From 184e1e01a2c50f0e8cbb8e14d649c225dbf99ed3 Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 31 Mar 2026 12:41:37 -0500
Subject: [PATCH 1/6] codex-authored fix for type checking

---
 MANIFEST.in            |   1 +
 cfa/dataops/catalog.py | 109 ++++++++++++++++++++---------------------
 cfa/dataops/py.typed   |   1 +
 pyproject.toml         |   3 ++
 4 files changed, 59 insertions(+), 55 deletions(-)
 create mode 100644 cfa/dataops/py.typed

diff --git a/MANIFEST.in b/MANIFEST.in
index a369d05..5263ae4 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,3 +1,4 @@
 recursive-include cfa/dataops/reporting/reports
 recursive-include cfa/dataops/etl/transform_templates
 include cfa/dataops/config.ini
+include cfa/dataops/py.typed
diff --git a/cfa/dataops/catalog.py b/cfa/dataops/catalog.py
index 39e3c73..82d6387 100644
--- a/cfa/dataops/catalog.py
+++ b/cfa/dataops/catalog.py
@@ -7,7 +7,7 @@
 from importlib import import_module
 from io import BytesIO
 from types import SimpleNamespace
-from typing import Any, List, Sequence
+from typing import TYPE_CHECKING, Any, List, Literal, Sequence, overload
 
 import pandas as pd
 import polars as pl
@@ -51,9 +51,7 @@ def get_all_catalogs() -> list:
     catalog_nspace = _config.get("DEFAULT", "catalog_namespaces")
     try:
         catalog_pkg = import_module(catalog_nspace)
-        for module_finder, modname, ispkg in pkgutil.iter_modules(
-            catalog_pkg.__path__
-        ):
+        for module_finder, modname, ispkg in pkgutil.iter_modules(catalog_pkg.__path__):
             if ispkg:
                 catalogs.append((catalog_nspace, modname, module_finder.path))
     except ModuleNotFoundError:
@@ -74,9 +72,7 @@ def get_all_catalogs() -> list:
     report_mod = import_module(f"{cns}.{cat_name}.reports")
     all_dataset_ns_map.update(dataset_mod.dataset_ns_map)
     all_reports_ns_map.update(report_mod.report_ns_map)
-    with open(
-        os.path.join(cat_path, cat_name, "catalog_defaults.toml"), "rb"
-    ) as f:
+    with open(os.path.join(cat_path, cat_name, "catalog_defaults.toml"), "rb") as f:
         defaults = tomli.load(f)
     for k in dataset_mod.dataset_ns_map.keys():
         all_defaults.update({k: defaults})
@@ -85,11 +81,40 @@ def get_all_catalogs() -> list:
 report_namespaces = get_dataset_dot_path(all_reports_ns_map)
 
 
+class CatalogNamespace(SimpleNamespace):
+    """Recursive namespace wrapper for statically-typed catalog access.
+
+    Runtime instances still behave like ``SimpleNamespace`` objects, but the
+    declared attributes let editors resolve endpoint methods on dynamic access
+    chains such as ``datacat.public.team.dataset.load``.
+    """
+
+    if TYPE_CHECKING:
+        load: "BlobEndpoint"
+        extract: "BlobEndpoint"
+        data: "BlobEndpoint"
+        _ledger_endpoint: "BlobEndpoint"
+        config: dict[str, Any]
+        __namespace_list__: list[str]
+
+    def __getattr__(self, name: str) -> "CatalogNamespace":
+        raise AttributeError(
+            f"{type(self).__name__!s} object has no attribute {name!r}"
+        )
+
+
 class DatasetEndpoint:
     """The DatasetEndpoint class for including in the datacat namespace.
     This ends the namespace branching at a config file and creates all the
     blob endpoints for each 'stage' of the config (e.g., extract, load, stage_01)."""
 
+    if TYPE_CHECKING:
+        config: dict[str, Any]
+        load: "BlobEndpoint"
+        extract: "BlobEndpoint"
+        data: "BlobEndpoint"
+        _ledger_endpoint: "BlobEndpoint"
+
     def __init__(self, config_path: str, defaults: dict, ns: str):
         """Basic functionality to interact with datasets to be included
         via the datasets configs.
@@ -109,13 +134,9 @@ def __init__(self, config_path: str, defaults: dict, ns: str):
                 account = v.get("account", "")
                 container = v.get("container", "")
                 if account == "":
-                    self.config[k]["account"] = self.defaults["storage"][
-                        "account"
-                    ]
+                    self.config[k]["account"] = self.defaults["storage"]["account"]
                 if container == "":
-                    self.config[k]["container"] = self.defaults["storage"][
-                        "container"
-                    ]
+                    self.config[k]["container"] = self.defaults["storage"]["container"]
         self.validate_dataset_config(config_path)
         self._ledger_location = {
             "account": self.defaults["storage"]["account"],
@@ -142,8 +163,7 @@ def validate_dataset_config(self, config_path) -> None:
             config_models = {}
             for c_key, c_value in self.config.items():
                 if (
-                    c_key.startswith("stage_")
-                    or c_key in ["load", "extract", "data"]
+                    c_key.startswith("stage_") or c_key in ["load", "extract", "data"]
                 ) and c_value is not None:
                     config_models[c_key] = StorageEndpointValidation(**c_value)
                 elif c_key == "properties":
@@ -205,9 +225,7 @@ def write_blob(
             append (bool, optional): whether to append to existing file (only for single file writes).
         """
         if auto_version and not append:
-            path_after_prefix = (
-                f"{get_timestamp()}/{path_after_prefix.lstrip('/')}"
-            )
+            path_after_prefix = f"{get_timestamp()}/{path_after_prefix.lstrip('/')}"
         path_after_prefix = path_after_prefix.lstrip("/")
         full_path = f"{self.prefix}/{path_after_prefix}"
         if isinstance(file_buffer, bytes):
@@ -229,9 +247,7 @@ def write_blob(
         self.ledger_entry(action="write")
         # print(f"file written to: {full_path}")
 
-    def read_blobs(
-        self, version: str = "latest", newest: bool = True
-    ) -> List[bytes]:
+    def read_blobs(self, version: str = "latest", newest: bool = True) -> List[bytes]:
         """Read a blob in as bytes so it can be loaded into a dataframe
 
         Args:
@@ -293,18 +309,16 @@ def get_file_ext(self, version: str = "latest") -> str:
         Returns:
             str: the file extension
         """
-        return self._get_version_blobs(version=version, print_version=False)[
-            0
-        ]["name"].split(".")[-1]
+        return self._get_version_blobs(version=version, print_version=False)[0][
+            "name"
+        ].split(".")[-1]
 
     def _get_version_blobs(
         self, version: str = "latest", newest=True, print_version=True
     ) -> list:
         if not self.is_ledger:
             available_versions = self.get_versions()
-            version = version_matcher(
-                version, available_versions, newest=newest
-            )
+            version = version_matcher(version, available_versions, newest=newest)
             if not version:
                 raise ValueError(
                     f"Version {version} not found in available versions: {available_versions}"
@@ -451,9 +465,7 @@ def get_dataframe(
             return df
         elif file_ext == "jsonl":
             if output in ["pandas", "pd"]:
-                df = pd.concat(
-                    [pd.read_json(blob, lines=True) for blob in blob_files]
-                )
+                df = pd.concat([pd.read_json(blob, lines=True) for blob in blob_files])
                 df.reset_index(inplace=True, drop=True)
             else:
                 df = pl.concat(
@@ -465,9 +477,7 @@ def get_dataframe(
             return df
         elif file_ext == "parquet" or file_ext == "parq":
             if output in ["pandas", "pd"]:
-                df = pd.concat(
-                    [pd.read_parquet(pq_file) for pq_file in blob_files]
-                )
+                df = pd.concat([pd.read_parquet(pq_file) for pq_file in blob_files])
                 df.reset_index(inplace=True, drop=True)
             else:
                 df = pl.concat(
@@ -525,9 +535,7 @@ def save_dataframe(
             raise ValueError(
                 f"File format {file_format} not supported. Use 'parquet', 'csv', 'json', or 'jsonl'."
             )
-        if file_format in ["json", "jsonl"] and path_after_prefix.endswith(
-            ".json"
-        ):
+        if file_format in ["json", "jsonl"] and path_after_prefix.endswith(".json"):
             path_after_prefix = path_after_prefix[:-5] + ".jsonl"
             print("Changing file extension to .jsonl for line-delimited JSON.")
         if isinstance(df, pd.DataFrame):
@@ -550,9 +558,7 @@ def save_dataframe(
                     auto_version=auto_version,
                 )
             elif file_format in ["json", "jsonl"]:
-                json_bytes = df.to_json(orient="records", lines=True).encode(
-                    "utf-8"
-                )
+                json_bytes = df.to_json(orient="records", lines=True).encode("utf-8")
                 self.write_blob(
                     file_buffer=json_bytes,
                     path_after_prefix=path_after_prefix
@@ -644,7 +650,7 @@ def save_dir_to_blob(
                 )
 
 
-def dict_to_sn(d: Any, defaults: dict = None, ns: str = "") -> SimpleNamespace:
+def dict_to_sn(d: Any, defaults: dict | None = None, ns: str = "") -> CatalogNamespace:
     """Simple recursive namespace construction
 
     Args:
@@ -653,9 +659,9 @@ def dict_to_sn(d: Any, defaults: dict = None, ns: str = "") -> SimpleNamespace:
         ns (str, optional): the current namespace path. Defaults to ''.
 
     Returns:
-        SimpleNamespace: namespace representation
+        CatalogNamespace: namespace representation
     """
-    x = SimpleNamespace()
+    x = CatalogNamespace()
     ns_prefix = f"{ns}." if ns != "" else ""
     _ = [
         setattr(
@@ -694,19 +700,15 @@ def dict_to_sn(d: Any, defaults: dict = None, ns: str = "") -> SimpleNamespace:
 rc = []
 for k in all_reports_ns_map.keys():
     rc.append(report_dict_to_sn({k: all_reports_ns_map[k]}))
-combined_reports_dict = {
-    key: value for ns in rc for key, value in vars(ns).items()
-}
+combined_reports_dict = {key: value for ns in rc for key, value in vars(ns).items()}
 
-datacat = SimpleNamespace(**combined_dict)
+datacat: CatalogNamespace = CatalogNamespace(**combined_dict)
 datacat.__setattr__("__namespace_list__", dataset_namespaces)
-reportcat = SimpleNamespace(**combined_reports_dict)
+reportcat: CatalogNamespace = CatalogNamespace(**combined_reports_dict)
 reportcat.__setattr__("__namespace_list__", report_namespaces)
 
 
-def _attach_schema_mock_functions(
-    datacat: SimpleNamespace, catalogs: list
-) -> None:
+def _attach_schema_mock_functions(datacat: SimpleNamespace, catalogs: list) -> None:
     """Recursively walk the datacat namespace and attach mock_data functions to
     the extract and load BlobEndpoints of each DatasetEndpoint, sourced from
     a schema module co-located with the dataset.
@@ -744,14 +746,11 @@ def _walk(ns: SimpleNamespace) -> None:
                     # strip cat_name prefix -> "stf.nhsn_hrd_prelim"
                     # then split into team ("stf") and dataset ("nhsn_hrd_prelim")
                     # so the schema lives at: datasets.stf.schemas.nhsn_hrd_prelim
-                    ns_within_datasets = val.__ns_str__.removeprefix(
-                        f"{cat_name}."
-                    )
+                    ns_within_datasets = val.__ns_str__.removeprefix(f"{cat_name}.")
                     ns_parts = ns_within_datasets.rsplit(".", 1)
                     team_path = ns_parts[0] if len(ns_parts) > 1 else ""
                     schema_mod_path = (
-                        f"{cns}.{cat_name}.datasets"
-                        f".{team_path}.schemas.{dataset_name}"
+                        f"{cns}.{cat_name}.datasets.{team_path}.schemas.{dataset_name}"
                         if team_path
                         else f"{cns}.{cat_name}.datasets.schemas.{dataset_name}"
                     )
diff --git a/cfa/dataops/py.typed b/cfa/dataops/py.typed
new file mode 100644
index 0000000..8b13789
--- /dev/null
+++ b/cfa/dataops/py.typed
@@ -0,0 +1 @@
+
diff --git a/pyproject.toml b/pyproject.toml
index cbe86b5..988a4ea 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -37,6 +37,9 @@ dependencies = [
 
 [tool.poetry]
 packages = [{ include = "cfa" }]
+include = [
+    { path = "cfa/dataops/py.typed", format = ["sdist", "wheel"] },
+]
 
 
 [tool.poetry.group.dev.dependencies]

From d5f5ed8d437fbf7c8a7fca1ae3285ffa94451cb6 Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 31 Mar 2026 12:57:28 -0500
Subject: [PATCH 2/6] ruff format

---
 cfa/dataops/catalog.py           | 69 +++++++++++++++++++++++---------
 cfa/dataops/reporting/catalog.py |  6 +--
 cfa/dataops/soda.py              |  6 +--
 tests/test_create_catalog.py     | 12 +++---
 4 files changed, 62 insertions(+), 31 deletions(-)

diff --git a/cfa/dataops/catalog.py b/cfa/dataops/catalog.py
index 82d6387..7478352 100644
--- a/cfa/dataops/catalog.py
+++ b/cfa/dataops/catalog.py
@@ -51,7 +51,9 @@ def get_all_catalogs() -> list:
     catalog_nspace = _config.get("DEFAULT", "catalog_namespaces")
     try:
         catalog_pkg = import_module(catalog_nspace)
-        for module_finder, modname, ispkg in pkgutil.iter_modules(catalog_pkg.__path__):
+        for module_finder, modname, ispkg in pkgutil.iter_modules(
+            catalog_pkg.__path__
+        ):
             if ispkg:
                 catalogs.append((catalog_nspace, modname, module_finder.path))
     except ModuleNotFoundError:
@@ -72,7 +74,9 @@ def get_all_catalogs() -> list:
     report_mod = import_module(f"{cns}.{cat_name}.reports")
     all_dataset_ns_map.update(dataset_mod.dataset_ns_map)
     all_reports_ns_map.update(report_mod.report_ns_map)
-    with open(os.path.join(cat_path, cat_name, "catalog_defaults.toml"), "rb") as f:
+    with open(
+        os.path.join(cat_path, cat_name, "catalog_defaults.toml"), "rb"
+    ) as f:
         defaults = tomli.load(f)
     for k in dataset_mod.dataset_ns_map.keys():
         all_defaults.update({k: defaults})
@@ -134,9 +138,13 @@ def __init__(self, config_path: str, defaults: dict, ns: str):
                 account = v.get("account", "")
                 container = v.get("container", "")
                 if account == "":
-                    self.config[k]["account"] = self.defaults["storage"]["account"]
+                    self.config[k]["account"] = self.defaults["storage"][
+                        "account"
+                    ]
                 if container == "":
-                    self.config[k]["container"] = self.defaults["storage"]["container"]
+                    self.config[k]["container"] = self.defaults["storage"][
+                        "container"
+                    ]
         self.validate_dataset_config(config_path)
         self._ledger_location = {
             "account": self.defaults["storage"]["account"],
@@ -163,7 +171,8 @@ def validate_dataset_config(self, config_path) -> None:
             config_models = {}
             for c_key, c_value in self.config.items():
                 if (
-                    c_key.startswith("stage_") or c_key in ["load", "extract", "data"]
+                    c_key.startswith("stage_")
+                    or c_key in ["load", "extract", "data"]
                 ) and c_value is not None:
                     config_models[c_key] = StorageEndpointValidation(**c_value)
                 elif c_key == "properties":
@@ -225,7 +234,9 @@ def write_blob(
             append (bool, optional): whether to append to existing file (only for single file writes).
         """
         if auto_version and not append:
-            path_after_prefix = f"{get_timestamp()}/{path_after_prefix.lstrip('/')}"
+            path_after_prefix = (
+                f"{get_timestamp()}/{path_after_prefix.lstrip('/')}"
+            )
         path_after_prefix = path_after_prefix.lstrip("/")
         full_path = f"{self.prefix}/{path_after_prefix}"
         if isinstance(file_buffer, bytes):
@@ -247,7 +258,9 @@ def write_blob(
         self.ledger_entry(action="write")
         # print(f"file written to: {full_path}")
 
-    def read_blobs(self, version: str = "latest", newest: bool = True) -> List[bytes]:
+    def read_blobs(
+        self, version: str = "latest", newest: bool = True
+    ) -> List[bytes]:
         """Read a blob in as bytes so it can be loaded into a dataframe
 
         Args:
@@ -309,16 +322,18 @@ def get_file_ext(self, version: str = "latest") -> str:
         Returns:
             str: the file extension
         """
-        return self._get_version_blobs(version=version, print_version=False)[0][
-            "name"
-        ].split(".")[-1]
+        return self._get_version_blobs(version=version, print_version=False)[
+            0
+        ]["name"].split(".")[-1]
 
     def _get_version_blobs(
         self, version: str = "latest", newest=True, print_version=True
     ) -> list:
         if not self.is_ledger:
             available_versions = self.get_versions()
-            version = version_matcher(version, available_versions, newest=newest)
+            version = version_matcher(
+                version, available_versions, newest=newest
+            )
             if not version:
                 raise ValueError(
                     f"Version {version} not found in available versions: {available_versions}"
@@ -465,7 +480,9 @@ def get_dataframe(
             return df
         elif file_ext == "jsonl":
             if output in ["pandas", "pd"]:
-                df = pd.concat([pd.read_json(blob, lines=True) for blob in blob_files])
+                df = pd.concat(
+                    [pd.read_json(blob, lines=True) for blob in blob_files]
+                )
                 df.reset_index(inplace=True, drop=True)
             else:
                 df = pl.concat(
@@ -477,7 +494,9 @@ def get_dataframe(
             return df
         elif file_ext == "parquet" or file_ext == "parq":
             if output in ["pandas", "pd"]:
-                df = pd.concat([pd.read_parquet(pq_file) for pq_file in blob_files])
+                df = pd.concat(
+                    [pd.read_parquet(pq_file) for pq_file in blob_files]
+                )
                 df.reset_index(inplace=True, drop=True)
             else:
                 df = pl.concat(
@@ -535,7 +554,9 @@ def save_dataframe(
             raise ValueError(
                 f"File format {file_format} not supported. Use 'parquet', 'csv', 'json', or 'jsonl'."
             )
-        if file_format in ["json", "jsonl"] and path_after_prefix.endswith(".json"):
+        if file_format in ["json", "jsonl"] and path_after_prefix.endswith(
+            ".json"
+        ):
             path_after_prefix = path_after_prefix[:-5] + ".jsonl"
             print("Changing file extension to .jsonl for line-delimited JSON.")
         if isinstance(df, pd.DataFrame):
@@ -558,7 +579,9 @@ def save_dataframe(
                     auto_version=auto_version,
                 )
             elif file_format in ["json", "jsonl"]:
-                json_bytes = df.to_json(orient="records", lines=True).encode("utf-8")
+                json_bytes = df.to_json(orient="records", lines=True).encode(
+                    "utf-8"
+                )
                 self.write_blob(
                     file_buffer=json_bytes,
                     path_after_prefix=path_after_prefix
@@ -650,7 +673,9 @@ def save_dir_to_blob(
                 )
 
 
-def dict_to_sn(d: Any, defaults: dict | None = None, ns: str = "") -> CatalogNamespace:
+def dict_to_sn(
+    d: Any, defaults: dict | None = None, ns: str = ""
+) -> CatalogNamespace:
     """Simple recursive namespace construction
 
     Args:
@@ -700,7 +725,9 @@ def dict_to_sn(d: Any, defaults: dict | None = None, ns: str = "") -> CatalogNam
 rc = []
 for k in all_reports_ns_map.keys():
     rc.append(report_dict_to_sn({k: all_reports_ns_map[k]}))
-combined_reports_dict = {key: value for ns in rc for key, value in vars(ns).items()}
+combined_reports_dict = {
+    key: value for ns in rc for key, value in vars(ns).items()
+}
 
 datacat: CatalogNamespace = CatalogNamespace(**combined_dict)
 datacat.__setattr__("__namespace_list__", dataset_namespaces)
@@ -708,7 +735,9 @@ def dict_to_sn(d: Any, defaults: dict | None = None, ns: str = "") -> CatalogNam
 reportcat.__setattr__("__namespace_list__", report_namespaces)
 
 
-def _attach_schema_mock_functions(datacat: SimpleNamespace, catalogs: list) -> None:
+def _attach_schema_mock_functions(
+    datacat: SimpleNamespace, catalogs: list
+) -> None:
     """Recursively walk the datacat namespace and attach mock_data functions to
     the extract and load BlobEndpoints of each DatasetEndpoint, sourced from
     a schema module co-located with the dataset.
@@ -746,7 +775,9 @@ def _walk(ns: SimpleNamespace) -> None:
                     # strip cat_name prefix -> "stf.nhsn_hrd_prelim"
                     # then split into team ("stf") and dataset ("nhsn_hrd_prelim")
                     # so the schema lives at: datasets.stf.schemas.nhsn_hrd_prelim
-                    ns_within_datasets = val.__ns_str__.removeprefix(f"{cat_name}.")
+                    ns_within_datasets = val.__ns_str__.removeprefix(
+                        f"{cat_name}."
+                    )
                     ns_parts = ns_within_datasets.rsplit(".", 1)
                     team_path = ns_parts[0] if len(ns_parts) > 1 else ""
                     schema_mod_path = (
diff --git a/cfa/dataops/reporting/catalog.py b/cfa/dataops/reporting/catalog.py
index c4c37d8..3bcd08d 100644
--- a/cfa/dataops/reporting/catalog.py
+++ b/cfa/dataops/reporting/catalog.py
@@ -123,9 +123,9 @@ def nb_to_html_file(
         Returns:
             None, saves the html content to a file.
         """
-        assert html_out_path.endswith(
-            ".html"
-        ), "Output path must end with .html"
+        assert html_out_path.endswith(".html"), (
+            "Output path must end with .html"
+        )
         html_content = self.nb_to_html_str(nb_title=nb_title, **kwargs)
         os.makedirs(os.path.dirname(html_out_path), exist_ok=True)
         with open(html_out_path, "w", encoding="utf-8") as f:
diff --git a/cfa/dataops/soda.py b/cfa/dataops/soda.py
index 7dd0cd5..a4159bc 100644
--- a/cfa/dataops/soda.py
+++ b/cfa/dataops/soda.py
@@ -121,9 +121,9 @@ def n_rows(self) -> int:
 
     def _get_records(self, start: int, end: int) -> list[dict]:
         assert end >= start
-        assert (
-            self.limit is None or end < self.limit
-        ), f"End index {end} is larger than limit {self.limit}."
+        assert self.limit is None or end < self.limit, (
+            f"End index {end} is larger than limit {self.limit}."
+        )
         n_rows = end - start + 1
 
         return self._get_request(
diff --git a/tests/test_create_catalog.py b/tests/test_create_catalog.py
index 236b800..ac5a751 100644
--- a/tests/test_create_catalog.py
+++ b/tests/test_create_catalog.py
@@ -192,9 +192,9 @@ def test_create_expanded_catalog(catalog_parent):
     ]
 
     for file_name in cfa_files:
-        assert catalog_location.join(file_name).check(
-            file=True
-        ), f"Missing CFA file: {file_name}"
+        assert catalog_location.join(file_name).check(file=True), (
+            f"Missing CFA file: {file_name}"
+        )
 
 
 def test_unique_name_sanitization(catalog_parent):
@@ -285,9 +285,9 @@ def test_datasets_directory_structure(catalog_parent):
     ]
 
     for example_file in example_files:
-        assert datasets_path.join(example_file).check(
-            file=True
-        ), f"Missing example file: {example_file}"
+        assert datasets_path.join(example_file).check(file=True), (
+            f"Missing example file: {example_file}"
+        )
 
 
 def test_reports_directory_structure(catalog_parent):

From cdd4a1d525c342a3456d42c6b2b6f456ce6b8de9 Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 31 Mar 2026 13:06:51 -0500
Subject: [PATCH 3/6] pre-commit

---
 cfa/dataops/py.typed             |  1 -
 cfa/dataops/reporting/catalog.py |  6 +++---
 cfa/dataops/soda.py              |  6 +++---
 tests/test_create_catalog.py     | 12 ++++++------
 4 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/cfa/dataops/py.typed b/cfa/dataops/py.typed
index 8b13789..e69de29 100644
--- a/cfa/dataops/py.typed
+++ b/cfa/dataops/py.typed
@@ -1 +0,0 @@
-
diff --git a/cfa/dataops/reporting/catalog.py b/cfa/dataops/reporting/catalog.py
index 3bcd08d..c4c37d8 100644
--- a/cfa/dataops/reporting/catalog.py
+++ b/cfa/dataops/reporting/catalog.py
@@ -123,9 +123,9 @@ def nb_to_html_file(
         Returns:
             None, saves the html content to a file.
         """
-        assert html_out_path.endswith(".html"), (
-            "Output path must end with .html"
-        )
+        assert html_out_path.endswith(
+            ".html"
+        ), "Output path must end with .html"
         html_content = self.nb_to_html_str(nb_title=nb_title, **kwargs)
         os.makedirs(os.path.dirname(html_out_path), exist_ok=True)
         with open(html_out_path, "w", encoding="utf-8") as f:
diff --git a/cfa/dataops/soda.py b/cfa/dataops/soda.py
index a4159bc..7dd0cd5 100644
--- a/cfa/dataops/soda.py
+++ b/cfa/dataops/soda.py
@@ -121,9 +121,9 @@ def n_rows(self) -> int:
 
     def _get_records(self, start: int, end: int) -> list[dict]:
         assert end >= start
-        assert self.limit is None or end < self.limit, (
-            f"End index {end} is larger than limit {self.limit}."
-        )
+        assert (
+            self.limit is None or end < self.limit
+        ), f"End index {end} is larger than limit {self.limit}."
         n_rows = end - start + 1
 
         return self._get_request(
diff --git a/tests/test_create_catalog.py b/tests/test_create_catalog.py
index ac5a751..236b800 100644
--- a/tests/test_create_catalog.py
+++ b/tests/test_create_catalog.py
@@ -192,9 +192,9 @@ def test_create_expanded_catalog(catalog_parent):
     ]
 
     for file_name in cfa_files:
-        assert catalog_location.join(file_name).check(file=True), (
-            f"Missing CFA file: {file_name}"
-        )
+        assert catalog_location.join(file_name).check(
+            file=True
+        ), f"Missing CFA file: {file_name}"
 
 
 def test_unique_name_sanitization(catalog_parent):
@@ -285,9 +285,9 @@ def test_datasets_directory_structure(catalog_parent):
     ]
 
     for example_file in example_files:
-        assert datasets_path.join(example_file).check(file=True), (
-            f"Missing example file: {example_file}"
-        )
+        assert datasets_path.join(example_file).check(
+            file=True
+        ), f"Missing example file: {example_file}"
 
 
 def test_reports_directory_structure(catalog_parent):

From 6f8f62a79afff94d849856514a9e1399326d0d1a Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 31 Mar 2026 13:12:55 -0500
Subject: [PATCH 4/6] pre-commit

---
 cfa/dataops/catalog.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cfa/dataops/catalog.py b/cfa/dataops/catalog.py
index 7478352..c0c9527 100644
--- a/cfa/dataops/catalog.py
+++ b/cfa/dataops/catalog.py
@@ -7,7 +7,7 @@
 from importlib import import_module
 from io import BytesIO
 from types import SimpleNamespace
-from typing import TYPE_CHECKING, Any, List, Literal, Sequence, overload
+from typing import TYPE_CHECKING, Any, List, Sequence
 
 import pandas as pd
 import polars as pl

From a691b63fb0ad1c22cca8c81890f6b659ce46f577 Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 21 Apr 2026 09:48:56 -0500
Subject: [PATCH 5/6] import literal

---
 cfa/dataops/catalog.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cfa/dataops/catalog.py b/cfa/dataops/catalog.py
index 7e9534c..54b8fa6 100644
--- a/cfa/dataops/catalog.py
+++ b/cfa/dataops/catalog.py
@@ -9,7 +9,7 @@
 from pathlib import PurePosixPath
 from types import SimpleNamespace
 
-from typing import TYPE_CHECKING, Any, List, Sequence, overload
+from typing import TYPE_CHECKING, Any, List, Sequence, overload, Literal
 
 import pandas as pd
 import polars as pl

From 9332f607296e249ffbafc0293ae68e77a0f48bb6 Mon Sep 17 00:00:00 2001
From: Damon Bayer <xum8@cdc.gov>
Date: Tue, 28 Apr 2026 10:29:00 -0500
Subject: [PATCH 6/6] Update catalog.py

---
 cfa/dataops/catalog.py | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/cfa/dataops/catalog.py b/cfa/dataops/catalog.py
index 464e4aa..1485cdd 100644
--- a/cfa/dataops/catalog.py
+++ b/cfa/dataops/catalog.py
@@ -9,8 +9,7 @@
 from io import BytesIO
 from pathlib import PurePosixPath
 from types import SimpleNamespace
-
-from typing import TYPE_CHECKING, Any, List, Sequence, overload, Literal
+from typing import TYPE_CHECKING, Any, Literal, overload
 
 import pandas as pd
 import polars as pl
@@ -715,9 +714,7 @@ def save_dir_to_blob(
                 )
 
 
-def dict_to_sn(
-    d: Any, defaults: dict | None = None, ns: str = ""
-) -> CatalogNamespace:
+def dict_to_sn(d: Any, defaults: dict | None = None, ns: str = "") -> CatalogNamespace:
     """Simple recursive namespace construction
 
     Args: