Support customizable URI templates in llms.txt (#48)

Author: jdillard

CHANGELOG.rst

@@ -1,6 +1,12 @@
 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
 -----
 

docs/source/advanced-configuration.rst

@@ -261,6 +261,37 @@ 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``)
+
 .. _integration_examples:
 
 Integration Examples
@@ -285,6 +316,7 @@ 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/"

docs/source/conf.py

@@ -15,6 +15,7 @@
 project = "sphinx-llms-txt"
 copyright = "Jared Dillard"
 author = "Jared Dillard"
+llms_txt_uri_template = "{base_url}{docname}.md"
 llms_txt_code_files = ["+:../../sphinx_llms_txt/*.py"]
 llms_txt_summary = """
 A Sphinx extension that generates a summary llms.txt file,written in Markdown,
@@ -88,7 +89,7 @@
     "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 ---------------------------------------------

docs/source/configuration-values.rst

@@ -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

sphinx_llms_txt/__init__.py

@@ -21,7 +21,7 @@
 from .processor import DocumentProcessor
 from .writer import FileWriter
 
-__version__ = "0.6.0"
+__version__ = "0.7.0"
 
 # Export classes needed by tests
 __all__ = [
@@ -85,6 +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,
@@ -115,6 +116,7 @@ def setup(app: Sphinx) -> Dict[str, Any]:
 
     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")

sphinx_llms_txt/manager.py

@@ -223,6 +223,7 @@ def combine_sources(self, outdir: str, srcdir: str):
                     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
@@ -523,6 +524,7 @@ def combine_sources(self, outdir: str, srcdir: str):
                         filtered_page_order,
                         self.collector.page_titles,
                         total_line_count,
+                        sources_dir,
                     )
                 return
             elif action == "note":
@@ -536,6 +538,7 @@ def combine_sources(self, outdir: str, srcdir: str):
                         filtered_page_order,
                         self.collector.page_titles,
                         total_line_count,
+                        sources_dir,
                     )
                 return
             elif action == "keep":
@@ -554,7 +557,10 @@ def combine_sources(self, outdir: str, srcdir: str):
         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]:

sphinx_llms_txt/writer.py

@@ -19,6 +19,42 @@ def __init__(self, config: Dict[str, Any], outdir: str = None, app: Sphinx = Non
         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:
@@ -50,13 +86,15 @@ def write_verbose_info_to_file(
         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.
 
         Args:
             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 @@ def write_verbose_info_to_file(
                 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

tests/test_llms_txt.py

@@ -794,6 +794,7 @@ class Config:
             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"