Lucene使用Sort方法对文档进行排序

浏览数：17 / 时间：2015年06月08日

/*
* 这段代码使用的是Lucene对于文档排序使用的sort方法
* 这里可以使用多个sort的构造方法，来自己定义，所想要实现的功能。
* */
package score;

import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.TermQuery;

public class SortScore {

public SortScore(String INDEX_STORE_PATH){

try{

IndexWriter writer = new IndexWriter(INDEX_STORE_PATH, new StandardAnalyzer(), true);

writer.setUseCompoundFile(false);

//首先定义文本
Document doc1 = new Document();
Field f1 = new Field("bookNumber", "0000001", Field.Store.YES, Field.Index.UN_TOKENIZED);
Field f2 = new Field("bookname", "钢铁是怎样炼成的", Field.Store.YES, Field.Index.TOKENIZED);
Field f3 = new Field("publishdate", "1970-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc1.add(f1);
doc1.add(f2);
doc1.add(f3);

Document doc2 = new Document();
f1 = new Field("bookNumber", "0000002", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "钢铁战士", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1980-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc2.add(f1);
doc2.add(f2);
doc2.add(f3);

Document doc3 = new Document();
f1 = new Field("bookNumber", "0000003", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "篱笆女人和狗", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1990-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc3.add(f1);
doc3.add(f2);
doc3.add(f3);

Document doc4 = new Document();
f1 = new Field("bookNumber", "0000004", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "女人是水做的", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1999-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc4.add(f1);
doc4.add(f2);
doc4.add(f3);

Document doc5 = new Document();
f1 = new Field("bookNumber", "0000005", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "英雄儿女", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "2002-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc5.add(f1);
doc5.add(f2);
doc5.add(f3);

Document doc6 = new Document();
f1 = new Field("bookNumber", "0000006", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "白毛女", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1985-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc6.add(f1);
doc6.add(f2);
doc6.add(f3);

Document doc7 = new Document();
f1 = new Field("bookNumber", "0000007", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "我的兄弟和女儿", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1978-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
doc7.add(f1);
doc7.add(f2);
doc7.add(f3);

//将书信息加入索引
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.addDocument(doc3);
writer.addDocument(doc4);
writer.addDocument(doc5);
writer.addDocument(doc6);
writer.addDocument(doc7);
writer.close();

IndexSearcher searcher = new IndexSearcher(INDEX_STORE_PATH);
TermQuery q = new TermQuery(new Term("bookname", "女"));

//使用sort。RELEVANCE来制定排序的准则
Hits hits = searcher.search(q, Sort.RELEVANCE);

for(int i = 0; i < hits.length(); i++){
Document doc = hits.doc(i);
System.out.print("书名：");
System.out.println(doc.get("bookname"));
System.out.print("得分 :");
System.out.println(hits.score(i));
System.out.print("内部ID :");
System.out.println(hits.id(i));
System.out.print("书号 : ");
System.out.println(doc.get("bookNumber"));
System.out.print("发行日期 : ");
System.out.println(doc.get("publishdate"));
System.out.println("===========================");

}

}catch(IOException e){
e.printStackTrace();
}
}
public static void main(String[] args) {
// TODO Auto-generated method stub

SortScore ss = new SortScore("E:\\Lucene项目\\索引文件");

}

}

结果显示排序后的截图：