Lucene4.7.2实例之用索引搜索文件

来源:互联网 时间:1970-01-01


上一篇写完了创建索引的过程,这篇写用索引搜索文件,环境window64+jdk1.6+lucene4.7.2(lucene4.8要求jdk1.7)

步骤:

1.创建Directory对象,即索引文件夹

2.创建IndexReader对象,读取索引文件夹

3.创建IndexSearch对象,建立索引查询

4.创建QueryParser对象

5.把查询的值通过QueryParser对象转Query对象

6.创建TopDocs对象

7.用TopDocs对象根据Query对象查询

8.关闭IndexReader对象


import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;


import org.apache.lucene.analysis.Analyzer;
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.ParseException;
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.FSDirectory;
import org.apache.lucene.util.Version;


public class SearchFiles {


    @SuppressWarnings("unused")
    public SearchFiles() throws IOException, ParseException {
String indexPath = "D://lucene-test//index";
String field = "contents";
String queries = null;
int repeat = 0;
boolean raw = false;
String queryString = null;
int hitsPerPage = 10;


IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexPath)));
IndexSearcher searcher = new IndexSearcher(reader);
// :Post-Release-Update-Version.LUCENE_XY:
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);


BufferedReader in = null;
if (queries != null) {
   in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
} else {
   in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
// :Post-Release-Update-Version.LUCENE_XY:
QueryParser parser = new QueryParser(Version.LUCENE_47, field, analyzer);
while (true) {
   if (queries == null && queryString == null) { // prompt the user
System.out.println("Enter query: ");
   }


   String line = queryString != null ? queryString : in.readLine();


   if (line == null || line.length() == -1) {
break;
   }


   line = line.trim();
   if (line.length() == 0) {
break;
   }


   Query query = parser.parse(line);
   System.out.println("Searching for: " + query.toString(field));


   if (repeat > 0) { // repeat & time as benchmark
Date start = new Date();
for (int i = 0; i < repeat; i++) {
   searcher.search(query, null, 100);
}
Date end = new Date();
System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
   }


   doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);


   if (queryString != null) {
break;
   }
}
reader.close();
    }


    private void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw, boolean b) throws IOException {
// Collect enough docs to show 5 pages
TopDocs results = searcher.search(query, 5 * hitsPerPage);
ScoreDoc[] hits = results.scoreDocs;


int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");


int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);


while (true) {
   if (end > hits.length) {
System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected.");
System.out.println("Collect more (y/n) ?");
String line = in.readLine();
if (line.length() == 0 || line.charAt(0) == 'n') {
   break;
}


hits = searcher.search(query, numTotalHits).scoreDocs;
   }


   end = Math.min(hits.length, start + hitsPerPage);


   for (int i = start; i < end; i++) {
if (raw) { // output raw format
   System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
   continue;
}


Document doc = searcher.doc(hits[i].doc);
String path = doc.get("path");
if (path != null) {
   System.out.println((i + 1) + ". " + path);
   String title = doc.get("title");
   if (title != null) {
System.out.println("   Title: " + doc.get("title"));
   }
} else {
   System.out.println((i + 1) + ". " + "No path for this document");
}


   }


   // if (!interactive || end == 0) {
   // break;
   // }


   if (numTotalHits >= end) {
boolean quit = false;
while (true) {
   System.out.print("Press ");
   if (start - hitsPerPage >= 0) {
System.out.print("(p)revious page, ");
   }
   if (start + hitsPerPage < numTotalHits) {
System.out.print("(n)ext page, ");
   }
   System.out.println("(q)uit or enter number to jump to a page.");


   String line = in.readLine();
   if (line.length() == 0 || line.charAt(0) == 'q') {
quit = true;
break;
   }
   if (line.charAt(0) == 'p') {
start = Math.max(0, start - hitsPerPage);
break;
   } else if (line.charAt(0) == 'n') {
if (start + hitsPerPage < numTotalHits) {
   start += hitsPerPage;
}
break;
   } else {
int page = Integer.parseInt(line);
if ((page - 1) * hitsPerPage < numTotalHits) {
   start = (page - 1) * hitsPerPage;
   break;
} else {
   System.out.println("No such page");
}
   }
}
if (quit)
   break;
end = Math.min(numTotalHits, start + hitsPerPage);
   }
}
    }


    public static void main(String[] args) {
try {
   new SearchFiles();
} catch (IOException e) {
   e.printStackTrace();
} catch (ParseException e) {
   e.printStackTrace();
}
    }
}




相关阅读:
Top