Merge branch 'main' into feature/add-mypy

.pre-commit-config.yaml

@@ -18,6 +18,13 @@ 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:

sphinx_llms_txt/__init__.py

@@ -107,7 +107,7 @@ def build_finished(app: Sphinx, exception):
                     _manager.update_page_title(docname, title)
 
         # Create the combined file
-        _manager.combine_sources(app.outdir, app.srcdir)
+        _manager.combine_sources(str(app.outdir), str(app.srcdir))
 
 
 def setup(app: Sphinx) -> Dict[str, Any]:

sphinx_llms_txt/collector.py

@@ -3,7 +3,7 @@ Document collector module for sphinx-llms-txt.
 """
 
 import fnmatch
-from typing import Any, Dict, List, Tuple
+from typing import Any, Dict, List, Optional, 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: str = None
-        self.env: BuildEnvironment = None
+        self.master_doc: Optional[str] = None
+        self.env: Optional[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) -> str:
+    def _get_docname_suffix(self, docname: str, sources_dir) -> Optional[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, str]]:
+    def get_page_order(self, sources_dir=None) -> List[Tuple[str, Optional[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 = []
+        page_order: List[Tuple[str, Optional[str]]] = []
         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 = None
+                suffix: Optional[str] = None
                 if sources_dir:
                     suffix = self._get_docname_suffix(docname, sources_dir)
                 page_order.append((docname, suffix))
@@ -135,18 +135,21 @@ class DocumentCollector:
             try:
                 # Look for toctree_includes which contains the direct children
                 if (
-                    hasattr(self.env, "toctree_includes")
+                    self.env
+                    and hasattr(self.env, "toctree_includes")
                     and docname in self.env.toctree_includes
                 ):
                     for child_docname in self.env.toctree_includes[docname]:
-                        collect_from_toctree(child_docname)
+                        collect_from_toctree(str(child_docname))
                 # Try to use dependencies to find related documents
                 elif (
-                    hasattr(self.env, "dependencies")
+                    self.env
+                    and hasattr(self.env, "dependencies")
                     and docname in self.env.dependencies
                 ):
                     # Extract the dependent documents from the dependencies dict
-                    for child_docname in self.env.dependencies[docname]:
+                    for child_docname_obj in self.env.dependencies[docname]:
+                        child_docname = str(child_docname_obj)
                         # Only add documents actually in the document set
                         if (
                             hasattr(self.env, "all_docs")
@@ -154,7 +157,11 @@ class DocumentCollector:
                         ):
                             collect_from_toctree(child_docname)
                 # Fallback to titles or other available references
-                elif hasattr(self.env, "titles") and hasattr(self.env, "all_docs"):
+                elif (
+                    self.env
+                    and hasattr(self.env, "titles")
+                    and hasattr(self.env, "all_docs")
+                ):
                     # Get all document names
                     all_docnames = list(self.env.all_docs.keys())
 
@@ -185,7 +192,7 @@ class DocumentCollector:
                 ]
             )
             for docname in remaining:
-                suffix = None
+                suffix: Optional[str] = None
                 if sources_dir:
                     suffix = self._get_docname_suffix(docname, sources_dir)
                 page_order.append((docname, suffix))
@@ -193,8 +200,8 @@ class DocumentCollector:
         return page_order
 
     def filter_excluded_pages(
-        self, page_order: List[Tuple[str, str]]
-    ) -> List[Tuple[str, str]]:
+        self, page_order: List[Tuple[str, Optional[str]]]
+    ) -> List[Tuple[str, Optional[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
+from typing import Any, Dict, List, Optional, Tuple, Union, cast
 
 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, str]]]
-    ) -> Union[List[str], List[Tuple[str, str]]]:
+        self, page_order: Union[List[str], List[Tuple[str, Optional[str]]]]
+    ) -> Union[List[str], List[Tuple[str, Optional[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 filtered_pages
+        return cast(Union[List[str], List[Tuple[str, Optional[str]]]], filtered_pages)
 
     def set_config(self, config: Dict[str, Any]):
         """Set configuration options."""
@@ -225,7 +225,7 @@ class LLMSFullManager:
 
         # Determine output file name and location
         output_filename = self.config.get("llms_txt_full_filename")
-        output_path = Path(outdir) / output_filename
+        output_path = Path(outdir) / str(output_filename)
 
         # Log discovered files and page order
         logger.debug(f"sphinx-llms-txt: Page order (after exclusion): {page_order}")
@@ -286,7 +286,7 @@ class LLMSFullManager:
         content_parts = []
 
         # Track code files for later processing
-        code_file_parts = []
+        code_file_parts: List[str] = []
 
         # Count lines in code files (initially 0)
         code_files_line_count = 0
@@ -365,7 +365,7 @@ 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 = []
+            all_source_files: List[Path] = []
             for src_suffix in source_suffixes:
                 # Avoid duplicate extensions when source_suffix == source_link_suffix
                 if src_suffix == source_link_suffix:
@@ -735,9 +735,9 @@ class LLMSFullManager:
                                 title = Path(title_str[len(base_path) :])
                     except ValueError:
                         # File is not relative to srcdir, use filename
-                        title = file_path.name
+                        title = Path(file_path.name)
                 else:
-                    title = file_path.name
+                    title = Path(file_path.name)
 
                 # Format as code block with equals underline
                 title_str = str(title)
@@ -769,7 +769,9 @@ class LLMSFullManager:
 
         return code_parts, sorted(processed_files)
 
-    def _create_code_files_section_header(self, file_paths: List[Path] = None) -> str:
+    def _create_code_files_section_header(
+        self, file_paths: Optional[List[Path]] = None
+    ) -> str:
         """Create the section header for source code files.
 
         Args:
@@ -817,7 +819,7 @@ class LLMSFullManager:
             return ""
 
         # Convert to relative paths if possible and create tree structure
-        tree_data = {}
+        tree_data: Dict[str, Any] = {}
 
         for file_path in sorted(file_paths):
             # Get relative path from source directory for display
@@ -870,7 +872,7 @@ class LLMSFullManager:
                 current[parts[-1]] = None  # None indicates it's a file
 
         # Convert tree structure to string representation
-        lines = []
+        lines: List[str] = []
         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")
+        custom_path_directives = self.config.get("llms_txt_directives") or []
         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, Tuple, Union
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from sphinx.application import Sphinx
 from sphinx.util import logging
@@ -14,7 +14,12 @@ logger = logging.getLogger(__name__)
 class FileWriter:
     """Handles writing processed content to output files."""
 
-    def __init__(self, config: Dict[str, Any], outdir: str = None, app: Sphinx = None):
+    def __init__(
+        self,
+        config: Dict[str, Any],
+        outdir: Optional[str] = None,
+        app: Optional[Sphinx] = None,
+    ):
         self.config = config
         self.outdir = outdir
         self.app = app
@@ -47,7 +52,7 @@ class FileWriter:
 
     def write_verbose_info_to_file(
         self,
-        page_order: Union[List[str], List[Tuple[str, str]]],
+        page_order: Union[List[str], List[Tuple[str, Optional[str]]]],
         page_titles: Dict[str, str],
         total_line_count: int = 0,
     ) -> bool:
@@ -67,13 +72,13 @@ class FileWriter:
             )
             return False
 
-        output_path = Path(self.outdir) / self.config.get("llms_txt_filename")
+        output_path = Path(self.outdir) / str(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 = self.config.get("llms_txt_title")
+                    project_name = str(self.config.get("llms_txt_title"))
                 # Second priority: use project name from Sphinx app if available
                 elif (
                     self.app