对网上盛传的lucene使用方法进行了一些修改.网上的是对某个目录下所有HTML文件进行索引和搜索。但是不支持多重目录下的搜索。这里做了一点修改。大部分还是网上的代码。
Constants.java
package testlucene;public class Constants { //要索引的文件的存放路径 public final static String INDEX_FILE_PATH = "c:\\dataDir"; //索引的存放位置 public final static String INDEX_STORE_PATH = "c:\\indexDir";}
LuceneIndex.java
package testlucene;import java.io.*;import java.util.*;import org.apache.lucene.document.*;import org.apache.lucene.index.*;import org.mira.lucene.analysis.IK_CAnalyzer;public class LuceneIndex { private IndexWriter writer = null; public LuceneIndex(){ try { writer = new IndexWriter(Constants.INDEX_STORE_PATH,new IK_CAnalyzer(),true); //true表示可以重写（覆盖？） }catch(Exception e){ e.printStackTrace(); } } @SuppressWarnings("deprecation") private Document getDocument(File f) throws Exception{ //为每个文件建立一个Document文档，里面增加内容 Document doc = new Document(); if(f.isFile()){ FileInputStream is = new FileInputStream(f); Reader reader = new BufferedReader(new InputStreamReader(is)); doc.add(new Field("contents",reader)); doc.add(new Field("path",f.getCanonicalPath(),Field.Store.YES,Field.Index.TOKENIZED)); } return doc; } public void writeToIndex() throws Exception{ File folder = new File(Constants.INDEX_FILE_PATH); if(folder.isDirectory()){ File[] files = getFileList(new File(Constants.INDEX_FILE_PATH)); for(int i=0; i<files.length; i++){ File file = new File(files[i].toString()); Document doc = getDocument(file); System.out.println("正在为文件 (" + file + ") 建立索引..."); writer.addDocument(doc); } } } public void close()throws Exception{ writer.close(); } public static void main(String[] args)throws Exception{ LuceneIndex indexer = new LuceneIndex(); Date start = new Date(); indexer.writeToIndex(); Date end = new Date(); System.out.println("建立索引用时 " + (end.getTime() - start.getTime()) + "毫秒"); indexer.close(); } @SuppressWarnings("unchecked") private File[] getFileList(File file){ File[] list = null; ArrayList show = new ArrayList(); if(file.isFile()){list = new File[1];list[0] = file;return list;} else if(file.isDirectory()){ File[] subDir = file.listFiles(); for(int j=0;j<subDir.length;j++){ if(subDir[j].isFile()){ show.add(subDir[j]); }else if(subDir[j].isDirectory()){ File[] third = getFileList(subDir[j]); for(int k=0;null!=third&&k<third.length;k++) show.add(third[k]); } } } list = new File[show.size()]; for(int m=0;m<show.size();m++)list[m]=new File(show.get(m).toString()); return list; }}
package testlucene;import java.io.BufferedReader;import java.io.File;import java.io.FileInputStream;import java.io.FileNotFoundException;import java.io.FileReader;import java.io.InputStreamReader;import java.io.RandomAccessFile;import java.util.*;import org.apache.lucene.document.*;import org.apache.lucene.queryParser.*;import org.apache.lucene.search.*;import org.mira.lucene.analysis.IK_CAnalyzer;public class LuceneSearch { private IndexSearcher searcher = null; private Query query = null; private File shopInfoTxt = null; private RandomAccessFile bw; public LuceneSearch() { try { searcher = new IndexSearcher(Constants.INDEX_STORE_PATH); } catch (Exception e) { e.printStackTrace(); } } @SuppressWarnings("deprecation") public final Hits Search(String keyword) { System.out.println("正在检索关键字 " + keyword); try { query = new QueryParser("contents", new IK_CAnalyzer()) .parse(keyword); Date start = new Date(); Hits hits = searcher.search(query); Date end = new Date(); System.out.println("检索完成，用时" + (end.getTime() - start.getTime()) + "毫秒"); return hits; } catch (Exception e) { e.printStackTrace(); return null; } } @SuppressWarnings("deprecation") public String printResult(Hits h, String test) {//显示关键字再哪个文件的哪行，用|隔开 if (h.length() == 0) { System.out.println("对不起，没有找到您要的结果。"); return ""; } else { for (int i = 0; i < h.length(); i++) { try { Document doc = h.doc(i); System.out.print("这是第" + (i + 1) + "个检索到的结果，文件名为 ："); System.out.println(doc.get("path")); BufferedReader br = new BufferedReader(new FileReader(doc.get("path"))); String line = null; int lineNum = 0; while ((line = br.readLine()) != null) { lineNum++; if (line.indexOf(test) != -1) return doc.get("path")+"|"+lineNum; } } catch (Exception e) { e.printStackTrace(); } } } return ""; } public static void main(String[] args) throws Exception { LuceneSearch temp = new LuceneSearch(); //得到分类信息 String content = temp.getInnerContent3("nav_w","main_w"); content = content.replaceAll(" ", ""); content = content.replaceAll(">", ">"); System.out.println("==========分类信息:=============\n"+content+"\n================"); String typeinfo = content; //得到商家具体信息 String shopInfo = ""; content = temp.getInnerContent3("shopInfo","shopRemark"); shopInfo = content; //DataOutputStream write = new DataOutputStream(new FileOutputStream(temp.getShopInfoTxt())); //write.write(typeinfo.getBytes()); temp.getBw().write(typeinfo.getBytes()); System.out.println("得到商家信息:\n"+content); //地址信息 int addStart = content.indexOf("地址"); int addEnd = content.indexOf("电话"); if(addStart>0&&addEnd>0){ content = content.substring(addStart+3, addEnd); content = content.replaceAll(" ", ""); System.out.println("==========地址信息:=============\n"+content+"\n==============="); } //write.write(content.getBytes()); temp.getBw().write(content.getBytes()); temp.getBw().write("\n".getBytes()); //电话信息 content = shopInfo; int telStart = content.indexOf("电话"); int telEnd = content.indexOf("报错"); if(telStart>0&&telEnd>0){ content = content.substring(telStart+3,telEnd); content = content.replaceAll(" ", ""); System.out.println("=================电话信息:================\n"+content+"\n=================="); //write.write(content.getBytes()); temp.getBw().write(content.getBytes()); temp.getBw().write("\n".getBytes()); } //商家介绍 content = shopInfo; int introStart = content.indexOf("商户简介"); int introEnd = content.indexOf("分类标签"); if(introStart>0&&introEnd>0){ content = content.substring(introStart+5,introEnd); content = content.replaceAll(" ", ""); System.out.println("=================商家介绍:===============\n"+content+"\n==================="); //write.write(content.getBytes()); temp.getBw().write(content.getBytes()); temp.getBw().write("\n".getBytes()); } //分类标签 content = shopInfo; int typeStart = content.indexOf("分类标签"); int typeEnd = content.indexOf("网友推荐"); if(typeStart>0&&typeEnd>0){ content = content.substring(typeStart+4,typeEnd); content = content.replaceAll(" ", ""); System.out.println("=================分类标签:===============\n"+content+"\n==================="); //write.write(content.getBytes()); temp.getBw().write(content.getBytes()); temp.getBw().write("\n".getBytes()); } //网友推荐 content = shopInfo; int suggestEnd = content.lastIndexOf(")"); if(typeEnd>0&&suggestEnd>0){ content = content.substring(typeEnd+4,suggestEnd+1); content = content.replaceAll(" ", ""); System.out.println("=================网友推荐:===============\n"+content+"\n==================="); //write.write(content.getBytes()); //write.close(); temp.getBw().write(content.getBytes()); temp.getBw().write("\n".getBytes()); } temp.getBw().close(); } @SuppressWarnings("deprecation") public String getInnerContent3(String first,String sec) throws Exception, FileNotFoundException{ //选择两个字段之间的内容，读取其中的内容 LuceneSearch test = new LuceneSearch(); Hits h = null; String scrrenString = ""; //first = "nav_w";//起始位置 h = test.Search(first); String start = test.printResult(h, first); String fileName = start.substring(0, start.indexOf("|")); int startLine = Integer.parseInt(start.substring(start.indexOf("|")+1, start.length())); //sec = "main_w";//截止位置 h = test.Search(sec); String end = test.printResult(h, sec); String fileName2 = start.substring(0, start.indexOf("|")); int endLine = Integer.parseInt(end.substring(end.indexOf("|")+1, end.length())); if(fileName2.equalsIgnoreCase(fileName)){ String tempFileName = ""; tempFileName = fileName.substring(fileName.lastIndexOf("\\")).replace(".html", ".txt"); tempFileName = fileName.substring(fileName.lastIndexOf("\\")).replace(".htm", ".txt"); shopInfoTxt = new File("c:/temp/",tempFileName); if(!shopInfoTxt.exists())shopInfoTxt.createNewFile(); bw = new RandomAccessFile(shopInfoTxt,"rw"); BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(fileName),"utf-8")); String line = null; int lineNum = 0; System.out.println("sentences from "+startLine+" to "+endLine); while ((line = br.readLine()) != null) { lineNum++; if (lineNum>=startLine&&lineNum<endLine)scrrenString+=line; } scrrenString = getShortFormat(scrrenString); scrrenString = scrrenString.substring(scrrenString.indexOf("：")+1); } return scrrenString; } public File getShopInfoTxt() { return shopInfoTxt; } public RandomAccessFile getBw() { return bw; } private static String getShortFormat(String content){//去掉<>里面的内容 String finalString = content.trim(); int first = finalString.indexOf("<"); int end = finalString.indexOf(">"); if(first>-1&&end>-1){ finalString = finalString.substring(0, first).trim()+finalString.substring(end+1, finalString.length()).trim(); finalString = getShortFormat(finalString); } return finalString; }}
相关资源：基于Lucene的搜索引擎的实现
