feat: add a new check to map artifacts to pipelines (#471)

This PR adds a new check, `mcn_infer_artifact_pipeline_1` to detect a 
potential pipeline from which an artifact is published.

When a verifiable provenance is found for an artifact, the result of this 
check can be discarded. Otherwise, we check whether a CI workflow 
run has automatically published the artifact.

This check supports Maven artifacts built using Gradle or Maven and 
published on Maven Central only. Support for other registries and ecosystems will be added in the future.

Signed-off-by: behnazh-w <[email protected]>

Author: behnazh-w

docs/source/index.rst

@@ -74,6 +74,9 @@ the requirements that are currently supported by Macaron.
    * - 3
      - **Build as code** - If a trusted builder is not present, this requirement determines that the build definition and configuration executed by the build service is verifiably derived from text file definitions stored in a version control system.
      - Identify and validate the CI service(s) used to build and deploy/publish an artifact.
+   * - 3
+     - **Infer artifact publish pipeline** - When a provenance is not available, checks whether a CI workflow run has automatically published the artifact.
+     - Identify a workflow run that has triggered the deploy step determined by the ``Build as code`` check.
    * - 3
      - **Provenance Level three** - Check whether the target has SLSA provenance level 3.
      - Use the `slsa-verifier <https://github.com/slsa-framework/slsa-verifier>`_ to attest to the subjects in the SLSA provenance that accompanies an artifact.

docs/source/pages/developers_guide/apidoc/macaron.slsa_analyzer.checks.rst

@@ -49,6 +49,14 @@ macaron.slsa\_analyzer.checks.check\_result module
    :undoc-members:
    :show-inheritance:
 
+macaron.slsa\_analyzer.checks.infer\_artifact\_pipeline\_check module
+---------------------------------------------------------------------
+
+.. automodule:: macaron.slsa_analyzer.checks.infer_artifact_pipeline_check
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 macaron.slsa\_analyzer.checks.provenance\_available\_check module
 -----------------------------------------------------------------
 

docs/source/pages/developers_guide/apidoc/macaron.slsa_analyzer.package_registry.rst

@@ -17,6 +17,14 @@ macaron.slsa\_analyzer.package\_registry.jfrog\_maven\_registry module
    :undoc-members:
    :show-inheritance:
 
+macaron.slsa\_analyzer.package\_registry.maven\_central\_registry module
+------------------------------------------------------------------------
+
+.. automodule:: macaron.slsa_analyzer.package_registry.maven_central_registry
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 macaron.slsa\_analyzer.package\_registry.package\_registry module
 -----------------------------------------------------------------
 

docs/source/pages/supported_technologies/index.rst

@@ -41,6 +41,9 @@ Package Registries
    * - `JFrog Artifactory <https://jfrog.com/artifactory>`_
      - Only projects built with Gradle and publishing to a JFrog Artifactory repo following `Maven layout <https://maven.apache.org/repository/layout.html>`_
      - :doc:`page </pages/supported_technologies/jfrog>`
+   * - `Maven Central Artifactory <https://central.sonatype.com>`_
+     - Only projects built with Gradle or Maven and published to the Maven Central Artifactory.
+     - :doc:`page </pages/supported_technologies/maven_central>`
 
 -----------
 Provenances
@@ -70,3 +73,4 @@ See also
 
    jfrog
    witness
+   maven_central

docs/source/pages/supported_technologies/maven_central.rst

@@ -0,0 +1,6 @@
+.. Copyright (c) 2023 - 2023, Oracle and/or its affiliates. All rights reserved.
+.. Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/.
+
+=============
+Maven Central
+=============

scripts/dev_scripts/integration_tests.sh

@@ -267,6 +267,16 @@ python $COMPARE_JSON_OUT $JSON_RESULT $JSON_EXPECTED || log_fail
 
 # python $COMPARE_DEPS $DEP_RESULT $DEP_EXPECTED || log_fail
 
+echo -e "\n----------------------------------------------------------------------------------"
+echo "google/guava: Analyzing with PURL and repository path without dependency resolution."
+echo -e "----------------------------------------------------------------------------------\n"
+JSON_EXPECTED=$WORKSPACE/tests/e2e/expected_results/purl/com_google_guava/guava/guava.json
+JSON_RESULT=$WORKSPACE/output/reports/maven/com_google_guava/guava/guava.json
+$RUN_MACARON analyze -purl pkg:maven/com.google.guava/[email protected]?type=jar -rp https://github.com/google/guava -b master -d d8633ac8539dae52c8361f79c7a0dbd9ad6dd2c4 --skip-deps || log_fail
+
+python $COMPARE_JSON_OUT $JSON_RESULT $JSON_EXPECTED || log_fail
+
+
 # Running Macaron using local paths.
 echo -e "\n=================================================================================="
 echo "Run integration tests with local paths for apache/maven..."

src/macaron/config/defaults.ini

@@ -375,10 +375,20 @@ predicate_types =
     https://witness.testifysec.com/attestation-collection/v0.1
 artifact_extensions =
     jar
-
 # Package registries.
+[package_registry]
+# The allowed time range (in seconds) from a deploy workflow run start time to publish time.
+publish_time_range = 3600
+
 # [package_registry.jfrog.maven]
 # In this example, the Maven repo can be accessed at `https://internal.registry.org/repo-name`.
 # hostname = internal.registry.org
 # repo = repo-name
 # download_timeout = 120
+
+[package_registry.maven_central]
+# Maven Central host name.
+hostname = search.maven.org
+# The search REST API. See https://central.sonatype.org/search/rest-api-guide/
+search_endpoint = solrsearch/select
+request_timeout = 20

src/macaron/dependency_analyzer/cyclonedx.py

@@ -174,6 +174,7 @@ def convert_components_to_artifacts(
                 version=component.get("version") or "",
                 group=component.get("group") or "",
                 name=component.get("name") or "",
+                purl=component.get("purl") or "",
                 url="",
                 note="",
                 available=SCMStatus.AVAILABLE,

src/macaron/dependency_analyzer/dependency_resolver.py

@@ -34,6 +34,7 @@ class DependencyInfo(TypedDict):
     version: str
     group: str
     name: str
+    purl: str
     url: str
     note: str
     available: SCMStatus
@@ -262,6 +263,7 @@ def merge_configs(
                 Configuration(
                     {
                         "id": key,
+                        "purl": value.get("purl"),
                         "path": value.get("url"),
                         "branch": "",
                         "digest": "",

src/macaron/errors.py

@@ -50,3 +50,7 @@ class InvalidPURLError(MacaronError):
 
 class DuplicateError(MacaronError):
     """The class for errors for duplicated data."""
+
+
+class InvalidHTTPResponseError(MacaronError):
+    """Happens when the HTTP response is invalid or unexpected."""

src/macaron/parsers/bashparser.py

@@ -33,6 +33,10 @@ class BashCommands(TypedDict):
     """CI service type."""
     commands: list[list[str]]
     """Parsed bash commands."""
+    job_name: str
+    """The name of the job where commands were called."""
+    step_name: str
+    """The name of the step where commands were called."""
 
 
 def parse_file(file_path: str, macaron_path: str = "") -> dict:
@@ -119,6 +123,8 @@ def extract_bash_from_ci(
     recursive: bool = False,
     repo_path: str = "",
     working_dir: str = "",
+    job_name: str = "",
+    step_name: str = "",
 ) -> Iterable[BashCommands]:
     """Parse the bash scripts triggered from CI.
 
@@ -140,6 +146,10 @@ def extract_bash_from_ci(
     working_dir : str
         The working directory from which the bash script has run.
         Empty value is considered as the root of the repo.
+    job_name: str
+        The name of the job where commands were called.
+    step_name: str
+        The name of the step where commands were called.
 
     Yields
     ------
@@ -152,7 +162,14 @@ def extract_bash_from_ci(
     parsed_parent = parse(bash_content)
     caller_commands = parsed_parent.get("commands", [])
     if caller_commands:
-        yield BashCommands(caller_path=ci_file, CI_path=ci_file, CI_type=ci_type, commands=caller_commands)
+        yield BashCommands(
+            caller_path=ci_file,
+            CI_path=ci_file,
+            CI_type=ci_type,
+            commands=caller_commands,
+            job_name=job_name,
+            step_name=step_name,
+        )
 
     # Parse the bash script files called from the current script.
     if recursive and repo_path:
@@ -170,4 +187,6 @@ def extract_bash_from_ci(
                     CI_path=ci_file,
                     CI_type=ci_type,
                     commands=callee_commands,
+                    job_name=job_name,
+                    step_name=step_name,
                 )

src/macaron/slsa_analyzer/checks/build_as_code_check.py

@@ -188,7 +188,7 @@ def _check_build_tool(
                                 ctx.component.repository.branch_name,
                                 ctx.component.repository.commit_sha,
                                 ctx.component.repository.commit_date,
-                                os.path.basename(callee.caller_path),
+                                callee.caller_path,
                             )
 
                             # TODO: include in the justification multiple cases of external action usage
@@ -253,7 +253,7 @@ def _check_build_tool(
                             ctx.component.repository.branch_name,
                             ctx.component.repository.commit_sha,
                             ctx.component.repository.commit_date,
-                            os.path.basename(bash_cmd["CI_path"]),
+                            bash_cmd["CI_path"],
                         )
 
                         justification_cmd: list[str | dict[str, str]] = [
@@ -283,6 +283,8 @@ def _check_build_tool(
                                 "sha1"
                             ] = ctx.component.repository.commit_sha
                             predicate["invocation"]["configSource"]["entryPoint"] = trigger_link
+                            predicate["buildConfig"]["jobID"] = bash_cmd["job_name"]
+                            predicate["buildConfig"]["stepID"] = bash_cmd["step_name"]
                             predicate["metadata"]["buildInvocationId"] = html_url
                         check_result["result_tables"].append(
                             BuildAsCodeFacts(