Improve _sources directory handling (#47)

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>

.github/workflows/test.yml

@@ -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: |

.pre-commit-config.yaml

@@ -18,13 +18,6 @@ repos:
     hooks:
     - id: flake8
 
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.11.2
-    hooks:
-    - id: mypy
-      files: ^sphinx_llms_txt/
-      additional_dependencies: [types-docutils]
-
   - repo: https://github.com/sphinx-contrib/sphinx-lint
     rev: v1.0.0
     hooks:

CHANGELOG.rst

@@ -1,6 +1,30 @@
 Changelog
 =========
 
+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
 -----
 

docs/source/contributing.rst

@@ -19,7 +19,7 @@ Local development
 
    .. code-block:: console
 
-      pip install -e ".[dev]"
+      pip install -e . --group dev
 
 #. Install pre-commit Git hook scripts:
 

pyproject.toml

@@ -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",
@@ -40,7 +43,6 @@ dev = [
     "mypy",
     "isort",
     "pre-commit",
-    "sphinx",
 ]
 test = [
     "pytest>=7.0.0",

sphinx_llms_txt/__init__.py

@@ -21,7 +21,7 @@ from .manager import LLMSFullManager
 from .processor import DocumentProcessor
 from .writer import FileWriter
 
-__version__ = "0.5.0"
+__version__ = "0.6.0"
 
 # Export classes needed by tests
 __all__ = [
@@ -107,13 +107,12 @@ def build_finished(app: Sphinx, exception):
                     _manager.update_page_title(docname, title)
 
         # Create the combined file
-        _manager.combine_sources(str(app.outdir), str(app.srcdir))
+        _manager.combine_sources(app.outdir, app.srcdir)
 
 
 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_full_file", True, "env")
@@ -127,15 +126,21 @@ 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."""
 
+        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__,
         "parallel_read_safe": True,

sphinx_llms_txt/collector.py

@@ -3,7 +3,7 @@ Document collector module for sphinx-llms-txt.
 """
 
 import fnmatch
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Tuple
 
 from sphinx.environment import BuildEnvironment
 from sphinx.util import logging
@@ -16,8 +16,8 @@ class DocumentCollector:
 
     def __init__(self):
         self.page_titles: Dict[str, str] = {}
-        self.master_doc: Optional[str] = None
-        self.env: Optional[BuildEnvironment] = None
+        self.master_doc: str = None
+        self.env: BuildEnvironment = None
         self.config: Dict[str, Any] = {}
         self.app = None
 
@@ -60,7 +60,7 @@ class DocumentCollector:
         else:
             return [source_suffix]  # String format
 
-    def _get_docname_suffix(self, docname: str, sources_dir) -> Optional[str]:
+    def _get_docname_suffix(self, docname: str, sources_dir) -> str:
         """
         Determine the source suffix for a given docname by checking which
         file exists.
@@ -102,7 +102,7 @@ class DocumentCollector:
 
         return None
 
-    def get_page_order(self, sources_dir=None) -> List[Tuple[str, Optional[str]]]:
+    def get_page_order(self, sources_dir=None) -> List[Tuple[str, str]]:
         """Get the correct page order from the toctree structure.
 
         Args:
@@ -114,7 +114,7 @@ class DocumentCollector:
         if not self.env or not self.master_doc:
             return []
 
-        page_order: List[Tuple[str, Optional[str]]] = []
+        page_order = []
         visited = set()
 
         def collect_from_toctree(docname: str):
@@ -126,7 +126,7 @@ class DocumentCollector:
 
             # Add the current document with its suffix
             if docname not in [doc for doc, _ in page_order]:
-                suffix: Optional[str] = None
+                suffix = None
                 if sources_dir:
                     suffix = self._get_docname_suffix(docname, sources_dir)
                 page_order.append((docname, suffix))
@@ -135,21 +135,18 @@ class DocumentCollector:
             try:
                 # Look for toctree_includes which contains the direct children
                 if (
-                    self.env
-                    and hasattr(self.env, "toctree_includes")
+                    hasattr(self.env, "toctree_includes")
                     and docname in self.env.toctree_includes
                 ):
                     for child_docname in self.env.toctree_includes[docname]:
-                        collect_from_toctree(str(child_docname))
+                        collect_from_toctree(child_docname)
                 # Try to use dependencies to find related documents
                 elif (
-                    self.env
-                    and hasattr(self.env, "dependencies")
+                    hasattr(self.env, "dependencies")
                     and docname in self.env.dependencies
                 ):
                     # Extract the dependent documents from the dependencies dict
-                    for child_docname_obj in self.env.dependencies[docname]:
-                        child_docname = str(child_docname_obj)
+                    for child_docname in self.env.dependencies[docname]:
                         # Only add documents actually in the document set
                         if (
                             hasattr(self.env, "all_docs")
@@ -157,11 +154,7 @@ class DocumentCollector:
                         ):
                             collect_from_toctree(child_docname)
                 # Fallback to titles or other available references
-                elif (
-                    self.env
-                    and hasattr(self.env, "titles")
-                    and hasattr(self.env, "all_docs")
-                ):
+                elif hasattr(self.env, "titles") and hasattr(self.env, "all_docs"):
                     # Get all document names
                     all_docnames = list(self.env.all_docs.keys())
 
@@ -192,7 +185,7 @@ class DocumentCollector:
                 ]
             )
             for docname in remaining:
-                suffix: Optional[str] = None
+                suffix = None
                 if sources_dir:
                     suffix = self._get_docname_suffix(docname, sources_dir)
                 page_order.append((docname, suffix))
@@ -200,8 +193,8 @@ class DocumentCollector:
         return page_order
 
     def filter_excluded_pages(
-        self, page_order: List[Tuple[str, Optional[str]]]
-    ) -> List[Tuple[str, Optional[str]]]:
+        self, page_order: List[Tuple[str, str]]
+    ) -> List[Tuple[str, str]]:
         """Filter out excluded pages from the page order."""
         exclude_patterns = self.config.get("llms_txt_exclude")
         if exclude_patterns:

sphinx_llms_txt/manager.py

@@ -5,7 +5,7 @@ Main manager module for sphinx-llms-txt.
 import glob
 import subprocess
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple, Union, cast
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from sphinx.application import Sphinx
 from sphinx.environment import BuildEnvironment
@@ -150,8 +150,8 @@ class LLMSFullManager:
         self.ignored_pages.add(docname)
 
     def _filter_ignored_pages(
-        self, page_order: Union[List[str], List[Tuple[str, Optional[str]]]]
-    ) -> Union[List[str], List[Tuple[str, Optional[str]]]]:
+        self, page_order: Union[List[str], List[Tuple[str, str]]]
+    ) -> Union[List[str], List[Tuple[str, str]]]:
         """Filter out ignored pages from page_order."""
         filtered_pages = []
         for item in page_order:
@@ -164,7 +164,7 @@ class LLMSFullManager:
             if docname not in self.ignored_pages:
                 filtered_pages.append(item)
 
-        return cast(Union[List[str], List[Tuple[str, Optional[str]]]], filtered_pages)
+        return filtered_pages
 
     def set_config(self, config: Dict[str, Any]):
         """Set configuration options."""
@@ -197,7 +197,6 @@ class LLMSFullManager:
         possible_sources = [
             Path(outdir) / "_sources",
             Path(outdir) / "html" / "_sources",
-            Path(outdir) / "singlehtml" / "_sources",
         ]
 
         for path in possible_sources:
@@ -205,27 +204,44 @@ 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
+                )
+
+            # 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) / str(output_filename)
+        output_path = Path(outdir) / output_filename
 
         # Log discovered files and page order
         logger.debug(f"sphinx-llms-txt: Page order (after exclusion): {page_order}")
@@ -286,7 +302,7 @@ class LLMSFullManager:
         content_parts = []
 
         # Track code files for later processing
-        code_file_parts: List[str] = []
+        code_file_parts = []
 
         # Count lines in code files (initially 0)
         code_files_line_count = 0
@@ -365,7 +381,7 @@ class LLMSFullManager:
         if not (size_limit_exceeded and should_abort_early):
             # Get all source files in the _sources directory using configured suffixes
             source_suffixes = self._get_source_suffixes()
-            all_source_files: List[Path] = []
+            all_source_files = []
             for src_suffix in source_suffixes:
                 # Avoid duplicate extensions when source_suffix == source_link_suffix
                 if src_suffix == source_link_suffix:
@@ -735,9 +751,9 @@ class LLMSFullManager:
                                 title = Path(title_str[len(base_path) :])
                     except ValueError:
                         # File is not relative to srcdir, use filename
-                        title = Path(file_path.name)
+                        title = file_path.name
                 else:
-                    title = Path(file_path.name)
+                    title = file_path.name
 
                 # Format as code block with equals underline
                 title_str = str(title)
@@ -769,9 +785,7 @@ class LLMSFullManager:
 
         return code_parts, sorted(processed_files)
 
-    def _create_code_files_section_header(
-        self, file_paths: Optional[List[Path]] = None
-    ) -> str:
+    def _create_code_files_section_header(self, file_paths: List[Path] = None) -> str:
         """Create the section header for source code files.
 
         Args:
@@ -819,7 +833,7 @@ class LLMSFullManager:
             return ""
 
         # Convert to relative paths if possible and create tree structure
-        tree_data: Dict[str, Any] = {}
+        tree_data = {}
 
         for file_path in sorted(file_paths):
             # Get relative path from source directory for display
@@ -872,7 +886,7 @@ class LLMSFullManager:
                 current[parts[-1]] = None  # None indicates it's a file
 
         # Convert tree structure to string representation
-        lines: List[str] = []
+        lines = []
         self._format_tree_node(tree_data, lines, "", True)
 
         # Indent each line for reStructuredText code block

sphinx_llms_txt/processor.py

@@ -130,7 +130,7 @@ class DocumentProcessor:
         """
         # Get the configured path directives to process
         default_path_directives = ["image", "figure"]
-        custom_path_directives = self.config.get("llms_txt_directives") or []
+        custom_path_directives = self.config.get("llms_txt_directives")
         path_directives = set(default_path_directives + custom_path_directives)
 
         # Build the regex pattern to match all configured directives

sphinx_llms_txt/writer.py

@@ -3,7 +3,7 @@ File writer module for sphinx-llms-txt.
 """
 
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Tuple, Union
 
 from sphinx.application import Sphinx
 from sphinx.util import logging
@@ -14,12 +14,7 @@ logger = logging.getLogger(__name__)
 class FileWriter:
     """Handles writing processed content to output files."""
 
-    def __init__(
-        self,
-        config: Dict[str, Any],
-        outdir: Optional[str] = None,
-        app: Optional[Sphinx] = None,
-    ):
+    def __init__(self, config: Dict[str, Any], outdir: str = None, app: Sphinx = None):
         self.config = config
         self.outdir = outdir
         self.app = app
@@ -52,7 +47,7 @@ class FileWriter:
 
     def write_verbose_info_to_file(
         self,
-        page_order: Union[List[str], List[Tuple[str, Optional[str]]]],
+        page_order: Union[List[str], List[Tuple[str, str]]],
         page_titles: Dict[str, str],
         total_line_count: int = 0,
     ) -> bool:
@@ -72,13 +67,13 @@ class FileWriter:
             )
             return False
 
-        output_path = Path(self.outdir) / str(self.config.get("llms_txt_filename"))
+        output_path = Path(self.outdir) / self.config.get("llms_txt_filename")
         try:
             with open(output_path, "w", encoding="utf-8") as f:
                 project_name = "llms-txt Summary"
                 # First priority: use title from config if available
                 if self.config.get("llms_txt_title"):
-                    project_name = str(self.config.get("llms_txt_title"))
+                    project_name = self.config.get("llms_txt_title")
                 # Second priority: use project name from Sphinx app if available
                 elif (
                     self.app

tests/test_llms_txt.py

@@ -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()
@@ -995,3 +1031,128 @@ 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()