模糊查询-lucene-IKAnalyzer

package com.beibei.webapp.search.index; import java.io.BufferedReader; import java.io.File; import java.io.FileReader; import java.io.FileWriter; import java.io.IOException; import java.io.PrintWriter; import java.sql.ResultSet; import java.util.List; import java.util.Map; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.Term; import org.apache.lucene.store.Directory; import org.htmlparser.Parser; import com.beibei.webapp.model.BbProduct; /** * <p> * ClassName : IndexManager.java * </p> * <p> * Title : TODO * </p> * <p> * Description : TODO * </p> * <p> * Copyright : beibei. * </p> * <p> * CreateTime : MAR 8, 2010 10:35:42 AM * * @author : minami * @version : 1.0 */ public class IndexManager { /** * 将ID写入到磁盘文件中 */ boolean indexFlag = false; public static boolean writeStoreId(String path, String storeId) { boolean b = false; try { File file = new File(path); if (!file.exists()) { file.createNewFile(); } FileWriter fw = new FileWriter(path); PrintWriter out = new PrintWriter(fw); out.write(storeId); out.close(); fw.close(); b = true; } catch (IOException e) { e.printStackTrace(); } return b; } /** * 取得存储在磁盘中的ID */ public static String getStoreId(String path) { String storeId = ""; try { File file = new File(path); if (!file.exists()) { file.createNewFile(); } FileReader fr = new FileReader(path); BufferedReader br = new BufferedReader(fr); storeId = br.readLine(); if (storeId == null || storeId == "") storeId = "0"; br.close(); fr.close(); } catch (Exception e) { e.printStackTrace(); } return storeId; } /** * Add one document to the lucene index * * @throws SQLException * @throws ParserException * @throws IOException * @throws CorruptIndexException */ /** * 为数据库建立索引。 首先要定义一个IndexWriter(),它是将索引写进Lucene自己的数据库中，它存放的位置是有你自己定义的。 * 在定义IndexWriter 是需要指定它的分析器。 getAnalyzer()它作用是对文本进行分析，判断如何进行切词。 * 接着，要定义一个Document。Document相当于二维表中一行数 据一样。 * Document里包含的是Field字段，Field相当于数据库中一列，也就是一个属性，一个字段。 * 最后应该对IndexWriter进行优化，方法很简单，就是writer.optimize(). */ @SuppressWarnings("unchecked") public boolean createIndex(Directory directory, String storeIdPath, List productList, Analyzer analyzer, Map<Integer, String> map) {// 把RS换成LIST原理一样 IndexWriter iwriter = null; try { boolean empty = isEmpty(storeIdPath); iwriter = new IndexWriter(directory, analyzer, empty, IndexWriter.MaxFieldLength.UNLIMITED); iwriter.setMergeFactor(100); iwriter.setMaxBufferedDocs(100); addIndex(iwriter, analyzer, productList, storeIdPath, map); return true; } catch (Exception e) { e.printStackTrace(); System.out.println("出错了" + e.getClass() + "\n 错误信息为: " + e.getMessage()); return false; } finally { try { iwriter.optimize(); iwriter.close(); } catch (Exception e) { e.printStackTrace(); } } } @SuppressWarnings("unchecked") public boolean createIndex(Directory directory, String storeIdPath, ResultSet rs, Analyzer analyzer, Map<String, String> map) {// 把RS换成LIST原理一样 IndexWriter iwriter = null; try { boolean empty = isEmpty(storeIdPath); System.out.println(empty); iwriter = new IndexWriter(directory, analyzer, empty, new IndexWriter.MaxFieldLength(100)); iwriter.setMergeFactor(100); iwriter.setMaxBufferedDocs(100); addIndex(iwriter, analyzer, rs, storeIdPath, map); return true; } catch (Exception e) { e.printStackTrace(); System.out.println("出错了" + e.getClass() + "\n 错误信息为: " + e.getMessage()); return false; } finally { try { iwriter.optimize(); iwriter.close(); rs.close(); } catch (Exception e) { e.printStackTrace(); } } } /* * 增加索引 */ @SuppressWarnings("unchecked") public void addIndex(IndexWriter iwriter, Analyzer analyzer, ResultSet rs, String storeIdPath, Map<String, String> map) { try { String storeId = getStoreId("/index/storeId.txt"); int id = Integer.parseInt(storeId); while (rs.next()) { Document d = new Document(); storeId = rs.getString("PRODUCTID"); if (Integer.parseInt(storeId) > id) { Parser parser = new Parser(); parser.setInputHTML("" + rs.getString("PRODUCTDESCRIBE")); String name = rs.getString("PRODUCTNAME"); if (null == name) { name = "wrong-product-name"; } String strings = parser.parse(null).elementAt(0) .toPlainTextString().trim(); String memberName = map.get(rs.getString("MEMBERID")); d.add(new Field("id", "" + rs.getString("PRODUCTID"), Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS)); d.add(new Field("name", name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS)); d.add(new Field("describe", strings, Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS)); d.add(new Field("cateId", "" + rs.getString("CATEID"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("memberName", memberName, Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("price", "" + rs.getString("PRICE"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("outDate", "" + rs.getString("OUTDATE"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("leastOrder", "" + rs.getString("LEASTORDER"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("area", "" + rs.getString("AREA"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("total", "" + rs.getString("TOTAL"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("image", "" + rs.getString("IMAGE"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); d.add(new Field("unit", "" + rs.getString("UNIT"), Field.Store.YES, Field.Index.NO, Field.TermVector.NO)); iwriter.addDocument(d); indexFlag = true; storeId = rs.getString("PRODUCTID"); } else { continue; } } if (indexFlag) { // 将最后一个的ID存到磁盘文件中 writeStoreId(storeIdPath, storeId); } } catch (Exception e) { e.printStackTrace(); } } public void addIndex(IndexWriter iwriter, Analyzer analyzer, List<BbProduct> productList, String storeIdPath, Map<Integer, String> map) { try { String storeId = getStoreId("/index/storeId.txt"); int id = Integer.parseInt(storeId); for (BbProduct bp : productList) { Document d = new Document(); if (bp.getProductId() > id) { Parser parser = new Parser(); parser.setInputHTML("" + bp.getProductDescribe()); String name = bp.getProductName(); if (null == name) { name = "wrong-product-name"; } String strings = parser.parse(null).elementAt(0) .toPlainTextString().trim(); String memberName = map.get(bp.getMemberId());