Remove unnecessary 'r' arg in

.github/hub/update_hub_repositories.py

@@ -104,7 +104,7 @@ def check_authorizations(user_info: dict):
 
 def apply_hacks_for_moon_landing(dataset_repo_path: Path):
     if (dataset_repo_path / "README.md").is_file():
-        with (dataset_repo_path / "README.md").open("r") as f:
+        with (dataset_repo_path / "README.md").open() as f:
             readme_content = f.read()
         if readme_content.count("---\n") > 1:
             _, tags, content = readme_content.split("---\n", 2)
@@ -185,7 +185,7 @@ def __call__(self, dataset_name: str) -> bool:
     datasets_lib_path = Path(os.environ["DATASETS_LIB_PATH"]).expanduser().resolve()
 
     if Path(token).expanduser().is_file():
-        with Path(token).expanduser().open("r") as f:
+        with Path(token).expanduser().open() as f:
             token = f.read().strip()
     user_info = whoami(token)
     check_authorizations(user_info)

datasets/evidence_infer_treatment/evidence_infer_treatment.py

@@ -140,21 +140,21 @@ def _split_generators(self, dl_manager):
         SPLITS = {}
         for split in ["train", "test", "validation"]:
             filename = os.path.join(dl_dir, "splits", f"{split}_article_ids.txt")
-            with open(filename, "r", encoding="utf-8") as f:
+            with open(filename, encoding="utf-8") as f:
                 for line in f:
                     id_ = int(line.strip())
                     SPLITS[id_] = split
 
         ALL_PROMPTS = {}
         prompts_filename = os.path.join(dl_dir, "prompts_merged.csv")
-        with open(prompts_filename, "r", encoding="utf-8") as f:
+        with open(prompts_filename, encoding="utf-8") as f:
             data = csv.DictReader(f)
             for item in data:
                 prompt_id = int(item["PromptID"])
                 ALL_PROMPTS[prompt_id] = {"Prompt": item, "Annotations": []}
 
         annotations_filename = os.path.join(dl_dir, "annotations_merged.csv")
-        with open(annotations_filename, "r", encoding="utf-8") as f:
+        with open(annotations_filename, encoding="utf-8") as f:
             data = csv.DictReader(f)
             for item in data:
                 prompt_id = int(item["PromptID"])

datasets/timit_asr/timit_asr.py

@@ -137,11 +137,11 @@ def _generate_examples(self, data_info_csv):
             wav_path = os.path.join(data_path, *(audio_data["path_from_data_dir"].split("/")))
 
             # extract transcript
-            with open(wav_path.replace(".WAV", ".TXT"), "r", encoding="utf-8") as op:
+            with open(wav_path.replace(".WAV", ".TXT"), encoding="utf-8") as op:
                 transcript = " ".join(op.readlines()[0].split()[2:])  # first two items are sample number
 
             # extract phonemes
-            with open(wav_path.replace(".WAV", ".PHN"), "r", encoding="utf-8") as op:
+            with open(wav_path.replace(".WAV", ".PHN"), encoding="utf-8") as op:
                 phonemes = [
                     {
                         "start": i.split(" ")[0],
@@ -152,7 +152,7 @@ def _generate_examples(self, data_info_csv):
                 ]
 
             # extract words
-            with open(wav_path.replace(".WAV", ".WRD"), "r", encoding="utf-8") as op:
+            with open(wav_path.replace(".WAV", ".WRD"), encoding="utf-8") as op:
                 words = [
                     {
                         "start": i.split(" ")[0],

tests/features/test_image.py

@@ -484,7 +484,7 @@ def _split_generators(self, dl_manager):
         ]
 
     def _generate_examples(self, filepath, **kwargs):
-        with open(filepath, "r", encoding="utf-8") as f:
+        with open(filepath, encoding="utf-8") as f:
             for i, line in enumerate(f):
                 image_path, caption = line.split(",")
                 yield i, {"image": image_path.strip(), "caption": caption.strip()}