JAVA 无BOM utf8文件编码判断

最新推荐文章于 2024-08-27 04:25:51 发布

代码鼠

最新推荐文章于 2024-08-27 04:25:51 发布

阅读量3.7k

点赞数 5

分类专栏： JAVA

本文链接：https://blog.csdn.net/srests/article/details/50751481

版权

JAVA 专栏收录该内容

0 篇文章 0 订阅

订阅专栏

/**
	 * @Comments ：获取文件编码格式
	 * @param fileName
	 * @return
	 */
	private static String getCharset(File fileName) {
		BufferedInputStream bin;
		int bom = 0;
		String str = " ";
		String str2 = "";
		try {
			bin = new BufferedInputStream(new FileInputStream(fileName));
			bom = (bin.read() << 8) + bin.read();
			// 获取两个字节内容，如果文件无BOM信息，则通过判断字的字节长度区分编码格式
			byte bs[] = new byte[10];
			while(str.matches("\\s+\\w*")){
				bin.read(bs);
				str = new String(bs, "UTF-8");
			}
			str2 = new String(bs, "GBK");
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}


		String code = null;
		// 有BOM
		switch (bom) {
		case 0xefbb:
			code = "UTF-8";
			break;
		case 0xfffe:
			code = "Unicode";
			break;
		case 0xfeff:
			code = "UTF-16BE";
			break;
		default:
			// 无BOM
			if (str.length() <=str2.length()) {
				code = "UTF-8";
			} else {
				code = "GBK";
			}
		}


		return code;
	}