Java通过InputStream判断word格式

Java通过InputStream判断word格式)

1. 传入inputStream文件流

2. 读取文件流前八个字节到字节流数组中

byte[] byteArray = new byte[8];
inputStream.read(byteArray, 0, 8);

3. 转为字符串

StringBuilder sb = new StringBuilder();
for (byte b : byteArray) {
    sb.append(String.format("%02X", b));
}

4. 对比字符串判断文件类型

if (hexString.startsWith("D0CF11E0A1B11AE1")) {
    return "doc";
} else if (hexString.startsWith("504B030414000600")) {
    return "docx";
} else {
    return "unknown";
}

5. 完整代码

/**
     * 通过流判断word格式
     * @param inputStream
     * @return
     * @throws IOException
     */
    public static String detectFileType(InputStream inputStream) throws IOException {
    byte[] byteArray = new byte[8];
    try{
        inputStream.read(byteArray, 0, 8);
        String hexString = bytesToHexString(byteArray);
        if (hexString.startsWith("D0CF11E0A1B11AE1")) {
            return "doc";
        } else if (hexString.startsWith("504B030414000600")) {
            return "docx";
        } else {
            return "unknown";
        }
    } finally {
        if (inputStream !=null) {
            inputStream.close();
        }
    }
}

private static String bytesToHexString(byte[] byteArray) {
    StringBuilder sb = new StringBuilder();
    for (byte b : byteArray) {
        sb.append(String.format("%02X", b));
    }
    return sb.toString();
}