diff --git a/src/utils/marked/marked.scss b/src/utils/marked/marked.scss index e526abf..d50f1f5 100644 --- a/src/utils/marked/marked.scss +++ b/src/utils/marked/marked.scss @@ -138,7 +138,7 @@ .image { display: inline-block; - max-width: 100%; + width: 100%; height: auto; } diff --git a/src/utils/marked/marked.ts b/src/utils/marked/marked.ts index 9534a27..892729e 100644 --- a/src/utils/marked/marked.ts +++ b/src/utils/marked/marked.ts @@ -1,10 +1,10 @@ -import type {Token, Tokens} from "marked" -import {lexer} from "./marked.esm" import {Attributes, ComponentType, createElement, ReactElement, ReactNode} from "react" import {View, Text, Image, Video, Audio} from "@tarojs/components" import {parseHeadingId, walkTokens, unescape} from "./utils" import TabLink from "./components/Tablink"; import './marked.scss' +import {Token, Tokens } from "./src/Tokens"; +import { lexer } from "./src/marked"; /** * 解析 Markdown 文本 diff --git a/src/utils/marked/src/Hooks.ts b/src/utils/marked/src/Hooks.ts new file mode 100644 index 0000000..0ace826 --- /dev/null +++ b/src/utils/marked/src/Hooks.ts @@ -0,0 +1,29 @@ +import { _defaults } from './defaults'; +import type { MarkedOptions } from './MarkedOptions'; + +export class _Hooks { + options: MarkedOptions; + + constructor(options?: MarkedOptions) { + this.options = options || _defaults; + } + + static passThroughHooks = new Set([ + 'preprocess', + 'postprocess' + ]); + + /** + * Process markdown before marked + */ + preprocess(markdown: string) { + return markdown; + } + + /** + * Process HTML after marked is finished + */ + postprocess(html: string) { + return html; + } +} diff --git a/src/utils/marked/src/Instance.ts b/src/utils/marked/src/Instance.ts new file mode 100644 index 0000000..3d49d61 --- /dev/null +++ b/src/utils/marked/src/Instance.ts @@ -0,0 +1,406 @@ +import { _getDefaults } from './defaults'; +import { _Lexer } from './Lexer'; +import { _Parser } from './Parser'; +import { _Hooks } from './Hooks'; +import { _Renderer } from './Renderer'; +import { _Tokenizer } from './Tokenizer'; +import { _TextRenderer } from './TextRenderer'; +import { _Slugger } from './Slugger'; +import { + checkDeprecations, + escape +} from './helpers'; +import type { MarkedExtension, MarkedOptions } from './MarkedOptions'; +import type { Token, Tokens, TokensList } from './Tokens'; + +export type ResultCallback = (error: Error | null, parseResult?: string) => undefined | void; + +type UnknownFunction = (...args: unknown[]) => unknown; +type GenericRendererFunction = (...args: unknown[]) => string | false; + +export class Marked { + defaults = _getDefaults(); + options = this.setOptions; + + parse = this.#parseMarkdown(_Lexer.lex, _Parser.parse); + parseInline = this.#parseMarkdown(_Lexer.lexInline, _Parser.parseInline); + + Parser = _Parser; + parser = _Parser.parse; + Renderer = _Renderer; + TextRenderer = _TextRenderer; + Lexer = _Lexer; + lexer = _Lexer.lex; + Tokenizer = _Tokenizer; + Slugger = _Slugger; + Hooks = _Hooks; + + constructor(...args: MarkedExtension[]) { + this.use(...args); + } + + /** + * Run callback for every token + */ + walkTokens (tokens: Token[] | TokensList, callback: (token: Token) => T | T[]) { + let values: T[] = []; + for (const token of tokens) { + values = values.concat(callback.call(this, token)); + switch (token.type) { + case 'table': { + const tableToken = token as Tokens.Table; + for (const cell of tableToken.header) { + values = values.concat(this.walkTokens(cell.tokens, callback)); + } + for (const row of tableToken.rows) { + for (const cell of row) { + values = values.concat(this.walkTokens(cell.tokens, callback)); + } + } + break; + } + case 'list': { + const listToken = token as Tokens.List; + values = values.concat(this.walkTokens(listToken.items, callback)); + break; + } + default: { + const genericToken = token as Tokens.Generic; + if (this.defaults.extensions?.childTokens?.[genericToken.type]) { + this.defaults.extensions.childTokens[genericToken.type].forEach((childTokens) => { + values = values.concat(this.walkTokens(genericToken[childTokens], callback)); + }); + } else if (genericToken.tokens) { + values = values.concat(this.walkTokens(genericToken.tokens, callback)); + } + } + } + } + return values; + } + + use(...args: MarkedExtension[]) { + const extensions: MarkedOptions['extensions'] = this.defaults.extensions || { renderers: {}, childTokens: {} }; + + args.forEach((pack) => { + // copy options to new object + const opts = { ...pack } as MarkedOptions; + + // set async to true if it was set to true before + opts.async = this.defaults.async || opts.async || false; + + // ==-- Parse "addon" extensions --== // + if (pack.extensions) { + pack.extensions.forEach((ext) => { + if (!ext.name) { + throw new Error('extension name required'); + } + if ('renderer' in ext) { // Renderer extensions + const prevRenderer = extensions.renderers[ext.name]; + if (prevRenderer) { + // Replace extension with func to run new extension but fall back if false + extensions.renderers[ext.name] = function(...args) { + let ret = ext.renderer.apply(this, args); + if (ret === false) { + ret = prevRenderer.apply(this, args); + } + return ret; + }; + } else { + extensions.renderers[ext.name] = ext.renderer; + } + } + if ('tokenizer' in ext) { // Tokenizer Extensions + if (!ext.level || (ext.level !== 'block' && ext.level !== 'inline')) { + throw new Error("extension level must be 'block' or 'inline'"); + } + const extLevel = extensions[ext.level]; + if (extLevel) { + extLevel.unshift(ext.tokenizer); + } else { + extensions[ext.level] = [ext.tokenizer]; + } + if (ext.start) { // Function to check for start of token + if (ext.level === 'block') { + if (extensions.startBlock) { + extensions.startBlock.push(ext.start); + } else { + extensions.startBlock = [ext.start]; + } + } else if (ext.level === 'inline') { + if (extensions.startInline) { + extensions.startInline.push(ext.start); + } else { + extensions.startInline = [ext.start]; + } + } + } + } + if ('childTokens' in ext && ext.childTokens) { // Child tokens to be visited by walkTokens + extensions.childTokens[ext.name] = ext.childTokens; + } + }); + opts.extensions = extensions; + } + + // ==-- Parse "overwrite" extensions --== // + if (pack.renderer) { + const renderer = this.defaults.renderer || new _Renderer(this.defaults); + for (const prop in pack.renderer) { + const rendererFunc = pack.renderer[prop as keyof MarkedExtension['renderer']] as GenericRendererFunction; + const rendererKey = prop as keyof _Renderer; + const prevRenderer = renderer[rendererKey] as GenericRendererFunction; + // Replace renderer with func to run extension, but fall back if false + renderer[rendererKey] = (...args: unknown[]) => { + let ret = rendererFunc.apply(renderer, args); + if (ret === false) { + ret = prevRenderer.apply(renderer, args); + } + return ret || ''; + }; + } + opts.renderer = renderer; + } + if (pack.tokenizer) { + const tokenizer = this.defaults.tokenizer || new _Tokenizer(this.defaults); + for (const prop in pack.tokenizer) { + const tokenizerFunc = pack.tokenizer[prop as keyof MarkedExtension['tokenizer']] as UnknownFunction; + const tokenizerKey = prop as keyof _Tokenizer; + const prevTokenizer = tokenizer[tokenizerKey] as UnknownFunction; + // Replace tokenizer with func to run extension, but fall back if false + tokenizer[tokenizerKey] = (...args: unknown[]) => { + let ret = tokenizerFunc.apply(tokenizer, args); + if (ret === false) { + ret = prevTokenizer.apply(tokenizer, args); + } + return ret; + }; + } + opts.tokenizer = tokenizer; + } + + // ==-- Parse Hooks extensions --== // + if (pack.hooks) { + const hooks = this.defaults.hooks || new _Hooks(); + for (const prop in pack.hooks) { + const hooksFunc = pack.hooks[prop as keyof MarkedExtension['hooks']] as UnknownFunction; + const hooksKey = prop as keyof _Hooks; + const prevHook = hooks[hooksKey] as UnknownFunction; + if (_Hooks.passThroughHooks.has(prop)) { + hooks[hooksKey as 'preprocess' | 'postprocess'] = (arg: string | undefined) => { + if (this.defaults.async) { + return Promise.resolve(hooksFunc.call(hooks, arg)).then(ret => { + return prevHook.call(hooks, ret) as string; + }); + } + + const ret = hooksFunc.call(hooks, arg); + return prevHook.call(hooks, ret) as string; + }; + } else { + hooks[hooksKey] = (...args: unknown[]) => { + let ret = hooksFunc.apply(hooks, args); + if (ret === false) { + ret = prevHook.apply(hooks, args); + } + return ret as string; + }; + } + } + opts.hooks = hooks; + } + + // ==-- Parse WalkTokens extensions --== // + if (pack.walkTokens) { + const walkTokens = this.defaults.walkTokens; + const packWalktokens = pack.walkTokens; + opts.walkTokens = function(token) { + let values: Array | void | unknown> = []; + values.push(packWalktokens.call(this, token)); + if (walkTokens) { + values = values.concat(walkTokens.call(this, token)); + } + return values; + }; + } + + this.defaults = { ...this.defaults, ...opts }; + }); + + return this; + } + + setOptions(opt: MarkedOptions) { + this.defaults = { ...this.defaults, ...opt }; + return this; + } + + #parseMarkdown(lexer: (src: string, options?: MarkedOptions) => TokensList | Token[], parser: (tokens: Token[], options?: MarkedOptions) => string) { + return (src: string, optOrCallback?: MarkedOptions | ResultCallback | undefined | null, callback?: ResultCallback | undefined): string | Promise | undefined => { + if (typeof optOrCallback === 'function') { + callback = optOrCallback; + optOrCallback = null; + } + + const origOpt = { ...optOrCallback }; + const opt = { ...this.defaults, ...origOpt }; + + // Show warning if an extension set async to true but the parse was called with async: false + if (this.defaults.async === true && origOpt.async === false) { + if (!opt.silent) { + console.warn('marked(): The async option was set to true by an extension. The async: false option sent to parse will be ignored.'); + } + + opt.async = true; + } + + const throwError = this.#onError(!!opt.silent, !!opt.async, callback); + + // throw error in case of non string input + if (typeof src === 'undefined' || src === null) { + return throwError(new Error('marked(): input parameter is undefined or null')); + } + if (typeof src !== 'string') { + return throwError(new Error('marked(): input parameter is of type ' + + Object.prototype.toString.call(src) + ', string expected')); + } + + checkDeprecations(opt, callback); + + if (opt.hooks) { + opt.hooks.options = opt; + } + + if (callback) { + const resultCallback = callback; + const highlight = opt.highlight; + let tokens: TokensList | Token[]; + + try { + if (opt.hooks) { + src = opt.hooks.preprocess(src) as string; + } + tokens = lexer(src, opt); + } catch (e) { + return throwError(e as Error); + } + + const done = (err?: Error) => { + let out; + + if (!err) { + try { + if (opt.walkTokens) { + this.walkTokens(tokens, opt.walkTokens); + } + out = parser(tokens, opt); + if (opt.hooks) { + out = opt.hooks.postprocess(out) as string; + } + } catch (e) { + err = e as Error; + } + } + + opt.highlight = highlight; + + return err + ? throwError(err) + : resultCallback(null, out) as undefined; + }; + + if (!highlight || highlight.length < 3) { + return done(); + } + + delete opt.highlight; + + if (!tokens.length) return done(); + + let pending = 0; + this.walkTokens(tokens, (token) => { + if (token.type === 'code') { + pending++; + setTimeout(() => { + highlight(token.text, token.lang, (err, code) => { + if (err) { + return done(err); + } + if (code != null && code !== token.text) { + token.text = code; + token.escaped = true; + } + + pending--; + if (pending === 0) { + done(); + } + }); + }, 0); + } + }); + + if (pending === 0) { + done(); + } + + return; + } + + if (opt.async) { + return Promise.resolve(opt.hooks ? opt.hooks.preprocess(src) : src) + .then(src => lexer(src, opt)) + .then(tokens => opt.walkTokens ? Promise.all(this.walkTokens(tokens, opt.walkTokens)).then(() => tokens) : tokens) + .then(tokens => parser(tokens, opt)) + .then(html => opt.hooks ? opt.hooks.postprocess(html) : html) + .catch(throwError); + } + + try { + if (opt.hooks) { + src = opt.hooks.preprocess(src) as string; + } + const tokens = lexer(src, opt); + if (opt.walkTokens) { + this.walkTokens(tokens, opt.walkTokens); + } + let html = parser(tokens, opt); + if (opt.hooks) { + html = opt.hooks.postprocess(html) as string; + } + return html; + } catch (e) { + return throwError(e as Error); + } + }; + } + + #onError(silent: boolean, async: boolean, callback?: ResultCallback) { + return (e: Error): string | Promise | undefined => { + e.message += '\nPlease report this to https://github.com/markedjs/marked.'; + + if (silent) { + const msg = '

An error occurred:

'
+          + escape(e.message + '', true)
+          + '
'; + if (async) { + return Promise.resolve(msg); + } + if (callback) { + callback(null, msg); + return; + } + return msg; + } + + if (async) { + return Promise.reject(e); + } + if (callback) { + callback(e); + return; + } + throw e; + }; + } +} diff --git a/src/utils/marked/src/Lexer.ts b/src/utils/marked/src/Lexer.ts new file mode 100644 index 0000000..4a93821 --- /dev/null +++ b/src/utils/marked/src/Lexer.ts @@ -0,0 +1,516 @@ +import { _Tokenizer } from './Tokenizer'; +import { _defaults } from './defaults'; +import { block, inline } from './rules'; +import type { Token, TokensList, Tokens } from './Tokens'; +import type { MarkedOptions, TokenizerExtension } from './MarkedOptions'; +import type { Rules } from './rules'; + +/** + * smartypants text replacement + */ +function smartypants(text: string) { + return text + // em-dashes + .replace(/---/g, '\u2014') + // en-dashes + .replace(/--/g, '\u2013') + // opening singles + .replace(/(^|[-\u2014/(\[{"\s])'/g, '$1\u2018') + // closing singles & apostrophes + .replace(/'/g, '\u2019') + // opening doubles + .replace(/(^|[-\u2014/(\[{\u2018\s])"/g, '$1\u201c') + // closing doubles + .replace(/"/g, '\u201d') + // ellipses + .replace(/\.{3}/g, '\u2026'); +} + +/** + * mangle email addresses + */ +function mangle(text: string) { + let out = ''; + + for (let i = 0; i < text.length; i++) { + const ch = Math.random() > 0.5 + ? 'x' + text.charCodeAt(i).toString(16) + : text.charCodeAt(i).toString(); + out += '&#' + ch + ';'; + } + + return out; +} + +/** + * Block Lexer + */ +export class _Lexer { + tokens: TokensList; + options: MarkedOptions; + state: { + inLink: boolean; + inRawBlock: boolean; + top: boolean; + }; + + private tokenizer: _Tokenizer; + private inlineQueue: {src: string, tokens: Token[]}[]; + + constructor(options?: MarkedOptions) { + // TokenList cannot be created in one go + // @ts-expect-error + this.tokens = []; + this.tokens.links = Object.create(null); + this.options = options || _defaults; + this.options.tokenizer = this.options.tokenizer || new _Tokenizer(); + this.tokenizer = this.options.tokenizer; + this.tokenizer.options = this.options; + this.tokenizer.lexer = this; + this.inlineQueue = []; + this.state = { + inLink: false, + inRawBlock: false, + top: true + }; + + const rules = { + block: block.normal, + inline: inline.normal + }; + + if (this.options.pedantic) { + rules.block = block.pedantic; + rules.inline = inline.pedantic; + } else if (this.options.gfm) { + rules.block = block.gfm; + if (this.options.breaks) { + rules.inline = inline.breaks; + } else { + rules.inline = inline.gfm; + } + } + this.tokenizer.rules = rules; + } + + /** + * Expose Rules + */ + static get rules(): Rules { + return { + block, + inline + }; + } + + /** + * Static Lex Method + */ + static lex(src: string, options?: MarkedOptions) { + const lexer = new _Lexer(options); + return lexer.lex(src); + } + + /** + * Static Lex Inline Method + */ + static lexInline(src: string, options?: MarkedOptions) { + const lexer = new _Lexer(options); + return lexer.inlineTokens(src); + } + + /** + * Preprocessing + */ + lex(src: string) { + src = src + .replace(/\r\n|\r/g, '\n'); + + this.blockTokens(src, this.tokens); + + let next; + while (next = this.inlineQueue.shift()) { + this.inlineTokens(next.src, next.tokens); + } + + return this.tokens; + } + + /** + * Lexing + */ + blockTokens(src: string, tokens?: Token[]): Token[]; + blockTokens(src: string, tokens?: TokensList): TokensList; + blockTokens(src: string, tokens: Token[] = []) { + if (this.options.pedantic) { + src = src.replace(/\t/g, ' ').replace(/^ +$/gm, ''); + } else { + src = src.replace(/^( *)(\t+)/gm, (_, leading, tabs) => { + return leading + ' '.repeat(tabs.length); + }); + } + + let token: Tokens.Generic | undefined; + let lastToken; + let cutSrc; + let lastParagraphClipped; + + while (src) { + if (this.options.extensions + && this.options.extensions.block + && this.options.extensions.block.some((extTokenizer: TokenizerExtension['tokenizer']) => { + if (token = extTokenizer.call({ lexer: this }, src, tokens)) { + src = src.substring(token.raw.length); + tokens.push(token); + return true; + } + return false; + })) { + continue; + } + + // newline + if (token = this.tokenizer.space(src)) { + src = src.substring(token.raw.length); + if (token.raw.length === 1 && tokens.length > 0) { + // if there's a single \n as a spacer, it's terminating the last line, + // so move it there so that we don't get unecessary paragraph tags + tokens[tokens.length - 1].raw += '\n'; + } else { + tokens.push(token); + } + continue; + } + + // code + if (token = this.tokenizer.code(src)) { + src = src.substring(token.raw.length); + lastToken = tokens[tokens.length - 1]; + // An indented code block cannot interrupt a paragraph. + if (lastToken && (lastToken.type === 'paragraph' || lastToken.type === 'text')) { + lastToken.raw += '\n' + token.raw; + lastToken.text += '\n' + token.text; + this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text; + } else { + tokens.push(token); + } + continue; + } + + // fences + if (token = this.tokenizer.fences(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // heading + if (token = this.tokenizer.heading(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // hr + if (token = this.tokenizer.hr(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // blockquote + if (token = this.tokenizer.blockquote(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // list + if (token = this.tokenizer.list(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // html + if (token = this.tokenizer.html(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // def + if (token = this.tokenizer.def(src)) { + src = src.substring(token.raw.length); + lastToken = tokens[tokens.length - 1]; + if (lastToken && (lastToken.type === 'paragraph' || lastToken.type === 'text')) { + lastToken.raw += '\n' + token.raw; + lastToken.text += '\n' + token.raw; + this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text; + } else if (!this.tokens.links[token.tag]) { + this.tokens.links[token.tag] = { + href: token.href, + title: token.title + }; + } + continue; + } + + // table (gfm) + if (token = this.tokenizer.table(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // lheading + if (token = this.tokenizer.lheading(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // top-level paragraph + // prevent paragraph consuming extensions by clipping 'src' to extension start + cutSrc = src; + if (this.options.extensions && this.options.extensions.startBlock) { + let startIndex = Infinity; + const tempSrc = src.slice(1); + let tempStart; + this.options.extensions.startBlock.forEach((getStartIndex) => { + tempStart = getStartIndex.call({ lexer: this }, tempSrc); + if (typeof tempStart === 'number' && tempStart >= 0) { startIndex = Math.min(startIndex, tempStart); } + }); + if (startIndex < Infinity && startIndex >= 0) { + cutSrc = src.substring(0, startIndex + 1); + } + } + if (this.state.top && (token = this.tokenizer.paragraph(cutSrc))) { + lastToken = tokens[tokens.length - 1]; + if (lastParagraphClipped && lastToken.type === 'paragraph') { + lastToken.raw += '\n' + token.raw; + lastToken.text += '\n' + token.text; + this.inlineQueue.pop(); + this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text; + } else { + tokens.push(token); + } + lastParagraphClipped = (cutSrc.length !== src.length); + src = src.substring(token.raw.length); + continue; + } + + // text + if (token = this.tokenizer.text(src)) { + src = src.substring(token.raw.length); + lastToken = tokens[tokens.length - 1]; + if (lastToken && lastToken.type === 'text') { + lastToken.raw += '\n' + token.raw; + lastToken.text += '\n' + token.text; + this.inlineQueue.pop(); + this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text; + } else { + tokens.push(token); + } + continue; + } + + if (src) { + const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0); + if (this.options.silent) { + console.error(errMsg); + break; + } else { + throw new Error(errMsg); + } + } + } + + this.state.top = true; + return tokens; + } + + inline(src: string, tokens: Token[] = []) { + this.inlineQueue.push({ src, tokens }); + return tokens; + } + + /** + * Lexing/Compiling + */ + inlineTokens(src: string, tokens: Token[] = []): Token[] { + let token, lastToken, cutSrc; + + // String with links masked to avoid interference with em and strong + let maskedSrc = src; + let match; + let keepPrevChar, prevChar; + + // Mask out reflinks + if (this.tokens.links) { + const links = Object.keys(this.tokens.links); + if (links.length > 0) { + while ((match = this.tokenizer.rules.inline.reflinkSearch.exec(maskedSrc)) != null) { + if (links.includes(match[0].slice(match[0].lastIndexOf('[') + 1, -1))) { + maskedSrc = maskedSrc.slice(0, match.index) + '[' + 'a'.repeat(match[0].length - 2) + ']' + maskedSrc.slice(this.tokenizer.rules.inline.reflinkSearch.lastIndex); + } + } + } + } + // Mask out other blocks + while ((match = this.tokenizer.rules.inline.blockSkip.exec(maskedSrc)) != null) { + maskedSrc = maskedSrc.slice(0, match.index) + '[' + 'a'.repeat(match[0].length - 2) + ']' + maskedSrc.slice(this.tokenizer.rules.inline.blockSkip.lastIndex); + } + + // Mask out escaped characters + while ((match = this.tokenizer.rules.inline.anyPunctuation.exec(maskedSrc)) != null) { + maskedSrc = maskedSrc.slice(0, match.index) + '++' + maskedSrc.slice(this.tokenizer.rules.inline.anyPunctuation.lastIndex); + } + + while (src) { + if (!keepPrevChar) { + prevChar = ''; + } + keepPrevChar = false; + + // extensions + if (this.options.extensions + && this.options.extensions.inline + && this.options.extensions.inline.some((extTokenizer) => { + if (token = extTokenizer.call({ lexer: this }, src, tokens)) { + src = src.substring(token.raw.length); + tokens.push(token); + return true; + } + return false; + })) { + continue; + } + + // escape + if (token = this.tokenizer.escape(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // tag + if (token = this.tokenizer.tag(src)) { + src = src.substring(token.raw.length); + lastToken = tokens[tokens.length - 1]; + if (lastToken && token.type === 'text' && lastToken.type === 'text') { + lastToken.raw += token.raw; + lastToken.text += token.text; + } else { + tokens.push(token); + } + continue; + } + + // link + if (token = this.tokenizer.link(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // reflink, nolink + if (token = this.tokenizer.reflink(src, this.tokens.links)) { + src = src.substring(token.raw.length); + lastToken = tokens[tokens.length - 1]; + if (lastToken && token.type === 'text' && lastToken.type === 'text') { + lastToken.raw += token.raw; + lastToken.text += token.text; + } else { + tokens.push(token); + } + continue; + } + + // em & strong + if (token = this.tokenizer.emStrong(src, maskedSrc, prevChar)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // code + if (token = this.tokenizer.codespan(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // br + if (token = this.tokenizer.br(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // del (gfm) + if (token = this.tokenizer.del(src)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // autolink + if (token = this.tokenizer.autolink(src, mangle)) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // url (gfm) + if (!this.state.inLink && (token = this.tokenizer.url(src, mangle))) { + src = src.substring(token.raw.length); + tokens.push(token); + continue; + } + + // text + // prevent inlineText consuming extensions by clipping 'src' to extension start + cutSrc = src; + if (this.options.extensions && this.options.extensions.startInline) { + let startIndex = Infinity; + const tempSrc = src.slice(1); + let tempStart; + this.options.extensions.startInline.forEach((getStartIndex) => { + tempStart = getStartIndex.call({ lexer: this }, tempSrc); + if (typeof tempStart === 'number' && tempStart >= 0) { startIndex = Math.min(startIndex, tempStart); } + }); + if (startIndex < Infinity && startIndex >= 0) { + cutSrc = src.substring(0, startIndex + 1); + } + } + if (token = this.tokenizer.inlineText(cutSrc, smartypants)) { + src = src.substring(token.raw.length); + if (token.raw.slice(-1) !== '_') { // Track prevChar before string of ____ started + prevChar = token.raw.slice(-1); + } + keepPrevChar = true; + lastToken = tokens[tokens.length - 1]; + if (lastToken && lastToken.type === 'text') { + lastToken.raw += token.raw; + lastToken.text += token.text; + } else { + tokens.push(token); + } + continue; + } + + if (src) { + const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0); + if (this.options.silent) { + console.error(errMsg); + break; + } else { + throw new Error(errMsg); + } + } + } + + return tokens; + } +} diff --git a/src/utils/marked/src/MarkedOptions.ts b/src/utils/marked/src/MarkedOptions.ts new file mode 100644 index 0000000..399411a --- /dev/null +++ b/src/utils/marked/src/MarkedOptions.ts @@ -0,0 +1,217 @@ +import type { Token, Tokens, TokensList } from './Tokens'; +import type { _Parser } from './Parser'; +import type { _Lexer } from './Lexer'; +import type { _Renderer } from './Renderer'; +import type { _Tokenizer } from './Tokenizer'; + +export interface SluggerOptions { + /** Generates the next unique slug without updating the internal accumulator. */ + dryrun?: boolean; +} + +export interface TokenizerThis { + lexer: _Lexer; +} + +export type TokenizerExtensionFunction = (this: TokenizerThis, src: string, tokens: Token[] | TokensList) => Tokens.Generic | undefined; + +export type TokenizerStartFunction = (this: TokenizerThis, src: string) => number | void; + +export interface TokenizerExtension { + name: string; + level: 'block' | 'inline'; + start?: TokenizerStartFunction | undefined; + tokenizer: TokenizerExtensionFunction; + childTokens?: string[] | undefined; +} + +export interface RendererThis { + parser: _Parser; +} + +export type RendererExtensionFunction = (this: RendererThis, token: Tokens.Generic) => string | false | undefined; + +export interface RendererExtension { + name: string; + renderer: RendererExtensionFunction; +} + +export type TokenizerAndRendererExtension = TokenizerExtension | RendererExtension | (TokenizerExtension & RendererExtension); + +type RendererApi = Omit<_Renderer, 'constructor' | 'options'>; +type RendererObject = { + [K in keyof RendererApi]?: (...args: Parameters) => ReturnType | false +}; + +type TokenizerApi = Omit<_Tokenizer, 'constructor' | 'options' | 'rules' | 'lexer'>; +type TokenizerObject = { + [K in keyof TokenizerApi]?: (...args: Parameters) => ReturnType | false +}; + +export interface MarkedExtension { + /** + * True will tell marked to await any walkTokens functions before parsing the tokens and returning an HTML string. + */ + async?: boolean; + + /** + * A prefix URL for any relative link. + * @deprecated Deprecated in v5.0.0 use marked-base-url to prefix url for any relative link. + */ + baseUrl?: string | undefined | null; + + /** + * Enable GFM line breaks. This option requires the gfm option to be true. + */ + breaks?: boolean | undefined; + + /** + * Add tokenizers and renderers to marked + */ + extensions?: + | TokenizerAndRendererExtension[] + | undefined | null; + + /** + * Enable GitHub flavored markdown. + */ + gfm?: boolean | undefined; + + /** + * Include an id attribute when emitting headings. + * @deprecated Deprecated in v5.0.0 use marked-gfm-heading-id to include an id attribute when emitting headings (h1, h2, h3, etc). + */ + headerIds?: boolean | undefined; + + /** + * Set the prefix for header tag ids. + * @deprecated Deprecated in v5.0.0 use marked-gfm-heading-id to add a string to prefix the id attribute when emitting headings (h1, h2, h3, etc). + */ + headerPrefix?: string | undefined; + + /** + * A function to highlight code blocks. The function can either be + * synchronous (returning a string) or asynchronous (callback invoked + * with an error if any occurred during highlighting and a string + * if highlighting was successful) + * @deprecated Deprecated in v5.0.0 use marked-highlight to add highlighting to code blocks. + */ + highlight?: ((code: string, lang: string | undefined, callback?: (error: Error, code?: string) => void) => string | void) | null; + + /** + * Hooks are methods that hook into some part of marked. + * preprocess is called to process markdown before sending it to marked. + * postprocess is called to process html after marked has finished parsing. + */ + hooks?: { + preprocess: (markdown: string) => string | Promise, + postprocess: (html: string) => string | Promise, + // eslint-disable-next-line no-use-before-define + options?: MarkedOptions + } | null; + + /** + * Set the prefix for code block classes. + * @deprecated Deprecated in v5.0.0 use marked-highlight to prefix the className in a block. Useful for syntax highlighting. + */ + langPrefix?: string | undefined; + + /** + * Mangle autolinks (). + * @deprecated Deprecated in v5.0.0 use marked-mangle to mangle email addresses. + */ + mangle?: boolean | undefined; + + /** + * Conform to obscure parts of markdown.pl as much as possible. Don't fix any of the original markdown bugs or poor behavior. + */ + pedantic?: boolean | undefined; + + /** + * Type: object Default: new Renderer() + * + * An object containing functions to render tokens to HTML. + */ + renderer?: RendererObject | undefined | null; + + /** + * Sanitize the output. Ignore any HTML that has been input. If true, sanitize the HTML passed into markdownString with the sanitizer function. + * @deprecated Warning: This feature is deprecated and it should NOT be used as it cannot be considered secure. Instead use a sanitize library, like DOMPurify (recommended), sanitize-html or insane on the output HTML! + */ + sanitize?: boolean | undefined; + + /** + * Optionally sanitize found HTML with a sanitizer function. + * @deprecated A function to sanitize the HTML passed into markdownString. + */ + sanitizer?: ((html: string) => string) | null; + + /** + * Shows an HTML error message when rendering fails. + */ + silent?: boolean | undefined; + + /** + * Use smarter list behavior than the original markdown. May eventually be default with the old behavior moved into pedantic. + */ + smartLists?: boolean | undefined; + + /** + * Use "smart" typograhic punctuation for things like quotes and dashes. + * @deprecated Deprecated in v5.0.0 use marked-smartypants to use "smart" typographic punctuation for things like quotes and dashes. + */ + smartypants?: boolean | undefined; + + /** + * The tokenizer defines how to turn markdown text into tokens. + */ + tokenizer?: TokenizerObject | undefined | null; + + /** + * The walkTokens function gets called with every token. + * Child tokens are called before moving on to sibling tokens. + * Each token is passed by reference so updates are persisted when passed to the parser. + * The return value of the function is ignored. + */ + walkTokens?: ((token: Token) => void | unknown | Promise) | undefined | null; + /** + * Generate closing slash for self-closing tags (
instead of
) + * @deprecated Deprecated in v5.0.0 use marked-xhtml to emit self-closing HTML tags for void elements (
, , etc.) with a "/" as required by XHTML. + */ + xhtml?: boolean | undefined; +} + +export interface MarkedOptions extends Omit { + /** + * Type: object Default: new Renderer() + * + * An object containing functions to render tokens to HTML. + */ + renderer?: _Renderer | undefined | null; + + /** + * The tokenizer defines how to turn markdown text into tokens. + */ + tokenizer?: _Tokenizer | undefined | null; + + /** + * Custom extensions + */ + extensions?: null | { + renderers: { + [name: string]: RendererExtensionFunction; + }; + childTokens: { + [name: string]: string[]; + }; + inline?: TokenizerExtensionFunction[]; + block?: TokenizerExtensionFunction[]; + startInline?: TokenizerStartFunction[]; + startBlock?: TokenizerStartFunction[]; + }; + + /** + * walkTokens function returns array of values for Promise.all + */ + walkTokens?: null | ((token: Token) => void | (unknown | Promise)[]); +} diff --git a/src/utils/marked/src/Parser.ts b/src/utils/marked/src/Parser.ts new file mode 100644 index 0000000..dd095a9 --- /dev/null +++ b/src/utils/marked/src/Parser.ts @@ -0,0 +1,281 @@ +import { _Renderer } from './Renderer'; +import { _TextRenderer } from './TextRenderer'; +import { _Slugger } from './Slugger'; +import { _defaults } from './defaults'; +import { + unescape +} from './helpers'; +import type { Token, Tokens } from './Tokens'; +import type { MarkedOptions } from './MarkedOptions'; + +/** + * Parsing & Compiling + */ +export class _Parser { + options: MarkedOptions; + renderer: _Renderer; + textRenderer: _TextRenderer; + slugger: _Slugger; + constructor(options?: MarkedOptions) { + this.options = options || _defaults; + this.options.renderer = this.options.renderer || new _Renderer(); + this.renderer = this.options.renderer; + this.renderer.options = this.options; + this.textRenderer = new _TextRenderer(); + this.slugger = new _Slugger(); + } + + /** + * Static Parse Method + */ + static parse(tokens: Token[], options?: MarkedOptions) { + const parser = new _Parser(options); + return parser.parse(tokens); + } + + /** + * Static Parse Inline Method + */ + static parseInline(tokens: Token[], options?: MarkedOptions) { + const parser = new _Parser(options); + return parser.parseInline(tokens); + } + + /** + * Parse Loop + */ + parse(tokens: Token[], top = true): string { + let out = ''; + + for (let i = 0; i < tokens.length; i++) { + const token = tokens[i]; + + // Run any renderer extensions + if (this.options.extensions && this.options.extensions.renderers && this.options.extensions.renderers[token.type]) { + const genericToken = token as Tokens.Generic; + const ret = this.options.extensions.renderers[genericToken.type].call({ parser: this }, genericToken); + if (ret !== false || !['space', 'hr', 'heading', 'code', 'table', 'blockquote', 'list', 'html', 'paragraph', 'text'].includes(genericToken.type)) { + out += ret || ''; + continue; + } + } + + switch (token.type) { + case 'space': { + continue; + } + case 'hr': { + out += this.renderer.hr(); + continue; + } + case 'heading': { + const headingToken = token as Tokens.Heading; + out += this.renderer.heading( + this.parseInline(headingToken.tokens), + headingToken.depth, + unescape(this.parseInline(headingToken.tokens, this.textRenderer)), + this.slugger); + continue; + } + case 'code': { + const codeToken = token as Tokens.Code; + out += this.renderer.code(codeToken.text, + codeToken.lang, + !!codeToken.escaped); + continue; + } + case 'table': { + const tableToken = token as Tokens.Table; + let header = ''; + + // header + let cell = ''; + for (let j = 0; j < tableToken.header.length; j++) { + cell += this.renderer.tablecell( + this.parseInline(tableToken.header[j].tokens), + { header: true, align: tableToken.align[j] } + ); + } + header += this.renderer.tablerow(cell); + + let body = ''; + for (let j = 0; j < tableToken.rows.length; j++) { + const row = tableToken.rows[j]; + + cell = ''; + for (let k = 0; k < row.length; k++) { + cell += this.renderer.tablecell( + this.parseInline(row[k].tokens), + { header: false, align: tableToken.align[k] } + ); + } + + body += this.renderer.tablerow(cell); + } + out += this.renderer.table(header, body); + continue; + } + case 'blockquote': { + const blockquoteToken = token as Tokens.Blockquote; + const body = this.parse(blockquoteToken.tokens); + out += this.renderer.blockquote(body); + continue; + } + case 'list': { + const listToken = token as Tokens.List; + const ordered = listToken.ordered; + const start = listToken.start; + const loose = listToken.loose; + + let body = ''; + for (let j = 0; j < listToken.items.length; j++) { + const item = listToken.items[j]; + const checked = item.checked; + const task = item.task; + + let itemBody = ''; + if (item.task) { + const checkbox = this.renderer.checkbox(!!checked); + if (loose) { + if (item.tokens.length > 0 && item.tokens[0].type === 'paragraph') { + item.tokens[0].text = checkbox + ' ' + item.tokens[0].text; + if (item.tokens[0].tokens && item.tokens[0].tokens.length > 0 && item.tokens[0].tokens[0].type === 'text') { + item.tokens[0].tokens[0].text = checkbox + ' ' + item.tokens[0].tokens[0].text; + } + } else { + item.tokens.unshift({ + type: 'text', + text: checkbox + } as Tokens.Text); + } + } else { + itemBody += checkbox; + } + } + + itemBody += this.parse(item.tokens, loose); + body += this.renderer.listitem(itemBody, task, !!checked); + } + + out += this.renderer.list(body, ordered, start); + continue; + } + case 'html': { + const htmlToken = token as Tokens.HTML; + out += this.renderer.html(htmlToken.text, htmlToken.block); + continue; + } + case 'paragraph': { + const paragraphToken = token as Tokens.Paragraph; + out += this.renderer.paragraph(this.parseInline(paragraphToken.tokens)); + continue; + } + case 'text': { + let textToken = token as Tokens.Text; + let body = textToken.tokens ? this.parseInline(textToken.tokens) : textToken.text; + while (i + 1 < tokens.length && tokens[i + 1].type === 'text') { + textToken = tokens[++i] as Tokens.Text; + body += '\n' + (textToken.tokens ? this.parseInline(textToken.tokens) : textToken.text); + } + out += top ? this.renderer.paragraph(body) : body; + continue; + } + + default: { + const errMsg = 'Token with "' + token.type + '" type was not found.'; + if (this.options.silent) { + console.error(errMsg); + return ''; + } else { + throw new Error(errMsg); + } + } + } + } + + return out; + } + + /** + * Parse Inline Tokens + */ + parseInline(tokens: Token[], renderer?: _Renderer | _TextRenderer): string { + renderer = renderer || this.renderer; + let out = ''; + + for (let i = 0; i < tokens.length; i++) { + const token = tokens[i]; + + // Run any renderer extensions + if (this.options.extensions && this.options.extensions.renderers && this.options.extensions.renderers[token.type]) { + const ret = this.options.extensions.renderers[token.type].call({ parser: this }, token); + if (ret !== false || !['escape', 'html', 'link', 'image', 'strong', 'em', 'codespan', 'br', 'del', 'text'].includes(token.type)) { + out += ret || ''; + continue; + } + } + + switch (token.type) { + case 'escape': { + const escapeToken = token as Tokens.Escape; + out += renderer.text(escapeToken.text); + break; + } + case 'html': { + const tagToken = token as Tokens.Tag; + out += renderer.html(tagToken.text); + break; + } + case 'link': { + const linkToken = token as Tokens.Link; + out += renderer.link(linkToken.href, linkToken.title, this.parseInline(linkToken.tokens, renderer)); + break; + } + case 'image': { + const imageToken = token as Tokens.Image; + out += renderer.image(imageToken.href, imageToken.title, imageToken.text); + break; + } + case 'strong': { + const strongToken = token as Tokens.Strong; + out += renderer.strong(this.parseInline(strongToken.tokens, renderer)); + break; + } + case 'em': { + const emToken = token as Tokens.Em; + out += renderer.em(this.parseInline(emToken.tokens, renderer)); + break; + } + case 'codespan': { + const codespanToken = token as Tokens.Codespan; + out += renderer.codespan(codespanToken.text); + break; + } + case 'br': { + out += renderer.br(); + break; + } + case 'del': { + const delToken = token as Tokens.Del; + out += renderer.del(this.parseInline(delToken.tokens, renderer)); + break; + } + case 'text': { + const textToken = token as Tokens.Text; + out += renderer.text(textToken.text); + break; + } + default: { + const errMsg = 'Token with "' + token.type + '" type was not found.'; + if (this.options.silent) { + console.error(errMsg); + return ''; + } else { + throw new Error(errMsg); + } + } + } + } + return out; + } +} diff --git a/src/utils/marked/src/Renderer.ts b/src/utils/marked/src/Renderer.ts new file mode 100644 index 0000000..6563355 --- /dev/null +++ b/src/utils/marked/src/Renderer.ts @@ -0,0 +1,169 @@ +import { _defaults } from './defaults'; +import { + cleanUrl, + escape +} from './helpers'; +import type { MarkedOptions } from './MarkedOptions'; +import type { _Slugger } from './Slugger'; + +/** + * Renderer + */ +export class _Renderer { + options: MarkedOptions; + constructor(options?: MarkedOptions) { + this.options = options || _defaults; + } + + code(code: string, infostring: string | undefined, escaped: boolean): string { + const lang = (infostring || '').match(/^\S*/)?.[0]; + if (this.options.highlight) { + const out = this.options.highlight(code, lang); + if (out != null && out !== code) { + escaped = true; + code = out; + } + } + + code = code.replace(/\n$/, '') + '\n'; + + if (!lang) { + return '
'
+        + (escaped ? code : escape(code, true))
+        + '
\n'; + } + + return '
'
+      + (escaped ? code : escape(code, true))
+      + '
\n'; + } + + blockquote(quote: string): string { + return `
\n${quote}
\n`; + } + + html(html: string, block?: boolean) : string { + return html; + } + + heading(text: string, level: number, raw: string, slugger: _Slugger): string { + if (this.options.headerIds) { + const id = this.options.headerPrefix + slugger.slug(raw); + return `${text}\n`; + } + + // ignore IDs + return `${text}\n`; + } + + hr(): string { + return this.options.xhtml ? '
\n' : '
\n'; + } + + list(body: string, ordered: boolean, start: number | ''): string { + const type = ordered ? 'ol' : 'ul'; + const startatt = (ordered && start !== 1) ? (' start="' + start + '"') : ''; + return '<' + type + startatt + '>\n' + body + '\n'; + } + + listitem(text: string, task: boolean, checked: boolean): string { + return `
  • ${text}
  • \n`; + } + + checkbox(checked: boolean): string { + return ' '; + } + + paragraph(text: string): string { + return `

    ${text}

    \n`; + } + + table(header: string, body: string): string { + if (body) body = `${body}`; + + return '\n' + + '\n' + + header + + '\n' + + body + + '
    \n'; + } + + tablerow(content: string): string { + return `\n${content}\n`; + } + + tablecell(content: string, flags: { + header: boolean; + align: 'center' | 'left' | 'right' | null; + }): string { + const type = flags.header ? 'th' : 'td'; + const tag = flags.align + ? `<${type} align="${flags.align}">` + : `<${type}>`; + return tag + content + `\n`; + } + + /** + * span level renderer + */ + strong(text: string): string { + return `${text}`; + } + + em(text: string): string { + return `${text}`; + } + + codespan(text: string): string { + return `${text}`; + } + + br(): string { + return this.options.xhtml ? '
    ' : '
    '; + } + + del(text: string): string { + return `${text}`; + } + + link(href: string, title: string | null | undefined, text: string): string { + const cleanHref = cleanUrl(this.options.sanitize, this.options.baseUrl, href); + if (cleanHref === null) { + return text; + } + href = cleanHref; + let out = ''; + return out; + } + + image(href: string, title: string | null, text: string): string { + const cleanHref = cleanUrl(this.options.sanitize, this.options.baseUrl, href); + if (cleanHref === null) { + return text; + } + href = cleanHref; + + let out = `${text}' : '>'; + return out; + } + + text(text: string) : string { + return text; + } +} diff --git a/src/utils/marked/src/Slugger.ts b/src/utils/marked/src/Slugger.ts new file mode 100644 index 0000000..e8a98cc --- /dev/null +++ b/src/utils/marked/src/Slugger.ts @@ -0,0 +1,51 @@ +import type { SluggerOptions } from './MarkedOptions'; + +/** + * Slugger generates header id + */ +export class _Slugger { + seen: { [slugValue: string]: number }; + + constructor() { + this.seen = {}; + } + + serialize(value: string) { + return value + .toLowerCase() + .trim() + // remove html tags + .replace(/<[!\/a-z].*?>/ig, '') + // remove unwanted chars + .replace(/[\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&()*+,./:;<=>?@[\]^`{|}~]/g, '') + .replace(/\s/g, '-'); + } + + /** + * Finds the next safe (unique) slug to use + */ + getNextSafeSlug(originalSlug: string, isDryRun: boolean | undefined) { + let slug = originalSlug; + let occurenceAccumulator = 0; + if (this.seen.hasOwnProperty(slug)) { + occurenceAccumulator = this.seen[originalSlug]; + do { + occurenceAccumulator++; + slug = originalSlug + '-' + occurenceAccumulator; + } while (this.seen.hasOwnProperty(slug)); + } + if (!isDryRun) { + this.seen[originalSlug] = occurenceAccumulator; + this.seen[slug] = 0; + } + return slug; + } + + /** + * Convert string to unique id + */ + slug(value: string, options: SluggerOptions = {}) { + const slug = this.serialize(value); + return this.getNextSafeSlug(slug, options.dryrun); + } +} diff --git a/src/utils/marked/src/TextRenderer.ts b/src/utils/marked/src/TextRenderer.ts new file mode 100644 index 0000000..038b6db --- /dev/null +++ b/src/utils/marked/src/TextRenderer.ts @@ -0,0 +1,42 @@ +/** + * TextRenderer + * returns only the textual part of the token + */ +export class _TextRenderer { + // no need for block level renderers + strong(text: string) { + return text; + } + + em(text: string) { + return text; + } + + codespan(text: string) { + return text; + } + + del(text: string) { + return text; + } + + html(text: string) { + return text; + } + + text(text: string) { + return text; + } + + link(href: string, title: string | null | undefined, text: string) { + return '' + text; + } + + image(href: string, title: string | null, text: string) { + return '' + text; + } + + br() { + return ''; + } +} diff --git a/src/utils/marked/src/Tokenizer.ts b/src/utils/marked/src/Tokenizer.ts new file mode 100644 index 0000000..179144f --- /dev/null +++ b/src/utils/marked/src/Tokenizer.ts @@ -0,0 +1,813 @@ +import { _defaults } from './defaults'; +import { + rtrim, + splitCells, + escape, + findClosingBracket +} from './helpers'; +import type { _Lexer } from './Lexer'; +import type { Links, Tokens } from './Tokens'; +import type { MarkedOptions } from './MarkedOptions'; + +function outputLink(cap: string[], link: Pick, raw: string, lexer: _Lexer): Tokens.Link | Tokens.Image { + const href = link.href; + const title = link.title ? escape(link.title) : null; + const text = cap[1].replace(/\\([\[\]])/g, '$1'); + + if (cap[0].charAt(0) !== '!') { + lexer.state.inLink = true; + const token: Tokens.Link = { + type: 'link', + raw, + href, + title, + text, + tokens: lexer.inlineTokens(text) + }; + lexer.state.inLink = false; + return token; + } + return { + type: 'image', + raw, + href, + title, + text: escape(text) + }; +} + +function indentCodeCompensation(raw: string, text: string) { + const matchIndentToCode = raw.match(/^(\s+)(?:```)/); + + if (matchIndentToCode === null) { + return text; + } + + const indentToCode = matchIndentToCode[1]; + + return text + .split('\n') + .map(node => { + const matchIndentInNode = node.match(/^\s+/); + if (matchIndentInNode === null) { + return node; + } + + const [indentInNode] = matchIndentInNode; + + if (indentInNode.length >= indentToCode.length) { + return node.slice(indentToCode.length); + } + + return node; + }) + .join('\n'); +} + +/** + * Tokenizer + */ +export class _Tokenizer { + options: MarkedOptions; + // TODO: Fix this rules type + rules: any; + lexer!: _Lexer; + + constructor(options?: MarkedOptions) { + this.options = options || _defaults; + } + + space(src: string): Tokens.Space | undefined { + const cap = this.rules.block.newline.exec(src); + if (cap && cap[0].length > 0) { + return { + type: 'space', + raw: cap[0] + }; + } + } + + code(src: string): Tokens.Code | undefined { + const cap = this.rules.block.code.exec(src); + if (cap) { + const text = cap[0].replace(/^ {1,4}/gm, ''); + return { + type: 'code', + raw: cap[0], + codeBlockStyle: 'indented', + text: !this.options.pedantic + ? rtrim(text, '\n') + : text + }; + } + } + + fences(src: string): Tokens.Code | undefined { + const cap = this.rules.block.fences.exec(src); + if (cap) { + const raw = cap[0]; + const text = indentCodeCompensation(raw, cap[3] || ''); + + return { + type: 'code', + raw, + lang: cap[2] ? cap[2].trim().replace(this.rules.inline._escapes, '$1') : cap[2], + text + }; + } + } + + heading(src: string): Tokens.Heading | undefined { + const cap = this.rules.block.heading.exec(src); + if (cap) { + let text = cap[2].trim(); + + // remove trailing #s + if (/#$/.test(text)) { + const trimmed = rtrim(text, '#'); + if (this.options.pedantic) { + text = trimmed.trim(); + } else if (!trimmed || / $/.test(trimmed)) { + // CommonMark requires space before trailing #s + text = trimmed.trim(); + } + } + + return { + type: 'heading', + raw: cap[0], + depth: cap[1].length, + text, + tokens: this.lexer.inline(text) + }; + } + } + + hr(src: string): Tokens.Hr | undefined { + const cap = this.rules.block.hr.exec(src); + if (cap) { + return { + type: 'hr', + raw: cap[0] + }; + } + } + + blockquote(src: string): Tokens.Blockquote | undefined { + const cap = this.rules.block.blockquote.exec(src); + if (cap) { + const text = cap[0].replace(/^ *>[ \t]?/gm, ''); + const top = this.lexer.state.top; + this.lexer.state.top = true; + const tokens = this.lexer.blockTokens(text); + this.lexer.state.top = top; + return { + type: 'blockquote', + raw: cap[0], + tokens, + text + }; + } + } + + list(src: string): Tokens.List | undefined { + let cap = this.rules.block.list.exec(src); + if (cap) { + let bull = cap[1].trim(); + const isordered = bull.length > 1; + + const list: Tokens.List = { + type: 'list', + raw: '', + ordered: isordered, + start: isordered ? +bull.slice(0, -1) : '', + loose: false, + items: [] as Tokens.ListItem[] + }; + + bull = isordered ? `\\d{1,9}\\${bull.slice(-1)}` : `\\${bull}`; + + if (this.options.pedantic) { + bull = isordered ? bull : '[*+-]'; + } + + // Get next list item + const itemRegex = new RegExp(`^( {0,3}${bull})((?:[\t ][^\\n]*)?(?:\\n|$))`); + let raw = ''; + let itemContents = ''; + let endsWithBlankLine = false; + // Check if current bullet point can start a new List Item + while (src) { + let endEarly = false; + if (!(cap = itemRegex.exec(src))) { + break; + } + + if (this.rules.block.hr.test(src)) { // End list if bullet was actually HR (possibly move into itemRegex?) + break; + } + + raw = cap[0] as string; + src = src.substring(raw.length); + + let line = cap[2].split('\n', 1)[0].replace(/^\t+/, (t: string) => ' '.repeat(3 * t.length)) as string; + let nextLine = src.split('\n', 1)[0]; + + let indent = 0; + if (this.options.pedantic) { + indent = 2; + itemContents = line.trimLeft(); + } else { + indent = cap[2].search(/[^ ]/); // Find first non-space char + indent = indent > 4 ? 1 : indent; // Treat indented code blocks (> 4 spaces) as having only 1 indent + itemContents = line.slice(indent); + indent += cap[1].length; + } + + let blankLine = false; + + if (!line && /^ *$/.test(nextLine)) { // Items begin with at most one blank line + raw += nextLine + '\n'; + src = src.substring(nextLine.length + 1); + endEarly = true; + } + + if (!endEarly) { + const nextBulletRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}(?:[*+-]|\\d{1,9}[.)])((?:[ \t][^\\n]*)?(?:\\n|$))`); + const hrRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}((?:- *){3,}|(?:_ *){3,}|(?:\\* *){3,})(?:\\n+|$)`); + const fencesBeginRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}(?:\`\`\`|~~~)`); + const headingBeginRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}#`); + + // Check if following lines should be included in List Item + while (src) { + const rawLine = src.split('\n', 1)[0]; + nextLine = rawLine; + + // Re-align to follow commonmark nesting rules + if (this.options.pedantic) { + nextLine = nextLine.replace(/^ {1,4}(?=( {4})*[^ ])/g, ' '); + } + + // End list item if found code fences + if (fencesBeginRegex.test(nextLine)) { + break; + } + + // End list item if found start of new heading + if (headingBeginRegex.test(nextLine)) { + break; + } + + // End list item if found start of new bullet + if (nextBulletRegex.test(nextLine)) { + break; + } + + // Horizontal rule found + if (hrRegex.test(src)) { + break; + } + + if (nextLine.search(/[^ ]/) >= indent || !nextLine.trim()) { // Dedent if possible + itemContents += '\n' + nextLine.slice(indent); + } else { + // not enough indentation + if (blankLine) { + break; + } + + // paragraph continuation unless last line was a different block level element + if (line.search(/[^ ]/) >= 4) { // indented code block + break; + } + if (fencesBeginRegex.test(line)) { + break; + } + if (headingBeginRegex.test(line)) { + break; + } + if (hrRegex.test(line)) { + break; + } + + itemContents += '\n' + nextLine; + } + + if (!blankLine && !nextLine.trim()) { // Check if current line is blank + blankLine = true; + } + + raw += rawLine + '\n'; + src = src.substring(rawLine.length + 1); + line = nextLine.slice(indent); + } + } + + if (!list.loose) { + // If the previous item ended with a blank line, the list is loose + if (endsWithBlankLine) { + list.loose = true; + } else if (/\n *\n *$/.test(raw)) { + endsWithBlankLine = true; + } + } + + let istask: RegExpExecArray | null = null; + let ischecked: boolean | undefined; + // Check for task list items + if (this.options.gfm) { + istask = /^\[[ xX]\] /.exec(itemContents); + if (istask) { + ischecked = istask[0] !== '[ ] '; + itemContents = itemContents.replace(/^\[[ xX]\] +/, ''); + } + } + + list.items.push({ + type: 'list_item', + raw, + task: !!istask, + checked: ischecked, + loose: false, + text: itemContents, + tokens: [] + }); + + list.raw += raw; + } + + // Do not consume newlines at end of final item. Alternatively, make itemRegex *start* with any newlines to simplify/speed up endsWithBlankLine logic + list.items[list.items.length - 1].raw = raw.trimRight(); + (list.items[list.items.length - 1] as Tokens.ListItem).text = itemContents.trimRight(); + list.raw = list.raw.trimRight(); + + // Item child tokens handled here at end because we needed to have the final item to trim it first + for (let i = 0; i < list.items.length; i++) { + this.lexer.state.top = false; + list.items[i].tokens = this.lexer.blockTokens(list.items[i].text, []); + + if (!list.loose) { + // Check if list should be loose + const spacers = list.items[i].tokens.filter(t => t.type === 'space'); + const hasMultipleLineBreaks = spacers.length > 0 && spacers.some(t => /\n.*\n/.test(t.raw)); + + list.loose = hasMultipleLineBreaks; + } + } + + // Set all items to loose if list is loose + if (list.loose) { + for (let i = 0; i < list.items.length; i++) { + list.items[i].loose = true; + } + } + + return list; + } + } + + html(src: string): Tokens.HTML | Tokens.Paragraph | undefined { + const cap = this.rules.block.html.exec(src); + if (cap) { + const token: Tokens.HTML | Tokens.Paragraph = { + type: 'html', + block: true, + raw: cap[0], + pre: !this.options.sanitizer + && (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'), + text: cap[0] + }; + if (this.options.sanitize) { + const text = this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0]); + const paragraph = token as unknown as Tokens.Paragraph; + paragraph.type = 'paragraph'; + paragraph.text = text; + paragraph.tokens = this.lexer.inline(text); + } + return token; + } + } + + def(src: string): Tokens.Def | undefined { + const cap = this.rules.block.def.exec(src); + if (cap) { + const tag = cap[1].toLowerCase().replace(/\s+/g, ' '); + const href = cap[2] ? cap[2].replace(/^<(.*)>$/, '$1').replace(this.rules.inline._escapes, '$1') : ''; + const title = cap[3] ? cap[3].substring(1, cap[3].length - 1).replace(this.rules.inline._escapes, '$1') : cap[3]; + return { + type: 'def', + tag, + raw: cap[0], + href, + title + }; + } + } + + table(src: string): Tokens.Table | undefined { + const cap = this.rules.block.table.exec(src); + if (cap) { + const item: Tokens.Table = { + type: 'table', + raw: cap[0], + header: splitCells(cap[1]).map(c => { + return { text: c, tokens: [] }; + }), + align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */), + rows: cap[3] && cap[3].trim() ? cap[3].replace(/\n[ \t]*$/, '').split('\n') : [] + }; + + if (item.header.length === item.align.length) { + let l = item.align.length; + let i, j, k, row; + for (i = 0; i < l; i++) { + const align = item.align[i]; + if (align) { + if (/^ *-+: *$/.test(align)) { + item.align[i] = 'right'; + } else if (/^ *:-+: *$/.test(align)) { + item.align[i] = 'center'; + } else if (/^ *:-+ *$/.test(align)) { + item.align[i] = 'left'; + } else { + item.align[i] = null; + } + } + } + + l = item.rows.length; + for (i = 0; i < l; i++) { + item.rows[i] = splitCells(item.rows[i] as unknown as string, item.header.length).map(c => { + return { text: c, tokens: [] }; + }); + } + + // parse child tokens inside headers and cells + + // header child tokens + l = item.header.length; + for (j = 0; j < l; j++) { + item.header[j].tokens = this.lexer.inline(item.header[j].text); + } + + // cell child tokens + l = item.rows.length; + for (j = 0; j < l; j++) { + row = item.rows[j]; + for (k = 0; k < row.length; k++) { + row[k].tokens = this.lexer.inline(row[k].text); + } + } + + return item; + } + } + } + + lheading(src: string): Tokens.Heading | undefined { + const cap = this.rules.block.lheading.exec(src); + if (cap) { + return { + type: 'heading', + raw: cap[0], + depth: cap[2].charAt(0) === '=' ? 1 : 2, + text: cap[1], + tokens: this.lexer.inline(cap[1]) + }; + } + } + + paragraph(src: string): Tokens.Paragraph | undefined { + const cap = this.rules.block.paragraph.exec(src); + if (cap) { + const text = cap[1].charAt(cap[1].length - 1) === '\n' + ? cap[1].slice(0, -1) + : cap[1]; + return { + type: 'paragraph', + raw: cap[0], + text, + tokens: this.lexer.inline(text) + }; + } + } + + text(src: string): Tokens.Text | undefined { + const cap = this.rules.block.text.exec(src); + if (cap) { + return { + type: 'text', + raw: cap[0], + text: cap[0], + tokens: this.lexer.inline(cap[0]) + }; + } + } + + escape(src: string): Tokens.Escape | undefined { + const cap = this.rules.inline.escape.exec(src); + if (cap) { + return { + type: 'escape', + raw: cap[0], + text: escape(cap[1]) + }; + } + } + + tag(src: string): Tokens.Tag | undefined { + const cap = this.rules.inline.tag.exec(src); + if (cap) { + if (!this.lexer.state.inLink && /^/i.test(cap[0])) { + this.lexer.state.inLink = false; + } + if (!this.lexer.state.inRawBlock && /^<(pre|code|kbd|script)(\s|>)/i.test(cap[0])) { + this.lexer.state.inRawBlock = true; + } else if (this.lexer.state.inRawBlock && /^<\/(pre|code|kbd|script)(\s|>)/i.test(cap[0])) { + this.lexer.state.inRawBlock = false; + } + + return { + type: this.options.sanitize + ? 'text' + : 'html', + raw: cap[0], + inLink: this.lexer.state.inLink, + inRawBlock: this.lexer.state.inRawBlock, + block: false, + text: this.options.sanitize + ? (this.options.sanitizer + ? this.options.sanitizer(cap[0]) + : escape(cap[0])) + : cap[0] + }; + } + } + + link(src: string): Tokens.Link | Tokens.Image | undefined { + const cap = this.rules.inline.link.exec(src); + if (cap) { + const trimmedUrl = cap[2].trim(); + if (!this.options.pedantic && /^$/.test(trimmedUrl))) { + return; + } + + // ending angle bracket cannot be escaped + const rtrimSlash = rtrim(trimmedUrl.slice(0, -1), '\\'); + if ((trimmedUrl.length - rtrimSlash.length) % 2 === 0) { + return; + } + } else { + // find closing parenthesis + const lastParenIndex = findClosingBracket(cap[2], '()'); + if (lastParenIndex > -1) { + const start = cap[0].indexOf('!') === 0 ? 5 : 4; + const linkLen = start + cap[1].length + lastParenIndex; + cap[2] = cap[2].substring(0, lastParenIndex); + cap[0] = cap[0].substring(0, linkLen).trim(); + cap[3] = ''; + } + } + let href = cap[2]; + let title = ''; + if (this.options.pedantic) { + // split pedantic href and title + const link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href); + + if (link) { + href = link[1]; + title = link[3]; + } + } else { + title = cap[3] ? cap[3].slice(1, -1) : ''; + } + + href = href.trim(); + if (/^$/.test(trimmedUrl))) { + // pedantic allows starting angle bracket without ending angle bracket + href = href.slice(1); + } else { + href = href.slice(1, -1); + } + } + return outputLink(cap, { + href: href ? href.replace(this.rules.inline._escapes, '$1') : href, + title: title ? title.replace(this.rules.inline._escapes, '$1') : title + }, cap[0], this.lexer); + } + } + + reflink(src: string, links: Links): Tokens.Link | Tokens.Image | Tokens.Text | undefined { + let cap; + if ((cap = this.rules.inline.reflink.exec(src)) + || (cap = this.rules.inline.nolink.exec(src))) { + let link = (cap[2] || cap[1]).replace(/\s+/g, ' '); + link = links[link.toLowerCase()]; + if (!link) { + const text = cap[0].charAt(0); + return { + type: 'text', + raw: text, + text + }; + } + return outputLink(cap, link, cap[0], this.lexer); + } + } + + emStrong(src: string, maskedSrc: string, prevChar = ''): Tokens.Em | Tokens.Strong | undefined { + let match = this.rules.inline.emStrong.lDelim.exec(src); + if (!match) return; + + // _ can't be between two alphanumerics. \p{L}\p{N} includes non-english alphabet/numbers as well + if (match[3] && prevChar.match(/[\p{L}\p{N}]/u)) return; + + const nextChar = match[1] || match[2] || ''; + + if (!nextChar || !prevChar || this.rules.inline.punctuation.exec(prevChar)) { + // unicode Regex counts emoji as 1 char; spread into array for proper count (used multiple times below) + const lLength = [...match[0]].length - 1; + let rDelim, rLength, delimTotal = lLength, midDelimTotal = 0; + + const endReg = match[0][0] === '*' ? this.rules.inline.emStrong.rDelimAst : this.rules.inline.emStrong.rDelimUnd; + endReg.lastIndex = 0; + + // Clip maskedSrc to same section of string as src (move to lexer?) + maskedSrc = maskedSrc.slice(-1 * src.length + lLength); + + while ((match = endReg.exec(maskedSrc)) != null) { + rDelim = match[1] || match[2] || match[3] || match[4] || match[5] || match[6]; + + if (!rDelim) continue; // skip single * in __abc*abc__ + + rLength = [...rDelim].length; + + if (match[3] || match[4]) { // found another Left Delim + delimTotal += rLength; + continue; + } else if (match[5] || match[6]) { // either Left or Right Delim + if (lLength % 3 && !((lLength + rLength) % 3)) { + midDelimTotal += rLength; + continue; // CommonMark Emphasis Rules 9-10 + } + } + + delimTotal -= rLength; + + if (delimTotal > 0) continue; // Haven't found enough closing delimiters + + // Remove extra characters. *a*** -> *a* + rLength = Math.min(rLength, rLength + delimTotal + midDelimTotal); + + const raw = [...src].slice(0, lLength + match.index + rLength + 1).join(''); + + // Create `em` if smallest delimiter has odd char count. *a*** + if (Math.min(lLength, rLength) % 2) { + const text = raw.slice(1, -1); + return { + type: 'em', + raw, + text, + tokens: this.lexer.inlineTokens(text) + }; + } + + // Create 'strong' if smallest delimiter has even char count. **a*** + const text = raw.slice(2, -2); + return { + type: 'strong', + raw, + text, + tokens: this.lexer.inlineTokens(text) + }; + } + } + } + + codespan(src: string): Tokens.Codespan | undefined { + const cap = this.rules.inline.code.exec(src); + if (cap) { + let text = cap[2].replace(/\n/g, ' '); + const hasNonSpaceChars = /[^ ]/.test(text); + const hasSpaceCharsOnBothEnds = /^ /.test(text) && / $/.test(text); + if (hasNonSpaceChars && hasSpaceCharsOnBothEnds) { + text = text.substring(1, text.length - 1); + } + text = escape(text, true); + return { + type: 'codespan', + raw: cap[0], + text + }; + } + } + + br(src: string): Tokens.Br | undefined { + const cap = this.rules.inline.br.exec(src); + if (cap) { + return { + type: 'br', + raw: cap[0] + }; + } + } + + del(src: string): Tokens.Del | undefined { + const cap = this.rules.inline.del.exec(src); + if (cap) { + return { + type: 'del', + raw: cap[0], + text: cap[2], + tokens: this.lexer.inlineTokens(cap[2]) + }; + } + } + + autolink(src: string, mangle: (cap: string) => string): Tokens.Link | undefined { + const cap = this.rules.inline.autolink.exec(src); + if (cap) { + let text, href; + if (cap[2] === '@') { + text = escape(this.options.mangle ? mangle(cap[1]) : cap[1]); + href = 'mailto:' + text; + } else { + text = escape(cap[1]); + href = text; + } + + return { + type: 'link', + raw: cap[0], + text, + href, + tokens: [ + { + type: 'text', + raw: text, + text + } + ] + }; + } + } + + url(src: string, mangle: (cap: string) => string): Tokens.Link | undefined { + let cap; + if (cap = this.rules.inline.url.exec(src)) { + let text, href; + if (cap[2] === '@') { + text = escape(this.options.mangle ? mangle(cap[0]) : cap[0]); + href = 'mailto:' + text; + } else { + // do extended autolink path validation + let prevCapZero; + do { + prevCapZero = cap[0]; + cap[0] = this.rules.inline._backpedal.exec(cap[0])[0]; + } while (prevCapZero !== cap[0]); + text = escape(cap[0]); + if (cap[1] === 'www.') { + href = 'http://' + cap[0]; + } else { + href = cap[0]; + } + } + return { + type: 'link', + raw: cap[0], + text, + href, + tokens: [ + { + type: 'text', + raw: text, + text + } + ] + }; + } + } + + inlineText(src: string, smartypants: (cap: string) => string): Tokens.Text | undefined { + const cap = this.rules.inline.text.exec(src); + if (cap) { + let text; + if (this.lexer.state.inRawBlock) { + text = this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]; + } else { + text = escape(this.options.smartypants ? smartypants(cap[0]) : cap[0]); + } + return { + type: 'text', + raw: cap[0], + text + }; + } + } +} diff --git a/src/utils/marked/src/Tokens.ts b/src/utils/marked/src/Tokens.ts new file mode 100644 index 0000000..c5c846a --- /dev/null +++ b/src/utils/marked/src/Tokens.ts @@ -0,0 +1,201 @@ +/* eslint-disable no-use-before-define */ +export type Token = ( + Tokens.Space + | Tokens.Code + | Tokens.Heading + | Tokens.Table + | Tokens.Hr + | Tokens.Blockquote + | Tokens.List + | Tokens.ListItem + | Tokens.Paragraph + | Tokens.HTML + | Tokens.Text + | Tokens.Def + | Tokens.Escape + | Tokens.Tag + | Tokens.Image + | Tokens.Link + | Tokens.Strong + | Tokens.Em + | Tokens.Codespan + | Tokens.Br + | Tokens.Del + | Tokens.Generic); + +export namespace Tokens { + export interface Space { + type: 'space'; + raw: string; + } + + export interface Code { + type: 'code'; + raw: string; + codeBlockStyle?: 'indented' | undefined; + lang?: string | undefined; + text: string; + escaped?: boolean; + } + + export interface Heading { + type: 'heading'; + raw: string; + depth: number; + text: string; + tokens: Token[]; + } + + export interface Table { + type: 'table'; + raw: string; + align: Array<'center' | 'left' | 'right' | null>; + header: TableCell[]; + rows: TableCell[][]; + } + + export interface TableCell { + text: string; + tokens: Token[]; + } + + export interface Hr { + type: 'hr'; + raw: string; + } + + export interface Blockquote { + type: 'blockquote'; + raw: string; + text: string; + tokens: Token[]; + } + + export interface List { + type: 'list'; + raw: string; + ordered: boolean; + start: number | ''; + loose: boolean; + items: ListItem[]; + } + + export interface ListItem { + type: 'list_item'; + raw: string; + task: boolean; + checked?: boolean | undefined; + loose: boolean; + text: string; + tokens: Token[]; + } + + export interface Paragraph { + type: 'paragraph'; + raw: string; + pre?: boolean | undefined; + text: string; + tokens: Token[]; + } + + export interface HTML { + type: 'html'; + raw: string; + pre: boolean; + text: string; + block: boolean; + } + + export interface Text { + type: 'text'; + raw: string; + text: string; + tokens?: Token[]; + } + + export interface Def { + type: 'def'; + raw: string; + tag: string; + href: string; + title: string; + } + + export interface Escape { + type: 'escape'; + raw: string; + text: string; + } + + export interface Tag { + type: 'text' | 'html'; + raw: string; + inLink: boolean; + inRawBlock: boolean; + text: string; + block: boolean; + } + + export interface Link { + type: 'link'; + raw: string; + href: string; + title?: string | null; + text: string; + tokens: Token[]; + } + + export interface Image { + type: 'image'; + raw: string; + href: string; + title: string | null; + text: string; + } + + export interface Strong { + type: 'strong'; + raw: string; + text: string; + tokens: Token[]; + } + + export interface Em { + type: 'em'; + raw: string; + text: string; + tokens: Token[]; + } + + export interface Codespan { + type: 'codespan'; + raw: string; + text: string; + } + + export interface Br { + type: 'br'; + raw: string; + } + + export interface Del { + type: 'del'; + raw: string; + text: string; + tokens: Token[]; + } + + export interface Generic { + [index: string]: any; + + type: string; + raw: string; + tokens?: Token[] | undefined; + } +} + +export type Links = Record>; + +export type TokensList = Token[] & { + links: Links; +}; diff --git a/src/utils/marked/src/defaults.ts b/src/utils/marked/src/defaults.ts new file mode 100644 index 0000000..cf36e6b --- /dev/null +++ b/src/utils/marked/src/defaults.ts @@ -0,0 +1,35 @@ +import type { MarkedOptions } from './MarkedOptions'; + +/** + * Gets the original marked default options. + */ +export function _getDefaults(): MarkedOptions { + return { + async: false, + baseUrl: null, + breaks: false, + extensions: null, + gfm: true, + headerIds: false, + headerPrefix: '', + highlight: null, + hooks: null, + langPrefix: 'language-', + mangle: false, + pedantic: false, + renderer: null, + sanitize: false, + sanitizer: null, + silent: false, + smartypants: false, + tokenizer: null, + walkTokens: null, + xhtml: false + }; +} + +export let _defaults = _getDefaults(); + +export function changeDefaults(newDefaults: MarkedOptions) { + _defaults = newDefaults; +} diff --git a/src/utils/marked/src/helpers.ts b/src/utils/marked/src/helpers.ts new file mode 100644 index 0000000..47a58ae --- /dev/null +++ b/src/utils/marked/src/helpers.ts @@ -0,0 +1,265 @@ +import type { MarkedOptions } from './MarkedOptions'; +import type { ResultCallback } from './Instance'; +import type { Rule } from './rules'; + +/** + * Helpers + */ +const escapeTest = /[&<>"']/; +const escapeReplace = new RegExp(escapeTest.source, 'g'); +const escapeTestNoEncode = /[<>"']|&(?!(#\d{1,7}|#[Xx][a-fA-F0-9]{1,6}|\w+);)/; +const escapeReplaceNoEncode = new RegExp(escapeTestNoEncode.source, 'g'); +const escapeReplacements: {[index: string]: string} = { + '&': '&', + '<': '<', + '>': '>', + '"': '"', + "'": ''' +}; +const getEscapeReplacement = (ch: string) => escapeReplacements[ch]; + +export function escape(html: string, encode?: boolean) { + if (encode) { + if (escapeTest.test(html)) { + return html.replace(escapeReplace, getEscapeReplacement); + } + } else { + if (escapeTestNoEncode.test(html)) { + return html.replace(escapeReplaceNoEncode, getEscapeReplacement); + } + } + + return html; +} + +const unescapeTest = /&(#(?:\d+)|(?:#x[0-9A-Fa-f]+)|(?:\w+));?/ig; + +export function unescape(html: string) { + // explicitly match decimal, hex, and named HTML entities + return html.replace(unescapeTest, (_, n) => { + n = n.toLowerCase(); + if (n === 'colon') return ':'; + if (n.charAt(0) === '#') { + return n.charAt(1) === 'x' + ? String.fromCharCode(parseInt(n.substring(2), 16)) + : String.fromCharCode(+n.substring(1)); + } + return ''; + }); +} + +const caret = /(^|[^\[])\^/g; + +export function edit(regex: Rule, opt?: string) { + regex = typeof regex === 'string' ? regex : regex.source; + opt = opt || ''; + const obj = { + replace: (name: string | RegExp, val: string | RegExp) => { + val = typeof val === 'object' && 'source' in val ? val.source : val; + val = val.replace(caret, '$1'); + regex = (regex as string).replace(name, val); + return obj; + }, + getRegex: () => { + return new RegExp(regex, opt); + } + }; + return obj; +} + +const nonWordAndColonTest = /[^\w:]/g; +const originIndependentUrl = /^$|^[a-z][a-z0-9+.-]*:|^[?#]/i; + +export function cleanUrl(sanitize: boolean | undefined, base: string | undefined | null, href: string) { + if (sanitize) { + let prot; + try { + prot = decodeURIComponent(unescape(href)) + .replace(nonWordAndColonTest, '') + .toLowerCase(); + } catch (e) { + return null; + } + if (prot.indexOf('javascript:') === 0 || prot.indexOf('vbscript:') === 0 || prot.indexOf('data:') === 0) { + return null; + } + } + if (base && !originIndependentUrl.test(href)) { + href = resolveUrl(base, href); + } + try { + href = encodeURI(href).replace(/%25/g, '%'); + } catch (e) { + return null; + } + return href; +} + +const baseUrls: Record = {}; +const justDomain = /^[^:]+:\/*[^/]*$/; +const protocol = /^([^:]+:)[\s\S]*$/; +const domain = /^([^:]+:\/*[^/]*)[\s\S]*$/; + +export function resolveUrl(base: string, href: string) { + if (!baseUrls[' ' + base]) { + // we can ignore everything in base after the last slash of its path component, + // but we might need to add _that_ + // https://tools.ietf.org/html/rfc3986#section-3 + if (justDomain.test(base)) { + baseUrls[' ' + base] = base + '/'; + } else { + baseUrls[' ' + base] = rtrim(base, '/', true); + } + } + base = baseUrls[' ' + base]; + const relativeBase = base.indexOf(':') === -1; + + if (href.substring(0, 2) === '//') { + if (relativeBase) { + return href; + } + return base.replace(protocol, '$1') + href; + } else if (href.charAt(0) === '/') { + if (relativeBase) { + return href; + } + return base.replace(domain, '$1') + href; + } else { + return base + href; + } +} + +export const noopTest = { exec: () => null }; + +export function splitCells(tableRow: string, count?: number) { + // ensure that every cell-delimiting pipe has a space + // before it to distinguish it from an escaped pipe + const row = tableRow.replace(/\|/g, (_, offset, str) => { + let escaped = false; + let curr = offset; + while (--curr >= 0 && str[curr] === '\\') escaped = !escaped; + if (escaped) { + // odd number of slashes means | is escaped + // so we leave it alone + return '|'; + } else { + // add space before unescaped | + return ' |'; + } + }), + cells = row.split(/ \|/); + let i = 0; + + // First/last cell in a row cannot be empty if it has no leading/trailing pipe + if (!cells[0].trim()) { + cells.shift(); + } + if (cells.length > 0 && !cells[cells.length - 1].trim()) { + cells.pop(); + } + + if (count) { + if (cells.length > count) { + cells.splice(count); + } else { + while (cells.length < count) cells.push(''); + } + } + + for (; i < cells.length; i++) { + // leading or trailing whitespace is ignored per the gfm spec + cells[i] = cells[i].trim().replace(/\\\|/g, '|'); + } + return cells; +} + +/** + * Remove trailing 'c's. Equivalent to str.replace(/c*$/, ''). + * /c*$/ is vulnerable to REDOS. + * + * @param str + * @param c + * @param invert Remove suffix of non-c chars instead. Default falsey. + */ +export function rtrim(str: string, c: string, invert?: boolean) { + const l = str.length; + if (l === 0) { + return ''; + } + + // Length of suffix matching the invert condition. + let suffLen = 0; + + // Step left until we fail to match the invert condition. + while (suffLen < l) { + const currChar = str.charAt(l - suffLen - 1); + if (currChar === c && !invert) { + suffLen++; + } else if (currChar !== c && invert) { + suffLen++; + } else { + break; + } + } + + return str.slice(0, l - suffLen); +} + +export function findClosingBracket(str: string, b: string) { + if (str.indexOf(b[1]) === -1) { + return -1; + } + + let level = 0; + for (let i = 0; i < str.length; i++) { + if (str[i] === '\\') { + i++; + } else if (str[i] === b[0]) { + level++; + } else if (str[i] === b[1]) { + level--; + if (level < 0) { + return i; + } + } + } + return -1; +} + +export function checkDeprecations(opt: MarkedOptions, callback?: ResultCallback) { + if (!opt || opt.silent) { + return; + } + + if (callback) { + console.warn('marked(): callback is deprecated since version 5.0.0, should not be used and will be removed in the future. Read more here: https://marked.js.org/using_pro#async'); + } + + if (opt.sanitize || opt.sanitizer) { + console.warn('marked(): sanitize and sanitizer parameters are deprecated since version 0.7.0, should not be used and will be removed in the future. Read more here: https://marked.js.org/#/USING_ADVANCED.md#options'); + } + + if (opt.highlight || opt.langPrefix !== 'language-') { + console.warn('marked(): highlight and langPrefix parameters are deprecated since version 5.0.0, should not be used and will be removed in the future. Instead use https://www.npmjs.com/package/marked-highlight.'); + } + + if (opt.mangle) { + console.warn('marked(): mangle parameter is enabled by default, but is deprecated since version 5.0.0, and will be removed in the future. To clear this warning, install https://www.npmjs.com/package/marked-mangle, or disable by setting `{mangle: false}`.'); + } + + if (opt.baseUrl) { + console.warn('marked(): baseUrl parameter is deprecated since version 5.0.0, should not be used and will be removed in the future. Instead use https://www.npmjs.com/package/marked-base-url.'); + } + + if (opt.smartypants) { + console.warn('marked(): smartypants parameter is deprecated since version 5.0.0, should not be used and will be removed in the future. Instead use https://www.npmjs.com/package/marked-smartypants.'); + } + + if (opt.xhtml) { + console.warn('marked(): xhtml parameter is deprecated since version 5.0.0, should not be used and will be removed in the future. Instead use https://www.npmjs.com/package/marked-xhtml.'); + } + + if (opt.headerIds || opt.headerPrefix) { + console.warn('marked(): headerIds and headerPrefix parameters enabled by default, but are deprecated since version 5.0.0, and will be removed in the future. To clear this warning, install https://www.npmjs.com/package/marked-gfm-heading-id, or disable by setting `{headerIds: false}`.'); + } +} diff --git a/src/utils/marked/src/marked.ts b/src/utils/marked/src/marked.ts new file mode 100644 index 0000000..6fd52b0 --- /dev/null +++ b/src/utils/marked/src/marked.ts @@ -0,0 +1,143 @@ +import { _Lexer } from './Lexer'; +import { _Parser } from './Parser'; +import { _Tokenizer } from './Tokenizer'; +import { _Renderer } from './Renderer'; +import { _TextRenderer } from './TextRenderer'; +import { _Slugger } from './Slugger'; +import { _Hooks } from './Hooks'; +import { Marked } from './Instance'; +import { + _getDefaults, + changeDefaults, + _defaults +} from './defaults'; +import type { MarkedExtension, MarkedOptions } from './MarkedOptions'; +import type { Token, TokensList } from './Tokens'; +import type { ResultCallback } from './Instance'; + +const markedInstance = new Marked(); + +/** + * Compiles markdown to HTML asynchronously. + * + * @param src String of markdown source to be compiled + * @param options Hash of options, having async: true + * @return Promise of string of compiled HTML + */ +export function marked(src: string, options: MarkedOptions & { async: true }): Promise; + +/** + * Compiles markdown to HTML synchronously. + * + * @param src String of markdown source to be compiled + * @param options Optional hash of options + * @return String of compiled HTML + */ +export function marked(src: string, options?: MarkedOptions): string; + +/** + * Compiles markdown to HTML asynchronously with a callback. + * + * @param src String of markdown source to be compiled + * @param callback Function called when the markdownString has been fully parsed when using async highlighting + */ +export function marked(src: string, callback: ResultCallback): void; + +/** + * Compiles markdown to HTML asynchronously with a callback. + * + * @param src String of markdown source to be compiled + * @param options Hash of options + * @param callback Function called when the markdownString has been fully parsed when using async highlighting + */ +export function marked( + src: string, + options: MarkedOptions, + callback: ResultCallback, +): void; +export function marked(src: string, opt?: MarkedOptions | ResultCallback, callback?: ResultCallback): string | Promise | undefined { + return markedInstance.parse(src, opt, callback); +} + +/** + * Sets the default options. + * + * @param options Hash of options + */ +marked.options = +marked.setOptions = function(options: MarkedOptions) { + markedInstance.setOptions(options); + marked.defaults = markedInstance.defaults; + changeDefaults(marked.defaults); + return marked; +}; + +/** + * Gets the original marked default options. + */ +marked.getDefaults = _getDefaults; + +marked.defaults = _defaults; + +/** + * Use Extension + */ + +marked.use = function(...args: MarkedExtension[]) { + markedInstance.use(...args); + marked.defaults = markedInstance.defaults; + changeDefaults(marked.defaults); + return marked; +}; + +/** + * Run callback for every token + */ + +marked.walkTokens = function (tokens: Token[] | TokensList, callback: (token: Token) => T | T[]) { + return markedInstance.walkTokens(tokens, callback); +}; + +/** + * Compiles markdown to HTML without enclosing `p` tag. + * + * @param src String of markdown source to be compiled + * @param options Hash of options + * @return String of compiled HTML + */ +marked.parseInline = markedInstance.parseInline; + +/** + * Expose + */ +marked.Parser = _Parser; +marked.parser = _Parser.parse; +marked.Renderer = _Renderer; +marked.TextRenderer = _TextRenderer; +marked.Lexer = _Lexer; +marked.lexer = _Lexer.lex; +marked.Tokenizer = _Tokenizer; +marked.Slugger = _Slugger; +marked.Hooks = _Hooks; +marked.parse = marked; + +export const options = marked.options; +export const setOptions = marked.setOptions; +export const use = marked.use; +export const walkTokens = marked.walkTokens; +export const parseInline = marked.parseInline; +export const parse = marked; +export const parser = _Parser.parse; +export const lexer = _Lexer.lex; +export { _defaults as defaults, _getDefaults as getDefaults } from './defaults'; +export { _Lexer as Lexer } from './Lexer'; +export { _Parser as Parser } from './Parser'; +export { _Tokenizer as Tokenizer } from './Tokenizer'; +export { _Renderer as Renderer } from './Renderer'; +export { _TextRenderer as TextRenderer } from './TextRenderer'; +export { _Slugger as Slugger } from './Slugger'; +export { _Hooks as Hooks } from './Hooks'; +export { Marked } from './Instance'; +export * from './MarkedOptions'; +export * from './rules'; +export * from './Tokens'; diff --git a/src/utils/marked/src/rules.ts b/src/utils/marked/src/rules.ts new file mode 100644 index 0000000..16a510e --- /dev/null +++ b/src/utils/marked/src/rules.ts @@ -0,0 +1,384 @@ +import { + noopTest, + edit +} from './helpers'; + +export type Rule = RegExp | string; + +export interface Rules { + [ruleName: string]: Pick | Rule | Rules; +} + +type BlockRuleNames = + | 'newline' + | 'code' + | 'fences' + | 'hr' + | 'heading' + | 'blockquote' + | 'list' + | 'html' + | 'def' + | 'lheading' + | '_paragraph' + | 'text' + | '_label' + | '_title' + | 'bullet' + | 'listItemStart' + | '_tag' + | '_comment' + | 'paragraph' + | 'uote' ; + +type BlockSubRuleNames = 'normal' | 'gfm' | 'pedantic'; + +type InlineRuleNames = + | 'escape' + | 'autolink' + | 'tag' + | 'link' + | 'reflink' + | 'nolink' + | 'reflinkSearch' + | 'code' + | 'br' + | 'text' + | '_punctuation' + | 'punctuation' + | 'blockSkip' + | 'escapedEmSt' + | '_comment' + | '_escapes' + | '_scheme' + | '_email' + | '_attribute' + | '_label' + | '_href' + | '_title' + | 'strong' + | '_extended_email' + | '_backpedal'; + +type InlineSubRuleNames = 'gfm' | 'emStrong' | 'normal' | 'pedantic'| 'breaks'; + +/** + * Block-Level Grammar + */ +// Not all rules are defined in the object literal +// @ts-expect-error +export const block: Record & Record & Rules = { + newline: /^(?: *(?:\n|$))+/, + code: /^( {4}[^\n]+(?:\n(?: *(?:\n|$))*)?)+/, + fences: /^ {0,3}(`{3,}(?=[^`\n]*(?:\n|$))|~{3,})([^\n]*)(?:\n|$)(?:|([\s\S]*?)(?:\n|$))(?: {0,3}\1[~`]* *(?=\n|$)|$)/, + hr: /^ {0,3}((?:-[\t ]*){3,}|(?:_[ \t]*){3,}|(?:\*[ \t]*){3,})(?:\n+|$)/, + heading: /^ {0,3}(#{1,6})(?=\s|$)(.*)(?:\n+|$)/, + blockquote: /^( {0,3}> ?(paragraph|[^\n]*)(?:\n|$))+/, + list: /^( {0,3}bull)([ \t][^\n]+?)?(?:\n|$)/, + html: '^ {0,3}(?:' // optional indentation + + '<(script|pre|style|textarea)[\\s>][\\s\\S]*?(?:[^\\n]*\\n+|$)' // (1) + + '|comment[^\\n]*(\\n+|$)' // (2) + + '|<\\?[\\s\\S]*?(?:\\?>\\n*|$)' // (3) + + '|\\n*|$)' // (4) + + '|\\n*|$)' // (5) + + '|)[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (6) + + '|<(?!script|pre|style|textarea)([a-z][\\w-]*)(?:attribute)*? */?>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (7) open tag + + '|(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (7) closing tag + + ')', + def: /^ {0,3}\[(label)\]: *(?:\n *)?([^<\s][^\s]*|<.*?>)(?:(?: +(?:\n *)?| *\n *)(title))? *(?:\n+|$)/, + table: noopTest, + lheading: /^((?:(?!^bull ).|\n(?!\n|bull ))+?)\n {0,3}(=+|-+) *(?:\n+|$)/, + // regex template, placeholders will be replaced according to different paragraph + // interruption rules of commonmark and the original markdown spec: + _paragraph: /^([^\n]+(?:\n(?!hr|heading|lheading|blockquote|fences|list|html|table| +\n)[^\n]+)*)/, + text: /^[^\n]+/ +}; + +block._label = /(?!\s*\])(?:\\.|[^\[\]\\])+/; +block._title = /(?:"(?:\\"?|[^"\\])*"|'[^'\n]*(?:\n[^'\n]+)*\n?'|\([^()]*\))/; +block.def = edit(block.def) + .replace('label', block._label) + .replace('title', block._title) + .getRegex(); + +block.bullet = /(?:[*+-]|\d{1,9}[.)])/; +block.listItemStart = edit(/^( *)(bull) */) + .replace('bull', block.bullet) + .getRegex(); + +block.list = edit(block.list) + .replace(/bull/g, block.bullet) + .replace('hr', '\\n+(?=\\1?(?:(?:- *){3,}|(?:_ *){3,}|(?:\\* *){3,})(?:\\n+|$))') + .replace('def', '\\n+(?=' + block.def.source + ')') + .getRegex(); + +block._tag = 'address|article|aside|base|basefont|blockquote|body|caption' + + '|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption' + + '|figure|footer|form|frame|frameset|h[1-6]|head|header|hr|html|iframe' + + '|legend|li|link|main|menu|menuitem|meta|nav|noframes|ol|optgroup|option' + + '|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr' + + '|track|ul'; +block._comment = /|$)/; +block.html = edit(block.html, 'i') + .replace('comment', block._comment) + .replace('tag', block._tag) + .replace('attribute', / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/) + .getRegex(); + +block.lheading = edit(block.lheading) + .replace(/bull/g, block.bullet) // lists can interrupt + .getRegex(); + +block.paragraph = edit(block._paragraph) + .replace('hr', block.hr) + .replace('heading', ' {0,3}#{1,6} ') + .replace('|lheading', '') // setex headings don't interrupt commonmark paragraphs + .replace('|table', '') + .replace('blockquote', ' {0,3}>') + .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n') + .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt + .replace('html', ')|<(?:script|pre|style|textarea|!--)') + .replace('tag', block._tag) // pars can be interrupted by type (6) html blocks + .getRegex(); + +block.blockquote = edit(block.blockquote) + .replace('paragraph', block.paragraph) + .getRegex(); + +/** + * Normal Block Grammar + */ + +block.normal = { ...block }; + +/** + * GFM Block Grammar + */ + +block.gfm = { + ...block.normal, + table: '^ *([^\\n ].*\\|.*)\\n' // Header + + ' {0,3}(?:\\| *)?(:?-+:? *(?:\\| *:?-+:? *)*)(?:\\| *)?' // Align + + '(?:\\n((?:(?! *\\n|hr|heading|blockquote|code|fences|list|html).*(?:\\n|$))*)\\n*|$)' // Cells +}; + +block.gfm.table = edit(block.gfm.table as Rule) + .replace('hr', block.hr) + .replace('heading', ' {0,3}#{1,6} ') + .replace('blockquote', ' {0,3}>') + .replace('code', ' {4}[^\\n]') + .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n') + .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt + .replace('html', ')|<(?:script|pre|style|textarea|!--)') + .replace('tag', block._tag) // tables can be interrupted by type (6) html blocks + .getRegex(); + +block.gfm.paragraph = edit(block._paragraph) + .replace('hr', block.hr) + .replace('heading', ' {0,3}#{1,6} ') + .replace('|lheading', '') // setex headings don't interrupt commonmark paragraphs + .replace('table', block.gfm.table as RegExp) // interrupt paragraphs with table + .replace('blockquote', ' {0,3}>') + .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n') + .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt + .replace('html', ')|<(?:script|pre|style|textarea|!--)') + .replace('tag', block._tag) // pars can be interrupted by type (6) html blocks + .getRegex(); +/** + * Pedantic grammar (original John Gruber's loose markdown specification) + */ + +block.pedantic = { + ...block.normal, + html: edit( + '^ *(?:comment *(?:\\n|\\s*$)' + + '|<(tag)[\\s\\S]+? *(?:\\n{2,}|\\s*$)' // closed tag + + '|\\s]*)*?/?> *(?:\\n{2,}|\\s*$))') + .replace('comment', block._comment) + .replace(/tag/g, '(?!(?:' + + 'a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub' + + '|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)' + + '\\b)\\w+(?!:|[^\\w\\s@]*@)\\b') + .getRegex(), + def: /^ *\[([^\]]+)\]: *]+)>?(?: +(["(][^\n]+[")]))? *(?:\n+|$)/, + heading: /^(#{1,6})(.*)(?:\n+|$)/, + fences: noopTest, // fences not supported + lheading: /^(.+?)\n {0,3}(=+|-+) *(?:\n+|$)/, + paragraph: edit(block.normal._paragraph as Rule) + .replace('hr', block.hr) + .replace('heading', ' *#{1,6} *[^\n]') + .replace('lheading', block.lheading) + .replace('blockquote', ' {0,3}>') + .replace('|fences', '') + .replace('|list', '') + .replace('|html', '') + .getRegex() +}; + +/** + * Inline-Level Grammar + */ +// Not all rules are defined in the object literal +// @ts-expect-error +export const inline: Record & Record & Rules = { + escape: /^\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/, + autolink: /^<(scheme:[^\s\x00-\x1f<>]*|email)>/, + url: noopTest, + tag: '^comment' + + '|^' // self-closing tag + + '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag + + '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. + + '|^' // declaration, e.g. + + '|^', // CDATA section + link: /^!?\[(label)\]\(\s*(href)(?:\s+(title))?\s*\)/, + reflink: /^!?\[(label)\]\[(ref)\]/, + nolink: /^!?\[(ref)\](?:\[\])?/, + reflinkSearch: 'reflink|nolink(?!\\()', + emStrong: { + lDelim: /^(?:\*+(?:((?!\*)[punct])|[^\s*]))|^_+(?:((?!_)[punct])|([^\s_]))/, + // (1) and (2) can only be a Right Delimiter. (3) and (4) can only be Left. (5) and (6) can be either Left or Right. + // | Skip orphan inside strong | Consume to delim | (1) #*** | (2) a***#, a*** | (3) #***a, ***a | (4) ***# | (5) #***# | (6) a***a + rDelimAst: /^[^_*]*?__[^_*]*?\*[^_*]*?(?=__)|[^*]+(?=[^*])|(?!\*)[punct](\*+)(?=[\s]|$)|[^punct\s](\*+)(?!\*)(?=[punct\s]|$)|(?!\*)[punct\s](\*+)(?=[^punct\s])|[\s](\*+)(?!\*)(?=[punct])|(?!\*)[punct](\*+)(?!\*)(?=[punct])|[^punct\s](\*+)(?=[^punct\s])/, + rDelimUnd: /^[^_*]*?\*\*[^_*]*?_[^_*]*?(?=\*\*)|[^_]+(?=[^_])|(?!_)[punct](_+)(?=[\s]|$)|[^punct\s](_+)(?!_)(?=[punct\s]|$)|(?!_)[punct\s](_+)(?=[^punct\s])|[\s](_+)(?!_)(?=[punct])|(?!_)[punct](_+)(?!_)(?=[punct])/ // ^- Not allowed for _ + }, + code: /^(`+)([^`]|[^`][\s\S]*?[^`])\1(?!`)/, + br: /^( {2,}|\\)\n(?!\s*$)/, + del: noopTest, + text: /^(`+|[^`])(?:(?= {2,}\n)|[\s\S]*?(?:(?=[\\`^|~'; +// list of punctuation marks from CommonMark spec +// without * and _ to handle the different emphasis markers * and _ +inline._uc_punctuation = '\\u00A1\\u00A7\\u00AB\\u00B6\\u00B7\\u00BB\\u00BF\\u037E\\u0387\\u055A-\\u055F\\u0589\\u058A\\u05BE\\u05C0\\u05C3\\u05C6\\u05F3\\u05F4\\u0609\\u060A\\u060C\\u060D\\u061B\\u061E\\u061F\\u066A-\\u066D\\u06D4\\u0700-\\u070D\\u07F7-\\u07F9\\u0830-\\u083E\\u085E\\u0964\\u0965\\u0970\\u0AF0\\u0DF4\\u0E4F\\u0E5A\\u0E5B\\u0F04-\\u0F12\\u0F14\\u0F3A-\\u0F3D\\u0F85\\u0FD0-\\u0FD4\\u0FD9\\u0FDA\\u104A-\\u104F\\u10FB\\u1360-\\u1368\\u1400\\u166D\\u166E\\u169B\\u169C\\u16EB-\\u16ED\\u1735\\u1736\\u17D4-\\u17D6\\u17D8-\\u17DA\\u1800-\\u180A\\u1944\\u1945\\u1A1E\\u1A1F\\u1AA0-\\u1AA6\\u1AA8-\\u1AAD\\u1B5A-\\u1B60\\u1BFC-\\u1BFF\\u1C3B-\\u1C3F\\u1C7E\\u1C7F\\u1CC0-\\u1CC7\\u1CD3\\u2010-\\u2027\\u2030-\\u2043\\u2045-\\u2051\\u2053-\\u205E\\u207D\\u207E\\u208D\\u208E\\u2308-\\u230B\\u2329\\u232A\\u2768-\\u2775\\u27C5\\u27C6\\u27E6-\\u27EF\\u2983-\\u2998\\u29D8-\\u29DB\\u29FC\\u29FD\\u2CF9-\\u2CFC\\u2CFE\\u2CFF\\u2D70\\u2E00-\\u2E2E\\u2E30-\\u2E42\\u3001-\\u3003\\u3008-\\u3011\\u3014-\\u301F\\u3030\\u303D\\u30A0\\u30FB\\uA4FE\\uA4FF\\uA60D-\\uA60F\\uA673\\uA67E\\uA6F2-\\uA6F7\\uA874-\\uA877\\uA8CE\\uA8CF\\uA8F8-\\uA8FA\\uA8FC\\uA92E\\uA92F\\uA95F\\uA9C1-\\uA9CD\\uA9DE\\uA9DF\\uAA5C-\\uAA5F\\uAADE\\uAADF\\uAAF0\\uAAF1\\uABEB\\uFD3E\\uFD3F\\uFE10-\\uFE19\\uFE30-\\uFE52\\uFE54-\\uFE61\\uFE63\\uFE68\\uFE6A\\uFE6B\\uFF01-\\uFF03\\uFF05-\\uFF0A\\uFF0C-\\uFF0F\\uFF1A\\uFF1B\\uFF1F\\uFF20\\uFF3B-\\uFF3D\\uFF3F\\uFF5B\\uFF5D\\uFF5F-\\uFF65'; +inline._punctuation = '!"#$%&\'()+\\-.,/:;<=>?@\\[\\]`^{|}~\\\\' + inline._uc_punctuation; +inline.punctuation = edit(inline.punctuation, 'u').replace(/punctuation/g, inline._punctuation).getRegex(); + +// sequences em should skip over [title](link), `code`, +inline.blockSkip = /\[[^[\]]*?\]\([^\(\)]*?\)|`[^`]*?`|<[^<>]*?>/g; +inline.anyPunctuation = /\\[punct]/g; +inline._escapes = /\\([punct])/g; + +inline._comment = edit(block._comment).replace('(?:-->|$)', '-->').getRegex(); + +inline.emStrong.lDelim = edit(inline.emStrong.lDelim as Rule, 'u') + .replace(/punct/g, inline._punctuation) + .getRegex(); + +inline.emStrong.rDelimAst = edit(inline.emStrong.rDelimAst as Rule, 'gu') + .replace(/punct/g, inline._punctuation) + .getRegex(); + +inline.emStrong.rDelimUnd = edit(inline.emStrong.rDelimUnd as Rule, 'gu') + .replace(/punct/g, inline._punctuation) + .getRegex(); + +inline.anyPunctuation = edit(inline.anyPunctuation as Rule, 'gu') + .replace(/punct/g, inline._punctuation) + .getRegex(); + +inline._escapes = edit(inline._escapes, 'gu') + .replace(/punct/g, inline._punctuation) + .getRegex(); + +inline._scheme = /[a-zA-Z][a-zA-Z0-9+.-]{1,31}/; +inline._email = /[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+(@)[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)+(?![-_])/; +inline.autolink = edit(inline.autolink) + .replace('scheme', inline._scheme) + .replace('email', inline._email) + .getRegex(); + +inline._attribute = /\s+[a-zA-Z:_][\w.:-]*(?:\s*=\s*"[^"]*"|\s*=\s*'[^']*'|\s*=\s*[^\s"'=<>`]+)?/; + +inline.tag = edit(inline.tag) + .replace('comment', inline._comment) + .replace('attribute', inline._attribute) + .getRegex(); + +inline._label = /(?:\[(?:\\.|[^\[\]\\])*\]|\\.|`[^`]*`|[^\[\]\\`])*?/; +inline._href = /<(?:\\.|[^\n<>\\])+>|[^\s\x00-\x1f]*/; +inline._title = /"(?:\\"?|[^"\\])*"|'(?:\\'?|[^'\\])*'|\((?:\\\)?|[^)\\])*\)/; + +inline.link = edit(inline.link) + .replace('label', inline._label) + .replace('href', inline._href) + .replace('title', inline._title) + .getRegex(); + +inline.reflink = edit(inline.reflink) + .replace('label', inline._label) + .replace('ref', block._label) + .getRegex(); + +inline.nolink = edit(inline.nolink) + .replace('ref', block._label) + .getRegex(); + +inline.reflinkSearch = edit(inline.reflinkSearch, 'g') + .replace('reflink', inline.reflink) + .replace('nolink', inline.nolink) + .getRegex(); + +/** + * Normal Inline Grammar + */ + +inline.normal = { ...inline }; + +/** + * Pedantic Inline Grammar + */ + +inline.pedantic = { + ...inline.normal, + strong: { + start: /^__|\*\*/, + middle: /^__(?=\S)([\s\S]*?\S)__(?!_)|^\*\*(?=\S)([\s\S]*?\S)\*\*(?!\*)/, + endAst: /\*\*(?!\*)/g, + endUnd: /__(?!_)/g + }, + em: { + start: /^_|\*/, + middle: /^()\*(?=\S)([\s\S]*?\S)\*(?!\*)|^_(?=\S)([\s\S]*?\S)_(?!_)/, + endAst: /\*(?!\*)/g, + endUnd: /_(?!_)/g + }, + link: edit(/^!?\[(label)\]\((.*?)\)/) + .replace('label', inline._label) + .getRegex(), + reflink: edit(/^!?\[(label)\]\s*\[([^\]]*)\]/) + .replace('label', inline._label) + .getRegex() +}; + +/** + * GFM Inline Grammar + */ + +inline.gfm = { + ...inline.normal, + escape: edit(inline.escape).replace('])', '~|])').getRegex(), + _extended_email: /[A-Za-z0-9._+-]+(@)[a-zA-Z0-9-_]+(?:\.[a-zA-Z0-9-_]*[a-zA-Z0-9])+(?![-_])/, + url: /^((?:ftp|https?):\/\/|www\.)(?:[a-zA-Z0-9\-]+\.?)+[^\s<]*|^email/, + _backpedal: /(?:[^?!.,:;*_'"~()&]+|\([^)]*\)|&(?![a-zA-Z0-9]+;$)|[?!.,:;*_'"~)]+(?!$))+/, + del: /^(~~?)(?=[^\s~])([\s\S]*?[^\s~])\1(?=[^~]|$)/, + text: /^([`~]+|[^`~])(?:(?= {2,}\n)|(?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@)|[\s\S]*?(?:(?=[\\