• lucene 4.0学习


    一:官方文件

      http://lucene.apache.org/core/4_0_0/

      ps:网上参考文章:http://www.cnblogs.com/xing901022/p/3933675.html

    二:jar包

    (1)lucene-core-4.0.0.jar

    (2)lucene-analyzers-common-4.0.0.jar

    (3)lucene-analyzers-smartcn-4.0.0.jar

    (4)lucene-queries-4.0.0.jar

    (5)lucene-queryparser-4.0.0.jar

    (6)jxl.jar

    (7)spring相关jar包

    (8)poi包

    注:目前最新的lucene6.2需要jdk1.8,貌似是myeclipse8.5不兼容jdk1.8,导致出错,所以还是选用了jdk1.6+lucene4.0

    三:例子

    package demo;
    
    import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileReader;
    import java.util.ArrayList;
    import java.util.Date;
    import java.util.List;
    
    import jxl.Cell;
    import jxl.Sheet;
    import jxl.Workbook;
    
    import org.apache.lucene.analysis.Analyzer;
    import org.apache.lucene.analysis.standard.StandardAnalyzer;
    import org.apache.lucene.document.Document;
    import org.apache.lucene.document.TextField;
    import org.apache.lucene.document.Field.Store;
    import org.apache.lucene.index.DirectoryReader;
    import org.apache.lucene.index.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    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.store.Directory;
    import org.apache.lucene.store.FSDirectory;
    import org.apache.lucene.util.Version;
    import org.apache.poi.hwpf.HWPFDocument;
    import org.apache.poi.hwpf.usermodel.Range;
    import org.springframework.stereotype.Controller;
    import org.springframework.web.bind.annotation.RequestMapping;
    import org.springframework.web.bind.annotation.ResponseBody;
    
    /**
     * @author xinghl
     *
     */
    @Controller
    @RequestMapping("/luceneController")
    public class luceneController{
        private static String content="";
        
        private static String INDEX_DIR = "D:\luceneIndex";
        private static String DATA_DIR = "D:\luceneData";
        private static Analyzer analyzer = null;
        private static Directory directory = null;
        private static IndexWriter indexWriter = null;
        
      
         * 创建当前文件目录的索引
         * @param path 当前文件目录
         * @return 是否成功
         */
        @SuppressWarnings({ "deprecation" })
        public static boolean createIndex(String path){
            Date date1 = new Date();
            List<File> fileList = getFileList(path);
            for (File file : fileList) {
                content = "";
                //获取文件后缀
                String type = file.getName().substring(file.getName().lastIndexOf(".")+1);
                if("txt".equalsIgnoreCase(type)){
                    
                    content += txt2String(file);
                
                }else if("doc".equalsIgnoreCase(type)){
                
                    content += doc2String(file);
                
                }else if("xls".equalsIgnoreCase(type)){
                    
                    content += xls2String(file);
                    
                }
                
                System.out.println("name :"+file.getName());
                System.out.println("path :"+file.getPath());
                System.out.println();
                
                
                try{
                    analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
                    directory = FSDirectory.open(new File(INDEX_DIR));
        
                    File indexFile = new File(INDEX_DIR);
                    if (!indexFile.exists()) {
                        indexFile.mkdirs();
                    }
                    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_CURRENT, analyzer);
                    indexWriter = new IndexWriter(directory, config);
                    
                    Document document = new Document();
                    document.add(new TextField("filename", file.getName(), Store.YES));
                    document.add(new TextField("content", content, Store.YES));
                    document.add(new TextField("path", file.getPath(), Store.YES));
                    indexWriter.addDocument(document);
                    indexWriter.commit();
                    closeWriter();
        
                    
                }catch(Exception e){
                    e.printStackTrace();
                }
                content = "";
            }
            Date date2 = new Date();
            System.out.println("创建索引-----耗时:" + (date2.getTime() - date1.getTime()) + "ms
    ");
            return true;
        }
        
        /**
         * 读取txt文件的内容
         * @param file 想要读取的文件对象
         * @return 返回文件内容
         */
        public static String txt2String(File file){
            String result = "";
            try{
                BufferedReader br = new BufferedReader(new FileReader(file));//构造一个BufferedReader类来读取文件
                String s = null;
                while((s = br.readLine())!=null){//使用readLine方法,一次读一行
                    result = result + "
    " +s;
                }
                br.close();    
            }catch(Exception e){
                e.printStackTrace();
            }
            return result;
        }
        
        /**
         * 读取doc文件内容
         * @param file 想要读取的文件对象
         * @return 返回文件内容
         */
        public static String doc2String(File file){
            String result = "";
            try{
                FileInputStream fis = new FileInputStream(file);
                HWPFDocument doc = new HWPFDocument(fis);
                Range rang = doc.getRange();
                result += rang.text();
                fis.close();
            }catch(Exception e){
                e.printStackTrace();
            }
            return result;
        }
        
        /**
         * 读取xls文件内容
         * @param file 想要读取的文件对象
         * @return 返回文件内容
         */
        public static String xls2String(File file){
            String result = "";
            try{
                FileInputStream fis = new FileInputStream(file);   
                StringBuilder sb = new StringBuilder();   
                jxl.Workbook rwb = Workbook.getWorkbook(fis);   
                Sheet[] sheet = rwb.getSheets();   
                for (int i = 0; i < sheet.length; i++) {   
                    Sheet rs = rwb.getSheet(i);   
                    for (int j = 0; j < rs.getRows(); j++) {   
                       Cell[] cells = rs.getRow(j);   
                       for(int k=0;k<cells.length;k++)   
                       sb.append(cells[k].getContents());   
                    }   
                }   
                fis.close();   
                result += sb.toString();
            }catch(Exception e){
                e.printStackTrace();
            }
            return result;
        }
        /**
         * 查找索引,返回符合条件的文件
         * @param text 查找的字符串
         * @return 符合条件的文件List
         */
        public static void searchIndex(String text){
            Date date1 = new Date();
            try{
                directory = FSDirectory.open(new File(INDEX_DIR));
                analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
                DirectoryReader ireader = DirectoryReader.open(directory); //DATA_DIR目录下为空时,这里会报异常并被捕获
                IndexSearcher isearcher = new IndexSearcher(ireader);
        
                QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content", analyzer);
                Query query = parser.parse(text);
                
                ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
            
                for (int i = 0; i < hits.length; i++) {
                    Document hitDoc = isearcher.doc(hits[i].doc);
                    System.out.println("____________________________");
                    System.out.println(hitDoc.get("filename"));
                    System.out.println(hitDoc.get("content"));
                    System.out.println(hitDoc.get("path"));
                    System.out.println("____________________________");
                }
                ireader.close();
                directory.close();
            }catch(Exception e){
                e.printStackTrace();
            }
            Date date2 = new Date();
            System.out.println("查看索引-----耗时:" + (date2.getTime() - date1.getTime()) + "ms
    ");
        }
        /**
         * 过滤目录下的文件
         * @param dirPath 想要获取文件的目录
         * @return 返回文件list
         */
        public static List<File> getFileList(String dirPath) {
            File[] files = new File(dirPath).listFiles();
            List<File> fileList = new ArrayList<File>();
            for (File file : files) {
                if (isTxtFile(file.getName())) {
                    fileList.add(file);
                }
            }
            return fileList;
        }
        /**
         * 判断是否为目标文件,目前支持txt xls doc格式
         * @param fileName 文件名称
         * @return 如果是文件类型满足过滤条件,返回true;否则返回false
         */
        public static boolean isTxtFile(String fileName) {
            if (fileName.lastIndexOf(".txt") > 0) {
                return true;
            }else if (fileName.lastIndexOf(".xls") > 0) {
                return true;
            }else if (fileName.lastIndexOf(".doc") > 0) {
                return true;
            }
            return false;
        }
        
        public static void closeWriter() throws Exception {
            if (indexWriter != null) {
                indexWriter.close();
            }
        }
        /**
         * 删除文件目录下的所有文件
         * @param file 要删除的文件目录
         * @return 如果成功,返回true.
         */
        public static boolean deleteDir(File file){
            if(file.isDirectory()){
                File[] files = file.listFiles();
                for(int i=0; i<files.length; i++){
                    deleteDir(files[i]);
                }
            }
            file.delete();
            return true;
        }
        
        @RequestMapping(params="test")
        @ResponseBody
        public String main(String value){   //value为前端传过来的要查询的字符串
            File fileIndex = new File(INDEX_DIR);
            if(deleteDir(fileIndex)){
                fileIndex.mkdir();
            }else{
                fileIndex.mkdir();
            }
            
            createIndex(DATA_DIR);
            searchIndex(value);
            return "success";
        }
    }

     四:前端

    <body>
         <form id="testform" method="post" action="luceneController.do?test">
            <button id="one">点我开始测试</button>
            <input type="text" name="value"/>
        </form>
      </body>
      <script type="text/javascript">
        $("#one").live("click",function(){
            $("#testform").submit();
        });
      </script>
  • 相关阅读:
    [刘阳Java]_什么是MyBatis_第1讲
    [刘阳Java]_斗胆介绍一下Eclipse快捷键大全[超详细]_第6讲
    [刘阳Java]_避开环境配置快速的使用Java的开发工具_第5讲
    [刘阳Java]_JVM工作流程_第4讲
    [刘阳Java]_Java程序员的成长路线_第3讲
    [刘阳Java]_Java环境搭建_第2讲
    使用node操作mongodb
    mongodb学习
    node多文件处理方法
    yarn工具的使用
  • 原文地址:https://www.cnblogs.com/fdzfd/p/5843024.html
Copyright © 2020-2023  润新知