lucence入门

2019独角兽企业重金招聘Python工程师标准>>>

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;

/**
* Lucene create Index and search key word
*
* @author Hongten (hongtenzone@foxmail.com) <br />
* @date 2012-11-28
*/
public class LuceneIndex {

    /**
     * 创建索引
     */
    public void index() {
        IndexWriter writer = null;
        try {
            // 1.创建Directory
            // 这种方式是建立在内存中
            // Directory directory = new RAMDirectory();
            // 这种方式是存放在硬盘中
            Directory directory = FSDirectory.open(new File(
                    "D:/WordPlace/lucene/lucene_0100_helloworld/lucene/index"));
            // 2.创建IndexWriter
            IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35,
                    new StandardAnalyzer(Version.LUCENE_35));

            writer = new IndexWriter(directory, iwc);
            // 3.创建Document对象
            Document doc = null;
            // 4.为Document添加Field
            File f = new File(
                    "D:/WordPlace/lucene/lucene_0100_helloworld/lucene/example");
            for (File file : f.listFiles()) {
                doc = new Document();
                doc.add(new Field("content", new FileReader(file)));
                doc.add(new Field("filename", file.getName(), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));
                doc.add(new Field("path", file.getAbsolutePath(),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));
                // 5.通过IndexWriter添加文档到索引中
                writer.addDocument(doc);
            }
        } catch (CorruptIndexException ce) {
            ce.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                if (writer != null) {
                    writer.close();
                }
            } catch (CorruptIndexException e2) {
                e2.printStackTrace();
            } catch (IOException ioe) {
                ioe.printStackTrace();
            }
        }
    }

    /**
     * 搜索关键字为key的n条记录
     *
     * @param key
     *            关键字
     * @param n
     *            搜索的记录数
     */
    public void search(String key, int n) {
        try {
            // 1.创建Directory
            Directory directory = FSDirectory.open(new File(
                    "D:/WordPlace/lucene/lucene_0100_helloworld/lucene/index"));
            // 2.创建IndexReader
            Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_35);
            IndexReader reader = IndexReader.open(directory);
            // 3.根据IndexReader创建IndexSearcher
            IndexSearcher searcher = new IndexSearcher(reader);
            // 4.创建搜索的Query
            // 创建parser来确定要搜索的文件的内容，第二个参数表示搜索的域
            QueryParser parser = new QueryParser(Version.LUCENE_35, "content",analyzer);
            // 创建query，表示搜索域为content中包含key的文档
            Query query = parser.parse(key);
            // 5.根据searcher搜索并返回TopDocs
            TopDocs tds = searcher.search(query, n);
            // 6.根据TopDocs获取ScoreDoc对象
            ScoreDoc[] sds = tds.scoreDocs;
            SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span>", "</span>");
            Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); 
            for (int i=0;i<sds.length;i++) {
                // 7.根据searcher和ScordDoc对象获取具体的Document对象
                Document document = searcher.doc(sds[i].doc);
                document.get("filename");
            }

            // 9.关闭reader
            reader.close();
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        }
    }

}

转载于:https://my.oschina.net/liujiawan/blog/416886