refactor: refactoring existing source code analysis functionality

Author: art1f1c3R

src/macaron/__main__.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2022 - 2024, Oracle and/or its affiliates. All rights reserved.
+# Copyright (c) 2022 - 2025, 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/.
 
 """This is the main entrypoint to run Macaron."""
@@ -179,7 +179,7 @@ def analyze_slsa_levels_single(analyzer_single_args: argparse.Namespace) -> None
         analyzer_single_args.sbom_path,
         deps_depth,
         provenance_payload=prov_payload,
-        validate_malware_switch=analyzer_single_args.validate_malware_switch,
+        analyze_source=analyzer_single_args.analyze_source,
     )
     sys.exit(status_code)
 
@@ -486,10 +486,13 @@ def main(argv: list[str] | None = None) -> None:
     )
 
     single_analyze_parser.add_argument(
-        "--validate-malware-switch",
+        "--analyze-source",
         required=False,
         action="store_true",
-        help=("Enable malware validation."),
+        help=(
+            "EXPERIMENTAL. For improved malware detection, analyze the source code of the"
+            + " (PyPI) package using a textual scan and dataflow analysis."
+        ),
     )
 
     # Dump the default values.

src/macaron/config/defaults.ini

@@ -594,3 +594,7 @@ major_threshold = 20
 epoch_threshold = 3
 # The number of days +/- the day of publish the calendar versioning day may be.
 day_publish_error = 4
+
+# yaml configuration file containing suspicious patterns. Can be full path or relative to
+# folder where macaron is installed
+suspicious_patterns_file = src/macaron/malware_analyzer/pypi_heuristics/sourcecode/suspicious_patterns.yaml

src/macaron/malware_analyzer/pypi_heuristics/heuristics.py

@@ -37,6 +37,9 @@ class Heuristics(str, Enum):
     #: Indicates that the package has an unusually large version number for a single release.
     ANOMALOUS_VERSION = "anomalous_version"
 
+    #: Indicates that the package source code contains suspicious code patterns.
+    SUSPICIOUS_PATTERNS = "suspicious_patterns"
+
 
 class HeuristicResult(str, Enum):
     """Result type indicating the outcome of a heuristic."""