Migrate from yapf to black

.pre-commit-config.yaml

@@ -1,50 +1,50 @@
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
-    hooks:
-      - id: check-executables-have-shebangs
-      - id: check-json
-      - id: check-merge-conflict
-      - id: check-shebang-scripts-are-executable
-      - id: check-toml
-      - id: check-yaml
-      - id: double-quote-string-fixer
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
-        args: ["--fix=lf"]
-      - id: requirements-txt-fixer
-      - id: trailing-whitespace
-  - repo: https://github.com/myint/docformatter
-    rev: v1.4
-    hooks:
-      - id: docformatter
-        args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.991
-    hooks:
-      - id: mypy
-        args: ["--ignore-missing-imports"]
-        additional_dependencies: ["types-python-slugify", "types-requests"]
-  - repo: https://github.com/google/yapf
-    rev: v0.32.0
-    hooks:
-      - id: yapf
-        args: ["--parallel", "--in-place"]
-  - repo: https://github.com/kynan/nbstripout
-    rev: 0.6.0
-    hooks:
-      - id: nbstripout
-        args:
-          [
-            "--extra-keys",
-            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
-          ]
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.7.0
-    hooks:
-      - id: nbqa-isort
-      - id: nbqa-yapf
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.4.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ["--fix=lf"]
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.7.5
+  hooks:
+  - id: docformatter
+    args: ["--in-place"]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+      args: ["--profile", "black"]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.5.1
+  hooks:
+    - id: mypy
+      args: ["--ignore-missing-imports"]
+      additional_dependencies: ["types-python-slugify", "types-requests", "types-PyYAML"]
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.10
+      args: ["--line-length", "119"]
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.6.1
+  hooks:
+    - id: nbstripout
+      args: ["--extra-keys", "metadata.interpreter metadata.kernelspec cell.metadata.pycharm"]
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.7.0
+  hooks:
+    - id: nbqa-black
+    - id: nbqa-pyupgrade
+      args: ["--py37-plus"]
+    - id: nbqa-isort
+      args: ["--float-to-top"]

.style.yapf

@@ -1,5 +0,0 @@
-[style]
-based_on_style = pep8
-blank_line_before_nested_class_or_def = false
-spaces_before_comment = 2
-split_before_logical_operator = true

.vscode/settings.json

@@ -1,18 +1,21 @@
 {
-    "python.linting.enabled": true,
-    "python.linting.flake8Enabled": true,
-    "python.linting.pylintEnabled": false,
-    "python.linting.lintOnSave": true,
-    "python.formatting.provider": "yapf",
-    "python.formatting.yapfArgs": [
-        "--style={based_on_style: pep8, indent_width: 4, blank_line_before_nested_class_or_def: false, spaces_before_comment: 2, split_before_logical_operator: true}"
-    ],
     "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
         "editor.formatOnType": true,
         "editor.codeActionsOnSave": {
             "source.organizeImports": true
         }
     },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.args": [
+        "--line-length=119"
+    ],
     "editor.formatOnSave": true,
     "files.insertFinalNewline": true
 }

app.py

@@ -7,22 +7,22 @@ import gradio as gr
 from papers import PaperList, get_df
 from update_scheduler import UpdateScheduler
 
-DESCRIPTION = '''# [Daily Papers](https://huggingface.co/papers)'''
+DESCRIPTION = "# [Daily Papers](https://huggingface.co/papers)"
 
-paper_list = PaperList(get_df('papers.csv'))
+paper_list = PaperList(get_df("papers.csv"))
 
-if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
-    CRON_HOUR = os.getenv('CRON_HOUR', '*/4')
-    CRON_MINUTE = os.getenv('CRON_MINUTE', '0')
-    scheduler = UpdateScheduler(space_id=SPACE_ID,
-                                cron_hour=CRON_HOUR,
-                                cron_minute=CRON_MINUTE)
+if (SPACE_ID := os.getenv("SPACE_ID")) is not None:
+    CRON_HOUR = os.getenv("CRON_HOUR", "*/4")
+    CRON_MINUTE = os.getenv("CRON_MINUTE", "0")
+    scheduler = UpdateScheduler(space_id=SPACE_ID, cron_hour=CRON_HOUR, cron_minute=CRON_MINUTE)
     scheduler.start()
 
-with gr.Blocks(css='style.css') as demo:
+with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
-    df = gr.Dataframe(value=paper_list.df_prettified,
-                      datatype=paper_list.column_datatype,
-                      type='pandas',
-                      interactive=False)
+    df = gr.Dataframe(
+        value=paper_list.df_prettified,
+        datatype=paper_list.column_datatype,
+        type="pandas",
+        interactive=False,
+    )
 demo.queue(api_open=False).launch()

papers.py

@@ -19,31 +19,28 @@ class PaperInfo:
     published_at: str
 
     def __post_init__(self):
-        object.__setattr__(self, 'published_at',
-                           PaperInfo.convert_timestamp(self.published_at))
+        object.__setattr__(self, "published_at", PaperInfo.convert_timestamp(self.published_at))
 
     @staticmethod
     def convert_timestamp(timestamp: str) -> str:
         try:
-            return datetime.datetime.strptime(
-                timestamp,
-                '%Y-%m-%dT%H:%M:%S.%fZ').strftime('%Y/%m/%d %H:%M:%S')
+            return datetime.datetime.strptime(timestamp, "%Y-%m-%dT%H:%M:%S.%fZ").strftime("%Y/%m/%d %H:%M:%S")
         except ValueError:
             return timestamp
 
 
 def get_df(path: pathlib.Path | str) -> pd.DataFrame:
-    df = pd.read_csv(path, dtype=str).fillna('')
+    df = pd.read_csv(path, dtype=str).fillna("")
     paper_info = []
     for _, row in tqdm.auto.tqdm(df.iterrows(), total=len(df)):
-        res = requests.get(
-            f'https://huggingface.co/api/papers/{row.arxiv_id}').json()
+        res = requests.get(f"https://huggingface.co/api/papers/{row.arxiv_id}").json()
         info = PaperInfo(
             **row,
-            title=res['title'],
-            paper_page=f'https://huggingface.co/papers/{row.arxiv_id}',
-            upvotes=res['upvotes'],
-            published_at=res['publishedAt'])
+            title=res["title"],
+            paper_page=f"https://huggingface.co/papers/{row.arxiv_id}",
+            upvotes=res["upvotes"],
+            published_at=res["publishedAt"],
+        )
         paper_info.append(info)
     return pd.DataFrame([dataclasses.asdict(info) for info in paper_info])
 
@@ -52,8 +49,8 @@ class Prettifier:
     @staticmethod
     def get_github_link(link: str) -> str:
         if not link:
-            return ''
-        return Prettifier.create_link('github', link)
+            return ""
+        return Prettifier.create_link("github", link)
 
     @staticmethod
     def create_link(text: str, url: str) -> str:
@@ -62,23 +59,18 @@ class Prettifier:
     @staticmethod
     def to_div(text: str | None, category_name: str) -> str:
         if text is None:
-            text = ''
-        class_name = f'{category_name}-{text.lower()}'
+            text = ""
+        class_name = f"{category_name}-{text.lower()}"
         return f'<div class="{class_name}">{text}</div>'
 
     def __call__(self, df: pd.DataFrame) -> pd.DataFrame:
-        df = df.sort_values('arxiv_id', ascending=False).reset_index(drop=True)
+        df = df.sort_values("arxiv_id", ascending=False).reset_index(drop=True)
         new_rows = []
         for _, row in df.iterrows():
             new_row = dict(row) | {
-                'date':
-                Prettifier.create_link(
-                    row.date,
-                    f'https://huggingface.co/papers?date={row.date}'),
-                'paper_page':
-                Prettifier.create_link(row.arxiv_id, row.paper_page),
-                'github':
-                self.get_github_link(row.github),
+                "date": Prettifier.create_link(row.date, f"https://huggingface.co/papers?date={row.date}"),
+                "paper_page": Prettifier.create_link(row.arxiv_id, row.paper_page),
+                "github": self.get_github_link(row.github),
             }
             new_rows.append(new_row)
         return pd.DataFrame(new_rows, columns=df.columns)
@@ -86,11 +78,11 @@ class Prettifier:
 
 class PaperList:
     COLUMN_INFO = [
-        ['date', 'markdown'],
-        ['paper_page', 'markdown'],
-        ['title', 'str'],
-        ['github', 'markdown'],
-        ['upvotes', 'number'],
+        ["date", "markdown"],
+        ["paper_page", "markdown"],
+        ["title", "str"],
+        ["github", "markdown"],
+        ["upvotes", "number"],
     ]
 
     def __init__(self, df: pd.DataFrame):

update_scheduler.py

@@ -13,12 +13,12 @@ from huggingface_hub.utils import RepositoryNotFoundError
 class SpaceRestarter:
     def __init__(self, space_id: str):
         self.api = HfApi()
-        if self.api.get_token_permission() != 'write':
-            raise ValueError('The HF token must have write permission.')
+        if self.api.get_token_permission() != "write":
+            raise ValueError("The HF token must have write permission.")
         try:
             self.api.space_info(repo_id=space_id)
         except RepositoryNotFoundError:
-            raise ValueError('The Space ID does not exist.')
+            raise ValueError("The Space ID does not exist.")
         self.space_id = space_id
 
     def restart(self) -> None:
@@ -26,15 +26,13 @@ class SpaceRestarter:
 
 
 def find_github_links(summary: str) -> str:
-    links = re.findall(
-        r'https://github.com/[^/]+/[^/)}, ]+(?:/(?:tree|blob)/[^/]+/[^/)}, ]+)?',
-        summary)
+    links = re.findall(r"https://github.com/[^/]+/[^/)}, ]+(?:/(?:tree|blob)/[^/]+/[^/)}, ]+)?", summary)
     if len(links) == 0:
-        return ''
+        return ""
     if len(links) != 1:
-        raise RuntimeError(f'Found multiple GitHub links: {links}')
+        raise RuntimeError(f"Found multiple GitHub links: {links}")
     link = links[0]
-    if link.endswith('.'):
+    if link.endswith("."):
         link = link[:-1]
     link = link.strip()
     return link
@@ -43,68 +41,62 @@ def find_github_links(summary: str) -> str:
 class RepoUpdater:
     def __init__(self, repo_id: str, repo_type: str):
         api = HfApi()
-        if api.get_token_permission() != 'write':
-            raise ValueError('The HF token must have write permission.')
+        if api.get_token_permission() != "write":
+            raise ValueError("The HF token must have write permission.")
 
-        name = api.whoami()['name']
+        name = api.whoami()["name"]
 
-        repo_dir = pathlib.Path(
-            tempfile.tempdir) / repo_id.split('/')[-1]  # type: ignore
-        self.csv_path = repo_dir / 'papers.csv'
+        repo_dir = pathlib.Path(tempfile.tempdir) / repo_id.split("/")[-1]  # type: ignore
+        self.csv_path = repo_dir / "papers.csv"
         self.repo = Repository(
             local_dir=repo_dir,
             clone_from=repo_id,
             repo_type=repo_type,
             git_user=name,
-            git_email=f'{name}@users.noreply.huggingface.co')
+            git_email=f"{name}@users.noreply.huggingface.co",
+        )
         self.repo.git_pull()
 
     def update(self) -> None:
-        yesterday = (datetime.datetime.now() -
-                     datetime.timedelta(days=1)).strftime('%Y-%m-%d')
-        today = datetime.datetime.now().strftime('%Y-%m-%d')
+        yesterday = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
+        today = datetime.datetime.now().strftime("%Y-%m-%d")
         daily_papers = [
             {
-                'date':
-                yesterday,
-                'papers':
-                requests.get(
-                    f'https://huggingface.co/api/daily_papers?date={yesterday}'
-                ).json()
+                "date": yesterday,
+                "papers": requests.get(f"https://huggingface.co/api/daily_papers?date={yesterday}").json(),
             },
             {
-                'date':
-                today,
-                'papers':
-                requests.get(
-                    f'https://huggingface.co/api/daily_papers?date={today}').
-                json()
+                "date": today,
+                "papers": requests.get(f"https://huggingface.co/api/daily_papers?date={today}").json(),
             },
         ]
 
         self.repo.git_pull()
-        df = pd.read_csv(self.csv_path, dtype=str).fillna('')
+        df = pd.read_csv(self.csv_path, dtype=str).fillna("")
         rows = [row for _, row in df.iterrows()]
         arxiv_ids = {row.arxiv_id for row in rows}
 
         for d in daily_papers:
-            date = d['date']
-            papers = d['papers']
+            date = d["date"]
+            papers = d["papers"]
             for paper in papers:
-                arxiv_id = paper['paper']['id']
+                arxiv_id = paper["paper"]["id"]
                 if arxiv_id in arxiv_ids:
                     continue
                 try:
-                    github = find_github_links(paper['paper']['summary'])
+                    github = find_github_links(paper["paper"]["summary"])
                 except RuntimeError as e:
                     print(e)
                     continue
                 rows.append(
-                    pd.Series({
-                        'date': date,
-                        'arxiv_id': arxiv_id,
-                        'github': github,
-                    }))
+                    pd.Series(
+                        {
+                            "date": date,
+                            "arxiv_id": arxiv_id,
+                            "github": github,
+                        }
+                    )
+                )
         df = pd.DataFrame(rows).reset_index(drop=True)
         df.to_csv(self.csv_path, index=False)
 
@@ -113,17 +105,19 @@ class RepoUpdater:
 
 
 class UpdateScheduler:
-    def __init__(self, space_id: str, cron_hour: str, cron_minute: str):
+    def __init__(self, space_id: str, cron_hour: str, cron_minute: str, cron_second: str = "0"):
         self.space_restarter = SpaceRestarter(space_id=space_id)
-        self.repo_updater = RepoUpdater(repo_id=space_id, repo_type='space')
+        self.repo_updater = RepoUpdater(repo_id=space_id, repo_type="space")
 
         self.scheduler = BackgroundScheduler()
-        self.scheduler.add_job(func=self._update,
-                               trigger='cron',
-                               hour=cron_hour,
-                               minute=cron_minute,
-                               second=0,
-                               timezone='UTC')
+        self.scheduler.add_job(
+            func=self._update,
+            trigger="cron",
+            hour=cron_hour,
+            minute=cron_minute,
+            second=cron_second,
+            timezone="UTC",
+        )
 
     def _update(self) -> None:
         self.repo_updater.update()