-
Notifications
You must be signed in to change notification settings - Fork 0
/
tokenizer.go
267 lines (248 loc) · 7.39 KB
/
tokenizer.go
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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
package json5
import (
"fmt"
"strconv"
"strings"
"unicode"
"unicode/utf8"
)
// TokenType represents different types of JSON5 tokens
type TokenType int
const (
TOKEN_LBRACE TokenType = iota // {
TOKEN_RBRACE // }
TOKEN_LBRACKET // [
TOKEN_RBRACKET // ]
TOKEN_COLON // :
TOKEN_COMMA // ,
TOKEN_STRING // string (quoted or unquoted)
TOKEN_NUMBER // number (including hex)
TOKEN_TRUE // true
TOKEN_FALSE // false
TOKEN_NULL // null
TOKEN_COMMENT // comment
TOKEN_UNKNOWN // unknown
)
// Token represents a JSON5 token with its type and value
type Token struct {
Type TokenType
Value string
}
// isWhitespace checks if a character is a whitespace character
func isWhitespace(ch rune) bool {
return ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r'
}
// isDigit checks if a character is a digit
func isDigit(ch rune) bool {
return '0' <= ch && ch <= '9'
}
// isHexDigit checks if a character is a valid hexadecimal digit
func isHexDigit(ch rune) bool {
return ('0' <= ch && ch <= '9') || ('a' <= ch && ch <= 'f') || ('A' <= ch && ch <= 'F')
}
// isIdentifierStart checks if a character can be the start of an unquoted key
func isIdentifierStart(ch rune) bool {
return unicode.IsLetter(ch) || ch == '_' || ch == '$'
}
// isIdentifierPart checks if a character can be part of an unquoted key
func isIdentifierPart(ch rune) bool {
return unicode.IsLetter(ch) || unicode.IsDigit(ch) || ch == '_' || ch == '$'
}
// processEscapeSequences converts escape sequences such as \n, \t, \uXXXX, \UXXXXXXXX, \u{0x1FA}, and \U{0x1FA} into their actual representations
func processEscapeSequences(input string) (string, error) {
var result strings.Builder
length := len(input)
for i := 0; i < length; i++ {
ch := input[i]
if ch == '\\' && i+1 < length {
nextCh := input[i+1]
switch nextCh {
case 'n':
result.WriteByte('\n')
i++
case 'r':
result.WriteByte('\r')
i++
case 't':
result.WriteByte('\t')
i++
case '\\':
result.WriteByte('\\')
i++
case '"':
result.WriteByte('"')
i++
case '\'':
result.WriteByte('\'')
i++
case 'u', 'U': // Handle \uXXXX, \UXXXXXXXX, \u{0xXXXX}, \U{0xXXXX}
if i+2 < length && input[i+2] == '{' {
// Handle \u{...} or \U{...}
i += 3
start := i
for i < length && input[i] != '}' {
i++
}
if i >= length {
return "", fmt.Errorf("invalid Unicode escape: incomplete \\u or \\U sequence")
}
hex := input[start:i]
if strings.HasPrefix(hex, "0x") {
hex = hex[2:] // Remove 0x if present
}
codePoint, err := strconv.ParseInt(hex, 16, 32)
if err != nil || !utf8.ValidRune(rune(codePoint)) {
return "", fmt.Errorf("invalid Unicode escape: \\u{%s}", hex)
}
result.WriteRune(rune(codePoint))
} else if nextCh == 'u' && i+5 < length {
// Handle \uXXXX
hex := input[i+2 : i+6]
codePoint, err := strconv.ParseInt(hex, 16, 32)
if err != nil || !utf8.ValidRune(rune(codePoint)) {
return "", fmt.Errorf("invalid Unicode escape: \\u%s", hex)
}
result.WriteRune(rune(codePoint))
i += 5 // Move past the 4 hex digits
} else if nextCh == 'U' && i+9 < length {
// Handle \UXXXXXXXX
hex := input[i+2 : i+10]
codePoint, err := strconv.ParseInt(hex, 16, 32)
if err != nil || !utf8.ValidRune(rune(codePoint)) {
return "", fmt.Errorf("invalid Unicode escape: \\U%s", hex)
}
result.WriteRune(rune(codePoint))
i += 9 // Move past the 8 hex digits
} else {
return "", fmt.Errorf("invalid Unicode escape")
}
default:
result.WriteByte(ch)
}
} else {
result.WriteByte(ch)
}
}
return result.String(), nil
}
// tokenize is a function to tokenize a JSON5 string with unquoted key and hex number support, and escape sequence handling
func Tokenize(input string) []Token {
var tokens []Token
length := len(input)
i := 0
for i < length {
ch := rune(input[i])
// Skip whitespaces
if isWhitespace(ch) {
i++
continue
}
// Handle single-line (//) and multi-line (/* */) comments
if ch == '/' && i+1 < length {
nextCh := rune(input[i+1])
if nextCh == '/' {
// Single-line comment
start := i
i += 2
for i < length && input[i] != '\n' {
i++
}
tokens = append(tokens, Token{Type: TOKEN_COMMENT, Value: input[start:i]})
continue
} else if nextCh == '*' {
// Multi-line comment
start := i
i += 2
for i < length-1 && !(input[i] == '*' && input[i+1] == '/') {
i++
}
i += 2 // Skip over the closing */
tokens = append(tokens, Token{Type: TOKEN_COMMENT, Value: input[start:i]})
continue
}
}
switch ch {
case '{':
tokens = append(tokens, Token{Type: TOKEN_LBRACE, Value: "{"})
i++
case '}':
tokens = append(tokens, Token{Type: TOKEN_RBRACE, Value: "}"})
i++
case '[':
tokens = append(tokens, Token{Type: TOKEN_LBRACKET, Value: "["})
i++
case ']':
tokens = append(tokens, Token{Type: TOKEN_RBRACKET, Value: "]"})
i++
case ':':
tokens = append(tokens, Token{Type: TOKEN_COLON, Value: ":"})
i++
case ',':
tokens = append(tokens, Token{Type: TOKEN_COMMA, Value: ","})
i++
case '"', '\'':
// String token (quoted), handle both keys and values
start := i
quote := ch
i++
for i < length && rune(input[i]) != quote {
if input[i] == '\\' && i+1 < length {
// Escape sequence detected, skip it
i += 2
} else {
i++
}
}
i++ // Skip the closing quote
rawString := input[start+1 : i-1] // Remove quotes
processedString, err := processEscapeSequences(rawString) // Handle escape sequences
if err != nil {
tokens = append(tokens, Token{Type: TOKEN_UNKNOWN, Value: err.Error()})
} else {
tokens = append(tokens, Token{Type: TOKEN_STRING, Value: processedString})
}
default:
if isDigit(ch) || ch == '-' {
// Number token, including support for hex
start := i
if input[i:i+2] == "0x" || input[i:i+2] == "0X" {
// Hexadecimal number
i += 2
for i < length && isHexDigit(rune(input[i])) {
i++
}
tokens = append(tokens, Token{Type: TOKEN_NUMBER, Value: input[start:i]})
} else {
// Decimal number
for i < length && (isDigit(rune(input[i])) || input[i] == '.' || input[i] == 'e' || input[i] == 'E') {
i++
}
tokens = append(tokens, Token{Type: TOKEN_NUMBER, Value: input[start:i]})
}
} else if isIdentifierStart(ch) {
// Unquoted key or identifier
start := i
for i < length && isIdentifierPart(rune(input[i])) {
i++
}
unquotedString := input[start:i]
// Check if it's a boolean or null literal
switch unquotedString {
case "true":
tokens = append(tokens, Token{Type: TOKEN_TRUE, Value: "true"})
case "false":
tokens = append(tokens, Token{Type: TOKEN_FALSE, Value: "false"})
case "null":
tokens = append(tokens, Token{Type: TOKEN_NULL, Value: "null"})
default:
tokens = append(tokens, Token{Type: TOKEN_STRING, Value: unquotedString})
}
} else {
// Unknown token (for simplicity)
tokens = append(tokens, Token{Type: TOKEN_UNKNOWN, Value: string(ch)})
i++
}
}
}
return tokens
}