lucene依据文件类型自动解析的工厂类

2012-09-16

lucene根据文件类型自动解析的工厂类阅读本章之前请先参考其他几篇解析各类文档的章节http://wuzhaohuixy-

lucene根据文件类型自动解析的工厂类
阅读本章之前请先参考其他几篇解析各类文档的章节
http://wuzhaohuixy-qq-com.iteye.com/blog/780437
http://wuzhaohuixy-qq-com.iteye.com/blog/780431
http://wuzhaohuixy-qq-com.iteye.com/blog/780426
http://wuzhaohuixy-qq-com.iteye.com/blog/780423

这里主要讲解根据文件类型自动解析文档（ppt ， pdf ， txt，doc，html，htm）

用java中的反射机制
先准备属性文件
parser.properties

txt=com.cs.TextParserdoc=com.cs.DocParserrtf=com.cs.DocParserppt=com.cs.PPTParserpdf=com.cs.PdfParserhtml=com.cs.EasyHtmlParserhtm=com.cs.EasyHtmlParser

工厂类ParserFactory

package com.cs;import java.io.File;import java.io.FileInputStream;import java.io.FileNotFoundException;import java.io.IOException;import java.lang.reflect.Constructor;import java.lang.reflect.InvocationTargetException;import java.util.Properties;public class ParserFactory {//该类一加载就把配置文件读到内存static Properties ps ;static{ps = new Properties() ;try {ps.load(new FileInputStream("E:\\EclipseStudyWorkspace\\LuceneParse\\src\\parser.properties")) ;} catch (FileNotFoundException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (IOException e) {// TODO Auto-generated catch blocke.printStackTrace();}}//该方法根据文件的后缀名确定该文件的类型 然后格局配置文件的类型分词建立索引public static Parsable getParser(File file){String ext = file.getAbsolutePath().substring(file.getAbsolutePath().lastIndexOf(".") + 1) ; String className = ps.getProperty(ext) ;Parsable parser = null ;if (className != null){try {//此处不能直接Class.forName().newInstance()//原因:要传参数//所以要先拿到构造器 然后根据构造器区newInstance() 此时就可以传入参数了Class clazz = Class.forName(className) ;//根据参数的不同拿到不同的构造器Constructor constructor = clazz.getConstructor(new Class[]{File.class}) ;//此处传入的参数是Class类型parser = (Parsable)constructor.newInstance(new Object[]{file}) ;} catch (ClassNotFoundException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (SecurityException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (NoSuchMethodException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (IllegalArgumentException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (InstantiationException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (IllegalAccessException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (InvocationTargetException e) {// TODO Auto-generated catch blocke.printStackTrace();}}return parser ;}}

测试类

package com.cs;import java.io.File;public class Test {/** * @param args */public static void main(String[] args) {Parsable parser = null ;parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\搜索引擎－基础.ppt"));//parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\123.pdf"));//parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\www.htm"));//parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\XPDF使用文档.doc"));//parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\文档.txt"));//parser = ParserFactory.getParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\BaseItem.html"));System.out.println(" content : "+parser.getContent()) ;}}

热点排行

软件架构设计

lucene依据文件类型自动解析的工厂类