複習 Lucene 的用法 (6.x)

LuceneLab.java

import static org.junit.Assert.assertEquals;

import java.io.IOException;

import org.apache.log4j.Logger;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

public class LuceneLab {

    Logger logger = Logger.getLogger(LuceneLab.class);

    Directory directory;

    @Before
    public void setUp() throws Exception {
        directory = new RAMDirectory();
        try (IndexWriter writer = createIndexWriter(directory)) {
            Document document = new Document();
            document.add(new TextField("NAME", "誠實豆沙包", Store.YES));
            writer.addDocument(document);
        }
    }

    @After
    public void tearDown() throws IOException {
        directory.close();
    }

    @Test
    public void testSearch() throws Exception {
        assertEquals(1, search("誠實豆沙包"));
        assertEquals(0, search("慚愧棒棒糖"));
    }

    protected int search(String key) throws CorruptIndexException, IOException, ParseException {
        try (DirectoryReader reader = DirectoryReader.open(directory)) {
            IndexSearcher searcher = new IndexSearcher(reader);
            QueryParser parser = new QueryParser("NAME", new CJKAnalyzer());
            Query query = parser.parse(key);
            TopDocs docs = searcher.search(query, 100);

            logger.info(String.format("尋找 %s", key));
            if (docs.totalHits == 0) {
                logger.info(String.format("找不到 %s", key));
            } else {
                logger.info(String.format("發現 %s", key));
            }
            return docs.totalHits;
        }
    }

    protected IndexWriter createIndexWriter(Directory directory) throws IOException {
        Analyzer analyzer = new CJKAnalyzer();
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        config.setOpenMode(OpenMode.CREATE_OR_APPEND);
        return new IndexWriter(directory, config);
    }

}

// gradle dep
// compile group: 'org.apache.lucene', name: 'lucene-core', version: '6.2.0'
// compile group: 'org.apache.lucene', name: 'lucene-analyzers-common', version: '6.2.0'
// compile group: 'org.apache.lucene', name: 'lucene-queryparser', version: '6.2.0'

Output:

 INFO [main] (LuceneLab.java:59) - 尋找 誠實豆沙包
 INFO [main] (LuceneLab.java:63) - 發現 誠實豆沙包
 INFO [main] (LuceneLab.java:59) - 尋找 慚愧棒棒糖
 INFO [main] (LuceneLab.java:61) - 找不到 慚愧棒棒糖

幫加註：如果之後要算term vector，不能用 text field。