feat(datasets): pass artifact arguments to benchmark commands

Author: nolliv22

codesectools/datasets/BenchmarkJava/dataset.py

@@ -54,6 +54,11 @@ class BenchmarkJava(PrebuiltFileDataset):
     Attributes:
         name (str): The name of the dataset, "BenchmarkJava".
         supported_languages (list[str]): A list of supported programming languages.
+        license (str): The license under which the dataset is distributed.
+        license_url (str): A URL to the full text of the license.
+        build_command (str): The command to build the Java project.
+        prebuilt_expected (tuple): A tuple defining the path and glob pattern for expected build artifacts.
+        artefacts_arg (str): The argument to specify the location of build artifacts for SAST tools.
 
     """
 
@@ -64,6 +69,7 @@ class BenchmarkJava(PrebuiltFileDataset):
 
     build_command = "mvn clean compile"
     prebuilt_expected = (Path("target/classes/org/owasp/benchmark/testcode"), "*.class")
+    artefacts_arg = "."
 
     def __init__(self, lang: None | str = None) -> None:
         """Initialize the BenchmarkJava dataset.

codesectools/datasets/core/dataset.py

@@ -150,10 +150,19 @@ def list_dataset_full_names(cls) -> list[str]:
 
 
 class PrebuiltDatasetMixin:
-    """Provide functionality for datasets that require a build step."""
+    """Provide functionality for datasets that require a build step.
+
+    Attributes:
+        build_command (str): The command required to build the dataset.
+        prebuilt_expected (tuple[Path, str]): A tuple containing the path and glob pattern
+            to find the built artifacts.
+        artefacts_arg (str): The argument to pass to the SAST tool command template.
+
+    """
 
     build_command: str
     prebuilt_expected: tuple[Path, str]
+    artefacts_arg: str
 
     def is_built(self) -> bool:
         """Check if the dataset has been built."""
@@ -271,15 +280,7 @@ def save(self, dir: Path) -> None:
 
 
 class FileDataset(Dataset):
-    """Abstract base class for datasets composed of individual files.
-
-    Attributes:
-        directory (Path): The directory path for the dataset.
-        lang (str): The programming language of the dataset.
-        full_name (str): The full name of the dataset, including the language.
-        files (list[File]): A list of `File` objects loaded from the dataset.
-
-    """
+    """Abstract base class for datasets composed of individual files."""
 
     def __init__(self, lang: str) -> None:
         """Initialize a FileDataset instance.

codesectools/sasts/core/sast/__init__.py

@@ -374,7 +374,12 @@ def analyze_files(
                 )
                 return
 
-        self.run_analysis(dataset.lang, dataset.directory, result_path)
+        self.run_analysis(
+            dataset.lang,
+            dataset.directory,
+            result_path,
+            artifacts=dataset.artefacts_arg,
+        )
 
 
 class PrebuiltBuildlessSAST(PrebuiltSAST, BuildlessSAST):