functionalscript 0.0.405 → 0.0.406
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/html/module.f.cjs +3 -3
- package/json/tokenizer/test.f.cjs +2 -2
- package/package.json +1 -1
- package/test.f.cjs +2 -1
- package/text/encoding/README.md +10 -6
- package/text/encoding/utf16/module.f.cjs +90 -0
- package/text/encoding/utf16/test.f.cjs +118 -0
- package/text/encoding/utf8/module.f.cjs +96 -0
- package/text/encoding/utf8/test.f.cjs +144 -0
- package/text/encoding/module.f.cjs +0 -154
- package/text/encoding/test.f.cjs +0 -223
package/html/module.f.cjs
CHANGED
|
@@ -3,8 +3,8 @@ const { map, flatMap, flat, concat: listConcat } = list
|
|
|
3
3
|
const { concat: stringConcat } = require('../types/string/module.f.cjs')
|
|
4
4
|
const object = require('../types/object/module.f.cjs')
|
|
5
5
|
const { compose } = require('../types/function/module.f.cjs')
|
|
6
|
-
const encoding = require('../text/encoding/module.f.cjs');
|
|
7
|
-
const {
|
|
6
|
+
const encoding = require('../text/encoding/utf16/module.f.cjs');
|
|
7
|
+
const { stringToList } = encoding
|
|
8
8
|
|
|
9
9
|
const { fromCharCode } = String
|
|
10
10
|
const { entries } = Object
|
|
@@ -80,7 +80,7 @@ const escapeCharCode = code => {
|
|
|
80
80
|
}
|
|
81
81
|
}
|
|
82
82
|
|
|
83
|
-
const escape = compose(
|
|
83
|
+
const escape = compose(stringToList)(map(escapeCharCode))
|
|
84
84
|
|
|
85
85
|
/** @type {(n: Node) => list.List<string>} */
|
|
86
86
|
const node = n => typeof n === 'string' ? escape(n) : element(n)
|
|
@@ -2,10 +2,10 @@ const tokenizer = require('./module.f.cjs')
|
|
|
2
2
|
const list = require('../../types/list/module.f.cjs')
|
|
3
3
|
const json = require('../module.f.cjs')
|
|
4
4
|
const { sort } = require('../../types/object/module.f.cjs')
|
|
5
|
-
const encoding = require('../../text/encoding/module.f.cjs');
|
|
5
|
+
const encoding = require('../../text/encoding/utf16/module.f.cjs');
|
|
6
6
|
|
|
7
7
|
/** @type {(s: string) => readonly tokenizer.JsonToken[]} */
|
|
8
|
-
const tokenizeString = s => list.toArray(tokenizer.tokenize(encoding.
|
|
8
|
+
const tokenizeString = s => list.toArray(tokenizer.tokenize(encoding.stringToList(s)))
|
|
9
9
|
|
|
10
10
|
const stringify = json.stringify(sort)
|
|
11
11
|
|
package/package.json
CHANGED
package/test.f.cjs
CHANGED
|
@@ -22,7 +22,8 @@ require('./commonjs/build/test.f.cjs')
|
|
|
22
22
|
require('./types/range/test.f.cjs')
|
|
23
23
|
require('./html/test.f.cjs')
|
|
24
24
|
require('./text/test.f.cjs')
|
|
25
|
-
require('./text/encoding/test.f.cjs')
|
|
25
|
+
require('./text/encoding/utf8/test.f.cjs')
|
|
26
|
+
require('./text/encoding/utf16/test.f.cjs')
|
|
26
27
|
require('./com/cs/test.f.cjs')
|
|
27
28
|
require('./com/cpp/test.f.cjs')
|
|
28
29
|
require('./nodejs/version/test.f.cjs')
|
package/text/encoding/README.md
CHANGED
|
@@ -34,12 +34,14 @@ Total error states:
|
|
|
34
34
|
- 34_432
|
|
35
35
|
- < 2^16
|
|
36
36
|
|
|
37
|
+
### utf8/module.f.cjs
|
|
38
|
+
|
|
37
39
|
```js
|
|
38
40
|
/** @type {(input: List<u8|undefined>) => List<i32>} */
|
|
39
|
-
const
|
|
41
|
+
const toCodePointList
|
|
40
42
|
|
|
41
43
|
/** @type {(input: List<i32>) => List<u8>} */
|
|
42
|
-
const
|
|
44
|
+
const fromCodePointList
|
|
43
45
|
```
|
|
44
46
|
|
|
45
47
|
## UTF-16
|
|
@@ -67,18 +69,20 @@ Requirement: no loss for UTF16 => codepoint => UTF16
|
|
|
67
69
|
|
|
68
70
|
Total error states: 11 bit
|
|
69
71
|
|
|
72
|
+
### utf16/module.f.cjs
|
|
73
|
+
|
|
70
74
|
```js
|
|
71
75
|
/** @type {(input: List<u16|undefined>) => List<i32>} */
|
|
72
|
-
const
|
|
76
|
+
const toCodePointList
|
|
73
77
|
|
|
74
78
|
/** @type {(input: List<i32>) => List<u16>} */
|
|
75
|
-
const
|
|
79
|
+
const fromCodePointList
|
|
76
80
|
|
|
77
81
|
/** @type {(input: string) => List<u16>} */
|
|
78
|
-
const
|
|
82
|
+
const stringToList
|
|
79
83
|
|
|
80
84
|
/** @type {(input: List<u16>) => string} */
|
|
81
|
-
const
|
|
85
|
+
const listToString
|
|
82
86
|
```
|
|
83
87
|
|
|
84
88
|
UTF-16 => CP => UTF-8 => CP = UTF-16
|
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
const list = require('../../../types/list/module.f.cjs')
|
|
2
|
+
const operator = require('../../../types/function/operator/module.f.cjs')
|
|
3
|
+
const array = require('../../../types/array/module.f.cjs')
|
|
4
|
+
const { contains } = require('../../../types/range/module.f.cjs')
|
|
5
|
+
const { compose } = require('../../../types/function/module.f.cjs')
|
|
6
|
+
const { map, flat, stateScan, concat, reduce, flatMap } = list
|
|
7
|
+
|
|
8
|
+
/** @typedef {u16|undefined} WordOrEof */
|
|
9
|
+
|
|
10
|
+
/** @typedef {undefined|number} Utf16State */
|
|
11
|
+
|
|
12
|
+
/** @typedef {number} u16 */
|
|
13
|
+
|
|
14
|
+
/** @typedef {number} i32 */
|
|
15
|
+
|
|
16
|
+
/** @type {(a:number) => boolean} */
|
|
17
|
+
const isBmpCodePoint = a => a >= 0x0000 && a <= 0xd7ff || a >= 0xe000 && a <= 0xffff
|
|
18
|
+
|
|
19
|
+
const isHighSurrogate = contains([0xd800, 0xdbff])
|
|
20
|
+
|
|
21
|
+
/** @type {(a:number) => boolean} */
|
|
22
|
+
const isLowSurrogate = contains([0xdc00, 0xdfff])
|
|
23
|
+
|
|
24
|
+
const errorMask = 0b1000_0000_0000_0000_0000_0000_0000_0000
|
|
25
|
+
|
|
26
|
+
/** @type {(input:i32) => list.List<u16>} */
|
|
27
|
+
const codePointToUtf16 = input =>
|
|
28
|
+
{
|
|
29
|
+
if (isBmpCodePoint(input)) { return [input] }
|
|
30
|
+
if (input >= 0x010000 && input <= 0x10ffff) {
|
|
31
|
+
const high = ((input - 0x10000) >> 10) + 0xd800
|
|
32
|
+
const low = ((input - 0x10000) & 0b0011_1111_1111) + 0xdc00
|
|
33
|
+
return [high, low]
|
|
34
|
+
}
|
|
35
|
+
return [input & 0xffff]
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
const fromCodePointList = flatMap(codePointToUtf16)
|
|
39
|
+
|
|
40
|
+
/** @type {operator.StateScan<u16, Utf16State, list.List<i32>>} */
|
|
41
|
+
const utf16ByteToCodePointOp = state => byte => {
|
|
42
|
+
if (byte < 0x00 || byte > 0xffff) {
|
|
43
|
+
return [[0xffffffff], state]
|
|
44
|
+
}
|
|
45
|
+
if (state === undefined) {
|
|
46
|
+
if (isBmpCodePoint(byte)) { return [[byte], undefined] }
|
|
47
|
+
if (isHighSurrogate(byte)) { return [[], byte] }
|
|
48
|
+
return [[byte | errorMask], undefined]
|
|
49
|
+
}
|
|
50
|
+
if (isLowSurrogate(byte)) {
|
|
51
|
+
const high = state - 0xd800
|
|
52
|
+
const low = byte - 0xdc00
|
|
53
|
+
return [[(high << 10) + low + 0x10000], undefined]
|
|
54
|
+
}
|
|
55
|
+
if (isBmpCodePoint(byte)) { return [[state | errorMask, byte], undefined] }
|
|
56
|
+
if (isHighSurrogate(byte)) { return [[state | errorMask], byte] }
|
|
57
|
+
return [[state | errorMask, byte | errorMask], undefined]
|
|
58
|
+
}
|
|
59
|
+
|
|
60
|
+
/** @type {(state: Utf16State) => readonly[list.List<i32>, Utf16State]} */
|
|
61
|
+
const utf16EofToCodePointOp = state => [state === undefined ? undefined : [state | errorMask], undefined]
|
|
62
|
+
|
|
63
|
+
/** @type {operator.StateScan<WordOrEof, Utf16State, list.List<i32>>} */
|
|
64
|
+
const utf16ByteOrEofToCodePointOp = state => input => input === undefined ? utf16EofToCodePointOp(state) : utf16ByteToCodePointOp(state)(input)
|
|
65
|
+
|
|
66
|
+
/** @type {(input: list.List<u16>) => list.List<i32>} */
|
|
67
|
+
const toCodePointList = input => flat(stateScan(utf16ByteOrEofToCodePointOp)(undefined)(concat(/** @type {list.List<WordOrEof>} */(input))([undefined])))
|
|
68
|
+
|
|
69
|
+
/** @type {(s: string) => list.List<u16>} */
|
|
70
|
+
const stringToList = s => {
|
|
71
|
+
/** @type {(i: number) => list.Result<number>} */
|
|
72
|
+
const at = i => {
|
|
73
|
+
const first = s.charCodeAt(i)
|
|
74
|
+
return isNaN(first) ? undefined : { first, tail: () => at(i + 1) }
|
|
75
|
+
}
|
|
76
|
+
return at(0)
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
const listToString = compose(map(String.fromCharCode))(reduce(operator.concat)(''))
|
|
80
|
+
|
|
81
|
+
module.exports = {
|
|
82
|
+
/** @readonly */
|
|
83
|
+
fromCodePointList,
|
|
84
|
+
/** @readonly */
|
|
85
|
+
toCodePointList,
|
|
86
|
+
/** @readonly */
|
|
87
|
+
stringToList,
|
|
88
|
+
/** @readonly */
|
|
89
|
+
listToString
|
|
90
|
+
}
|
|
@@ -0,0 +1,118 @@
|
|
|
1
|
+
const encoding = require('./module.f.cjs')
|
|
2
|
+
const json = require('../../../json/module.f.cjs')
|
|
3
|
+
const { sort } = require('../../../types/object/module.f.cjs')
|
|
4
|
+
const { list } = require('../../../types/module.f.cjs')
|
|
5
|
+
|
|
6
|
+
/** @type {(a: readonly json.Unknown[]) => string} */
|
|
7
|
+
const stringify = a => json.stringify(sort)(a)
|
|
8
|
+
|
|
9
|
+
{
|
|
10
|
+
const result = stringify(list.toArray(encoding.toCodePointList([-1, 65536])))
|
|
11
|
+
if (result !== '[4294967295,4294967295]') { throw result }
|
|
12
|
+
}
|
|
13
|
+
|
|
14
|
+
{
|
|
15
|
+
const result = stringify(list.toArray(encoding.toCodePointList([0, 36, 8364, 55295, 57344, 65535])))
|
|
16
|
+
if (result !== '[0,36,8364,55295,57344,65535]') { throw result }
|
|
17
|
+
}
|
|
18
|
+
|
|
19
|
+
{
|
|
20
|
+
const result = stringify(list.toArray(encoding.toCodePointList([56320, 57343])))
|
|
21
|
+
if (result !== '[-2147427328,-2147426305]') { throw result }
|
|
22
|
+
}
|
|
23
|
+
|
|
24
|
+
{
|
|
25
|
+
const result = stringify(list.toArray(encoding.toCodePointList([55296, 56320, 55297, 56375, 55378, 57186, 56319, 57343])))
|
|
26
|
+
if (result !== '[65536,66615,150370,1114111]') { throw result }
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
{
|
|
30
|
+
const result = stringify(list.toArray(encoding.toCodePointList([55296, 55296])))
|
|
31
|
+
if (result !== '[-2147428352,-2147428352]') { throw result }
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
{
|
|
35
|
+
const result = stringify(list.toArray(encoding.toCodePointList([55296, 0])))
|
|
36
|
+
if (result !== '[-2147428352,0]') { throw result }
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
{
|
|
40
|
+
const result = stringify(list.toArray(encoding.toCodePointList([56320])))
|
|
41
|
+
if (result !== '[-2147427328]') { throw result }
|
|
42
|
+
}
|
|
43
|
+
|
|
44
|
+
{
|
|
45
|
+
const result = stringify(list.toArray(encoding.toCodePointList([56320, 0])))
|
|
46
|
+
if (result !== '[-2147427328,0]') { throw result }
|
|
47
|
+
}
|
|
48
|
+
|
|
49
|
+
{
|
|
50
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0])))
|
|
51
|
+
if (result !== '[0]') { throw result }
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
{
|
|
55
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x24])))
|
|
56
|
+
if (result !== '[36]') { throw result }
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
{
|
|
60
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x20AC])))
|
|
61
|
+
if (result !== '[8364]') { throw result }
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
{
|
|
65
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0xd7ff])))
|
|
66
|
+
if (result !== '[55295]') { throw result }
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
{
|
|
70
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0xe000])))
|
|
71
|
+
if (result !== '[57344]') { throw result }
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
{
|
|
75
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0xffff])))
|
|
76
|
+
if (result !== '[65535]') { throw result }
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
{
|
|
80
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10000])))
|
|
81
|
+
if (result !== '[55296,56320]') { throw result }
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
{
|
|
85
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10437])))
|
|
86
|
+
if (result !== '[55297,56375]') { throw result }
|
|
87
|
+
}
|
|
88
|
+
|
|
89
|
+
{
|
|
90
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x24B62])))
|
|
91
|
+
if (result !== '[55378,57186]') { throw result }
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
{
|
|
95
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10ffff])))
|
|
96
|
+
if (result !== '[56319,57343]') { throw result }
|
|
97
|
+
}
|
|
98
|
+
|
|
99
|
+
{
|
|
100
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([-1, 0xd800, 0xdfff, 0x110000])))
|
|
101
|
+
if (result !== '[65535,55296,57343,0]') { throw result }
|
|
102
|
+
}
|
|
103
|
+
|
|
104
|
+
{
|
|
105
|
+
const utf16List = encoding.stringToList("Hello world!😂🚜🚲")
|
|
106
|
+
const result = encoding.listToString(utf16List)
|
|
107
|
+
if (result !== "Hello world!😂🚜🚲") { throw result }
|
|
108
|
+
}
|
|
109
|
+
|
|
110
|
+
{
|
|
111
|
+
const a = encoding.stringToList("Hello world!😂🚜🚲")
|
|
112
|
+
const b = encoding.toCodePointList(a)
|
|
113
|
+
const c = encoding.fromCodePointList(b)
|
|
114
|
+
const result = encoding.listToString(c)
|
|
115
|
+
if (result !== "Hello world!😂🚜🚲") { throw result }
|
|
116
|
+
}
|
|
117
|
+
|
|
118
|
+
module.exports = {}
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
const list = require('../../../types/list/module.f.cjs')
|
|
2
|
+
const operator = require('../../../types/function/operator/module.f.cjs')
|
|
3
|
+
const array = require('../../../types/array/module.f.cjs')
|
|
4
|
+
const { flatMap } = list
|
|
5
|
+
|
|
6
|
+
/** @typedef {u8|undefined} ByteOrEof */
|
|
7
|
+
|
|
8
|
+
/** @typedef {array.Array1<number>|array.Array2<number>|array.Array3<number>} Utf8NonEmptyState */
|
|
9
|
+
|
|
10
|
+
/** @typedef {undefined|Utf8NonEmptyState} Utf8State */
|
|
11
|
+
|
|
12
|
+
/** @typedef {number} u8 */
|
|
13
|
+
|
|
14
|
+
/** @typedef {number} i32 */
|
|
15
|
+
|
|
16
|
+
const errorMask = 0b1000_0000_0000_0000_0000_0000_0000_0000
|
|
17
|
+
|
|
18
|
+
/** @type {(input:number) => list.List<u8>} */
|
|
19
|
+
const codePointToUtf8 = input =>
|
|
20
|
+
{
|
|
21
|
+
if (input >= 0x0000 && input <= 0x007f) { return [input & 0b01111_1111] }
|
|
22
|
+
if (input >= 0x0080 && input <= 0x07ff) { return [input >> 6 | 0b1100_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
23
|
+
if (input >= 0x0800 && input <= 0xffff) { return [input >> 12 | 0b1110_0000, input >> 6 & 0b0011_1111 | 0b1000_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
24
|
+
if (input >= 0x10000 && input <= 0x10ffff) { return [input >> 18 | 0b1111_0000, input >> 12 & 0b0011_1111 | 0b1000_0000, input >> 6 & 0b0011_1111 | 0b1000_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
25
|
+
if ((input & errorMask) !== 0) {
|
|
26
|
+
if ((input & 0b1000_0000_0000_0000) !== 0) { return [input >> 12 & 0b0000_0111 | 0b1111_0000, input >> 6 & 0b0011_1111 | 0b1000_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
27
|
+
if ((input & 0b0000_0100_0000_0000) !== 0) { return [input >> 6 & 0b0000_1111 | 0b1110_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
28
|
+
if ((input & 0b0000_0010_0000_0000) !== 0) { return [input >> 6 & 0b0000_0111 | 0b1111_0000, input & 0b0011_1111 | 0b1000_0000] }
|
|
29
|
+
if ((input & 0b0000_0000_1000_0000) !== 0) { return [input & 0b1111_1111] }
|
|
30
|
+
}
|
|
31
|
+
return [errorMask]
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
const fromCodePointList = flatMap(codePointToUtf8)
|
|
35
|
+
|
|
36
|
+
/** @type {(state: Utf8NonEmptyState) => i32}*/
|
|
37
|
+
const utf8StateToError = state => {
|
|
38
|
+
switch(state.length) {
|
|
39
|
+
case 1:
|
|
40
|
+
return state[0] | errorMask
|
|
41
|
+
case 2:
|
|
42
|
+
if (state[0] < 0b1111_0000) return (((state[0] & 0b0000_1111) << 6) + (state[1] & 0b0011_1111) + 0b0000_0100_0000_0000) | errorMask
|
|
43
|
+
return (((state[0] & 0b0000_0111) << 6) + (state[1] & 0b0011_1111) + 0b0000_0010_0000_0000) | errorMask
|
|
44
|
+
case 3:
|
|
45
|
+
return (((state[0] & 0b0000_0111) << 12) + ((state[1] & 0b0011_1111) << 6) + (state[2] & 0b0011_1111) + 0b1000_0000_0000_0000) | errorMask
|
|
46
|
+
}
|
|
47
|
+
}
|
|
48
|
+
|
|
49
|
+
/** @type {operator.StateScan<number, Utf8State, list.List<i32>>} */
|
|
50
|
+
const utf8ByteToCodePointOp = state => byte => {
|
|
51
|
+
if (byte < 0x00 || byte > 0xff) {
|
|
52
|
+
return [[errorMask], state]
|
|
53
|
+
}
|
|
54
|
+
if (state == undefined) {
|
|
55
|
+
if (byte < 0b1000_0000) { return [[byte], undefined] }
|
|
56
|
+
if (byte >= 0b1100_0010 && byte <= 0b1111_0100) { return [[], [byte]] }
|
|
57
|
+
return [[byte | errorMask], undefined]
|
|
58
|
+
}
|
|
59
|
+
if (byte >= 0b1000_0000 && byte < 0b1100_0000) {
|
|
60
|
+
switch(state.length) {
|
|
61
|
+
case 1:
|
|
62
|
+
if (state[0] < 0b1110_0000) { return [[((state[0] & 0b0001_1111) << 6) + (byte & 0b0011_1111)], undefined] }
|
|
63
|
+
if (state[0] < 0b1111_1000) { return [[], [state[0], byte]] }
|
|
64
|
+
break
|
|
65
|
+
case 2:
|
|
66
|
+
if (state[0] < 0b1111_0000) { return [[((state[0] & 0b0000_1111) << 12) + ((state[1] & 0b0011_1111) << 6) + (byte & 0b0011_1111)], undefined] }
|
|
67
|
+
if (state[0] < 0b1111_1000) { return [[], [state[0], state[1], byte]] }
|
|
68
|
+
break
|
|
69
|
+
case 3:
|
|
70
|
+
return [[((state[0] & 0b0000_0111) << 18) + ((state[1] & 0b0011_1111) << 12) + ((state[2] & 0b0011_1111) << 6) + (byte & 0b0011_1111)], undefined]
|
|
71
|
+
}
|
|
72
|
+
}
|
|
73
|
+
const error = utf8StateToError(state)
|
|
74
|
+
if (byte < 0b1000_0000) { return [[error, byte], undefined] }
|
|
75
|
+
if (byte >= 0b1100_0010 && byte <= 0b1111_0100) { return [[error], [byte]] }
|
|
76
|
+
return [[error, byte | errorMask], undefined]
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
/** @type {(state: Utf8State) => readonly[list.List<i32>, Utf8State]} */
|
|
80
|
+
const utf8EofToCodePointOp = state => {
|
|
81
|
+
if (state === undefined) { return [undefined, undefined] }
|
|
82
|
+
return [[utf8StateToError(state)], undefined]
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
/** @type {operator.StateScan<ByteOrEof, Utf8State, list.List<i32>>} */
|
|
86
|
+
const utf8ByteOrEofToCodePointOp = state => input => input === undefined ? utf8EofToCodePointOp(state) : utf8ByteToCodePointOp(state)(input)
|
|
87
|
+
|
|
88
|
+
/** @type {(input: list.List<u8>) => list.List<i32>} */
|
|
89
|
+
const toCodePointList = input => list.flat(list.stateScan(utf8ByteOrEofToCodePointOp)(undefined)(list.concat(/** @type {list.List<ByteOrEof>} */(input))([undefined])))
|
|
90
|
+
|
|
91
|
+
module.exports = {
|
|
92
|
+
/** @readonly */
|
|
93
|
+
fromCodePointList,
|
|
94
|
+
/** @readonly */
|
|
95
|
+
toCodePointList
|
|
96
|
+
}
|
|
@@ -0,0 +1,144 @@
|
|
|
1
|
+
const encoding = require('./module.f.cjs')
|
|
2
|
+
const json = require('../../../json/module.f.cjs')
|
|
3
|
+
const { sort } = require('../../../types/object/module.f.cjs')
|
|
4
|
+
const { list } = require('../../../types/module.f.cjs')
|
|
5
|
+
|
|
6
|
+
/** @type {(a: readonly json.Unknown[]) => string} */
|
|
7
|
+
const stringify = a => json.stringify(sort)(a)
|
|
8
|
+
|
|
9
|
+
{
|
|
10
|
+
const result = stringify(list.toArray(encoding.toCodePointList([-1, 256])))
|
|
11
|
+
if (result !== '[2147483648,2147483648]') { throw result }
|
|
12
|
+
}
|
|
13
|
+
|
|
14
|
+
{
|
|
15
|
+
const result = stringify(list.toArray(encoding.toCodePointList([128, 193, 245, 255])))
|
|
16
|
+
if (result !== '[-2147483520,-2147483455,-2147483403,-2147483393]') { throw result }
|
|
17
|
+
}
|
|
18
|
+
|
|
19
|
+
{
|
|
20
|
+
const result = stringify(list.toArray(encoding.toCodePointList([0, 1, 127])))
|
|
21
|
+
if (result !== '[0,1,127]') { throw result }
|
|
22
|
+
}
|
|
23
|
+
|
|
24
|
+
{
|
|
25
|
+
const result = stringify(list.toArray(encoding.toCodePointList([194, 128, 194, 169, 223, 191])))
|
|
26
|
+
if (result !== '[128,169,2047]') { throw result }
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
{
|
|
30
|
+
const result = stringify(list.toArray(encoding.toCodePointList([194, 194, 127, 194, 192, 194])))
|
|
31
|
+
if (result !== '[-2147483454,-2147483454,127,-2147483454,-2147483456,-2147483454]') { throw result }
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
{
|
|
35
|
+
const result = stringify(list.toArray(encoding.toCodePointList([224, 160, 128, 224, 160, 129, 239, 191, 191])))
|
|
36
|
+
if (result !== '[2048,2049,65535]') { throw result }
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
{
|
|
40
|
+
const result = stringify(list.toArray(encoding.toCodePointList([224, 224, 160, 127, 239, 191])))
|
|
41
|
+
if (result !== '[-2147483424,-2147482592,127,-2147481601]') { throw result }
|
|
42
|
+
}
|
|
43
|
+
|
|
44
|
+
{
|
|
45
|
+
const result = stringify(list.toArray(encoding.toCodePointList([240, 144, 128, 128, 240, 144, 128, 129, 244, 143, 191, 191])))
|
|
46
|
+
if (result !== '[65536,65537,1114111]') { throw result }
|
|
47
|
+
}
|
|
48
|
+
|
|
49
|
+
{
|
|
50
|
+
const result = stringify(list.toArray(encoding.toCodePointList([240, 240, 160, 127, 244, 191])))
|
|
51
|
+
if (result !== '[-2147483408,-2147483104,127,-2147482817]') { throw result }
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
{
|
|
55
|
+
const result = stringify(list.toArray(encoding.toCodePointList([240, 160, 160, 244, 160, 160])))
|
|
56
|
+
if (result !== '[-2147448800,-2147432416]') { throw result }
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
{
|
|
60
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0,1,0x7F])))
|
|
61
|
+
if (result !== '[0,1,127]') { throw result }
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
{
|
|
65
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x80])))
|
|
66
|
+
if (result !== '[194,128]') { throw result }
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
{
|
|
70
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0xa9])))
|
|
71
|
+
if (result !== '[194,169]') { throw result }
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
{
|
|
75
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x7ff])))
|
|
76
|
+
if (result !== '[223,191]') { throw result }
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
{
|
|
80
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x800])))
|
|
81
|
+
if (result !== '[224,160,128]') { throw result }
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
{
|
|
85
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x801])))
|
|
86
|
+
if (result !== '[224,160,129]') { throw result }
|
|
87
|
+
}
|
|
88
|
+
|
|
89
|
+
{
|
|
90
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0xffff])))
|
|
91
|
+
if (result !== '[239,191,191]') { throw result }
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
{
|
|
95
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10000])))
|
|
96
|
+
if (result !== '[240,144,128,128]') { throw result }
|
|
97
|
+
}
|
|
98
|
+
|
|
99
|
+
{
|
|
100
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10001])))
|
|
101
|
+
if (result !== '[240,144,128,129]') { throw result }
|
|
102
|
+
}
|
|
103
|
+
|
|
104
|
+
{
|
|
105
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x10FFFF])))
|
|
106
|
+
if (result !== '[244,143,191,191]') { throw result }
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
{
|
|
110
|
+
const result = stringify(list.toArray(encoding.fromCodePointList([0x110000,2147483648])))
|
|
111
|
+
if (result !== '[2147483648,2147483648]') { throw result }
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
{
|
|
115
|
+
const codePointList = encoding.toCodePointList([128, 193, 245, 255])
|
|
116
|
+
const result = stringify(list.toArray(encoding.fromCodePointList(codePointList)))
|
|
117
|
+
if (result !== '[128,193,245,255]') { throw result }
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
{
|
|
121
|
+
const codePointList = encoding.toCodePointList([194, 194, 127, 194, 192, 194])
|
|
122
|
+
const result = stringify(list.toArray(encoding.fromCodePointList(codePointList)))
|
|
123
|
+
if (result !== '[194,194,127,194,192,194]') { throw result }
|
|
124
|
+
}
|
|
125
|
+
|
|
126
|
+
{
|
|
127
|
+
const codePointList = encoding.toCodePointList([224, 224, 160, 127, 239, 191])
|
|
128
|
+
const result = stringify(list.toArray(encoding.fromCodePointList(codePointList)))
|
|
129
|
+
if (result !== '[224,224,160,127,239,191]') { throw result }
|
|
130
|
+
}
|
|
131
|
+
|
|
132
|
+
{
|
|
133
|
+
const codePointList = encoding.toCodePointList([240, 240, 160, 127, 244, 191])
|
|
134
|
+
const result = stringify(list.toArray(encoding.fromCodePointList(codePointList)))
|
|
135
|
+
if (result !== '[240,240,160,127,244,191]') { throw result }
|
|
136
|
+
}
|
|
137
|
+
|
|
138
|
+
{
|
|
139
|
+
const codePointList = encoding.toCodePointList([240, 160, 160, 244, 160, 160])
|
|
140
|
+
const result = stringify(list.toArray(encoding.fromCodePointList(codePointList)))
|
|
141
|
+
if (result !== '[240,160,160,244,160,160]') { throw result }
|
|
142
|
+
}
|
|
143
|
+
|
|
144
|
+
module.exports = {}
|
|
@@ -1,154 +0,0 @@
|
|
|
1
|
-
const result = require('../../types/result/module.f.cjs')
|
|
2
|
-
const list = require('../../types/list/module.f.cjs')
|
|
3
|
-
const operator = require('../../types/function/operator/module.f.cjs')
|
|
4
|
-
const array = require('../../types/array/module.f.cjs')
|
|
5
|
-
const { contains } = require('../../types/range/module.f.cjs')
|
|
6
|
-
const { compose } = require('../../types/function/module.f.cjs')
|
|
7
|
-
const { map, flat, stateScan, concat, reduce, toArray, flatMap } = list
|
|
8
|
-
const { ok, error } = result
|
|
9
|
-
|
|
10
|
-
/** @typedef {result.Result<number,number>} ByteResult */
|
|
11
|
-
|
|
12
|
-
/** @typedef {result.Result<number,readonly number[]>} CodePointResult */
|
|
13
|
-
|
|
14
|
-
/** @typedef {number|undefined} ByteOrEof */
|
|
15
|
-
|
|
16
|
-
/** @typedef {u16|undefined} WordOrEof */
|
|
17
|
-
|
|
18
|
-
/** @typedef {undefined|array.Array1<number>|array.Array2<number>|array.Array3<number>} Utf8State */
|
|
19
|
-
|
|
20
|
-
/** @typedef {undefined|number} Utf16State */
|
|
21
|
-
|
|
22
|
-
/** @typedef {number} u16 */
|
|
23
|
-
|
|
24
|
-
/** @typedef {number} i32 */
|
|
25
|
-
|
|
26
|
-
/** @type {(a:number) => boolean} */
|
|
27
|
-
const isBmpCodePoint = a => a >= 0x0000 && a <= 0xd7ff || a >= 0xe000 && a <= 0xffff
|
|
28
|
-
|
|
29
|
-
const isHighSurrogate = contains([0xd800, 0xdbff])
|
|
30
|
-
|
|
31
|
-
/** @type {(a:number) => boolean} */
|
|
32
|
-
const isLowSurrogate = contains([0xdc00, 0xdfff])
|
|
33
|
-
|
|
34
|
-
const errorMask = 0b1000_0000_0000_0000_0000_0000_0000_0000
|
|
35
|
-
|
|
36
|
-
/** @type {(input:number) => list.List<ByteResult>} */
|
|
37
|
-
const codePointToUtf8 = input =>
|
|
38
|
-
{
|
|
39
|
-
if (input >= 0x0000 && input <= 0x007f) { return [ok(input & 0x7f)] }
|
|
40
|
-
if (input >= 0x0080 && input <= 0x07ff) { return [ok(input >> 6 | 0xc0), ok(input & 0x3f | 0x80)] }
|
|
41
|
-
if (input >= 0x0800 && input <= 0xffff) { return [ok(input >> 12 | 0xe0), ok(input >> 6 & 0x3f | 0x80), ok(input & 0x3f | 0x80)] }
|
|
42
|
-
if (input >= 0x10000 && input <= 0x10ffff) { return [ok(input >> 18 | 0xf0), ok(input >> 12 & 0x3f | 0x80), ok(input >> 6 & 0x3f | 0x80), ok(input & 0x3f | 0x80)] }
|
|
43
|
-
return [error(input)]
|
|
44
|
-
}
|
|
45
|
-
|
|
46
|
-
/** @type {(input:i32) => list.List<u16>} */
|
|
47
|
-
const codePointToUtf16 = input =>
|
|
48
|
-
{
|
|
49
|
-
if (isBmpCodePoint(input)) { return [input] }
|
|
50
|
-
if (input >= 0x010000 && input <= 0x10ffff) {
|
|
51
|
-
const high = ((input - 0x10000) >> 10) + 0xd800
|
|
52
|
-
const low = ((input - 0x10000) & 0b0011_1111_1111) + 0xdc00
|
|
53
|
-
return [high, low]
|
|
54
|
-
}
|
|
55
|
-
return [input & 0xffff]
|
|
56
|
-
}
|
|
57
|
-
|
|
58
|
-
const codePointListToUtf8List = flatMap(codePointToUtf8)
|
|
59
|
-
|
|
60
|
-
const codePointListToUtf16List = flatMap(codePointToUtf16)
|
|
61
|
-
|
|
62
|
-
/** @type {operator.StateScan<number, Utf8State, list.List<CodePointResult>>} */
|
|
63
|
-
const utf8ByteToCodePointOp = state => byte => {
|
|
64
|
-
if (byte < 0x00 || byte > 0xff) {
|
|
65
|
-
return [[error([byte])], state]
|
|
66
|
-
}
|
|
67
|
-
if (state == undefined) {
|
|
68
|
-
if (byte < 0x80) { return [[ok(byte)], undefined] }
|
|
69
|
-
if (byte >= 0xc2 && byte <= 0xf4) { return [[], [byte]] }
|
|
70
|
-
return [[error([byte])], undefined]
|
|
71
|
-
}
|
|
72
|
-
if (byte >= 0x80 && byte < 0xc0)
|
|
73
|
-
{
|
|
74
|
-
switch(state.length)
|
|
75
|
-
{
|
|
76
|
-
case 1:
|
|
77
|
-
if (state[0] < 0xe0) { return [[ok(((state[0] & 0x1f) << 6) + (byte & 0x3f))], undefined] }
|
|
78
|
-
if (state[0] < 0xf8) { return [[], [state[0], byte]] }
|
|
79
|
-
break
|
|
80
|
-
case 2:
|
|
81
|
-
if (state[0] < 0xf0) { return [[ok(((state[0] & 0x0f) << 12) + ((state[1] & 0x3f) << 6) + (byte & 0x3f))], undefined] }
|
|
82
|
-
if (state[0] < 0xf8) { return [[], [state[0], state[1], byte]] }
|
|
83
|
-
break
|
|
84
|
-
case 3:
|
|
85
|
-
return [[ok(((state[0] & 0x07) << 18) + ((state[1] & 0x3f) << 12) + ((state[2] & 0x3f) << 6) + (byte & 0x3f))], undefined]
|
|
86
|
-
}
|
|
87
|
-
}
|
|
88
|
-
return [[error(toArray(concat(state)([byte])))], undefined]
|
|
89
|
-
}
|
|
90
|
-
|
|
91
|
-
/** @type {(state: Utf8State) => readonly[list.List<CodePointResult>, Utf8State]} */
|
|
92
|
-
const utf8EofToCodePointOp = state => [state === undefined ? undefined : [error(state)], undefined]
|
|
93
|
-
|
|
94
|
-
/** @type {operator.StateScan<ByteOrEof, Utf8State, list.List<CodePointResult>>} */
|
|
95
|
-
const utf8ByteOrEofToCodePointOp = state => input => input === undefined ? utf8EofToCodePointOp(state) : utf8ByteToCodePointOp(state)(input)
|
|
96
|
-
|
|
97
|
-
/** @type {(input: list.List<number>) => list.List<CodePointResult>} */
|
|
98
|
-
const utf8ListToCodePointList = input => flat(stateScan(utf8ByteOrEofToCodePointOp)(undefined)(concat(/** @type {list.List<ByteOrEof>} */(input))([undefined])))
|
|
99
|
-
|
|
100
|
-
/** @type {operator.StateScan<u16, Utf16State, list.List<i32>>} */
|
|
101
|
-
const utf16ByteToCodePointOp = state => byte => {
|
|
102
|
-
if (byte < 0x00 || byte > 0xffff) {
|
|
103
|
-
return [[0xffffffff], state]
|
|
104
|
-
}
|
|
105
|
-
if (state === undefined) {
|
|
106
|
-
if (isBmpCodePoint(byte)) { return [[byte], undefined] }
|
|
107
|
-
if (isHighSurrogate(byte)) { return [[], byte] }
|
|
108
|
-
return [[byte | errorMask], undefined]
|
|
109
|
-
}
|
|
110
|
-
if (isLowSurrogate(byte)) {
|
|
111
|
-
const high = state - 0xd800
|
|
112
|
-
const low = byte - 0xdc00
|
|
113
|
-
return [[(high << 10) + low + 0x10000], undefined]
|
|
114
|
-
}
|
|
115
|
-
if (isBmpCodePoint(byte)) { return [[state | errorMask, byte], undefined] }
|
|
116
|
-
if (isHighSurrogate(byte)) { return [[state | errorMask], byte] }
|
|
117
|
-
return [[state | errorMask, byte | errorMask], undefined]
|
|
118
|
-
}
|
|
119
|
-
|
|
120
|
-
/** @type {(state: Utf16State) => readonly[list.List<i32>, Utf16State]} */
|
|
121
|
-
const utf16EofToCodePointOp = state => [state === undefined ? undefined : [state | errorMask], undefined]
|
|
122
|
-
|
|
123
|
-
/** @type {operator.StateScan<WordOrEof, Utf16State, list.List<i32>>} */
|
|
124
|
-
const utf16ByteOrEofToCodePointOp = state => input => input === undefined ? utf16EofToCodePointOp(state) : utf16ByteToCodePointOp(state)(input)
|
|
125
|
-
|
|
126
|
-
/** @type {(input: list.List<u16>) => list.List<i32>} */
|
|
127
|
-
const utf16ListToCodePointList = input => flat(stateScan(utf16ByteOrEofToCodePointOp)(undefined)(concat(/** @type {list.List<WordOrEof>} */(input))([undefined])))
|
|
128
|
-
|
|
129
|
-
/** @type {(s: string) => list.List<u16>} */
|
|
130
|
-
const stringToUtf16List = s => {
|
|
131
|
-
/** @type {(i: number) => list.Result<number>} */
|
|
132
|
-
const at = i => {
|
|
133
|
-
const first = s.charCodeAt(i)
|
|
134
|
-
return isNaN(first) ? undefined : { first, tail: () => at(i + 1) }
|
|
135
|
-
}
|
|
136
|
-
return at(0)
|
|
137
|
-
}
|
|
138
|
-
|
|
139
|
-
const utf16ListToString = compose(map(String.fromCharCode))(reduce(operator.concat)(''))
|
|
140
|
-
|
|
141
|
-
module.exports = {
|
|
142
|
-
/** @readonly */
|
|
143
|
-
codePointListToUtf8List,
|
|
144
|
-
/** @readonly */
|
|
145
|
-
codePointListToUtf16List,
|
|
146
|
-
/** @readonly */
|
|
147
|
-
utf8ListToCodePointList,
|
|
148
|
-
/** @readonly */
|
|
149
|
-
utf16ListToCodePointList,
|
|
150
|
-
/** @readonly */
|
|
151
|
-
stringToUtf16List,
|
|
152
|
-
/** @readonly */
|
|
153
|
-
utf16ListToString
|
|
154
|
-
}
|
package/text/encoding/test.f.cjs
DELETED
|
@@ -1,223 +0,0 @@
|
|
|
1
|
-
const encoding = require('./module.f.cjs')
|
|
2
|
-
const json = require('../../json/module.f.cjs')
|
|
3
|
-
const { sort } = require('../../types/object/module.f.cjs')
|
|
4
|
-
const { list } = require('../../types/module.f.cjs')
|
|
5
|
-
|
|
6
|
-
/** @type {(a: readonly json.Unknown[]) => string} */
|
|
7
|
-
const stringify = a => json.stringify(sort)(a)
|
|
8
|
-
|
|
9
|
-
{
|
|
10
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0,1,0x7F])))
|
|
11
|
-
if (result !== '[["ok",0],["ok",1],["ok",127]]') { throw result }
|
|
12
|
-
}
|
|
13
|
-
|
|
14
|
-
{
|
|
15
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x80])))
|
|
16
|
-
if (result !== '[["ok",194],["ok",128]]') { throw result }
|
|
17
|
-
}
|
|
18
|
-
|
|
19
|
-
{
|
|
20
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0xa9])))
|
|
21
|
-
if (result !== '[["ok",194],["ok",169]]') { throw result }
|
|
22
|
-
}
|
|
23
|
-
|
|
24
|
-
{
|
|
25
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x7ff])))
|
|
26
|
-
if (result !== '[["ok",223],["ok",191]]') { throw result }
|
|
27
|
-
}
|
|
28
|
-
|
|
29
|
-
{
|
|
30
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x800])))
|
|
31
|
-
if (result !== '[["ok",224],["ok",160],["ok",128]]') { throw result }
|
|
32
|
-
}
|
|
33
|
-
|
|
34
|
-
{
|
|
35
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x801])))
|
|
36
|
-
if (result !== '[["ok",224],["ok",160],["ok",129]]') { throw result }
|
|
37
|
-
}
|
|
38
|
-
|
|
39
|
-
{
|
|
40
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0xffff])))
|
|
41
|
-
if (result !== '[["ok",239],["ok",191],["ok",191]]') { throw result }
|
|
42
|
-
}
|
|
43
|
-
|
|
44
|
-
{
|
|
45
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x10000])))
|
|
46
|
-
if (result !== '[["ok",240],["ok",144],["ok",128],["ok",128]]') { throw result }
|
|
47
|
-
}
|
|
48
|
-
|
|
49
|
-
{
|
|
50
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x10001])))
|
|
51
|
-
if (result !== '[["ok",240],["ok",144],["ok",128],["ok",129]]') { throw result }
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
{
|
|
55
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([0x10FFFF])))
|
|
56
|
-
if (result !== '[["ok",244],["ok",143],["ok",191],["ok",191]]') { throw result }
|
|
57
|
-
}
|
|
58
|
-
|
|
59
|
-
{
|
|
60
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf8List([-1,0x110000])))
|
|
61
|
-
if (result !== '[["error",-1],["error",1114112]]') { throw result }
|
|
62
|
-
}
|
|
63
|
-
|
|
64
|
-
{
|
|
65
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0])))
|
|
66
|
-
if (result !== '[0]') { throw result }
|
|
67
|
-
}
|
|
68
|
-
|
|
69
|
-
{
|
|
70
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x24])))
|
|
71
|
-
if (result !== '[36]') { throw result }
|
|
72
|
-
}
|
|
73
|
-
|
|
74
|
-
{
|
|
75
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x20AC])))
|
|
76
|
-
if (result !== '[8364]') { throw result }
|
|
77
|
-
}
|
|
78
|
-
|
|
79
|
-
{
|
|
80
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0xd7ff])))
|
|
81
|
-
if (result !== '[55295]') { throw result }
|
|
82
|
-
}
|
|
83
|
-
|
|
84
|
-
{
|
|
85
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0xe000])))
|
|
86
|
-
if (result !== '[57344]') { throw result }
|
|
87
|
-
}
|
|
88
|
-
|
|
89
|
-
{
|
|
90
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0xffff])))
|
|
91
|
-
if (result !== '[65535]') { throw result }
|
|
92
|
-
}
|
|
93
|
-
|
|
94
|
-
{
|
|
95
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x10000])))
|
|
96
|
-
if (result !== '[55296,56320]') { throw result }
|
|
97
|
-
}
|
|
98
|
-
|
|
99
|
-
{
|
|
100
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x10437])))
|
|
101
|
-
if (result !== '[55297,56375]') { throw result }
|
|
102
|
-
}
|
|
103
|
-
|
|
104
|
-
{
|
|
105
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x24B62])))
|
|
106
|
-
if (result !== '[55378,57186]') { throw result }
|
|
107
|
-
}
|
|
108
|
-
|
|
109
|
-
{
|
|
110
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([0x10ffff])))
|
|
111
|
-
if (result !== '[56319,57343]') { throw result }
|
|
112
|
-
}
|
|
113
|
-
|
|
114
|
-
{
|
|
115
|
-
const result = stringify(list.toArray(encoding.codePointListToUtf16List([-1, 0xd800, 0xdfff, 0x110000])))
|
|
116
|
-
if (result !== '[65535,55296,57343,0]') { throw result }
|
|
117
|
-
}
|
|
118
|
-
|
|
119
|
-
{
|
|
120
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([-1, 256])))
|
|
121
|
-
if (result !== '[["error",[-1]],["error",[256]]]') { throw result }
|
|
122
|
-
}
|
|
123
|
-
|
|
124
|
-
{
|
|
125
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([128, 193, 245, 255])))
|
|
126
|
-
if (result !== '[["error",[128]],["error",[193]],["error",[245]],["error",[255]]]') { throw result }
|
|
127
|
-
}
|
|
128
|
-
|
|
129
|
-
{
|
|
130
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([0, 1, 127])))
|
|
131
|
-
if (result !== '[["ok",0],["ok",1],["ok",127]]') { throw result }
|
|
132
|
-
}
|
|
133
|
-
|
|
134
|
-
{
|
|
135
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([194, 128, 194, 169, 223, 191])))
|
|
136
|
-
if (result !== '[["ok",128],["ok",169],["ok",2047]]') { throw result }
|
|
137
|
-
}
|
|
138
|
-
|
|
139
|
-
{
|
|
140
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([194, 127, 194, 192, 194])))
|
|
141
|
-
if (result !== '[["error",[194,127]],["error",[194,192]],["error",[194]]]') { throw result }
|
|
142
|
-
}
|
|
143
|
-
|
|
144
|
-
{
|
|
145
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([224, 160, 128, 224, 160, 129, 239, 191, 191])))
|
|
146
|
-
if (result !== '[["ok",2048],["ok",2049],["ok",65535]]') { throw result }
|
|
147
|
-
}
|
|
148
|
-
|
|
149
|
-
{
|
|
150
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([224, 160, 127, 224, 160, 192, 224, 160])))
|
|
151
|
-
if (result !== '[["error",[224,160,127]],["error",[224,160,192]],["error",[224,160]]]') { throw result }
|
|
152
|
-
}
|
|
153
|
-
|
|
154
|
-
{
|
|
155
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([240, 144, 128, 128, 240, 144, 128, 129, 244, 143, 191, 191])))
|
|
156
|
-
if (result !== '[["ok",65536],["ok",65537],["ok",1114111]]') { throw result }
|
|
157
|
-
}
|
|
158
|
-
|
|
159
|
-
{
|
|
160
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([240, 144, 128, 127, 240, 144, 128, 192, 240, 144, 128])))
|
|
161
|
-
if (result !== '[["error",[240,144,128,127]],["error",[240,144,128,192]],["error",[240,144,128]]]') { throw result }
|
|
162
|
-
}
|
|
163
|
-
|
|
164
|
-
{
|
|
165
|
-
const result = stringify(list.toArray(encoding.utf8ListToCodePointList([194, -1, 128])))
|
|
166
|
-
if (result !== '[["error",[-1]],["ok",128]]') { throw result }
|
|
167
|
-
}
|
|
168
|
-
|
|
169
|
-
{
|
|
170
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([-1, 65536])))
|
|
171
|
-
if (result !== '[4294967295,4294967295]') { throw result }
|
|
172
|
-
}
|
|
173
|
-
|
|
174
|
-
{
|
|
175
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([0, 36, 8364, 55295, 57344, 65535])))
|
|
176
|
-
if (result !== '[0,36,8364,55295,57344,65535]') { throw result }
|
|
177
|
-
}
|
|
178
|
-
|
|
179
|
-
{
|
|
180
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([56320, 57343])))
|
|
181
|
-
if (result !== '[-2147427328,-2147426305]') { throw result }
|
|
182
|
-
}
|
|
183
|
-
|
|
184
|
-
{
|
|
185
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([55296, 56320, 55297, 56375, 55378, 57186, 56319, 57343])))
|
|
186
|
-
if (result !== '[65536,66615,150370,1114111]') { throw result }
|
|
187
|
-
}
|
|
188
|
-
|
|
189
|
-
{
|
|
190
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([55296, 55296])))
|
|
191
|
-
if (result !== '[-2147428352,-2147428352]') { throw result }
|
|
192
|
-
}
|
|
193
|
-
|
|
194
|
-
{
|
|
195
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([55296, 0])))
|
|
196
|
-
if (result !== '[-2147428352,0]') { throw result }
|
|
197
|
-
}
|
|
198
|
-
|
|
199
|
-
{
|
|
200
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([56320])))
|
|
201
|
-
if (result !== '[-2147427328]') { throw result }
|
|
202
|
-
}
|
|
203
|
-
|
|
204
|
-
{
|
|
205
|
-
const result = stringify(list.toArray(encoding.utf16ListToCodePointList([56320, 0])))
|
|
206
|
-
if (result !== '[-2147427328,0]') { throw result }
|
|
207
|
-
}
|
|
208
|
-
|
|
209
|
-
{
|
|
210
|
-
const utf16List = encoding.stringToUtf16List("Hello world!😂🚜🚲")
|
|
211
|
-
const result = encoding.utf16ListToString(utf16List)
|
|
212
|
-
if (result !== "Hello world!😂🚜🚲") { throw result }
|
|
213
|
-
}
|
|
214
|
-
|
|
215
|
-
{
|
|
216
|
-
const a = encoding.stringToUtf16List("Hello world!😂🚜🚲")
|
|
217
|
-
const b = encoding.utf16ListToCodePointList(a)
|
|
218
|
-
const c = encoding.codePointListToUtf16List(b)
|
|
219
|
-
const result = encoding.utf16ListToString(c)
|
|
220
|
-
if (result !== "Hello world!😂🚜🚲") { throw result }
|
|
221
|
-
}
|
|
222
|
-
|
|
223
|
-
module.exports = {}
|