Lucene3.5自定义评分以及根据域进行自定义评分设定
一、首先来综述一下Lucene自定义评分的步骤：
1、创建一个评分域
FieldScoreQuery fd = new FieldScoreQuery("score", Type.INT);
2、根据评分域和原有的query创建自定义的query对象
MyCustomScoreQuery query = new MyCustomScoreQuery(q, fd);
@SuppressWarnings("serial")
private class MyCustomScoreQuery extends CustomScoreQuery {
public MyCustomScoreQuery(Query subQuery, ValueSourceQuery valSrcQuery) {
super(subQuery, valSrcQuery);
}
@Override
protected CustomScoreProvider getCustomScoreProvider(IndexReader reader)
throws IOException {
//默认情况实现的评分是通过原有的评分*传入进来的评分域所获取的评分来确定最终评分的
//为了根据不同的需求进行评分，需要自己进行评分的设定
/**
* 自定评分的步骤
* 创建一个类继承于CustomScoreProvider
* 覆盖customScore方法
*/
//return super.getCustomScoreProvider(reader);
return new MyCustomScoreProvider(reader);
}
}
3、创建一个类继承于CustomScoreProvider，覆盖customScore方法
private class MyCustomScoreProvider extends CustomScoreProvider {
public MyCustomScoreProvider(IndexReader reader) {
super(reader);
}
/**
* subQueryScore表示默认文档的打分
* valSrcScore表示评分域的打分
*/
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
//return super.customScore(doc, subQueryScore, valSrcScore);
return subQueryScore/valSrcScore;
}
}
二、根据域进行自定义评分设定
1、根据文件后缀名进行自定义评分
private class FilenameScoreQuery extends CustomScoreQuery {
public FilenameScoreQuery(Query subQuery) {
super(subQuery);
}
@Override
protected CustomScoreProvider getCustomScoreProvider(IndexReader reader)
throws IOException {
//return super.getCustomScoreProvider(reader);
return new FilenameScoreProvider(reader);
}
}
private class FilenameScoreProvider extends CustomScoreProvider {
String [] filenames = null;
public FilenameScoreProvider(IndexReader reader) {
super(reader);
try {
filenames = FieldCache.DEFAULT.getStrings(reader, "filename");
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
//如何根据doc获取相应的field的值
/**
* 在reader没有关闭之前，所有的数据会存储在一个缓存域中，可以通过缓存获取很多有用的信息
* filenames = FieldCache.DEFAULT.getStrings(reader, "filename");可以获取所有的filename域的信息
*/
String filename = filenames[doc];
if(filename.endsWith(".txt")||filename.endsWith(".ini")) {
return subQueryScore*1.5f;
}
//return super.customScore(doc, subQueryScore, valSrcScore);
return subQueryScore/1.5f;
}
}
2、根据日期进行自定义评分
private class DateScoreProvider extends CustomScoreProvider {
long[] dates = null;
public DateScoreProvider(IndexReader reader) {
super(reader);
try {
dates = FieldCache.DEFAULT.getLongs(reader, "date");
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
long date = dates[doc];
long today = new Date().getTime();
long year = 1000*60*60*365;
if(today - date <= year) {
//为其加分
}
return super.customScore(doc, subQueryScore, valSrcScore);
}
}
Lucene实现自定义评分的关键思想：
indexSearch.search中要传入一个CustomScoreQuery，要覆盖getCustomScoreProvider方法，并且要返回CustomScoreProvider 对象，在用匿名内部内的方式写一个CustomScoreProvider 覆盖customScore方法，这个方法有3个参数，第一个参数代表文档id，第二个参数代表原来评分，最后一个代表我们设置的评分域，然后我们就可以定义自己的一套评分算法为我们的搜索制定评分了。
完整代码如下：
1、工具类：
package com.dhb.util;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Random;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumericField;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
public class FileIndexUtils {
private static Directory directory = null;
static {
try {
directory = FSDirectory.open(new File("D:/luceneData/files/"));
} catch (IOException e) {
e.printStackTrace();
}
}
public static Directory getDirectory() {
return directory;
}
public static void index(boolean hasNew) {
IndexWriter writer = null;
try {
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35,
new StandardAnalyzer(Version.LUCENE_35));
writer = new IndexWriter(directory, iwc);
//是否新建索引
if(hasNew) {
writer.deleteAll();
}
Document doc = null;
File f = new File("D:/luceneData/example");
Random rand = new Random();
int index = 0;
for (File file : f.listFiles()) {
int score = rand.nextInt(600); //测试自定义评分用的
doc = new Document();
//测试自定义Filter用的
doc.add(new Field("id", String.valueOf(index++), Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
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));
doc.add(new NumericField("date", Field.Store.YES, true).setLongValue(file.lastModified()));
doc.add(new NumericField("size", Field.Store.YES, true).setIntValue((int) (file.length())));
doc.add(new NumericField("score", Field.Store.YES, true).setIntValue(score));
writer.addDocument(doc);
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if(writer!=null)
try {
writer.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
注意：（先自己生成索引，我这里就没调用了，因为放在另一个地方了，没有贴了）
2、自定义类
package com.dhb.util;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.FieldCache;
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.search.function.CustomScoreProvider;
import org.apache.lucene.search.function.CustomScoreQuery;
import org.apache.lucene.search.function.FieldScoreQuery;
import org.apache.lucene.search.function.FieldScoreQuery.Type;
import org.apache.lucene.search.function.ValueSourceQuery;
public class MyScoreQuery {
public void searchByScoreQuery() {
try {
IndexSearcher searcher = new IndexSearcher(IndexReader.open(FileIndexUtils.getDirectory()));
Query q = new TermQuery(new Term("content", "java"));
//1、创建一个评分域
FieldScoreQuery fd = new FieldScoreQuery("score", Type.INT);
//2、根据评分域和原有的query创建自定义的query对象
MyCustomScoreQuery query = new MyCustomScoreQuery(q, fd);
TopDocs tds = null;
tds = searcher.search(query, 100);
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
for (ScoreDoc sd : tds.scoreDocs) {
Document d = searcher.doc(sd.doc);
System.out.println(sd.doc + ":(" + sd.score + ")["
+ d.get("filename") + "【" + d.get("path") + "】---"
+ d.get("size") + "----" + sdf.format(Long.valueOf(d.get("date")))+"自定义评分："+d.get("score"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
public void searchByFileScoreQuery() {
try {
IndexSearcher searcher = new IndexSearcher(IndexReader.open(FileIndexUtils.getDirectory()));
Query q = new TermQuery(new Term("content", "java"));
//1、创建一个评分域
//FieldScoreQuery fd = new FieldScoreQuery("score", Type.INT);
FilenameScoreQuery query = new FilenameScoreQuery(q);
//2、根据评分域和原有的query创建自定义的query对象
//MyCustomScoreQuery query = new MyCustomScoreQuery(q, fd);
TopDocs tds = null;
tds = searcher.search(query, 100);
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
for (ScoreDoc sd : tds.scoreDocs) {
Document d = searcher.doc(sd.doc);
System.out.println(sd.doc + ":(" + sd.score + ")["
+ d.get("filename") + "【" + d.get("path") + "】---"
+ d.get("size") + "----" + sdf.format(Long.valueOf(d.get("date")))+"自定义评分："+d.get("score"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
@SuppressWarnings("serial")
private class MyCustomScoreQuery extends CustomScoreQuery {
public MyCustomScoreQuery(Query subQuery, ValueSourceQuery valSrcQuery) {
super(subQuery, valSrcQuery);
}
@Override
protected CustomScoreProvider getCustomScoreProvider(IndexReader reader)
throws IOException {
//默认情况实现的评分是通过原有的评分*传入进来的评分域所获取的评分来确定最终评分的
//为了根据不同的需求进行评分，需要自己进行评分的设定
/**
* 自定评分的步骤
* 创建一个类继承于CustomScoreProvider
* 覆盖customScore方法
*/
//return super.getCustomScoreProvider(reader);
return new MyCustomScoreProvider(reader);
}
}
private class MyCustomScoreProvider extends CustomScoreProvider {
public MyCustomScoreProvider(IndexReader reader) {
super(reader);
}
/**
* subQueryScore表示默认文档的打分
* valSrcScore表示评分域的打分
*/
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
//return super.customScore(doc, subQueryScore, valSrcScore);
return subQueryScore/valSrcScore;
}
}
@SuppressWarnings("serial")
private class FilenameScoreQuery extends CustomScoreQuery {
public FilenameScoreQuery(Query subQuery) {
super(subQuery);
}
@Override
protected CustomScoreProvider getCustomScoreProvider(IndexReader reader)
throws IOException {
//return super.getCustomScoreProvider(reader);
return new FilenameScoreProvider(reader);
}
}
private class FilenameScoreProvider extends CustomScoreProvider {
String [] filenames = null;
public FilenameScoreProvider(IndexReader reader) {
super(reader);
try {
filenames = FieldCache.DEFAULT.getStrings(reader, "filename");
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
//如何根据doc获取相应的field的值
/**
* 在reader没有关闭之前，所有的数据会存储在一个缓存域中，可以通过缓存获取很多有用的信息
* filenames = FieldCache.DEFAULT.getStrings(reader, "filename");可以获取所有的filename域的信息
*/
String filename = filenames[doc];
if(filename.endsWith(".txt")||filename.endsWith(".ini")) {
return subQueryScore*1.5f;
}
//return super.customScore(doc, subQueryScore, valSrcScore);
return subQueryScore/1.5f;
}
}
@SuppressWarnings("unused")
private class DateScoreProvider extends CustomScoreProvider {
long[] dates = null;
public DateScoreProvider(IndexReader reader) {
super(reader);
try {
dates = FieldCache.DEFAULT.getLongs(reader, "date");
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public float customScore(int doc, float subQueryScore, float valSrcScore)
throws IOException {
long date = dates[doc];
long today = new Date().getTime();
long year = 1000*60*60*365;
if(today - date <= year) {
//为其加分
}
return super.customScore(doc, subQueryScore, valSrcScore);
}
}
}
3、测试类
package com.dhb.test;
import org.junit.Test;
import com.dhb.util.MyScoreQuery;
public class TestCustomScore {
@Test
public void test01() {
MyScoreQuery msq = new MyScoreQuery();
msq.searchByScoreQuery();
}
@Test
public void test02() {
MyScoreQuery msq = new MyScoreQuery();
msq.searchByFileScoreQuery();
}
}