functionalscript 0.0.382 → 0.0.385

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 +136 -0
  2. package/package.json +1 -1
  3. package/text/encoding/README.md +42 -28
package/doc/vm.md ADDED
@@ -0,0 +1,136 @@
1
+ # VM
2
+
3
+ ## Tagged Pointers
4
+
5
+ https://en.wikipedia.org/wiki/Tagged_pointer
6
+
7
+ ### Common (3 bit)
8
+
9
+ - `false`
10
+ - `true`
11
+ - `undefined`
12
+ - `""`
13
+ - `-infinity`
14
+ - `+infinity`
15
+ - `-0`
16
+ - `NaN`
17
+
18
+ ### 32 bit platform
19
+
20
+ - `31` bigInt31 (-1_073_741_824..1_073_741_823)
21
+ - `31`:
22
+ - `30`: pointer + null, alignment - 4 bytes.
23
+ - `30`:
24
+ - `29`:
25
+ - `28`: 4 x 7 bit string
26
+ - `28`: 2 x 14 bit string
27
+ - `29`:
28
+ - `28`: int28 (-134_217_728..134_217_727)
29
+ - `28`:
30
+ - `27`: 3 x 9 bit string
31
+ - `20`: a UTF-16 surrogate pair
32
+ - `16`: 1 x 16 bit string
33
+ - `3`: common
34
+
35
+ ### 64 bit platform
36
+
37
+ - `63`: 9 x 7 bit string
38
+ - `63`:
39
+ - `62`:
40
+ - `61`: pointer + null, alignment - 8 bytes
41
+ - `61`: float61
42
+ - `62`:
43
+ - `60`: 6 x 10 bit string
44
+ - `60`: 5 x 12 bit string
45
+ - `60`: 4 x 15 bit string
46
+ - `60`:
47
+ - `59`: bigInt59 (-576_460_752_303_423_488..576_460_752_303_423_487)
48
+ - `59`:
49
+ - `56`: 8 x 7-bit string
50
+ - `56`: 7 x 8-bit string
51
+ - `48`: 3 x 16 bit string
52
+ - `32`: 2 x 16 bit string
53
+ - `32`: int32
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
+ ### Float61
79
+
80
+ - 1 bit - sign
81
+ - 8 bit - exponent
82
+ - 52 bit - fraction
83
+
84
+ |E |Description|
85
+ |---------|-----------|
86
+ |0000_0000|E = 2^-127 |
87
+ |... | |
88
+ |0111_1111|E = 2^0 |
89
+ |1000_0000|E = 2^1 |
90
+ |... | |
91
+ |1111_1111|E = 2^128 |
92
+
93
+ ## Object Structure
94
+
95
+ - type&counter: 32 + float64: 64
96
+ - type&counter: 32 + int32: 32
97
+ - type&counter: 32 + object: len: 32 + payload
98
+ - type&counter: 32 + array: len: 32 + payload
99
+ - type&counter: 32 + function: 32 + 32
100
+ - type&counter: 32 + string: len: 32 + payload
101
+ - type&counter: 32 + bigint: len: 32 + payload
102
+
103
+ minimal size: 64 bit = 8 byte. It means that a number of objects can't be more than 2^(32-3) on 32-bit platform and 2^(64-3) on 64-bit platform.
104
+ counter:
105
+ - 32 - 3 = 29 bit,
106
+ - 64 - 3 = 61 bit.
107
+
108
+ Max length of JS string/array/object can't be bigger that 2^53-1
109
+
110
+ ## Type
111
+
112
+ - 000 float64
113
+ - 001 string
114
+ - 010 object
115
+ - 011 array
116
+ - 100 function
117
+ - 101 bigint
118
+ - 110 int32
119
+ - 111 ...
120
+
121
+ ## Type & counter
122
+
123
+ |field |x32 |x64 |
124
+ |-------|------|------|
125
+ |type |29..31|61..63|
126
+ |counter|0..28 |0..62 |
127
+
128
+ ## Using Pools for small objects
129
+
130
+ |type |size on x32|size on x64|
131
+ |------------|-----------|-----------|
132
+ |float64 |4+8 = 12 |8+8 = 16 |
133
+ |function |4+4 = 8 |8+8 = 16 |
134
+ |int32 |4+4 = 8 |8+4 = 12 |
135
+ |empty object|4+4 = 8 |8+8 = 16 |
136
+ |empty array |4+4 = 8 |8+8 = 16 |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "functionalscript",
3
- "version": "0.0.382",
3
+ "version": "0.0.385",
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
@@ -90,3 +82,25 @@ const utf16ListToString
90
82
  ```
91
83
 
92
84
  UTF-16 => CP => UTF-8 => CP = UTF-16
85
+
86
+ ## Example
87
+
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