Solr4：利用Filter实现两组关键词组合查询

package com.clzhang.sample.solr;

import java.io.*;
import java.util.*;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.search.highlight.TokenSources;
import org.apache.lucene.util.Version;
import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.impl.HttpSolrServer;
import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrDocument;

import org.junit.After;
import org.junit.Before;
import org.junit.Test;

import com.chenlb.mmseg4j.Dictionary;
import com.chenlb.mmseg4j.analysis.ComplexAnalyzer;

/**
 * 综合：按客户名称查询客户网络上面的负面信息
 * @author Administrator
 *
 */
public class SlorJHighlightTest {
    // mmseg4j字典路径
    private static final String MMSEG4J_DICT_PATH = "C:\\solr\\mm4jdic";
    private static Dictionary dictionary = Dictionary.getInstance(MMSEG4J_DICT_PATH);

    private HttpSolrServer server;
    private static final String DEFAULT_URL = "http://localhost:8080/solr/news";

    @Before
    public void init() {
        // 初始化Solr服务器句柄
        server = new HttpSolrServer(DEFAULT_URL);
        server.setMaxRetries(1); // defaults to 0. > 1 not recommended.
        server.setConnectionTimeout(5000); // 5 seconds to establish TCP
        server.setSoTimeout(1000); // socket read timeout
        server.setDefaultMaxConnectionsPerHost(100);
        server.setMaxTotalConnections(100);
        server.setFollowRedirects(false); // defaults to false
        server.setAllowCompression(true);
    }

    @After
    public void destory() {
        server = null;
        System.runFinalization();
        System.gc();
    }

    @Test
    public void queryCase() {
        // 步骤一：查询关键词
        String keyword = "(盐城 盐城市)";
        SolrQuery params = new SolrQuery("webTitle:" + keyword);
        params.set("start", 0);
        params.set("rows", 5);
        params.set("fl", "objectId,webTitle,webContent");
//        params.set("sort", "webTime desc");

        // 步骤二：负面关键词
        String negativeWord = "(贪污 受贿 被曝 曝光 小三 裸照)"; 
        params.addFilterQuery("webTitle:" + negativeWord);

        try {
            // 步骤三：需要高亮的关键词，默认等于查询关键词+负面关键词
            String hlKeywords = keyword + " " + negativeWord;
            
            // 查询
            QueryResponse response = server.query(params);
            Analyzer analyzer = new ComplexAnalyzer(dictionary);
            QueryScorer scorer = new QueryScorer(new QueryParser(
                    Version.LUCENE_41, null, analyzer).parse(hlKeywords), null);
            Highlighter highlighter = new Highlighter(scorer);
            highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));

            // 输出
            SolrDocumentList list = response.getResults();
            System.out.println("返回：" + list.getNumFound() + "条记录\t耗时：" + response.getElapsedTime() + "毫秒");
            for (int i = 0; i < list.size(); i++) {
                SolrDocument doc = (SolrDocument)list.get(i);
                String objectId = doc.get("objectId").toString();
                String title = doc.get("webTitle").toString();
                String content = doc.get("webContent").toString();
                StringBuilder sbTitle = new StringBuilder();
                
                // 有高亮结果则用高亮结果；没有则用无高亮查询结果。
                // 仅对标题（webTitle）高亮，内容（webContent）忽略
                TokenStream streamContent = TokenSources.getTokenStream("", title, analyzer);
                String[] fragContent = highlighter.getBestFragments(streamContent, title, 5000);
                if(fragContent != null && fragContent.length > 0) {
                    for(String str: fragContent) {
                        sbTitle.append(str);
                    }
                }else {
                    sbTitle.append(title);
                }
                System.out.println(sbTitle.toString());
//                System.out.println(content);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } 
    }
}