Java FileWriter中文乱码
原文:http://www.malcolmhardie.com/weblogs/angus/2004/10/23/java-filewriter-xml-and-utf-8/
Java FileWriter 默认是用(ISO-8859-1 or US-ASCII)西方编码的,总之不是UTF-8的,而FileWriter类有getEncoding方法,却没有setEncoding的方法,如下的写法可以使正确输出UTF-8的文件:
OutputStreamWriter out = new OutputStreamWriter(new FileOutputStream(path),"UTF-8");
或者
Writer out = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(this.outputFilename),”UTF-8″));
--------------------------------------------------
最近在做HTML静态生成,需要从硬盘上把模版文件的内容读出来。然后,替换相关标签写到指定的文件中。无论是读写,都遇到了中文乱码问题。试过多种方法,发现下面一种可以避免中文乱码。(无论读取还是写入一定要进行编码转换。)
1、JAVA读取文件,避免中文乱码。
/**
* 读取文件内容
*
* @param filePathAndName
* String 如 c:\\1.txt 绝对路径
* @return boolean
*/
public static String readFile(String filePathAndName) {
String fileContent = "";
try {
File f = new File(filePathAndName);
if(f.isFile()&&f.exists()){
InputStreamReader read = new InputStreamReader(new FileInputStream(f),"UTF-8");
BufferedReader reader=new BufferedReader(read);
String line;
while ((line = reader.readLine()) != null) {
fileContent += line;
}
read.close();
}
} catch (Exception e) {
System.out.println("读取文件内容操作出错");
e.printStackTrace();
}
return fileContent;
}
2、JAVA写入文件,避免中文乱码。
public static void writeFile(String filePathAndName, String fileContent) {
try {
File f = new File(filePathAndName);
if (!f.exists()) {
f.createNewFile();
}
OutputStreamWriter write = new OutputStreamWriter(new FileOutputStream(f),"UTF-8");
BufferedWriter writer=new BufferedWriter(write);
//PrintWriter writer = new PrintWriter(new BufferedWriter(new FileWriter(filePathAndName)));
//PrintWriter writer = new PrintWriter(new FileWriter(filePathAndName));
writer.write(fileContent);
writer.close();
} catch (Exception e) {
System.out.println("写文件内容操作出错");
e.printStackTrace();
}
}
我试过写入的时候用
1、PrintWriter writer = new PrintWriter(new BufferedWriter(new FileWriter(filePathAndName)));
2、PrintWriter writer = new PrintWriter(new FileWriter(filePathAndName));
都不行。
以上代码经过运行可以避免中文乱码,关键是要编码转换。
---------------------------------------------------------------------------------
book.xml
Java就业基础教程书名>
张孝祥作者>
48元售价>
58元售价>
书>
JavaScript网页开发书名>
黎活明作者>
46元售价>
书>
书架>
Dom4j.java
package yyy.dom4j;
import java.io.File;
import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.util.List;
import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
import org.junit.Test;
public class Dom4j {
private File file = new File("src/book.xml");
//遍历xml文档
@Test
public void testList() throws Exception{
SAXReader reader = new SAXReader();
Document document = reader.read(file);
Element root = document.getRootElement();
list(root);
}
public void list(Element element){
System.out.println(element.getName());
List nodes = element.elements();
//System.out.println(nodes.size());
for(Node node : nodes){
if(node instanceof Element){
list((Element) node);
}
}
}
//读取某个节点的值
@Test
public void read() throws Exception{
SAXReader reader = new SAXReader();
Document document = reader.read(file);
Element root = document.getRootElement();
Element price = root.element("书").element("作者");
String value = price.getText();
System.out.println(value);
}
//添加某个节点
@Test
public void add() throws Exception{
SAXReader reader = new SAXReader();
Document document = reader.read(file);
Element price = DocumentHelper.createElement("售价"); //创建新的节点
price.setText("44元"); //设置节点值
Element root = document.getRootElement();
root.element("书").add(price); //添加节点
//将内存中的document对象重新写入xml文档 特别要注意乱码问题
//方法1:使用OutputStreamWriter设置写入文档时所使用的编码表 OutputStreamWriter out = new OutputStreamWriter(new FileOutputStream(file),"utf-8"); document.write(out); out.close(); /*//方法2: OutputFormat format = OutputFormat.createPrettyPrint(); format.setEncoding("gb2312"); XMLWriter writer = new XMLWriter(new FileWriter(file),format); writer.write(document); writer.close();*/ /*//方法3: OutputFormat format = OutputFormat.createPrettyPrint(); XMLWriter writer = new XMLWriter(new OutputStreamWriter(new FileOutputStream(file),"utf-8"),format); writer.write(document); writer.close();*/ /*//方法4: OutputFormat format = OutputFormat.createPrettyPrint(); format.setEncoding("gb2312"); //源文档用"gb2312"编码,既不改变源文档的编码格式,又不能有乱码 XMLWriter writer = new XMLWriter(new FileOutputStream(file),format); writer.write(document); writer.close();*/ /*//document对象在内存中是以"UTF-8"编码形式存在,用FileWriter将document对象以字符流的形式写入xml文档默认是用本地码表"gb2312"编码 * 乱码问题总结: * 1.用字符流向文件写入数据要考虑乱码问题,而用字节流就不必考虑乱码问题 * 用字符流向文件写入数据默认使用本地码表即"gb2312" * 2.任何对象读入内存都是以"UTF-8"编码的形式存在 * 默认情况下XMLWriter的write方法是以"UTF-8"的编码形式将内存中的document对象传给FileWriter,所以要想不发生乱码问题, * 就要使用包装流OutputStreamWriter并给定写入文件时所使用的编码表,或者使用OutputFormat的setEncoding方法指定传给 * 流对象时所使用的编码格式。 * */ } //向指定位置添加节点 @Test public void add2() throws Exception{ SAXReader reader = new SAXReader(); Document document = reader.read(file); Element root = document.getRootElement(); Element price = DocumentHelper.createElement("售价"); price.setText("48元"); List list = root.element("书").elements(); list.add(2,price); OutputFormat format = OutputFormat.createPrettyPrint(); XMLWriter writer = new XMLWriter(new FileOutputStream(file),format); writer.write(document); writer.close(); } //删除某个节点 @Test public void delete() throws Exception{ SAXReader reader = new SAXReader(); Document document = reader.read(file); Element root = document.getRootElement(); Element price = root.element("书").element("售价"); price.getParent().remove(price); OutputFormat format = OutputFormat.createPrettyPrint(); XMLWriter writer = new XMLWriter(new FileOutputStream(file),format); writer.write(document); writer.close(); } //更改某个节点的内容 @Test public void update() throws Exception{ SAXReader reader = new SAXReader(); Document document = reader.read(file); Element root = document.getRootElement(); Element price = root.element("书").element("售价"); price.setText("58元"); OutputFormat format = OutputFormat.createPrettyPrint(); XMLWriter writer = new XMLWriter(new FileOutputStream(file),format); writer.write(document); writer.close(); } }