Lucene 高级搜索

时间:2025-02-10 10:33:44

自定义评分

Lucene 高级搜索

public class MyScoreQuery {

     public void searchByScoreQuery(){
try {
IndexSearcher searcher=new IndexSearcher(IndexReader.open(FileIndexUtils.getDirectory()));
Query q=new TermQuery(new Term("content","java"));
//创建一个评分
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: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("score")+"--->"+
d.get("size")+" "+sdf.format(new Date(Long.valueOf(d.get("date"))))+"]");
}
searcher.close();
} catch (NumberFormatException e) {
e.printStackTrace();
} 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")); FilenameScoreQuery query=new FilenameScoreQuery(q);
TopDocs tds=null;
tds=searcher.search(query, 100);
SimpleDateFormat sdf=new SimpleDateFormat("yyyy-MM-dd hh: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("score")+"--->"+
d.get("size")+" "+sdf.format(new Date(Long.valueOf(d.get("date"))))+"]");
}
searcher.close();
} catch (NumberFormatException e) {
e.printStackTrace();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
} private class DateScoreProvider extends CustomScoreProvider{
long[] dates=null;
public DateScoreProvider(IndexReader reader) {
super(reader);
//通过域缓存获取文件名
try {
dates=FieldCache.DEFAULT.getLongs(reader, "date");
} catch (IOException e) {
e.printStackTrace();
}
} @Override
public float customScore(int doc, float subQueryScore, float valSrcScore) throws IOException {
//如何个格局doc的名称获取相应的field的值
/*
* 在reader在没有关闭之前,所有的数据会存储在一个域缓存中,可以通过域缓存获取很多有用的信息
*/
long date=dates[doc];
long today=new Date().getTime();
long year=1000*60*60*24*365;
//表示的是这一年之内的
if(today-date<=year){
//为其加分
} return subQueryScore/1.5f;
} } @SuppressWarnings("serial")
private class FilenameScoreQuery extends CustomScoreQuery{ public FilenameScoreQuery(Query subQuery) {
super(subQuery); } @Override
protected CustomScoreProvider getCustomScoreProvider(IndexReader reader) throws IOException { return new FilenameScoreProvider(reader);
} } private class FilenameScoreProvider extends CustomScoreProvider{
String[] filenames=null;
public FilenameScoreProvider(IndexReader reader) {
super(reader);
//通过域缓存获取文件名
try {
filenames=FieldCache.DEFAULT.getStrings(reader, "filename");
} catch (IOException e) {
e.printStackTrace();
}
} @Override
public float customScore(int doc, float subQueryScore, float valSrcScore) throws IOException {
//如何个格局doc的名称获取相应的field的值
/*
* 在reader在没有关闭之前,所有的数据会存储在一个域缓存中,可以通过域缓存获取很多有用的信息
*/
String filename=filenames[doc];
System.out.println(filename);
if(filename.endsWith("注解")|| filename .endsWith(".ini")){
return subQueryScore*1.5f;
} return subQueryScore/1.5f;
} } 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打分
//为了根据不同的需求进行评分,需要自己进行评分设定
/**
* 自定评分的步骤
* 创建一个类继承于CustomScoreProvider
* 覆盖customScore方法
*/
return new MyCustomScoreProvider(reader);
} } private class MyCustomScoreProvider extends CustomScoreProvider{ public MyCustomScoreProvider(IndexReader reader) {
super(reader);
// TODO Auto-generated constructor stub
} /**
* subQueryScore 表示默认文档的打分
* valScrScore 表示的评分域的打分
*/ @Override
public float customScore(int doc, float subQueryScore, float valSrcScore) throws IOException {
// TODO Auto-generated method stub
return subQueryScore/valSrcScore;
} } }

自定义Queryparser

Lucene 高级搜索

public class CustomParser extends QueryParser {

    public CustomParser(Version matchVersion, String f, Analyzer a) {
super(matchVersion, f, a);
} @Override
protected org.apache.lucene.search.Query getFuzzyQuery(String field, String termStr, float minSimilarity)
throws ParseException {
throw new ParseException("由于性能原因,已经禁用了模糊查询,请输入更精确的信息进行查询");
} @Override
protected org.apache.lucene.search.Query getWildcardQuery(String field, String termStr) throws ParseException {
throw new ParseException("由于性能原因,已经禁用了通配符查询,请输入更精确的信息进行查询"); } @Override
protected org.apache.lucene.search.Query getRangeQuery(String field, String arg1, String arg2, boolean arg3)
throws ParseException {
//
if(field.equals("size")){
return NumericRangeQuery.newIntRange(field, Integer.parseInt(arg1), Integer.parseInt(arg2), arg3, arg3);
}else if(field.equals("date")){
//格式化日期
String dateType="yyyy-MM-dd";
Pattern pattern = Pattern.compile("\\d{4}-\\d{2}-\\d{2}");
if(pattern.matcher(arg1).matches() && pattern.matcher(arg2).matches()){
SimpleDateFormat sdf=new SimpleDateFormat(dateType);
try {
long start=sdf.parse(arg1).getTime();
long end=sdf.parse(arg2).getTime();
return NumericRangeQuery.newLongRange(field, start, end, arg3, arg3);
} catch (java.text.ParseException e) {
e.printStackTrace();
}
}
}
return new TermRangeQuery(field,arg1,arg2,arg3,arg3);
} }