[文本处理] [已解决]如何能打开文件时自动识别编码处理后保存为ANSI？

function detectEncoding(str) {
  // 检查字符串开头的 BOM
  if (str.charCodeAt(0) === 0xFEFF) {
    return 'UTF-16BE';
  } else if (str.charCodeAt(0) === 0xFFFE) {
    return 'UTF-16LE';
  } else if (str.charCodeAt(0) === 0xEFBB && str.charCodeAt(1) === 0xBF) {
    return 'UTF-8BOM';
  }

  // 检查字符串开头的“UTF-32”标识符
  if (str.charCodeAt(0) === 0x0000 && str.charCodeAt(1) === 0x0000 && str.charCodeAt(2) === 0xFEFF) {
    return 'UTF-32BE';
  } else if (str.charCodeAt(0) === 0xFEFF && str.charCodeAt(1) === 0x0000 && str.charCodeAt(2) === 0x0000) {
    return 'UTF-32LE';
  }

  // 如果未找到上述模式，则假定字符串以 ASCII 或 ANSI 编码
  return 'ANSI/ASCII';
}
复制代码

To determine the character encoding of a string in JavaScript, you can use the .charCodeAt() method to get the numeric Unicode representation of each character in the string and then use some logic to determine the character encoding based on the values that are returned.

For example, to determine if a string is encoded in ANSI, you could use the following approach:

Copy code
function isANSI(str) {
  for (let i = 0; i < str.length; i++) {
    // If any character has a Unicode value greater than 255,
    // the string is not encoded in ANSI
    if (str.charCodeAt(i) > 255) return false;
  }

  // If all characters have a Unicode value less than or equal to 255,
  // the string is encoded in ANSI
  return true;
}
To determine if a string is encoded in UTF-8, you could use the following approach:

Copy code
function isUTF8(str) {
  for (let i = 0; i < str.length; i++) {
    let c = str.charCodeAt(i);

    // If the Unicode value of the character is in the range 0-127,
    // it is encoded as a single byte in UTF-8
    if (c >= 0 && c <= 127) continue;

    // If the Unicode value of the character is in the range 128-2047,
    // it is encoded as two bytes in UTF-8
    if (c >= 128 && c <= 2047) {
      i++;
      continue;
    }

    // If the Unicode value of the character is in the range 2048-65535,
    // it is encoded as three bytes in UTF-8
    if (c >= 2048 && c <= 65535) {
      i += 2;
      continue;
    }

    // If the Unicode value of the character is in the range 65536-1114111,
    // it is encoded as four bytes in UTF-8
    if (c >= 65536 && c <= 1114111) {
      i += 3;
      continue;
    }

    // If the character is not encoded as a single, double, triple, or
    // quadruple byte in UTF-8, the string is not encoded in UTF-8
    return false;
  }

  // If all characters in the string are encoded as a single, double,
  // triple, or quadruple byte in UTF-8, the string is encoded in UTF-8
  return true;
}
To determine if a string is encoded in UTF-8 with a BOM (Byte Order Mark), you could use the following approach:

Copy code
function isUTF8BOM(str) {
  // The BOM for UTF-8 is the byte sequence EF BB BF
  if (str.charCodeAt(0) === 0xEF && str.charCodeAt(1) === 0xBB && str.charCodeAt(2) === 0xBF) {
    // If the first three bytes of the string match the BOM for UTF-8,
    // check if the rest of the string is encoded in UTF-8
    return isUTF8(str.substring(3));
  }

  // If the first three bytes of the string do not match the BOM for UTF-8,
  // the string is not encoded in UTF-8


Try again
复制代码