nodejieba - npm Package Compare versions

Comparing version 0.2.5 to 0.2.7

ChangeLog.md

@@ -0,1 +1,13 @@
+# ChangeLog
+
+## v0.2.7
+
+* 关键词抽取支持自定义词典(可选参数)。
+
+## v0.2.6
+
+* 修复不同Node版本的兼容性问题，在v0.11.13下测试通过。
+* 支持自定义词典(可选参数)。
+* 增加关键词抽取功能。
+
 ## v0.2.5
@@ -2,0 +14,0 @@

package.json

 {
   "name": "nodejieba",
   "description": "chinese segment for node",
-  "version": "0.2.5",
-  "author": "Yanyi Wu <[e-mail]>",
+  "version": "0.2.7",
+  "author": "Yanyi Wu <[e-mail]>",
   "maintainers": [
-    "aszxqw <[e-mail]>"
+    "Yanyi Wu <[e-mail]>"
   ],
@@ -24,9 +24,9 @@ "main": "./index.js",
   "dependencies": {
-    "nan": "~1.2.0"
+    "nan": "~1.6.1"
   },
   "devDependencies": {},
   "scripts": {
-      "test": "node test/segment.js && node test/query_segment.js && node test/pos_tagger.js"
+      "test": "node test/segment.js && node test/query_segment.js && node test/pos_tagger.js && node test/keyword.js"
   },
   "license": "MIT"
 }

README.md

@@ -9,3 +9,3 @@ [![Build Status](https://travis-ci.org/aszxqw/nodejieba.png?branch=master)](https://travis-ci.org/aszxqw/nodejieba)
 
-## Introduction
+## 介绍 
 
@@ -16,3 +16,3 @@ `NodeJieba`只是[CppJieba]简单包装而成的`node`扩展，用来进行中文分词。
 
-## Install
+## 下载
 
@@ -23,3 +23,3 @@ ```sh
 
-因为`npm`速度很慢而且经常因为墙的原因出现莫名其妙的问题，在此强烈建议使用[cnpm]，命令如下：
+因为`npm`速度很慢而且经常因为墙的原因出现莫名其妙的问题，可以试试使用[cnpm]，命令如下：
 
@@ -30,3 +30,3 @@ ```sh
 
-## Usage
+## 用法
 
@@ -38,4 +38,4 @@ ### 默认分词算法
 ```js
-var segment = require("nodejieba");
-segment.loadDict("./node_modules/nodejieba/dict/jieba.dict.utf8", "./node_modules/nodejieba/dict/hmm_model.utf8");
+var nodejieba = require("nodejieba");
+nodejieba.loadDict("./node_modules/nodejieba/dict/jieba.dict.utf8", "./node_modules/nodejieba/dict/hmm_model.utf8", "./node_modules/nodejieba/dict/user.dict.utf8");
 ```
@@ -46,3 +46,3 @@
 ```js
-var wordList = segment.cutSync("阻塞模式分词");
+var wordList = nodejieba.cutSync("阻塞模式分词");
 if (wordList.constructor == Array) // just for tutorial, this is always be true 
@@ -59,3 +59,3 @@ {
 ```js
-segment.cut("非阻塞模式分词", function(wordList) {
+nodejieba.cut("非阻塞模式分词", function(wordList) {
     wordList.forEach(function(word) {
@@ -72,4 +72,4 @@ console.log(word);
 ```js
-var segment = require("nodejieba");
-segment.queryLoadDict("./node_modules/nodejieba/dict/jieba.dict.utf8", "./node_modules/nodejieba/dict/hmm_model.utf8");
+var nodejieba = require("nodejieba");
+nodejieba.queryLoadDict("./node_modules/nodejieba/dict/jieba.dict.utf8", "./node_modules/nodejieba/dict/hmm_model.utf8", "./node_modules/nodejieba/dict/user.dict.utf8");
 ```
@@ -80,3 +80,3 @@
 ```js
-var wordList = segment.queryCutSync("阻塞模式分词");
+var wordList = nodejieba.queryCutSync("阻塞模式分词");
 if (wordList.constructor == Array) // just for tutorial, this is always be true 
@@ -93,3 +93,3 @@ {
 ```js
-segment.queryCut("非阻塞模式分词", function(wordList) {
+nodejieba.queryCut("非阻塞模式分词", function(wordList) {
     wordList.forEach(function(word) {
@@ -107,18 +107,22 @@ console.log(word);
 
-## Testing
+### 关键词抽取
 
-在`node v0.10.2`下测试通过
+具体用法可以参考 `test/keyword.js`
 
-## Demo
+## 测试
 
+在`node v0.10.2`, `node v0.11.13`下测试通过。
+
+## 在线演示
+
 http://cppjieba-webdemo.herokuapp.com/
 (chrome is suggested)
 
-## Thanks
+## 鸣谢
 
 [Jieba中文分词]
 
-## Author
+## 作者
 
-- aszxqw   https://github.com/aszxqw   [e-mail]
+- YanyiWu   http://yanyiwu.com   [e-mail]
 - myl2821  https://github.com/myl2821  [e-mail]
@@ -125,0 +129,0 @@

test/pos_tagger.js

@@ -1,4 +0,6 @@
-var segment = require("../index.js");
-segment.taggerLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8");
-segment.tag("非阻塞的南京市长江大桥",  function(tl){
+var nodejieba = require("../index.js");
+// 第三个参数是可选参数
+//nodejieba.taggerLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8", "./dict/user.dict.utf8");
+nodejieba.taggerLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8");
+nodejieba.tag("非阻塞的南京市长江大桥",  function(tl){
 	for(var i = 0; i < tl.length; i++) {
@@ -8,3 +10,3 @@ console.log(i + " => " + tl[i]);
 });
-var tl = segment.tagSync("阻塞的南京市长江大桥");
+var tl = nodejieba.tagSync("阻塞的南京市长江大桥");
 for(var i = 0; i < tl.length; i++) {
@@ -11,0 +13,0 @@ console.log(i + " == " + tl[i]);

test/query_segment.js

@@ -1,6 +0,8 @@
-var segment = require("../index.js");
+var nodejieba = require("../index.js");
 // 第三个参数是分词的粒度阈值，当词长大于3时，会进行细粒度的再切割，不填时默认阈值是4。
-segment.queryLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8", 3);
+// 第四个参数是可选参数。
+// nodejieba.queryLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8", 3, "./dict/user.dict.utf8");
+nodejieba.queryLoadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8", 3);
 console.log("非阻塞的:");
-segment.queryCut("小明硕士毕业于中国科学院计算所，后在日本京都大学深造",  function(tl){
+nodejieba.queryCut("小明硕士毕业于中国科学院计算所，后在日本京都大学深造",  function(tl){
 	for(var i = 0; i < tl.length; i++) {
@@ -11,3 +13,3 @@ console.log(i + " => " + tl[i]);
 console.log("阻塞的:");
-var tl = segment.queryCutSync("小明硕士毕业于中国科学院计算所，后在日本京都大学深造");
+var tl = nodejieba.queryCutSync("小明硕士毕业于中国科学院计算所，后在日本京都大学深造");
 for(var i = 0; i < tl.length; i++) {
@@ -14,0 +16,0 @@ console.log(i + " == " + tl[i]);

test/segment.js

@@ -1,4 +0,6 @@
-var segment = require("../index.js");
-segment.loadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8");
-segment.cut("非阻塞的南京市长江大桥",  function(tl){
+var nodejieba = require("../index.js");
+// 第三个参数是可选参数
+// nodejieba.loadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8", "./dict/user.dict.utf8");
+nodejieba.loadDict("./dict/jieba.dict.utf8", "./dict/hmm_model.utf8");
+nodejieba.cut("非阻塞的南京市长江大桥",  function(tl){
 	for(var i = 0; i < tl.length; i++) {
@@ -8,3 +10,3 @@ console.log(i + " => " + tl[i]);
 });
-var tl = segment.cutSync("阻塞的南京市长江大桥");
+var tl = nodejieba.cutSync("阻塞的南京市长江大桥");
 for(var i = 0; i < tl.length; i++) {
@@ -11,0 +13,0 @@ console.log(i + " == " + tl[i]);

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Native code

Supply chain risk

Contains native code (e.g., compiled binaries or shared libraries). Including native code can obscure malicious behavior.

Found 1 instance in 1 package

Mixed license

License

(Experimental) Package contains multiple licenses.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Native code

Supply chain risk

Contains native code (e.g., compiled binaries or shared libraries). Including native code can obscure malicious behavior.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

15766096

increased by144.67%

Number of package files

75

increased by10.29%

Lines of code

56

increased by47.37%

Number of lines in readme file

123

increased by3.36%

Worsened metrics

Number of low license alerts

1

increased byInfinity%

Dependency changes

• + Addednan@1.6.2(transitive)

• - Removednan@1.2.0(transitive)

• Updatednan@~1.6.1