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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
package yaml
const (
// The size of the input raw buffer.
input_raw_buffer_size = 512
// The size of the input buffer.
// It should be possible to decode the whole raw buffer.
input_buffer_size = input_raw_buffer_size * 3
// The size of the output buffer.
output_buffer_size = 128
// The size of the output raw buffer.
// It should be possible to encode the whole output buffer.
output_raw_buffer_size = (output_buffer_size*2 + 2)
// The size of other stacks and queues.
initial_stack_size = 16
initial_queue_size = 16
initial_string_size = 16
)
// Check if the character at the specified position is an alphabetical
// character, a digit, '_', or '-'.
func is_alpha(b []byte, i int) bool {
return b[i] >= '0' && b[i] <= '9' || b[i] >= 'A' && b[i] <= 'Z' || b[i] >= 'a' && b[i] <= 'z' || b[i] == '_' || b[i] == '-'
}
// Check if the character at the specified position is a digit.
func is_digit(b []byte, i int) bool {
return b[i] >= '0' && b[i] <= '9'
}
// Get the value of a digit.
func as_digit(b []byte, i int) int {
return int(b[i]) - '0'
}
// Check if the character at the specified position is a hex-digit.
func is_hex(b []byte, i int) bool {
return b[i] >= '0' && b[i] <= '9' || b[i] >= 'A' && b[i] <= 'F' || b[i] >= 'a' && b[i] <= 'f'
}
// Get the value of a hex-digit.
func as_hex(b []byte, i int) int {
bi := b[i]
if bi >= 'A' && bi <= 'F' {
return int(bi) - 'A' + 10
}
if bi >= 'a' && bi <= 'f' {
return int(bi) - 'a' + 10
}
return int(bi) - '0'
}
// Check if the character is ASCII.
func is_ascii(b []byte, i int) bool {
return b[i] <= 0x7F
}
// Check if the character at the start of the buffer can be printed unescaped.
func is_printable(b []byte, i int) bool {
return ((b[i] == 0x0A) || // . == #x0A
(b[i] >= 0x20 && b[i] <= 0x7E) || // #x20 <= . <= #x7E
(b[i] == 0xC2 && b[i+1] >= 0xA0) || // #0xA0 <= . <= #xD7FF
(b[i] > 0xC2 && b[i] < 0xED) ||
(b[i] == 0xED && b[i+1] < 0xA0) ||
(b[i] == 0xEE) ||
(b[i] == 0xEF && // #xE000 <= . <= #xFFFD
!(b[i+1] == 0xBB && b[i+2] == 0xBF) && // && . != #xFEFF
!(b[i+1] == 0xBF && (b[i+2] == 0xBE || b[i+2] == 0xBF))))
}
// Check if the character at the specified position is NUL.
func is_z(b []byte, i int) bool {
return b[i] == 0x00
}
// Check if the beginning of the buffer is a BOM.
func is_bom(b []byte, i int) bool {
return b[0] == 0xEF && b[1] == 0xBB && b[2] == 0xBF
}
// Check if the character at the specified position is space.
func is_space(b []byte, i int) bool {
return b[i] == ' '
}
// Check if the character at the specified position is tab.
func is_tab(b []byte, i int) bool {
return b[i] == '\t'
}
// Check if the character at the specified position is blank (space or tab).
func is_blank(b []byte, i int) bool {
//return is_space(b, i) || is_tab(b, i)
return b[i] == ' ' || b[i] == '\t'
}
// Check if the character at the specified position is a line break.
func is_break(b []byte, i int) bool {
return (b[i] == '\r' || // CR (#xD)
b[i] == '\n' || // LF (#xA)
b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9) // PS (#x2029)
}
func is_crlf(b []byte, i int) bool {
return b[i] == '\r' && b[i+1] == '\n'
}
// Check if the character is a line break or NUL.
func is_breakz(b []byte, i int) bool {
//return is_break(b, i) || is_z(b, i)
return ( // is_break:
b[i] == '\r' || // CR (#xD)
b[i] == '\n' || // LF (#xA)
b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029)
// is_z:
b[i] == 0)
}
// Check if the character is a line break, space, or NUL.
func is_spacez(b []byte, i int) bool {
//return is_space(b, i) || is_breakz(b, i)
return ( // is_space:
b[i] == ' ' ||
// is_breakz:
b[i] == '\r' || // CR (#xD)
b[i] == '\n' || // LF (#xA)
b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029)
b[i] == 0)
}
// Check if the character is a line break, space, tab, or NUL.
func is_blankz(b []byte, i int) bool {
//return is_blank(b, i) || is_breakz(b, i)
return ( // is_blank:
b[i] == ' ' || b[i] == '\t' ||
// is_breakz:
b[i] == '\r' || // CR (#xD)
b[i] == '\n' || // LF (#xA)
b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028)
b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029)
b[i] == 0)
}
// Determine the width of the character.
func width(b byte) int {
// Don't replace these by a switch without first
// confirming that it is being inlined.
if b&0x80 == 0x00 {
return 1
}
if b&0xE0 == 0xC0 {
return 2
}
if b&0xF0 == 0xE0 {
return 3
}
if b&0xF8 == 0xF0 {
return 4
}
return 0
}
|
