Fix image paths to deployed images (#30)

CHANGELOG.rst

@@ -1,6 +1,25 @@
 Changelog
 =========
 
+0.3.2
+-----
+
+- Fix image paths to deployed images
+  `#30 <https://github.com/jdillard/sphinx-llms-txt/pull/30>`_
+
+
+0.3.1
+-----
+
+- Fix issue when ``source_suffix`` equals ``source_link_suffix``
+  `#29 <https://github.com/jdillard/sphinx-llms-txt/pull/29>`_
+
+0.3.0
+-----
+
+- Use first paragraph as default for ``llms_txt_summary``
+  `#22 <https://github.com/jdillard/sphinx-llms-txt/pull/22>`_
+
 0.2.4
 -----
 

README.md

@@ -3,6 +3,7 @@
 A Sphinx extension that generates a summary `llms.txt` file and a single combined documentation `llms-full.txt` file.
 
 [![PyPI version](https://img.shields.io/pypi/v/sphinx-llms-txt.svg)](https://pypi.python.org/pypi/sphinx-llms-txt)
+[![Conda Version](https://img.shields.io/conda/vn/conda-forge/sphinx-llms-txt.svg)](https://anaconda.org/conda-forge/sphinx-llms-txt)
 [![Downloads](https://static.pepy.tech/badge/sphinx-llms-txt/month)](https://pepy.tech/project/sphinx-llms-txt)
 [![Parallel Safe](https://img.shields.io/badge/parallel%20safe-true-brightgreen)](#)
 

docs/source/advanced-configuration.rst

@@ -146,7 +146,7 @@ Integration Examples
 Complete Configuration Example
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Here's a complete example showing multiple :ref:`configuration-values`:
+Here's a complete example showing multiple :doc:`configuration-values`:
 
 .. code-block:: python
 

docs/source/conf.py

@@ -81,7 +81,11 @@ html_theme = "furo"
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-html_theme_options = {}
+html_theme_options = {
+    "source_repository": "https://github.com/jdillard/sphinx-llms-txt/",
+    "source_branch": "main",
+    "source_directory": "docs/source/",
+}
 
 html_baseurl = "https://sphinx-llms-txt.readthedocs.org/"
 

docs/source/configuration-values.rst

@@ -67,8 +67,8 @@ Project Configuration Values
 
 .. confval:: llms_txt_summary
 
-   - **Type**: string or ``None``
-   - **Default**: ``None``
+   - **Type**: string
+   - **Default**: The first paragraph in the root document, else an empty string
    - **Description**: Optional, but recommended, summary description for ``llms.txt``.
      See :ref:`custom_summary`.
 

docs/source/getting-started.rst

@@ -31,7 +31,7 @@ Once added, the extension will automatically generate the LLMs.txt files during
 See :doc:`advanced-configuration` for more information about how to use **sphinx-llms-txt**.
 
 How It Works
------------
+------------
 
 During the Sphinx build process:
 

docs/source/index.rst

@@ -3,7 +3,7 @@ Sphinx llms.txt Generator
 
 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.
 
-|PyPI version| |Downloads| |Parallel Safe| |GitHub Stars|
+|PyPI version| |Conda Version| |Downloads| |Parallel Safe| |GitHub Stars|
 
 .. toctree::
    :maxdepth: 2
@@ -20,6 +20,9 @@ A `Sphinx`_ extension that generates a summary ``llms.txt`` file, written in Mar
 .. |PyPI version| image:: https://img.shields.io/pypi/v/sphinx-llms-txt.svg
    :target: https://pypi.python.org/pypi/sphinx-llms-txt
    :alt: Latest PyPi Version
+.. |Conda Version| image:: https://img.shields.io/conda/vn/conda-forge/sphinx-llms-txt.svg
+    :target: https://anaconda.org/conda-forge/sphinx-llms-txt
+    :alt: Latest Conda Version
 .. |Downloads| image:: https://static.pepy.tech/badge/sphinx-llms-txt/month
     :target: https://pepy.tech/project/sphinx-llms-txt
     :alt: PyPi Downloads per month

sphinx_llms_txt/__init__.py

@@ -12,7 +12,7 @@ from .manager import LLMSFullManager
 from .processor import DocumentProcessor
 from .writer import FileWriter
 
-__version__ = "0.2.4"
+__version__ = "0.3.2"
 
 # Export classes needed by tests
 __all__ = [
@@ -25,9 +25,14 @@ __all__ = [
 # Global manager instance
 _manager = LLMSFullManager()
 
+# Store root document first paragraph
+_root_first_paragraph = ""
+
 
 def doctree_resolved(app: Sphinx, doctree, docname: str):
     """Called when a docname has been resolved to a document."""
+    global _root_first_paragraph
+
     # Extract title from the document
     title = None
     # findall() returns a generator, convert to list to check if it has elements
@@ -38,6 +43,14 @@ def doctree_resolved(app: Sphinx, doctree, docname: str):
     if title:
         _manager.update_page_title(docname, title)
 
+    # Extract first paragraph from root document
+    if docname == app.config.master_doc:
+        for node in doctree.traverse(nodes.paragraph):
+            first_para = node.astext()
+            if first_para:
+                _root_first_paragraph = first_para
+                break
+
 
 def build_finished(app: Sphinx, exception):
     """Called when the build is finished."""
@@ -47,12 +60,17 @@ def build_finished(app: Sphinx, exception):
         _manager.set_master_doc(app.config.master_doc)
         _manager.set_app(app)
 
+        # Get the summary - use configured value or extracted first paragraph
+        summary = app.config.llms_txt_summary
+        if summary is None:
+            summary = _root_first_paragraph
+
         # Set up configuration
         config = {
             "llms_txt_file": app.config.llms_txt_file,
             "llms_txt_filename": app.config.llms_txt_filename,
             "llms_txt_title": app.config.llms_txt_title,
-            "llms_txt_summary": app.config.llms_txt_summary,
+            "llms_txt_summary": summary,
             "llms_txt_full_file": app.config.llms_txt_full_file,
             "llms_txt_full_filename": app.config.llms_txt_full_filename,
             "llms_txt_full_max_size": app.config.llms_txt_full_max_size,
@@ -91,9 +109,10 @@ def setup(app: Sphinx) -> Dict[str, Any]:
     app.connect("doctree-resolved", doctree_resolved)
     app.connect("build-finished", build_finished)
 
-    # Reset manager for each build
-    global _manager
+    # Reset manager and root paragraph for each build
+    global _manager, _root_first_paragraph
     _manager = LLMSFullManager()
+    _root_first_paragraph = ""
 
     return {
         "version": __version__,

sphinx_llms_txt/collector.py

@@ -90,7 +90,13 @@ class DocumentCollector:
 
         # Try to find the source file with any of the valid source suffixes
         for src_suffix in source_suffixes:
-            candidate_file = sources_dir / f"{docname}{src_suffix}{source_link_suffix}"
+            # Avoid duplicate extensions when source_suffix == source_link_suffix
+            if src_suffix == source_link_suffix:
+                candidate_file = sources_dir / f"{docname}{src_suffix}"
+            else:
+                candidate_file = (
+                    sources_dir / f"{docname}{src_suffix}{source_link_suffix}"
+                )
             if candidate_file.exists():
                 return src_suffix
 

sphinx_llms_txt/manager.py

@@ -138,13 +138,22 @@ class LLMSFullManager:
 
             # Build the source file path directly using the known suffix
             if src_suffix:
-                source_file = sources_dir / f"{docname}{src_suffix}{source_link_suffix}"
+                # Avoid duplicate extensions when source_suffix == source_link_suffix
+                if src_suffix == source_link_suffix:
+                    source_file = sources_dir / f"{docname}{src_suffix}"
+                    expected_suffix = src_suffix
+                else:
+                    source_file = (
+                        sources_dir / f"{docname}{src_suffix}{source_link_suffix}"
+                    )
+                    expected_suffix = f"{src_suffix}{source_link_suffix}"
+
                 if source_file.exists():
                     docname_to_file[docname] = source_file
                 else:
                     logger.warning(
                         f"sphinx-llms-txt: Source file not found for: {docname}."
-                        f"Expected: {docname}{src_suffix}{source_link_suffix}"
+                        f"Expected: {docname}{expected_suffix}"
                     )
             else:
                 logger.warning(
@@ -205,7 +214,11 @@ class LLMSFullManager:
             source_suffixes = self._get_source_suffixes()
             all_source_files = []
             for src_suffix in source_suffixes:
-                glob_pattern = f"**/*{src_suffix}{source_link_suffix}"
+                # Avoid duplicate extensions when source_suffix == source_link_suffix
+                if src_suffix == source_link_suffix:
+                    glob_pattern = f"**/*{src_suffix}"
+                else:
+                    glob_pattern = f"**/*{src_suffix}{source_link_suffix}"
                 all_source_files.extend(sources_dir.glob(glob_pattern))
 
             processed_paths = set(file.resolve() for file in docname_to_file.values())
@@ -231,7 +244,12 @@ class LLMSFullManager:
 
                 # Try each source suffix to find which one this file uses
                 for src_suffix in source_suffixes:
-                    combined_suffix = f"{src_suffix}{source_link_suffix}"
+                    # Avoid duplicate extensions when suffixes match
+                    if src_suffix == source_link_suffix:
+                        combined_suffix = src_suffix
+                    else:
+                        combined_suffix = f"{src_suffix}{source_link_suffix}"
+
                     if rel_path.endswith(combined_suffix):
                         docname = rel_path[: -len(combined_suffix)]  # Remove suffix
                         break

sphinx_llms_txt/processor.py

@@ -94,8 +94,14 @@ class DocumentProcessor:
         if not base_url:
             return path
 
+        # Ensure base URL ends with slash
         if not base_url.endswith("/"):
             base_url += "/"
+
+        # Remove leading slash from path to avoid double slashes
+        if path.startswith("/"):
+            path = path[1:]
+
         return f"{base_url}{path}"
 
     def _is_absolute_or_url(self, path: str) -> bool:
@@ -137,12 +143,73 @@ class DocumentProcessor:
             prefix = match.group(1)  # The entire directive prefix including whitespace
             path = match.group(3).strip()  # The path argument
 
-            # Only process relative paths, not absolute paths or URLs
-            if not self._is_absolute_or_url(path):
-                # Special case for test files
-                if is_test:
-                    # Add subdir/ prefix to match test expectations
-                    full_path = "subdir/" + path
+            # Handle URLs and data URIs - leave unchanged
+            if path.startswith(("http://", "https://", "data:")):
+                return match.group(0)
+
+            # For ALL paths, check if image exists in _images first
+            # Extract filename from the path
+            filename = os.path.basename(path)
+
+            # Check if image exists in _images directory
+            # First determine the build directory from source_path
+            build_dir = None
+            if "_sources" in str(source_path):
+                # Extract build directory (parent of _sources)
+                path_parts = str(source_path).split("_sources/")
+                if len(path_parts) > 1:
+                    build_dir = path_parts[0].rstrip("/")
+
+            # If we can determine the build directory, check if image exists in _images
+            if build_dir:
+                images_path = os.path.join(build_dir, "_images", filename)
+                if os.path.exists(images_path):
+                    # Image exists in _images, use _images path
+                    full_path = f"/_images/{filename}"
+                    # Add base URL if configured
+                    full_path = self._add_base_url(full_path, base_url)
+                    return f"{prefix}{full_path}"
+
+            # Image doesn't exist in _images, handle based on path type
+            # Handle absolute paths (starting with /) - add base URL if configured
+            if path.startswith("/"):
+                # Add base URL to absolute paths if configured
+                full_path = self._add_base_url(path, base_url)
+                return f"{prefix}{full_path}"
+
+            # Handle relative paths with original logic for backward compatibility
+            # Special case for test files
+            if is_test:
+                # Add subdir/ prefix to match test expectations
+                full_path = "subdir/" + path
+
+                # If base_url is set, prepend it to the path
+                full_path = self._add_base_url(full_path, base_url)
+
+                # Return the updated directive with the full path
+                return f"{prefix}{full_path}"
+
+            # Production case (not in test)
+            elif "_sources" in str(source_path):
+                # Extract the part after _sources/
+                rel_doc_path, rel_doc_dir, rel_doc_path_parts = (
+                    self._extract_relative_document_path(source_path)
+                )
+
+                if rel_doc_path_parts:
+                    # For test subdirectory handling - this is for our test cases
+                    if (
+                        len(rel_doc_path_parts) > 0
+                        and rel_doc_path_parts[0] == "subdir"
+                    ):
+                        full_path = os.path.normpath(os.path.join("subdir", path))
+                    # Only add the rel_doc_dir if it's not empty
+                    elif rel_doc_dir:
+                        # Join with the original path to form full path relative
+                        # to srcdir
+                        full_path = os.path.normpath(os.path.join(rel_doc_dir, path))
+                    else:
+                        full_path = path
 
                     # If base_url is set, prepend it to the path
                     full_path = self._add_base_url(full_path, base_url)
@@ -150,37 +217,12 @@ class DocumentProcessor:
                     # Return the updated directive with the full path
                     return f"{prefix}{full_path}"
 
-                # Production case (not in test)
-                elif "_sources" in str(source_path):
-                    # Extract the part after _sources/
-                    rel_doc_path, rel_doc_dir, rel_doc_path_parts = (
-                        self._extract_relative_document_path(source_path)
-                    )
+            # Fallback for relative paths - add base URL if configured
+            else:
+                full_path = self._add_base_url(path, base_url)
+                return f"{prefix}{full_path}"
 
-                    if rel_doc_path_parts:
-                        # For test subdirectory handling - this is for our test cases
-                        if (
-                            len(rel_doc_path_parts) > 0
-                            and rel_doc_path_parts[0] == "subdir"
-                        ):
-                            full_path = os.path.normpath(os.path.join("subdir", path))
-                        # Only add the rel_doc_dir if it's not empty
-                        elif rel_doc_dir:
-                            # Join with the original path to form full path relative
-                            # to srcdir
-                            full_path = os.path.normpath(
-                                os.path.join(rel_doc_dir, path)
-                            )
-                        else:
-                            full_path = path
-
-                        # If base_url is set, prepend it to the path
-                        full_path = self._add_base_url(full_path, base_url)
-
-                        # Return the updated directive with the full path
-                        return f"{prefix}{full_path}"
-
-            # If we couldn't resolve the path or it's already absolute, return unchanged
+            # If we couldn't resolve the path, return unchanged
             return match.group(0)
 
         # Replace directive paths in the content

sphinx_llms_txt/writer.py

@@ -88,10 +88,12 @@ class FileWriter:
                 if description:
                     # Trim leading and trailing whitespace
                     description = description.strip()
-                    # Replace newlines with newline + blockquote marker to maintain
-                    # blockquote formatting
-                    description = description.replace("\n", "\n> ")
-                    f.write(f"> {description}\n\n")
+                    if description:
+                        # Only add blockquote if description is not empty
+                        # Replace newlines with newline + blockquote marker to maintain
+                        # blockquote formatting
+                        description = description.replace("\n", "\n> ")
+                        f.write(f"> {description}\n\n")
 
                 f.write("## Docs\n\n")
                 # Get base URL from config

tests/test_llms_txt.py

@@ -727,3 +727,84 @@ def test_source_suffix_detection_priority():
 
         # RST should come before MD (due to priority in toctree processing)
         assert rst_pos < md_pos, "RST content should appear before MD content"
+
+
+def test_summary_default_uses_first_paragraph():
+    """
+    Test that summary defaults to first paragraph of root document when not configured.
+    """
+    from docutils import nodes
+    from docutils.frontend import OptionParser
+    from docutils.parsers.rst import Parser
+    from docutils.utils import new_document
+
+    from sphinx_llms_txt import build_finished, doctree_resolved
+
+    # Create a proper document with settings
+    settings = OptionParser(components=(Parser,)).get_default_values()
+    doctree = new_document("<rst-doc>", settings)
+
+    title = nodes.title(text="Test Title")
+    paragraph = nodes.paragraph(
+        text="This is the first paragraph that should be used as summary."
+    )
+    doctree.append(title)
+    doctree.append(paragraph)
+
+    # Mock Sphinx app
+    class MockApp:
+        class Config:
+            master_doc = "index"
+            llms_txt_summary = None  # Not configured
+            llms_txt_file = True
+            llms_txt_filename = "llms.txt"
+            llms_txt_title = None
+            llms_txt_full_file = True
+            llms_txt_full_filename = "llms-full.txt"
+            llms_txt_full_max_size = None
+            llms_txt_directives = []
+            llms_txt_exclude = []
+            html_baseurl = ""
+
+        config = Config()
+        outdir = "/tmp/build"
+        srcdir = "/tmp/source"
+
+        class Env:
+            titles = {
+                "index": type("TitleNode", (), {"astext": lambda self: "Test Title"})()
+            }
+
+        env = Env()
+
+    app = MockApp()
+
+    # Reset the global state
+    import sphinx_llms_txt
+
+    sphinx_llms_txt._root_first_paragraph = ""
+
+    # Call doctree_resolved to extract the first paragraph
+    doctree_resolved(app, doctree, "index")
+
+    # Verify the first paragraph was extracted
+    assert (
+        sphinx_llms_txt._root_first_paragraph
+        == "This is the first paragraph that should be used as summary."
+    )
+
+    # Mock the manager methods to avoid actual file operations
+    original_combine_sources = sphinx_llms_txt._manager.combine_sources
+    sphinx_llms_txt._manager.combine_sources = lambda outdir, srcdir: None
+
+    # Call build_finished and verify the summary is set correctly
+    build_finished(app, None)
+
+    # Check that the summary was properly configured
+    assert (
+        sphinx_llms_txt._manager.config["llms_txt_summary"]
+        == "This is the first paragraph that should be used as summary."
+    )
+
+    # Restore original method
+    sphinx_llms_txt._manager.combine_sources = original_combine_sources

tests/test_path_directives.py

@@ -102,7 +102,7 @@ def test_process_path_directives_with_html_baseurl(tmp_path):
 
 
 def test_process_path_directives_absolute_urls(tmp_path):
-    """Test that absolute URLs are not modified."""
+    """Test that absolute URLs are not modified but absolute paths get base URL."""
     # Create a processor
     config = {
         "llms_txt_directives": [],
@@ -127,10 +127,17 @@ def test_process_path_directives_absolute_urls(tmp_path):
     with open(source_file, "w", encoding="utf-8") as f:
         f.write(source_content)
 
-    # Process the directives (should remain unchanged)
+    # Process the directives
     processed_content = processor._process_path_directives(source_content, source_file)
 
-    assert processed_content == source_content
+    # Expected: URLs and data URIs unchanged, absolute paths get base URL
+    expected_content = (
+        ".. image:: https://othersite.com/images/test.png\n"
+        ".. image:: https://example.com/docs/absolute/path/image.png\n"
+        ".. image:: data:image/png;base64,iVBORw0KG...\n"
+    )
+
+    assert processed_content == expected_content
 
 
 def test_process_path_directives_custom_directives(tmp_path):
@@ -251,3 +258,149 @@ def test_process_content_end_to_end(tmp_path):
     )
 
     assert processed_content == expected_content
+
+
+def test_process_path_directives_images_directory(tmp_path):
+    """Test that _images directory paths are handled correctly."""
+    # Create a processor with base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "https://example.com/docs",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create _sources directory to mimic Sphinx output
+    build_dir = tmp_path / "build"
+    build_dir.mkdir()
+    sources_dir = build_dir / "_sources"
+    sources_dir.mkdir()
+
+    # Create a source file with various _images directory paths
+    source_content = (
+        "Some content.\n"
+        ".. image:: _images/test.png\n"  # Relative _images should become /_images
+        ".. image:: /_images/absolute.png\n"  # Absolute _images should get base URL
+        ".. figure:: _images/figure.png\n"  # Test with figure directive too
+        "   :alt: A test figure\n"
+        ".. image:: images/normal.png\n"  # Normal relative path should be unchanged
+    )
+
+    # Create source file in sources directory to simulate Sphinx build output
+    source_file = sources_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: _images paths should be converted and get base URL
+    expected_content = (
+        "Some content.\n"
+        ".. image:: https://example.com/docs/_images/test.png\n"
+        ".. image:: https://example.com/docs/_images/absolute.png\n"
+        ".. figure:: https://example.com/docs/_images/figure.png\n"
+        "   :alt: A test figure\n"
+        ".. image:: https://example.com/docs/images/normal.png\n"
+    )
+
+    assert processed_content == expected_content
+
+
+def test_process_path_directives_images_directory_no_baseurl(tmp_path):
+    """
+    Test that _images directory paths work correctly without base URL.
+    Only converts when image exists.
+    """
+    # Create a processor without base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create _sources directory to mimic Sphinx output
+    build_dir = tmp_path / "build"
+    build_dir.mkdir()
+    sources_dir = build_dir / "_sources"
+    sources_dir.mkdir()
+
+    # Create _images directory and one test image
+    images_dir = build_dir / "_images"
+    images_dir.mkdir()
+    (images_dir / "test.png").write_text("fake image content")
+    # Note: absolute.png is not created, so it won't be converted
+
+    # Create a source file with _images directory paths
+    source_content = (
+        ".. image:: _images/test.png\n"  # Should become /_images (image exists)
+        ".. image:: /_images/absolute.png\n"  # Should stay unchanged (absolute path)
+    )
+
+    # Create source file in sources directory to simulate Sphinx build output
+    source_file = sources_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: only test.png gets converted because it exists in _images
+    expected_content = (
+        ".. image:: /_images/test.png\n"  # Converted because image exists
+        ".. image:: /_images/absolute.png\n"  # Absolute path unchanged
+    )
+
+    assert processed_content == expected_content
+
+
+def test_process_path_directives_all_absolute_paths_get_baseurl(tmp_path):
+    """Test that all absolute paths (starting with /) get base URL prepended."""
+    # Create a processor with base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "https://mysite.com/docs/",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create a source file with various absolute paths
+    source_content = (
+        ".. image:: /static/images/logo.png\n"
+        ".. figure:: /assets/diagrams/flow.svg\n"
+        ".. image:: /media/photos/team.jpg\n"
+        "   :alt: Team photo\n"
+        ".. image:: relative/path.png\n"  # This should still get normal processing
+    )
+
+    # Create source file
+    source_file = src_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: All absolute paths get base URL prepended
+    expected_content = (
+        ".. image:: https://mysite.com/docs/static/images/logo.png\n"
+        ".. figure:: https://mysite.com/docs/assets/diagrams/flow.svg\n"
+        ".. image:: https://mysite.com/docs/media/photos/team.jpg\n"
+        "   :alt: Team photo\n"
+        ".. image:: https://mysite.com/docs/relative/path.png\n"
+    )
+
+    assert processed_content == expected_content