Compare commits

..
Author SHA1 Message Date
Jared Dillard a3b52396cf Merge branch 'main' into feature/singlemarkdown 2025-12-02 22:09:36 -08:00
Jared Dillard c23c6d4468 Add tabs 2025-12-02 22:09:14 -08:00
Jared Dillard 43eae65122 Merge branch 'main' into feature/singlemarkdown 2025-12-02 16:56:08 -08:00
Jared Dillard db32dc60a7 Improve CMake bits 2025-12-02 16:48:29 -08:00
Jared DillardandGitHub 543efabebb [docs] Add restbuilder builder for single page .rst builds (#53) 2025-12-01 13:34:45 -08:00
Jared Dillard 883a6080bb rename cmake file 2025-10-28 12:43:54 -07:00
Jared Dillard 98c45ba092 move function to cmake folder 2025-10-28 12:40:13 -07:00
Jared Dillard 6a07ce7b03 Merge branch 'main' into feature/singlemarkdown 2025-10-28 12:28:18 -07:00
Jared Dillard 141e0e29f6 clean up the cmake 2025-10-28 12:26:45 -07:00
Jared Dillard 5dd59ed613 change to add_sphinx_builder function 2025-10-28 12:25:13 -07:00
Jared Dillard f5c6207eb7 turn off llms-full.txt 2025-10-28 00:12:00 -07:00
Jared Dillard 109fee898e Add to presets 2025-10-28 00:09:34 -07:00
Jared Dillard 74c919c807 add singlemarkdown builder 2025-10-28 00:02:39 -07:00
Jared DillardandGitHub 1b08b2f362 Add docs on markdown usage (#50) 2025-10-27 20:33:28 -07:00
Jared DillardandGitHub 5bfbb0168f Support customizable URI templates in llms.txt (#48) 2025-10-27 17:41:04 -07:00
Jared DillardandGitHub e2a80faf04 Add CMake support for also building Markdown docs in parallel (#49) 2025-10-26 20:11:09 -07:00
Jared DillardandGitHub b63801bcff Improve _sources directory handling (#47) 2025-10-13 23:53:46 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
c45ebb0369 Bump the all-github-actions group with 2 updates (#45)
Bumps the all-github-actions group with 2 updates: [actions/checkout](https://github.com/actions/checkout) and [actions/setup-python](https://github.com/actions/setup-python).


Updates `actions/checkout` from 4 to 5
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v4...v5)

Updates `actions/setup-python` from 5 to 6
- [Release notes](https://github.com/actions/setup-python/releases)
- [Commits](https://github.com/actions/setup-python/compare/v5...v6)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: all-github-actions
- dependency-name: actions/setup-python
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: all-github-actions
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-10-04 18:59:29 -07:00
Jared DillardandGitHub f5dcd15889 Fix optional sphinx dependency (#44) 2025-09-17 10:51:07 -07:00
Jared DillardandGitHub e64e20133a Remove support for singlehtml (#40) 2025-08-29 15:22:32 -07:00
Jared Dillard 52949a952a Update changelog 2025-08-20 16:01:44 -07:00
Jared DillardandGitHub 3d7edbf7d9 Only allow builders that have a _sources directory (#38) 2025-08-20 15:57:47 -07:00
Jared Dillard 7e390546ba Improve docstring 2025-08-18 18:25:58 -07:00
Jared DillardandGitHub 75380589e1 fix syntax 2025-08-09 01:40:01 -07:00
Jared DillardandGitHub 19c224c199 Add contributing to README.md 2025-08-09 01:39:06 -07:00
20 changed files with 691 additions and 53 deletions
+5 -5
View File
@@ -10,9 +10,9 @@ jobs:
pre-commit:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v5
- name: Set up Python 3.10
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: "3.10"
- uses: pre-commit/action@v3.0.1
@@ -23,17 +23,17 @@ jobs:
python-version: ['3.9', '3.10', '3.11', '3.12']
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v5
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -e ".[dev]"
pip install -e . --group dev
# - name: Run mypy
# run: |
+13 -11
View File
@@ -1,15 +1,17 @@
version: 2
build:
os: "ubuntu-20.04"
os: ubuntu-24.04
tools:
python: "3.10"
sphinx:
configuration: docs/source/conf.py
python:
install:
- requirements: docs/requirements.txt
- method: pip
path: .
python: "3.13"
commands:
- pip install cmake
- pip install -r docs/requirements.txt
- pip install -e .
- cmake --workflow --preset documentation-workflow
# Copy built documentation to Read the Docs output directory
- mkdir -p $READTHEDOCS_OUTPUT/html
- cp -r build/html/* $READTHEDOCS_OUTPUT/html/
- cp -r build/markdown/* $READTHEDOCS_OUTPUT/html/
- cp build/singlemarkdown/index.md $READTHEDOCS_OUTPUT/html/llms-full.txt
- cp -r build/rst/* $READTHEDOCS_OUTPUT/html/
+30
View File
@@ -1,6 +1,36 @@
Changelog
=========
0.7.0
-----
- Add :confval:`llms_txt_uri_template` configuration option to control the link behavior in :confval:`llms_txt_filename`.
`#48 <https://github.com/jdillard/sphinx-llms-txt/pull/48>`_
0.6.0
-----
- Improve _sources directory handling
`#47 <https://github.com/jdillard/sphinx-llms-txt/pull/47>`_
0.5.3
-----
- Make sphinx a required dependency since there are imports from Sphinx
`#44 <https://github.com/jdillard/sphinx-llms-txt/pull/44>`_
0.5.2
-----
- Remove support for singlehtml
`#40 <https://github.com/jdillard/sphinx-llms-txt/pull/40>`_
0.5.1
-----
- Only allow builders that have _sources directory
`#38 <https://github.com/jdillard/sphinx-llms-txt/pull/38>`_
0.5.0
-----
+8
View File
@@ -0,0 +1,8 @@
cmake_minimum_required(VERSION 3.15)
project(SphinxLLMsTxt VERSION 1.0.0 LANGUAGES NONE)
# Add CMake module path
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
# Add documentation
add_subdirectory(docs)
+59
View File
@@ -0,0 +1,59 @@
{
"version": 6,
"configurePresets": [
{
"name": "documentation",
"displayName": "Documentation Build",
"description": "Configure project with documentation environment setup",
"binaryDir": "${sourceDir}/build"
}
],
"buildPresets": [
{
"name": "html",
"displayName": "Build HTML Documentation",
"configurePreset": "documentation",
"targets": ["html"]
},
{
"name": "markdown",
"displayName": "Build Markdown Documentation",
"configurePreset": "documentation",
"targets": ["markdown"]
},
{
"name": "singlemarkdown",
"displayName": "Build Single Markdown Documentation",
"configurePreset": "documentation",
"targets": ["singlemarkdown"]
},
{
"name": "rst",
"displayName": "Build reStructuredText Documentation",
"configurePreset": "documentation",
"targets": ["rst"]
},
{
"name": "docs-parallel",
"displayName": "Build HTML and Markdown in parallel",
"configurePreset": "documentation",
"targets": ["html", "markdown", "singlemarkdown", "rst"]
}
],
"workflowPresets": [
{
"name": "documentation-workflow",
"displayName": "Documentation Build Workflow",
"steps": [
{
"type": "configure",
"name": "documentation"
},
{
"type": "build",
"name": "docs-parallel"
}
]
}
]
}
+4
View File
@@ -11,6 +11,10 @@ A Sphinx extension that generates a summary `llms.txt` file and a single combine
See [sphinx-llms-txt documentation](https://sphinx-llms-txt.readthedocs.io/en/latest/index.html) for installation and configuration instructions.
## Contributing
Pull Requests welcome! See [Contributing](https://sphinx-llms-txt.readthedocs.io/en/latest/contributing.html) for instructions on how best to contribute.
## License
MIT License - see LICENSE file for details.
+28
View File
@@ -0,0 +1,28 @@
# Sphinx related utilities
set(SPHINX_SOURCE ${CMAKE_CURRENT_SOURCE_DIR}/source)
set(SPHINX_BUILD ${CMAKE_BINARY_DIR})
# Function to find Sphinx in the system
function(setup_sphinx_environment)
# Find sphinx-build executable in system
find_program(SPHINX_EXECUTABLE
NAMES sphinx-build
DOC "Sphinx documentation generator"
)
if(NOT SPHINX_EXECUTABLE)
message(FATAL_ERROR "sphinx-build not found. Please install Sphinx.")
endif()
# Export to parent scope
set(SPHINX_EXECUTABLE "${SPHINX_EXECUTABLE}" PARENT_SCOPE)
endfunction()
# Function to add a Sphinx builder target
function(add_sphinx_builder builder_name)
add_custom_target(${builder_name}
COMMAND ${SPHINX_EXECUTABLE} -b ${builder_name} ${SPHINX_SOURCE} ${SPHINX_BUILD}/${builder_name}
VERBATIM
)
endfunction()
+8
View File
@@ -0,0 +1,8 @@
include(SphinxUtils)
setup_sphinx_environment()
add_sphinx_builder(html)
add_sphinx_builder(markdown)
add_sphinx_builder(singlemarkdown)
add_sphinx_builder(rst)
+3
View File
@@ -3,4 +3,7 @@ esbonio
sphinx-contributors
sphinx
sphinx-llms-txt
sphinx-inline-tabs
sphinxext-opengraph
sphinx-markdown-builder @ git+https://github.com/akaihola/sphinx-markdown-builder.git@singlemarkdown
sphinxcontrib-restbuilder
+37
View File
@@ -261,6 +261,42 @@ If you want to include absolute URLs for resources in your documentation, you ca
When this option is set, all resolved paths in directives will be prefixed with this URL, creating absolute paths in the generated files.
.. _customizing_uri_links:
Customizing URI Links in llms.txt
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
By default, the ``llms.txt`` file links to source files in the ``_sources`` directory when available, falling back to HTML pages when sources aren't available.
You can customize this behavior using URI templates with :confval:`llms_txt_uri_template`:
.. code-block:: python
# Default: Link to source files, if _sources exists
llms_txt_uri_template = "{base_url}_sources/{docname}{suffix}{sourcelink_suffix}"
# Default: Link to HTML pages instead, if _sources doesn't exist
llms_txt_uri_template = "{base_url}{docname}.html"
# Manual: Link to a custom markdown build
llms_txt_uri_template = "{base_url}{docname}.md"
.. _available_template_variables:
Available Template Variables
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Your URI template can use the following variables:
- ``{base_url}`` - The base URL from ``html_baseurl`` configuration (includes trailing slash)
- ``{docname}`` - The document name (e.g., ``index``, ``guide/intro``)
- ``{suffix}`` - The source file suffix (e.g., ``.rst``, ``.md``) - may be empty if no source file exists
- ``{sourcelink_suffix}`` - The suffix from ``html_sourcelink_suffix`` configuration (e.g., ``.txt``)
.. tip::
Instead of using the default of linking to ``_sources``, you can generate Markdown and/or reStructuredText files from your documentation and link to those in ``llms.txt``.
See this package's `CMake setup <https://github.com/jdillard/sphinx-llms-txt>`_ for an example of building both HTML and Markdown and/or reStructuredText in parallel.
Note that ``_sources`` is still needed for ``llms-full.txt`` at this time.
.. _integration_examples:
Integration Examples
@@ -285,6 +321,7 @@ Here's a complete example showing multiple :doc:`configuration-values`:
This is a comprehensive documentation set for our project.
It includes API references, usage examples, and tutorials.
"""
llms_txt_uri_template = "{base_url}{docname}.md"
# Path handling
html_baseurl = "https://docs.example.com/"
+9 -1
View File
@@ -15,12 +15,18 @@ import subprocess
project = "sphinx-llms-txt"
copyright = "Jared Dillard"
author = "Jared Dillard"
llms_txt_uri_template = "{base_url}{docname}.md"
llms_txt_full_file = False
llms_txt_code_files = ["+:../../sphinx_llms_txt/*.py"]
llms_txt_summary = """
A Sphinx extension that generates a summary llms.txt file,written in Markdown,
and a single combined documentation llms-full.txt file, written in reStructuredText.
"""
# This doesn't seem to be supported
# rst_file_suffix = ".html.rst"
# check if the current commit is tagged as a release (vX.Y.Z)
try:
GIT_TAG_OUTPUT = subprocess.check_output(["git", "tag", "--points-at", "HEAD"])
@@ -49,6 +55,8 @@ extensions = [
"sphinx.ext.intersphinx",
"sphinx_contributors",
"sphinx_llms_txt",
"sphinxcontrib.restbuilder",
"sphinx_inline_tabs",
]
# The language for content autogenerated by Sphinx. Refer to documentation
@@ -88,7 +96,7 @@ html_theme_options = {
"source_directory": "docs/source/",
}
html_baseurl = "https://sphinx-llms-txt.readthedocs.org/"
html_baseurl = "https://sphinx-llms-txt.readthedocs.org/en/latest/"
# -- Options for HTMLHelp output ---------------------------------------------
+9
View File
@@ -58,6 +58,15 @@ Project Configuration Values
.. versionadded:: 0.2.0
.. confval:: llms_txt_uri_template
- **Type**: string or ``None``
- **Default**: ``None``
- **Description**: Template string for generating URIs in ``llms.txt``.
See :ref:`customizing_uri_links`.
.. versionadded:: 0.7.0
.. confval:: llms_txt_directives
- **Type**: list of strings
+1 -1
View File
@@ -19,7 +19,7 @@ Local development
.. code-block:: console
pip install -e ".[dev]"
pip install -e . --group dev
#. Install pre-commit Git hook scripts:
+8 -6
View File
@@ -4,17 +4,19 @@ Getting Started
Installation
------------
Directly install via ``pip`` by using:
Directly install by using:
.. code-block:: bash
.. tab:: via pip
pip install sphinx-llms-txt
.. code-block:: bash
Or with ``conda`` via ``conda-forge``:
pip install sphinx-llms-txt
.. code::
.. tab:: via conda:
conda install -c conda-forge sphinx-llms-txt
.. code-block:: bash
conda install -c conda-forge sphinx-llms-txt
Usage
-----
+6 -2
View File
@@ -26,13 +26,16 @@ classifiers = [
license = {text = "MIT"}
readme = "README.md"
dynamic = ["version"]
dependencies = [
"sphinx",
]
[project.urls]
download = "https://pypi.org/project/sphinx-llms-txt/"
source = "https://github.com/jdillard/sphinx-llms-txt"
changelog = "https://github.com/jdillard/sphinx-llms-txt/blob/master/CHANGELOG.rst"
[project.optional-dependencies]
[dependency-groups]
dev = [
"pytest>=7.0.0",
"black",
@@ -40,12 +43,13 @@ dev = [
"mypy",
"isort",
"pre-commit",
"sphinx",
]
test = [
"pytest>=7.0.0",
]
[tool.setuptools]
packages = ["sphinx_llms_txt"]
[tool.setuptools.dynamic]
version = {attr = "sphinx_llms_txt.__version__"}
+26 -10
View File
@@ -1,5 +1,14 @@
"""
Sphinx extension to create a combined sources file (llms-full.txt)
Sphinx extension that generates llms.txt and llms-full.txt files for LLM consumption.
This extension collects documentation content from Sphinx projects and generates
two output files:
- llms.txt: A concise Markdown summary with project overview and page links
- llms-full.txt: A comprehensive reStructuredText file containing all documentation
content with resolved includes and path references
The extension processes content during the build phase, handles page-level and
block-level ignore directives, and can optionally include source code files.
"""
from typing import Any, Dict
@@ -12,7 +21,7 @@ from .manager import LLMSFullManager
from .processor import DocumentProcessor
from .writer import FileWriter
__version__ = "0.5.0"
__version__ = "0.7.0"
# Export classes needed by tests
__all__ = [
@@ -76,6 +85,7 @@ def build_finished(app: Sphinx, exception):
config = {
"llms_txt_file": app.config.llms_txt_file,
"llms_txt_filename": app.config.llms_txt_filename,
"llms_txt_uri_template": app.config.llms_txt_uri_template,
"llms_txt_title": app.config.llms_txt_title,
"llms_txt_summary": summary,
"llms_txt_full_file": app.config.llms_txt_full_file,
@@ -104,9 +114,9 @@ def build_finished(app: Sphinx, exception):
def setup(app: Sphinx) -> Dict[str, Any]:
"""Set up the Sphinx extension."""
# Add configuration options
app.add_config_value("llms_txt_file", True, "env")
app.add_config_value("llms_txt_filename", "llms.txt", "env")
app.add_config_value("llms_txt_uri_template", None, "env")
app.add_config_value("llms_txt_full_file", True, "env")
app.add_config_value("llms_txt_full_filename", "llms-full.txt", "env")
app.add_config_value("llms_txt_full_max_size", None, "env")
@@ -118,14 +128,20 @@ def setup(app: Sphinx) -> Dict[str, Any]:
app.add_config_value("llms_txt_code_files", [], "env")
app.add_config_value("llms_txt_code_base_path", None, "env")
# Connect to Sphinx events
app.connect("doctree-resolved", doctree_resolved)
app.connect("build-finished", build_finished)
def builder_inited(app):
"""Used to limit what builders are allowed to run the extension."""
# Reset manager and root paragraph for each build
global _manager, _root_first_paragraph
_manager = LLMSFullManager()
_root_first_paragraph = ""
allowed_builders = ["html", "dirhtml"]
if hasattr(app, "builder") and app.builder.name in allowed_builders:
# Reset manager and root paragraph for each build
global _manager, _root_first_paragraph
_manager = LLMSFullManager()
_root_first_paragraph = ""
app.connect("doctree-resolved", doctree_resolved)
app.connect("build-finished", build_finished)
app.connect("builder-inited", builder_inited)
return {
"version": __version__,
+35 -13
View File
@@ -197,7 +197,6 @@ class LLMSFullManager:
possible_sources = [
Path(outdir) / "_sources",
Path(outdir) / "html" / "_sources",
Path(outdir) / "singlehtml" / "_sources",
]
for path in possible_sources:
@@ -205,25 +204,43 @@ class LLMSFullManager:
sources_dir = path
break
if not sources_dir:
logger.warning(
"Could not find _sources directory, skipping llms-full creation"
)
return
# Get the correct page order with source suffixes
# Get the correct page order (with or without source suffixes)
page_order = self.collector.get_page_order(sources_dir)
if not page_order:
logger.warning(
"Could not determine page order, skipping llms-full creation"
)
logger.warning("Could not determine page order, skipping file generation")
return
# Apply exclusion filter if configured
page_order = self.collector.filter_excluded_pages(page_order)
# Determine output file name and location
# If no sources directory, only generate llms.txt and return early
if not sources_dir:
# Generate llms.txt if requested
if self.config.get("llms_txt_file"):
filtered_page_order = self._filter_ignored_pages(page_order)
self.writer.write_verbose_info_to_file(
filtered_page_order,
self.collector.page_titles,
0, # No line count since no llms-full.txt
sources_dir,
)
# Only warn if user explicitly wants llms-full.txt
if self.config.get("llms_txt_full_file"):
# Check if html_copy_source is False
if self.app and not self.app.config.html_copy_source:
logger.warning(
"Could not find _sources directory, skipping llms-full.txt."
"Set html_copy_source = True in conf.py to enable."
)
else:
logger.warning(
"Could not find _sources directory, skipping llms-full.txt"
)
return
# Determine output file name and location for llms-full.txt
output_filename = self.config.get("llms_txt_full_filename")
output_path = Path(outdir) / output_filename
@@ -507,6 +524,7 @@ class LLMSFullManager:
filtered_page_order,
self.collector.page_titles,
total_line_count,
sources_dir,
)
return
elif action == "note":
@@ -520,6 +538,7 @@ class LLMSFullManager:
filtered_page_order,
self.collector.page_titles,
total_line_count,
sources_dir,
)
return
elif action == "keep":
@@ -538,7 +557,10 @@ class LLMSFullManager:
if success and self.config.get("llms_txt_file"):
filtered_page_order = self._filter_ignored_pages(page_order)
self.writer.write_verbose_info_to_file(
filtered_page_order, self.collector.page_titles, total_line_count
filtered_page_order,
self.collector.page_titles,
total_line_count,
sources_dir,
)
def _read_source_file(self, file_path: Path, docname: str) -> Tuple[str, int]:
+63 -2
View File
@@ -19,6 +19,42 @@ class FileWriter:
self.outdir = outdir
self.app = app
def _resolve_uri_template(self, sources_dir: Path = None) -> str:
"""Resolve which URI template to use based on configuration and sources_dir.
Args:
sources_dir: Path to _sources directory (None if not found)
Returns:
The template string to use for generating URIs
"""
# If custom template exists
custom_template = self.config.get("llms_txt_uri_template")
if custom_template:
# Validate user's template by checking for valid variable names
try:
# Try formatting with test valid values to validate syntax
test_values = {
"base_url": "http://example.com/",
"docname": "test",
"suffix": ".rst",
"sourcelink_suffix": ".txt",
}
custom_template.format(**test_values)
return custom_template
except (KeyError, ValueError) as e:
logger.warning(
f"sphinx-llms-txt: Invalid llms_txt_uri_template: {e}. "
f"Falling back to default."
)
# Else, use one of the default templates
if sources_dir:
return "{base_url}_sources/{docname}{suffix}{sourcelink_suffix}"
else:
return "{base_url}{docname}.html"
def write_combined_file(
self, content_parts: List[str], output_path: Path, total_line_count: int
) -> bool:
@@ -50,6 +86,7 @@ class FileWriter:
page_order: Union[List[str], List[Tuple[str, str]]],
page_titles: Dict[str, str],
total_line_count: int = 0,
sources_dir: Path = None,
) -> bool:
"""Write summary information to the llms.txt file.
@@ -57,6 +94,7 @@ class FileWriter:
page_order: Ordered list of document names or (docname, suffix) tuples
page_titles: Dictionary mapping docnames to titles
total_line_count: Total number of lines in the combined content
sources_dir: Path to _sources directory (None if not found)
Returns:
True if successful, False otherwise
@@ -102,14 +140,37 @@ class FileWriter:
if not base_url.endswith("/"):
base_url += "/"
# Get sourcelink suffix from Sphinx config
sourcelink_suffix = ""
if self.app and hasattr(self.app.config, "html_sourcelink_suffix"):
sourcelink_suffix = self.app.config.html_sourcelink_suffix
# Handle empty string case specially
if sourcelink_suffix == "":
sourcelink_suffix = "" # Keep it empty
elif not sourcelink_suffix.startswith("."):
sourcelink_suffix = "." + sourcelink_suffix
# Resolve which template to use
uri_template = self._resolve_uri_template(sources_dir)
for item in page_order:
# Handle both old format (str) and new format (tuple)
if isinstance(item, tuple):
docname, _ = item
docname, suffix = item
else:
docname = item
suffix = None
title = page_titles.get(docname, docname)
f.write(f"- [{title}]({base_url}{docname}.html)\n")
uri = uri_template.format(
base_url=base_url,
docname=docname,
suffix=suffix or "",
sourcelink_suffix=sourcelink_suffix,
)
f.write(f"- [{title}]({uri})\n")
logger.info(f"sphinx-llms-txt: created {output_path}")
return True
+162
View File
@@ -41,6 +41,42 @@ def test_setup_returns_valid_dict():
assert "parallel_write_safe" in result
def test_builder_inited_with_disallowed_builder():
"""Test that disallowed builders do not trigger extension setup."""
import sphinx_llms_txt
# Reset global state
sphinx_llms_txt._manager = sphinx_llms_txt.LLMSFullManager()
sphinx_llms_txt._root_first_paragraph = ""
# Mock a Sphinx app with a disallowed builder
class MockBuilder:
name = "text" # Not in allowed list
class MockApp:
def __init__(self):
self.config_values = {}
self.connections = {}
self.builder = MockBuilder()
def add_config_value(self, name, default, rebuild):
self.config_values[name] = (default, rebuild)
def connect(self, event, handler):
self.connections[event] = handler
app = MockApp()
setup(app)
# Trigger builder-inited
builder_inited_handler = app.connections["builder-inited"]
builder_inited_handler(app)
# With disallowed builder, other events should NOT be connected
assert "doctree-resolved" not in app.connections
assert "build-finished" not in app.connections
def test_document_collector_initialization():
"""Test initialization of DocumentCollector."""
collector = DocumentCollector()
@@ -758,6 +794,7 @@ def test_summary_default_uses_first_paragraph():
llms_txt_summary = None # Not configured
llms_txt_file = True
llms_txt_filename = "llms.txt"
llms_txt_uri_template = None
llms_txt_title = None
llms_txt_full_file = True
llms_txt_full_filename = "llms-full.txt"
@@ -995,3 +1032,128 @@ def test_code_files_ignored_patterns(tmp_path, caplog):
assert (
"Code file pattern 'docs/**/*.rst' ignored." in captured_warnings[0]
), f"Warning message should contain expected text. Got: {captured_warnings[0]}"
def test_llms_txt_generated_without_sources_dir(tmp_path):
"""Test that llms.txt is generated even when _sources directory doesn't exist."""
from sphinx_llms_txt.manager import LLMSFullManager
# Create manager
manager = LLMSFullManager()
# Set config to enable llms.txt
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
"llms_txt_full_file": True,
"llms_txt_full_filename": "llms-full.txt",
"llms_txt_exclude": [],
"llms_txt_directives": [],
}
manager.set_config(config)
# Create directories (but no _sources)
outdir = tmp_path / "build"
srcdir = tmp_path / "source"
outdir.mkdir()
srcdir.mkdir()
# Mock env with documents
class MockEnv:
all_docs = {"index": None, "about": None}
titles = {
"index": type("TitleNode", (), {"astext": lambda self: "Home"})(),
"about": type("TitleNode", (), {"astext": lambda self: "About"})(),
}
toctree_includes = {"index": ["about"]}
manager.set_env(MockEnv())
manager.set_master_doc("index")
# Update page titles directly in the collector
manager.update_page_title("index", "Home")
manager.update_page_title("about", "About")
# Call combine_sources - should generate llms.txt even without _sources
manager.combine_sources(str(outdir), str(srcdir))
# Verify llms.txt was created
llms_txt = outdir / "llms.txt"
assert llms_txt.exists(), "llms.txt should be generated even without _sources"
# Verify llms-full.txt was NOT created (since no _sources)
llms_full_txt = outdir / "llms-full.txt"
assert (
not llms_full_txt.exists()
), "llms-full.txt should not be generated without _sources"
# Read llms.txt and verify it has content
with open(llms_txt, "r", encoding="utf-8") as f:
content = f.read()
# Should contain page titles and links
assert "Home" in content
assert "About" in content
assert "index.html" in content
assert "about.html" in content
def test_llms_txt_no_warning_when_full_file_disabled(tmp_path, caplog):
"""
Test that no warning is logged when llms_txt_full_file=False and
_sources doesn't exist.
"""
from unittest.mock import patch
from sphinx_llms_txt.manager import LLMSFullManager
# Create manager
manager = LLMSFullManager()
# Set config with llms_txt_full_file=False
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
"llms_txt_full_file": False, # User doesn't want llms-full.txt
"llms_txt_full_filename": "llms-full.txt",
"llms_txt_exclude": [],
"llms_txt_directives": [],
}
manager.set_config(config)
# Create directories (but no _sources)
outdir = tmp_path / "build"
srcdir = tmp_path / "source"
outdir.mkdir()
srcdir.mkdir()
# Mock env with documents
class MockEnv:
all_docs = {"index": None}
titles = {"index": type("TitleNode", (), {"astext": lambda self: "Home"})()}
toctree_includes = {"index": []}
manager.set_env(MockEnv())
manager.set_master_doc("index")
manager.update_page_title("index", "Home")
# Capture warnings
captured_warnings = []
def capture_warning(message, *args, **kwargs):
if "_sources" in str(message):
captured_warnings.append(message)
with patch("sphinx_llms_txt.manager.logger.warning", side_effect=capture_warning):
# Call combine_sources
manager.combine_sources(str(outdir), str(srcdir))
# Verify NO warning was logged since llms_txt_full_file=False
assert (
len(captured_warnings) == 0
), "No warning should be logged when llms_txt_full_file=False"
# Verify llms.txt was still created
llms_txt = outdir / "llms.txt"
assert llms_txt.exists()
+175
View File
@@ -0,0 +1,175 @@
"""Test URI template functionality for llms.txt links."""
from sphinx_llms_txt import FileWriter
def test_uri_template_with_sources_dir(tmp_path):
"""Test that default template uses _sources links when sources_dir exists."""
build_dir = tmp_path / "build"
build_dir.mkdir()
# Create _sources directory to simulate its existence
sources_dir = build_dir / "_sources"
sources_dir.mkdir()
# Mock app with html_sourcelink_suffix
class MockApp:
class Config:
html_sourcelink_suffix = ".txt"
config = Config()
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
"llms_txt_uri_template": (
"{base_url}_sources/{docname}{suffix}{sourcelink_suffix}"
),
"html_baseurl": "https://example.com",
}
writer = FileWriter(config, str(build_dir), MockApp())
page_titles = {
"index": "Home Page",
"about": "About Us",
}
# Page order with suffixes (simulating _sources files exist)
page_order = [("index", ".rst"), ("about", ".md")]
writer.write_verbose_info_to_file(page_order, page_titles, 0, sources_dir)
# Check that the file was created
verbose_file = build_dir / "llms.txt"
assert verbose_file.exists()
# Read the file content
with open(verbose_file, "r", encoding="utf-8") as f:
content = f.read()
# Should link to _sources files
assert "- [Home Page](https://example.com/_sources/index.rst.txt)" in content
assert "- [About Us](https://example.com/_sources/about.md.txt)" in content
def test_uri_template_without_sources_dir(tmp_path):
"""
Test that HTML template is used when sources_dir doesn't exist and no custom
template.
"""
build_dir = tmp_path / "build"
build_dir.mkdir()
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
# No custom template set
"html_baseurl": "https://example.com",
}
writer = FileWriter(config, str(build_dir))
page_titles = {
"index": "Home Page",
"about": "About Us",
}
# Page order without suffixes (simulating no _sources)
page_order = [("index", None), ("about", None)]
# Pass None for sources_dir to simulate it doesn't exist
writer.write_verbose_info_to_file(page_order, page_titles, 0, None)
# Check that the file was created
verbose_file = build_dir / "llms.txt"
assert verbose_file.exists()
# Read the file content
with open(verbose_file, "r", encoding="utf-8") as f:
content = f.read()
# Should fallback to HTML links
assert "- [Home Page](https://example.com/index.html)" in content
assert "- [About Us](https://example.com/about.html)" in content
def test_uri_template_custom(tmp_path):
"""Test that custom URI template works correctly."""
build_dir = tmp_path / "build"
build_dir.mkdir()
sources_dir = build_dir / "_sources"
sources_dir.mkdir()
# Mock app with html_sourcelink_suffix
class MockApp:
class Config:
html_sourcelink_suffix = ".txt"
config = Config()
# Custom template that uses different path
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
"llms_txt_uri_template": "{base_url}raw/{docname}{suffix}",
"html_baseurl": "https://example.com/",
}
writer = FileWriter(config, str(build_dir), MockApp())
page_titles = {
"index": "Home Page",
}
page_order = [("index", ".rst")]
writer.write_verbose_info_to_file(page_order, page_titles, 0, sources_dir)
verbose_file = build_dir / "llms.txt"
with open(verbose_file, "r", encoding="utf-8") as f:
content = f.read()
# Should use custom template
assert "- [Home Page](https://example.com/raw/index.rst)" in content
def test_uri_template_invalid_fallback(tmp_path):
"""
Test that invalid template falls back to default sources template when
sources_dir exists.
"""
build_dir = tmp_path / "build"
build_dir.mkdir()
sources_dir = build_dir / "_sources"
sources_dir.mkdir()
# Mock app with html_sourcelink_suffix
class MockApp:
class Config:
html_sourcelink_suffix = ".txt"
config = Config()
# Invalid template with typo in variable name
config = {
"llms_txt_file": True,
"llms_txt_filename": "llms.txt",
"llms_txt_uri_template": "{base_urll}/{docname}",
"html_baseurl": "https://example.com",
}
writer = FileWriter(config, str(build_dir), MockApp())
page_titles = {
"index": "Home Page",
}
page_order = [("index", ".rst")]
writer.write_verbose_info_to_file(page_order, page_titles, 0, sources_dir)
verbose_file = build_dir / "llms.txt"
with open(verbose_file, "r", encoding="utf-8") as f:
content = f.read()
# Should fallback to default sources template
assert "- [Home Page](https://example.com/_sources/index.rst.txt)" in content