Fix include paths and spacing (#31)

CHANGELOG.rst

@@ -1,6 +1,24 @@
 Changelog
 =========
 
+0.4.1
+-----
+
+- Fix include paths and spacing
+  `#31 <https://github.com/jdillard/sphinx-llms-txt/pull/31>`_
+
+0.4.0
+-----
+
+- Add support for including source code files with :confval:`llms_txt_code_files` and :confval:`llms_txt_code_base_path` configuration options
+  `#24 <https://github.com/jdillard/sphinx-llms-txt/pull/24>`_
+
+0.3.2
+-----
+
+- Fix image paths to deployed images
+  `#30 <https://github.com/jdillard/sphinx-llms-txt/pull/30>`_
+
 0.3.1
 -----
 

docs/source/advanced-configuration.rst

@@ -125,6 +125,50 @@ You can exclude specific pages from being included in the generated files:
 
 This is useful for excluding auto-generated pages, indexes, or content that isn't relevant for LLM consumption.
 
+.. _including_code_files:
+
+Including Source Code Files
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+You can include source code files from your project at the end of :confval:`llms_txt_full_filename`.
+
+Use include/exclude syntax to precisely control which files are included:
+
+.. code-block:: python
+
+   llms_txt_code_files = [
+       "+:src/**/*.py",           # Include all Python files in src
+       "-:src/**/__pycache__/**", # Exclude Python cache files
+   ]
+
+Pattern syntax:
+
+- **+:pattern**: Include files matching the pattern. Processed first to collect matching files.
+- **-:pattern**: Exclude files matching the pattern. Applied to filter out unwanted files.
+
+Code files are processed as follows:
+
+- **Glob patterns**: Use standard glob patterns (``*``, ``**``, ``?``) to match files
+- **Relative paths**: Patterns are resolved relative to your Sphinx source directory
+- **Formatting**: Each file is presented with a title and syntax-highlighted code block
+
+.. _customizing_code_paths:
+
+Customizing Code File Paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default, the extension automatically detects the relative path from your Sphinx source directory to the git root and strips that prefix from displayed file paths. You can customize this behavior:
+
+.. code-block:: python
+
+   # Manually specify base path to strip
+   llms_txt_code_base_path = "../../"
+
+   # Disable path stripping entirely
+   llms_txt_code_base_path = ""
+
+This helps create cleaner, more readable file paths in the generated documentation.
+
 .. _using_html_baseurl:
 
 Using HTML Base URL
@@ -168,3 +212,11 @@ Here's a complete example showing multiple :doc:`configuration-values`:
 
    # Content filtering
    llms_txt_exclude = ["search", "genindex", "404", "private_*"]
+
+   # Source code inclusion with include/exclude patterns
+   llms_txt_code_files = [
+       "+:../../src/**/*.py",           # Include Python files
+       "+:../../config/*.yaml",         # Include config files
+       "-:../../src/**/__pycache__/**", # Exclude cache files
+   ]
+   llms_txt_code_base_path = "../../"

docs/source/conf.py

@@ -15,6 +15,7 @@ import subprocess
 project = "sphinx-llms-txt"
 copyright = "Jared Dillard"
 author = "Jared Dillard"
+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.

docs/source/configuration-values.rst

@@ -82,3 +82,22 @@ Project Configuration Values
      See :ref:`excluding_content`.
 
    .. versionadded:: 0.2.1
+
+.. confval:: llms_txt_code_files
+
+   - **Type**: list of strings
+   - **Default**: ``[]``
+   - **Description**: A list of glob patterns that appends source code files to :confval:`llms_txt_full_filename`.
+     See :ref:`including_code_files`.
+
+   .. versionadded:: 0.4.0
+
+.. confval:: llms_txt_code_base_path
+
+   - **Type**: string or ``None``
+   - **Default**: ``None`` (auto-detect from git root)
+   - **Description**: Base path to strip from code file paths when displaying titles.
+     When ``None``, automatically detects the relative path from the Sphinx source
+     directory to the git root and strips that prefix from file paths.
+
+   .. versionadded:: 0.4.0

sphinx_llms_txt/__init__.py

@@ -12,7 +12,7 @@ from .manager import LLMSFullManager
 from .processor import DocumentProcessor
 from .writer import FileWriter
 
-__version__ = "0.3.1"
+__version__ = "0.4.1"
 
 # Export classes needed by tests
 __all__ = [
@@ -76,6 +76,8 @@ def build_finished(app: Sphinx, exception):
             "llms_txt_full_max_size": app.config.llms_txt_full_max_size,
             "llms_txt_directives": app.config.llms_txt_directives,
             "llms_txt_exclude": app.config.llms_txt_exclude,
+            "llms_txt_code_files": app.config.llms_txt_code_files,
+            "llms_txt_code_base_path": app.config.llms_txt_code_base_path,
             "html_baseurl": getattr(app.config, "html_baseurl", ""),
         }
         _manager.set_config(config)
@@ -104,6 +106,8 @@ def setup(app: Sphinx) -> Dict[str, Any]:
     app.add_config_value("llms_txt_title", None, "env")
     app.add_config_value("llms_txt_summary", None, "env")
     app.add_config_value("llms_txt_exclude", [], "env")
+    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)

sphinx_llms_txt/manager.py

@@ -2,8 +2,10 @@
 Main manager module for sphinx-llms-txt.
 """
 
+import glob
+import subprocess
 from pathlib import Path
-from typing import Any, Dict, Optional, Tuple
+from typing import Any, Dict, List, Optional, Tuple
 
 from sphinx.application import Sphinx
 from sphinx.environment import BuildEnvironment
@@ -16,6 +18,104 @@ from .writer import FileWriter
 logger = logging.getLogger(__name__)
 
 
+def _get_git_root(path: Path) -> Optional[Path]:
+    """Get the git root directory for a given path."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--show-toplevel"],
+            cwd=path,
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+        return Path(result.stdout.strip())
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        return None
+
+
+def _get_language_from_extension(file_path: Path) -> str:
+    """Map file extension to language identifier for code blocks."""
+    extension_map = {
+        ".py": "python",
+        ".js": "javascript",
+        ".jsx": "jsx",
+        ".ts": "typescript",
+        ".tsx": "tsx",
+        ".java": "java",
+        ".c": "c",
+        ".cpp": "cpp",
+        ".cc": "cpp",
+        ".cxx": "cpp",
+        ".h": "c",
+        ".hpp": "cpp",
+        ".cs": "csharp",
+        ".php": "php",
+        ".rb": "ruby",
+        ".go": "go",
+        ".rs": "rust",
+        ".swift": "swift",
+        ".kt": "kotlin",
+        ".scala": "scala",
+        ".sh": "bash",
+        ".bash": "bash",
+        ".zsh": "zsh",
+        ".fish": "fish",
+        ".ps1": "powershell",
+        ".html": "html",
+        ".htm": "html",
+        ".xml": "xml",
+        ".css": "css",
+        ".scss": "scss",
+        ".sass": "sass",
+        ".less": "less",
+        ".json": "json",
+        ".yaml": "yaml",
+        ".yml": "yaml",
+        ".toml": "toml",
+        ".ini": "ini",
+        ".cfg": "ini",
+        ".conf": "ini",
+        ".sql": "sql",
+        ".md": "markdown",
+        ".rst": "rst",
+        ".txt": "text",
+        ".dockerfile": "dockerfile",
+        ".dockerignore": "text",
+        ".gitignore": "text",
+        ".gitattributes": "text",
+        ".editorconfig": "ini",
+        ".makefile": "makefile",
+        ".r": "r",
+        ".R": "r",
+        ".m": "matlab",
+        ".pl": "perl",
+        ".lua": "lua",
+        ".vim": "vim",
+        ".vimrc": "vim",
+        ".proto": "protobuf",
+        ".thrift": "thrift",
+        ".graphql": "graphql",
+        ".gql": "graphql",
+    }
+
+    # Get the extension from the file path
+    ext = file_path.suffix.lower()
+
+    # Handle special cases like Makefile, Dockerfile without extension
+    if not ext:
+        name = file_path.name.lower()
+        if name in ["makefile", "gnumakefile"]:
+            return "makefile"
+        elif name in ["dockerfile", "dockerfile.dev", "dockerfile.prod"]:
+            return "dockerfile"
+        elif name.startswith("dockerfile."):
+            return "dockerfile"
+        else:
+            return "text"
+
+    return extension_map.get(ext, "text")
+
+
 class LLMSFullManager:
     """Manages the collection and ordering of documentation sources."""
 
@@ -163,9 +263,15 @@ class LLMSFullManager:
         # Generate content
         content_parts = []
 
+        # Track code files for later processing
+        code_file_parts = []
+
+        # Count lines in code files (initially 0)
+        code_files_line_count = 0
+
         # Add pages in order
         added_files = set()
-        total_line_count = 0
+        total_line_count = code_files_line_count
         max_lines = self.config.get("llms_txt_full_max_size")
         abort_due_to_max_lines = False
 
@@ -277,6 +383,37 @@ class LLMSFullManager:
                     content_parts.append(content)
                     total_line_count += line_count
 
+        # Process code files at the end if configured
+        if not abort_due_to_max_lines:
+            code_file_parts, processed_file_paths = self._process_code_files()
+            code_files_line_count = sum(
+                part.count("\n") + 1 for part in code_file_parts
+            )
+
+            # Check if adding code files would exceed the maximum line count
+            max_lines = self.config.get("llms_txt_full_max_size")
+            if (
+                max_lines is not None
+                and total_line_count + code_files_line_count > max_lines
+            ):
+                logger.warning(
+                    f"sphinx-llms-txt: Adding code files would exceed max line limit "
+                    f"({max_lines}). Current: {total_line_count}, "
+                    f"Code files: {code_files_line_count}. Skipping code files."
+                )
+            else:
+                # Add source code files section if there are any code files
+                if code_file_parts:
+                    section_header = self._create_code_files_section_header(
+                        processed_file_paths
+                    )
+                    content_parts.append(section_header)
+                    content_parts.extend(code_file_parts)
+                    # Add line count for the section header too
+                    total_line_count += (
+                        code_files_line_count + section_header.count("\n") + 1
+                    )
+
         # Check if line limit was exceeded before creating the file
         max_lines = self.config.get("llms_txt_full_max_size")
         if abort_due_to_max_lines or (
@@ -370,3 +507,309 @@ class LLMSFullManager:
             return source_suffix
         else:
             return [source_suffix]  # String format
+
+    def _process_code_files(self) -> Tuple[List[str], List[Path]]:
+        """Process code files specified in llms_txt_code_files configuration.
+
+        Supports include/exclude patterns with +:/- : prefixes:
+        - '+:pattern' = include files matching pattern
+        - '-:pattern' = exclude files matching pattern
+        - 'pattern' (no prefix) = ignored (no special handling)
+
+        Returns:
+            Tuple of (formatted code block strings, list of processed file paths)
+        """
+        code_file_patterns = self.config.get("llms_txt_code_files", [])
+        if not code_file_patterns:
+            return [], []
+
+        # Parse patterns into include and exclude lists
+        include_patterns = []
+        exclude_patterns = []
+
+        for pattern in code_file_patterns:
+            if pattern.startswith("-:"):
+                exclude_patterns.append(pattern[2:])  # Remove the '-:' prefix
+            elif pattern.startswith("+:"):
+                include_patterns.append(pattern[2:])  # Remove the '+:' prefix
+            else:
+                # No prefix = log warning about ignored pattern
+                logger.warning(
+                    f"sphinx-llms-txt: Code file pattern '{pattern}' ignored."
+                    f"Use '+:{pattern}' to include or '-:{pattern}' to exclude."
+                )
+
+        # If no include patterns specified, nothing to process
+        if not include_patterns:
+            return [], []
+
+        code_parts = []
+        processed_files = set()
+        all_matching_files = set()
+
+        # First, collect all files matching include patterns
+        for pattern in include_patterns:
+            # Resolve pattern relative to source directory
+            if self.srcdir:
+                pattern_path = Path(self.srcdir) / pattern
+            else:
+                pattern_path = Path(pattern)
+
+            # Use glob to find matching files
+            matching_files = glob.glob(str(pattern_path), recursive=True)
+
+            for file_path_str in matching_files:
+                file_path = Path(file_path_str)
+                if file_path.is_file():  # Only add files, not directories
+                    all_matching_files.add(file_path.resolve())
+
+        # Filter out files matching exclude patterns
+        filtered_files = set()
+        for file_path in all_matching_files:
+            should_exclude = False
+
+            for exclude_pattern in exclude_patterns:
+                # Resolve exclude pattern relative to source directory
+                if self.srcdir:
+                    exclude_pattern_path = Path(self.srcdir) / exclude_pattern
+                else:
+                    exclude_pattern_path = Path(exclude_pattern)
+
+                # Check if this file matches the exclude pattern
+                exclude_matches = glob.glob(str(exclude_pattern_path), recursive=True)
+                if str(file_path) in exclude_matches:
+                    should_exclude = True
+                    logger.debug(
+                        f"sphinx-llms-txt: Excluding code file: {file_path} "
+                        f"(matched pattern: {exclude_pattern})"
+                    )
+                    break
+
+            if not should_exclude:
+                filtered_files.add(file_path)
+
+        # Sort files for consistent ordering
+        sorted_files = sorted(filtered_files)
+
+        for file_path in sorted_files:
+            # Skip if already processed (shouldn't happen with set, but safety check)
+            if file_path in processed_files:
+                continue
+
+            try:
+                # Read the file content
+                with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+                    content = f.read()
+
+                # Get language identifier
+                language = _get_language_from_extension(file_path)
+
+                # Get relative path from source directory for title
+                if self.srcdir:
+                    try:
+                        title = file_path.relative_to(Path(self.srcdir))
+
+                        # Strip base path if configured,
+                        # or auto-detect from git root
+                        base_path = self.config.get("llms_txt_code_base_path")
+                        if base_path is None:
+                            # Auto-detect: try to make path relative to git root
+                            git_root = _get_git_root(Path(self.srcdir))
+                            if git_root:
+                                try:
+                                    # Get srcdir relative to git root
+                                    srcdir_relative = Path(self.srcdir).relative_to(
+                                        git_root
+                                    )
+                                    # Calculate relative path from srcdir to
+                                    # git root
+                                    if srcdir_relative != Path("."):
+                                        # Count directory levels to go up
+                                        up_levels = len(srcdir_relative.parts)
+                                        base_path = "../" * up_levels
+                                    else:
+                                        base_path = None
+                                except ValueError:
+                                    base_path = None
+
+                        if base_path:
+                            title_str = str(title)
+                            if title_str.startswith(base_path):
+                                title = Path(title_str[len(base_path) :])
+                    except ValueError:
+                        # File is not relative to srcdir, use filename
+                        title = file_path.name
+                else:
+                    title = file_path.name
+
+                # Format as code block with equals underline
+                title_str = str(title)
+                equals_line = "=" * len(title_str)
+
+                # Indent the content for reStructuredText code-block directive
+                indented_content = "\n".join(
+                    f"   {line}" if line.strip() else ""
+                    for line in content.splitlines()
+                )
+
+                code_block = f"""
+{title_str}
+{equals_line}
+
+.. code-block:: {language}
+
+{indented_content}"""
+                code_parts.append(code_block)
+
+                processed_files.add(file_path)
+                logger.debug(f"sphinx-llms-txt: Added code file: {title}")
+
+            except Exception as e:
+                logger.warning(
+                    f"sphinx-llms-txt: Error reading code file {file_path}: {e}"
+                )
+                continue
+
+        return code_parts, sorted(processed_files)
+
+    def _create_code_files_section_header(self, file_paths: List[Path] = None) -> str:
+        """Create the section header for source code files.
+
+        Args:
+            file_paths: List of file paths that were added to generate tree view
+
+        Returns:
+            String containing the section header with title, underlines, description,
+            and file tree
+        """
+        section_title = "Source Code Files"
+        star_line = "*" * len(section_title)
+
+        description = "This section contains source code files from the project repository. These files are included to provide implementation context and technical details that complement the documentation above."  # noqa: E501
+
+        header = f"""
+{star_line}
+{section_title}
+{star_line}
+
+{description}"""
+
+        # Add file tree if file paths are provided
+        if file_paths:
+            tree_display = self._generate_file_tree(file_paths)
+            header += f"""
+
+**Files included:**
+
+.. code-block:: text
+
+{tree_display}"""
+
+        return header
+
+    def _generate_file_tree(self, file_paths: List[Path]) -> str:
+        """Generate a tree-like representation of file paths.
+
+        Args:
+            file_paths: List of file paths to display in tree format
+
+        Returns:
+            String containing indented tree representation of the files
+        """
+        if not file_paths:
+            return ""
+
+        # Convert to relative paths if possible and create tree structure
+        tree_data = {}
+
+        for file_path in sorted(file_paths):
+            # Get relative path from source directory for display
+            if self.srcdir:
+                try:
+                    rel_path = file_path.relative_to(Path(self.srcdir))
+
+                    # Apply base path stripping logic similar to code processing
+                    base_path = self.config.get("llms_txt_code_base_path")
+                    if base_path is None:
+                        # Auto-detect: try to make path relative to git root
+                        git_root = _get_git_root(Path(self.srcdir))
+                        if git_root:
+                            try:
+                                # Get srcdir relative to git root
+                                srcdir_relative = Path(self.srcdir).relative_to(
+                                    git_root
+                                )
+                                # Calculate relative path from srcdir to git root
+                                if srcdir_relative != Path("."):
+                                    # Count directory levels to go up
+                                    up_levels = len(srcdir_relative.parts)
+                                    base_path = "../" * up_levels
+                                else:
+                                    base_path = None
+                            except ValueError:
+                                base_path = None
+
+                    if base_path:
+                        rel_path_str = str(rel_path)
+                        if rel_path_str.startswith(base_path):
+                            rel_path = Path(rel_path_str[len(base_path) :])
+
+                except ValueError:
+                    # File is not relative to srcdir, use filename
+                    rel_path = Path(file_path.name)
+            else:
+                rel_path = Path(file_path.name)
+
+            # Build nested dictionary structure
+            parts = rel_path.parts
+            current = tree_data
+            for part in parts[:-1]:  # All but the last part (directories)
+                if part not in current:
+                    current[part] = {}
+                current = current[part]
+
+            # Add the file (last part)
+            if parts:
+                current[parts[-1]] = None  # None indicates it's a file
+
+        # Convert tree structure to string representation
+        lines = []
+        self._format_tree_node(tree_data, lines, "", True)
+
+        # Indent each line for reStructuredText code block
+        indented_lines = [f"   {line}" for line in lines]
+        return "\n".join(indented_lines)
+
+    def _format_tree_node(
+        self, node: dict, lines: List[str], prefix: str, is_root: bool
+    ):
+        """Recursively format tree nodes into lines with proper tree characters.
+
+        Args:
+            node: Dictionary representing the tree structure
+            lines: List to append formatted lines to
+            prefix: Current prefix for indentation and tree characters
+            is_root: Whether this is the root level (no tree characters)
+        """
+        if not node:
+            return
+
+        items = sorted(node.items())
+
+        for i, (name, subtree) in enumerate(items):
+            is_last = i == len(items) - 1
+
+            if is_root:
+                # Root level - no tree characters
+                current_prefix = ""
+                next_prefix = ""
+            else:
+                # Use tree characters
+                current_prefix = prefix + ("└── " if is_last else "├── ")
+                next_prefix = prefix + ("    " if is_last else "│   ")
+
+            lines.append(current_prefix + name)
+
+            # Recursively handle subdirectories
+            if subtree is not None:  # It's a directory
+                self._format_tree_node(subtree, lines, next_prefix, False)

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
+            # Handle URLs and data URIs - leave unchanged
-            if not self._is_absolute_or_url(path):
+            if path.startswith(("http://", "https://", "data:")):
-                # Special case for test files
+                return match.group(0)
-                if is_test:
+
-                    # Add subdir/ prefix to match test expectations
+            # For ALL paths, check if image exists in _images first
-                    full_path = "subdir/" + path
+            # 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)
+            # Fallback for relative paths - add base URL if configured
-                elif "_sources" in str(source_path):
+            else:
-                    # Extract the part after _sources/
+                full_path = self._add_base_url(path, base_url)
-                    rel_doc_path, rel_doc_dir, rel_doc_path_parts = (
+                return f"{prefix}{full_path}"
-                        self._extract_relative_document_path(source_path)
-                    )
 
-                    if rel_doc_path_parts:
+            # If we couldn't resolve the path, return unchanged
-                        # 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
             return match.group(0)
 
         # Replace directive paths in the content
@@ -201,9 +243,12 @@ class DocumentProcessor:
         """
         possible_paths = []
 
-        # If it's an absolute path, use it directly
+        # If it's an absolute path, treat it as relative to srcdir
         if os.path.isabs(include_path):
-            possible_paths.append(Path(include_path))
+            # Remove the leading slash and treat as relative to srcdir
+            relative_path = include_path.lstrip("/")
+            if self.srcdir:
+                possible_paths.append((Path(self.srcdir) / relative_path).resolve())
         else:
             # Relative to the source file (in _sources directory)
             possible_paths.append((source_path.parent / include_path).resolve())
@@ -244,6 +289,9 @@ class DocumentProcessor:
         # Function to replace each include with content
         def replace_include(match):
             include_path = match.group(3)
+            directive_part = match.group(
+                1
+            )  # The ".. include:: " part with leading whitespace
 
             # Get all possible paths to try
             possible_paths = self._resolve_include_paths(include_path, source_path)
@@ -254,7 +302,18 @@ class DocumentProcessor:
                     if path_to_try.exists():
                         with open(path_to_try, "r", encoding="utf-8") as f:
                             included_content = f.read()
-                        return included_content
+
+                        # Find where the actual directive starts, after any whitespace
+                        directive_start = directive_part.find("..")
+                        if directive_start > 0:
+                            # There's leading whitespace/newlines before the directive
+                            leading_part = directive_part[:directive_start]
+                            # Replace directive with content, preserving the structure
+                            return leading_part + included_content
+                        else:
+                            # No leading whitespace, just return the content
+                            return included_content
+
                 except Exception as e:
                     logger.error(
                         f"sphinx-llms-txt: Error reading include file {path_to_try}:"
@@ -266,7 +325,14 @@ class DocumentProcessor:
             paths_tried = ", ".join(str(p) for p in possible_paths)
             logger.warning(f"sphinx-llms-txt: Include file not found: {include_path}")
             logger.debug(f"sphinx-llms-txt: Tried paths: {paths_tried}")
-            return f"[Include file not found: {include_path}]"
+
+            # Preserve spacing structure for error message too
+            directive_start = match.group(1).find("..")
+            if directive_start > 0:
+                leading_part = match.group(1)[:directive_start]
+                return leading_part + f"[Include file not found: {include_path}]"
+            else:
+                return f"[Include file not found: {include_path}]"
 
         # Replace all includes with their content
         processed_content = include_pattern.sub(replace_include, content)

tests/test_llms_txt.py

@@ -764,6 +764,8 @@ def test_summary_default_uses_first_paragraph():
             llms_txt_full_max_size = None
             llms_txt_directives = []
             llms_txt_exclude = []
+            llms_txt_code_files = []
+            llms_txt_code_base_path = None
             html_baseurl = ""
 
         config = Config()
@@ -808,3 +810,187 @@ def test_summary_default_uses_first_paragraph():
 
     # Restore original method
     sphinx_llms_txt._manager.combine_sources = original_combine_sources
+
+
+def test_code_files_include_exclude_patterns(tmp_path):
+    """Test the +/- pattern syntax for llms_txt_code_files configuration."""
+    from sphinx_llms_txt.manager import LLMSFullManager
+
+    # Create test directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+
+    docs_dir = src_dir / "docs"
+    docs_dir.mkdir()
+
+    cache_dir = docs_dir / "__pycache__"
+    cache_dir.mkdir()
+
+    # Create test files
+    (docs_dir / "example.rst").write_text("Example RST content")
+    (docs_dir / "guide.rst").write_text("Guide RST content")
+    (docs_dir / "backup.bak").write_text("Backup file content")
+    (cache_dir / "compiled.pyc").write_text("Compiled Python")
+
+    # Create manager and set source directory
+    manager = LLMSFullManager()
+    manager.srcdir = str(src_dir)
+
+    # Test configuration with include/exclude patterns
+    config = {
+        "llms_txt_code_files": [
+            "+:docs/**/*.rst",  # Include all RST files in docs
+            "-:docs/**/__pycache__/**",  # Exclude pycache files
+            "-:docs/**/*.bak",  # Exclude backup files
+        ]
+    }
+    manager.set_config(config)
+
+    # Process code files
+    code_parts, _ = manager._process_code_files()
+
+    # Verify we have the expected number of files
+    assert len(code_parts) == 2, f"Expected 2 files, got {len(code_parts)}"
+
+    # Extract file titles from code blocks
+    titles = []
+    for part in code_parts:
+        lines = part.strip().split("\n")
+        if lines:
+            titles.append(lines[0])
+
+    # Verify expected files are included
+    assert "docs/example.rst" in titles
+    assert "docs/guide.rst" in titles
+
+    # Verify excluded files are not present
+    content = "\n".join(code_parts)
+    assert "backup.bak" not in content
+    assert "__pycache__" not in content
+    assert "compiled.pyc" not in content
+
+
+def test_code_files_exclude_only_patterns(tmp_path):
+    """Test that exclude-only patterns result in no files being included."""
+    from sphinx_llms_txt.manager import LLMSFullManager
+
+    # Create test directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+
+    docs_dir = src_dir / "docs"
+    docs_dir.mkdir()
+
+    # Create test files
+    (docs_dir / "example.rst").write_text("Example RST content")
+
+    # Create manager and set source directory
+    manager = LLMSFullManager()
+    manager.srcdir = str(src_dir)
+
+    # Test configuration with only exclude patterns
+    config = {
+        "llms_txt_code_files": [
+            "-:docs/**/*.rst",  # Only exclude pattern, no includes
+        ]
+    }
+    manager.set_config(config)
+
+    # Process code files
+    code_parts, _ = manager._process_code_files()
+
+    # Should have no files with exclude-only patterns
+    assert len(code_parts) == 0, "Should have no files with exclude-only patterns"
+
+
+def test_code_files_no_prefix_patterns(tmp_path):
+    """Test that patterns without prefix are ignored."""
+    from sphinx_llms_txt.manager import LLMSFullManager
+
+    # Create test directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+
+    docs_dir = src_dir / "docs"
+    docs_dir.mkdir()
+
+    # Create test files
+    (docs_dir / "example.rst").write_text("Example RST content")
+    (docs_dir / "backup.bak").write_text("Backup file content")
+
+    # Create manager and set source directory
+    manager = LLMSFullManager()
+    manager.srcdir = str(src_dir)
+
+    # Test configuration with no prefix (should be ignored)
+    config = {
+        "llms_txt_code_files": [
+            "docs/**/*.rst",  # No prefix = ignored
+            "+:docs/**/*.rst",  # Include RST files
+            "-:docs/**/*.bak",  # Exclude backup files
+        ]
+    }
+    manager.set_config(config)
+
+    # Process code files
+    code_parts, _ = manager._process_code_files()
+
+    # Should include RST files (from +: pattern) and exclude BAK files (from -: pattern)
+    assert len(code_parts) == 1, "Should include RST files and exclude BAK files"
+
+    content = "\n".join(code_parts)
+    assert "Example RST content" in content
+    assert "backup.bak" not in content
+
+
+def test_code_files_ignored_patterns(tmp_path, caplog):
+    """Test that patterns without +: or -: prefix log a warning and are ignored."""
+    from unittest.mock import patch
+
+    from sphinx_llms_txt.manager import LLMSFullManager
+
+    # Create test directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+
+    docs_dir = src_dir / "docs"
+    docs_dir.mkdir()
+
+    # Create test files
+    (docs_dir / "example.rst").write_text("Example RST content")
+
+    # Use a mock to capture the warning message directly
+    captured_warnings = []
+
+    def capture_warning(message, *args, **kwargs):
+        captured_warnings.append(message)
+
+    # Patch the logger to capture warnings
+    with patch("sphinx_llms_txt.manager.logger.warning", side_effect=capture_warning):
+        # Create manager and set source directory
+        manager = LLMSFullManager()
+        manager.srcdir = str(src_dir)
+
+        # Test configuration with only no-prefix patterns (should result in no files)
+        config = {
+            "llms_txt_code_files": [
+                "docs/**/*.rst",  # No prefix = ignored with warning
+            ]
+        }
+        manager.set_config(config)
+
+        # Process code files
+        code_parts, _ = manager._process_code_files()
+
+    # Should have no files since the pattern without prefix is ignored
+    assert (
+        len(code_parts) == 0
+    ), "Should have no files when only using patterns without prefix"
+
+    # Check that a warning was logged
+    assert (
+        len(captured_warnings) == 1
+    ), f"Expected 1 warning, got {len(captured_warnings)}"
+    assert (
+        "Code file pattern 'docs/**/*.rst' ignored." in captured_warnings[0]
+    ), f"Warning message should contain expected text. Got: {captured_warnings[0]}"

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