docsify（二）：新增生成字典/词库功能

放假了，马上要封楼，先大概记录一下思路与实现过程，细节年后再完善。（其实我是怕自己年后给忘了。。。。）

依赖docsify 和 docsify-pdf-converter@2.1.0-beta.0

可参考《docsify（一）》

要求原docsify工程中index.html里的配置参数，单独写成独立的docsify.config.js文件。

其余无需改动

项目部署完成，执行 npm run convert，会生成在项目目录中生成pdf文档和词库（dictionaries.json）

再正常启动docsify工程执行docsify serve

服务启动后，平台端可以通过访问http://localhost:3000/dictionaries.json来获取词库，再返回给ics项目前端，从而完成项目web页面中对文档的检索功能。

前端（或后台）拿到词库后，按照docsify中的dosearch函数逻辑即可完成检索

具体实现方式，新增以下代码：

相关文件：

markdown-combine.js 源文件改动了部分代码（中文注释处）；

slugify.js 新增文件此文件中的代码取自docsify源码slugify.函数部分；

marked.js 新增文件此文件中的代码取自docsify源码marked函数部分；

createLibrary.js 新增文件此文件中代码都是新开发的，重要逻辑已添加注释；

1. node_modules\docsify-pdf-converter\src\markdown-combine.js

const fs = require("fs");
const util = require("util");
const path = require("path");
const logger = require("./logger.js");
const processImagesPaths = require("./process-images-paths.js");
const processInnerLinks = require("./process-inner-links.js");
const createLibrary = require("./createLibrary");const [readFile, writeFile, exists] = [fs.readFile, fs.writeFile, fs.exists].map(fn =>util.promisify(fn),
);const combineMarkdowns = ({ contents, pathToStatic, mainMdFilename, mkdir }) => async links => {let contentsPaths = Array.isArray(contents) ? contents : [contents];//是否开启目录mkdir && links.unshift(contentsPaths[0].replace(/\//g, '\\'))//获取根路径  40行传给process-inner-links模块let dir = path.dirname(path.resolve(contentsPaths[0]))try {const files = await Promise.all(await links.map(async filename => {const fileExist = await exists(filename);if (fileExist) {const content = await readFile(filename, {encoding: "utf8",});return {content,name: filename,};}throw new Error(`file ${filename} is not exist, but listed in ${contents}`);}),);const resultFilePath = path.resolve(pathToStatic, mainMdFilename);// 所有内容前面拼接的字符串let baseContentStart = ''//创建字典备用的两个参数let tempLinks = [...links]let tempFiles = [...files]//如果开启目录if (mkdir) {//创建字典时需要把目录页忽略tempLinks.shift()tempFiles.shift()//目录页后 另起新的页面files[0].content = files[0].content + "<div style='page-break-after:always;'></div>"//在“目录”前拼接目录标题baseContentStart = '# **目录** \r\n'}createLibrary(tempLinks, tempFiles, dir)try {const content = files.map((...rest) => processInnerLinks(dir, ...rest)) //设置内部链接.map(processImagesPaths({ pathToStatic })).join("\n\n\n\n\n\n");await writeFile(resultFilePath, baseContentStart + content);} catch (e) {logger.err("markdown combining error", e);throw e;}return resultFilePath;} catch (err) {logger.err("combineMarkdowns", err);throw err;}
};module.exports = config => ({combineMarkdowns: combineMarkdowns(config),
});

2. node_modules\docsify-pdf-converter\src\slugify.js

/*** 此模块取自docsify 源码部分 slugify相关模块*/
var hasOwn = Object.prototype.hasOwnProperty;
var re = /[\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&()*+,./:;<=>?@[\]^`{|}~]/g;
var cache$1 = {};function lower(string) {return string.toLowerCase()
}function slugify(str) {if (typeof str !== 'string') {return ''}var slug = str.trim().replace(/[A-Z]+/g, lower).replace(/<[^>\d]+>/g, '').replace(re, '').replace(/\s/g, '-').replace(/-+/g, '-').replace(/^(\d)/, '_$1');var count = cache$1[slug];count = hasOwn.call(cache$1, slug) ? count + 1 : 0;cache$1[slug] = count;if (count) {slug = slug + '-' + count;}return slug
}slugify.clear = function () {cache$1 = {};
};module.exports = slugify

3. node_modules\docsify-pdf-converter\src\marked.js

/*** 此模块取自docsify 源码部分 marked相关模块*/
var commonjsGlobal = typeof window !== 'undefined' ? window : typeof global !== 'undefined' ? global : typeof self !== 'undefined' ? self : {};function createCommonjsModule(fn, module) {return module = { exports: {} }, fn(module, module.exports), module.exports;
}function edit(regex, opt) {regex = regex.source || regex;opt = opt || '';return {replace: function (name, val) {val = val.source || val;val = val.replace(/(^|[^\[])\^/g, '$1');regex = regex.replace(name, val);return this;},getRegex: function () {return new RegExp(regex, opt);}};
}function merge(obj) {var arguments$1 = arguments;var i = 1,target,key;for (; i < arguments.length; i++) {target = arguments$1[i];for (key in target) {if (Object.prototype.hasOwnProperty.call(target, key)) {obj[key] = target[key];}}}return obj;
}module.exports = createCommonjsModule(function (module, exports) {/*** marked - a markdown parser* Copyright (c) 2011-2018, Christopher Jeffrey. (MIT Licensed)* https://github.com/markedjs/marked*/(function (root) {var block = {newline: /^\n+/,code: /^( {4}[^\n]+\n*)+/,fences: noop,hr: /^ {0,3}((?:- *){3,}|(?:_ *){3,}|(?:\* *){3,})(?:\n+|$)/,heading: /^ *(#{1,6}) *([^\n]+?) *(?:#+ *)?(?:\n+|$)/,nptable: noop,blockquote: /^( {0,3}> ?(paragraph|[^\n]*)(?:\n|$))+/,list: /^( *)(bull) [\s\S]+?(?:hr|def|\n{2,}(?! )(?!\1bull )\n*|\s*$)/,html: '^ {0,3}(?:' // optional indentation+ '<(script|pre|style)[\\s>][\\s\\S]*?(?:</\\1>[^\\n]*\\n+|$)' // (1)+ '|comment[^\\n]*(\\n+|$)' // (2)+ '|<\\?[\\s\\S]*?\\?>\\n*' // (3)+ '|<![A-Z][\\s\\S]*?>\\n*' // (4)+ '|<!\\[CDATA\\[[\\s\\S]*?\\]\\]>\\n*' // (5)+ '|</?(tag)(?: +|\\n|/?>)[\\s\\S]*?(?:\\n{2,}|$)' // (6)+ '|<(?!script|pre|style)([a-z][\\w-]*)(?:attribute)*? */?>(?=\\h*\\n)[\\s\\S]*?(?:\\n{2,}|$)' // (7) open tag+ '|</(?!script|pre|style)[a-z][\\w-]*\\s*>(?=\\h*\\n)[\\s\\S]*?(?:\\n{2,}|$)' // (7) closing tag+ ')',def: /^ {0,3}\[(label)\]: *\n? *<?([^\s>]+)>?(?:(?: +\n? *| *\n *)(title))? *(?:\n+|$)/,table: noop,lheading: /^([^\n]+)\n *(=|-){2,} *(?:\n+|$)/,paragraph: /^([^\n]+(?:\n(?!hr|heading|lheading| {0,3}>|<\/?(?:tag)(?: +|\n|\/?>)|<(?:script|pre|style|!--))[^\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+\.)/;block.item = /^( *)(bull) [^\n]*(?:\n(?!\1bull )[^\n]*)*/;block.item = edit(block.item, 'gm').replace(/bull/g, block.bullet).getRegex();block.list = edit(block.list).replace(/bull/g, block.bullet).replace('hr', '\\n+(?=\\1?(?:(?:- *){3,}|(?:_ *){3,}|(?:\\* *){3,})(?:\\n+|$))').replace('def', '\\n+(?=' + block.def.source + ')').getRegex();block._tag = 'address|article|aside|base|basefont|blockquote|body|caption'+ '|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption'+ '|figure|footer|form|frame|frameset|h[1-6]|head|header|hr|html|iframe'+ '|legend|li|link|main|menu|menuitem|meta|nav|noframes|ol|optgroup|option'+ '|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr'+ '|track|ul';block._comment = /<!--(?!-?>)[\s\S]*?-->/;block.html = edit(block.html, 'i').replace('comment', block._comment).replace('tag', block._tag).replace('attribute', / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/).getRegex();block.paragraph = edit(block.paragraph).replace('hr', block.hr).replace('heading', block.heading).replace('lheading', block.lheading).replace('tag', block._tag) // pars can be interrupted by type (6) html blocks.getRegex();block.blockquote = edit(block.blockquote).replace('paragraph', block.paragraph).getRegex();/*** Normal Block Grammar*/block.normal = merge({}, block);/*** GFM Block Grammar*/block.gfm = merge({}, block.normal, {fences: /^ *(`{3,}|~{3,})[ \.]*(\S+)? *\n([\s\S]*?)\n? *\1 *(?:\n+|$)/,paragraph: /^/,heading: /^ *(#{1,6}) +([^\n]+?) *#* *(?:\n+|$)/});block.gfm.paragraph = edit(block.paragraph).replace('(?!', '(?!'+ block.gfm.fences.source.replace('\\1', '\\2') + '|'+ block.list.source.replace('\\1', '\\3') + '|').getRegex();/*** GFM + Tables Block Grammar*/block.tables = merge({}, block.gfm, {nptable: /^ *([^|\n ].*\|.*)\n *([-:]+ *\|[-| :]*)(?:\n((?:.*[^>\n ].*(?:\n|$))*)\n*|$)/,table: /^ *\|(.+)\n *\|?( *[-:]+[-| :]*)(?:\n((?: *[^>\n ].*(?:\n|$))*)\n*|$)/});/*** Pedantic grammar*/block.pedantic = merge({}, block.normal, {html: edit('^ *(?:comment *(?:\\n|\\s*$)'+ '|<(tag)[\\s\\S]+?</\\1> *(?:\\n{2,}|\\s*$)' // closed tag+ '|<tag(?:"[^"]*"|\'[^\']*\'|\\s[^\'"/>\\s]*)*?/?> *(?:\\n{2,}|\\s*$))').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: /^ *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +(["(][^\n]+[")]))? *(?:\n+|$)/});/*** Block Lexer*/function Lexer(options) {this.tokens = [];this.tokens.links = Object.create(null);this.options = options || marked.defaults;this.rules = block.normal;if (this.options.pedantic) {this.rules = block.pedantic;} else if (this.options.gfm) {if (this.options.tables) {this.rules = block.tables;} else {this.rules = block.gfm;}}}/*** Expose Block Rules*/Lexer.rules = block;/*** Static Lex Method*/Lexer.lex = function (src, options) {var lexer = new Lexer(options);return lexer.lex(src);};/*** Preprocessing*/Lexer.prototype.lex = function (src) {src = src.replace(/\r\n|\r/g, '\n').replace(/\t/g, '    ').replace(/\u00a0/g, ' ').replace(/\u2424/g, '\n');return this.token(src, true);};/*** Lexing*/Lexer.prototype.token = function (src, top) {var this$1 = this;src = src.replace(/^ +$/gm, '');var next,loose,cap,bull,b,item,listStart,listItems,t,space,i,tag,l,isordered,istask,ischecked;while (src) {// newlineif (cap = this$1.rules.newline.exec(src)) {src = src.substring(cap[0].length);if (cap[0].length > 1) {this$1.tokens.push({type: 'space'});}}// codeif (cap = this$1.rules.code.exec(src)) {src = src.substring(cap[0].length);cap = cap[0].replace(/^ {4}/gm, '');this$1.tokens.push({type: 'code',text: !this$1.options.pedantic? rtrim(cap, '\n'): cap});continue;}// fences (gfm)if (cap = this$1.rules.fences.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'code',lang: cap[2],text: cap[3] || ''});continue;}// headingif (cap = this$1.rules.heading.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'heading',depth: cap[1].length,text: cap[2]});continue;}// table no leading pipe (gfm)if (top && (cap = this$1.rules.nptable.exec(src))) {item = {type: 'table',header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : []};if (item.header.length === item.align.length) {src = src.substring(cap[0].length);for (i = 0; i < item.align.length; i++) {if (/^ *-+: *$/.test(item.align[i])) {item.align[i] = 'right';} else if (/^ *:-+: *$/.test(item.align[i])) {item.align[i] = 'center';} else if (/^ *:-+ *$/.test(item.align[i])) {item.align[i] = 'left';} else {item.align[i] = null;}}for (i = 0; i < item.cells.length; i++) {item.cells[i] = splitCells(item.cells[i], item.header.length);}this$1.tokens.push(item);continue;}}// hrif (cap = this$1.rules.hr.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'hr'});continue;}// blockquoteif (cap = this$1.rules.blockquote.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'blockquote_start'});cap = cap[0].replace(/^ *> ?/gm, '');// Pass `top` to keep the current// "toplevel" state. This is exactly// how markdown.pl works.this$1.token(cap, top);this$1.tokens.push({type: 'blockquote_end'});continue;}// listif (cap = this$1.rules.list.exec(src)) {src = src.substring(cap[0].length);bull = cap[2];isordered = bull.length > 1;listStart = {type: 'list_start',ordered: isordered,start: isordered ? +bull : '',loose: false};this$1.tokens.push(listStart);// Get each top-level item.cap = cap[0].match(this$1.rules.item);listItems = [];next = false;l = cap.length;i = 0;for (; i < l; i++) {item = cap[i];// Remove the list item's bullet// so it is seen as the next token.space = item.length;item = item.replace(/^ *([*+-]|\d+\.) +/, '');// Outdent whatever the// list item contains. Hacky.if (~item.indexOf('\n ')) {space -= item.length;item = !this$1.options.pedantic? item.replace(new RegExp('^ {1,' + space + '}', 'gm'), ''): item.replace(/^ {1,4}/gm, '');}// Determine whether the next list item belongs here.// Backpedal if it does not belong in this list.if (this$1.options.smartLists && i !== l - 1) {b = block.bullet.exec(cap[i + 1])[0];if (bull !== b && !(bull.length > 1 && b.length > 1)) {src = cap.slice(i + 1).join('\n') + src;i = l - 1;}}// Determine whether item is loose or not.// Use: /(^|\n)(?! )[^\n]+\n\n(?!\s*$)/// for discount behavior.loose = next || /\n\n(?!\s*$)/.test(item);if (i !== l - 1) {next = item.charAt(item.length - 1) === '\n';if (!loose) { loose = next; }}if (loose) {listStart.loose = true;}// Check for task list itemsistask = /^\[[ xX]\] /.test(item);ischecked = undefined;if (istask) {ischecked = item[1] !== ' ';item = item.replace(/^\[[ xX]\] +/, '');}t = {type: 'list_item_start',task: istask,checked: ischecked,loose: loose};listItems.push(t);this$1.tokens.push(t);// Recurse.this$1.token(item, false);this$1.tokens.push({type: 'list_item_end'});}if (listStart.loose) {l = listItems.length;i = 0;for (; i < l; i++) {listItems[i].loose = true;}}this$1.tokens.push({type: 'list_end'});continue;}// htmlif (cap = this$1.rules.html.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: this$1.options.sanitize? 'paragraph': 'html',pre: !this$1.options.sanitizer&& (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'),text: cap[0]});continue;}// defif (top && (cap = this$1.rules.def.exec(src))) {src = src.substring(cap[0].length);if (cap[3]) { cap[3] = cap[3].substring(1, cap[3].length - 1); }tag = cap[1].toLowerCase().replace(/\s+/g, ' ');if (!this$1.tokens.links[tag]) {this$1.tokens.links[tag] = {href: cap[2],title: cap[3]};}continue;}// table (gfm)if (top && (cap = this$1.rules.table.exec(src))) {item = {type: 'table',header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),cells: cap[3] ? cap[3].replace(/(?: *\| *)?\n$/, '').split('\n') : []};if (item.header.length === item.align.length) {src = src.substring(cap[0].length);for (i = 0; i < item.align.length; i++) {if (/^ *-+: *$/.test(item.align[i])) {item.align[i] = 'right';} else if (/^ *:-+: *$/.test(item.align[i])) {item.align[i] = 'center';} else if (/^ *:-+ *$/.test(item.align[i])) {item.align[i] = 'left';} else {item.align[i] = null;}}for (i = 0; i < item.cells.length; i++) {item.cells[i] = splitCells(item.cells[i].replace(/^ *\| *| *\| *$/g, ''),item.header.length);}this$1.tokens.push(item);continue;}}// lheadingif (cap = this$1.rules.lheading.exec(src)) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'heading',depth: cap[2] === '=' ? 1 : 2,text: cap[1]});continue;}// top-level paragraphif (top && (cap = this$1.rules.paragraph.exec(src))) {src = src.substring(cap[0].length);this$1.tokens.push({type: 'paragraph',text: cap[1].charAt(cap[1].length - 1) === '\n'? cap[1].slice(0, -1): cap[1]});continue;}// textif (cap = this$1.rules.text.exec(src)) {// Top-level should never reach here.src = src.substring(cap[0].length);this$1.tokens.push({type: 'text',text: cap[0]});continue;}if (src) {throw new Error('Infinite loop on byte: ' + src.charCodeAt(0));}}return this.tokens;};/*** Inline-Level Grammar*/var inline = {escape: /^\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/,autolink: /^<(scheme:[^\s\x00-\x1f<>]*|email)>/,url: noop,tag: '^comment'+ '|^</[a-zA-Z][\\w:-]*\\s*>' // self-closing tag+ '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag+ '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. <?php ?>+ '|^<![a-zA-Z]+\\s[\\s\\S]*?>' // declaration, e.g. <!DOCTYPE html>+ '|^<!\\[CDATA\\[[\\s\\S]*?\\]\\]>', // CDATA sectionlink: /^!?\[(label)\]\(href(?:\s+(title))?\s*\)/,reflink: /^!?\[(label)\]\[(?!\s*\])((?:\\[\[\]]?|[^\[\]\\])+)\]/,nolink: /^!?\[(?!\s*\])((?:\[[^\[\]]*\]|\\[\[\]]|[^\[\]])*)\](?:\[\])?/,strong: /^__([^\s])__(?!_)|^\*\*([^\s])\*\*(?!\*)|^__([^\s][\s\S]*?[^\s])__(?!_)|^\*\*([^\s][\s\S]*?[^\s])\*\*(?!\*)/,em: /^_([^\s_])_(?!_)|^\*([^\s*"<\[])\*(?!\*)|^_([^\s][\s\S]*?[^\s_])_(?!_)|^_([^\s_][\s\S]*?[^\s])_(?!_)|^\*([^\s"<\[][\s\S]*?[^\s*])\*(?!\*)|^\*([^\s*"<\[][\s\S]*?[^\s])\*(?!\*)/,code: /^(`+)([^`]|[^`][\s\S]*?[^`])\1(?!`)/,br: /^( {2,}|\\)\n(?!\s*$)/,del: noop,text: /^(`+|[^`])[\s\S]*?(?=[\\<!\[`*]|\b_| {2,}\n|$)/};inline._escapes = /\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/g;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', block._comment).replace('attribute', inline._attribute).getRegex();inline._label = /(?:\[[^\[\]]*\]|\\[\[\]]?|`[^`]*`|[^\[\]\\])*?/;inline._href = /\s*(<(?:\\[<>]?|[^\s<>\\])*>|(?:\\[()]?|\([^\s\x00-\x1f\\]*\)|[^\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).getRegex();/*** Normal Inline Grammar*/inline.normal = merge({}, inline);/*** Pedantic Inline Grammar*/inline.pedantic = merge({}, inline.normal, {strong: /^__(?=\S)([\s\S]*?\S)__(?!_)|^\*\*(?=\S)([\s\S]*?\S)\*\*(?!\*)/,em: /^_(?=\S)([\s\S]*?\S)_(?!_)|^\*(?=\S)([\s\S]*?\S)\*(?!\*)/,link: edit(/^!?\[(label)\]\((.*?)\)/).replace('label', inline._label).getRegex(),reflink: edit(/^!?\[(label)\]\s*\[([^\]]*)\]/).replace('label', inline._label).getRegex()});/*** GFM Inline Grammar*/inline.gfm = merge({}, 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)~+/,text: edit(inline.text).replace(']|', '~]|').replace('|$', '|https?://|ftp://|www\\.|[a-zA-Z0-9.!#$%&\'*+/=?^_`{\\|}~-]+@|$').getRegex()});inline.gfm.url = edit(inline.gfm.url).replace('email', inline.gfm._extended_email).getRegex();/*** GFM + Line Breaks Inline Grammar*/inline.breaks = merge({}, inline.gfm, {br: edit(inline.br).replace('{2,}', '*').getRegex(),text: edit(inline.gfm.text).replace('{2,}', '*').getRegex()});/*** Inline Lexer & Compiler*/function InlineLexer(links, options) {this.options = options || marked.defaults;this.links = links;this.rules = inline.normal;this.renderer = this.options.renderer || new Renderer();this.renderer.options = this.options;if (!this.links) {throw new Error('Tokens array requires a `links` property.');}if (this.options.pedantic) {this.rules = inline.pedantic;} else if (this.options.gfm) {if (this.options.breaks) {this.rules = inline.breaks;} else {this.rules = inline.gfm;}}}/*** Expose Inline Rules*/InlineLexer.rules = inline;/*** Static Lexing/Compiling Method*/InlineLexer.output = function (src, links, options) {var inline = new InlineLexer(links, options);return inline.output(src);};/*** Lexing/Compiling*/InlineLexer.prototype.output = function (src) {var this$1 = this;var out = '',link,text,href,title,cap,prevCapZero;while (src) {// escapeif (cap = this$1.rules.escape.exec(src)) {src = src.substring(cap[0].length);out += cap[1];continue;}// autolinkif (cap = this$1.rules.autolink.exec(src)) {src = src.substring(cap[0].length);if (cap[2] === '@') {text = escape(this$1.mangle(cap[1]));href = 'mailto:' + text;} else {text = escape(cap[1]);href = text;}out += this$1.renderer.link(href, null, text);continue;}// url (gfm)if (!this$1.inLink && (cap = this$1.rules.url.exec(src))) {if (cap[2] === '@') {text = escape(cap[0]);href = 'mailto:' + text;} else {// do extended autolink path validationdo {prevCapZero = cap[0];cap[0] = this$1.rules._backpedal.exec(cap[0])[0];} while (prevCapZero !== cap[0]);text = escape(cap[0]);if (cap[1] === 'www.') {href = 'http://' + text;} else {href = text;}}src = src.substring(cap[0].length);out += this$1.renderer.link(href, null, text);continue;}// tagif (cap = this$1.rules.tag.exec(src)) {if (!this$1.inLink && /^<a /i.test(cap[0])) {this$1.inLink = true;} else if (this$1.inLink && /^<\/a>/i.test(cap[0])) {this$1.inLink = false;}if (!this$1.inRawBlock && /^<(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {this$1.inRawBlock = true;} else if (this$1.inRawBlock && /^<\/(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {this$1.inRawBlock = false;}src = src.substring(cap[0].length);out += this$1.options.sanitize? this$1.options.sanitizer? this$1.options.sanitizer(cap[0]): escape(cap[0]): cap[0];continue;}// linkif (cap = this$1.rules.link.exec(src)) {src = src.substring(cap[0].length);this$1.inLink = true;href = cap[2];if (this$1.options.pedantic) {link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href);if (link) {href = link[1];title = link[3];} else {title = '';}} else {title = cap[3] ? cap[3].slice(1, -1) : '';}href = href.trim().replace(/^<([\s\S]*)>$/, '$1');out += this$1.outputLink(cap, {href: InlineLexer.escapes(href),title: InlineLexer.escapes(title)});this$1.inLink = false;continue;}// reflink, nolinkif ((cap = this$1.rules.reflink.exec(src))|| (cap = this$1.rules.nolink.exec(src))) {src = src.substring(cap[0].length);link = (cap[2] || cap[1]).replace(/\s+/g, ' ');link = this$1.links[link.toLowerCase()];if (!link || !link.href) {out += cap[0].charAt(0);src = cap[0].substring(1) + src;continue;}this$1.inLink = true;out += this$1.outputLink(cap, link);this$1.inLink = false;continue;}// strongif (cap = this$1.rules.strong.exec(src)) {src = src.substring(cap[0].length);out += this$1.renderer.strong(this$1.output(cap[4] || cap[3] || cap[2] || cap[1]));continue;}// emif (cap = this$1.rules.em.exec(src)) {src = src.substring(cap[0].length);out += this$1.renderer.em(this$1.output(cap[6] || cap[5] || cap[4] || cap[3] || cap[2] || cap[1]));continue;}// codeif (cap = this$1.rules.code.exec(src)) {src = src.substring(cap[0].length);out += this$1.renderer.codespan(escape(cap[2].trim(), true));continue;}// brif (cap = this$1.rules.br.exec(src)) {src = src.substring(cap[0].length);out += this$1.renderer.br();continue;}// del (gfm)if (cap = this$1.rules.del.exec(src)) {src = src.substring(cap[0].length);out += this$1.renderer.del(this$1.output(cap[1]));continue;}// textif (cap = this$1.rules.text.exec(src)) {src = src.substring(cap[0].length);if (this$1.inRawBlock) {out += this$1.renderer.text(cap[0]);} else {out += this$1.renderer.text(escape(this$1.smartypants(cap[0])));}continue;}if (src) {throw new Error('Infinite loop on byte: ' + src.charCodeAt(0));}}return out;};InlineLexer.escapes = function (text) {return text ? text.replace(InlineLexer.rules._escapes, '$1') : text;};/*** Compile Link*/InlineLexer.prototype.outputLink = function (cap, link) {var href = link.href,title = link.title ? escape(link.title) : null;return cap[0].charAt(0) !== '!'? this.renderer.link(href, title, this.output(cap[1])): this.renderer.image(href, title, escape(cap[1]));};/*** Smartypants Transformations*/InlineLexer.prototype.smartypants = function (text) {if (!this.options.smartypants) { return text; }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 Links*/InlineLexer.prototype.mangle = function (text) {if (!this.options.mangle) { return text; }var out = '',l = text.length,i = 0,ch;for (; i < l; i++) {ch = text.charCodeAt(i);if (Math.random() > 0.5) {ch = 'x' + ch.toString(16);}out += '&#' + ch + ';';}return out;};/*** Renderer*/function Renderer(options) {this.options = options || marked.defaults;}Renderer.prototype.code = function (code, lang, escaped) {if (this.options.highlight) {var out = this.options.highlight(code, lang);if (out != null && out !== code) {escaped = true;code = out;}}if (!lang) {return '<pre><code>'+ (escaped ? code : escape(code, true))+ '</code></pre>';}return '<pre><code class="'+ this.options.langPrefix+ escape(lang, true)+ '">'+ (escaped ? code : escape(code, true))+ '</code></pre>\n';};Renderer.prototype.blockquote = function (quote) {return '<blockquote>\n' + quote + '</blockquote>\n';};Renderer.prototype.html = function (html) {return html;};Renderer.prototype.heading = function (text, level, raw) {if (this.options.headerIds) {return '<h'+ level+ ' id="'+ this.options.headerPrefix+ raw.toLowerCase().replace(/[^\w]+/g, '-')+ '">'+ text+ '</h'+ level+ '>\n';}// ignore IDsreturn '<h' + level + '>' + text + '</h' + level + '>\n';};Renderer.prototype.hr = function () {return this.options.xhtml ? '<hr/>\n' : '<hr>\n';};Renderer.prototype.list = function (body, ordered, start) {var type = ordered ? 'ol' : 'ul',startatt = (ordered && start !== 1) ? (' start="' + start + '"') : '';return '<' + type + startatt + '>\n' + body + '</' + type + '>\n';};Renderer.prototype.listitem = function (text) {return '<li>' + text + '</li>\n';};Renderer.prototype.checkbox = function (checked) {return '<input '+ (checked ? 'checked="" ' : '')+ 'disabled="" type="checkbox"'+ (this.options.xhtml ? ' /' : '')+ '> ';};Renderer.prototype.paragraph = function (text) {return '<p>' + text + '</p>\n';};Renderer.prototype.table = function (header, body) {if (body) { body = '<tbody>' + body + '</tbody>'; }return '<table>\n'+ '<thead>\n'+ header+ '</thead>\n'+ body+ '</table>\n';};Renderer.prototype.tablerow = function (content) {return '<tr>\n' + content + '</tr>\n';};Renderer.prototype.tablecell = function (content, flags) {var type = flags.header ? 'th' : 'td';var tag = flags.align? '<' + type + ' align="' + flags.align + '">': '<' + type + '>';return tag + content + '</' + type + '>\n';};// span level rendererRenderer.prototype.strong = function (text) {return '<strong>' + text + '</strong>';};Renderer.prototype.em = function (text) {return '<em>' + text + '</em>';};Renderer.prototype.codespan = function (text) {return '<code>' + text + '</code>';};Renderer.prototype.br = function () {return this.options.xhtml ? '<br/>' : '<br>';};Renderer.prototype.del = function (text) {return '<del>' + text + '</del>';};Renderer.prototype.link = function (href, title, text) {if (this.options.sanitize) {try {var prot = decodeURIComponent(unescape(href)).replace(/[^\w:]/g, '').toLowerCase();} catch (e) {return text;}if (prot.indexOf('javascript:') === 0 || prot.indexOf('vbscript:') === 0 || prot.indexOf('data:') === 0) {return text;}}if (this.options.baseUrl && !originIndependentUrl.test(href)) {href = resolveUrl(this.options.baseUrl, href);}try {href = encodeURI(href).replace(/%25/g, '%');} catch (e) {return text;}var out = '<a href="' + escape(href) + '"';if (title) {out += ' title="' + title + '"';}out += '>' + text + '</a>';return out;};Renderer.prototype.image = function (href, title, text) {if (this.options.baseUrl && !originIndependentUrl.test(href)) {href = resolveUrl(this.options.baseUrl, href);}var out = '<img src="' + href + '" alt="' + text + '"';if (title) {out += ' title="' + title + '"';}out += this.options.xhtml ? '/>' : '>';return out;};Renderer.prototype.text = function (text) {return text;};/*** TextRenderer* returns only the textual part of the token*/function TextRenderer() { }// no need for block level renderersTextRenderer.prototype.strong =TextRenderer.prototype.em =TextRenderer.prototype.codespan =TextRenderer.prototype.del =TextRenderer.prototype.text = function (text) {return text;};TextRenderer.prototype.link =TextRenderer.prototype.image = function (href, title, text) {return '' + text;};TextRenderer.prototype.br = function () {return '';};/*** Parsing & Compiling*/function Parser(options) {this.tokens = [];this.token = null;this.options = options || marked.defaults;this.options.renderer = this.options.renderer || new Renderer();this.renderer = this.options.renderer;this.renderer.options = this.options;}/*** Static Parse Method*/Parser.parse = function (src, options) {var parser = new Parser(options);return parser.parse(src);};/*** Parse Loop*/Parser.prototype.parse = function (src) {var this$1 = this;this.inline = new InlineLexer(src.links, this.options);// use an InlineLexer with a TextRenderer to extract pure textthis.inlineText = new InlineLexer(src.links,merge({}, this.options, { renderer: new TextRenderer() }));this.tokens = src.reverse();var out = '';while (this.next()) {out += this$1.tok();}return out;};/*** Next Token*/Parser.prototype.next = function () {return this.token = this.tokens.pop();};/*** Preview Next Token*/Parser.prototype.peek = function () {return this.tokens[this.tokens.length - 1] || 0;};/*** Parse Text Tokens*/Parser.prototype.parseText = function () {var this$1 = this;var body = this.token.text;while (this.peek().type === 'text') {body += '\n' + this$1.next().text;}return this.inline.output(body);};/*** Parse Current Token*/Parser.prototype.tok = function () {var this$1 = this;switch (this.token.type) {case 'space': {return '';}case 'hr': {return this.renderer.hr();}case 'heading': {return this.renderer.heading(this.inline.output(this.token.text),this.token.depth,unescape(this.inlineText.output(this.token.text)));}case 'code': {return this.renderer.code(this.token.text,this.token.lang,this.token.escaped);}case 'table': {var header = '',body = '',i,row,cell,j;// headercell = '';for (i = 0; i < this.token.header.length; i++) {cell += this$1.renderer.tablecell(this$1.inline.output(this$1.token.header[i]),{ header: true, align: this$1.token.align[i] });}header += this.renderer.tablerow(cell);for (i = 0; i < this.token.cells.length; i++) {row = this$1.token.cells[i];cell = '';for (j = 0; j < row.length; j++) {cell += this$1.renderer.tablecell(this$1.inline.output(row[j]),{ header: false, align: this$1.token.align[j] });}body += this$1.renderer.tablerow(cell);}return this.renderer.table(header, body);}case 'blockquote_start': {body = '';while (this.next().type !== 'blockquote_end') {body += this$1.tok();}return this.renderer.blockquote(body);}case 'list_start': {body = '';var ordered = this.token.ordered,start = this.token.start;while (this.next().type !== 'list_end') {body += this$1.tok();}return this.renderer.list(body, ordered, start);}case 'list_item_start': {body = '';var loose = this.token.loose;if (this.token.task) {body += this.renderer.checkbox(this.token.checked);}while (this.next().type !== 'list_item_end') {body += !loose && this$1.token.type === 'text'? this$1.parseText(): this$1.tok();}return this.renderer.listitem(body);}case 'html': {// TODO parse inline content if parameter markdown=1return this.renderer.html(this.token.text);}case 'paragraph': {return this.renderer.paragraph(this.inline.output(this.token.text));}case 'text': {return this.renderer.paragraph(this.parseText());}}};/*** Helpers*/function escape(html, encode) {if (encode) {if (escape.escapeTest.test(html)) {return html.replace(escape.escapeReplace, function (ch) { return escape.replacements[ch] });}} else {if (escape.escapeTestNoEncode.test(html)) {return html.replace(escape.escapeReplaceNoEncode, function (ch) { return escape.replacements[ch] });}}return html;}escape.escapeTest = /[&<>"']/;escape.escapeReplace = /[&<>"']/g;escape.replacements = {'&': '&amp;','<': '&lt;','>': '&gt;','"': '&quot;',"'": '&#39;'};escape.escapeTestNoEncode = /[<>"']|&(?!#?\w+;)/;escape.escapeReplaceNoEncode = /[<>"']|&(?!#?\w+;)/g;function unescape(html) {// explicitly match decimal, hex, and named HTML entitiesreturn html.replace(/&(#(?:\d+)|(?:#x[0-9A-Fa-f]+)|(?:\w+));?/ig, function (_, 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 '';});}function edit(regex, opt) {regex = regex.source || regex;opt = opt || '';return {replace: function (name, val) {val = val.source || val;val = val.replace(/(^|[^\[])\^/g, '$1');regex = regex.replace(name, val);return this;},getRegex: function () {return new RegExp(regex, opt);}};}function resolveUrl(base, href) {if (!baseUrls[' ' + base]) {// we can ignore everything in base after the last slash of its path component,// but we might need to add _that_// https://tools.ietf.org/html/rfc3986#section-3if (/^[^:]+:\/*[^/]*$/.test(base)) {baseUrls[' ' + base] = base + '/';} else {baseUrls[' ' + base] = rtrim(base, '/', true);}}base = baseUrls[' ' + base];if (href.slice(0, 2) === '//') {return base.replace(/:[\s\S]*/, ':') + href;} else if (href.charAt(0) === '/') {return base.replace(/(:\/*[^/]*)[\s\S]*/, '$1') + href;} else {return base + href;}}var baseUrls = {};var originIndependentUrl = /^$|^[a-z][a-z0-9+.-]*:|^[?#]/i;function noop() { }noop.exec = noop;function merge(obj) {var arguments$1 = arguments;var i = 1,target,key;for (; i < arguments.length; i++) {target = arguments$1[i];for (key in target) {if (Object.prototype.hasOwnProperty.call(target, key)) {obj[key] = target[key];}}}return obj;}function splitCells(tableRow, count) {// ensure that every cell-delimiting pipe has a space// before it to distinguish it from an escaped pipevar row = tableRow.replace(/\|/g, function (match, offset, str) {var escaped = false,curr = offset;while (--curr >= 0 && str[curr] === '\\') { escaped = !escaped; }if (escaped) {// odd number of slashes means | is escaped// so we leave it alonereturn '|';} else {// add space before unescaped |return ' |';}}),cells = row.split(/ \|/),i = 0;if (cells.length > count) {cells.splice(count);} else {while (cells.length < count) { cells.push(''); }}for (; i < cells.length; i++) {// leading or trailing whitespace is ignored per the gfm speccells[i] = cells[i].trim().replace(/\\\|/g, '|');}return cells;}// Remove trailing 'c's. Equivalent to str.replace(/c*$/, '').// /c*$/ is vulnerable to REDOS.// invert: Remove suffix of non-c chars instead. Default falsey.function rtrim(str, c, invert) {if (str.length === 0) {return '';}// Length of suffix matching the invert condition.var suffLen = 0;// Step left until we fail to match the invert condition.while (suffLen < str.length) {var currChar = str.charAt(str.length - suffLen - 1);if (currChar === c && !invert) {suffLen++;} else if (currChar !== c && invert) {suffLen++;} else {break;}}return str.substr(0, str.length - suffLen);}/*** Marked*/function marked(src, opt, callback) {// throw error in case of non string inputif (typeof src === 'undefined' || src === null) {throw new Error('marked(): input parameter is undefined or null');}if (typeof src !== 'string') {throw new Error('marked(): input parameter is of type '+ Object.prototype.toString.call(src) + ', string expected');}if (callback || typeof opt === 'function') {if (!callback) {callback = opt;opt = null;}opt = merge({}, marked.defaults, opt || {});var highlight = opt.highlight,tokens,pending,i = 0;try {tokens = Lexer.lex(src, opt);} catch (e) {return callback(e);}pending = tokens.length;var done = function (err) {if (err) {opt.highlight = highlight;return callback(err);}var out;try {out = Parser.parse(tokens, opt);} catch (e) {err = e;}opt.highlight = highlight;return err? callback(err): callback(null, out);};if (!highlight || highlight.length < 3) {return done();}delete opt.highlight;if (!pending) { return done(); }for (; i < tokens.length; i++) {(function (token) {if (token.type !== 'code') {return --pending || done();}return highlight(token.text, token.lang, function (err, code) {if (err) { return done(err); }if (code == null || code === token.text) {return --pending || done();}token.text = code;token.escaped = true;--pending || done();});})(tokens[i]);}return;}try {if (opt) { opt = merge({}, marked.defaults, opt); }return Parser.parse(Lexer.lex(src, opt), opt);} catch (e) {e.message += '\nPlease report this to https://github.com/markedjs/marked.';if ((opt || marked.defaults).silent) {return '<p>An error occurred:</p><pre>'+ escape(e.message + '', true)+ '</pre>';}throw e;}}/*** Options*/marked.options =marked.setOptions = function (opt) {merge(marked.defaults, opt);return marked;};marked.getDefaults = function () {return {baseUrl: null,breaks: false,gfm: true,headerIds: true,headerPrefix: '',highlight: null,langPrefix: 'language-',mangle: true,pedantic: false,renderer: new Renderer(),sanitize: false,sanitizer: null,silent: false,smartLists: false,smartypants: false,tables: true,xhtml: false};};marked.defaults = marked.getDefaults();/*** Expose*/marked.Parser = Parser;marked.parser = Parser.parse;marked.Renderer = Renderer;marked.TextRenderer = TextRenderer;marked.Lexer = Lexer;marked.lexer = Lexer.lex;marked.InlineLexer = InlineLexer;marked.inlineLexer = InlineLexer.output;marked.parse = marked;{module.exports = marked;}})(commonjsGlobal || (typeof window !== 'undefined' ? window : commonjsGlobal));
});

4. node_modules\docsify-pdf-converter\src\createLibrary.js

/*** 创建字典*/const marked = require("docsify-pdf-converter/src/marked");
const slugify = require("docsify-pdf-converter/src/slugify");
const util = require("util");
const fs = require("fs");
const [readFile, writeFile, exists] = [fs.readFile, fs.writeFile, fs.exists].map(fn =>util.promisify(fn),
);function merge(obj) {var arguments$1 = arguments;var i = 1,target,key;for (; i < arguments.length; i++) {target = arguments$1[i];for (key in target) {if (Object.prototype.hasOwnProperty.call(target, key)) {obj[key] = target[key];}}}return obj;
}/*** 获取docsify配置 合并默认配置* @param {Object} params * @returns */
function getConfig(params) {return merge({el: '#app',repo: '',maxLevel: 6,subMaxLevel: 0,loadSidebar: null,loadNavbar: null,homepage: 'README.md',coverpage: '',basePath: '',auto2top: false,name: '',themeColor: '',autoHeader: false,executeScript: null,noEmoji: false,ga: '',ext: '.md',mergeNavbar: false,formatUpdated: '',externalLinkTarget: '_blank',routerMode: 'hash',noCompileLinks: []},params);
}
/*** 读取docsify配置文件  获取配置  指定配置文件为 docsify.config.js* @param {String} dir * @returns */
async function getConfigObj(dir) {let configPath = dir + "/docsify.config.js"const isExists = await exists(configPath);if (isExists) {const configFile = await readFile(configPath, {encoding: "utf8",});let config = eval("(" + configFile.substring(configFile.indexOf("{")) + ")")return config}
}/*** 生成字典* @param {*} path * @param {*} content * @param {*} depth * @returns */
function genIndex(path, content, depth) {if (content === void 0) content = '';var tokens = marked.lexer(content)var index = {};var slug;tokens.forEach(function (token) {if (token.type === 'heading' && token.depth <= depth) {slug = "#" + path + "?id=" + slugify(token.text);index[slug] = { slug: slug, title: token.text, body: '' };} else {if (!slug) {return}if (!index[slug]) {index[slug] = { slug: slug, title: '', body: '' };} else if (index[slug].body) {index[slug].body += '\n' + (token.text || '');} else {index[slug].body = token.text;}}});slugify.clear();return index
}module.exports = function (paths, files, dir) {let fileObj = {}let INDEXS = {}paths.shift()files.shift()dir = dir.replace(/\\/g, '/')files.map(file => {fileObj[file.name] = file.content})getConfigObj(dir).then(res => {let config = getConfig(res)paths.map(path => {// 格式化文件路径  与页面端保持一致let tempPath = path.replace(/\\/g, '/').replace(dir, '').replace('.md', '')INDEXS[tempPath] = genIndex(tempPath, fileObj[path], config.search.depth || 2)})// 将生成的字典保存到项目本地writeFile('dictionaries.json', JSON.stringify(INDEXS), 'utf-8', function (err) {if (err) {console.error(err)} else {console.log("字典创建成功！")}});})}

docsify（二）：新增生成字典/词库功能相关推荐

wordweb在线编辑_使用WordWeb享受按需词典和词库功能
wordweb在线编辑 Run across an unusual word or need a synonym for a word quickly? Usually that means ope ...
自编记单词小程序项目（自定义词库，多功能）C/C++语言实现
一款方便实用又简洁的记单词小程序,自定义单词库,多功能协助记忆!!! github地址:https://github.com/Knock-man/Memorizing-words-program 如今 ...
手机词库编辑器(可以由词库直接生成手机词典)
http://www.mobilemate.cn/ [原创]手机词库编辑器(可以由词库直接生成手机词典) 中秋节台风来,也没有出去玩,于是尝试在Ubuntu下,重写了原来基于.Net的C#词库编辑器. ...
发现新词 | NLP之无监督方式构建词库(一)
文章目录一.数据介绍及处理二.寻找未登录词 1.统计语料库中的词信息 2.利用互信息熵得到初始化词库 3.对语料库进行切分 4.利用搜索引擎判断新词 5.迭代寻找新词 6.方法总结一.数据介绍及 ...
敏感词过滤之——自定义构建查询词库与快速查询实现
关于敏感词过滤的一点思考与实践业务场景思考与研究逻辑分析代码实现(php) 构建敏感词树分割字符串敏感词树长分支的递归实现读取敏感词库敏感词树的查询查询实现调用测试.分析与总结 ...
IKAnalyzer实现扩展词库+动态更新词库的方法
为什么80%的码农都做不了架构师?>>> 当前IKAnalyzer从发布最后一个版本后就一直没有再更新,使用过程中,经常遇到需要扩展词库以及动态更新字典表的问题,此处给出一种解 ...
深蓝词库转换1.6发布
由于在技术上和功能上没有什么突破,一直心里的痛就是对QQ拼音分类词库(qpyd格式)的解析,一直无从下手,所以这半年来我一直都没有发布新版本的"深蓝词库转换".期间也收到了很多朋友 ...
python--中文分词与词云制作--入门笔记（附停用词库及Mac字体资源）
这里写自定义目录标题一.中文分词基本说明二.停用词库.自定义词典的使用 (一)停用词 (二)自定义词典三.词云绘制四.中文字体的使用说明 (一)Mac 字体使用说明五.附件 (一)ttf字体 ...
用sed命令shell扩大王林快码词库
比如我用王林快码,只有单字和二字组,二字组不太多,不现代,比如没有安卓和微信词组,又下载了搜狗二字组细胞词库已经转化为txt,想把该词组中快码没有的词组用快码的方式生成,就是取前两位加以组合.比如有快 ...

docsify（二）：新增生成字典/词库功能

docsify（二）：新增生成字典/词库功能相关推荐

最新文章

热门文章