StringView

The aims of this library are:

to create a C-like interface for strings (i.e., an array of character codes — an ArrayBufferView in JavaScript) based upon the JavaScript ArrayBuffer interface
to create a highly extensible library that anyone can extend by adding methods to the object StringView.prototype
to create a collection of methods for such string-like objects (since now: stringViews) which work strictly on arrays of numbers rather than on creating new immutable JavaScript strings
to work with Unicode encodings other than JavaScript's default UTF-16 DOMStrings

Introduction

As web applications become more and more powerful, adding features such as audio and video manipulation, access to raw data using WebSockets, and so forth, it has become clear that there are times when it would be helpful for JavaScript code to be able to quickly and easily manipulate raw binary data. In the past, this had to be simulated by treating the raw data as a string and using the charCodeAt() method to read the bytes from the data buffer.

However, this is slow and error-prone, due to the need for multiple conversions (especially if the binary data is not actually byte-format data, but, for example, 32-bit integers or floats).

JavaScript typed arrays provide a mechanism for accessing raw binary data much more efficiently. The StringView constructor is one level above typed arrays.

The code

stringview.js

"use strict";

/*\
|*|
|*|  :: Number.isInteger() polyfill ::
|*|
|*|  https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Number/isInteger
|*|
\*/

if (!Number.isInteger) {
  Number.isInteger = function isInteger (nVal) {
    return typeof nVal === "number" && isFinite(nVal) && nVal > -9007199254740992 && nVal < 9007199254740992 && Math.floor(nVal) === nVal;
  };
}

/*\
|*|
|*|  StringView - Mozilla Developer Network
|*|
|*|  Revision #8, October 6, 2014
|*|
|*|  https://developer.mozilla.org/en-US/docs/Web/JavaScript/Typed_arrays/StringView
|*|  https://developer.mozilla.org/en-US/docs/User:fusionchess
|*|
|*|  This framework is released under the GNU Lesser General Public License, version 3 or later.
|*|  https://www.gnu.org/licenses/lgpl-3.0.html
|*|
\*/

function StringView (vInput, sEncoding /* optional (default: UTF-8) */, nOffset /* optional */, nLength /* optional */) {

  var fTAView, aWhole, aRaw, fPutOutptCode, fGetOutptChrSize, nInptLen, nStartIdx = isFinite(nOffset) ? nOffset : 0, nTranscrType = 15;

  if (sEncoding) { this.encoding = sEncoding.toString(); }

  encSwitch: switch (this.encoding) {
    case "UTF-8":
      fPutOutptCode = StringView.putUTF8CharCode;
      fGetOutptChrSize = StringView.getUTF8CharLength;
      fTAView = Uint8Array;
      break encSwitch;
    case "UTF-16":
      fPutOutptCode = StringView.putUTF16CharCode;
      fGetOutptChrSize = StringView.getUTF16CharLength;
      fTAView = Uint16Array;
      break encSwitch;
    case "UTF-32":
      fTAView = Uint32Array;
      nTranscrType &= 14;
      break encSwitch;
    default:
      /* case "ASCII", or case "BinaryString" or unknown cases */
      fTAView = Uint8Array;
      nTranscrType &= 14;
  }

  typeSwitch: switch (typeof vInput) {
    case "string":
      /* the input argument is a primitive string: a new buffer will be created. */
      nTranscrType &= 7;
      break typeSwitch;
    case "object":
      classSwitch: switch (vInput.constructor) {
        case StringView:
          /* the input argument is a stringView: a new buffer will be created. */
          nTranscrType &= 3;
          break typeSwitch;
        case String:
          /* the input argument is an objectified string: a new buffer will be created. */
          nTranscrType &= 7;
          break typeSwitch;
        case ArrayBuffer:
          /* the input argument is an arrayBuffer: the buffer will be shared. */
          aWhole = new fTAView(vInput);
          nInptLen = this.encoding === "UTF-32" ?
              vInput.byteLength >>> 2
            : this.encoding === "UTF-16" ?
              vInput.byteLength >>> 1
            :
              vInput.byteLength;
          aRaw = nStartIdx === 0 && (!isFinite(nLength) || nLength === nInptLen) ?
            aWhole
            : new fTAView(vInput, nStartIdx, !isFinite(nLength) ? nInptLen - nStartIdx : nLength);

          break typeSwitch;
        case Uint32Array:
        case Uint16Array:
        case Uint8Array:
          /* the input argument is a typedArray: the buffer, and possibly the array itself, will be shared. */
          fTAView = vInput.constructor;
          nInptLen = vInput.length;
          aWhole = vInput.byteOffset === 0 && vInput.length === (
            fTAView === Uint32Array ?
              vInput.buffer.byteLength >>> 2
            : fTAView === Uint16Array ?
              vInput.buffer.byteLength >>> 1
            :
              vInput.buffer.byteLength
          ) ? vInput : new fTAView(vInput.buffer);
          aRaw = nStartIdx === 0 && (!isFinite(nLength) || nLength === nInptLen) ?
            vInput
            : vInput.subarray(nStartIdx, isFinite(nLength) ? nStartIdx + nLength : nInptLen);

          break typeSwitch;
        default:
          /* the input argument is an array or another serializable object: a new typedArray will be created. */
          aWhole = new fTAView(vInput);
          nInptLen = aWhole.length;
          aRaw = nStartIdx === 0 && (!isFinite(nLength) || nLength === nInptLen) ?
            aWhole
            : aWhole.subarray(nStartIdx, isFinite(nLength) ? nStartIdx + nLength : nInptLen);
      }
      break typeSwitch;
    default:
      /* the input argument is a number, a boolean or a function: a new typedArray will be created. */
      aWhole = aRaw = new fTAView(Number(vInput) || 0);

  }

  if (nTranscrType < 8) {

    var vSource, nOutptLen, nCharStart, nCharEnd, nEndIdx, fGetInptChrSize, fGetInptChrCode;

    if (nTranscrType & 4) { /* input is string */

      vSource = vInput;
      nOutptLen = nInptLen = vSource.length;
      nTranscrType ^= this.encoding === "UTF-32" ? 0 : 2;
      /* ...or...: nTranscrType ^= Number(this.encoding !== "UTF-32") << 1; */
      nStartIdx = nCharStart = nOffset ? Math.max((nOutptLen + nOffset) % nOutptLen, 0) : 0;
      nEndIdx = nCharEnd = (Number.isInteger(nLength) ? Math.min(Math.max(nLength, 0) + nStartIdx, nOutptLen) : nOutptLen) - 1;

    } else { /* input is stringView */

      vSource = vInput.rawData;
      nInptLen = vInput.makeIndex();
      nStartIdx = nCharStart = nOffset ? Math.max((nInptLen + nOffset) % nInptLen, 0) : 0;
      nOutptLen = Number.isInteger(nLength) ? Math.min(Math.max(nLength, 0), nInptLen - nCharStart) : nInptLen;
      nEndIdx = nCharEnd = nOutptLen + nCharStart;

      if (vInput.encoding === "UTF-8") {
        fGetInptChrSize = StringView.getUTF8CharLength;
        fGetInptChrCode = StringView.loadUTF8CharCode;
      } else if (vInput.encoding === "UTF-16") {
        fGetInptChrSize = StringView.getUTF16CharLength;
        fGetInptChrCode = StringView.loadUTF16CharCode;
      } else {
        nTranscrType &= 1;
      }

    }

    if (nOutptLen === 0 || nTranscrType < 4 && vSource.encoding === this.encoding && nCharStart === 0 && nOutptLen === nInptLen) {

      /* the encoding is the same, the length too and the offset is 0... or the input is empty! */

      nTranscrType = 7;

    }

    conversionSwitch: switch (nTranscrType) {

      case 0:

      /* both the source and the new StringView have a fixed-length encoding... */

        aWhole = new fTAView(nOutptLen);
        for (var nOutptIdx = 0; nOutptIdx < nOutptLen; aWhole[nOutptIdx] = vSource[nStartIdx + nOutptIdx++]);
        break conversionSwitch;

      case 1:

      /* the source has a fixed-length encoding but the new StringView has a variable-length encoding... */

        /* mapping... */

        nOutptLen = 0;

        for (var nInptIdx = nStartIdx; nInptIdx < nEndIdx; nInptIdx++) {
          nOutptLen += fGetOutptChrSize(vSource[nInptIdx]);
        }

        aWhole = new fTAView(nOutptLen);

        /* transcription of the source... */

        for (var nInptIdx = nStartIdx, nOutptIdx = 0; nOutptIdx < nOutptLen; nInptIdx++) {
          nOutptIdx = fPutOutptCode(aWhole, vSource[nInptIdx], nOutptIdx);
        }

        break conversionSwitch;

      case 2:

      /* the source has a variable-length encoding but the new StringView has a fixed-length encoding... */

        /* mapping... */

        nStartIdx = 0;

        var nChrCode;

        for (nChrIdx = 0; nChrIdx < nCharStart; nChrIdx++) {
          nChrCode = fGetInptChrCode(vSource, nStartIdx);
          nStartIdx += fGetInptChrSize(nChrCode);
        }

        aWhole = new fTAView(nOutptLen);

        /* transcription of the source... */

        for (var nInptIdx = nStartIdx, nOutptIdx = 0; nOutptIdx < nOutptLen; nInptIdx += fGetInptChrSize(nChrCode), nOutptIdx++) {
          nChrCode = fGetInptChrCode(vSource, nInptIdx);
          aWhole[nOutptIdx] = nChrCode;
        }

        break conversionSwitch;

      case 3:

      /* both the source and the new StringView have a variable-length encoding... */

        /* mapping... */

        nOutptLen = 0;

        var nChrCode;

        for (var nChrIdx = 0, nInptIdx = 0; nChrIdx < nCharEnd; nInptIdx += fGetInptChrSize(nChrCode)) {
          nChrCode = fGetInptChrCode(vSource, nInptIdx);
          if (nChrIdx === nCharStart) { nStartIdx = nInptIdx; }
          if (++nChrIdx > nCharStart) { nOutptLen += fGetOutptChrSize(nChrCode); }
        }

        aWhole = new fTAView(nOutptLen);

        /* transcription... */

        for (var nInptIdx = nStartIdx, nOutptIdx = 0; nOutptIdx < nOutptLen; nInptIdx += fGetInptChrSize(nChrCode)) {
          nChrCode = fGetInptChrCode(vSource, nInptIdx);
          nOutptIdx = fPutOutptCode(aWhole, nChrCode, nOutptIdx);
        }

        break conversionSwitch;

      case 4:

      /* DOMString to ASCII or BinaryString or other unknown encodings */

        aWhole = new fTAView(nOutptLen);

        /* transcription... */

        for (var nIdx = 0; nIdx < nOutptLen; nIdx++) {
          aWhole[nIdx] = vSource.charCodeAt(nIdx) & 0xff;
        }

        break conversionSwitch;

      case 5:

      /* DOMString to UTF-8 or to UTF-16 */

        /* mapping... */

        nOutptLen = 0;

        for (var nMapIdx = 0; nMapIdx < nInptLen; nMapIdx++) {
          if (nMapIdx === nCharStart) { nStartIdx = nOutptLen; }
          nOutptLen += fGetOutptChrSize(vSource.charCodeAt(nMapIdx));
          if (nMapIdx === nCharEnd) { nEndIdx = nOutptLen; }
        }

        aWhole = new fTAView(nOutptLen);

        /* transcription... */

        for (var nOutptIdx = 0, nChrIdx = 0; nOutptIdx < nOutptLen; nChrIdx++) {
          nOutptIdx = fPutOutptCode(aWhole, vSource.charCodeAt(nChrIdx), nOutptIdx);
        }

        break conversionSwitch;

      case 6:

      /* DOMString to UTF-32 */

        aWhole = new fTAView(nOutptLen);

        /* transcription... */

        for (var nIdx = 0; nIdx < nOutptLen; nIdx++) {
          aWhole[nIdx] = vSource.charCodeAt(nIdx);
        }

        break conversionSwitch;

      case 7:

        aWhole = new fTAView(nOutptLen ? vSource : 0);
        break conversionSwitch;

    }

    aRaw = nTranscrType > 3 && (nStartIdx > 0 || nEndIdx < aWhole.length - 1) ? aWhole.subarray(nStartIdx, nEndIdx) : aWhole;

  }

  this.buffer = aWhole.buffer;
  this.bufferView = aWhole;
  this.rawData = aRaw;

  Object.freeze(this);

}

/* CONSTRUCTOR'S METHODS */

StringView.loadUTF8CharCode = function (aChars, nIdx) {

  var nLen = aChars.length, nPart = aChars[nIdx];

  return nPart > 251 && nPart < 254 && nIdx + 5 < nLen ?
      /* (nPart - 252 << 30) may be not safe in ECMAScript! So...: */
      /* six bytes */ (nPart - 252) * 1073741824 + (aChars[nIdx + 1] - 128 << 24) + (aChars[nIdx + 2] - 128 << 18) + (aChars[nIdx + 3] - 128 << 12) + (aChars[nIdx + 4] - 128 << 6) + aChars[nIdx + 5] - 128
    : nPart > 247 && nPart < 252 && nIdx + 4 < nLen ?
      /* five bytes */ (nPart - 248 << 24) + (aChars[nIdx + 1] - 128 << 18) + (aChars[nIdx + 2] - 128 << 12) + (aChars[nIdx + 3] - 128 << 6) + aChars[nIdx + 4] - 128
    : nPart > 239 && nPart < 248 && nIdx + 3 < nLen ?
      /* four bytes */(nPart - 240 << 18) + (aChars[nIdx + 1] - 128 << 12) + (aChars[nIdx + 2] - 128 << 6) + aChars[nIdx + 3] - 128
    : nPart > 223 && nPart < 240 && nIdx + 2 < nLen ?
      /* three bytes */ (nPart - 224 << 12) + (aChars[nIdx + 1] - 128 << 6) + aChars[nIdx + 2] - 128
    : nPart > 191 && nPart < 224 && nIdx + 1 < nLen ?
      /* two bytes */ (nPart - 192 << 6) + aChars[nIdx + 1] - 128
    :
      /* one byte */ nPart;

};

StringView.putUTF8CharCode = function (aTarget, nChar, nPutAt) {

  var nIdx = nPutAt;

  if (nChar < 0x80 /* 128 */) {
    /* one byte */
    aTarget[nIdx++] = nChar;
  } else if (nChar < 0x800 /* 2048 */) {
    /* two bytes */
    aTarget[nIdx++] = 0xc0 /* 192 */ + (nChar >>> 6);
    aTarget[nIdx++] = 0x80 /* 128 */ + (nChar & 0x3f /* 63 */);
  } else if (nChar < 0x10000 /* 65536 */) {
    /* three bytes */
    aTarget[nIdx++] = 0xe0 /* 224 */ + (nChar >>> 12);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 6) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + (nChar & 0x3f /* 63 */);
  } else if (nChar < 0x200000 /* 2097152 */) {
    /* four bytes */
    aTarget[nIdx++] = 0xf0 /* 240 */ + (nChar >>> 18);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 12) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 6) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + (nChar & 0x3f /* 63 */);
  } else if (nChar < 0x4000000 /* 67108864 */) {
    /* five bytes */
    aTarget[nIdx++] = 0xf8 /* 248 */ + (nChar >>> 24);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 18) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 12) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 6) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + (nChar & 0x3f /* 63 */);
  } else /* if (nChar <= 0x7fffffff) */ { /* 2147483647 */
    /* six bytes */
    aTarget[nIdx++] = 0xfc /* 252 */ + /* (nChar >>> 30) may be not safe in ECMAScript! So...: */ (nChar / 1073741824);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 24) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 18) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 12) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + ((nChar >>> 6) & 0x3f /* 63 */);
    aTarget[nIdx++] = 0x80 /* 128 */ + (nChar & 0x3f /* 63 */);
  }

  return nIdx;

};

StringView.getUTF8CharLength = function (nChar) {
  return nChar < 0x80 ? 1 : nChar < 0x800 ? 2 : nChar < 0x10000 ? 3 : nChar < 0x200000 ? 4 : nChar < 0x4000000 ? 5 : 6;
};

StringView.loadUTF16CharCode = function (aChars, nIdx) {

  /* UTF-16 to DOMString decoding algorithm */
  var nFrstChr = aChars[nIdx];

  return nFrstChr > 0xD7BF /* 55231 */ && nIdx + 1 < aChars.length ?
    (nFrstChr - 0xD800 /* 55296 */ << 10) + aChars[nIdx + 1] + 0x2400 /* 9216 */
    : nFrstChr;

};

StringView.putUTF16CharCode = function (aTarget, nChar, nPutAt) {

  var nIdx = nPutAt;

  if (nChar < 0x10000 /* 65536 */) {
    /* one element */
    aTarget[nIdx++] = nChar;
  } else {
    /* two elements */
    aTarget[nIdx++] = 0xD7C0 /* 55232 */ + (nChar >>> 10);
    aTarget[nIdx++] = 0xDC00 /* 56320 */ + (nChar & 0x3FF /* 1023 */);
  }

  return nIdx;

};

StringView.getUTF16CharLength = function (nChar) {
  return nChar < 0x10000 ? 1 : 2;
};

/* Array of bytes to base64 string decoding */

StringView.b64ToUint6 = function (nChr) {

  return nChr > 64 && nChr < 91 ?
      nChr - 65
    : nChr > 96 && nChr < 123 ?
      nChr - 71
    : nChr > 47 && nChr < 58 ?
      nChr + 4
    : nChr === 43 ?
      62
    : nChr === 47 ?
      63
    :
      0;

};

StringView.uint6ToB64 = function (nUint6) {

  return nUint6 < 26 ?
      nUint6 + 65
    : nUint6 < 52 ?
      nUint6 + 71
    : nUint6 < 62 ?
      nUint6 - 4
    : nUint6 === 62 ?
      43
    : nUint6 === 63 ?
      47
    :
      65;

};

/* Base64 string to array encoding */

StringView.bytesToBase64 = function (aBytes) {

  var sB64Enc = "";

  for (var nMod3, nLen = aBytes.length, nUint24 = 0, nIdx = 0; nIdx < nLen; nIdx++) {
    nMod3 = nIdx % 3;
    /* Uncomment the following line in order to split the output in lines 76-character long: */
    /*
    if (nIdx > 0 && (nIdx * 4 / 3) % 76 === 0) { sB64Enc += "\r\n"; }
    */
    nUint24 |= aBytes[nIdx] << (16 >>> nMod3 & 24);
    if (nMod3 === 2 || aBytes.length - nIdx === 1) {
      sB64Enc += String.fromCharCode(StringView.uint6ToB64(nUint24 >>> 18 & 63), StringView.uint6ToB64(nUint24 >>> 12 & 63), StringView.uint6ToB64(nUint24 >>> 6 & 63), StringView.uint6ToB64(nUint24 & 63));
      nUint24 = 0;
    }
  }

  return sB64Enc.replace(/A(?=A$|$)/g, "=");

};


StringView.base64ToBytes = function (sBase64, nBlockBytes) {

  var
    sB64Enc = sBase64.replace(/[^A-Za-z0-9\+\/]/g, ""), nInLen = sB64Enc.length,
    nOutLen = nBlockBytes ? Math.ceil((nInLen * 3 + 1 >>> 2) / nBlockBytes) * nBlockBytes : nInLen * 3 + 1 >>> 2, aBytes = new Uint8Array(nOutLen);

  for (var nMod3, nMod4, nUint24 = 0, nOutIdx = 0, nInIdx = 0; nInIdx < nInLen; nInIdx++) {
    nMod4 = nInIdx & 3;
    nUint24 |= StringView.b64ToUint6(sB64Enc.charCodeAt(nInIdx)) << 18 - 6 * nMod4;
    if (nMod4 === 3 || nInLen - nInIdx === 1) {
      for (nMod3 = 0; nMod3 < 3 && nOutIdx < nOutLen; nMod3++, nOutIdx++) {
        aBytes[nOutIdx] = nUint24 >>> (16 >>> nMod3 & 24) & 255;
      }
      nUint24 = 0;
    }
  }

  return aBytes;

};

StringView.makeFromBase64 = function (sB64Inpt, sEncoding, nByteOffset, nLength) {

  return new StringView(sEncoding === "UTF-16" || sEncoding === "UTF-32" ? StringView.base64ToBytes(sB64Inpt, sEncoding === "UTF-16" ? 2 : 4).buffer : StringView.base64ToBytes(sB64Inpt), sEncoding, nByteOffset, nLength);

};

/* DEFAULT VALUES */

StringView.prototype.encoding = "UTF-8"; /* Default encoding... */

/* INSTANCES' METHODS */

StringView.prototype.makeIndex = function (nChrLength, nStartFrom) {

  var

    aTarget = this.rawData, nChrEnd, nRawLength = aTarget.length,
    nStartIdx = nStartFrom || 0, nIdxEnd = nStartIdx, nStopAtChr = isNaN(nChrLength) ? Infinity : nChrLength;

  if (nChrLength + 1 > aTarget.length) { throw new RangeError("StringView.prototype.makeIndex - The offset can\'t be major than the length of the array - 1."); }

  switch (this.encoding) {

    case "UTF-8":

      var nPart;

      for (nChrEnd = 0; nIdxEnd < nRawLength && nChrEnd < nStopAtChr; nChrEnd++) {
        nPart = aTarget[nIdxEnd];
        nIdxEnd += nPart > 251 && nPart < 254 && nIdxEnd + 5 < nRawLength ? 6
          : nPart > 247 && nPart < 252 && nIdxEnd + 4 < nRawLength ? 5
          : nPart > 239 && nPart < 248 && nIdxEnd + 3 < nRawLength ? 4
          : nPart > 223 && nPart < 240 && nIdxEnd + 2 < nRawLength ? 3
          : nPart > 191 && nPart < 224 && nIdxEnd + 1 < nRawLength ? 2
          : 1;
      }

      break;

    case "UTF-16":

      for (nChrEnd = nStartIdx; nIdxEnd < nRawLength && nChrEnd < nStopAtChr; nChrEnd++) {
        nIdxEnd += aTarget[nIdxEnd] > 0xD7BF /* 55231 */ && nIdxEnd + 1 < aTarget.length ? 2 : 1;
      }

      break;

    default:

      nIdxEnd = nChrEnd = isFinite(nChrLength) ? nChrLength : nRawLength - 1;

  }

  if (nChrLength) { return nIdxEnd; }

  return nChrEnd;

};

StringView.prototype.toBase64 = function (bWholeBuffer) {

  return StringView.bytesToBase64(
    bWholeBuffer ?
      (
        this.bufferView.constructor === Uint8Array ?
          this.bufferView
        :
          new Uint8Array(this.buffer)
      )
    : this.rawData.constructor === Uint8Array ?
      this.rawData
    :
      new Uint8Array(this.buffer, this.rawData.byteOffset, this.rawData.length << (this.rawData.constructor === Uint16Array ? 1 : 2))
    );

};

StringView.prototype.subview = function (nCharOffset /* optional */, nCharLength /* optional */) {

  var

    nChrLen, nCharStart, nStrLen, bVariableLen = this.encoding === "UTF-8" || this.encoding === "UTF-16",
    nStartOffset = nCharOffset, nStringLength, nRawLen = this.rawData.length;

  if (nRawLen === 0) {
    return new StringView(this.buffer, this.encoding);
  }

  nStringLength = bVariableLen ? this.makeIndex() : nRawLen;
  nCharStart = nCharOffset ? Math.max((nStringLength + nCharOffset) % nStringLength, 0) : 0;
  nStrLen = Number.isInteger(nCharLength) ? Math.max(nCharLength, 0) + nCharStart > nStringLength ? nStringLength - nCharStart : nCharLength : nStringLength;

  if (nCharStart === 0 && nStrLen === nStringLength) { return this; }

  if (bVariableLen) {
    nStartOffset = this.makeIndex(nCharStart);
    nChrLen = this.makeIndex(nStrLen, nStartOffset) - nStartOffset;
  } else {
    nStartOffset = nCharStart;
    nChrLen = nStrLen - nCharStart;
  }

  if (this.encoding === "UTF-16") {
    nStartOffset <<= 1;
  } else if (this.encoding === "UTF-32") {
    nStartOffset <<= 2;
  }

  return new StringView(this.buffer, this.encoding, nStartOffset, nChrLen);

};

StringView.prototype.forEachChar = function (fCallback, oThat, nChrOffset, nChrLen) {

  var aSource = this.rawData, nRawEnd, nRawIdx;

  if (this.encoding === "UTF-8" || this.encoding === "UTF-16") {

    var fGetInptChrSize, fGetInptChrCode;

    if (this.encoding === "UTF-8") {
      fGetInptChrSize = StringView.getUTF8CharLength;
      fGetInptChrCode = StringView.loadUTF8CharCode;
    } else if (this.encoding === "UTF-16") {
      fGetInptChrSize = StringView.getUTF16CharLength;
      fGetInptChrCode = StringView.loadUTF16CharCode;
    }

    nRawIdx = isFinite(nChrOffset) ? this.makeIndex(nChrOffset) : 0;
    nRawEnd = isFinite(nChrLen) ? this.makeIndex(nChrLen, nRawIdx) : aSource.length;

    for (var nChrCode, nChrIdx = 0; nRawIdx < nRawEnd; nChrIdx++) {
      nChrCode = fGetInptChrCode(aSource, nRawIdx);
      fCallback.call(oThat || null, nChrCode, nChrIdx, nRawIdx, aSource);
      nRawIdx += fGetInptChrSize(nChrCode);
    }

  } else {

    nRawIdx = isFinite(nChrOffset) ? nChrOffset : 0;
    nRawEnd = isFinite(nChrLen) ? nChrLen + nRawIdx : aSource.length;

    for (nRawIdx; nRawIdx < nRawEnd; nRawIdx++) {
      fCallback.call(oThat || null, aSource[nRawIdx], nRawIdx, nRawIdx, aSource);
    }

  }

};

StringView.prototype.valueOf = StringView.prototype.toString = function () {

  if (this.encoding !== "UTF-8" && this.encoding !== "UTF-16") {
    /* ASCII, UTF-32 or BinaryString to DOMString */
    return String.fromCharCode.apply(null, this.rawData);
  }

  var fGetCode, fGetIncr, sView = "";

  if (this.encoding === "UTF-8") {
    fGetIncr = StringView.getUTF8CharLength;
    fGetCode = StringView.loadUTF8CharCode;
  } else if (this.encoding === "UTF-16") {
    fGetIncr = StringView.getUTF16CharLength;
    fGetCode = StringView.loadUTF16CharCode;
  }

  for (var nChr, nLen = this.rawData.length, nIdx = 0; nIdx < nLen; nIdx += fGetIncr(nChr)) {
    nChr = fGetCode(this.rawData, nIdx);
    sView += String.fromCharCode(nChr);
  }

  return sView;

};

Manual

Methods overview

Constructor
`stringView new StringView(stringView input, optional DOMString encoding, optional unsigned long startOffset, optional unsigned long length);` `stringView new StringView(DOMString input, optional DOMString encoding, optional unsigned long startOffset, optional unsigned long length);` `stringView new StringView(unsigned long input);` `stringView new StringView(arrayBuffer input, optional DOMString encoding, optional unsigned long byteOffset, optional unsigned long length);` `stringView new StringView(arrayBufferView input, optional DOMString encoding, optional unsigned long startOffset, optional unsigned long length);` `stringView new StringView(array input, optional DOMString encoding, optional unsigned long startOffset, optional unsigned long length);`
Constructor's methods
`stringView StringView.makeFromBase64(DOMString base64String, optional DOMString encoding, optional unsigned long byteOffset, optional unsigned long length)`
Other constructor's methods
`DOMString StringView.bytesToBase64(uint8Array` `uint8Array);`
`uint8Array StringView.base64ToBytes(DOMString base64String, optional unsigned char charSize);`
`unsigned long StringView.loadUTF8CharCode(arrayBufferView typedArray, unsigned long index);`
`void StringView.putUTF8CharCode(arrayBufferView typedArray, unsigned long charCode, unsigned long index);`
`unsigned char StringView.getUTF8CharLength(unsigned long charCode);`
`unsigned long StringView.loadUTF16CharCode(arrayBufferView typedArray, unsigned long index);`
`void StringView.putUTF16CharCode(arrayBufferView typedArray, unsigned long charCode, unsigned long index);`
`unsigned char StringView.getUTF16CharLength(unsigned long charCode);`
`unsigned char StringView.b64ToUint6(unsigned char charCode);`
`unsigned char StringView.uint6ToB64(unsigned char uint6);`
Instances' methods
`unsigned long stringView.makeIndex(optional unsigned long charactersLength, optional unsigned long startFrom);`
`DOMString stringView.toBase64(optional boolean wholeBuffer);`
`stringView stringView.subview(unsigned long characterOffset, optional unsigned long charactersLength);`
`void stringView.forEachChar(function callback, optional object thisObject, optional unsigned long characterOffset, optional unsigned long charactersLength);`
`DOMString stringView.valueOf();`
`DOMString stringView.toString();`

Properties overview

Attribute	Type	Description
`encoding` Read only	`DOMString`	A string expressing the encoding type. For actually supported values see here.
`buffer` Read only	`arrayBuffer`	The buffer to be shared between `stringView.rawData` and `stringView.bufferView` view references.
`rawData` Read only	`arrayBufferView`	An arrayBufferView containing the representation of the string as array of 8-bit, 16-bit, or 32-bit integers (depending on the chosen encoding).
`bufferView` Read only	`arrayBufferView`	An arrayBufferView containing the representation of the whole buffer as array of 8-bit, 16-bit, or 32-bit integers (depending on the chosen encoding).

Constructor

Syntax

new StringView(input[, encoding[, startOffset[, length]]])

Description

Create a new string-like object based upon an ArrayBuffer.

Arguments

input (required)

The argument the stringView is constructed from. It can be:

another stringView
a string
a number
an arrayBuffer
a typed array of uint8Array, uint16Array, or uint32Array subclass
any other kind of ordered object (like arrays, collections, etc.)

If it is a number it will become the length of the new stringView; otherwise it will become its content. The following table shows the behavior of the StringView constructor.

`input` class	`stringView.buffer`	`stringView.rawData`	`stringView.bufferView`
`StringView`	A new arrayBuffer will be created.	Object reference to `stringView.bufferView` or a new arrayBufferView of `stringView.buffer` will be created (depending on `startOffset` and `length` arguments passed).	A new arrayBufferView of `stringView.buffer` will be created.
`DOMString`	A new arrayBuffer will be created.	Object reference to `stringView.bufferView` or a new arrayBufferView of `stringView.buffer` will be created (depending on `startOffset` and `length` arguments passed).	A new arrayBufferView of `stringView.buffer` will be created.
`Number`	A new arrayBuffer will be created.	Object reference to `stringView.bufferView`.	A new arrayBufferView of `stringView.buffer` will be created.
`ArrayBuffer`	Object reference to `input.buffer`.	Object reference to `stringView.bufferView` or a new arrayBufferView of `stringView.buffer` will be created (depending on `startOffset` and `length` arguments passed).	A new arrayBufferView of `stringView.buffer` will be created.
`ArrayBufferView`	Object reference to `input.buffer`.	Object reference to `input` or a new arrayBufferView of the buffer `input.buffer` (depending on many factors regarding the position of the focused parts).	Object reference to `input` or a new arrayBufferView of the buffer `input.buffer` (depending on many factors regarding the position of the focused parts).
other ordered object (like `Array`, collections, etc.)	A new arrayBuffer will be created.	Object reference to `stringView.bufferView` or a new arrayBufferView of `stringView.buffer` will be created (depending on `startOffset` and `length` arguments passed).	A new arrayBufferView of `stringView.buffer` will be created.

encoding Optional

A string expressing the encoding type. Possible values are:

UTF-8 (default)
UTF-16
UTF-32
Another custom string. In this case it will be treated as ASCII ISO/IEC 8859-15 during conversion to and/or from string. However it is usable also for binary strings.

If not specified (or specified as null) it will default to UTF-8.

startOffset Optional

A number expressing:

The start offset of the new stringView in bytes if the input argument is an arrayBuffer
The start offset of the new stringView in raw elements if the input argument is a typed array or other ordered object
The start offset of the new stringView in codepoints if the input argument is a stringView or a string

If not specified (or specified as null) it will default to 0.

length Optional

A number expressing in codepoints the length of the new stringView if the input argument is a string or a stringView, or in raw elements if the input is a typed array, an arrayBuffer or any other kind of ordered object (like Array, collections, etc.). If not specified it will take the length of the input. It never can be more than the length of the input. If you want to see how to create a stringView bigger than its content, please, see this note.

Examples

var myStringView1 = new StringView("Hello world!"); // UTF-8

alert(myStringView1) // "Hello world!"

var myStringView2 = new StringView(myStringView1, "UTF-16");

alert(myStringView1.buffer.byteLength); // 12
alert(myStringView2.buffer.byteLength); // 24

`StringView` constructor's methods

makeFromBase64()

Syntax

StringView.makeFromBase64(base64String[, encoding][, byteOffset][, length])

Description

Returns a new instance of StringView constructed decoding a given base64-encoded string.

Arguments

base64String (required): A base64-encoded string which will be decoded and copied into the new stringView object.
encoding Optional: A string expressing the encoding type. For possible values see here.
byteOffset Optional: A number expressing the start offset in bytes of the new stringView. If not specified (or specified as null) it will be considered as 0.
length Optional: A number expressing the length in codepoints of the new stringView. If not specified it will take the length of the input.

Examples

var myStringView = StringView.makeFromBase64("SGVsbG8gd29ybGQh");
alert(myStringView) // "Hello world!"

This function is useful in order to pass binary data containing strings. See also this example.

`StringView` instances' properties

encoding: A string expressing the encoding type. For possible values see here.
buffer: The buffer to be shared between stringView.rawData and stringView.bufferView view references.
rawData: An arrayBufferView containing the representation of the string as an array of 8-bit, 16-bit, or 32-bit integers (depending on the chosen encoding).
bufferView: An arrayBufferView containing the representation of the whole buffer as an array of 8-bit, 16-bit, or 32-bit integers (depending on the chosen encoding).

`StringView` instances' methods

makeIndex()

Syntax

stringView.makeIndex([charactersLength[, startFrom]])

Description

If the charactersLength argument is a number it will be taken as codepoints length and makeIndex() will return the index in elements of that position starting from 0. If the startFrom argument is passed the analysis will be done starting from it. If the charactersLength argument is omitted, makeIndex() will return the length in codepoints (ASCII or UTF-encoded) of the stringView object.

Arguments

charactersLength Optional: A number expressing the distance in codepoints from startFrom of the index of stringView.rawData to be returned.
startFrom Optional: A number expressing the position in raw elements of the characters parts to skip. If omitted it will be considered as 0.

Examples

var myStringView = new StringView("\u6432\u6432\u6432\u6432");
alert(myStringView.makeIndex()) // 4
alert(myStringView.makeIndex(2)) // 6

…using the startFrom argument…

var myStringView = StringView.makeFromBase64("5Lit5paHIGVzcGHDsW9sIEVuZ2xpc2gg4KS54KS/4KSo4KWN4KSm4KWAINin2YTYudix2KjZitipIHBvcnR1Z3XDqnMg4Kas4Ka+4KaC4Kay4Ka+INGA0YPRgdGB0LrQuNC5IOaXpeacrOiqniDgqKrgqbDgqJzgqL7gqKzgqY==");

alert(myStringView);

/* Get the Hindi subview... */
var mySubview1 = myStringView.subview(19, 6);

/* Get the Hindi subview passing an uint8Array as argument... */

var nHindiStart = myStringView.makeIndex(19);
var nHindiEnd = myStringView.makeIndex(6, nHindiStart);
var mySubview2 = new StringView(myStringView.rawData.subarray(nHindiStart, nHindiEnd), "UTF-8");

alert(mySubview1.rawData.length); // 18
alert(mySubview2.rawData.length); // 18

Appendix: other `StringView` constructor's methods (utilities)

bytesToBase64()

Syntax

StringView.bytesToBase64(uint8Array)

Description

Converts an array of bytes (a typed array of Uint8Array subclass) into a base64-encoded string.

Arguments

typedArray (required): The Uint8Array of bytes to encode to base64.

Examples

alert(StringView.bytesToBase64([72,101,108,108,111,32,119,111,114,108,100,33])); // "SGVsbG8gd29ybGQh"

StringView.bytesToBase64() is useful to encode an UTF-8 string to base64. See this article for other stuff.

base64ToBytes()

Syntax

StringView.base64ToBytes(base64String[, regSize])

Description

Decode a base64 string to an array of bytes and return it. The returned array will be a typed array of Uint8Array subclass.

Arguments

base64String (required): The string to decode from base64.
regSize Optional: The number of bytes of which the length must result in a multiple (1 or omitted for ASCII, binary strings or UTF-8-encoded strings, 2 for UTF-16 strings, 4 for UTF-32 strings).

Examples

alert(String.fromCharCode.apply(null, StringView.base64ToBytes("SGVsbG8gd29ybGQh"))); // "Hello world!"

StringView.base64ToBytes() is a generic utility useful also for binary data. If you want to pass the StringView.base64ToBytes(base64String[, regSize]).buffer property to an ArrayBufferView subclass different from Uint8Array, you should make use of the regSize argument.

loadUTF8CharCode()

Syntax

StringView.loadUTF8CharCode(typedArray, index)

Description

Returns the single codepoint at the given location from an array of UTF-8-encoded elements. An UTF-8-encoded codepoint can occupy up to six elements. This function will recompose all these parts into a codepoint.

Arguments

typedArray (required): A typed array containing the UTF-8 encoded elements.
index (required): The location to be read.

Examples

var myStringView = new StringView("Hello world!"); // an UTF-8 stringView...
alert(StringView.loadUTF8CharCode(myStringView.rawData, 6)); // 119, which is the character code for "w"

StringView.loadUTF8CharCode() is mainly for internal use and generally is of little utility.

putUTF8CharCode()

Syntax

StringView.putUTF8CharCode(typedArray, charCode, index)

Description

Write a single codepoint at the given position into a typed array. A single UTF-8-encoded codepoint can occupy many elements (up to six). This function will split it into the needed parts and will write them. Returns undefined.

Arguments

typedArray (required): A typed array containing the UTF-8 encoded elements.
charCode (required): A number expressing the Unicode representation of a character (codepoint).
index (required): The location to be overwritten.

Examples

var myStringView = new StringView("Hello world!"); // an UTF-8 stringView...
StringView.putUTF8CharCode(myStringView.rawData, "_".charCodeAt(0), 5)
alert(myStringView); // "Hello_world!"

StringView.putUTF8CharCode() is mainly for internal use and generally is of little utility.

getUTF8CharLength()

Syntax

StringView.getUTF8CharLength(charCode)

Description

Returns the number of elements occupied by an UTF-8-encoded codepoint.

Arguments

charCode (required): A number expressing the Unicode representation of a character (codepoint).

Examples

alert(StringView.getUTF8CharLength("C".charCodeAt(0))); // "C" occupies 1 UTF-8-encoded element...
alert(StringView.getUTF8CharLength("⁈".charCodeAt(0))); // "⁈" occupies 3 UTF-8-encoded elements...

StringView.getUTF8CharLength() is mainly for internal use and generally is of little utility.

loadUTF16CharCode()

Syntax

StringView.loadUTF16CharCode(typedArray, index)

Description

Returns the single codepoint at the given location from an array of UTF-16-encoded elements. An UTF-16 codepoint can occupy up to two UTF-16-encoded elements. This function will recompose all these parts into a codepoint.

Arguments

typedArray (required): A typed array containing the UTF-16 encoded elements.
index (required): The location to be read.

Examples

var myStringView = new StringView("Hello world!", "UTF-16"); // an UTF-16 stringView...
alert(StringView.loadUTF16CharCode(myStringView.rawData, 6)); // 119, which is the character code of "w"

StringView.loadUTF16CharCode() is mainly for internal use and generally is of little utility.

putUTF16CharCode()

Syntax

StringView.putUTF16CharCode(typedArray, charCode, index)

Description

Write a single codepoint at the given position into a typed array. A single UTF-16-encoded codepoint can occupy up to two UTF-16-encoded elements. This function will split it into the needed parts and will write them. Returns undefined.

Arguments

typedArray (required): A typed array containing the UTF-16 encoded elements.
charCode (required): A number expressing the Unicode representation of a character (codepoint).
index (required): The location to be overwritten.

Examples

var myStringView = new StringView("Hello world!", "UTF-16"); // an UTF-16 stringView...
StringView.putUTF16CharCode(myStringView.rawData, "_".charCodeAt(0), 5)
alert(myStringView); // "Hello_world!"

StringView.putUTF16CharCode() is mainly for internal use and generally is of little utility.

getUTF16CharLength()

Syntax

StringView.getUTF16CharLength(charCode)

Description

Returns the number of elements occupied by an UTF-16-encoded codepoint.

Arguments

charCode (required): A number expressing the Unicode representation of a character (codepoint).

Examples

alert("\uD950\uDF21"); // 0x64321
alert(StringView.b64ToUint6(0x64321)); // "\uD950\uDF21" occupies 2 UTF-16-encoded elements...

StringView.getUTF16CharLength() is mainly for internal use and generally is of little utility.

b64ToUint6()

Syntax

StringView.b64ToUint6(charCode)

Description

Returns the 6-bit number corresponding to the given base64 character code.

Arguments

charCode (required): A number expressing a base64 character code.

Examples

alert(StringView.b64ToUint6("B".charCodeAt(0))); // "B" stands for 1 in base64 encoding...

StringView.b64ToUint6() is mainly for internal use and generally is of little utility.

uint6ToB64()

Syntax

StringView.uint6ToB64(uint6)

Description

Returns the base64 character code corresponding to the given 6-bit number.

Arguments

uint6 (required): A 6-bit unsigned number (0 = uint6 < 64).

Examples

alert(String.fromCharCode(StringView.uint6ToB64(1))); // 1 is represented by "B" in base64 encoding...

StringView.uint6ToB64() is mainly for internal use and generally is of little utility.

Advanced examples

Edit an ASCII part contained within a binary file

Let's compile this C program:

#include <stdio.h>

int main () {
    printf("Hello world!\n");
    return 0;
}

In a 64-bit machine it will result in an output like the following first alert. Let's try to translate the "Hello world!" string into the Italian "Ciao mondo!!"…

var swHelloWorld = StringView.makeFromBase64("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", "ASCII", 1444, 12);

alert(String.fromCharCode.apply(null, swHelloWorld.bufferView)); // swHelloWorld.buffer contains the whole file
alert(swHelloWorld); // "Hello world"

/* traslating "Hello world" into italian... */

swHelloWorld.rawData.set((new StringView("Ciao mondo!!", "ASCII")).rawData);

/* download the new executable file... */

location.assign(URL.createObjectURL(new Blob([swHelloWorld.buffer], { "type": "application\/x-executable" })));

Note: The executable above has been compiled with GNU GCC 4.8.1 running on a 64-bit machine with Arch GNU/Linux.

Glossary

Element: An item of the backing array (whether Uint8Array, Uint16Array, Uint32Array, etc.)
Codepoint: An unique number for each Unicode character. It is rappresented by a collection of 1-6 uint8 elements for UTF-8, 1-2 uint16 elements for UTF-16, 1 uint32 element for UCS4, 1 uint8 element for ASCII, or something else.
Byte: A collection of 8 bits.
NULL codepoint: The character whose codepoint is equal to 0 ('\0').

Notes

When you include the script stringview.js into a page, no variables other than StringView itself will be added to the global scope.

StringView is a highly extensible library, that anyone can extend by adding methods to the object StringView.prototype.
For example, imagine you want to create a method similar to string.replace(), but for stringView objects. Maybe you would like to solve a situation like the following:

var oMyStringView = new StringView("Hello,&nbsp;strange&nbsp;people!"); // UTF-8
var oMyRegExp = new CLikeRegExp("&nbsp;", "g");

alert(oMyStringView.replace(oMyRegExp, " ")); // "Hello, strange people!\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000"

/* stringView.replace() will be different from string.replace() because it act also on the source: */
alert(oMyStringView); // "Hello, strange people!\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000"

As you can see, the previous example needs you to create two new algorithms: the CLikeRegExp() constructor – a constructor of C-like regular expression objects – and StringView.prototype.replace() – the new method, able to act on stringView instances. Well, just include stringview.js to your scope and work on them in another script:

/* A constructor of C-like regular expression objects... */
function CLikeRegExp (sRegExp, sFlags) {
    /**
    *  [...]
    *
    *  CONSTRUCTOR CODE HERE!
    **/
}

/* A "replace" method for StringView... */
StringView.prototype.replace = function (oCLikeRegExp, sWith) {
    /**
    *  [...]
    *
    *  METHOD CODE HERE!
    **/
};

If you want to create a stringView inside a bigger empty buffer, like in the following C line

/* myBuffer: 12 character followed by 1012 NULLs... */
char myBuffer[1024] = "Hello world!";

you should do something like this:

var myBuffer = new StringView(1024);
/* myBuffer: 12 character followed by 1012 NULLs... */
var myContent = new StringView("Hello world!");
myBuffer.rawData.set(myContent.rawData, myContent.rawData.length);

StringView is a constructor and a collection of methods whose aim is to work strictly on arrays of numbers, rather than on creating new immutable JavaScript strings. Keep it in mind when you try to extend its prototype.
Since stringView, unlike C strings, has a length property, there is no reason to add a NULL codepoint ('\0') after the termination of a string.
StringView has been proposed as strawman for ES6 on ECMAScript Bugs. Everyone can participate in the discussion at bug 1557 or at esdiscuss.

StringView

The aims of this library are:

Introduction

The code

Manual

Methods overview

Properties overview

Constructor

Syntax

Description

Arguments

Examples

StringView constructor's methods

StringView instances' properties

StringView instances' methods

Appendix: other StringView constructor's methods (utilities)

Advanced examples

Edit an ASCII part contained within a binary file

Glossary

Notes

See also

ドキュメントのタグと貢献者

`StringView` constructor's methods

`StringView` instances' properties

`StringView` instances' methods

Appendix: other `StringView` constructor's methods (utilities)