node/lib/querystring.js

// Query String Utilities

'use strict';

const QueryString = exports;
const Buffer = require('buffer').Buffer;


function charCode(c) {
  return c.charCodeAt(0);
}


// a safe fast alternative to decodeURIComponent
QueryString.unescapeBuffer = function(s, decodeSpaces) {
  var out = new Buffer(s.length);
  var state = 'CHAR'; // states: CHAR, HEX0, HEX1
  var n, m, hexchar;

  for (var inIndex = 0, outIndex = 0; inIndex <= s.length; inIndex++) {
    var c = s.charCodeAt(inIndex);
    switch (state) {
      case 'CHAR':
        switch (c) {
          case charCode('%'):
            n = 0;
            m = 0;
            state = 'HEX0';
            break;
          case charCode('+'):
            if (decodeSpaces) c = charCode(' ');
            // falls through
          default:
            out[outIndex++] = c;
            break;
        }
        break;

      case 'HEX0':
        state = 'HEX1';
        hexchar = c;
        if (charCode('0') <= c && c <= charCode('9')) {
          n = c - charCode('0');
        } else if (charCode('a') <= c && c <= charCode('f')) {
          n = c - charCode('a') + 10;
        } else if (charCode('A') <= c && c <= charCode('F')) {
          n = c - charCode('A') + 10;
        } else {
          out[outIndex++] = charCode('%');
          out[outIndex++] = c;
          state = 'CHAR';
          break;
        }
        break;

      case 'HEX1':
        state = 'CHAR';
        if (charCode('0') <= c && c <= charCode('9')) {
          m = c - charCode('0');
        } else if (charCode('a') <= c && c <= charCode('f')) {
          m = c - charCode('a') + 10;
        } else if (charCode('A') <= c && c <= charCode('F')) {
          m = c - charCode('A') + 10;
        } else {
          out[outIndex++] = charCode('%');
          out[outIndex++] = hexchar;
          out[outIndex++] = c;
          break;
        }
        out[outIndex++] = 16 * n + m;
        break;
    }
  }

  // TODO support returning arbitrary buffers.

  return out.slice(0, outIndex - 1);
};


QueryString.unescape = function(s, decodeSpaces) {
  try {
    return decodeURIComponent(s);
  } catch (e) {
    return QueryString.unescapeBuffer(s, decodeSpaces).toString();
  }
};


var hexTable = new Array(256);
for (var i = 0; i < 256; ++i)
  hexTable[i] = '%' + ((i < 16 ? '0' : '') + i.toString(16)).toUpperCase();
QueryString.escape = function(str) {
  // replaces encodeURIComponent
  // http://www.ecma-international.org/ecma-262/5.1/#sec-15.1.3.4
  str = '' + str;
  var len = str.length;
  var out = '';
  var i, c;

  if (len === 0)
    return str;

  for (i = 0; i < len; ++i) {
    c = str.charCodeAt(i);

    // These characters do not need escaping (in order):
    // ! - . _ ~
    // ' ( ) *
    // digits
    // alpha (uppercase)
    // alpha (lowercase)
    if (c === 0x21 || c === 0x2D || c === 0x2E || c === 0x5F || c === 0x7E ||
        (c >= 0x27 && c <= 0x2A) ||
        (c >= 0x30 && c <= 0x39) ||
        (c >= 0x41 && c <= 0x5A) ||
        (c >= 0x61 && c <= 0x7A)) {
      out += str[i];
      continue;
    }

    // Other ASCII characters
    if (c < 0x80) {
      out += hexTable[c];
      continue;
    }

    // Multi-byte characters ...
    if (c < 0x800) {
      out += hexTable[0xC0 | (c >> 6)] + hexTable[0x80 | (c & 0x3F)];
      continue;
    }
    if (c < 0xD800 || c >= 0xE000) {
      out += hexTable[0xE0 | (c >> 12)] +
             hexTable[0x80 | ((c >> 6) & 0x3F)] +
             hexTable[0x80 | (c & 0x3F)];
      continue;
    }
    // Surrogate pair
    ++i;
    var c2;
    if (i < str.length)
      c2 = str.charCodeAt(i) & 0x3FF;
    else
      throw new URIError('URI malformed');
    c = 0x10000 + (((c & 0x3FF) << 10) | c2);
    out += hexTable[0xF0 | (c >> 18)] +
           hexTable[0x80 | ((c >> 12) & 0x3F)] +
           hexTable[0x80 | ((c >> 6) & 0x3F)] +
           hexTable[0x80 | (c & 0x3F)];
  }
  return out;
};

var stringifyPrimitive = function(v) {
  if (typeof v === 'string')
    return v;
  if (typeof v === 'number' && isFinite(v))
    return '' + v;
  if (typeof v === 'boolean')
    return v ? 'true' : 'false';
  return '';
};


QueryString.stringify = QueryString.encode = function(obj, sep, eq, options) {
  sep = sep || '&';
  eq = eq || '=';

  var encode = QueryString.escape;
  if (options && typeof options.encodeURIComponent === 'function') {
    encode = options.encodeURIComponent;
  }

  if (obj !== null && typeof obj === 'object') {
    var keys = Object.keys(obj);
    var len = keys.length;
    var flast = len - 1;
    var fields = '';
    for (var i = 0; i < len; ++i) {
      var k = keys[i];
      var v = obj[k];
      var ks = encode(stringifyPrimitive(k)) + eq;

      if (Array.isArray(v)) {
        var vlen = v.length;
        var vlast = vlen - 1;
        for (var j = 0; j < vlen; ++j) {
          fields += ks + encode(stringifyPrimitive(v[j]));
          if (j < vlast)
            fields += sep;
        }
        if (vlen && i < flast)
          fields += sep;
      } else {
        fields += ks + encode(stringifyPrimitive(v));
        if (i < flast)
          fields += sep;
      }
    }
    return fields;
  }
  return '';
};

// Parse a key=val string.
QueryString.parse = QueryString.decode = function(qs, sep, eq, options) {
  sep = sep || '&';
  eq = eq || '=';
  const eqLen = eq.length;
  var obj = {};

  if (typeof qs !== 'string' || qs.length === 0) {
    return obj;
  }

  qs = qs.split(sep);

  var maxKeys = 1000;
  if (options && typeof options.maxKeys === 'number') {
    maxKeys = options.maxKeys;
  }

  var len = qs.length;
  // maxKeys <= 0 means that we should not limit keys count
  if (maxKeys > 0 && len > maxKeys) {
    len = maxKeys;
  }

  var decode = QueryString.unescape;
  if (options && typeof options.decodeURIComponent === 'function') {
    decode = options.decodeURIComponent;
  }

  var keys = [];
  for (var i = 0; i < len; ++i) {
    // replacePlus() is used instead of a regexp because it is ~15-30% faster
    // with v8 4.7
    const x = replacePlus(qs[i]);
    const idx = x.indexOf(eq);
    var k, v;

    if (idx >= 0) {
      k = decodeStr(x.substring(0, idx), decode);
      v = decodeStr(x.substring(idx + eqLen), decode);
    } else {
      k = decodeStr(x, decode);
      v = '';
    }

    // Use a key array lookup instead of using hasOwnProperty(), which is slower
    if (keys.indexOf(k) === -1) {
      obj[k] = v;
      keys.push(k);
    } else if (obj[k] instanceof Array) {
      // `instanceof Array` is used instead of Array.isArray() because it is
      // ~15-20% faster with v8 4.7 and is safe to use because we are using it
      // with values being created within this function
      obj[k].push(v);
    } else {
      obj[k] = [obj[k], v];
    }
  }

  return obj;
};


function replacePlus(str) {
  var ret = '';
  var start = 0;
  var i = -1;
  while ((i = str.indexOf('+', i + 1)) !== -1) {
    ret += str.slice(start, i);
    ret += '%20';
    start = i + 1;
  }
  if (start === 0)
    return str;
  if (start < str.length)
    ret += str.slice(start);
  return ret;
}


// v8 does not optimize functions with try-catch blocks, so we isolate them here
// to minimize the damage
function decodeStr(s, decoder) {
  try {
    return decoder(s);
  } catch (e) {
    return QueryString.unescape(s, true);
  }
}