luceneindexlocaldisk.java

Lucene+nuctch一书的全部源码 测试源码 和几个简单的项目

				document.add(field_path);
				
				Field field_type = new Field("filetype","pdf",   
						Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加类型字段
				document.add(field_type);
				
				RAMWriter.addDocument(document);                           // 添加文档到索引
				RAMWriter.optimize();
				RAMWriter.close();                                         // 索引完毕
				fswriter.addIndexes(new Directory[]{ramdirectory});
				
			  }catch (IOException e) {
				e.printStackTrace();
			}
			System.out.println("----------创建索引：PDF 文件成功. ----------");
	}
	
	private static void  Handledoc (IndexWriter fswriter,File subPath)
	{
		try {
			// 处理分析DOC文档，并索引文档内容
			Directory ramdirectory = new RAMDirectory();
			Analyzer TextAnalyzer = new StandardAnalyzer();            // 生成分析器
			IndexWriter RAMWriter = new IndexWriter(ramdirectory ,TextAnalyzer ,true); // 生成索引器
			
			RAMWriter.setUseCompoundFile(true);                        // 根据指定文件创建输入流

			Document document = new Document() ;                       // 由Office文件生成文档对象
		    FileInputStream in = new FileInputStream(subPath);
		    HWPFDocument doc = new HWPFDocument(in);
		    Range range = doc.getRange();
		    String text = range.text(); 
			Field field_doc = new Field("contents", text, 
					Field.Store.YES,Field.Index.TOKENIZED);
			document.add(field_doc);
			
			Field field_name = new Field("filename", subPath.getName(),   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加名字字段
			document.add(field_name); 
			
			Field field_path = new Field("filepath", subPath.getAbsolutePath(), 
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加路径字段
			document.add(field_path);
			
			Field field_type = new Field("filetype", "doc",   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加类型字段
			document.add(field_type); 
			
			System.out.println("----------创建索引：Office 文件内容  ----------");
			RAMWriter.addDocument(document);                          // 添加文档到索引
			RAMWriter.optimize();
			RAMWriter.close();                                        // 索引完毕
			fswriter.addIndexes(new Directory[]{ramdirectory});

		}catch (IOException e) {
			e.printStackTrace();
		}
		
		System.out.println("----------创建索引：Office 文件成功. ----------");
	}

	private static void  Handlexml(IndexWriter fswriter,File subPath)
	{
		try {		// 处理分析XML文档，并索引文档内容
			Directory ramdirectory = new RAMDirectory();
			Analyzer TextAnalyzer = new StandardAnalyzer();            // 生成分析器
			IndexWriter RAMWriter = new IndexWriter(ramdirectory ,TextAnalyzer ,true); // 生成索引器
			
			RAMWriter.setUseCompoundFile(true);                        // 根据指定文件创建输入流
			
			Document document = new Document() ;                       // 由Office文件生成文档对象
			XMLExtractor extractor = new XMLExtractor();
		    String text = extractor.getXMLContent( subPath.getName() );
			Field field_doc = new Field("contents", text, 
					Field.Store.YES,Field.Index.TOKENIZED);
			document.add(field_doc);
			
			Field field_name = new Field("filename", subPath.getName(),   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加名字字段
			document.add(field_name); 
			
			Field field_path = new Field("filepath", subPath.getAbsolutePath(), 
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加路径字段
			document.add(field_path);
			
			Field field_type = new Field("filetype", "xml",   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加类型字段
			document.add(field_type); 
			
			System.out.println("----------创建索引：XML 文件内容  ----------");
			//System.out.println(document);
			RAMWriter.addDocument(document);                          // 添加文档到索引
			RAMWriter.optimize();
			RAMWriter.close();                                        // 索引完毕
			fswriter.addIndexes(new Directory[]{ramdirectory});

		}catch (IOException e) {
				e.printStackTrace();
		}
		System.out.println("----------创建索引：Office 文件成功. ----------");
	}
	
	private static void  Handlehtml(IndexWriter fswriter,File subPath) throws IOException
	{
		
		System.out.println("handlehtml....");
		try{
			Directory ramdirectory = new RAMDirectory();
			Analyzer TextAnalyzer = new StandardAnalyzer();            // 生成分析器
			IndexWriter RAMWriter = new IndexWriter(ramdirectory ,TextAnalyzer ,true); // 生成索引器
			
			RAMWriter.setUseCompoundFile(true);                        // 根据指定文件创建输入流
			
			Document document = new Document() ;                       // 由Office文件生成文档对象
			
          Parser parser = new Parser();                             // 访问目标网站
          parser.setEncoding("GB2312");                             // 设置解析编码格式

          int len =  (int) subPath.length();
          char[] buffer = new char[len] ;
          FileReader reader = new FileReader(subPath);
          reader.read(buffer);
          
          String inputHTML = new String(buffer);
          
          parser.setInputHTML(inputHTML);
          TextExtractingVisitor visitor = new TextExtractingVisitor (); // 生成文本内容抽取对象 
          
          
          NodeFilter textFilter = new NodeClassFilter(TextNode.class);  // 生成文本过滤器
         // new TagNameFilter("body")
         // NodeList nodes = parser.extractAllNodesThatMatch( new TagNameFilter("body") ); // 利用文本过滤器解析文档
		 NodeList nodes = parser.parse(new TagNameFilter("body")); // here

         String text =nodes.asString().trim();
			if(text.length()<=0){
				text=" ";
			}
			text = text.replace("&nbsp;", "");
			text = text.replace("&gt", "");
			text = text.replace("&lt", "");
			Field field_doc = new Field("contents", text, 
					Field.Store.YES,Field.Index.TOKENIZED);
			document.add(field_doc);
			
	        System.out.println(visitor.getExtractedText());            // 输出网页正文

			Field field_name = new Field("filename", subPath.getName(),   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加名字字段
			document.add(field_name); 
			
			Field field_path = new Field("filepath", subPath.getAbsolutePath(), 
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加路径字段
			document.add(field_path);
			
			Field field_type = new Field("filetype", "html",   
					Field.Store.YES,Field.Index.UN_TOKENIZED);         // 追加类型字段
			document.add(field_type); 
			//System.out.println(text);
			System.out.println("----------创建索引：HTML 文件内容  ----------");
			//System.out.println(document);
			RAMWriter.addDocument(document);                          // 添加文档到索引
			RAMWriter.optimize();
			RAMWriter.close();                                        // 索引完毕
			fswriter.addIndexes(new Directory[]{ramdirectory});
          
		} catch (ParserException e){
			e.printStackTrace();
		}
	}

	/*========================================================
	 * 递归函数，递归分析目录，如果找到子目录，继续递归；如果找到文件分析索引
	 *========================================================*/		
	private static void  SubindexBuilder(IndexWriter fswriter,File subPath)  
		throws IOException{
		
			File[] filelist = subPath.listFiles();
			System.out.println(subPath.getAbsolutePath() + " :子目录个数 " + filelist.length);

			for(int i = 0; i< filelist.length;i++){
				File file = filelist[i];
				if(file.isDirectory()){
					SubindexBuilder(fswriter,file);
				} else if(IsValidType(file.getName())){

					fileindexBuilder(fswriter,file);
				}
			}
		}
}