问题:一连串的字符串如何进行分词,例如“onlyLoveforYouYEAH”
想着lucence自带一些analyzer,没有仔细看里面的功能,就开始用了,发现效果并不太好。后来发现需要处理的字符串有一定模式,所以决定不用analyzer了,这里只是做个备忘,指不定以后还会用得着。
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.KeywordAnalyzer;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.Version;
public class test{
public static void main(String[] args) throws IOException {
String s1="";
String s2="";
String s="drive_tohomeyeah";
StringReader sr=new StringReader(s);
StandardAnalyzer an1 =