com.github.cosycode.ext.se.util.FileUtils Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of extend-mod Show documentation

扩展模块, 用于存放一些非常用的工具或模块的扩展类, 例如在poi基础上扩展的excel的导入模块, 模拟按键模块

The newest version!

package com.github.cosycode.ext.se.util;

import lombok.extern.slf4j.Slf4j;

import java.io.*;

/**
 * Description : 
 * 
 * created in  2021/4/30
 *
 * @author CPF
 **/
@Slf4j
public class FileUtils {

    /**
     * 判断文件的编码格式
     *
     * @param fileName :file
     * @return 文件编码格式
     */
    public static String analysisTextFileEncode(File fileName) {
        try (BufferedInputStream bis = new BufferedInputStream(new FileInputStream(fileName))) {
            String charset = "GBK";
            byte[] first3Bytes = new byte[3];
            boolean checked = false;
            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。
            // Wagsn 注：不过暂时使用正常，遂不改之
            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) {
                        break;
                    }
                    if (0xC0 <= read && read <= 0xDF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            // (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;
                        }
                    }
                }
            }
            return charset;
        } catch (IOException e) {
            log.error("", e);
        }
        return "null";
    }

}