pre-commit

jeffjennings · jeffjennings · commit 31d5916a85da · 2025-06-17T08:12:36.000-04:00
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
@@ -8,7 +8,7 @@ on:
 
 jobs:
 
-  lint: 
+  lint:
     # could be re-implemented if desired
     if: false
     runs-on: ubuntu-latest
@@ -55,7 +55,7 @@ jobs:
 
       - name: Run mypy
         run: tox -e typing
-  
+
   test:
     runs-on: ubuntu-latest
 
diff --git a/astropylibrarian/__init__.py b/astropylibrarian/__init__.py
@@ -6,7 +6,7 @@
 __all__ = ("__version__",)
 
 try:
-    from ._version import __version__ 
+    from ._version import __version__
 except ImportError:
     # package is not installed
     __version__ = ""
diff --git a/astropylibrarian/__main__.py b/astropylibrarian/__main__.py
@@ -1,7 +1,7 @@
 # Licensed under a 3-clause BSD style license - see LICENSE.rst
 """This module enables running the CLI as::
 
-    python -m astropylibrarian
+python -m astropylibrarian
 """
 
 from astropylibrarian.cli.app import app
diff --git a/astropylibrarian/algolia/records.py b/astropylibrarian/algolia/records.py
@@ -55,9 +55,7 @@ class AlgoliaRecord(BaseModel):
     )
 
     root_summary: Optional[str] = Field(
-        description=(
-            "Short summary of the content corresponding to the root_url."
-        )
+        description=("Short summary of the content corresponding to the root_url.")
     )
 
     content_type: ContentType = Field(description="Content type.")
@@ -87,8 +85,7 @@ class AlgoliaRecord(BaseModel):
 
     base_url: HttpUrl = Field(
         description=(
-            "The base URL of the page, without fragments, parameters, "
-            "queries, etc."
+            "The base URL of the page, without fragments, parameters, queries, etc."
         ),
     )
 
@@ -140,9 +137,7 @@ def compute_object_id_for_section(section: Section) -> str:
         str
             The ``objectID`` for an Algolia record.
         """
-        url_component = b64encode(section.url.lower().encode("utf-8")).decode(
-            "utf-8"
-        )
+        url_component = b64encode(section.url.lower().encode("utf-8")).decode("utf-8")
         heading_component = b64encode(
             " ".join(section.headings).encode("utf-8")
         ).decode("utf-8")
@@ -235,9 +230,7 @@ class TutorialRecord(AlgoliaRecord):
         description="List of python package keywords.",
     )
 
-    task_keywords: Optional[List[str]] = Field(
-        description="List of task keywords."
-    )
+    task_keywords: Optional[List[str]] = Field(description="List of task keywords.")
 
     science_keywords: Optional[List[str]] = Field(
         description="List of science keywords."
@@ -307,16 +300,12 @@ def from_section(
             "python_package_keywords": keyworddb.filter_keywords(
                 tutorial.keywords, "python_package"
             ),
-            "task_keywords": keyworddb.filter_keywords(
-                tutorial.keywords, "task"
-            ),
-            "science_keywords": keyworddb.filter_keywords(
-                tutorial.keywords, "science"
-            ),
+            "task_keywords": keyworddb.filter_keywords(tutorial.keywords, "task"),
+            "science_keywords": keyworddb.filter_keywords(tutorial.keywords, "science"),
             "priority": priority,
         }
         for i, heading in enumerate(section.headings):
-            kwargs[f"h{i+1}"] = heading
+            kwargs[f"h{i + 1}"] = heading
         if tutorial.images:
             # TODO consider an explicitly set thumbnail from tutorial metadata
             kwargs["thumbnail_url"] = tutorial.images[0]
@@ -372,9 +361,7 @@ def from_section(
         # The importance of 1 is reserved for the homepage URL so that the
         # homepage is featured in default listings. All other records have
         # importance bumped down lower.
-        if (page.url == site_metadata.homepage_url) and (
-            section.header_level == 1
-        ):
+        if (page.url == site_metadata.homepage_url) and (section.header_level == 1):
             importance = 1
         else:
             importance = section.header_level + 1
@@ -393,5 +380,5 @@ def from_section(
             "priority": site_metadata.priority,
         }
         for i, heading in enumerate(section.headings):
-            kwargs[f"h{i+1}"] = heading
+            kwargs[f"h{i + 1}"] = heading
         return cls(**kwargs)
diff --git a/astropylibrarian/cli/app.py b/astropylibrarian/cli/app.py
@@ -12,9 +12,7 @@
 from astropylibrarian.cli import index
 from astropylibrarian.workflows.deleterooturl import delete_root_url
 
-app = typer.Typer(
-    short_help="Manage the content indexed by the Learn Astropy project."
-)
+app = typer.Typer(short_help="Manage the content indexed by the Learn Astropy project.")
 app.add_typer(index.app, name="index")
 
 
@@ -29,7 +27,7 @@ def main_callback(
             "Verbose output. Use -v for info-type logging and -vv for "
             "debug-level logging."
         ),
-    )
+    ),
 ) -> None:
     """Manage the content index for the Learn Astropy project.
 
@@ -49,16 +47,12 @@ def main_callback(
 
     if logging_level == logging.DEBUG:
         # Include the module name in the logging for easier debugging
-        log_format = (
-            "%(asctime)s %(levelname)8s %(name)s:%(lineno)d | %(message)s"
-        )
+        log_format = "%(asctime)s %(levelname)8s %(name)s:%(lineno)d | %(message)s"
     else:
         log_format = "%(levelname)s: %(message)s"
 
     handler = logging.StreamHandler()
-    handler.setFormatter(
-        logging.Formatter(log_format, datefmt="%Y-%m-%d:%H:%M:%S")
-    )
+    handler.setFormatter(logging.Formatter(log_format, datefmt="%Y-%m-%d:%H:%M:%S"))
     logger = logging.getLogger("astropylibrarian")
     logger.addHandler(handler)
     logger.setLevel(logging_level)
@@ -67,9 +61,7 @@ def main_callback(
 @app.command()
 def delete(
     url: str = typer.Argument(..., help="Root URL to delete"),
-    algolia_id: str = typer.Option(
-        ..., help="Algolia app ID.", envvar="ALGOLIA_ID"
-    ),
+    algolia_id: str = typer.Option(..., help="Algolia app ID.", envvar="ALGOLIA_ID"),
     algolia_key: str = typer.Option(
         ...,
         help="Algolia API key.",
diff --git a/astropylibrarian/cli/index.py b/astropylibrarian/cli/index.py
@@ -23,9 +23,7 @@
 @app.command()
 def tutorial(
     url: str = typer.Argument(..., help="URL or path for a tutorial."),
-    algolia_id: str = typer.Option(
-        ..., help="Algolia app ID.", envvar="ALGOLIA_ID"
-    ),
+    algolia_id: str = typer.Option(..., help="Algolia app ID.", envvar="ALGOLIA_ID"),
     algolia_key: str = typer.Option(
         ...,
         help="Algolia API key.",
@@ -61,13 +59,9 @@ def tutorial(
 
 @app.command("tutorial-site")
 def tutorial_site(
-    site_dir: Path = typer.Argument(
-        ..., help="Local path tutorial build directory"
-    ),
+    site_dir: Path = typer.Argument(..., help="Local path tutorial build directory"),
     url: str = typer.Argument(..., help="Base URL for tutorials."),
-    algolia_id: str = typer.Option(
-        ..., help="Algolia app ID.", envvar="ALGOLIA_ID"
-    ),
+    algolia_id: str = typer.Option(..., help="Algolia app ID.", envvar="ALGOLIA_ID"),
     algolia_key: str = typer.Option(
         ...,
         help="Algolia API key.",
@@ -179,9 +173,7 @@ async def run_index_tutorial(
 @app.command()
 def guide(
     url: str = typer.Argument(..., help="Root URL for a guide."),
-    algolia_id: str = typer.Option(
-        ..., help="Algolia app ID.", envvar="ALGOLIA_ID"
-    ),
+    algolia_id: str = typer.Option(..., help="Algolia app ID.", envvar="ALGOLIA_ID"),
     algolia_key: str = typer.Option(
         ...,
         help="Algolia API key.",
diff --git a/astropylibrarian/keywords.py b/astropylibrarian/keywords.py
@@ -54,15 +54,13 @@ def load(cls, path: Optional[Path] = None) -> "KeywordDb":
 
         keyword_groups: Dict[str, KeywordTable] = {}
         for group_name in db:
-            keyword_groups[group_name] = cls._load_keyword_table(
-                db[group_name]
-            )
+            keyword_groups[group_name] = cls._load_keyword_table(db[group_name])
 
         return cls(**keyword_groups)
 
     @staticmethod
     def _load_keyword_table(
-        group: Sequence[Union[str, Dict[str, Sequence[str]]]]
+        group: Sequence[Union[str, Dict[str, Sequence[str]]]],
     ) -> KeywordTable:
         keywords: KeywordTable = {}
         for keyword_item in group:
diff --git a/astropylibrarian/reducers/jupyterbook.py b/astropylibrarian/reducers/jupyterbook.py
@@ -224,9 +224,7 @@ class JupyterBookMetadata(BaseModel):
     def all_page_urls(self) -> List[str]:
         """The ``page_urls`` along with the ``homepage_url``."""
         return list(
-            set(
-                [str(url) for url in self.page_urls] + [str(self.homepage_url)]
-            )
+            set([str(url) for url in self.page_urls] + [str(self.homepage_url)])
         )
 
     @validator("root_url")
diff --git a/astropylibrarian/reducers/tutorial.py b/astropylibrarian/reducers/tutorial.py
@@ -154,9 +154,7 @@ def iter_algolia_objects(
             An object compatible with algolia search ``save_objects``-type
             methods.
         """
-        for record in self.iter_records(
-            index_epoch=index_epoch, priority=priority
-        ):
+        for record in self.iter_records(index_epoch=index_epoch, priority=priority):
             yield from record.export_capped_records_to_algolia()
 
     def _set_summary_on_h1_section(self) -> None:
@@ -186,9 +184,7 @@ def process_html(self, html_page: HtmlPage) -> None:
             pass
 
         try:
-            authors_paragraph = doc.cssselect(
-                ".card section p, .card .section p"
-            )[0]
+            authors_paragraph = doc.cssselect(".card section p, .card .section p")[0]
             self._authors = self._parse_comma_list(authors_paragraph)
         except IndexError:
             pass
@@ -254,9 +250,7 @@ def process_html(self, html_page: HtmlPage) -> None:
         doc = html_page.parse()
 
         try:
-            self._h1 = (
-                doc.cssselect("h1")[0].text_content().rstrip("¶").strip()
-            )
+            self._h1 = doc.cssselect("h1")[0].text_content().rstrip("¶").strip()
         except IndexError:
             logger.warning("Did not find h1")
             pass
diff --git a/astropylibrarian/reducers/utils.py b/astropylibrarian/reducers/utils.py
@@ -1,6 +1,5 @@
 # Licensed under a 3-clause BSD style license - see LICENSE.rst
-"""Utilities for reducing HTML pages into search records.
-"""
+"""Utilities for reducing HTML pages into search records."""
 
 from __future__ import annotations
 
@@ -145,9 +144,7 @@ def iter_sphinx_sections(
                 logger.debug("Could not get content from %s", content_element)
                 continue
 
-    yield Section(
-        content="\n\n".join(text_elements), headings=current_headers, url=url
-    )
+    yield Section(content="\n\n".join(text_elements), headings=current_headers, url=url)
 
 
 def iter_nbcollection_sections(
@@ -204,9 +201,7 @@ def iter_nbcollection_sections(
             if "id" in content_element.attrib.keys():
                 header_id = content_element.attrib["id"]
             if header_callback:
-                header_content = header_callback(
-                    content_element.text_content()
-                )
+                header_content = header_callback(content_element.text_content())
             else:
                 header_content = content_element.text_content()
             logger.debug("Got header %s\n", header_content)
diff --git a/astropylibrarian/resources.py b/astropylibrarian/resources.py
@@ -39,9 +39,7 @@ def parse(self) -> lxml.html.HtmlElement:
         return lxml.html.document_fromstring(self.html)
 
     @classmethod
-    def from_path(
-        cls: Type[HtmlPageType], *, path: Path, url: str
-    ) -> HtmlPageType:
+    def from_path(cls: Type[HtmlPageType], *, path: Path, url: str) -> HtmlPageType:
         """Open an HtmlPage from a local file.
 
         Parameters
diff --git a/astropylibrarian/workflows/download.py b/astropylibrarian/workflows/download.py
@@ -1,6 +1,5 @@
 # Licensed under a 3-clause BSD style license - see LICENSE.rst
-"""Workflow for downloading an HTML page.
-"""
+"""Workflow for downloading an HTML page."""
 
 __all__ = ["download_html"]
 
@@ -12,9 +11,7 @@
     import aiohttp
 
 
-async def download_html(
-    *, url: str, http_client: "aiohttp.ClientSession"
-) -> HtmlPage:
+async def download_html(*, url: str, http_client: "aiohttp.ClientSession") -> HtmlPage:
     """Asynchronously download an HTML page (awaitable function).
 
     Parameters
diff --git a/astropylibrarian/workflows/expirerecords.py b/astropylibrarian/workflows/expirerecords.py
@@ -38,7 +38,7 @@ async def expire_old_records(
     old_object_ids: List[str] = []
     # for r in await algolia_index.browse_objects(obj).hits:
     records = await algolia_index.browse_objects(obj).hits
-    for r in records:    
+    for r in records:
         # Double check that we're deleting the right things.
         if r.root_url != root_url:
             logger.warning("root_url does not match: %s", r.root_url)
@@ -58,4 +58,4 @@ async def expire_old_records(
 
     logger.info("Finished deleting expired objects for %s", root_url)
 
-    return old_object_ids
+    return old_object_ids
diff --git a/astropylibrarian/workflows/indexjupyterbook.py b/astropylibrarian/workflows/indexjupyterbook.py
@@ -87,9 +87,7 @@ async def index_jupyterbook(
         _objectids = await result
         object_ids.extend(_objectids)
 
-    logger.info(
-        "Finished indexing JupyterBook %s (%d records)", url, len(object_ids)
-    )
+    logger.info("Finished indexing JupyterBook %s (%d records)", url, len(object_ids))
 
     if object_ids:
         await expire_old_records(
@@ -128,9 +126,7 @@ async def download_homepage(
         # Detect if the URL is a redirect to the true first content page
         redirect_url = detect_redirect(index_page)
         if isinstance(redirect_url, str):
-            return await download_html(
-                url=redirect_url, http_client=http_client
-            )
+            return await download_html(url=redirect_url, http_client=http_client)
     except Exception:
         pass
 
diff --git a/astropylibrarian/workflows/indexjupyterbookpage.py b/astropylibrarian/workflows/indexjupyterbookpage.py
@@ -39,9 +39,7 @@ async def index_jupyterbook_page(
             site_metadata=jupyterbook_metadata, index_epoch=index_epoch
         )
     ]
-    logger.debug(
-        "Indexing %d records for Jupyter Book page at %s", len(records), url
-    )
+    logger.debug("Indexing %d records for Jupyter Book page at %s", len(records), url)
     response = await algolia_index.save_objects(objects=records)
     # logger.debug("Algolia save_objects: %s", response.raw_responses)
 
diff --git a/pyproject.toml b/pyproject.toml
@@ -88,4 +88,4 @@ exclude = '''
 include_trailing_comma = true
 multi_line_output = 3
 known_first_party = ["astropylibrarian", "tests"]
-skip = ["docs/conf.py"]
+skip = ["docs/conf.py"]
diff --git a/tests/data/ccd-guide/notebooks/00-00-Preface.html b/tests/data/ccd-guide/notebooks/00-00-Preface.html
@@ -608,4 +608,4 @@ <h3>List of data files<a class="headerlink" href="#list-of-data-files" title="Pe
 
 
   </body>
-</html>
+</html>
diff --git a/tests/data/ccd-guide/notebooks/01-05-Calibration-overview.html b/tests/data/ccd-guide/notebooks/01-05-Calibration-overview.html
@@ -754,4 +754,4 @@ <h3><span class="section-number">1.4.2.6. </span>Reducing the image increases th
 
 
   </body>
-</html>
+</html>
diff --git a/tests/data/nbcollection-tutorials/2-Coordinates-Transforms.html b/tests/data/nbcollection-tutorials/2-Coordinates-Transforms.html
diff --git a/tests/data/tutorials/Coordinates-Transform.html b/tests/data/tutorials/Coordinates-Transform.html
diff --git a/tests/data/tutorials/color-excess-v2.html b/tests/data/tutorials/color-excess-v2.html
diff --git a/tests/data/tutorials/color-excess.html b/tests/data/tutorials/color-excess.html
diff --git a/tests/test_algolia_records.py b/tests/test_algolia_records.py
diff --git a/tests/test_reducers_jupyterbook.py b/tests/test_reducers_jupyterbook.py
diff --git a/tests/test_reducers_tutorial.py b/tests/test_reducers_tutorial.py
diff --git a/tests/test_reducers_utils.py b/tests/test_reducers_utils.py
diff --git a/tests/test_workflows_indexjupyterbook.py b/tests/test_workflows_indexjupyterbook.py
