location = self.data / "asgiref" / "asgiref-3.3.0_toolkit_scan.json"
         project1.copy_input_from(input_location)
@@ -1609,7 +1637,7 @@ def test_scanpipe_populate_purldb_pipeline_integration_without_assembly(
         self, mock_is_available, mock_request_post
     ):
         pipeline_name = "populate_purldb"
-        project1 = Project.objects.create(name="Utility: PurlDB")
+        project1 = make_project()
 
         def mock_request_post_return(url, data, headers, timeout):
             payload = json.loads(data)
@@ -1649,7 +1677,7 @@ def mock_request_post_return(url, data, headers, timeout):
     @skipIf(sys.platform == "darwin", "Not supported on macOS")
     def test_scanpipe_collect_symbols_ctags_pipeline_integration(self):
         pipeline_name = "collect_symbols_ctags"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         dir = project1.codebase_path / "codefile"
         dir.mkdir(parents=True)
@@ -1673,7 +1701,7 @@ def test_scanpipe_collect_symbols_ctags_pipeline_integration(self):
     @skipIf(sys.platform != "linux", "Only supported on Linux")
     def test_scanpipe_collect_strings_gettext_pipeline_integration(self):
         pipeline_name = "collect_strings_gettext"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         dir = project1.codebase_path / "codefile"
         dir.mkdir(parents=True)
@@ -1700,7 +1728,7 @@ def test_scanpipe_collect_strings_gettext_pipeline_integration(self):
     @skipIf(sys.platform == "darwin", "Not supported on macOS")
     def test_scanpipe_collect_symbols_pygments_pipeline_integration(self):
         pipeline_name = "collect_symbols_pygments"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         dir = project1.codebase_path / "codefile"
         dir.mkdir(parents=True)
@@ -1731,7 +1759,7 @@ def test_scanpipe_collect_symbols_pygments_pipeline_integration(self):
     @skipIf(sys.platform == "darwin", "Not supported on macOS")
     def test_scanpipe_collect_symbols_tree_sitter_pipeline_integration(self):
         pipeline_name = "collect_symbols_tree_sitter"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
 
         dir = project1.codebase_path / "codefile"
         dir.mkdir(parents=True)
@@ -1766,7 +1794,7 @@ def test_scanpipe_enrich_with_purldb_pipeline_integration(
         self, mock_collect_data, mock_is_configured, mock_is_available
     ):
         pipeline_name = "enrich_with_purldb"
-        project1 = Project.objects.create(name="Analysis")
+        project1 = make_project()
         package1 = make_package(project1, package_url="pkg:npm/csvtojson@2.0.10")
 
         mock_is_configured.return_value = True

From c9a2a0965e50c05cc43e7a8188b859eb7b51175c Mon Sep 17 00:00:00 2001
From: tdruez <489057+tdruez@users.noreply.github.com>
Date: Fri, 21 Mar 2025 13:58:52 +0400
Subject: [PATCH 2/6] Bump version for v34.10.0 release (#1637)

Signed-off-by: tdruez <tdruez@nexb.com>
Signed-off-by: Model Monster <van@modelmonster.ai>
---
 CHANGELOG.rst          | 4 ++--
 RELEASE.md             | 2 +-
 scancodeio/__init__.py | 2 +-
 setup.cfg              | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 1d0d83fac..e61192d58 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,8 +1,8 @@
 Changelog
 =========
 
-v34.9.6 (unreleased)
---------------------
+v34.10.0 (2025-03-21)
+---------------------
 
 - Rename the ``docker``, ``docker_windows``, and ``root_filesystem`` modules to
   ``analyze_docker``, ``analyze_docker_windows``, and ``analyze_root_filesystem``
diff --git a/RELEASE.md b/RELEASE.md
index 20ed80362..580738d98 100644
--- a/RELEASE.md
+++ b/RELEASE.md
@@ -9,7 +9,7 @@
   - `CHANGELOG.rst` (set date)
 - Commit and push this branch
 - Create a PR and merge once approved
-- Tag and push that tag. This will triggers the `pypi-release.yml` GitHub workflow that 
+- Tag and push that tag. This will trigger the `pypi-release.yml` GitHub workflow that 
   takes care of building the dist release files and upload those to pypi:
   ```
   VERSION=vx.x.x  # <- Set the new version here
diff --git a/scancodeio/__init__.py b/scancodeio/__init__.py
index 1492250d7..8206c539c 100644
--- a/scancodeio/__init__.py
+++ b/scancodeio/__init__.py
@@ -28,7 +28,7 @@
 
 import git
 
-VERSION = "34.9.5"
+VERSION = "34.10.0"
 
 PROJECT_DIR = Path(__file__).resolve().parent
 ROOT_DIR = PROJECT_DIR.parent
diff --git a/setup.cfg b/setup.cfg
index af35a17ea..928098303 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
 [metadata]
 name = scancodeio
-version = 34.9.5
+version = 34.10.0
 license = Apache-2.0
 description = Automate software composition analysis pipelines
 long_description = file:README.rst
@@ -159,7 +159,7 @@ scancodeio_pipelines =
 
 [bumpver]
 version_pattern = "MAJOR.MINOR.PATCH"
-current_version = "34.9.5"
+current_version = "34.10.0"
 
 [bumpver:file_patterns]
 setup.cfg =

From 1bc14ebcc9ad09bcfd29103c321966ed85430fde Mon Sep 17 00:00:00 2001
From: tdruez <tdruez@nexb.com>
Date: Fri, 21 Mar 2025 15:02:18 +0400
Subject: [PATCH 3/6] Truncate the task output in get_slack_payload to block
 message limit

Signed-off-by: tdruez <tdruez@nexb.com>
Signed-off-by: Model Monster <van@modelmonster.ai>
---
 scanpipe/models.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/scanpipe/models.py b/scanpipe/models.py
index fcdb8604a..388c8a4b2 100644
--- a/scanpipe/models.py
+++ b/scanpipe/models.py
@@ -4203,11 +4203,19 @@ def get_slack_payload(pipeline_run):
 
         # Adds the task output in case of run failure
         if pipeline_run.status == Run.Status.FAILURE and pipeline_run.task_output:
+            slack_text_max_length = 3000  # Slack's block message limit
+            output_text = pipeline_run.task_output
+            # Truncate the task output and add an indicator if it was cut off
+            if len(output_text) > slack_text_max_length:
+                output_text = (
+                    output_text[: slack_text_max_length - 30] + "\n... (truncated)"
+                )
+
             task_output_block = {
                 "type": "section",
                 "text": {
                     "type": "mrkdwn",
-                    "text": f"```{pipeline_run.task_output}```",
+                    "text": f"```{output_text}```",
                 },
             }
             blocks.append(task_output_block)

From e8ab39a05b8787e611e3158eb3fd915f8b0ba7cb Mon Sep 17 00:00:00 2001
From: Model Monster <van@modelmonster.ai>
Date: Mon, 24 Mar 2025 14:24:44 -0500
Subject: [PATCH 4/6] Use fully qualified image names in docker-compose files

Signed-off-by: Model Monster <van@modelmonster.ai>
---
 docker-compose-offline.yml | 6 +++---
 docker-compose.yml         | 8 ++++----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/docker-compose-offline.yml b/docker-compose-offline.yml
index 2bf7c96d3..d26d12100 100644
--- a/docker-compose-offline.yml
+++ b/docker-compose-offline.yml
@@ -1,13 +1,13 @@
 services:
   db:
-    image: postgres:13
+    image: docker.io/library/postgres:13
     env_file:
       - docker.env
     volumes:
       - db_data:/var/lib/postgresql/data/
 
   redis:
-    image: redis
+    image: docker.io/library/redis:latest
     # Enable redis data persistence using the "Append Only File" with the
     # default policy of fsync every second. See https://redis.io/topics/persistence
     command: redis-server --appendonly yes
@@ -45,7 +45,7 @@ services:
       - web # Ensure that potential db migrations run first
 
   nginx:
-    image: nginx
+    image: docker.io/library/nginx:latest
     ports:
       - 80:80
       - 443:443
diff --git a/docker-compose.yml b/docker-compose.yml
index f494dd174..c05453ebb 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,6 +1,6 @@
 services:
   db:
-    image: postgres:13
+    image: docker.io/library/postgres:13
     env_file:
       - docker.env
     volumes:
@@ -9,7 +9,7 @@ services:
     restart: always
 
   redis:
-    image: redis
+    image: docker.io/library/redis:latest
     # Enable redis data persistence using the "Append Only File" with the
     # default policy of fsync every second. See https://redis.io/topics/persistence
     command: redis-server --appendonly yes
@@ -54,7 +54,7 @@ services:
       - web
 
   nginx:
-    image: nginx:alpine
+    image: docker.io/library/nginx:alpine
     ports:
       - "${NGINX_PUBLISHED_HTTP_PORT:-80}:80"
       - "${NGINX_PUBLISHED_HTTPS_PORT:-443}:443"
@@ -67,7 +67,7 @@ services:
     restart: always
 
   clamav:
-    image: clamav/clamav
+    image: docker.io/clamav/clamav:latest
     volumes:
       - clamav_data:/var/lib/clamav
       - workspace:/var/scancodeio/workspace/

From 89a9fa2f6522fa162aceb2b95582347588e93314 Mon Sep 17 00:00:00 2001
From: Model Monster <van@modelmonster.ai>
Date: Mon, 24 Mar 2025 15:20:08 -0500
Subject: [PATCH 5/6] Add name property to docker-compose files to ensure
 consistent container naming

Signed-off-by: Model Monster <van@modelmonster.ai>
---
 docker-compose-offline.yml            | 1 +
 docker-compose.dev.yml                | 1 +
 docker-compose.purldb-scan-worker.yml | 1 +
 docker-compose.yml                    | 1 +
 4 files changed, 4 insertions(+)

diff --git a/docker-compose-offline.yml b/docker-compose-offline.yml
index d26d12100..d64203524 100644
--- a/docker-compose-offline.yml
+++ b/docker-compose-offline.yml
@@ -1,3 +1,4 @@
+name: scancodeio
 services:
   db:
     image: docker.io/library/postgres:13
diff --git a/docker-compose.dev.yml b/docker-compose.dev.yml
index 51bf7d4d0..597518a92 100644
--- a/docker-compose.dev.yml
+++ b/docker-compose.dev.yml
@@ -6,6 +6,7 @@
 # $ docker compose -f docker-compose.yml -f docker-compose.dev.yml run --rm web bash
 # $ SCANCODEIO_TEST_FIXTURES_REGEN=1 ./manage.py test
 
+name: scancodeio
 services:
   web:
     env_file:
diff --git a/docker-compose.purldb-scan-worker.yml b/docker-compose.purldb-scan-worker.yml
index 065eb779f..3636b26a3 100644
--- a/docker-compose.purldb-scan-worker.yml
+++ b/docker-compose.purldb-scan-worker.yml
@@ -1,6 +1,7 @@
 include:
   - docker-compose.yml
 
+name: scancodeio
 services:
   purldb_scan_worker:
     build: .
diff --git a/docker-compose.yml b/docker-compose.yml
index c05453ebb..321bc0f30 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,3 +1,4 @@
+name: scancodeio
 services:
   db:
     image: docker.io/library/postgres:13

From 6e74f9ff22207acdaed99ae8560615f8af41efdd Mon Sep 17 00:00:00 2001
From: Model Monster <van@modelmonster.ai>
Date: Mon, 24 Mar 2025 15:53:43 -0500
Subject: [PATCH 6/6] Add COMPOSE_PROJECT_NAME to .env file creation

Signed-off-by: Model Monster <van@modelmonster.ai>
---
 Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Makefile b/Makefile
index d09b2f6cc..d2ea5bf32 100644
--- a/Makefile
+++ b/Makefile
@@ -62,6 +62,7 @@ envfile:
 	@if test -f ${ENV_FILE}; then echo ".env file exists already"; exit 1; fi
 	@mkdir -p $(shell dirname ${ENV_FILE}) && touch ${ENV_FILE}
 	@echo SECRET_KEY=\"${GET_SECRET_KEY}\" > ${ENV_FILE}
+	@echo COMPOSE_PROJECT_NAME=\"scancodeio\" >> ${ENV_FILE}
 
 doc8:
 	@echo "-> Run doc8 validation"