1 | 'use strict'
|
---|
2 |
|
---|
3 | const SINGLE_QUOTE = "'".charCodeAt(0)
|
---|
4 | const DOUBLE_QUOTE = '"'.charCodeAt(0)
|
---|
5 | const BACKSLASH = '\\'.charCodeAt(0)
|
---|
6 | const SLASH = '/'.charCodeAt(0)
|
---|
7 | const NEWLINE = '\n'.charCodeAt(0)
|
---|
8 | const SPACE = ' '.charCodeAt(0)
|
---|
9 | const FEED = '\f'.charCodeAt(0)
|
---|
10 | const TAB = '\t'.charCodeAt(0)
|
---|
11 | const CR = '\r'.charCodeAt(0)
|
---|
12 | const OPEN_SQUARE = '['.charCodeAt(0)
|
---|
13 | const CLOSE_SQUARE = ']'.charCodeAt(0)
|
---|
14 | const OPEN_PARENTHESES = '('.charCodeAt(0)
|
---|
15 | const CLOSE_PARENTHESES = ')'.charCodeAt(0)
|
---|
16 | const OPEN_CURLY = '{'.charCodeAt(0)
|
---|
17 | const CLOSE_CURLY = '}'.charCodeAt(0)
|
---|
18 | const SEMICOLON = ';'.charCodeAt(0)
|
---|
19 | const ASTERISK = '*'.charCodeAt(0)
|
---|
20 | const COLON = ':'.charCodeAt(0)
|
---|
21 | const AT = '@'.charCodeAt(0)
|
---|
22 |
|
---|
23 | const RE_AT_END = /[\t\n\f\r "#'()/;[\\\]{}]/g
|
---|
24 | const RE_WORD_END = /[\t\n\f\r !"#'():;@[\\\]{}]|\/(?=\*)/g
|
---|
25 | const RE_BAD_BRACKET = /.[\n"'(/\\]/
|
---|
26 | const RE_HEX_ESCAPE = /[\da-f]/i
|
---|
27 |
|
---|
28 | module.exports = function tokenizer(input, options = {}) {
|
---|
29 | let css = input.css.valueOf()
|
---|
30 | let ignore = options.ignoreErrors
|
---|
31 |
|
---|
32 | let code, next, quote, content, escape
|
---|
33 | let escaped, escapePos, prev, n, currentToken
|
---|
34 |
|
---|
35 | let length = css.length
|
---|
36 | let pos = 0
|
---|
37 | let buffer = []
|
---|
38 | let returned = []
|
---|
39 |
|
---|
40 | function position() {
|
---|
41 | return pos
|
---|
42 | }
|
---|
43 |
|
---|
44 | function unclosed(what) {
|
---|
45 | throw input.error('Unclosed ' + what, pos)
|
---|
46 | }
|
---|
47 |
|
---|
48 | function endOfFile() {
|
---|
49 | return returned.length === 0 && pos >= length
|
---|
50 | }
|
---|
51 |
|
---|
52 | function nextToken(opts) {
|
---|
53 | if (returned.length) return returned.pop()
|
---|
54 | if (pos >= length) return
|
---|
55 |
|
---|
56 | let ignoreUnclosed = opts ? opts.ignoreUnclosed : false
|
---|
57 |
|
---|
58 | code = css.charCodeAt(pos)
|
---|
59 |
|
---|
60 | switch (code) {
|
---|
61 | case NEWLINE:
|
---|
62 | case SPACE:
|
---|
63 | case TAB:
|
---|
64 | case CR:
|
---|
65 | case FEED: {
|
---|
66 | next = pos
|
---|
67 | do {
|
---|
68 | next += 1
|
---|
69 | code = css.charCodeAt(next)
|
---|
70 | } while (
|
---|
71 | code === SPACE ||
|
---|
72 | code === NEWLINE ||
|
---|
73 | code === TAB ||
|
---|
74 | code === CR ||
|
---|
75 | code === FEED
|
---|
76 | )
|
---|
77 |
|
---|
78 | currentToken = ['space', css.slice(pos, next)]
|
---|
79 | pos = next - 1
|
---|
80 | break
|
---|
81 | }
|
---|
82 |
|
---|
83 | case OPEN_SQUARE:
|
---|
84 | case CLOSE_SQUARE:
|
---|
85 | case OPEN_CURLY:
|
---|
86 | case CLOSE_CURLY:
|
---|
87 | case COLON:
|
---|
88 | case SEMICOLON:
|
---|
89 | case CLOSE_PARENTHESES: {
|
---|
90 | let controlChar = String.fromCharCode(code)
|
---|
91 | currentToken = [controlChar, controlChar, pos]
|
---|
92 | break
|
---|
93 | }
|
---|
94 |
|
---|
95 | case OPEN_PARENTHESES: {
|
---|
96 | prev = buffer.length ? buffer.pop()[1] : ''
|
---|
97 | n = css.charCodeAt(pos + 1)
|
---|
98 | if (
|
---|
99 | prev === 'url' &&
|
---|
100 | n !== SINGLE_QUOTE &&
|
---|
101 | n !== DOUBLE_QUOTE &&
|
---|
102 | n !== SPACE &&
|
---|
103 | n !== NEWLINE &&
|
---|
104 | n !== TAB &&
|
---|
105 | n !== FEED &&
|
---|
106 | n !== CR
|
---|
107 | ) {
|
---|
108 | next = pos
|
---|
109 | do {
|
---|
110 | escaped = false
|
---|
111 | next = css.indexOf(')', next + 1)
|
---|
112 | if (next === -1) {
|
---|
113 | if (ignore || ignoreUnclosed) {
|
---|
114 | next = pos
|
---|
115 | break
|
---|
116 | } else {
|
---|
117 | unclosed('bracket')
|
---|
118 | }
|
---|
119 | }
|
---|
120 | escapePos = next
|
---|
121 | while (css.charCodeAt(escapePos - 1) === BACKSLASH) {
|
---|
122 | escapePos -= 1
|
---|
123 | escaped = !escaped
|
---|
124 | }
|
---|
125 | } while (escaped)
|
---|
126 |
|
---|
127 | currentToken = ['brackets', css.slice(pos, next + 1), pos, next]
|
---|
128 |
|
---|
129 | pos = next
|
---|
130 | } else {
|
---|
131 | next = css.indexOf(')', pos + 1)
|
---|
132 | content = css.slice(pos, next + 1)
|
---|
133 |
|
---|
134 | if (next === -1 || RE_BAD_BRACKET.test(content)) {
|
---|
135 | currentToken = ['(', '(', pos]
|
---|
136 | } else {
|
---|
137 | currentToken = ['brackets', content, pos, next]
|
---|
138 | pos = next
|
---|
139 | }
|
---|
140 | }
|
---|
141 |
|
---|
142 | break
|
---|
143 | }
|
---|
144 |
|
---|
145 | case SINGLE_QUOTE:
|
---|
146 | case DOUBLE_QUOTE: {
|
---|
147 | quote = code === SINGLE_QUOTE ? "'" : '"'
|
---|
148 | next = pos
|
---|
149 | do {
|
---|
150 | escaped = false
|
---|
151 | next = css.indexOf(quote, next + 1)
|
---|
152 | if (next === -1) {
|
---|
153 | if (ignore || ignoreUnclosed) {
|
---|
154 | next = pos + 1
|
---|
155 | break
|
---|
156 | } else {
|
---|
157 | unclosed('string')
|
---|
158 | }
|
---|
159 | }
|
---|
160 | escapePos = next
|
---|
161 | while (css.charCodeAt(escapePos - 1) === BACKSLASH) {
|
---|
162 | escapePos -= 1
|
---|
163 | escaped = !escaped
|
---|
164 | }
|
---|
165 | } while (escaped)
|
---|
166 |
|
---|
167 | currentToken = ['string', css.slice(pos, next + 1), pos, next]
|
---|
168 | pos = next
|
---|
169 | break
|
---|
170 | }
|
---|
171 |
|
---|
172 | case AT: {
|
---|
173 | RE_AT_END.lastIndex = pos + 1
|
---|
174 | RE_AT_END.test(css)
|
---|
175 | if (RE_AT_END.lastIndex === 0) {
|
---|
176 | next = css.length - 1
|
---|
177 | } else {
|
---|
178 | next = RE_AT_END.lastIndex - 2
|
---|
179 | }
|
---|
180 |
|
---|
181 | currentToken = ['at-word', css.slice(pos, next + 1), pos, next]
|
---|
182 |
|
---|
183 | pos = next
|
---|
184 | break
|
---|
185 | }
|
---|
186 |
|
---|
187 | case BACKSLASH: {
|
---|
188 | next = pos
|
---|
189 | escape = true
|
---|
190 | while (css.charCodeAt(next + 1) === BACKSLASH) {
|
---|
191 | next += 1
|
---|
192 | escape = !escape
|
---|
193 | }
|
---|
194 | code = css.charCodeAt(next + 1)
|
---|
195 | if (
|
---|
196 | escape &&
|
---|
197 | code !== SLASH &&
|
---|
198 | code !== SPACE &&
|
---|
199 | code !== NEWLINE &&
|
---|
200 | code !== TAB &&
|
---|
201 | code !== CR &&
|
---|
202 | code !== FEED
|
---|
203 | ) {
|
---|
204 | next += 1
|
---|
205 | if (RE_HEX_ESCAPE.test(css.charAt(next))) {
|
---|
206 | while (RE_HEX_ESCAPE.test(css.charAt(next + 1))) {
|
---|
207 | next += 1
|
---|
208 | }
|
---|
209 | if (css.charCodeAt(next + 1) === SPACE) {
|
---|
210 | next += 1
|
---|
211 | }
|
---|
212 | }
|
---|
213 | }
|
---|
214 |
|
---|
215 | currentToken = ['word', css.slice(pos, next + 1), pos, next]
|
---|
216 |
|
---|
217 | pos = next
|
---|
218 | break
|
---|
219 | }
|
---|
220 |
|
---|
221 | default: {
|
---|
222 | if (code === SLASH && css.charCodeAt(pos + 1) === ASTERISK) {
|
---|
223 | next = css.indexOf('*/', pos + 2) + 1
|
---|
224 | if (next === 0) {
|
---|
225 | if (ignore || ignoreUnclosed) {
|
---|
226 | next = css.length
|
---|
227 | } else {
|
---|
228 | unclosed('comment')
|
---|
229 | }
|
---|
230 | }
|
---|
231 |
|
---|
232 | currentToken = ['comment', css.slice(pos, next + 1), pos, next]
|
---|
233 | pos = next
|
---|
234 | } else {
|
---|
235 | RE_WORD_END.lastIndex = pos + 1
|
---|
236 | RE_WORD_END.test(css)
|
---|
237 | if (RE_WORD_END.lastIndex === 0) {
|
---|
238 | next = css.length - 1
|
---|
239 | } else {
|
---|
240 | next = RE_WORD_END.lastIndex - 2
|
---|
241 | }
|
---|
242 |
|
---|
243 | currentToken = ['word', css.slice(pos, next + 1), pos, next]
|
---|
244 | buffer.push(currentToken)
|
---|
245 | pos = next
|
---|
246 | }
|
---|
247 |
|
---|
248 | break
|
---|
249 | }
|
---|
250 | }
|
---|
251 |
|
---|
252 | pos++
|
---|
253 | return currentToken
|
---|
254 | }
|
---|
255 |
|
---|
256 | function back(token) {
|
---|
257 | returned.push(token)
|
---|
258 | }
|
---|
259 |
|
---|
260 | return {
|
---|
261 | back,
|
---|
262 | nextToken,
|
---|
263 | endOfFile,
|
---|
264 | position
|
---|
265 | }
|
---|
266 | }
|
---|