1. 程式人生 > >Lucene筆記21-Lucene的自定義排序

Lucene筆記21-Lucene的自定義排序

一、排序介紹

Lucene對文件搜尋完成後,顯示的結果是有一個順序的,如果沒有設定排序規則,那麼這個順序就是按照文件的評分降序排列,至於評分的計算,是一個比較複雜的公式,這裡不先研究了。可是有時候,我們需要根據需求,改變預設的排序規則,這時候就要用到自定義排序啦,下面來看一下自定義排序是怎麼使用的吧。

二、程式碼演示

package com.wsy;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

public class CustomSortTest {
    private static Directory directory;
    private static IndexReader indexReader;

    static {
        try {
            directory = FSDirectory.open(new File("E:\\Lucene\\IndexLibrary"));
            indexReader = IndexReader.open(directory);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public void index(boolean update) {
        IndexWriter indexWriter = null;
        try {
            indexWriter = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
            if (update) {
                indexWriter.deleteAll();
            }
            File[] files = new File("E:\\Lucene\\SearchSource").listFiles();
            for (File file : files) {
                Document document = new Document();
                document.add(new Field("content", new FileReader(file)));
                document.add(new Field("fileName", file.getName(), Field.Store.YES, Field.Index.NOT_ANALYZED));
                document.add(new Field("path", file.getAbsolutePath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
                document.add(new NumericField("date", Field.Store.YES, true).setLongValue(file.lastModified()));
                document.add(new NumericField("size", Field.Store.YES, true).setIntValue((int) (file.length())));
                indexWriter.addDocument(document);
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (indexWriter != null) {
                try {
                    indexWriter.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    public IndexSearcher getIndexSearcher() {
        try {
            if (indexReader == null) {
                indexReader = IndexReader.open(directory);
            } else {
                IndexReader temp = IndexReader.openIfChanged(indexReader);
                if (temp != null) {
                    indexReader.close();
                    indexReader = temp;
                }
            }
            return new IndexSearcher(indexReader);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    public void searcher(String queryString, Sort sort) {
        try {
            IndexSearcher indexSearcher = getIndexSearcher();
            QueryParser queryParser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
            Query query = queryParser.parse(queryString);
            TopDocs topDocs;
            if (sort != null) {
                topDocs = indexSearcher.search(query, 100, sort);
            } else {
                topDocs = indexSearcher.search(query, 100);
            }
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
            for (ScoreDoc scoreDoc : scoreDocs) {
                Document document = indexSearcher.doc(scoreDoc.doc);
                // 依次輸出文件id,文件得分,文件名字,文件路徑,文件大小,文件修改時間
                System.out.println(scoreDoc.doc + "-->" + scoreDoc.score + "-->" + document.get("fileName") + "-->" + document.get("path") + "-->" + document.get("size") + "-->" + simpleDateFormat.format(new Date(Long.valueOf(document.get("date")))));
            }
            indexSearcher.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        CustomSortTest customSortTest = new CustomSortTest();
        customSortTest.index(true);
        // 預設排序(按照評分從高到底降序排列)
        System.out.println("預設排序(按照評分從高到底降序排列)");
        customSortTest.searcher("java", null);
        // Sort.INDEXORDER是通過doc的id進行升序排序
        System.out.println("Sort.INDEXORDER是通過doc的id進行升序排序");
        customSortTest.searcher("java", Sort.INDEXORDER);
        // Sort.RELEVANCE是按照關聯性來排序
        System.out.println("Sort.RELEVANCE是按照關聯性來排序");
        customSortTest.searcher("java", Sort.RELEVANCE);
        // 自定義排序,預設是升序,如果需要降序,根據SortField(String field, int type, boolean reverse)構造方法,多傳一個true即可
        System.out.println("自定義排序,這裡是按照檔案大小升序排序");
        customSortTest.searcher("java", new Sort(new SortField("size", SortField.INT)));
        System.out.println("自定義排序,這裡是按照檔案日期升序排序");
        customSortTest.searcher("java", new Sort(new SortField("date", SortField.LONG)));
        System.out.println("自定義排序,這裡是按照檔名稱升序排序");
        customSortTest.searcher("java", new Sort(new SortField("fileName", SortField.STRING)));
        // 多欄位排序
        System.out.println("自定義多欄位排序,這裡是先按照檔案日期升序排序,再按照大小降序");
        customSortTest.searcher("java", new Sort(new SortField("date", SortField.LONG), new SortField("size", SortField.INT, true)));
    }
}