mmseg4j分詞

 

    mmseg4j分詞,所需jar:mmseg4j-analysis-1.9.1.jar,mmseg4j-core-1.9.1.jar。

public class Demo {

	public static void main(String[] args) throws IOException {
		
		String txt  = "十動然拒思密達";
		File file = new File("E:/temp/dic_mmseg");
		//目錄下的文件必須是words開頭的dic文件,且第一行跳過,寫註釋
		Dictionary dic = Dictionary.getInstance(file);
		Seg seg = null; 
//		seg = new SimpleSeg(dic); 
		seg = new ComplexSeg(dic); 
//		seg = new MaxWordSeg(dic);
		MMSeg mmSeg = new MMSeg(new StringReader(txt), seg); 
		Word word = null;
		while((word = mmSeg.next())!=null) {			
				if(word != null) {
					System.out.print(word + "|");
			} 
		}
		
	}
}

 

    詞典words.dic內容:

#詞典
十動然拒
思密達

 

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章