使用Lucene全文检索并使用中文版和高亮显示

使用Lucene全文检索并使用中文版和高亮显示

中文分词需要引入 中文分词发的jar 包,咱们从maven中获取

org.apache.lucene
lucene-analyzers-smartcn
5.3.1

下面是分词和索引的事例

package LuceneTest.LuceneTest;

import java.nio.file.Paths;

import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
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.junit.Test;

public class IndexChina {

private Directory dir; //存放索引的位置

//准备一下用来测试的数据
private Integer ids[] = {1, 2, 3}; //用来标识文档
private String citys[] = {"上海", "南京", "青岛"};
private String descs[] = {
"上海是个繁华的城市。",
"南京是一个有文化的城市。",
"青岛是一个美丽的城市。"
};

//生成索引
@Test
public void index(String indexDir) throws Exception {
dir = FSDirectory.open(Paths.get(indexDir));
IndexWriter writer = getWriter();
for(int i = 0; i < ids.length; i++) {
Document doc = new Document();
doc.add(new IntField("id", ids[i], Store.YES));
doc.add(new StringField("city", citys[i], Store.YES));
doc.add(new TextField("desc", descs[i], Store.YES));
writer.addDocument(doc); //添加文档
}
writer.close(); //close了才真正写到文档中
}

//获取IndexWriter实例
private IndexWriter getWriter() throws Exception {
SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();//使用中文分词器
IndexWriterConfig config = new IndexWriterConfig(analyzer); //将标准分词器配到写索引的配置中
IndexWriter writer = new IndexWriter(dir, config); //实例化写索引对象
return writer;
}

public static void main(String[] args) throws Exception {
new IndexChina().index("D:\lucene2");
}
}

新建的查询

package LuceneTest.LuceneTest;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.IndexSearcher;
import org.apache.lucene.search.Query;
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 SearcherChina {

public static void search(String indexDir, String q) throws Exception {

Directory dir = FSDirectory.open(Paths.get(indexDir)); //获取要查询的路径，也就是索引所在的位置
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer(); //使用中文分词器
QueryParser parser = new QueryParser("desc", analyzer); //查询解析器
Query query = parser.parse(q); //通过解析要查询的String，获取查询对象

long startTime = System.currentTimeMillis(); //记录索引开始时间
TopDocs docs = searcher.search(query, 10);//开始查询，查询前10条数据，将记录保存在docs中
long endTime = System.currentTimeMillis(); //记录索引结束时间
System.out.println("匹配" + q + "共耗时" + (endTime-startTime) + "毫秒");
System.out.println("查询到" + docs.totalHits + "条记录");

for(ScoreDoc scoreDoc : docs.scoreDocs) { //取出每条查询结果
Document doc = searcher.doc(scoreDoc.doc); //scoreDoc.doc相当于docID,根据这个docID来获取文档
System.out.println(doc.get("city"));
System.out.println(doc.get("desc"));
String desc = doc.get("desc");
}
reader.close();
}

public static void main(String[] args) {
String indexDir = "D:\lucene2";
String q = "上海繁华"; //查询这个字符
try {
search(indexDir, q);
} catch (Exception e) {
e.printStackTrace();
}
}
}

搜索结果的高亮显示

引入jar文件

org.apache.lucene
lucene-highlighter
5.3.1

新建查询并将查询的结果高亮

package LuceneTest.LuceneTest;

import java.io.StringReader;
import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class SearcherChina {

public static void search(String indexDir, String q) throws Exception {

Directory dir = FSDirectory.open(Paths.get(indexDir)); //获取要查询的路径，也就是索引所在的位置
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer(); //使用中文分词器
QueryParser parser = new QueryParser("desc", analyzer); //查询解析器
Query query = parser.parse(q); //通过解析要查询的String，获取查询对象

long startTime = System.currentTimeMillis(); //记录索引开始时间
TopDocs docs = searcher.search(query, 10);//开始查询，查询前10条数据，将记录保存在docs中
long endTime = System.currentTimeMillis(); //记录索引结束时间
System.out.println("匹配" + q + "共耗时" + (endTime-startTime) + "毫秒");
System.out.println("查询到" + docs.totalHits + "条记录");

//此处加入的是搜索结果的高亮部分
SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("",""); //如果不指定参数的话，默认是加粗，即
QueryScorer scorer = new QueryScorer(query);//计算得分，会初始化一个查询结果最高的得分
Fragmenter fragmenter = new SimpleSpanFragmenter(scorer); //根据这个得分计算出一个片段
Highlighter highlighter = new Highlighter(simpleHTMLFormatter, scorer);
highlighter.setTextFragmenter(fragmenter); //设置一下要显示的片段

for(ScoreDoc scoreDoc : docs.scoreDocs) { //取出每条查询结果
Document doc = searcher.doc(scoreDoc.doc); //scoreDoc.doc相当于docID,根据这个docID来获取文档
System.out.println(doc.get("city"));
System.out.println(doc.get("desc"));
String desc = doc.get("desc");

//显示高亮部分
if(desc != null) {
TokenStream tokenStream = analyzer.tokenStream("desc", new StringReader(desc));
String summary = highlighter.getBestFragment(tokenStream, desc);
System.out.println(summary);
}

}

reader.close();
}

public static void main(String[] args) {
String indexDir = "D:\lucene2";
String q = "南京文化"; //查询这个字符
try {
search(indexDir, q);
} catch (Exception e) {
e.printStackTrace();
}
}
}