# charsets URL: /api/parsing/charsets/ Section: parsing -------------------------------------------------------------------------------- charsets - Patitas window.BENGAL_THEME_DEFAULTS = { appearance: 'light', palette: 'brown-bengal' }; window.Bengal = window.Bengal || {}; window.Bengal.enhanceBaseUrl = '/patitas/assets/js/enhancements'; window.Bengal.watchDom = true; window.Bengal.debug = false; window.Bengal.enhanceUrls = { 'toc': '/patitas/assets/js/enhancements/toc.632a9783.js', 'docs-nav': '/patitas/assets/js/enhancements/docs-nav.57e4b129.js', 'tabs': '/patitas/assets/js/enhancements/tabs.aac9e817.js', 'lightbox': '/patitas/assets/js/enhancements/lightbox.1ca22aa1.js', 'interactive': '/patitas/assets/js/enhancements/interactive.fc077855.js', 'mobile-nav': '/patitas/assets/js/enhancements/mobile-nav.d991657f.js', 'action-bar': '/patitas/assets/js/enhancements/action-bar.d62417f4.js', 'copy-link': '/patitas/assets/js/enhancements/copy-link.7d9a5c29.js', 'data-table': '/patitas/assets/js/enhancements/data-table.1f5bc1eb.js', 'lazy-loaders': '/patitas/assets/js/enhancements/lazy-loaders.a5c38245.js', 'holo': '/patitas/assets/js/enhancements/holo.ee13c841.js', 'link-previews': '/patitas/assets/js/enhancements/link-previews.8d906535.js' }; (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'); } })(); { "prerender": [ { "where": { "and": [ { "href_matches": "/docs/*" }, { "not": { "selector_matches": "[data-external], [target=_blank], .external" } } ] }, "eagerness": "conservative" } ], "prefetch": [ { "where": { "and": [ { "href_matches": "/*" }, { "not": { "selector_matches": "[data-external], [target=_blank], .external" } } ] }, "eagerness": "conservative" } ] } Skip to main content Magnifying Glass ESC Recent Clear Magnifying Glass No results for "" Start typing to search... ↑↓ Navigate ↵ Open ESC Close Powered by Lunr ฅᨐฅ DocumentationArrow ClockwiseGet StartedCodeSyntaxDirectivesStarburstExtendingBookmarkReferenceInfoAboutTroubleshootingReleasesDevGitHubPatitas API Reference 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 ฅᨐฅ Magnifying Glass Search X Close Documentation Caret Down Arrow Clockwise Get Started Code Syntax Directives Starburst Extending Bookmark Reference Info About Troubleshooting Releases Dev Caret Down GitHub Patitas API Reference Palette Appearance Chevron Down Mode Monitor System Sun Light Moon Dark Palette Snow Lynx Brown Bengal Silver Bengal Charcoal Bengal Blue Bengal Patitas API Reference Caret Right Directives Caret Right Builtins admonition container dropdown tabs contracts decorator options protocol registry Caret Right Lexer Caret Right Classifiers directive fence footnote heading html link_ref list quote thematic Caret Right Scanners block directive fence html core modes Caret Right Parsing Caret Right Blocks Caret Right List blank_line indent item_blocks marker mixin nested trace types core directive footnote table Caret Right Inline core emphasis links match_registry special tokens charsets containers token_nav Caret Right Plugins autolinks footnotes math strikethrough table task_lists Caret Right Renderers html Caret Right Roles Caret Right Builtins formatting icons math reference protocol registry Caret Right Utils hashing logger text errors highlighting icons location nodes parser patitas protocols stringbuilder tokens Patitas API ReferenceParsing 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 parsing.charsets Character sets for O(1) classification. All sets are frozensets for: O(1) membership testing (vs O(n) for strings) Immutability (thread-safe) Module-level caching (no per-call allocation) Reference: CommonMark 0.31.2 specification Usage: from patitas.parsing.charsets import ASCII_PUNCTUATION if char in ASCII_PUNCTUATION: # O(1) lookup ... 2Functions Functions is_unicode_punctuation 1 bool ▼ Check if character is Unicode punctuation (Pc, Pd, Pe, Pf, Pi, Po, Ps, or Sc, S… def is_unicode_punctuation(char: str) -> bool Check if character is Unicode punctuation (Pc, Pd, Pe, Pf, Pi, Po, Ps, or Sc, Sk, Sm, So). CommonMark uses Unicode punctuation categories for flanking rules. This includes ASCII punctuation as a subset. Parameters Name Type Description char str Returns bool is_unicode_whitespace 1 bool ▼ Check if character is Unicode whitespace. CommonMark uses Unicode whitespace f… def is_unicode_whitespace(char: str) -> bool Check if character is Unicode whitespace. CommonMark uses Unicode whitespace for emphasis flanking rules. Includes ASCII whitespace and Unicode category Zs (space separator). Also treats empty string as whitespace (for boundary checks). Parameters Name Type Description char str Returns bool Next → containers List © 2026 Patitas built in ᓚᘏᗢ { "linkPreviews": { "enabled": true, "hoverDelay": 200, "hideDelay": 150, "showSection": true, "showReadingTime": true, "showWordCount": true, "showDate": true, "showTags": true, "maxTags": 3, "includeSelectors": [".prose"], "excludeSelectors": ["nav", ".toc", ".breadcrumb", ".pagination", ".card", "[class*='-card']", ".tab-nav", "[class*='-widget']", ".child-items", ".content-tiles"], "allowedHosts": [], "allowedSchemes": ["https"], "hostFailureThreshold": 3 } } window.BENGAL_LAZY_ASSETS = { tabulator: '/patitas/assets/js/tabulator.min.js', dataTable: '/patitas/assets/js/data-table.js', mermaidToolbar: '/patitas/assets/js/mermaid-toolbar.9de5abba.js', mermaidTheme: '/patitas/assets/js/mermaid-theme.344822c5.js', graphMinimap: '/patitas/assets/js/graph-minimap.ff04e939.js', graphContextual: '/patitas/assets/js/graph-contextual.355458ba.js' }; window.BENGAL_ICONS = { close: '/patitas/assets/icons/close.911d4fe1.svg', enlarge: '/patitas/assets/icons/enlarge.652035e5.svg', copy: '/patitas/assets/icons/copy.3d56e945.svg', 'download-svg': '/patitas/assets/icons/download.04f07e1b.svg', 'download-png': '/patitas/assets/icons/image.c34dfd40.svg', 'zoom-in': '/patitas/assets/icons/zoom-in.237b4a83.svg', 'zoom-out': '/patitas/assets/icons/zoom-out.38857c77.svg', reset: '/patitas/assets/icons/reset.d26dba29.svg' }; Arrow Up -------------------------------------------------------------------------------- Metadata: - Word Count: 706 - Reading Time: 4 minutes