仅学习使用
问题:
需要动态获取文件的编码格式
使用第三方库
没有依赖可以去官网下载jar包
来到官网https://sourceforge.net/projects/cpdetector/files/ 官网后下载了一个压缩包,将所有红框中的包放到项目的libs文件夹下
/**
* 获取文件编码字符串
*
* @param file
* @return
*/
public static String getCharsetName(File file) throws IOException {
String charsetName = "UTF-8";
// 获取 CodepageDetectorProxy 实例
CodepageDetectorProxy detector = CodepageDetectorProxy.getInstance();
// 添加解析器,会使用到添加的后 2 个 ext 里的 jar 包
detector.add(new ParsingDetector(false));
detector.add(JChardetFacade.getInstance());
detector.add(ASCIIDetector.getInstance());
detector.add(UnicodeDetector.getInstance());
Charset charset = detector.detectCodepage(file.toURI().toURL());
if (charset != null) charsetName = charset.name();
return charsetName;
}
package com.example.springbootfileuploaddemo.util;
import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.InputStream;
public class FileUtils {
public static String codeString(String fileName) throws Exception {
BufferedInputStream bin = new BufferedInputStream(new FileInputStream(fileName));
int p = (bin.read() << 8) + bin.read();
bin.close();
String code = null;
switch (p) {
case 0xefbb:
code = "UTF-8";
break;
case 0xfffe:
code = "Unicode";
break;
case 0xfeff:
code = "UTF-16BE";
break;
default:
code = "GBK";
}
return code;
}
/**
* 判断文本文件的字符集,文件开头三个字节表明编码格式。
* @param path
* @return
* @throws Exception
* @throws Exception
*/
public static String charset(String path) {
String charset = "GBK";
byte[] first3Bytes = new byte[3];
try {
boolean checked = false;
BufferedInputStream bis = new BufferedInputStream(new FileInputStream(path));
bis.mark(0); // 读者注: bis.mark(0);修改为 bis.mark(100);我用过这段代码,需要修改上面标出的地方。
int read = bis.read(first3Bytes, 0, 3);
if (read == -1) {
bis.close();
return charset; // 文件编码为 ANSI
} else if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
charset = "UTF-16LE"; // 文件编码为 Unicode
checked = true;
} else if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
charset = "UTF-16BE"; // 文件编码为 Unicode big endian
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
charset = "UTF-8"; // 文件编码为 UTF-8
checked = true;
}
bis.reset();
if (!checked) {
while ((read = bis.read()) != -1) {
if (read >= 0xF0)
break;
if (0x80 <= read && read <= 0xBF) // 单独出现BF以下的,也算是GBK
break;
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) // 双字节 (0xC0 - 0xDF)
// (0x80 - 0xBF),也可能在GB编码内
continue;
else
break;
} else if (0xE0 <= read && read <= 0xEF) { // 也有可能出错,但是几率较小
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
charset = "UTF-8";
break;
} else
break;
} else
break;
}
}
}
bis.close();
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("--文件-> [" + path + "] 采用的字符集为: [" + charset + "]");
return charset;
}
public static String getFileCharset(String filePath) throws Exception {
CodepageDetectorProxy detector = CodepageDetectorProxy.getInstance();
/*ParsingDetector可用于检查HTML、XML等文件或字符流的编码,
* 构造方法中的参数用于指示是否显示探测过程的详细信息,为false不显示。
*/
detector.add(new ParsingDetector(false));
/*JChardetFacade封装了由Mozilla组织提供的JChardet,它可以完成大多数文件的编码测定。
* 所以,一般有了这个探测器就可满足大多数项目的要求,如果你还不放心,可以再多加几个探测器,
* 比如下面的ASCIIDetector、UnicodeDetector等。
*/
detector.add(JChardetFacade.getInstance());
detector.add(ASCIIDetector.getInstance());
detector.add(UnicodeDetector.getInstance());
Charset charset = null;
File file = new File(filePath);
try {
//charset = detector.detectCodepage(file.toURI().toURL());
InputStream is = new BufferedInputStream(new FileInputStream(filePath));
charset = detector.detectCodepage(is, 8);
} catch (Exception e) {
e.printStackTrace();
throw e;
}
String charsetName = "GBK";
if (charset != null) {
if (charset.name().equals("US-ASCII")) {
charsetName = "ISO_8859_1";
} else if (charset.name().startsWith("UTF")) {
charsetName = charset.name();// 例如:UTF-8,UTF-16BE.
}
}
return charsetName;
}
}