# content_discovery URL: /api/discovery/content_discovery/ Section: discovery -------------------------------------------------------------------------------- content_discovery - Bengal window.BENGAL_THEME_DEFAULTS = { appearance: 'dark', palette: 'snow-lynx' }; // Progressive Enhancement System Configuration window.Bengal = window.Bengal || {}; window.Bengal.enhanceBaseUrl = '/bengal/assets/js/enhancements'; window.Bengal.watchDom = true; window.Bengal.debug = false; (function () { try { var defaults = window.BENGAL_THEME_DEFAULTS || { appearance: 'system', palette: '' }; var defaultAppearance = defaults.appearance; if (defaultAppearance === 'system') { defaultAppearance = (window.matchMedia && window.matchMedia('(prefers-color-scheme: dark)').matches) ? 'dark' : 'light'; } var storedTheme = localStorage.getItem('bengal-theme'); var storedPalette = localStorage.getItem('bengal-palette'); var theme = storedTheme ? (storedTheme === 'system' ? defaultAppearance : storedTheme) : defaultAppearance; var palette = storedPalette ?? defaults.palette; document.documentElement.setAttribute('data-theme', theme); if (palette) { document.documentElement.setAttribute('data-palette', palette); } } catch (e) { document.documentElement.setAttribute('data-theme', 'light'); } })(); Skip to main content Magnifying Glass ESC Recent Clear Magnifying Glass No results for "" Try different keywords or check your spelling Start typing to search... ↑↓ Navigate ↵ Open ESC Close Powered by Lunr ᓚᘏᗢ Documentation Info About Arrow Clockwise Get Started Note Tutorials File Text Content Palette Theming Settings Building Starburst Extending Bookmark Reference Learning Tracks Releases Dev GitHub API Reference bengal CLI Magnifying Glass Search ⌘K Palette Appearance Chevron Down Mode Monitor System Sun Light Moon Dark Palette Snow Lynx Brown Bengal Silver Bengal Charcoal Bengal Blue Bengal List ᓚᘏᗢ Magnifying Glass Search X Close Documentation Info About Arrow Clockwise Get Started Note Tutorials File Text Content Palette Theming Settings Building Starburst Extending Bookmark Reference Learning Tracks Releases Dev GitHub API Reference bengal CLI Palette Appearance Chevron Down Mode Monitor System Sun Light Moon Dark Palette Snow Lynx Brown Bengal Silver Bengal Charcoal Bengal Blue Bengal API Reference __main__ bengal Caret Right Folder Analysis community_detection graph_analysis graph_reporting graph_visualizer knowledge_graph link_suggestions link_types page_rank path_analysis performance_advisor results Caret Right Folder Assets manifest pipeline Caret Right Folder Autodoc base config docstring_parser utils virtual_orchestrator Caret Right Folder Extractors cli openapi python Caret Right Folder Models cli common openapi python Caret Right Folder Cache asset_dependency_map cache_store cacheable compression dependency_tracker page_discovery_cache query_index query_index_registry taxonomy_index utils Caret Right Folder Build Cache autodoc_tracking core file_tracking fingerprint parsed_content_cache rendered_output_cache taxonomy_index_mixin validation_cache Caret Right Folder Indexes author_index category_index date_range_index section_index Caret Right Folder Cli __main__ base site_templates utils Caret Right Folder Commands assets build clean collections config debug explain fix health init perf project serve site skeleton sources theme utils validate Caret Right Folder Graph __main__ bridges communities orphans pagerank report suggest Caret Right Folder New config presets scaffolds site wizard Caret Right Folder Helpers cli_app_loader cli_output config_validation error_handling menu_config metadata progress site_loader traceback validation Caret Right Folder Skeleton hydrator schema Caret Right Folder Templates base registry Caret Right Folder Blog template Caret Right Folder Changelog template Caret Right Folder Default template Caret Right Folder Docs template Caret Right Folder Landing template Caret Right Folder Portfolio template Caret Right Folder Resume template Caret Right Folder Collections errors loader schemas validator Caret Right Folder Config defaults deprecation directory_loader env_overrides environment feature_mappings hash loader merge origin_tracker validators Caret Right Folder Content Layer entry loaders manager source Caret Right Folder Sources github local notion rest Caret Right Folder Content Types base registry strategies Caret Right Folder Core build_context cascade_engine menu section theme Caret Right Folder Asset asset_core css_transforms Caret Right Folder Page computed content metadata navigation operations page_core proxy relationships utils Caret Right Folder Site core data discovery factories page_caches properties section_registry theme Caret Right Folder Debug base config_inspector content_migrator delta_analyzer dependency_visualizer explainer incremental_debugger models reporter shortcode_sandbox Caret Right Folder Discovery asset_discovery content_discovery Caret Right Folder Fonts downloader generator Caret Right Folder Health autofix base health_check report Caret Right Folder Linkcheck async_checker ignore_policy internal_checker models orchestrator Caret Right Folder Validators anchors assets cache config connectivity cross_ref fonts links menu navigation output performance rendering rss sitemap taxonomy tracks Caret Right Folder Directives analysis checkers constants Caret Right Folder Orchestration asset content full_to_incremental incremental menu postprocess related_posts render section static streaming taxonomy Caret Right Folder Postprocess html_output redirects rss sitemap special_pages Caret Right Folder Output Formats index_generator json_generator llm_generator lunr_index_generator txt_generator utils Caret Right Folder Rendering api_doc_enhancer asset_extractor errors jinja_utils link_transformer link_validator pygments_cache renderer template_context template_profiler validator Caret Right Folder Parsers base factory mistune native_html pygments_patch python_markdown Caret Right Folder Pipeline core output thread_local toc transforms Caret Right Folder Plugins badges cross_references inline_icon term variable_substitution Caret Right Folder Directives _icons admonitions badge base button cache cards checklist code_tabs container contracts data_table dropdown embed errors example_label fenced figure glossary icon include list_table literalinclude marimo navigation options rubric steps tabs target term terminal tokens utils validator video Caret Right Folder Template Engine asset_url core environment manifest menu url_helpers Caret Right Folder Template Functions advanced_collections advanced_strings autodoc collections content crossref data dates debug files get_page i18n icons images math_functions navigation pagination_helpers seo strings tables taxonomies theme urls Caret Right Folder Server build_handler component_preview constants dev_server live_reload pid_manager reload_controller request_handler request_logger resource_manager utils Caret Right Folder Services validation Caret Right Folder Themes config Caret Right Folder Utils atomic_write autodoc build_context build_stats build_summary cli_output css_minifier dates dotdict error_handlers file_io file_lock hashing incremental_constants js_bundler live_progress logger metadata observability page_initializer pagination path_resolver paths performance_collector performance_report profile progress retry rich_console sections swizzle text theme_registry theme_resolution thread_local traceback_config traceback_renderer url_normalization url_strategy API Reference Discovery ᗢ Caret Down Link Copy URL External Open LLM text Copy Copy LLM text Share with AI Ask Claude Ask ChatGPT Ask Gemini Ask Copilot Module discovery.content_discovery Content discovery - finds and organizes pages and sections. Robustness: Symlink loop detection via inode tracking to prevent infinite recursion Content collection validation (opt-in via collections.py) View source 1 Class Classes ContentDiscovery Discovers and organizes content files into pages and sections. Notes: - YAML errors in front matte… 14 Caret Right Discovers and organizes content files into pages and sections. Notes: YAML errors in front matter are downgraded to debug; we fall back to using the content and synthesize minimal metadata to keep the build progressing. UTF-8 BOM is stripped at read time by bengal.utils.file_io.read_text_file to avoid confusing the YAML/front matter parser. I18n dir-prefix strategy is supported (e.g., content/en/...); hidden files/dirs are skipped except _index.md. Parsing uses a thread pool for concurrency; unchanged pages can be represented as PageProxy in lazy modes. Symlink loops are detected via inode tracking to prevent infinite recursion. Content collections: When collections.py is present at project root, frontmatter is validated against schemas during discovery (fail fast). Methods 1 discover Discover all content in the content directory. Supports optional lazy loading … 2 tuple[list[Section]… Caret Right def discover(self, use_cache: bool = False, cache: Any | None = None) -> tuple[list[Section], list[Page]] Discover all content in the content directory. Supports optional lazy loading with PageProxy for incremental builds. Parameters 2 use_cache bool Whether to use PageDiscoveryCache for lazy loading cache Any | None PageDiscoveryCache instance (if use_cache=True) Returns tuple[list[Section], list[Page]] — Tuple of (sections, pages) Internal Methods 13 Caret Right __init__ Initialize content discovery. 2 None Caret Right def __init__(self, content_dir: Path, site: Any | None = None) -> None Initialize content discovery. Parameters 2 content_dir Path Root content directory site Any | None Optional Site reference for configuration access _discover_full Full discovery (current behavior) - discover all pages completely. 0 tuple[list[Section]… Caret Right def _discover_full(self) -> tuple[list[Section], list[Page]] Full discovery (current behavior) - discover all pages completely. Returns tuple[list[Section], list[Page]] — Tuple of (sections, pages) _discover_with_cache Discover content with lazy loading from cache. Uses PageProxy for unchanged pa… 1 tuple[list[Section]… Caret Right def _discover_with_cache(self, cache: Any) -> tuple[list[Section], list[Page]] Discover content with lazy loading from cache. Uses PageProxy for unchanged pages (metadata only) and parses changed pages. Parameters 1 cache Any PageDiscoveryCache instance Returns tuple[list[Section], list[Page]] — Tuple of (sections, pages) with mixed Page and PageProxy objects _cache_is_valid Check if cached metadata is still valid for a page. 2 bool Caret Right def _cache_is_valid(self, page: Page, cached_metadata: Any) -> bool Check if cached metadata is still valid for a page. Parameters 2 page Page Discovered page cached_metadata Any Cached metadata from PageDiscoveryCache Returns bool — True if cache is valid and can be used (unchanged page) _walk_directory Recursively walk a directory to discover content. Uses inode tracking to detec… 3 None Caret Right def _walk_directory(self, directory: Path, parent_section: Section, current_lang: str | None = None) -> None Recursively walk a directory to discover content. Uses inode tracking to detect and skip symlink loops. Parameters 3 directory Path Directory to walk parent_section Section Parent section to add content to current_lang str | None _is_content_file Check if a file is a content file. 1 bool Caret Right def _is_content_file(self, file_path: Path) -> bool Check if a file is a content file. Parameters 1 file_path Path Path to check Returns bool — True if it's a content file _validate_against_collection Validate frontmatter against collection schema if applicable. 2 dict[str, Any] Caret Right def _validate_against_collection(self, file_path: Path, metadata: dict[str, Any]) -> dict[str, Any] Validate frontmatter against collection schema if applicable. Parameters 2 file_path Path Path to content file metadata dict[str, Any] Parsed frontmatter metadata Returns dict[str, Any] — Validated metadata (possibly with schema-enforced defaults) _get_collection_for_file Find which collection a file belongs to based on its path. 1 tuple[str | None, C… Caret Right def _get_collection_for_file(self, file_path: Path) -> tuple[str | None, CollectionConfig[Any] | None] Find which collection a file belongs to based on its path. Parameters 1 file_path Path Path to content file Returns tuple[str | None, CollectionConfig[Any] | None] — Tuple of (collection_name, CollectionConfig) or (None, None) _create_page Create a Page object from a file with robust error handling. Handles: - Valid … 3 Page Caret Right def _create_page(self, file_path: Path, current_lang: str | None = None, section: Section | None = None) -> Page Create a Page object from a file with robust error handling. Handles: Valid frontmatter Invalid YAML in frontmatter Missing frontmatter File encoding issues IO errors Collection schema validation (when collections defined) Parameters 3 file_path Path Path to content file current_lang str | None section Section | None Returns Page — Page object (always succeeds with fallback metadata) _parse_content_file Parse content file with robust error handling. Caches raw content in BuildCont… 1 tuple[str, dict[str… Caret Right def _parse_content_file(self, file_path: Path) -> tuple[str, dict[str, Any]] Parse content file with robust error handling. Caches raw content in BuildContext for later use by validators, eliminating redundant disk I/O during health checks. Parameters 1 file_path Path Path to content file Returns tuple[str, dict[str, Any]] — Tuple of (content, metadata) _extract_content_skip_frontmatter Extract content, skipping broken frontmatter section. Frontmatter is between -… 1 str Caret Right def _extract_content_skip_frontmatter(self, file_content: str) -> str Extract content, skipping broken frontmatter section. Frontmatter is between --- delimiters at start of file. If parsing failed, skip the section entirely. Parameters 1 file_content str Full file content Returns str — Content without frontmatter section _sort_all_sections Sort all sections and their children by weight. This recursively sorts: - Page… 0 None Caret Right def _sort_all_sections(self) -> None Sort all sections and their children by weight. This recursively sorts: Pages within each section Subsections within each section Called after content discovery is complete. _sort_section_recursive Recursively sort a section and all its subsections. 1 None Caret Right def _sort_section_recursive(self, section: Section) -> None Recursively sort a section and all its subsections. Parameters 1 section Section Section to sort ← Previous asset_discovery Next → discovery List © 2025 Bengal ᓚᘏᗢ window.BENGAL_LAZY_ASSETS = { tabulator: '/bengal/assets/js/tabulator.min.js', dataTable: '/bengal/assets/js/data-table.js', mermaidToolbar: '/bengal/assets/js/mermaid-toolbar.9de5abba.js', mermaidTheme: '/bengal/assets/js/mermaid-theme.344822c5.js', graphMinimap: '/bengal/assets/js/graph-minimap.cc7e42e3.js', graphContextual: '/bengal/assets/js/graph-contextual.440e59c6.js' }; window.BENGAL_ICONS = { close: '/bengal/assets/icons/close.911d4fe1.svg', enlarge: '/bengal/assets/icons/enlarge.652035e5.svg', copy: '/bengal/assets/icons/copy.3d56e945.svg', 'download-svg': '/bengal/assets/icons/download.04f07e1b.svg', 'download-png': '/bengal/assets/icons/image.c34dfd40.svg', 'zoom-in': '/bengal/assets/icons/zoom-in.237b4a83.svg', 'zoom-out': '/bengal/assets/icons/zoom-out.38857c77.svg', reset: '/bengal/assets/icons/reset.d26dba29.svg' }; Arrow Up X -------------------------------------------------------------------------------- Metadata: - Author: lbliii - Word Count: 1887 - Reading Time: 9 minutes