nodejieba-plus 3.5.8

package/test/test.js

@@ -0,0 +1,366 @@
+var should = require("should");
+var nodejieba = require("../index.js");
+
+describe("nodejieba", function() {
+
+  var sentence = "我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。";
+
+  it("nodejieba.cut(sentence, true)", function() {
+    nodejieba.cut(sentence, true).should.eql([ '我',
+      '是',
+      '拖拉机',
+      '学院',
+      '手扶拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会',
+      '升职',
+      '加薪',
+      '，',
+      '当上',
+      'CEO',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it("nodejieba.cut('南京市长江大桥')", function() {
+    nodejieba.cut('南京市长江大桥').should.eql([ '南京市', '长江大桥' ]);
+  });
+
+  it("nodejieba.cut('南京市长江大桥')", function() {
+    nodejieba.cut('南京市长江大桥').should.eql([ '南京市', '长江大桥' ]);
+  });
+
+  it("nodejieba.cutHMM('南京市长江大桥')", function() {
+    nodejieba.cutHMM('南京市长江大桥').should.eql([ '南京市', '长江大桥' ]);
+  });
+
+  it("nodejieba.cut('南京市长江大桥', true)", function() {
+    nodejieba.cut('南京市长江大桥', true).should.eql([ '南京市', '长江大桥' ]);
+  });
+
+  it("nodejieba.cut('南京长江大桥')", function() {
+    nodejieba.cut('南京长江大桥').should.eql([ '南京长江大桥' ]);
+  });
+
+  it("nodejieba.cut('南京长江大桥')", function() {
+    nodejieba.cut('南京长江大桥').should.eql([ '南京长江大桥' ]);
+  });
+
+  it("nodejieba.cutHMM('南京长江大桥')", function() {
+    nodejieba.cutHMM('南京长江大桥').should.eql([ '南京长', '江大桥' ]);
+  });
+
+  it("nodejieba.cut('南京长江大桥', true)", function() {
+    nodejieba.cut('南京长江大桥', true).should.eql([ '南京长江大桥' ]);
+  });
+
+  it('nodejieba.cut(sentence)', function() {
+    nodejieba.cut(sentence).should.eql([ '我',
+      '是',
+      '拖拉机',
+      '学院',
+      '手扶拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会',
+      '升职',
+      '加薪',
+      '，',
+      '当',
+      '上',
+      'C',
+      'E',
+      'O',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  })
+
+  it('nodejieba.cutHMM(sentence)', function() {
+    nodejieba.cutHMM(sentence).should.eql([ '我',
+      '是',
+      '拖拉机',
+      '学院',
+      '手',
+      '扶',
+      '拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会升',
+      '职加薪',
+      '，',
+      '当上',
+      'CEO',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it('nodejieba.cut(sentence, true)', function() {
+    nodejieba.cut(sentence, true).should.eql([ '我',
+      '是',
+      '拖拉机',
+      '学院',
+      '手扶拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会',
+      '升职',
+      '加薪',
+      '，',
+      '当上',
+      'CEO',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it('nodejieba.cutAll(sentence)', function() {
+    nodejieba.cutAll(sentence).should.eql([ '我',
+      '是',
+      '拖拉',
+      '拖拉机',
+      '学院',
+      '手扶',
+      '手扶拖拉机',
+      '拖拉',
+      '拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会升',
+      '升职',
+      '加薪',
+      '，',
+      '当上',
+      'C',
+      'E',
+      'O',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it('nodejieba.cutForSearch(sentence)', function() {
+    nodejieba.cutForSearch(sentence).should.eql([ '我',
+      '是',
+      '拖拉',
+      '拖拉机',
+      '学院',
+      '手扶',
+      '拖拉',
+      '拖拉机',
+      '手扶拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会',
+      '升职',
+      '加薪',
+      '，',
+      '当',
+      '上',
+      'C',
+      'E',
+      'O',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it('nodejieba.cutForSearch(sentence, true)', function() {
+    nodejieba.cutForSearch(sentence, true).should.eql([ '我',
+      '是',
+      '拖拉',
+      '拖拉机',
+      '学院',
+      '手扶',
+      '拖拉',
+      '拖拉机',
+      '手扶拖拉机',
+      '专业',
+      '的',
+      '。',
+      '不用',
+      '多久',
+      '，',
+      '我',
+      '就',
+      '会',
+      '升职',
+      '加薪',
+      '，',
+      '当上',
+      'CEO',
+      '，',
+      '走上',
+      '人生',
+      '巅峰',
+      '。' ]);
+  });
+
+  it('nodejieba.tag(sentence)', function() {
+    nodejieba.tag(sentence).should.eql([ { word: '我', tag: 'r' },
+      { word: '是', tag: 'v' },
+      { word: '拖拉机', tag: 'n' },
+      { word: '学院', tag: 'n' },
+      { word: '手扶拖拉机', tag: 'n' },
+      { word: '专业', tag: 'n' },
+      { word: '的', tag: 'uj' },
+      { word: '。', tag: 'x' },
+      { word: '不用', tag: 'v' },
+      { word: '多久', tag: 'm' },
+      { word: '，', tag: 'x' },
+      { word: '我', tag: 'r' },
+      { word: '就', tag: 'd' },
+      { word: '会', tag: 'v' },
+      { word: '升职', tag: 'v' },
+      { word: '加薪', tag: 'nr' },
+      { word: '，', tag: 'x' },
+      { word: '当上', tag: 't' },
+      { word: 'CEO', tag: 'eng' },
+      { word: '，', tag: 'x' },
+      { word: '走上', tag: 'v' },
+      { word: '人生', tag: 'n' },
+      { word: '巅峰', tag: 'n' },
+      { word: '。', tag: 'x' } ]);
+  });
+
+  // float compare error in multi platform (macos, windows)
+  //it('nodejieba.extract(sentence, 5)', function() {
+  //  nodejieba.extract(sentence, 5).should.eql([
+  //        {
+  //            "weight": 11.739204307083542,
+  //            "word": "CEO"
+  //        },
+  //        {
+  //            "weight": 10.8561552143,
+  //            "word": "升职"
+  //        },
+  //        {
+  //            "weight": 10.642581114,
+  //            "word": "加薪"
+  //        },
+  //        {
+  //            "weight": 10.0088573539,
+  //            "word": "手扶拖拉机"
+  //        },
+  //        {
+  //            "weight": 9.49395840471,
+  //            "word": "巅峰"
+  //        }]);
+  //});
+
+  //it('nodejieba.textRankExtract(sentence, 5)', function() {
+  //  nodejieba.textRankExtract(sentence, 5).should.eql([
+  //      	  {
+  //            "weight": 1,
+  //      	      "word": "当上"
+  //      	  },
+  //      	  {
+  //            "weight": 0.9898479330698993,
+  //      	      "word": "不用"
+  //      	  },
+  //      	  {
+  //      	      "weight": 0.9851260595435759,
+  //      	      "word": "多久"
+  //      	  },
+  //      	  {
+  //      	      "weight": 0.9830464899847804,
+  //      	      "word": "加薪"
+  //      	  },
+  //      	  {
+  //      	      "weight": 0.9802777682279076,
+  //      	      "word": "升职"
+  //      	  }]);
+  //});
+
+  it('nodejieba.cut("红掌拨清波")', function() {
+    nodejieba.cut("红掌拨清波").should.eql([
+      '红掌',
+      '拨',
+      '清波',
+    ]);
+  });
+
+  it('nodejieba.cut("男默女泪")', function() {
+    nodejieba.cut("男默女泪").should.eql([ '男', '默',
+      '女', '泪' ]);
+  });
+  it('nodejieba.insertWord("男默女泪")', function() {
+    nodejieba.insertWord("男默女泪").should.eql(true);
+  });
+  it('nodejieba.cut("男默女泪")', function() {
+    nodejieba.cut("男默女泪").should.eql([ '男默女泪' ]);
+  });
+
+  it('nodejieba.cut("今天天气很好，🙋 我们去郊游。")', function() {
+    nodejieba.cut("今天天气很好，🙋 我们去郊游。").should.eql([ '今天天气', '很', '好', '，', '🙋', ' ', '我们', '去', '郊游', '。' ]);
+  });
+
+  it('nodejieba.cutSmall("南京市长江大桥", 3)', function() {
+    nodejieba.cutSmall("南京市长江大桥", 3).should.eql([ '南京市', 
+    '长江',
+    '大桥']);
+  });
+
+  it('nodejieba.cut("区块链")', function() {
+    nodejieba.cut("区块链").should.eql(['区块链']);
+  });
+  it('nodejieba.tag("区块链")', function() {
+    nodejieba.tag("区块链").should.eql([ { word: '区块链', tag: 'nz' }]);
+  });
+  it('nodejieba.cut("访问www.baidu.com进行搜索")',function(){
+    nodejieba.cut("访问www.baidu.com进行搜索", true).should.eql([
+        '访问', 'www', '.', 'baidu', '.', 'com', '进行', '搜索',
+    ]);
+  });
+});

package/test/testdata/userdict.utf8

@@ -0,0 +1 @@
+红掌拨清波

package/tsconfig.json

@@ -0,0 +1,59 @@
+{
+  "compilerOptions": {
+    /* Basic Options */
+    "target": "es5",                          /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017','ES2018' or 'ESNEXT'. */
+    "module": "commonjs",                     /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', or 'ESNext'. */
+    // "lib": [],                             /* Specify library files to be included in the compilation. */
+    // "allowJs": true,                       /* Allow javascript files to be compiled. */
+    // "checkJs": true,                       /* Report errors in .js files. */
+    // "jsx": "preserve",                     /* Specify JSX code generation: 'preserve', 'react-native', or 'react'. */
+    // "declaration": true,                   /* Generates corresponding '.d.ts' file. */
+    // "declarationMap": true,                /* Generates a sourcemap for each corresponding '.d.ts' file. */
+    // "sourceMap": true,                     /* Generates corresponding '.map' file. */
+    // "outFile": "./",                       /* Concatenate and emit output to single file. */
+    // "outDir": "./",                        /* Redirect output structure to the directory. */
+    // "rootDir": "./",                       /* Specify the root directory of input files. Use to control the output directory structure with --outDir. */
+    // "composite": true,                     /* Enable project compilation */
+    // "removeComments": true,                /* Do not emit comments to output. */
+    // "noEmit": true,                        /* Do not emit outputs. */
+    // "importHelpers": true,                 /* Import emit helpers from 'tslib'. */
+    // "downlevelIteration": true,            /* Provide full support for iterables in 'for-of', spread, and destructuring when targeting 'ES5' or 'ES3'. */
+    // "isolatedModules": true,               /* Transpile each file as a separate module (similar to 'ts.transpileModule'). */
+
+    /* Strict Type-Checking Options */
+    "strict": true,                           /* Enable all strict type-checking options. */
+    // "noImplicitAny": true,                 /* Raise error on expressions and declarations with an implied 'any' type. */
+    // "strictNullChecks": true,              /* Enable strict null checks. */
+    // "strictFunctionTypes": true,           /* Enable strict checking of function types. */
+    // "strictPropertyInitialization": true,  /* Enable strict checking of property initialization in classes. */
+    // "noImplicitThis": true,                /* Raise error on 'this' expressions with an implied 'any' type. */
+    // "alwaysStrict": true,                  /* Parse in strict mode and emit "use strict" for each source file. */
+
+    /* Additional Checks */
+    // "noUnusedLocals": true,                /* Report errors on unused locals. */
+    // "noUnusedParameters": true,            /* Report errors on unused parameters. */
+    // "noImplicitReturns": true,             /* Report error when not all code paths in function return a value. */
+    // "noFallthroughCasesInSwitch": true,    /* Report errors for fallthrough cases in switch statement. */
+
+    /* Module Resolution Options */
+    // "moduleResolution": "node",            /* Specify module resolution strategy: 'node' (Node.js) or 'classic' (TypeScript pre-1.6). */
+    // "baseUrl": "./",                       /* Base directory to resolve non-absolute module names. */
+    // "paths": {},                           /* A series of entries which re-map imports to lookup locations relative to the 'baseUrl'. */
+    // "rootDirs": [],                        /* List of root folders whose combined content represents the structure of the project at runtime. */
+    // "typeRoots": [],                       /* List of folders to include type definitions from. */
+    // "types": [],                           /* Type declaration files to be included in compilation. */
+    // "allowSyntheticDefaultImports": true,  /* Allow default imports from modules with no default export. This does not affect code emit, just typechecking. */
+    "esModuleInterop": true                   /* Enables emit interoperability between CommonJS and ES Modules via creation of namespace objects for all imports. Implies 'allowSyntheticDefaultImports'. */
+    // "preserveSymlinks": true,              /* Do not resolve the real path of symlinks. */
+
+    /* Source Map Options */
+    // "sourceRoot": "",                      /* Specify the location where debugger should locate TypeScript files instead of source locations. */
+    // "mapRoot": "",                         /* Specify the location where debugger should locate map files instead of generated locations. */
+    // "inlineSourceMap": true,               /* Emit a single file with source maps instead of having a separate file. */
+    // "inlineSources": true,                 /* Emit the source alongside the sourcemaps within a single file; requires '--inlineSourceMap' or '--sourceMap' to be set. */
+
+    /* Experimental Options */
+    // "experimentalDecorators": true,        /* Enables experimental support for ES7 decorators. */
+    // "emitDecoratorMetadata": true,         /* Enables experimental support for emitting type metadata for decorators. */
+  }
+}

package/types/index.d.ts

@@ -0,0 +1,30 @@
+declare module "nodejieba" {
+  export interface LoadOptions {
+    dict?: string;
+    hmmDict?: string;
+    userDict?: string;
+    idfDict?: string;
+    stopWordDict?: string;
+  }
+  
+  export interface TagResult {
+    word: string;
+    tag: string;
+  }
+  
+  export interface ExtractResult {
+    word: string;
+    weight: number;
+  }
+
+  export function load(dict?: LoadOptions): void;
+  export function cut(sentence: string, strict?: boolean): string[];
+  export function cutHMM(sentence: string): string[];
+  export function cutAll(sentence: string): string[];
+  export function cutForSearch(sentence: string, strict?: boolean): string[];
+  export function tag(sentence: string): TagResult[];
+  export function extract(sentence: string, threshold: number): ExtractResult[];
+  export function textRankExtract(sentence: string, threshold: number): ExtractResult[];
+  export function insertWord(word: string, tag?: string): boolean;
+  export function cutSmall(sentence: string, small: number): string[];
+}

package/typescript_demo.ts

@@ -0,0 +1,38 @@
+import nodejieba from "nodejieba";
+
+const sentence = "我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。";
+let result: any;
+
+result = nodejieba.cut(sentence);
+console.log(result);
+
+result = nodejieba.cut(sentence, true);
+console.log(result);
+
+result = nodejieba.cutHMM(sentence);
+console.log(result);
+
+result = nodejieba.cutAll(sentence);
+console.log(result);
+
+result = nodejieba.cutForSearch(sentence);
+console.log(result);
+
+result = nodejieba.tag(sentence);
+console.log(result);
+
+const topN = 5;
+result = nodejieba.extract(sentence, topN);
+console.log(result);
+
+result = nodejieba.textRankExtract(sentence, topN);
+console.log(result);
+
+result = nodejieba.cut("男默女泪");
+console.log(result);
+nodejieba.insertWord("男默女泪");
+result = nodejieba.cut("男默女泪");
+console.log(result);
+
+result = nodejieba.cutSmall("南京市长江大桥", 3);
+console.log(result);