版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/guotong1988/article/details/85911001
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.*;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
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;
import java.io.IOException;
import java.nio.file.Paths;
public class Example {
public static IndexWriter writer;
public static RAMDirectory idxDir;
public static StandardAnalyzer analyzer;
public static void makeIndex() throws IOException, ParseException {
FSDirectory fsDir = FSDirectory.open(Paths.get("C:\\Users\\gt\\Desktop\\_ROKID_\\fast-sent-match\\example"));
idxDir = new RAMDirectory(fsDir, IOContext.DEFAULT);
//analyzer = new SmartChineseAnalyzer();
analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setSimilarity(new BM25Similarity());
iwc.setOpenMode(OpenMode.CREATE);
writer = new IndexWriter(idxDir, iwc);
Document doc = new Document();
doc.add(new TextField("questionID", "82C69C047B89457E86C4799B34B86090", Field.Store.YES));//存储不分词且索引
doc.add(new TextField("question", "中华人民共和国", Field.Store.YES));
Document doc2 = new Document();
doc2.add(new TextField("questionID", "82C69C047B89457Exxxxxxxxxxxxxxx", Field.Store.YES));//存储不分词且索引
doc2.add(new TextField("question", "浙江省杭州市西湖区", Field.Store.YES));
writer.addDocument(doc);
writer.addDocument(doc2);
int nMaxDoc = writer.maxDoc();
System.out.println("nMaxDoc = " + nMaxDoc);
writer.commit();
writer.close();
iwc = new IndexWriterConfig(analyzer);
iwc.setSimilarity(new BM25Similarity());
iwc.setOpenMode(OpenMode.APPEND);
writer = new IndexWriter(idxDir, iwc);
System.out.println("前 = " + writer.numDocs());
// writer.deleteAll();
String[] stringQuery = {"82C69C047B89457E86C4799B34B86090", "中华人民共和国"};
String[] fields = {"questionID", "question"};
Occur[] occ = {Occur.MUST, Occur.MUST};
Query query = MultiFieldQueryParser.parse(stringQuery, fields, occ, analyzer);
writer.deleteDocuments(query);
writer.commit();
writer.forceMergeDeletes();
writer.commit();
System.out.println("后 = " + writer.numDocs());
writer.close();
}
public static void main(String[] args) throws IOException, ParseException {
makeIndex();
// String[] stringQuery={"2","金古江湖"}; //通过1,2来筛选
String[] stringQuery = {"82C69C047B89457Exxxxxxxxxxxxxxx", "浙江省杭州市西湖区"};
String[] fields = {"questionID", "question"};
Occur[] occ = {Occur.MUST, 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, 3);
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);
}
}
}