Lucene4.10.3自定义过滤器

只需两步实现自定义过滤器

一、

package search;


import org.apache.lucene.index.AtomicReader;
import org.apache.lucene.index.AtomicReaderContext;
import org.apache.lucene.index.DocsEnum;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.DocIdSet;
import org.apache.lucene.search.Filter;
import org.apache.lucene.util.Bits;
import org.apache.lucene.util.OpenBitSet;


import java.io.IOException;


/**
 * 自定义过滤器，过滤文档大小
 * Created with IntelliJ IDEA.
 * User: wxshi
 * Date: 15-2-10
 * Time: 下午7:54
 * To change this template use File | Settings | File Templates.
 */
public class MyFilters  extends Filter {


    private String fieldKey;
    private String fieldValue;


    //定义域：域值
    public MyFilters(String fieldKey, String fieldValue)
    {
        super();
        this.fieldKey=fieldKey;
        this.fieldValue=fieldValue;
    }


    //重写过滤细节，返回过滤结果
    @Override
    public DocIdSet getDocIdSet(AtomicReaderContext atomicReaderContext, Bits bits) throws IOException {
        AtomicReader reader = atomicReaderContext.reader();
        OpenBitSet bitSet = new OpenBitSet(reader.numDocs());    //获取搜索的文档总数
        Term term = new Term(this.fieldKey,this.fieldValue);     //过滤的域条件
        DocsEnum docEnum = reader.termDocsEnum(term);             //获取 DocsEnum，返回过滤的文档，并枚举
        for(int i=0;i<reader.numDocs();i++){
            bitSet.set(docEnum.nextDoc());                        //将过滤返回的文档加入返回的集合
        }


        return bitSet;  //To change body of implemented methods use File | Settings | File Templates.
    }
}

二、

package search;


import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.Query;


import java.text.SimpleDateFormat;
import java.util.regex.Pattern;


/**
 * 自定义查询器，通过覆盖制定查询方法实现自定义查询
 * 本例通过覆盖通配符和模糊查询而禁用此类查询，提高系统性能，其他查询方法不变
 *
 * Created with IntelliJ IDEA.
 * User: wxshi
 * Date: 15-2-26
 * Time: 上午11:33
 * To change this template use File | Settings | File Templates.
 */
public class MyQueryParser extends QueryParser {
    public MyQueryParser(String f, Analyzer a) {
        super(f, a);
    }
    @Override
    protected Query getWildcardQuery (String field, String term) throws ParseException {
        throw new ParseException("系统禁用通配符查询");
        //return super.getWildcardQuery(f, term);
    }


    @Override
    protected Query getFuzzyQuery (String field, String term,float s) throws ParseException {
        throw new ParseException("系统禁用模糊查询");
        //return super.getWildcardQuery(f, term);
    }


    //覆盖范围查询
    @Override
    protected Query getRangeQuery (String field, String part1,String part2,boolean startInclude,boolean endInclude) throws ParseException {


        if("size".equals(field)){ //文件大小
            return NumericRangeQuery.newIntRange(field, Integer.parseInt(part1), Integer.parseInt(part2), startInclude, endInclude);
        }else if("time".equals(field)){    //日期
            String dateType = "yyyy-MM-dd";
            Pattern rex = Pattern.compile("\\d{4}-\\d{2}-\\d{2}");
            if(rex.matcher(part1).matches()&&rex.matcher(part2).matches()) {
                SimpleDateFormat formate = new SimpleDateFormat(dateType);
                try {
                    long start = formate.parse(part1).getTime();
                    long end = formate.parse(part2).getTime();
                    return NumericRangeQuery.newLongRange(field, start,end, startInclude, endInclude);
                } catch (java.text.ParseException e) {
                    e.printStackTrace();  //To change body of catch statement use File | Settings | File Templates.
                }
            }
        }
        return newRangeQuery( field,  part1, part2, startInclude, endInclude);
    }
}

三、搜索测试

package search;


import myscore.MyCustomScoreQuery;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.store.FSDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;
import utils.ConstantUtil;


import java.io.File;
import java.io.IOException;


/**
 * Created with IntelliJ IDEA.
 * User: wxshi
 * Date: 15-2-6
 * Time: 下午2:02
 * To change this template use File | Settings | File Templates.
 */
public class MYSearch {
    private IndexSearcher indexSearch = null;
    private Query query = null;
    private static Filter filter = null;
    private static CachingWrapperFilter cachingWrapperFilter;// 缓存过滤结果
    //封装IndexSearch对象
    public MYSearch(){
        try {
            IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(ConstantUtil.INDEX_STORE_PATH)));
            indexSearch = new IndexSearcher(reader);
        } catch (IOException e) {
            e.printStackTrace();  //To change body of catch statement use File | Settings | File Templates.
        }
    }


    //定义自己的filter
    public void getFilter() {
        //以包含指定项的文档进行匹配
        //filter = new FieldCacheTermsFilter("content", new String[] {"你"});


        //以特殊前缀开始的项的文档进行匹配
        //filter = new PrefixFilter(new Term("title", "文件"));


        //过滤字符开头从a到i的内容
        //filter = new TermRangeFilter("content", new BytesRef("a"), new BytesRef("m"), true, true);


        //过滤域从XX开头到XX结尾的文档
        //filter = TermRangeFilter.newStringRange("title", "1", "txt", true, true);


        //过滤文档大小XX~XX的文档
        //filter = NumericRangeFilter.newLongRange("size", 1L, 50L, true, true);


        //通过包装query对结果再进行过滤，相当于二次搜索
        //filter = new QueryWrapperFilter(new WildcardQuery(new Term("content","历史")));


        //自定义过滤器
        filter = new MyFilters("title","文件1.txt");


        // 缓存过滤器，提高搜索性能 （此过滤器会缓存过滤结果）
        cachingWrapperFilter = new CachingWrapperFilter(filter);
    }


    //搜索
    public TopDocs search(String filed,String keyWord){
        try {
            Analyzer analyzer = new IKAnalyzer();
            //在field域中查询
            QueryParser parser = new MyQueryParser(filed,analyzer);
            query = parser.parse(keyWord); //传入的搜索词
            MyCustomScoreQuery myQuery = new MyCustomScoreQuery(query);


           //使用评分排序
           // TopDocs results = indexSearch.search(myQuery,5,Sort.RELEVANCE);


           //使用docId进行排序
           // TopDocs results = indexSearch.search(myQuery,5,Sort.INDEXORDER);


           //按文件大小来排
           // TopDocs results = indexSearch.search(myQuery,5,new Sort(new SortField("size",SortField.Type.LONG)));


           //按文件名来排 ,true代表降序
           // TopDocs results = indexSearch.search(myQuery,5,new Sort(new SortField("title",SortField.Type.STRING,true)));


           //按多个域进行排序，先按评分，再按标题，再按大小
           // TopDocs results = indexSearch.search(myQuery,5,new Sort(SortField.FIELD_SCORE,new SortField("title",SortField.Type.STRING),new SortField("size",SortField.Type.LONG)));


            //不使用自定义排序，此时会根据评分排序，且能获取分数
            TopDocs results = indexSearch.search(myQuery,filter,5);


            return results;
        } catch (Exception e) {
            e.printStackTrace();  //To change body of catch statement use File | Settings | File Templates.
        }
        return null;
    }


    //解析搜索结果
    public void printResult(TopDocs results){
        ScoreDoc docs[] = results.scoreDocs;
        if(docs.length>0){
           for(int i=0;i<docs.length;i++){
               try {
                   Document doc = indexSearch.doc(docs[i].doc);


                   int j = i+1;


                   System.out.print("这是第" + j + "个检索到的结果，文件路径为：");
                   System.out.println(doc.get("path"));
                   System.out.print("这是第" + j + "个检索到的结果，文件标题为：");
                   System.out.println(doc.get("title"));
                   System.out.print("这是第" + j + "个检索到的结果，文件内容为：");
                   System.out.println(doc.get("content"));
                   System.out.print("这是第" + j + "个检索到的结果，文件大小为：");
                   System.out.println(doc.get("size"));
                   System.out.println("评分为：" + docs[i].score);
                   System.out.println("--------------------------------------------");


               } catch (IOException e) {
                   e.printStackTrace();  //To change body of catch statement use File | Settings | File Templates.
               }
           }
        }else{
            System.out.println("没有搜索结果");
        }
    }
}