Initial packaging of the project

- Changed project structure to a flat layout
- Fixed package data path using importlib.resources.files
- Stored result output in the user’s home directory

Author: nolliv22

.gitignore

@@ -1,6 +1,9 @@
+build/
+
 # Python
 __pycache__/
 .venv/
+*.egg-info
 
 # Ruff
 .ruff_cache

data/README.md

@@ -1,9 +1,14 @@
 [project]
 name = "SASTBenchmark"
-version = "1.0.0"
-description = "A collection of scripts and wrappers around SASTs and datasets for benchmarking and project testing purposes."
+version = "1.1.0"
+description = "Scripts and wrappers for SASTs and datasets, with abstractions to support integration, benchmarking, and testing."
 readme = "README.md"
+license = "AGPL-3.0-only"
+license-files = ["LICENSE"]
 requires-python = ">=3.12"
+authors = [
+  {name = "Villon Chen"},
+]
 dependencies = [
     "blessed>=1.21.0",
     "click>=8.2.1",
@@ -19,6 +24,19 @@ dependencies = [
     "xmltodict>=0.14.2",
 ]
 
+[project.scripts]
+sastb = "sastbenchmark.main:cli"
+
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+include = ["sastbenchmark", "sastbenchmark.*"]
+
+[tool.setuptools]
+include-package-data = true
+
 [tool.ruff.lint]
-select = ["E", "F", "I", "ANN", "B"]
-ignore = ["E501", "ANN101", "ANN102", "ANN204"]
+select = ["E", "F", "I", "ANN", "B", "TC"]
+ignore = ["E501"]

datasets/README.md

@@ -2,8 +2,10 @@
 import glob
 import os
 
+from sastbenchmark.utils import PACKAGE_DIR
+
 CWE = {}
-for file_path in glob.glob(os.path.join("data", "cwe", "CWE_*.csv")):
+for file_path in glob.glob(os.path.join(PACKAGE_DIR, "data", "cwe", "CWE_*.csv")):
     with open(file_path, mode="r", encoding="utf-8") as file:
         reader = csv.DictReader(file)
         for row in reader:

datasets/__init__.py

@@ -3,7 +3,7 @@
 import zipfile
 from typing import Self
 
-from datasets._base.dataset import File, FileDataset
+from sastbenchmark.datasets._base.dataset import File, FileDataset
 
 
 class TestFile(File):
@@ -14,7 +14,7 @@ def __init__(
         cwe_ids: list[int],
         vuln_type: str,
         is_real: bool,
-    ):
+    ) -> None:
         super().__init__(
             filename=filename, content=content, cwe_ids=cwe_ids, is_real=is_real
         )
@@ -25,14 +25,16 @@ def __init__(
 class BenchmarkJava(FileDataset):
     name = "BenchmarkJava"
 
-    def __init__(self, lang: None | str = None):
+    def __init__(self, lang: None | str = None) -> None:
         super().__init__(lang)
 
-    def __eq__(self, other: str | Self):
+    def __eq__(self, other: str | Self) -> bool:
         if isinstance(other, str):
             return self.name == other
         elif isinstance(other, self.__class__):
             return self.name == other.name
+        else:
+            return False
 
     def load_dataset(self) -> list[TestFile]:
         files = []