Lucene 7.2.1 自定义TokenFilter

1.自定义TokenFilter

import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

public class CourtesyTokenFilter extends TokenFilter {

    private Map<String, String> courtesyMap = new HashMap<>();
    private CharTermAttribute charTermAttribute;

    public CourtesyTokenFilter(TokenStream input) {
        super(input);
        this.charTermAttribute = this.addAttribute(CharTermAttribute.class);
        courtesyMap.put("dr", "doctor");
        courtesyMap.put("mr", "mister");
        courtesyMap.put("mrs", "miss");
    }

    @Override
    public final boolean incrementToken() throws IOException {
        if (!this.input.incrementToken()) {
            return false;
        }

        String term = this.charTermAttribute.toString();
        if (courtesyMap.containsKey(term)) {
            this.charTermAttribute.setEmpty().append(this.courtesyMap.get(term));
        }

        return true;
    }
}

2.应用TokenFilter:

String text = "Hi, Dr Wang, Mr Liu asks if you stay with Mrs Liu yesterday!";
        StandardAnalyzer standardAnalyzer = new StandardAnalyzer();
        CourtesyTokenFilter courtesyTokenFilter = new CourtesyTokenFilter(standardAnalyzer.tokenStream("text", text));
        CharTermAttribute charTermAttribute = courtesyTokenFilter.addAttribute(CharTermAttribute.class);
        courtesyTokenFilter.reset();
        while (courtesyTokenFilter.incrementToken()) {
            System.out.print(charTermAttribute + " ");
        }

3.场景解析

"Hi, Dr Wang, Mr Liu asks if you stay with Mrs Liu yesterday!" 这段文本中，有Dr, Mrs这两个词，我们看不懂，要用全称来显示。