一般文本文件

我们以日志文件.log文件为例：

import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.FileReader; import java.io.IOException; public class File_Test { /** * @param args */ public static void main(String[] args) { File file = new File("D:logserrorMsg.log"); if(file.exists()){ System.out.println("此文件存在"); } else { System.out.println("此文件不存在"); } try { FileReader fr = new FileReader(file); BufferedReader br = new BufferedReader(fr); String s; while((s=br.readLine())!=null){ System.out.println(s); } System.out.println("文件大小为（MB）："+new FileInputStream(file).available() / 1024 / 1024 +"M"); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } }

.doc文件

这里我们使用WordExtractor读取Word文档，WordExtractor来自于Apache的poi类库项目，官方下载地址：https://poi.apache.org/download.html

import java.io.FileInputStream; import org.textmining.text.extraction.WordExtractor; public class WordTest { public static void main(String args[]) throws Exception { new WordTest().readByOther(); } public void readByText() throws Exception { FileInputStream in = new FileInputStream("C://test.doc "); WordExtractor extractor = new WordExtractor(); String str = extractor.extractText(in); System.out.println(str); } }