functionalscript 0.0.383 → 0.0.386

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.
Files changed (3) hide show
  1. package/doc/vm.md +165 -0
  2. package/package.json +1 -1
  3. package/text/encoding/README.md +39 -29
package/doc/vm.md ADDED
@@ -0,0 +1,165 @@
1
+ # VM
2
+
3
+ [Tagged Pointer](https://en.wikipedia.org/wiki/Tagged_pointer).
4
+
5
+ ## Common (3 bit)
6
+
7
+ - `false`
8
+ - `true`
9
+ - `undefined`
10
+ - `""`
11
+ - `+infinity`
12
+ - `-infinity`
13
+ - `-0`
14
+ - `NaN`
15
+
16
+ ## 6-bit Id String
17
+
18
+ |symbol |code |# |sum|
19
+ |--------|--------------|--|---|
20
+ |`$` |`\x24` | 1| 1|
21
+ |`0`..`9`|`\x30`..`\x39`| A| B|
22
+ |`A`..`Z`|`\x41`..`\x5A`|1A| 25|
23
+ |`_` |`\x5F` | 1| 26|
24
+ |`a`..`z`|`\x61`..`\x7A`|1A| 40|
25
+
26
+ ## 64 bit platform
27
+
28
+ Alignment: 8 bytes.
29
+
30
+ Pointer: 2^64 / 2^3 = 2^61 bit
31
+
32
+ ### Value
33
+
34
+ - `63`: 9 x 7 bit string
35
+ - `63`:
36
+ - `61`: pointer + null, alignment - 8 bytes
37
+ - `61`:
38
+ - `60`: 4 x 15 bit string
39
+ - `60`: 10 x 6 bit string
40
+ - `61`:
41
+ - `60`: 6 x 10 bit string
42
+ - `60`: 5 x 12 bit string
43
+ - `61`
44
+ - `60`: float60
45
+ - `60`:
46
+ - `59`: bigInt59 (-576_460_752_303_423_488..576_460_752_303_423_487)
47
+ - `59`:
48
+ - `56`: 8 x 7-bit string
49
+ - `56`: 7 x 8-bit string
50
+ - `53`: int53
51
+ - `53`: stringUInt53
52
+ - `48`: 3 x 16 bit string
53
+ - `32`: 2 x 16 bit string
54
+ - `16`: 1 x UTF16 string
55
+ - `3`: common
56
+
57
+ ## Float64
58
+
59
+ https://en.wikipedia.org/wiki/Double-precision_floating-point_format
60
+
61
+ - 1 bit - sign (S)
62
+ - 11 bit - exponent (E)
63
+ - 52 bit - fraction (F)
64
+
65
+ |E |Description |
66
+ |-------------|------------------------|
67
+ |000_0000_0000|F = 0: signed zeros |
68
+ | |F != 0: subnormals |
69
+ |000_0000_0001|E = 2^-1022 |
70
+ |... | |
71
+ |011_1111_1111|E = 2^0 |
72
+ |100_0000_0000|E = 2^1 |
73
+ |... | |
74
+ |111_1111_1110|E = 2^1023 |
75
+ |111_1111_1111|F = 0: signed infinities|
76
+ | |F != 0: NaN |
77
+
78
+ ## Float60
79
+
80
+ - 1 bit - sign
81
+ - 7 bit - exponent
82
+ - 52 bit - fraction
83
+
84
+ |E |Description|
85
+ |--------|-----------|
86
+ |000_0000|E = 2^-63 |
87
+ |... | |
88
+ |011_1111|E = 2^0 |
89
+ |100_0000|E = 2^1 |
90
+ |... | |
91
+ |111_1111|E = 2^64 |
92
+
93
+ Note: the type has no `+0`, `-0`, `+inf`, `-inf`, `NaN`.
94
+
95
+ ## Object Structure
96
+
97
+ Value Size = 8
98
+ Counter size = max_memory_size / value_size.
99
+
100
+ ### Type
101
+
102
+ - `000`: double
103
+ - `001`: string
104
+ - `010`: array
105
+ - `011`: object
106
+ - `100`: bigInt
107
+ - `101`: function
108
+ - `110`:
109
+ - `111`:
110
+
111
+ ### Type & Counter
112
+
113
+ - AtomicUSize:
114
+ - `3`: type
115
+ - `...`: counter
116
+
117
+ ### String
118
+
119
+ ```rust
120
+ struct String {
121
+ length: u32,
122
+ array: [u16; self.length],
123
+ }
124
+ ```
125
+
126
+ ### Function
127
+
128
+ ```rust
129
+ struct Function<length: u32> {
130
+ func: pointer,
131
+ array: [value; length]
132
+ }
133
+ ```
134
+
135
+ ### BigInt
136
+
137
+ ```rust
138
+ struct BigInt {
139
+ length: u32,
140
+ array: [u64; self.length],
141
+ }
142
+ ```
143
+
144
+ ### Array
145
+
146
+ ```rust
147
+ struct Array {
148
+ length: u32,
149
+ array: [Value; self.length],
150
+ }
151
+ ```
152
+
153
+ ### Object
154
+
155
+ ```rust
156
+ struct Object {
157
+ length: u32,
158
+ array: [(Value, Value), self.length],
159
+ indexArray: [u32, (self.length * log2(self.length) + 31) / u32],
160
+ }
161
+ ```
162
+
163
+ Note: see https://262.ecma-international.org/6.0/#sec-ordinary-object-internal-methods-and-internal-slots-ownpropertykeys and https://262.ecma-international.org/6.0/#sec-object-type
164
+
165
+ An integer index for Node.js, Deno and Bun means a value from `0` to `4294967294` including. 4_294_967_294 = 0xFFFF_FFFE. But an integer index in the ES6 standard is +0..2^53-1.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "functionalscript",
3
- "version": "0.0.383",
3
+ "version": "0.0.386",
4
4
  "description": "FunctionalScript is a functional subset of JavaScript",
5
5
  "main": "module.f.cjs",
6
6
  "scripts": {
package/text/encoding/README.md CHANGED
@@ -4,34 +4,14 @@
4
4
 
5
5
  Requirement: no loss for UTF8 => codepoint => UTF8
6
6
 
7
- |utf8 |codepoint |size |
8
- |---------|---------------------------------------|---------|
9
- |[a] |0xxx_xxxx |7 bit |
10
- |[b,a] |110x_xxxx 10xx_xxxx |11 bit |
11
- |[c,b,a] |1110_xxxx 10xx_xxxx 10xx_xxxx |16 bit |
12
- |[d,c,b,a]|1111_0xxx 10xx_xxxx 10xx_xxxx 10xx_xxxx|21 bit |
13
-
14
- |utf8 error|codepoint |size |
15
- |----------|-----------------------------|------|
16
- |[e] |10xx_xxxx |6 bit |
17
- |[e] |1111_1xxx |3 bit |
18
- |[b,] |110x_xxxx |5 bit |
19
- |[c,] |1110_xxxx |4 bit |
20
- |[c,b,] |1110_xxxx 10xx_xxxx |10 bit|
21
- |[d,] |1111_0xxx |3 bit |
22
- |[d,c,] |1111_0xxx 10xx_xxxx |9 bit |
23
- |[d,c,b,] |1111_0xxx 10xx_xxxx 10xx_xxxx|15 bit|
24
-
25
- Total error states:
26
-
27
- - 2^6 + 2^3 + 2^5 + 2^4 + 2^10 + 2^3 + + 2^9 + 2^15
28
- - 2^4 + 2^6 + 2^5 + 2^4 + 2^10 + 2^9 + 2^15
29
- - 2^5 + 2^6 + 2^5 + 2^10 + 2^9 + 2^15
30
- - 2^6 + 2^6 + 2^10 + 2^9 + 2^15
31
- - 2^7 + 2^9 + 2^10 + 2^15
32
- - < 2^16
33
-
34
- |utf8 error|codepoint |size |map |
7
+ |utf8 |codepoint |size |codepoint |
8
+ |---------|---------------------------------------|---------|--------------------------------------------------|
9
+ |[a] |0xxx_xxxx |7 bit |0_0000_0000_0000_0xxx_xxxx |
10
+ |[b,a] |110x_xxxx 10xx_xxxx |11 bit |0_0000_0000_0xxx_xxxx_xxxx + 0_0000_0000_1000_0000|
11
+ |[c,b,a] |1110_xxxx 10xx_xxxx 10xx_xxxx |16 bit |0_0000_xxxx_xxxx_xxxx_xxxx + 0_0000_1000_0000_0000|
12
+ |[d,c,b,a]|1111_0xxx 10xx_xxxx 10xx_xxxx 10xx_xxxx|21 bit |x_xxxx_xxxx_xxxx_xxxx_xxxx + 1_0000_0000_0000_0000|
13
+
14
+ |utf8 error| |size |codepoint |
35
15
  |----------|-----------------------------|------|-------------------|
36
16
  |[e] |1111_1xxx | 3 bit| |
37
17
  |[d,] |1111_0xxx | 3 bit| |
@@ -42,6 +22,18 @@ Total error states:
42
22
  |[c,b,] |1110_xxxx 10xx_xxxx |10 bit|0000_01xx xxxx_xxxx|
43
23
  |[d,c,b,] |1111_0xxx 10xx_xxxx 10xx_xxxx|15 bit|1xxx_xxxx xxxx_xxxx|
44
24
 
25
+ Total error states:
26
+
27
+ - 2^6 + 2^3 + 2^5 + 2^4 + 2^10 + 2^3 + + 2^9 + 2^15
28
+ - 2^4 + 2^6 + 2^5 + 2^4 + 2^10 + 2^9 + 2^15
29
+ - 2^5 + 2^6 + 2^5 + 2^10 + 2^9 + 2^15
30
+ - 2^6 + 2^6 + 2^10 + 2^9 + 2^15
31
+ - 2^7 + 2^9 + 2^10 + 2^15
32
+ - 0b1000_0110_1000_000
33
+ - 128 + 512 + 1024 + 32_768
34
+ - 34_432
35
+ - < 2^16
36
+
45
37
  ```js
46
38
  /** @type {(input: List<u8|undefined>) => List<i32>} */
47
39
  const utf8ToCodePoint
@@ -93,4 +85,22 @@ UTF-16 => CP => UTF-8 => CP = UTF-16
93
85
 
94
86
  ## Example
95
87
 
96
- UTF-8: 1101_11xx_xxxx_xxxx 1101_11xx_xxxx_xxxx
88
+ - UTF-16:
89
+ - 1101_11xx_xxxx_xxxx
90
+ - 1101_11xx_xxxx_xxxx
91
+ - CP:
92
+ - 1000_0000_0000_0000_1101_11xx_xxxx_xxxx
93
+ - 1000_0000_0000_0000_1101_11xx_xxxx_xxxx
94
+ - UTF-8:
95
+ - 1111_0.101
96
+ - 10.11_xxxx
97
+ - 10xx_xxxx
98
+ - 1111_0.101
99
+ - 10.11_xxxx
100
+ - 10xx_xxxx
101
+ - CP:
102
+ - 1000_0000_0000_0000_1101_11xx_xxxx_xxxx
103
+ - 1000_0000_0000_0000_1101_11xx_xxxx_xxxx
104
+ - UTF-16:
105
+ - 1101_11xx_xxxx_xxxx
106
+ - 1101_11xx_xxxx_xxxx