summaryrefslogtreecommitdiff
path: root/lib/string_decoder.js
blob: 6e730c2fbd385f811825d9d6f0e8f38e53048f4f (plain)
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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.

var StringDecoder = exports.StringDecoder = function(encoding) {
  this.encoding = (encoding || 'utf8').toLowerCase().replace(/[-_]/, '');
  if (this.encoding === 'utf8') {
    this.charBuffer = new Buffer(6);
    this.charReceived = 0;
    this.charLength = 0;
  }
};


StringDecoder.prototype.write = function(buffer) {
  // If not utf8...
  if (this.encoding !== 'utf8') {
    return buffer.toString(this.encoding);
  }

  var charStr = '';
  var offset = 0;
  // if our last write ended with an incomplete multibyte character
  while (this.charLength) {
    // determine how many remaining bytes this buffer has to offer for this char
    var i = (buffer.length >= this.charLength - this.charReceived) ?
                this.charLength - this.charReceived :
                buffer.length;

    // add the new bytes to the char buffer
    buffer.copy(this.charBuffer, this.charReceived, offset, i);
    this.charReceived += (i - offset);
    offset = i;

    if (this.charReceived < this.charLength) {
      // still not enough chars in this buffer? wait for more ...
      return '';
    }

    // get the character that was split
    charStr = this.charBuffer.slice(0, this.charLength).toString();

    // lead surrogate (D800-DBFF) is also the incomplete character
    if (this.charLength === 3) {
      var charCode = charStr.charCodeAt(0);
      if (charCode >= 0xD800 && charCode <= 0xDBFF) {
        charStr = '';
        this.charLength += 3; // size of trail surrogate (DC00-DFFF)
        continue;
      }
    }
    this.charReceived = this.charLength = 0;

    // if there are no more bytes in this buffer, just emit our char
    if (i == buffer.length) return charStr;

    // otherwise cut off the characters end from the beginning of this buffer
    buffer = buffer.slice(i, buffer.length);
    break;
  }


  // determine how many bytes we have to check at the end of this buffer
  var i = (buffer.length >= 3) ? 3 : buffer.length;

  // Figure out if one of the last i bytes of our buffer announces an
  // incomplete char.
  for (; i > 0; i--) {
    var c = buffer[buffer.length - i];

    // See http://en.wikipedia.org/wiki/UTF-8#Description

    // 110XXXXX
    if (i == 1 && c >> 5 == 0x06) {
      this.charLength = 2;
      break;
    }

    // 1110XXXX
    if (i <= 2 && c >> 4 == 0x0E) {
      this.charLength = 3;
      break;
    }

    // 11110XXX
    if (i <= 3 && c >> 3 == 0x1E) {
      this.charLength = 4;
      break;
    }
  }

  var end = buffer.length;
  if (this.charLength) {
    // buffer the incomplete character bytes we got
    buffer.copy(this.charBuffer, 0, buffer.length - i, buffer.length);
    this.charReceived = i;
    end -= i;
  }

  charStr += buffer.toString('utf8', 0, end);

  // lead surrogate (D800-DBFF) is also the incomplete character
  end = charStr.length - 1;
  var charCode = charStr.charCodeAt(end);
  if (charCode >= 0xD800 && charCode <= 0xDBFF) {
    // CESU-8 represents each of Surrogate Pair by 3-bytes
    this.charLength += 3
    this.charReceived += 3
    this.charBuffer.copy(this.charBuffer, 3, 0, 3);
    this.charBuffer.write(charStr.charAt(end));
    return charStr.substring(0, end);
  }

  // or just emit the charStr
  return charStr;
};