tokenize.js
6.38 KB
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
'use strict'
const SINGLE_QUOTE = "'".charCodeAt(0)
const DOUBLE_QUOTE = '"'.charCodeAt(0)
const BACKSLASH = '\\'.charCodeAt(0)
const SLASH = '/'.charCodeAt(0)
const NEWLINE = '\n'.charCodeAt(0)
const SPACE = ' '.charCodeAt(0)
const FEED = '\f'.charCodeAt(0)
const TAB = '\t'.charCodeAt(0)
const CR = '\r'.charCodeAt(0)
const OPEN_SQUARE = '['.charCodeAt(0)
const CLOSE_SQUARE = ']'.charCodeAt(0)
const OPEN_PARENTHESES = '('.charCodeAt(0)
const CLOSE_PARENTHESES = ')'.charCodeAt(0)
const OPEN_CURLY = '{'.charCodeAt(0)
const CLOSE_CURLY = '}'.charCodeAt(0)
const SEMICOLON = ';'.charCodeAt(0)
const ASTERISK = '*'.charCodeAt(0)
const COLON = ':'.charCodeAt(0)
const AT = '@'.charCodeAt(0)
const RE_AT_END = /[\t\n\f\r "#'()/;[\\\]{}]/g
const RE_WORD_END = /[\t\n\f\r !"#'():;@[\\\]{}]|\/(?=\*)/g
const RE_BAD_BRACKET = /.[\n"'(/\\]/
const RE_HEX_ESCAPE = /[\da-f]/i
module.exports = function tokenizer(input, options = {}) {
let css = input.css.valueOf()
let ignore = options.ignoreErrors
let code, next, quote, content, escape
let escaped, escapePos, prev, n, currentToken
let length = css.length
let pos = 0
let buffer = []
let returned = []
function position() {
return pos
}
function unclosed(what) {
throw input.error('Unclosed ' + what, pos)
}
function endOfFile() {
return returned.length === 0 && pos >= length
}
function nextToken(opts) {
if (returned.length) return returned.pop()
if (pos >= length) return
let ignoreUnclosed = opts ? opts.ignoreUnclosed : false
code = css.charCodeAt(pos)
switch (code) {
case NEWLINE:
case SPACE:
case TAB:
case CR:
case FEED: {
next = pos
do {
next += 1
code = css.charCodeAt(next)
} while (
code === SPACE ||
code === NEWLINE ||
code === TAB ||
code === CR ||
code === FEED
)
currentToken = ['space', css.slice(pos, next)]
pos = next - 1
break
}
case OPEN_SQUARE:
case CLOSE_SQUARE:
case OPEN_CURLY:
case CLOSE_CURLY:
case COLON:
case SEMICOLON:
case CLOSE_PARENTHESES: {
let controlChar = String.fromCharCode(code)
currentToken = [controlChar, controlChar, pos]
break
}
case OPEN_PARENTHESES: {
prev = buffer.length ? buffer.pop()[1] : ''
n = css.charCodeAt(pos + 1)
if (
prev === 'url' &&
n !== SINGLE_QUOTE &&
n !== DOUBLE_QUOTE &&
n !== SPACE &&
n !== NEWLINE &&
n !== TAB &&
n !== FEED &&
n !== CR
) {
next = pos
do {
escaped = false
next = css.indexOf(')', next + 1)
if (next === -1) {
if (ignore || ignoreUnclosed) {
next = pos
break
} else {
unclosed('bracket')
}
}
escapePos = next
while (css.charCodeAt(escapePos - 1) === BACKSLASH) {
escapePos -= 1
escaped = !escaped
}
} while (escaped)
currentToken = ['brackets', css.slice(pos, next + 1), pos, next]
pos = next
} else {
next = css.indexOf(')', pos + 1)
content = css.slice(pos, next + 1)
if (next === -1 || RE_BAD_BRACKET.test(content)) {
currentToken = ['(', '(', pos]
} else {
currentToken = ['brackets', content, pos, next]
pos = next
}
}
break
}
case SINGLE_QUOTE:
case DOUBLE_QUOTE: {
quote = code === SINGLE_QUOTE ? "'" : '"'
next = pos
do {
escaped = false
next = css.indexOf(quote, next + 1)
if (next === -1) {
if (ignore || ignoreUnclosed) {
next = pos + 1
break
} else {
unclosed('string')
}
}
escapePos = next
while (css.charCodeAt(escapePos - 1) === BACKSLASH) {
escapePos -= 1
escaped = !escaped
}
} while (escaped)
currentToken = ['string', css.slice(pos, next + 1), pos, next]
pos = next
break
}
case AT: {
RE_AT_END.lastIndex = pos + 1
RE_AT_END.test(css)
if (RE_AT_END.lastIndex === 0) {
next = css.length - 1
} else {
next = RE_AT_END.lastIndex - 2
}
currentToken = ['at-word', css.slice(pos, next + 1), pos, next]
pos = next
break
}
case BACKSLASH: {
next = pos
escape = true
while (css.charCodeAt(next + 1) === BACKSLASH) {
next += 1
escape = !escape
}
code = css.charCodeAt(next + 1)
if (
escape &&
code !== SLASH &&
code !== SPACE &&
code !== NEWLINE &&
code !== TAB &&
code !== CR &&
code !== FEED
) {
next += 1
if (RE_HEX_ESCAPE.test(css.charAt(next))) {
while (RE_HEX_ESCAPE.test(css.charAt(next + 1))) {
next += 1
}
if (css.charCodeAt(next + 1) === SPACE) {
next += 1
}
}
}
currentToken = ['word', css.slice(pos, next + 1), pos, next]
pos = next
break
}
default: {
if (code === SLASH && css.charCodeAt(pos + 1) === ASTERISK) {
next = css.indexOf('*/', pos + 2) + 1
if (next === 0) {
if (ignore || ignoreUnclosed) {
next = css.length
} else {
unclosed('comment')
}
}
currentToken = ['comment', css.slice(pos, next + 1), pos, next]
pos = next
} else {
RE_WORD_END.lastIndex = pos + 1
RE_WORD_END.test(css)
if (RE_WORD_END.lastIndex === 0) {
next = css.length - 1
} else {
next = RE_WORD_END.lastIndex - 2
}
currentToken = ['word', css.slice(pos, next + 1), pos, next]
buffer.push(currentToken)
pos = next
}
break
}
}
pos++
return currentToken
}
function back(token) {
returned.push(token)
}
return {
back,
nextToken,
endOfFile,
position
}
}