lucene当中的各种query（三）

MultiTermQuery包含以下query：

FuzzyQuery, NumericRangeQuery, PrefixQuery, TermRangeQuery, WildcardQuery

FuzzyQuery是一种模糊查询，它可以简单地识别两个相近的词语。 即相似度匹配

NumericRangeQuery数字形式的范围查询

PrefixQuery前缀搜索A Query that matches documents containing terms with a specified prefix. A PrefixQuery is built by QueryParser for input like app*.

TermRangeQuery：主要用于文本范围查找;

使用通配符查询，*代表0个或多个字母，?代表0个或1个字母。

Query query=new WildcardQuery(new Term("contents","?ild*"));

Hits hits=searcher.search(query);

使用QueryParser和wildcardQuery使用的是相同的语法。但使用QueryParser时，首个字母不能是通配符

 

SpanQuery按照词在文章中的距离或者查询几个相邻词的查询

SpanQuery包括以下几种：

SpanTermQuery：词距查询的基础，结果和TermQuery相似，只不过是增加了查询结果中单词的距离信息。

SpanFirstQuery：在指定距离可以找到第一个单词的查询。

SpanNearQuery：查询的几个语句之间保持者一定的距离。

SpanOrQuery：同时查询几个词句查询。

SpanNotQuery：从一个词距查询结果中，去除一个词距查询。

 

 

ConstantScoreQuery

A query that wraps a filter and simply returns a constant score equal to the query boost for every document in the filter

看了一下这个类的构造函数ConstantScoreQuery(Filter filter) ，我的理解就是通过构造filter来完成文档的过滤，并且返回一个复合当前过滤条件的文档的常量分数，这个分数等于为查询条件设置的boost

 

 

 

2、自定义评分一、根据文件大小来评分，文件越大，权重越低

 

package util;

import java.io.IOException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
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.ValueSourceQuery;
import org.apache.lucene.search.function.FieldScoreQuery.Type;

public class MyScoreQuery1{

    public void searchByScoreQuery() throws Exception{
        IndexSearcher searcher = DocUtil.getSearcher();
        Query query = new TermQuery(new Term("content","java"));

        //1、创建评分域，如果Type是String类型，那么是Type.BYTE
        //该域必须是数值型的，并且不能使用norms索引，以及每个文档中该域只能由一个语汇
        //单元，通常可用Field.Index.not_analyzer_no_norms来进行创建索引
        FieldScoreQuery fieldScoreQuery = new FieldScoreQuery("size",Type.INT);
        //2、根据评分域和原有的Query创建自定义的Query对象
        //query是原有的query，fieldScoreQuery是专门做评分的query
        MyCustomScoreQuery customQuery = new MyCustomScoreQuery(query, fieldScoreQuery);

        TopDocs topdoc = searcher.search(customQuery, 100);
        DocUtil.printDocument(topdoc, searcher);
        searcher.close();

    }

    @SuppressWarnings("serial")
    private class MyCustomScoreQuery extends CustomScoreQuery{

        public MyCustomScoreQuery(Query subQuery, ValueSourceQuery valSrcQuery) {
            super(subQuery, valSrcQuery);
        }

        /**
         * 这里的reader是针对段的，意思是如果索引包含的段不止一个，那么搜索期间会多次调用
         * 这个方法，强调这点是重要的，因为它使你的评分逻辑能够有效使用段reader来对域缓存
         * 中的值进行检索
         */
        @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表示的评分域的打分
         * 默认是subQueryScore*valSrcScore返回的
         */
        @Override
        public float customScore(int doc, float subQueryScore, float valSrcScore)throws IOException {
            System.out.println("Doc:"+doc);
            System.out.println("subQueryScore:"+subQueryScore);
            System.out.println("valSrcScore:"+valSrcScore);
//          return super.customScore(doc, subQueryScore, valSrcScore);
            return subQueryScore / valSrcScore;
        }

    }
}

3、根据特定的几个文件名来评分，选中的文件名权重变大

 

 

package util;

import java.io.IOException;
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.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.function.CustomScoreProvider;
import org.apache.lucene.search.function.CustomScoreQuery;
/**
 * 此类的功能是给特定的文件名加权，也就是加评分
 * 也可以实现搜索书籍的时候把近一两年的出版的图书给增加权重
 * @author user
 */
public class MyScoreQuery2 {
    public void searchByFileScoreQuery() throws Exception{
        IndexSearcher searcher = DocUtil.getSearcher();
        Query query = new TermQuery(new Term("content","java"));

        FilenameScoreQuery fieldScoreQuery = new FilenameScoreQuery(query);

        TopDocs topdoc = searcher.search(fieldScoreQuery, 100);
        DocUtil.printDocument(topdoc, searcher);
        searcher.close();

    }

    @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();}
        }

        //如何根据doc获取相应的field的值
        /*
         * 在reader没有关闭之前，所有的数据会存储要一个域缓存中，可以通过域缓存获取很多有用
         * 的信息filenames = FieldCache.DEFAULT.getStrings(reader, "filename");可以获取
         * 所有的filename域的信息
         */
        @Override
        public float customScore(int doc, float subQueryScore, float valSrcScore)
                throws IOException {
            String fileName = filenames[doc];
            System.out.println(doc+":"+fileName);
//          return super.customScore(doc, subQueryScore, valSrcScore);
            if("9.txt".equals(fileName) || "4.txt".equals(fileName)) {
                return subQueryScore*1.5f;
            }
            return subQueryScore/1.5f;
        }

    }
}

4、测试junit

 

 

package test;
import org.junit.Test;
import util.MyScoreQuery1;
import util.MyScoreQuery2;

public class TestCustomScore {

    @Test
    public void test01() throws Exception {
        MyScoreQuery1 msq = new MyScoreQuery1();
        msq.searchByScoreQuery();
    }

    @Test
    public void test02() throws Exception {
        MyScoreQuery2 msq = new MyScoreQuery2();
        msq.searchByFileScoreQuery();
    }
}

5、文档操作的工具类

 

 

package util;

import java.io.File;
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.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class DocUtil {
    private static IndexReader reader;
    //得到indexSearch对象
    public static IndexSearcher getSearcher(){
        try {
            Directory directory = FSDirectory.open(new File("D:\\Workspaces\\customscore\\index"));
            reader = IndexReader.open(directory);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        IndexSearcher searcher = new IndexSearcher(reader);
        return searcher;
    }

    /**
     * 打印文档信息
     * @param topdoc
     */
    public static void printDocument(TopDocs topdoc,IndexSearcher searcher){
        SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss");
        for(ScoreDoc scoredoc : topdoc.scoreDocs){
            try {
                Document doc = searcher.doc(scoredoc.doc);
                System.out.println(scoredoc.doc+":("+scoredoc.score+")" +
                        "["+doc.get("filename")+"【"+doc.get("path")+"】--->"+
                        doc.get("size")+"-----"+sdf.format(new Date(Long.valueOf(doc.get("date"))))+"]");
            } catch (CorruptIndexException e) {
                e.printStackTrace();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

6、创建索引

 

 

package index;
import java.io.File;
import java.io.IOException;
import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.Analyzer;
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;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class FileIndexUtils {
    private static Directory directory = null;
    private static Analyzer analyzer = new IKAnalyzer();
    public static void main(String[] args) {
        index(true);
    }
    static{
        try {
            directory = FSDirectory.open(new File("D:\\Workspaces\\customscore\\index"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static Directory getDirectory() {
        return directory;
    }

    public static void index(boolean hasNew) {
        IndexWriter writer = null;
        try {
            writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, analyzer));
            if(hasNew) {
                writer.deleteAll();
            }
            File file = new File("D:\\Workspaces\\customscore\\resource");
            Document doc = null;
            for(File f:file.listFiles()) {
                doc = new Document();
                doc.add(new Field("content",FileUtils.readFileToString(f),Field.Store.YES,Field.Index.ANALYZED));
                doc.add(new Field("filename",f.getName(),Field.Store.YES,Field.Index.ANALYZED));
                doc.add(new Field("classid","5312",Field.Store.YES,Field.Index.ANALYZED));
                doc.add(new Field("path",f.getAbsolutePath(),Field.Store.YES,Field.Index.ANALYZED));
                doc.add(new NumericField("date",Field.Store.YES,true).setLongValue(f.lastModified()));
                doc.add(new NumericField("size",Field.Store.YES,true).setIntValue((int)(f.length())));
                writer.addDocument(doc);
            }
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                if(writer!=null) writer.close();
            } catch (CorruptIndexException e) {
                e.printStackTrace();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

工程下载路径：http://download.csdn.net/detail/wxwzy738/5320772

 

 

http://blog.csdn.net/wxwzy738/article/details/8873094