Updat quality dependencies and lint setup.py

Author: mariosasko

.github/workflows/ci.yml

@@ -28,8 +28,8 @@ jobs:
           pip install .[quality]
       - name: Check quality
         run: |
-          ruff check tests src benchmarks metrics utils # linter
-          ruff format --check tests src benchmarks metrics utils # formatter
+          ruff check tests src benchmarks metrics utils setup.py # linter
+          ruff format --check tests src benchmarks metrics utils setup.py # formatter
 
   test:
     needs: check_code_quality

Makefile

@@ -5,14 +5,14 @@ check_dirs := tests src benchmarks metrics utils
 # Check that source code meets quality standards
 
 quality:
-	ruff check $(check_dirs)  # linter
-	ruff format --check $(check_dirs) # formatter
+	ruff check $(check_dirs) setup.py  # linter
+	ruff format --check $(check_dirs) setup.py # formatter
 
 # Format source code automatically
 
 style:
-	ruff check --fix $(check_dirs) # linter
-	ruff format $(check_dirs) # formatter
+	ruff check --fix $(check_dirs) setup.py # linter
+	ruff format $(check_dirs) setup.py # formatter
 
 # Run tests for the library
 

setup.py

@@ -216,7 +216,7 @@
 TESTS_REQUIRE.extend(VISION_REQUIRE)
 TESTS_REQUIRE.extend(AUDIO_REQUIRE)
 
-QUALITY_REQUIRE = ["black~=23.1", "ruff>=0.0.241", "pyyaml>=5.3.1"]
+QUALITY_REQUIRE = ["ruff>=0.1.5"]
 
 DOCS_REQUIRE = [
     # Might need to add doc-builder and some specific deps in the future

src/datasets/filesystems/compression.py

@@ -10,7 +10,9 @@ class BaseCompressedFileFileSystem(AbstractArchiveFileSystem):
     """Read contents of compressed file as a filesystem with one file inside."""
 
     root_marker = ""
-    protocol: str = None  # protocol passed in prefix to the url. ex: "gzip", for gzip://file.txt::http://foo.bar/file.txt.gz
+    protocol: str = (
+        None  # protocol passed in prefix to the url. ex: "gzip", for gzip://file.txt::http://foo.bar/file.txt.gz
+    )
     compression: str = None  # compression type in fsspec. ex: "gzip"
     extension: str = None  # extension of the filename to strip. ex: "".gz" to get file.txt from file.txt.gz
 

src/datasets/splits.py

@@ -111,6 +111,7 @@ class SplitBase(metaclass=abc.ABCMeta):
              to define which files to read and how to skip examples within file.
 
     """
+
     # pylint: enable=line-too-long
 
     @abc.abstractmethod

tests/test_load.py

@@ -84,9 +84,7 @@ def _generate_examples(self, filepath, **kwargs):
 SAMPLE_DATASET_IDENTIFIER = "hf-internal-testing/dataset_with_script"  # has dataset script
 SAMPLE_DATASET_IDENTIFIER2 = "hf-internal-testing/dataset_with_data_files"  # only has data files
 SAMPLE_DATASET_IDENTIFIER3 = "hf-internal-testing/multi_dir_dataset"  # has multiple data directories
-SAMPLE_DATASET_IDENTIFIER4 = (
-    "hf-internal-testing/imagefolder_with_metadata"
-)  # imagefolder with a metadata file outside of the train/test directories
+SAMPLE_DATASET_IDENTIFIER4 = "hf-internal-testing/imagefolder_with_metadata"  # imagefolder with a metadata file outside of the train/test directories
 SAMPLE_NOT_EXISTING_DATASET_IDENTIFIER = "hf-internal-testing/_dummy"
 SAMPLE_DATASET_NAME_THAT_DOESNT_EXIST = "_dummy"
 SAMPLE_DATASET_NO_CONFIGS_IN_METADATA = "hf-internal-testing/audiofolder_no_configs_in_metadata"