Lucene筆記12-Lucene的搜尋-複習和再查詢分頁搜尋
阿新 • • 發佈:2018-11-04
一、Lucene的分頁搜尋
Lucene的分頁不像資料庫中的limit的方式,而是提供了一種“再查詢”的方式。什麼是“再查詢”呢?就是第一次把所有的資料都取出來,第二次查詢再根據需求,從第幾條取到第幾條,分兩步進行查詢,所以叫“再查詢”。
二、測試程式碼
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.ParseException; import org.apache.lucene.queryParser.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; import org.apache.lucene.util.Version; import java.io.File; import java.io.FileReader; import java.io.IOException; public class FileIndexUtils { private static Directory directory; private static IndexReader indexReader; static { try { directory = FSDirectory.open(new File("E:\\Lucene\\IndexLibrary")); } catch (IOException e) { e.printStackTrace(); } } public FileIndexUtils() { try { indexReader = IndexReader.open(directory); } catch (IOException e) { e.printStackTrace(); } } public static 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() / 1024))); indexWriter.addDocument(document); } } catch (IOException e) { e.printStackTrace(); } finally { if (indexWriter != null) { try { indexWriter.close(); } catch (IOException e) { e.printStackTrace(); } } } } public void searchPage(String queryString, int pageIndex, int pageSize) { try { IndexSearcher indexSearcher = new IndexSearcher(indexReader); QueryParser queryParser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35)); Query query = queryParser.parse(queryString); TopDocs topDocs = indexSearcher.search(query, pageIndex * pageSize); ScoreDoc[] scoreDocs = topDocs.scoreDocs; // 分頁查詢 for (int i = (pageIndex - 1) * pageSize; i < pageIndex * pageSize; i++) { Document document = indexSearcher.doc(scoreDocs[i].doc); System.out.println(scoreDocs[i].doc + ":" + document.get("path") + " " + document.get("fileName")); } System.out.println("-------------------------------------------------"); // 不分頁查詢 for (int i = 0; i < scoreDocs.length; i++) { Document document = indexSearcher.doc(scoreDocs[i].doc); System.out.println(scoreDocs[i].doc + ":" + document.get("path") + " " + document.get("fileName")); } indexSearcher.close(); } catch (ParseException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } public static void main(String[] args) { FileIndexUtils.index(true); FileIndexUtils fileIndexUtils = new FileIndexUtils(); fileIndexUtils.searchPage("java", 2, 3); } }
在searchPage()裡面,我們對分頁和不分頁都做了查詢,用於對比,可以知道分頁結果正確。