转:java读文件时判断其编码格式(亲测可用),java编码格式
分享于 点击 19137 次 点评:54
转:java读文件时判断其编码格式(亲测可用),java编码格式
最近java读取文件的时候,经常碰到中文乱码,特研究了一下java 的编码格式,在java 中java | txt |
unicode | unicode big endian |
utf-8 | utf-8 |
utf-16 | unicode |
gb2312 | ANSI |
private static String getFilecharset(File sourceFile) { String charset = "GBK"; byte[] first3Bytes = new byte[3]; try { boolean checked = false; BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile)); bis.mark(0); int read = bis.read(first3Bytes, 0, 3); if (read == -1) { 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) { int loc = 0; while ((read = bis.read()) != -1) { loc++; 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(); } return charset; }
相关文章
- 暂无相关文章
用户点评