lucene通过修改boost值改善index索引

来源：互联网

并不是所有的Document和Field是平等创建的。Document增量是个使得这种需求能够简单实现的一个特征。默认情况下，所有的 Document都没有增量，他们都有相同的增量因数1.0。通过改变某个Document的增量因数，可以让Lucene认为它比索引中的其他 Document更重要或更不重要。在索引的时候只需执行setBoost(float)方法。

看两个示例，就能明白其中的用法。

示例1，使用默认的的boost

[java] view plaincopy

package com.cn;
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.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
public class TT {
public static void main(String []args) throws Exception {
String [] ids = {"1","2","3","4","5"};
String [] province = {"shanghai","beijing","liaoning","liaoning","zhejiang"};
String [] contents = {"shanghai is a city","beijing is a city","jinzhou is a city","shenyang is a city","hangzhou is a city"};
String [] city = {"shanghai","beijing","jinzhou","shenyang","hangzhou"};
Directory directory = new RAMDirectory();
IndexWriter indexWriter = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_34, new StandardAnalyzer(Version.LUCENE_34)));
for(int i = 0;i < ids.length;i++){
Document doc = new Document();
doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("province",province[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("contents",contents[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("city",city[i],Field.Store.YES,Field.Index.ANALYZED));
indexWriter.addDocument(doc);
}
System.out.println("total:"+indexWriter.numDocs());
indexWriter.close();
queryMethod(directory,"contents","city");
}
public static void queryMethod(Directory directory,String item,String txt)throws Exception {
Term term = new Term(item,txt);
Query query = new TermQuery(term);
IndexSearcher indexSearcher = new IndexSearcher(directory);
TopDocs topDocs = indexSearcher.search(query, 10);
System.out.println("it has "+topDocs.totalHits+" "+txt+" in "+item);
ScoreDoc [] scoreDoc = topDocs.scoreDocs;
for(int i=0;i<scoreDoc.length;i++){
Document d = indexSearcher.doc(scoreDoc[i].doc);
System.out.println("city:"+d.get("city"));
System.out.println("contents:"+d.get("contents"));
}
}
}

运行结果为：

total:5
it has 5 city in contents
province:shanghai city:shanghai
contents:shanghai is a city
province:beijing city:beijing
contents:beijing is a city
province:liaoning city:jinzhou
contents:jinzhou is a city
province:liaoning city:shenyang
contents:shenyang is a city
province:zhejiang city:hangzhou
contents:hangzhou is a city

示例2，增加了boost，代码为

[java] view plaincopy

package com.cn;
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.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
public class TT {
public static void main(String []args) throws Exception {
String [] ids = {"1","2","3","4","5"};
String [] province = {"shanghai","beijing","liaoning","liaoning","zhejiang"};
String [] contents = {"shanghai is a city","beijing is a city","jinzhou is a city","shenyang is a city","hangzhou is a city"};
String [] city = {"shanghai","beijing","jinzhou","shenyang","hangzhou"};
Directory directory = new RAMDirectory();
IndexWriter indexWriter = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_34, new StandardAnalyzer(Version.LUCENE_34)));
for(int i = 0;i < ids.length;i++){
Document doc = new Document();
doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("province",province[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("contents",contents[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("city",city[i],Field.Store.YES,Field.Index.ANALYZED));
if(province[i].equals("liaoning")){
if(city[i].equals("shenyang")){
doc.setBoost(5.0f);
}else{
doc.setBoost(2.0f);
}
}
indexWriter.addDocument(doc);
}
System.out.println("total:"+indexWriter.numDocs());
indexWriter.close();
queryMethod(directory,"contents","city");
}
public static void queryMethod(Directory directory,String item,String txt)throws Exception {
Term term = new Term(item,txt);
Query query = new TermQuery(term);
IndexSearcher indexSearcher = new IndexSearcher(directory);
TopDocs topDocs = indexSearcher.search(query, 10);
System.out.println("it has "+topDocs.totalHits+" "+txt+" in "+item);
ScoreDoc [] scoreDoc = topDocs.scoreDocs;
for(int i=0;i<scoreDoc.length;i++){
Document d = indexSearcher.doc(scoreDoc[i].doc);
System.out.println("city:"+d.get("city"));
System.out.println("contents:"+d.get("contents"));
}
}
}

运行结果为： total:5
it has 5 city in contents
city:shenyang
contents:shenyang is a city
city:jinzhou
contents:jinzhou is a city
city:shanghai
contents:shanghai is a city
city:beijing
contents:beijing is a city
city:hangzhou
contents:hangzhou is a city

从两个例子中看出属于辽宁省的结果在靠前位置了，而且shenyang比jinzhou还要靠前。