1. 程式人生 > >lucene 部分更新,例項

lucene 部分更新,例項

import java.io.IOException;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.index.IndexReader;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
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.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.search.BooleanClause.Occur;
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.similarities.BM25Similarity;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.RAMDirectory;

public class Example2 {

    public static IndexWriter writer;
    public static RAMDirectory idxDir;
    public static SmartChineseAnalyzer analyzer;

    public static void makeIndex() throws IOException {

        FSDirectory fsDir = FSDirectory.open(Paths.get("C:\\Users\\gt\\Desktop\\_ROKID_\\fast-sent-match\\example"));
        idxDir = new RAMDirectory(fsDir, IOContext.DEFAULT);
        analyzer = new SmartChineseAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        iwc.setSimilarity(new BM25Similarity());

        iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        writer = new IndexWriter(idxDir, iwc);

        List<String> listSent = new ArrayList<String>();
        listSent.add("金古江湖是最好玩的金庸遊戲1");
        listSent.add("金古江湖是最好玩的金庸遊戲2");
        int id = 0;
        for (String sent : listSent) {
            id++;
            Document doc = new Document();
            doc.add(new TextField("questionType", "A", Field.Store.YES));
            doc.add(new TextField("questionId", String.valueOf(id), Field.Store.YES));
            doc.add(new TextField("question", sent.trim(), Field.Store.YES));
            writer.addDocument(doc);
        }
        
        List<String> listSent2 = new ArrayList<String>();
        listSent2.add("金古江湖是最好玩的金庸遊戲3");
        for (String sent : listSent2) {
            Document doc = new Document();
            doc.add(new TextField("questionType", "A", Field.Store.YES));
            doc.add(new TextField("questionId", String.valueOf(1), Field.Store.YES));
            doc.add(new TextField("question", sent.trim(), Field.Store.YES));
            writer.updateDocument(new Term("questionId", "1"), doc);
        }
        writer.commit();
        writer.close();
    }

    public static void main(String[] args) throws IOException, ParseException {
        makeIndex();

        String[] stringQuery = { "A", "1", "金古江湖" };
        String[] fields = { "questionType", "questionId", "question" };
        Occur[] occ = { Occur.MUST, Occur.SHOULD, Occur.MUST };
        Query query = MultiFieldQueryParser.parse(stringQuery, fields, occ, analyzer);

        TopDocs results = null;
        IndexReader reader = DirectoryReader.open(idxDir);
        IndexSearcher searcher = new IndexSearcher(reader);
        results = searcher.search(query, 5);
        ScoreDoc[] hits = results.scoreDocs;
        for (int i = 0; i < hits.length; ++i) {
            Document doc = searcher.doc(hits[i].doc);
            String strDocSent = doc.get("question");
            System.out.println(strDocSent);
        }
    }
}