<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd"> <properties> <comment>IK Analyzer 扩展配置</comment> <entry key="ext_dict">ext.dic;</entry> <entry key="ext_stopwords">stopword.dic;</entry> </properties>
public class MyIkTest {
public static String str = "中国人民银行我是中国人";
public static void main(String[] args) {
MyIkTest test = new MyIkTest();
test.wordCount("", str);
}
private void wordCount(String arg,String content) {
Analyzer analyzer = new IKAnalyzer(true); // IK实现分词 true:用最大词长分词 false:最细粒度切分
StringReader reader = null;
TokenStream ts = null; try {
reader = new StringReader(content);
ts = analyzer.tokenStream(arg,reader);
CharTermAttribute term = ts.addAttribute(CharTermAttribute.class);
ts.reset();
Map<String, Integer> map = new HashMap<String, Integer>(); //统计
while (ts.incrementToken()) {
String str = term.toString();
Object o = map.get(str);
if (o == null) {
map.put(str, new Integer(1));
} else {
Integer i = new Integer(((Integer) o).intValue() + 1);
map.put(str, i);
}
}
List<Entry<String, Integer>> list = new ArrayList<Entry<String, Integer>>(map.entrySet());
Collections.sort(list,new Comparator<Map.Entry<String, Integer>>() {
public int compare(Map.Entry<String, Integer> o1,Map.Entry<String, Integer> o2) {
return (o2.getValue() - o1.getValue());
} });
for (int k=0;k<list.size();k++) {
Entry<String, Integer> it=list.get(k);
String word = it.getKey().toString();
System.err.println(word+"["+it.getValue()+"]");
}
} catch (Exception e) {
} finally {
if(reader != null){
reader.close();
}
if (analyzer != null) {
analyzer.close();
}
}
}
}
机械节能产品生产企业官网模板...
大气智能家居家具装修装饰类企业通用网站模板...
礼品公司网站模板
宽屏简约大气婚纱摄影影楼模板...
蓝白WAP手机综合医院类整站源码(独立后台)...苏ICP备2024110244号-2 苏公网安备32050702011978号 增值电信业务经营许可证编号:苏B2-20251499 | Copyright 2018 - 2025 源码网商城 (www.ymwmall.com) 版权所有