Spaces:
Runtime error
Runtime error
File size: 20,670 Bytes
b5ea024 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 |
import * as TYPE from './types.js';
import {
isNewline,
isName,
isValidEscape,
isNumberStart,
isIdentifierStart,
isBOM,
charCodeCategory,
WhiteSpaceCategory,
DigitCategory,
NameStartCategory,
NonPrintableCategory
} from './char-code-definitions.js';
import {
cmpStr,
getNewlineLength,
findWhiteSpaceEnd,
consumeEscaped,
consumeName,
consumeNumber,
consumeBadUrlRemnants
} from './utils.js';
export function tokenize(source, onToken) {
function getCharCode(offset) {
return offset < sourceLength ? source.charCodeAt(offset) : 0;
}
// § 4.3.3. Consume a numeric token
function consumeNumericToken() {
// Consume a number and let number be the result.
offset = consumeNumber(source, offset);
// If the next 3 input code points would start an identifier, then:
if (isIdentifierStart(getCharCode(offset), getCharCode(offset + 1), getCharCode(offset + 2))) {
// Create a <dimension-token> with the same value and type flag as number, and a unit set initially to the empty string.
// Consume a name. Set the <dimension-token>’s unit to the returned value.
// Return the <dimension-token>.
type = TYPE.Dimension;
offset = consumeName(source, offset);
return;
}
// Otherwise, if the next input code point is U+0025 PERCENTAGE SIGN (%), consume it.
if (getCharCode(offset) === 0x0025) {
// Create a <percentage-token> with the same value as number, and return it.
type = TYPE.Percentage;
offset++;
return;
}
// Otherwise, create a <number-token> with the same value and type flag as number, and return it.
type = TYPE.Number;
}
// § 4.3.4. Consume an ident-like token
function consumeIdentLikeToken() {
const nameStartOffset = offset;
// Consume a name, and let string be the result.
offset = consumeName(source, offset);
// If string’s value is an ASCII case-insensitive match for "url",
// and the next input code point is U+0028 LEFT PARENTHESIS ((), consume it.
if (cmpStr(source, nameStartOffset, offset, 'url') && getCharCode(offset) === 0x0028) {
// While the next two input code points are whitespace, consume the next input code point.
offset = findWhiteSpaceEnd(source, offset + 1);
// If the next one or two input code points are U+0022 QUOTATION MARK ("), U+0027 APOSTROPHE ('),
// or whitespace followed by U+0022 QUOTATION MARK (") or U+0027 APOSTROPHE ('),
// then create a <function-token> with its value set to string and return it.
if (getCharCode(offset) === 0x0022 ||
getCharCode(offset) === 0x0027) {
type = TYPE.Function;
offset = nameStartOffset + 4;
return;
}
// Otherwise, consume a url token, and return it.
consumeUrlToken();
return;
}
// Otherwise, if the next input code point is U+0028 LEFT PARENTHESIS ((), consume it.
// Create a <function-token> with its value set to string and return it.
if (getCharCode(offset) === 0x0028) {
type = TYPE.Function;
offset++;
return;
}
// Otherwise, create an <ident-token> with its value set to string and return it.
type = TYPE.Ident;
}
// § 4.3.5. Consume a string token
function consumeStringToken(endingCodePoint) {
// This algorithm may be called with an ending code point, which denotes the code point
// that ends the string. If an ending code point is not specified,
// the current input code point is used.
if (!endingCodePoint) {
endingCodePoint = getCharCode(offset++);
}
// Initially create a <string-token> with its value set to the empty string.
type = TYPE.String;
// Repeatedly consume the next input code point from the stream:
for (; offset < source.length; offset++) {
const code = source.charCodeAt(offset);
switch (charCodeCategory(code)) {
// ending code point
case endingCodePoint:
// Return the <string-token>.
offset++;
return;
// EOF
// case EofCategory:
// This is a parse error. Return the <string-token>.
// return;
// newline
case WhiteSpaceCategory:
if (isNewline(code)) {
// This is a parse error. Reconsume the current input code point,
// create a <bad-string-token>, and return it.
offset += getNewlineLength(source, offset, code);
type = TYPE.BadString;
return;
}
break;
// U+005C REVERSE SOLIDUS (\)
case 0x005C:
// If the next input code point is EOF, do nothing.
if (offset === source.length - 1) {
break;
}
const nextCode = getCharCode(offset + 1);
// Otherwise, if the next input code point is a newline, consume it.
if (isNewline(nextCode)) {
offset += getNewlineLength(source, offset + 1, nextCode);
} else if (isValidEscape(code, nextCode)) {
// Otherwise, (the stream starts with a valid escape) consume
// an escaped code point and append the returned code point to
// the <string-token>’s value.
offset = consumeEscaped(source, offset) - 1;
}
break;
// anything else
// Append the current input code point to the <string-token>’s value.
}
}
}
// § 4.3.6. Consume a url token
// Note: This algorithm assumes that the initial "url(" has already been consumed.
// This algorithm also assumes that it’s being called to consume an "unquoted" value, like url(foo).
// A quoted value, like url("foo"), is parsed as a <function-token>. Consume an ident-like token
// automatically handles this distinction; this algorithm shouldn’t be called directly otherwise.
function consumeUrlToken() {
// Initially create a <url-token> with its value set to the empty string.
type = TYPE.Url;
// Consume as much whitespace as possible.
offset = findWhiteSpaceEnd(source, offset);
// Repeatedly consume the next input code point from the stream:
for (; offset < source.length; offset++) {
const code = source.charCodeAt(offset);
switch (charCodeCategory(code)) {
// U+0029 RIGHT PARENTHESIS ())
case 0x0029:
// Return the <url-token>.
offset++;
return;
// EOF
// case EofCategory:
// This is a parse error. Return the <url-token>.
// return;
// whitespace
case WhiteSpaceCategory:
// Consume as much whitespace as possible.
offset = findWhiteSpaceEnd(source, offset);
// If the next input code point is U+0029 RIGHT PARENTHESIS ()) or EOF,
// consume it and return the <url-token>
// (if EOF was encountered, this is a parse error);
if (getCharCode(offset) === 0x0029 || offset >= source.length) {
if (offset < source.length) {
offset++;
}
return;
}
// otherwise, consume the remnants of a bad url, create a <bad-url-token>,
// and return it.
offset = consumeBadUrlRemnants(source, offset);
type = TYPE.BadUrl;
return;
// U+0022 QUOTATION MARK (")
// U+0027 APOSTROPHE (')
// U+0028 LEFT PARENTHESIS (()
// non-printable code point
case 0x0022:
case 0x0027:
case 0x0028:
case NonPrintableCategory:
// This is a parse error. Consume the remnants of a bad url,
// create a <bad-url-token>, and return it.
offset = consumeBadUrlRemnants(source, offset);
type = TYPE.BadUrl;
return;
// U+005C REVERSE SOLIDUS (\)
case 0x005C:
// If the stream starts with a valid escape, consume an escaped code point and
// append the returned code point to the <url-token>’s value.
if (isValidEscape(code, getCharCode(offset + 1))) {
offset = consumeEscaped(source, offset) - 1;
break;
}
// Otherwise, this is a parse error. Consume the remnants of a bad url,
// create a <bad-url-token>, and return it.
offset = consumeBadUrlRemnants(source, offset);
type = TYPE.BadUrl;
return;
// anything else
// Append the current input code point to the <url-token>’s value.
}
}
}
// ensure source is a string
source = String(source || '');
const sourceLength = source.length;
let start = isBOM(getCharCode(0));
let offset = start;
let type;
// https://drafts.csswg.org/css-syntax-3/#consume-token
// § 4.3.1. Consume a token
while (offset < sourceLength) {
const code = source.charCodeAt(offset);
switch (charCodeCategory(code)) {
// whitespace
case WhiteSpaceCategory:
// Consume as much whitespace as possible. Return a <whitespace-token>.
type = TYPE.WhiteSpace;
offset = findWhiteSpaceEnd(source, offset + 1);
break;
// U+0022 QUOTATION MARK (")
case 0x0022:
// Consume a string token and return it.
consumeStringToken();
break;
// U+0023 NUMBER SIGN (#)
case 0x0023:
// If the next input code point is a name code point or the next two input code points are a valid escape, then:
if (isName(getCharCode(offset + 1)) || isValidEscape(getCharCode(offset + 1), getCharCode(offset + 2))) {
// Create a <hash-token>.
type = TYPE.Hash;
// If the next 3 input code points would start an identifier, set the <hash-token>’s type flag to "id".
// if (isIdentifierStart(getCharCode(offset + 1), getCharCode(offset + 2), getCharCode(offset + 3))) {
// // TODO: set id flag
// }
// Consume a name, and set the <hash-token>’s value to the returned string.
offset = consumeName(source, offset + 1);
// Return the <hash-token>.
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+0027 APOSTROPHE (')
case 0x0027:
// Consume a string token and return it.
consumeStringToken();
break;
// U+0028 LEFT PARENTHESIS (()
case 0x0028:
// Return a <(-token>.
type = TYPE.LeftParenthesis;
offset++;
break;
// U+0029 RIGHT PARENTHESIS ())
case 0x0029:
// Return a <)-token>.
type = TYPE.RightParenthesis;
offset++;
break;
// U+002B PLUS SIGN (+)
case 0x002B:
// If the input stream starts with a number, ...
if (isNumberStart(code, getCharCode(offset + 1), getCharCode(offset + 2))) {
// ... reconsume the current input code point, consume a numeric token, and return it.
consumeNumericToken();
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+002C COMMA (,)
case 0x002C:
// Return a <comma-token>.
type = TYPE.Comma;
offset++;
break;
// U+002D HYPHEN-MINUS (-)
case 0x002D:
// If the input stream starts with a number, reconsume the current input code point, consume a numeric token, and return it.
if (isNumberStart(code, getCharCode(offset + 1), getCharCode(offset + 2))) {
consumeNumericToken();
} else {
// Otherwise, if the next 2 input code points are U+002D HYPHEN-MINUS U+003E GREATER-THAN SIGN (->), consume them and return a <CDC-token>.
if (getCharCode(offset + 1) === 0x002D &&
getCharCode(offset + 2) === 0x003E) {
type = TYPE.CDC;
offset = offset + 3;
} else {
// Otherwise, if the input stream starts with an identifier, ...
if (isIdentifierStart(code, getCharCode(offset + 1), getCharCode(offset + 2))) {
// ... reconsume the current input code point, consume an ident-like token, and return it.
consumeIdentLikeToken();
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
}
}
break;
// U+002E FULL STOP (.)
case 0x002E:
// If the input stream starts with a number, ...
if (isNumberStart(code, getCharCode(offset + 1), getCharCode(offset + 2))) {
// ... reconsume the current input code point, consume a numeric token, and return it.
consumeNumericToken();
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+002F SOLIDUS (/)
case 0x002F:
// If the next two input code point are U+002F SOLIDUS (/) followed by a U+002A ASTERISK (*),
if (getCharCode(offset + 1) === 0x002A) {
// ... consume them and all following code points up to and including the first U+002A ASTERISK (*)
// followed by a U+002F SOLIDUS (/), or up to an EOF code point.
type = TYPE.Comment;
offset = source.indexOf('*/', offset + 2);
offset = offset === -1 ? source.length : offset + 2;
} else {
type = TYPE.Delim;
offset++;
}
break;
// U+003A COLON (:)
case 0x003A:
// Return a <colon-token>.
type = TYPE.Colon;
offset++;
break;
// U+003B SEMICOLON (;)
case 0x003B:
// Return a <semicolon-token>.
type = TYPE.Semicolon;
offset++;
break;
// U+003C LESS-THAN SIGN (<)
case 0x003C:
// If the next 3 input code points are U+0021 EXCLAMATION MARK U+002D HYPHEN-MINUS U+002D HYPHEN-MINUS (!--), ...
if (getCharCode(offset + 1) === 0x0021 &&
getCharCode(offset + 2) === 0x002D &&
getCharCode(offset + 3) === 0x002D) {
// ... consume them and return a <CDO-token>.
type = TYPE.CDO;
offset = offset + 4;
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+0040 COMMERCIAL AT (@)
case 0x0040:
// If the next 3 input code points would start an identifier, ...
if (isIdentifierStart(getCharCode(offset + 1), getCharCode(offset + 2), getCharCode(offset + 3))) {
// ... consume a name, create an <at-keyword-token> with its value set to the returned value, and return it.
type = TYPE.AtKeyword;
offset = consumeName(source, offset + 1);
} else {
// Otherwise, return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+005B LEFT SQUARE BRACKET ([)
case 0x005B:
// Return a <[-token>.
type = TYPE.LeftSquareBracket;
offset++;
break;
// U+005C REVERSE SOLIDUS (\)
case 0x005C:
// If the input stream starts with a valid escape, ...
if (isValidEscape(code, getCharCode(offset + 1))) {
// ... reconsume the current input code point, consume an ident-like token, and return it.
consumeIdentLikeToken();
} else {
// Otherwise, this is a parse error. Return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
break;
// U+005D RIGHT SQUARE BRACKET (])
case 0x005D:
// Return a <]-token>.
type = TYPE.RightSquareBracket;
offset++;
break;
// U+007B LEFT CURLY BRACKET ({)
case 0x007B:
// Return a <{-token>.
type = TYPE.LeftCurlyBracket;
offset++;
break;
// U+007D RIGHT CURLY BRACKET (})
case 0x007D:
// Return a <}-token>.
type = TYPE.RightCurlyBracket;
offset++;
break;
// digit
case DigitCategory:
// Reconsume the current input code point, consume a numeric token, and return it.
consumeNumericToken();
break;
// name-start code point
case NameStartCategory:
// Reconsume the current input code point, consume an ident-like token, and return it.
consumeIdentLikeToken();
break;
// EOF
// case EofCategory:
// Return an <EOF-token>.
// break;
// anything else
default:
// Return a <delim-token> with its value set to the current input code point.
type = TYPE.Delim;
offset++;
}
// put token to stream
onToken(type, start, start = offset);
}
}
export * from './types.js';
export * as tokenTypes from './types.js';
export { default as tokenNames } from './names.js';
export * from './char-code-definitions.js';
export * from './utils.js';
export * from './OffsetToLocation.js';
export * from './TokenStream.js';
|