Move docs to docstrings and generate documentation with sphinx-autodoc

doc/source/api.rst

@@ -1,55 +1,5 @@
 API Reference
 =============
 
-.. py:function:: frame_to_hyper(df: pd.DataFrame, database: Union[str, pathlib.Path], *, table: Union[str, tableauhyperapi.Name, tableauhyperapi.TableName], table_mode: str = "w", not_null_columns: Optional[Iterable[str]] = None, json_columns: Optional[Iterable[str]] = None, geo_columns: Optional[Iterable[str]] = None) -> None:
-
-   Convert a DataFrame to a .hyper extract.
-
-   :param df: Data to be written out.
-   :param database: Name / location of the Hyper file to write to.
-   :param table: Table to write to.
-   :param table_mode: The mode to open the table with. Default is "w" for write, which truncates the file before writing. Another option is "a", which will append data to the file if it already contains information.
-   :param not_null_columns: Columns which should be considered "NOT NULL" in the target Hyper database. By default, all columns are considered nullable
-   :param json_columns: Columns to be written as a JSON data type
-   :param geo_columns: Columns to be written as a GEOGRAPHY data type
-   :param process_params: Parameters to pass to the Hyper Process constructor.
-
-.. py:function:: frame_from_hyper(source: Union[str, pathlib.Path, tab_api.Connection], *, table: Union[str, tableauhyperapi.Name, tableauhyperapi.TableName], return_type: Literal["pandas", "pyarrow", "polars"] = "pandas")
-
-   Extracts a DataFrame from a .hyper extract.
-
-   :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
-   :param table: Table to read.
-   :param return_type: The type of DataFrame to be returned
-   :param process_params: Parameters to pass to the Hyper Process constructor.
-
-
-.. py:function:: frames_to_hyper(dict_of_frames: Dict[Union[str, tableauhyperapi.Name, tableauhyperapi.TableName], pd.DataFrame], database: Union[str, pathlib.Path], *, table_mode: str = "w", not_null_columns: Optional[Iterable[str]] = None, json_columns: Optional[Iterable[str]] = None, geo_columns: Optional[Iterable[str]] = None,) -> None:
-
-   Writes multiple DataFrames to a .hyper extract.
-
-   :param dict_of_frames: A dictionary whose keys are valid table identifiers and values are dataframes
-   :param database: Name / location of the Hyper file to write to.
-   :param table_mode: The mode to open the table with. Default is "w" for write, which truncates the file before writing. Another option is "a", which will append data to the file if it already contains information.
-   :param not_null_columns: Columns which should be considered "NOT NULL" in the target Hyper database. By default, all columns are considered nullable
-   :param json_columns: Columns to be written as a JSON data type
-   :param geo_columns: Columns to be written as a GEOGRAPHY data type
-   :param process_params: Parameters to pass to the Hyper Process constructor.
-
-.. py:function:: frames_from_hyper(source: Union[str, pathlib.Path, tab_api.Connection], *, return_type: Literal["pandas", "pyarrow", "polars"] = "pandas") -> dict:
-
-   Extracts tables from a .hyper extract.
-
-   :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
-   :param return_type: The type of DataFrame to be returned
-   :param process_params: Parameters to pass to the Hyper Process constructor.
-
-
-.. py:function:: frame_from_hyper_query(source: Union[str, pathlib.Path, tab_api.Connection], query: str, *, return_type: Literal["pandas", "polars", "pyarrow"] = "pandas",)
-
-   Executes a SQL query and returns the result as a pandas dataframe
-
-   :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
-   :param query: SQL query to execute.
-   :param return_type: The type of DataFrame to be returned
-   :param process_params: Parameters to pass to the Hyper Process constructor.
+.. automodule:: pantab
+   :members:

doc/source/conf.py

@@ -1,5 +1,10 @@
+import pathlib
+import sys
 from typing import List
 
+srcdir = pathlib.Path(__file__).resolve().parent.parent.parent / "src"
+sys.path.insert(0, str(srcdir))
+
 # -- Project information -----------------------------------------------------
 
 project = "pantab"
@@ -13,6 +18,8 @@
 extensions = [
     "sphinx_rtd_theme",
     "sphinxext.opengraph",
+    "sphinx.ext.autodoc",
+    "sphinx_autodoc_typehints",
 ]
 
 templates_path = ["_templates"]
@@ -35,3 +42,10 @@
 ogp_site_url = "https://pantab.readthedocs.io/"
 ogp_use_first_image = False
 ogp_image = "https://pantab.readthedocs.io/en/latest/_static/pantab_logo.png"
+
+# -- Options for autodoc -----------------------------------------------------
+
+autodoc_mock_imports = ["pantab.libpantab"]
+autodoc_typehints = "none"
+typehints_use_signature = True
+typehints_use_signature_return = True

environment.yml

@@ -15,9 +15,9 @@ dependencies:
   - pyarrow
   - python
   - pytest
-  - pytest_xdist
   - scikit-build-core
   - sphinx
+  - sphinx-autodoc-typehints
   - pre-commit
   - sphinx_rtd_theme
   - sphinxext-opengraph

src/pantab/_reader.py

@@ -14,7 +14,14 @@ def frame_from_hyper_query(
     return_type: Literal["pandas", "polars", "pyarrow"] = "pandas",
     process_params: Optional[dict[str, str]] = None,
 ):
-    """See api.rst for documentation."""
+    """
+    Executes a SQL query and returns the result as a pandas dataframe
+
+    :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
+    :param query: SQL query to execute.
+    :param return_type: The type of DataFrame to be returned
+    :param process_params: Parameters to pass to the Hyper Process constructor.
+    """
     if process_params is None:
         process_params = {}
 
@@ -44,7 +51,14 @@ def frame_from_hyper(
     return_type: Literal["pandas", "polars", "pyarrow"] = "pandas",
     process_params: Optional[dict[str, str]] = None,
 ):
-    """See api.rst for documentation"""
+    """
+    Extracts a DataFrame from a .hyper extract.
+
+    :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
+    :param table: Table to read.
+    :param return_type: The type of DataFrame to be returned
+    :param process_params: Parameters to pass to the Hyper Process constructor.
+    """
     if isinstance(table, (pt_types.TableauName, pt_types.TableauTableName)):
         tbl = str(table)
     elif isinstance(table, tuple):
@@ -65,7 +79,13 @@ def frames_from_hyper(
     return_type: Literal["pandas", "polars", "pyarrow"] = "pandas",
     process_params: Optional[dict[str, str]] = None,
 ):
-    """See api.rst for documentation."""
+    """
+    Extracts tables from a .hyper extract.
+
+    :param source: Name / location of the Hyper file to be read  or Hyper-API connection.
+    :param return_type: The type of DataFrame to be returned
+    :param process_params: Parameters to pass to the Hyper Process constructor.
+    """
     result = {}
 
     table_names = libpantab.get_table_names(str(source))

src/pantab/_writer.py

@@ -57,7 +57,18 @@ def frame_to_hyper(
     geo_columns: Optional[set[str]] = None,
     process_params: Optional[dict[str, str]] = None,
 ) -> None:
-    """See api.rst for documentation"""
+    """
+    Convert a DataFrame to a .hyper extract.
+
+    :param df: Data to be written out.
+    :param database: Name / location of the Hyper file to write to.
+    :param table: Table to write to.
+    :param table_mode: The mode to open the table with. Default is "w" for write, which truncates the file before writing. Another option is "a", which will append data to the file if it already contains information.
+    :param not_null_columns: Columns which should be considered "NOT NULL" in the target Hyper database. By default, all columns are considered nullable
+    :param json_columns: Columns to be written as a JSON data type
+    :param geo_columns: Columns to be written as a GEOGRAPHY data type
+    :param process_params: Parameters to pass to the Hyper Process constructor.
+    """
     frames_to_hyper(
         {table: df},
         database,
@@ -79,7 +90,17 @@ def frames_to_hyper(
     geo_columns: Optional[set[str]] = None,
     process_params: Optional[dict[str, str]] = None,
 ) -> None:
-    """See api.rst for documentation."""
+    """
+    Writes multiple DataFrames to a .hyper extract.
+
+    :param dict_of_frames: A dictionary whose keys are valid table identifiers and values are dataframes
+    :param database: Name / location of the Hyper file to write to.
+    :param table_mode: The mode to open the table with. Default is "w" for write, which truncates the file before writing. Another option is "a", which will append data to the file if it already contains information.
+    :param not_null_columns: Columns which should be considered "NOT NULL" in the target Hyper database. By default, all columns are considered nullable
+    :param json_columns: Columns to be written as a JSON data type
+    :param geo_columns: Columns to be written as a GEOGRAPHY data type
+    :param process_params: Parameters to pass to the Hyper Process constructor.
+    """
     _validate_table_mode(table_mode)
 
     if not_null_columns is None: