js实现unicode码字符串与utf8字节数据互转详解

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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
/**
 * Created by hdwang on 2019/1/28.
 */
var convertUtf8 = (function() {

  /**
   * unicode string to utf-8
   * @param text 字符串
   * @returns {*} utf-8编码
   */
  function toBytes(text) {
    var result = [], i = 0;
    text = encodeURI(text);
    while (i < text.length) {
      var c = text.charCodeAt(i++);

      // if it is a % sign, encode the following 2 bytes as a hex value
      if (c === 37) {
        result.push(parseInt(text.substr(i, 2), 16))
        i += 2;

        // otherwise, just the actual byte
      } else {
        result.push(c)
      }
    }

    return coerceArray(result);
  }


  /**
   * utf8 byte to unicode string
   * @param utf8Bytes
   * @returns {string}
   */
  function utf8ByteToUnicodeStr(utf8Bytes){
    var unicodeStr ="";
    for (var pos = 0; pos < utf8Bytes.length;){
      var flag= utf8Bytes[pos];
      var unicode = 0 ;
      if ((flag >>>7) === 0 ) {
        unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
        pos += 1;

      } else if ((flag &0xFC) === 0xFC ){
        unicode = (utf8Bytes[pos] & 0x3) << 30;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 24;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 18;
        unicode |= (utf8Bytes[pos+3] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+4] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+5] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 6;

      }else if ((flag &0xF8) === 0xF8 ){
        unicode = (utf8Bytes[pos] & 0x7) << 24;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 18;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+3] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+4] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 5;

      } else if ((flag &0xF0) === 0xF0 ){
        unicode = (utf8Bytes[pos] & 0xF) << 18;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+3] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 4;

      } else if ((flag &0xE0) === 0xE0 ){
        unicode = (utf8Bytes[pos] & 0x1F) << 12;;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+2] & 0x3F);
        unicodeStr+= String.fromCharCode(unicode) ;
        pos += 3;

      } else if ((flag &0xC0) === 0xC0 ){ //110
        unicode = (utf8Bytes[pos] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+1] & 0x3F);
        unicodeStr+= String.fromCharCode(unicode) ;
        pos += 2;

      } else{
        unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
        pos += 1;
      }
    }
    return unicodeStr;
  }



  function checkInt(value) {
    return (parseInt(value) === value);
  }

  function checkInts(arrayish) {
    if (!checkInt(arrayish.length)) { return false; }

    for (var i = 0; i < arrayish.length; i++) {
      if (!checkInt(arrayish[i]) || arrayish[i] < 0 || arrayish[i] > 255) {
        return false;
      }
    }

    return true;
  }

  function coerceArray(arg, copy) {

    // ArrayBuffer view
    if (arg.buffer && arg.name === 'Uint8Array') {

      if (copy) {
        if (arg.slice) {
          arg = arg.slice();
        } else {
          arg = Array.prototype.slice.call(arg);
        }
      }

      return arg;
    }

    // It's an array; check it is a valid representation of a byte
    if (Array.isArray(arg)) {
      if (!checkInts(arg)) {
        throw new Error('Array contains invalid value: ' + arg);
      }

      return new Uint8Array(arg);
    }

    // Something else, but behaves like an array (maybe a Buffer? Arguments?)
    if (checkInt(arg.length) && checkInts(arg)) {
      return new Uint8Array(arg);
    }

    throw new Error('unsupported array-like object');
  }

  return {
    toBytes: toBytes,
    fromBytes: utf8ByteToUnicodeStr
  }
})()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
//高char10位[一个unicode字符] (2+6+2=10)
unicode =  ((utf8Bytes[pos] & 0x3)) << 8 |((utf8Bytes[pos+1] & 0x3f) << 2) |((utf8Bytes[pos+2] >> 4) & 0x03);

//减去‭1F600‬中的1，这里减去6个0即可，低位char已经占据10位
unicode = unicode - parseInt('1000000',2)

//加上utf-16高char的标识符
unicode = 0xD800 + unicode;
console.log(unicode);
unicodeStr += String.fromCharCode(unicode);

//低char10位[一个unicode字符](4+6)
unicode = ((utf8Bytes[pos+2] & 0x0F) << 6) | (utf8Bytes[pos+3] & 0x3F);
//加上utf-16低char的标识符
unicode = 0xDC00 + unicode;
console.log(unicode);
unicodeStr+= String.fromCharCode(unicode);
pos += 4;