Switched pylint/black to ruff

.github/workflows/check-style.yml

@@ -8,7 +8,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
-    - uses: psf/black@stable
     - name: Set up Python 3.12
       uses: actions/setup-python@v5
       with:

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
     -   id: check-added-large-files
         args: ['--maxkb=20000']
@@ -44,12 +44,9 @@ repos:
     -   id: rst-directive-colons
     -   id: rst-inline-touching-normal
     -   id: text-unicode-replacement-char
--   repo: https://github.com/psf/black
-    rev: 23.11.0
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.4
     hooks:
-    -   id: black
--   repo: https://github.com/PyCQA/pylint
-    rev: v3.0.1
-    hooks:
-    -   id: pylint
-        args: ['--disable=R0801,E0401,W0718,W0719,W1510,C0103,W0621']
+    -   id: ruff
+        args: [ --fix ]
+    -   id: ruff-format

Makefile

@@ -23,12 +23,12 @@ showvars:
 	@echo "PYTHON_FILES=${PYTHON_FILES}"
 
 python-style:
-	black ${PYTHON_FILES}
-	pylint -f parseable --disable=W,invalid-name,c-extension-no-member,duplicate-code ${PYTHON_FILES}
+	ruff format ${PYTHON_FILES}
+	ruff check ${PYTHON_FILES} --fix
 
 check-python-style:
-	black ${PYTHON_FILES} --check
-	pylint -f parseable --disable=W,invalid-name --disable=W,duplicate-code ${PYTHON_FILES}
+	ruff format ${PYTHON_FILES} --check
+	ruff check ${PYTHON_FILES}
 
 # This target deletes files that are not committed to version control.
 clean:

environment.yml

@@ -25,12 +25,11 @@ dependencies:
       - matplotlib==3.8.4
       - numpy==1.26.4
       - pandas==2.2.2
-      - pylint==3.1.0
+      - ruff==0.4.4
       - GitPython==3.1.43
       - prettytable==3.10.0
       - seaborn==0.13.2
       - rich==13.7.1
-      - black==24.4.2
       - psutil==5.9.8
       - termplotlib==0.3.9
       - loguru==0.7.2

src/python/add_jacoco_gradle.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Adds Jacoco plugin configuration to a Gradle build file. """
+"""Adds Jacoco plugin configuration to a Gradle build file."""
+
 import argparse
 
 

src/python/add_jacoco_maven.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Adds Jacoco plugin configuration to a Maven pom.xml file. """
+"""Adds Jacoco plugin configuration to a Maven pom.xml file."""
 
 from typing import Any
 import argparse

src/python/cache_merger.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Merge multiple caches into one. Usage:
-    python3 cache_merger.py <cache1> <cache2> ... <cacheN> --output_cache <output_cache>
+"""Merge multiple caches into one. Usage:
+python3 cache_merger.py <cache1> <cache2> ... <cacheN> --output_cache <output_cache>
 """
+
 import shutil
 import json
 from argparse import ArgumentParser

src/python/cache_utils.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Contains all the functions related to the caches. The functions to interact with each
+"""Contains all the functions related to the caches. The functions to interact with each
 of the caches are in this file. Each cache is interacted with through the functions
 of this file. The caches are all JSON files and are stored in the cache directory.
 There will be 4 caches in total which are stored on disk after running the run.sh script:

src/python/delete_adjacent_keys_from_cache.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
-""" Delete the keys containing 'imports' in the JSON files in the given directory. """
+"""Delete the keys containing 'imports' in the JSON files in the given directory."""
+
 import os
 import json
 

src/python/delete_import_keys_from_cache.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
-""" Delete the keys containing 'imports' in the JSON files in the given directory. """
+"""Delete the keys containing 'imports' in the JSON files in the given directory."""
+
 import os
 import json
 

src/python/latex_output.py

@@ -20,7 +20,6 @@
 - output_dir: path to the directory where the LaTeX files will be saved
 """
 
-
 import os
 import argparse
 from pathlib import Path
@@ -186,9 +185,7 @@ def build_table1(
     return table
 
 
-def build_table2(  # pylint: disable=too-many-locals
-    main: pd.DataFrame, merge_tools: List[str], feature
-) -> str:
+def build_table2(main: pd.DataFrame, merge_tools: List[str], feature) -> str:
     """Build a table with the results of the merge tools.
     Args:
         main: DataFrame containing the results of the merge tools for the main branch
@@ -261,7 +258,7 @@ def build_table2(  # pylint: disable=too-many-locals
     return table2
 
 
-def main():  # pylint: disable=too-many-locals,too-many-branches,too-many-statements
+def main():
     """Main function"""
     parser = argparse.ArgumentParser()
     parser.add_argument("--run_name", type=str, default="combined")
@@ -485,7 +482,7 @@ def merge_two_states(
             results = []
             for cost_factor in np.linspace(1, max_cost_intersection, 1000):
                 score = unhandled[idx] * 1 + incorrect[idx] * cost_factor
-                score = score / ((unhandled[idx] + incorrect[idx] + correct[idx]))
+                score = score / (unhandled[idx] + incorrect[idx] + correct[idx])
                 score = 1 - score
                 results.append(score)
             line_style = [(idx, (1, 1)), "--", "-."][idx % 3]
@@ -524,7 +521,7 @@ def merge_two_states(
         results = []
         for cost_factor in np.linspace(1, max_cost_intersection, 1000):
             score = unhandled[-1] * 1 + incorrect[-1] * cost_factor
-            score = score / ((unhandled[-1] + incorrect[-1] + correct[-1]))
+            score = score / (unhandled[-1] + incorrect[-1] + correct[-1])
             score = 1 - score
             results.append(score)
         # print(results)

src/python/merge_analyzer.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Analyze the merges i.e. check if the parents pass tests and statistics between merges.
+"""Analyze the merges i.e. check if the parents pass tests and statistics between merges.
 usage: python3 merge_analyzer.py --repos_head_passes_csv <path_to_repos_head_passes.csv>
                                 --merges_path <path_to_merges>
                                 --output_dir <output_dir>
@@ -149,8 +149,8 @@ def diff_merge_analyzer(
     return cache_data
 
 
-def merge_analyzer(  # pylint: disable=too-many-locals,too-many-statements
-    args: Tuple[str, pd.Series, Path]
+def merge_analyzer(
+    args: Tuple[str, pd.Series, Path],
 ) -> pd.Series:
     """
     Merges two branches and returns the result.

src/python/merge_runtime_measure.py

@@ -28,7 +28,7 @@
 )
 
 
-def main():  # pylint: disable=too-many-locals,too-many-statements
+def main():
     """Main function"""
     logger.info("merge_timer: Start")
     parser = argparse.ArgumentParser()

src/python/merge_tester.py

@@ -140,7 +140,7 @@ def build_arguments(
     ]
 
 
-def main():  # pylint: disable=too-many-locals,too-many-statements
+def main():
     """Main function"""
     logger.info("merge_tester: Start")
     parser = argparse.ArgumentParser()

src/python/merges_sampler.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-""" Samples n_merges for each repository.
+"""Samples n_merges for each repository.
 usage: python3 merges_sampler.py --repos_head_passes_csv <path_to_repos_head_passes.csv>
                                 --merges_path <path_to_merges>
                                 --output_dir <output_dir>

src/python/replay_merge.py

@@ -6,6 +6,7 @@
   replay_merge.py --idx INDEX
 where INDEX is, for example, 38-192 .
 """
+
 import argparse
 import os
 import sys
@@ -56,7 +57,6 @@ def delete_workdirs(results_df: pd.DataFrame) -> None:
     logger.info("Workdirs deleted")
 
 
-# pylint: disable=too-many-arguments, too-many-locals, too-many-branches, too-many-statements
 def merge_replay(
     merge_idx: str,
     repo_slug: str,
@@ -228,7 +228,7 @@ def merge_replay(
             ]
             assert repo.local_repo_path.exists()
 
-            if (  # pylint: disable=too-many-boolean-expressions
+            if (
                 merge_result
                 not in (
                     MERGE_STATE.Git_checkout_failed,

src/python/repo.py

@@ -164,7 +164,7 @@ def repo_test(wcopy_dir: Path, timeout: int) -> Tuple[TEST_STATE, str]:
         str(wcopy_dir),
     ]
     try:
-        p = subprocess.run(  # pylint: disable=consider-using-with
+        p = subprocess.run(
             command,
             capture_output=True,
             timeout=timeout,
@@ -179,10 +179,10 @@ def repo_test(wcopy_dir: Path, timeout: int) -> Tuple[TEST_STATE, str]:
     return TEST_STATE.Tests_failed, explanation
 
 
-class Repository:  # pylint: disable=too-many-instance-attributes
+class Repository:
     """A class that represents a repository."""
 
-    def __init__(  # pylint: disable=too-many-arguments
+    def __init__(
         self,
         repo_slug: str,
         cache_directory: Path = Path(""),
@@ -294,7 +294,7 @@ def checkout(self, commit: str, use_cache: bool = True) -> Tuple[bool, str]:
             set_in_cache(commit, cache_entry, self.repo_slug, self.sha_cache_directory)
         return True, explanation
 
-    def _merge_and_test(  # pylint: disable=too-many-arguments
+    def _merge_and_test(
         self,
         tool: MERGE_TOOL,
         left_commit: str,
@@ -348,7 +348,7 @@ def _merge_and_test(  # pylint: disable=too-many-arguments
             test_coverage,
         )
 
-    def merge_and_test(  # pylint: disable=too-many-arguments
+    def merge_and_test(
         self,
         tool: MERGE_TOOL,
         left_commit: str,
@@ -438,7 +438,7 @@ def create_branch(
         self.repo.git.checkout("-b", branch_name, force=True)
         return tree_fingerprint, explanation
 
-    def merge(  # pylint: disable=too-many-locals,too-many-arguments
+    def merge(
         self,
         tool: MERGE_TOOL,
         left_commit: str,
@@ -509,7 +509,7 @@ def merge(  # pylint: disable=too-many-locals,too-many-arguments
             RIGHT_BRANCH_NAME,
         ]
         try:
-            p = subprocess.run(  # pylint: disable=consider-using-with
+            p = subprocess.run(
                 command,
                 capture_output=True,
                 timeout=timeout if timeout > 0 else None,

src/python/test_repo_heads.py

@@ -12,6 +12,7 @@
 Cache_dir is the directory where the cache will be stored.
 Output: the rows of the input for which the commit at head hash passes tests.
 """
+
 import multiprocessing
 import os
 import argparse

src/scripts/merge_tools/resolve-conflicts.py

@@ -1,4 +1,4 @@
-#! /usr/bin/env python  # pylint: skip-file
+#! /usr/bin/env python
 # -*- coding: utf-8 -*-
 
 # This is a helper script for `resolve-adjacent-conflicts` and
@@ -39,7 +39,7 @@
 debug = False
 
 
-def main():  # pylint: disable=too-many-locals
+def main():
     """The main entry point."""
     arg_parser = ArgumentParser()
     arg_parser.add_argument("filename")
@@ -114,7 +114,7 @@ def main():  # pylint: disable=too-many-locals
         sys.exit(0)
 
 
-def looking_at_conflict(  # pylint: disable=too-many-return-statements
+def looking_at_conflict(
     filename: str, start_index: int, lines: List[str]
 ) -> Union[None, Tuple[List[str], List[str], List[str], int]]:
     """Tests whether the following text starts a conflict.
@@ -185,7 +185,7 @@ def looking_at_conflict(  # pylint: disable=too-many-return-statements
     return (base, parent1, parent2, index - start_index)
 
 
-def merge(  # pylint: disable=too-many-arguments
+def merge(
     base: List[str],
     parent1: List[str],
     parent2: List[str],
@@ -296,7 +296,6 @@ def merge_base_is_prefix_or_suffix(
     """
     base_len = len(base)
     parent1_len = len(parent1)
-    parent2_len = len(parent2)
     if base_len < parent1_len:
         if parent1[:base_len] == base:
             debug_print("startswith", parent1, base)

test/check_equal_csv.py

@@ -54,7 +54,7 @@ def remove_run_time(df):
                     raise ValueError(
                         f'goal_df.columns contains "run_time": {goal_df.columns}'
                     )
-                if not col in actual_df:
+                if col not in actual_df:
                     print(f"Column {col} is not in actual_df")
                     print(goal_df[col])
                     different_columns.append(col)