atob.js 3.63 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107
"use strict";

/**
 * Implementation of atob() according to the HTML and Infra specs, except that
 * instead of throwing INVALID_CHARACTER_ERR we return null.
 */
function atob(data) {
  // Web IDL requires DOMStrings to just be converted using ECMAScript
  // ToString, which in our case amounts to using a template literal.
  data = `${data}`;
  // "Remove all ASCII whitespace from data."
  data = data.replace(/[ \t\n\f\r]/g, "");
  // "If data's length divides by 4 leaving no remainder, then: if data ends
  // with one or two U+003D (=) code points, then remove them from data."
  if (data.length % 4 === 0) {
    data = data.replace(/==?$/, "");
  }
  // "If data's length divides by 4 leaving a remainder of 1, then return
  // failure."
  //
  // "If data contains a code point that is not one of
  //
  // U+002B (+)
  // U+002F (/)
  // ASCII alphanumeric
  //
  // then return failure."
  if (data.length % 4 === 1 || /[^+/0-9A-Za-z]/.test(data)) {
    return null;
  }
  // "Let output be an empty byte sequence."
  let output = "";
  // "Let buffer be an empty buffer that can have bits appended to it."
  //
  // We append bits via left-shift and or.  accumulatedBits is used to track
  // when we've gotten to 24 bits.
  let buffer = 0;
  let accumulatedBits = 0;
  // "Let position be a position variable for data, initially pointing at the
  // start of data."
  //
  // "While position does not point past the end of data:"
  for (let i = 0; i < data.length; i++) {
    // "Find the code point pointed to by position in the second column of
    // Table 1: The Base 64 Alphabet of RFC 4648. Let n be the number given in
    // the first cell of the same row.
    //
    // "Append to buffer the six bits corresponding to n, most significant bit
    // first."
    //
    // atobLookup() implements the table from RFC 4648.
    buffer <<= 6;
    buffer |= atobLookup(data[i]);
    accumulatedBits += 6;
    // "If buffer has accumulated 24 bits, interpret them as three 8-bit
    // big-endian numbers. Append three bytes with values equal to those
    // numbers to output, in the same order, and then empty buffer."
    if (accumulatedBits === 24) {
      output += String.fromCharCode((buffer & 0xff0000) >> 16);
      output += String.fromCharCode((buffer & 0xff00) >> 8);
      output += String.fromCharCode(buffer & 0xff);
      buffer = accumulatedBits = 0;
    }
    // "Advance position by 1."
  }
  // "If buffer is not empty, it contains either 12 or 18 bits. If it contains
  // 12 bits, then discard the last four and interpret the remaining eight as
  // an 8-bit big-endian number. If it contains 18 bits, then discard the last
  // two and interpret the remaining 16 as two 8-bit big-endian numbers. Append
  // the one or two bytes with values equal to those one or two numbers to
  // output, in the same order."
  if (accumulatedBits === 12) {
    buffer >>= 4;
    output += String.fromCharCode(buffer);
  } else if (accumulatedBits === 18) {
    buffer >>= 2;
    output += String.fromCharCode((buffer & 0xff00) >> 8);
    output += String.fromCharCode(buffer & 0xff);
  }
  // "Return output."
  return output;
}
/**
 * A lookup table for atob(), which converts an ASCII character to the
 * corresponding six-bit number.
 */
function atobLookup(chr) {
  if (/[A-Z]/.test(chr)) {
    return chr.charCodeAt(0) - "A".charCodeAt(0);
  }
  if (/[a-z]/.test(chr)) {
    return chr.charCodeAt(0) - "a".charCodeAt(0) + 26;
  }
  if (/[0-9]/.test(chr)) {
    return chr.charCodeAt(0) - "0".charCodeAt(0) + 52;
  }
  if (chr === "+") {
    return 62;
  }
  if (chr === "/") {
    return 63;
  }
  // Throw exception; should not be hit in tests
  return undefined;
}

module.exports = atob;