sphinx.ext.napoleon – Support for NumPy and Google style docstrings

Module author: Rob Ruana

Added in version 1.3.

Overview

Are you tired of writing docstrings that look like this:

:param path: The path of the file to wrap
:type path: str
:param field_storage: The :class:`FileStorage` instance to wrap
:type field_storage: FileStorage
:param temporary: Whether or not to delete the file when the File
 instance is destructed
:type temporary: bool
:returns: A buffered writable file descriptor
:rtype: BufferedFileStorage

reStructuredText is great, but it creates visually dense, hard to read docstrings. Compare the jumble above to the same thing rewritten according to the Google Python Style Guide:

Args:
 path (str): The path of the file to wrap
 field_storage (FileStorage): The :class:`FileStorage` instance to wrap
 temporary (bool): Whether or not to delete the file when the File
 instance is destructed
Returns:
 BufferedFileStorage: A buffered writable file descriptor

Much more legible, no?

Napoleon is a extension that enables Sphinx to parse both NumPy and Google style docstrings - the style recommended by Khan Academy.

Napoleon is a pre-processor that parses NumPy and Google style docstrings and converts them to reStructuredText before Sphinx attempts to parse them. This happens in an intermediate step while Sphinx is processing the documentation, so it doesn’t modify any of the docstrings in your actual source code files.

Getting Started

  1. After setting up Sphinx to build your docs, enable napoleon in the Sphinx conf.py file:

    # conf.py
# Add napoleon to the extensions list
extensions = ['sphinx.ext.napoleon']

  2. Use sphinx-apidoc to build your API documentation:

    $ sphinx-apidoc-f-odocs/sourceprojectdir

Docstrings

Napoleon interprets every docstring that autodoc can find, including docstrings on: modules, classes, attributes, methods, functions, and variables. Inside each docstring, specially formatted Sections are parsed and converted to reStructuredText.

All standard reStructuredText formatting still works as expected.

Docstring Sections

All of the following section headers are supported:

  • Args (alias of Parameters)

  • Arguments (alias of Parameters)

  • Attention

  • Attributes

  • Caution

  • Danger

  • Error

  • Example

  • Examples

  • Hint

  • Important

  • Keyword Args (alias of Keyword Arguments)

  • Keyword Arguments

  • Methods

  • Note

  • Notes

  • Other Parameters

  • Parameters

  • Return (alias of Returns)

  • Returns

  • Raise (alias of Raises)

  • Raises

  • References

  • See Also

  • Tip

  • Todo

  • Warning

  • Warnings (alias of Warning)

  • Warn (alias of Warns)

  • Warns

  • Yield (alias of Yields)

  • Yields

Google vs NumPy

Napoleon supports two styles of docstrings: Google and NumPy. The main difference between the two styles is that Google uses indentation to separate sections, whereas NumPy uses underlines.

Google style:

deffunc(arg1, arg2):
"""Summary line.
 Extended description of function.
 Args:
 arg1 (int): Description of arg1
 arg2 (str): Description of arg2
 Returns:
 bool: Description of return value
 """
 return True

NumPy style:

deffunc(arg1, arg2):
"""Summary line.
 Extended description of function.
 Parameters
 ----------
 arg1 : int
 Description of arg1
 arg2 : str
 Description of arg2
 Returns
 -------
 bool
 Description of return value
 """
 return True

NumPy style tends to require more vertical space, whereas Google style tends to use more horizontal space. Google style tends to be easier to read for short and simple docstrings, whereas NumPy style tends be easier to read for long and in-depth docstrings.

The choice between styles is largely aesthetic, but the two styles should not be mixed. Choose one style for your project and be consistent with it.

Type Annotations

PEP 484 introduced a standard way to express types in Python code. This is an alternative to expressing types directly in docstrings. One benefit of expressing types according to PEP 484 is that type checkers and IDEs can take advantage of them for static code analysis. PEP 484 was then extended by PEP 526 which introduced a similar way to annotate variables (and attributes).

Google style with type annotations:

deffunc(arg1: int, arg2: str) -> bool:
"""Summary line.
 Extended description of function.
 Args:
 arg1: Description of arg1
 arg2: Description of arg2
 Returns:
 Description of return value
 """
 return True
classClass:
"""Summary line.
 Extended description of class
 Attributes:
 attr1: Description of attr1
 attr2: Description of attr2
 """
 attr1: int
 attr2: str

Google style with types in docstrings:

deffunc(arg1, arg2):
"""Summary line.
 Extended description of function.
 Args:
 arg1 (int): Description of arg1
 arg2 (str): Description of arg2
 Returns:
 bool: Description of return value
 """
 return True
classClass:
"""Summary line.
 Extended description of class
 Attributes:
 attr1 (int): Description of attr1
 attr2 (str): Description of attr2
 """

Configuration

Listed below are all the settings used by napoleon and their default values. These settings can be changed in the Sphinx conf.py file. Make sure that "sphinx.ext.napoleon" is enabled in conf.py:

# conf.py
# Add any Sphinx extension module names here, as strings
extensions = ['sphinx.ext.napoleon']
# Napoleon settings
napoleon_google_docstring = True
napoleon_numpy_docstring = True
napoleon_include_init_with_doc = False
napoleon_include_private_with_doc = False
napoleon_include_special_with_doc = True
napoleon_use_admonition_for_examples = False
napoleon_use_admonition_for_notes = False
napoleon_use_admonition_for_references = False
napoleon_use_ivar = False
napoleon_use_param = True
napoleon_use_rtype = True
napoleon_preprocess_types = False
napoleon_type_aliases = None
napoleon_attr_annotations = True
napoleon_google_docstring
Type:
bool
Default:
True

True to parse Google style docstrings. False to disable support for Google style docstrings.

napoleon_numpy_docstring
Type:
bool
Default:
True

True to parse NumPy style docstrings. False to disable support for NumPy style docstrings.

napoleon_include_init_with_doc
Type:
bool
Default:
False

True to list __init___ docstrings separately from the class docstring. False to fall back to Sphinx’s default behavior, which considers the __init___ docstring as part of the class documentation.

If True:

def__init__(self):
"""
 This will be included in the docs because it has a docstring
 """
def__init__(self):
 # This will NOT be included in the docs
napoleon_include_private_with_doc
Type:
bool
Default:
False

True to include private members (like _membername) with docstrings in the documentation. False to fall back to Sphinx’s default behavior.

If True:

def_included(self):
"""
 This will be included in the docs because it has a docstring
 """
 pass
def_skipped(self):
 # This will NOT be included in the docs
 pass
napoleon_include_special_with_doc
Type:
bool
Default:
True

True to include special members (like __membername__) with docstrings in the documentation. False to fall back to Sphinx’s default behavior.

If True:

def__str__(self):
"""
 This will be included in the docs because it has a docstring
 """
 return unicode(self).encode('utf-8')
def__unicode__(self):
 # This will NOT be included in the docs
 return unicode(self.__class__.__name__)
napoleon_use_admonition_for_examples
Type:
bool
Default:
False

True to use the .. admonition:: directive for the Example and Examples sections. False to use the .. rubric:: directive instead. One may look better than the other depending on what HTML theme is used.

This NumPy style snippet will be converted as follows:

Example
-------
This is just a quick example

If True:

.. admonition:: Example
 This is just a quick example

If False:

.. rubric:: Example
This is just a quick example
napoleon_use_admonition_for_notes
Type:
bool
Default:
False

True to use the .. admonition:: directive for Notes sections. False to use the .. rubric:: directive instead.

Note

The singular Note section will always be converted to a .. note:: directive.

napoleon_use_admonition_for_references
Type:
bool
Default:
False

True to use the .. admonition:: directive for References sections. False to use the .. rubric:: directive instead.

napoleon_use_ivar
Type:
bool
Default:
False

True to use the :ivar: role for instance variables. False to use the .. attribute:: directive instead.

This NumPy style snippet will be converted as follows:

Attributes
----------
attr1 : int
 Description of `attr1`

If True:

:ivar attr1: Description of `attr1`
:vartype attr1: int

If False:

.. attribute:: attr1
 Description of `attr1`
 :type: int
napoleon_use_param
Type:
bool
Default:
True

True to use a :param: role for each function parameter. False to use a single :parameters: role for all the parameters.

This NumPy style snippet will be converted as follows:

Parameters
----------
arg1 : str
 Description of `arg1`
arg2 : int, optional
 Description of `arg2`, defaults to 0

If True:

:param arg1: Description of `arg1`
:type arg1: str
:param arg2: Description of `arg2`, defaults to 0
:type arg2: :class:`int`, *optional*

If False:

:parameters: * **arg1** (*str*) --
 Description of `arg1`
 * **arg2** (*int, optional*) --
 Description of `arg2`, defaults to 0
napoleon_use_keyword
Type:
bool
Default:
True

True to use a :keyword: role for each function keyword argument. False to use a single :keyword arguments: role for all the keywords.

This behaves similarly to napoleon_use_param. Note unlike docutils, :keyword: and :param: will not be treated the same way - there will be a separate "Keyword Arguments" section, rendered in the same fashion as "Parameters" section (type links created if possible)

napoleon_use_rtype
Type:
bool
Default:
True

True to use the :rtype: role for the return type. False to output the return type inline with the description.

This NumPy style snippet will be converted as follows:

Returns
-------
bool
 True if successful, False otherwise

If True:

:returns: True if successful, False otherwise
:rtype: bool

If False:

:returns: *bool* -- True if successful, False otherwise
napoleon_preprocess_types
Type:
bool
Default:
False

True to convert the type definitions in the docstrings as references.

Added in version 3.2.1.

Changed in version 3.5: Do preprocess the Google style docstrings also.

napoleon_type_aliases
Type:
dict[str, str] | None
Default:
None

A mapping to translate type names to other names or references. Works only when napoleon_use_param = True.

With:

napoleon_type_aliases = {
 "CustomType": "mypackage.CustomType",
 "dict-like": ":term:`dict-like <mapping>`",
}

This NumPy style snippet:

Parameters
----------
arg1 : CustomType
 Description of `arg1`
arg2 : dict-like
 Description of `arg2`

becomes:

:param arg1: Description of `arg1`
:type arg1: mypackage.CustomType
:param arg2: Description of `arg2`
:type arg2: :term:`dict-like <mapping>`

Added in version 3.2.

napoleon_attr_annotations
Type:
bool
Default:
True

True to allow using PEP 526 attributes annotations in classes. If an attribute is documented in the docstring without a type and has an annotation in the class body, that type is used.

Added in version 3.4.

napoleon_custom_sections
Type:
Sequence[str | tuple[str, str]] | None
Default:
None

Add a list of custom sections to include, expanding the list of parsed sections.

The entries can either be strings or tuples, depending on the intention:

  • To create a custom "generic" section, just pass a string.

  • To create an alias for an existing section, pass a tuple containing the alias name and the original, in that order.

  • To create a custom section that displays like the parameters or returns section, pass a tuple containing the custom section name and a string value, "params_style" or "returns_style".

If an entry is just a string, it is interpreted as a header for a generic section. If the entry is a tuple/list/indexed container, the first entry is the name of the section, the second is the section key to emulate. If the second entry value is "params_style" or "returns_style", the custom section will be displayed like the parameters section or returns section.

Added in version 1.8.

Changed in version 3.5: Support params_style and returns_style

Previous
Math support for HTML outputs in Sphinx
Next
sphinx.ext.todo – Support for todo items