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

sphinx_llms_txt/__init__.py

@@ -21,7 +21,7 @@ from .manager import LLMSFullManager
 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 @@ class LLMSFullManager:
                     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 @@ class LLMSFullManager:
                         filtered_page_order,
                         self.collector.page_titles,
                         total_line_count,
+                        sources_dir,
                     )
                 return
             elif action == "note":
@@ -536,6 +538,7 @@ class LLMSFullManager:
                         filtered_page_order,
                         self.collector.page_titles,
                         total_line_count,
+                        sources_dir,
                     )
                 return
             elif action == "keep":
@@ -554,7 +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]:

sphinx_llms_txt/writer.py

@@ -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