# taxonomy_index URL: /api/cache/taxonomy_index/ Section: cache -------------------------------------------------------------------------------- taxonomy_index - 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 Cache 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 cache.taxonomy_index Taxonomy Index for incremental builds. Maintains persistent index of tag-to-pages mappings to enable incremental taxonomy updates. Instead of rebuilding the entire taxonomy structure, incremental builds can update only affected tags. Architecture: Mapping: tag_slug → [page_paths] (which pages have which tags) Storage: .bengal/taxonomy_index.json (compact format) Tracking: Built during page discovery, updated on tag changes Incremental: Only update affected tags, reuse unchanged tags Performance Impact: Taxonomy rebuild skipped for unchanged pages (~60ms saved per 100 pages) Only affected tags regenerated Avoid full taxonomy structure rebuild View source 2 Classes Classes TagEntry dataclass Entry for a single tag in the index. Implements the Cacheable protocol for type-safe serialization. 4 Caret Right Entry for a single tag in the index. Implements the Cacheable protocol for type-safe serialization. Inherits from Cacheable Attributes Name Type Description tag_slug str tag_name str page_paths list[str] updated_at str is_valid bool Methods 4 to_cache_dict Serialize to cache-friendly dictionary (Cacheable protocol). 0 dict[str, Any] Caret Right def to_cache_dict(self) -> dict[str, Any] Serialize to cache-friendly dictionary (Cacheable protocol). Returns dict[str, Any] from_cache_dict classmethod Deserialize from cache dictionary (Cacheable protocol). 1 TagEntry Caret Right def from_cache_dict(cls, data: dict[str, Any]) -> TagEntry Deserialize from cache dictionary (Cacheable protocol). Parameters 1 data dict[str, Any] Returns TagEntry to_dict Alias for to_cache_dict (test compatibility). 0 dict[str, Any] Caret Right def to_dict(self) -> dict[str, Any] Alias for to_cache_dict (test compatibility). Returns dict[str, Any] from_dict classmethod Alias for from_cache_dict (test compatibility). 1 TagEntry Caret Right def from_dict(cls, data: dict[str, Any]) -> TagEntry Alias for from_cache_dict (test compatibility). Parameters 1 data dict[str, Any] Returns TagEntry TaxonomyIndex Persistent index of tag-to-pages mappings for incremental taxonomy updates. Purpose: - Track which… 17 Caret Right Persistent index of tag-to-pages mappings for incremental taxonomy updates. Purpose: Track which pages have which tags Enable incremental tag updates (only changed tags) Avoid full taxonomy rebuild on every page change Support incremental tag page generation Cache Format (JSON): { "version": 1, "tags": { "python": { "tag_slug": "python", "tag_name": "Python", "page_paths": ["content/post1.md", "content/post2.md"], "updated_at": "2025-10-16T12:00:00", "is_valid": true } } } Methods 15 save_to_disk Save taxonomy index to disk. 0 None Caret Right def save_to_disk(self) -> None Save taxonomy index to disk. update_tag Update or create a tag entry. 3 None Caret Right def update_tag(self, tag_slug: str, tag_name: str, page_paths: list[str]) -> None Update or create a tag entry. Parameters 3 tag_slug str Normalized tag identifier tag_name str Original tag name for display page_paths list[str] List of page paths with this tag get_tag Get a tag entry by slug. 1 TagEntry | None Caret Right def get_tag(self, tag_slug: str) -> TagEntry | None Get a tag entry by slug. Parameters 1 tag_slug str Normalized tag identifier Returns TagEntry | None — TagEntry if found and valid, None otherwise get_pages_for_tag Get pages with a specific tag. 1 list[str] | None Caret Right def get_pages_for_tag(self, tag_slug: str) -> list[str] | None Get pages with a specific tag. Parameters 1 tag_slug str Normalized tag identifier Returns list[str] | None — List of page paths or None if tag not found/invalid has_tag Check if tag exists and is valid. 1 bool Caret Right def has_tag(self, tag_slug: str) -> bool Check if tag exists and is valid. Parameters 1 tag_slug str Normalized tag identifier Returns bool — True if tag exists and is valid get_tags_for_page Get all tags for a specific page (reverse lookup). 1 set[str] Caret Right def get_tags_for_page(self, page_path: Path) -> set[str] Get all tags for a specific page (reverse lookup). Parameters 1 page_path Path Path to page Returns set[str] — Set of tag slugs for this page get_all_tags Get all valid tags. 0 dict[str, TagEntry] Caret Right def get_all_tags(self) -> dict[str, TagEntry] Get all valid tags. Returns dict[str, TagEntry] — Dictionary mapping tag_slug to TagEntry for valid tags invalidate_tag Mark a tag as invalid. 1 None Caret Right def invalidate_tag(self, tag_slug: str) -> None Mark a tag as invalid. Parameters 1 tag_slug str Normalized tag identifier invalidate_all Invalidate all tag entries. 0 None Caret Right def invalidate_all(self) -> None Invalidate all tag entries. clear Clear all tags. 0 None Caret Right def clear(self) -> None Clear all tags. remove_page_from_all_tags Remove a page from all tags it belongs to. 1 set[str] Caret Right def remove_page_from_all_tags(self, page_path: Path) -> set[str] Remove a page from all tags it belongs to. Parameters 1 page_path Path Path to page to remove Returns set[str] — Set of affected tag slugs get_valid_entries Get all valid tag entries. 0 dict[str, TagEntry] Caret Right def get_valid_entries(self) -> dict[str, TagEntry] Get all valid tag entries. Returns dict[str, TagEntry] — Dictionary mapping tag_slug to TagEntry for valid entries get_invalid_entries Get all invalid tag entries. 0 dict[str, TagEntry] Caret Right def get_invalid_entries(self) -> dict[str, TagEntry] Get all invalid tag entries. Returns dict[str, TagEntry] — Dictionary mapping tag_slug to TagEntry for invalid entries pages_changed Check if pages for a tag have changed (enabling skipping of unchanged tag regen… 2 bool Caret Right def pages_changed(self, tag_slug: str, new_page_paths: list[str]) -> bool Check if pages for a tag have changed (enabling skipping of unchanged tag regeneration). This is the key optimization for Phase 2c.2: If a tag's page membership hasn't changed, we can skip regenerating its HTML pages entirely since the output would be identical. Parameters 2 tag_slug str Normalized tag identifier new_page_paths list[str] New list of page paths for this tag Returns bool — True if tag pages have changed and need regeneration False if tag pages are identical to cached version stats Get taxonomy index statistics. 0 dict[str, Any] Caret Right def stats(self) -> dict[str, Any] Get taxonomy index statistics. Returns dict[str, Any] — Dictionary with index stats Internal Methods 2 Caret Right __init__ Initialize taxonomy index. 1 None Caret Right def __init__(self, cache_path: Path | None = None) Initialize taxonomy index. Parameters 1 cache_path Path | None Path to cache file (defaults to .bengal/taxonomy_index.json) _load_from_disk Load taxonomy index from disk if file exists. 0 None Caret Right def _load_from_disk(self) -> None Load taxonomy index from disk if file exists. ← Previous query_index_registry Next → utils 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: 1905 - Reading Time: 10 minutes