Lucene实战之基于StandardAnalyzer读写索引

前言

使用lucene创建索引时如果指定了解析器，则需要读写都使用这个解析器，目前我发现也就是在处理中文这块比较麻烦，像你在使用solr时如果配置了ik分词，则需要把index清空重新创建才能继续搜索。

本篇引用lucene-6.4.0和4.x的几个关键类会有不同的地方。

创建索引

  public void index(){

         Directory dir=null;
         Analyzer analyzer=null;
         IndexWriterConfig config=null;
         IndexWriter indexWriter=null;
         try{
             /**
              * SimpleFSDirectory 不能很好支持多线程操作
              * **/
             dir =new SimpleFSDirectory(Paths.get(INDEX_URL));

             analyzer=new StandardAnalyzer();
             config =new IndexWriterConfig(analyzer);
             /**
              * IndexWriter(Directory d,IndexWriterConfig config)
              * **/
             indexWriter =new IndexWriter(dir,config);

             indexWriter.deleteAll();
             List<UploadBook> books =bookDao.listAllBooks();
             Document document=null;

             SimpleDateFormat formatter = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");

             for(UploadBook book:books){
                 document=new Document();
                 document.add(new Field("id",book.getId().toString(), TextField.TYPE_STORED));
                 document.add(new Field("ip",book.getIp(), TextField.TYPE_STORED));
                 document.add(new Field("title",book.getOriginFileName(), TextField.TYPE_STORED));

                 document.add(new Field("content", PdfReader.read(INDEX_PDF+book.getNewFileName()),TextField.TYPE_STORED));
                 document.add(new Field("createtime",formatter.format(book.getCreateTime()), TextField.TYPE_STORED));

                 indexWriter.addDocument(document);
             }

             indexWriter.commit();

             System.out.println("======索引创建完成，公创建"+books.size()+"条索引========");
         }catch (IOException ex){
             ex.printStackTrace();
         }
         catch(Exception ex){
             ex.printStackTrace();
         }finally {
             if(indexWriter !=null){
                 try{
                     indexWriter.close();
                 }catch (IOException ex){
                     System.out.println("======indexWriter close exception========");
                 }
             }
         }

     }

读取索引

  public static List<Book> search2(String kw){
         Directory dir=null;
         Analyzer analyzer=null;
         List<Book> list = new ArrayList<Book>();
         try{
             dir= FSDirectory.open(Paths.get("e:\\soso\\index"));
             analyzer=new StandardAnalyzer();

             DirectoryReader reader =DirectoryReader.open(dir);
             IndexSearcher searcher=new IndexSearcher(reader);

             QueryParser parser=new QueryParser("content",analyzer);
             Query query =parser.parse(kw);

             ScoreDoc[] docs=searcher.search(query,100).scoreDocs;

             for (int i = 0; i < docs.length; i++) {
                 Document firstHit = searcher.doc(docs[i].doc);

                 Book book=new Book();
                 book.setId(Integer.parseInt(firstHit.getField("id").stringValue()));
                 book.setIp(firstHit.getField("ip").stringValue());

                 String title=firstHit.getField("title").stringValue();
                 title=title.substring(0,title.lastIndexOf("."));
                 book.setTitle(title);

                 String content=firstHit.getField("content").stringValue();
                 if(content.length()>=500){
                     content=content.substring(0,500)+"......";
                 }
                 book.setContent(content);

                 SimpleDateFormat format=new SimpleDateFormat("yyyy-MM-mm");
                 Date date =format.parse(firstHit.getField("createtime").stringValue());
                 book.setCreateTime(format.format(date));

                 list.add(book);

             }

         }catch(Exception ex){

         }finally {
             try{
                 dir.close();

             }catch(IOException ex){
                 ex.printStackTrace();
             }
         }

         return list;
     }