Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 | 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 6060x 48909x 24011x 457x 457x 3538x 457x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 104x 11788x 104x 104x 104x 104x 37x 1690x 1690x 1690x 1690x 1690x 1690x 1690x 1690x 1690x 1690x 1690x 32275x 32275x 32275x 32275x 32275x 32275x 18987x 11856x 11856x 32275x 11856x 11856x 32275x 1720x 17169x 4603x 1458x 4603x 4603x 12566x 20x 12546x 371x 371x 371x 104x 104x 104x 743x 740x 369x 369x 83x 369x 369x 371x 3x 3x 3x 3677x 394x 394x 394x 787x 758x 365x 365x 1x 364x 365x 393x 29x 29x 104x 104x 224x 224x 224x 95x 129x 109x 109x 115x 115x 115x 4694x 455x 453x 453x 448x 448x 448x 448x 453x 453x 453x 453x 2x 4241x 3207x 1034x 774x 80x 1x 79x 1x 1x 1x 694x 694x 260x 36x 36x 6x 6x 6x 6x 746x 41312x 41312x 1462x 41312x 744x 2x 2x 202x 102x 51x 4x 47x 51x 51x 51x 100x 51x 49x 49x 47x 115x 115x 558x 558x 558x 4603x 55x 55x 4548x 1x 1x 4547x 3028x 3028x 1115x 1913x 517x 1396x 1330x 158x 1172x 66x 1519x 1518x 1x 1x 10361x 2510x 3218x 517x 517x 436x 517x 3027x 3027x 3027x 3027x 1515x 1514x 1x 1x 1x 1x 1513x 1513x 7305x 1965x 1965x 1965x 1965x 1978x 1964x 1964x 7554x 2041x 2041x 454x 1587x 2041x 5513x 977x 977x 4x 4536x 1x 1x 1x 4535x 2051x 2x 2051x 2282x 712x 712x 1570x 432x 432x 432x 1138x 1138x 974x 973x 973x 973x 973x 1x 1x 1x 5054x 1137x 1137x 3917x 3x 3864x 630x 630x 3234x 75x 75x 75x 3159x 7x 7x 7x 2674x 459x 459x 2215x 39x 2176x 47x 47x 47x 232x 38x 194x 1x 1x 1x 1x 349x 54x 54x 295x 11x 11x 2281x 2281x 2281x 2281x 2550x 1724x 826x 325x 325x 325x 325x 501x 231x 231x 1725x 1694x 1694x 31x 11x 11x 20x 18x 18x 18x 14669x 1703x 1703x 1703x 1703x 12966x 19x 14644x 25x 61x 17x 17x 17x 17x 17x 44x 5x 39x 55x 6x 6x 49x 1x 1x 1x 1x 49x 49x 49x 49x 49x 266x 1x 265x 3x 262x 262x 158x 158x 111x 47x 47x 40x 40x 40x 40x 40x 40x 40x 40x 40x 40x 4x 1690x 1690x 87478x 87478x 1942x 87478x 17165x 17165x 371x 371x 3648x 3648x 393x 393x 224x 224x 4694x 4694x 36x 36x 14644x 14644x 5054x 5054x 3864x 3864x 2674x 2674x 232x 232x 349x 349x 202x 202x 4184x 4184x 9937x 9937x 3218x 3218x 6852x 6852x 4603x 4603x 269x 269x 25x 25x 1725x 1725x 1515x 1515x 14x 14x 266x 266x 158x 158x 43x 43x 974x 974x 55x 55x 49x 49x 1x 1x 40x 40x 87477x 1689x 1689x 1689x 307x 282x 282x 25x 3x 3x 1689x 1689x 1689x 1689x 1689x 1667x 22x 2x 1x 1x 20x 12x 37x 37x 16x 14x 16x 16x 16x 21x 3x 21x 21x 21x | /**
* This Tokenizer is adapted from htmlparser2 under the MIT License listed at
* https://github.com/fb55/htmlparser2/blob/master/LICENSE
Copyright 2010, 2011, Chris Winberry <chris@winberry.net>. All rights reserved.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to
deal in the Software without restriction, including without limitation the
rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
IN THE SOFTWARE.
*/
import { ErrorCodes } from './errors'
import type { ElementNode, Position } from './ast'
/**
* Note: entities is a non-browser-build-only dependency.
* In the browser, we use an HTML element to do the decoding.
* Make sure all imports from entities are only used in non-browser branches
* so that it can be properly treeshaken.
*/
import {
DecodingMode,
EntityDecoder,
fromCodePoint,
htmlDecodeTree,
} from 'entities/decode'
export enum ParseMode {
BASE,
HTML,
SFC,
}
export enum CharCodes {
Tab = 0x9, // "\t"
NewLine = 0xa, // "\n"
FormFeed = 0xc, // "\f"
CarriageReturn = 0xd, // "\r"
Space = 0x20, // " "
ExclamationMark = 0x21, // "!"
Number = 0x23, // "#"
Amp = 0x26, // "&"
SingleQuote = 0x27, // "'"
DoubleQuote = 0x22, // '"'
GraveAccent = 96, // "`"
Dash = 0x2d, // "-"
Slash = 0x2f, // "/"
Zero = 0x30, // "0"
Nine = 0x39, // "9"
Semi = 0x3b, // ";"
Lt = 0x3c, // "<"
Eq = 0x3d, // "="
Gt = 0x3e, // ">"
Questionmark = 0x3f, // "?"
UpperA = 0x41, // "A"
LowerA = 0x61, // "a"
UpperF = 0x46, // "F"
LowerF = 0x66, // "f"
UpperZ = 0x5a, // "Z"
LowerZ = 0x7a, // "z"
LowerX = 0x78, // "x"
LowerV = 0x76, // "v"
Dot = 0x2e, // "."
Colon = 0x3a, // ":"
At = 0x40, // "@"
LeftSquare = 91, // "["
RightSquare = 93, // "]"
}
const defaultDelimitersOpen = new Uint8Array([123, 123]) // "{{"
const defaultDelimitersClose = new Uint8Array([125, 125]) // "}}"
/** All the states the tokenizer can be in. */
export enum State {
Text = 1,
// interpolation
InterpolationOpen,
Interpolation,
InterpolationClose,
// Tags
BeforeTagName, // After <
InTagName,
InSelfClosingTag,
BeforeClosingTagName,
InClosingTagName,
AfterClosingTagName,
// Attrs
BeforeAttrName,
InAttrName,
InDirName,
InDirArg,
InDirDynamicArg,
InDirModifier,
AfterAttrName,
BeforeAttrValue,
InAttrValueDq, // "
InAttrValueSq, // '
InAttrValueNq,
// Declarations
BeforeDeclaration, // !
InDeclaration,
// Processing instructions
InProcessingInstruction, // ?
// Comments & CDATA
BeforeComment,
CDATASequence,
InSpecialComment,
InCommentLike,
// Special tags
BeforeSpecialS, // Decide if we deal with `<script` or `<style`
BeforeSpecialT, // Decide if we deal with `<title` or `<textarea`
SpecialStartSequence,
InRCDATA,
InEntity,
InSFCRootTagName,
}
/**
* HTML only allows ASCII alpha characters (a-z and A-Z) at the beginning of a
* tag name.
*/
function isTagStartChar(c: number): boolean {
return (
(c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||
(c >= CharCodes.UpperA && c <= CharCodes.UpperZ)
)
}
export function isWhitespace(c: number): boolean {
return (
c === CharCodes.Space ||
c === CharCodes.NewLine ||
c === CharCodes.Tab ||
c === CharCodes.FormFeed ||
c === CharCodes.CarriageReturn
)
}
function isEndOfTagSection(c: number): boolean {
return c === CharCodes.Slash || c === CharCodes.Gt || isWhitespace(c)
}
export function toCharCodes(str: string): Uint8Array {
const ret = new Uint8Array(str.length)
for (let i = 0; i < str.length; i++) {
ret[i] = str.charCodeAt(i)
}
return ret
}
export enum QuoteType {
NoValue = 0,
Unquoted = 1,
Single = 2,
Double = 3,
}
export interface Callbacks {
ontext(start: number, endIndex: number): void
ontextentity(char: string, start: number, endIndex: number): void
oninterpolation(start: number, endIndex: number): void
onopentagname(start: number, endIndex: number): void
onopentagend(endIndex: number): void
onselfclosingtag(endIndex: number): void
onclosetag(start: number, endIndex: number): void
onattribdata(start: number, endIndex: number): void
onattribentity(char: string, start: number, end: number): void
onattribend(quote: QuoteType, endIndex: number): void
onattribname(start: number, endIndex: number): void
onattribnameend(endIndex: number): void
ondirname(start: number, endIndex: number): void
ondirarg(start: number, endIndex: number): void
ondirmodifier(start: number, endIndex: number): void
oncomment(start: number, endIndex: number): void
oncdata(start: number, endIndex: number): void
onprocessinginstruction(start: number, endIndex: number): void
// ondeclaration(start: number, endIndex: number): void
onend(): void
onerr(code: ErrorCodes, index: number): void
}
/**
* Sequences used to match longer strings.
*
* We don't have `Script`, `Style`, or `Title` here. Instead, we re-use the *End
* sequences with an increased offset.
*/
export const Sequences: {
Cdata: Uint8Array
CdataEnd: Uint8Array
CommentEnd: Uint8Array
ScriptEnd: Uint8Array
StyleEnd: Uint8Array
TitleEnd: Uint8Array
TextareaEnd: Uint8Array
} = {
Cdata: new Uint8Array([0x43, 0x44, 0x41, 0x54, 0x41, 0x5b]), // CDATA[
CdataEnd: new Uint8Array([0x5d, 0x5d, 0x3e]), // ]]>
CommentEnd: new Uint8Array([0x2d, 0x2d, 0x3e]), // `-->`
ScriptEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74]), // `</script`
StyleEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x74, 0x79, 0x6c, 0x65]), // `</style`
TitleEnd: new Uint8Array([0x3c, 0x2f, 0x74, 0x69, 0x74, 0x6c, 0x65]), // `</title`
TextareaEnd: new Uint8Array([
0x3c, 0x2f, 116, 101, 120, 116, 97, 114, 101, 97,
]), // `</textarea
}
export default class Tokenizer {
/** The current state the tokenizer is in. */
public state: State = State.Text
/** The read buffer. */
private buffer = ''
/** The beginning of the section that is currently being read. */
public sectionStart = 0
/** The index within the buffer that we are currently looking at. */
private index = 0
/** The start of the last entity. */
private entityStart = 0
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
private baseState = State.Text
/** For special parsing behavior inside of script and style tags. */
public inRCDATA = false
/** For disabling RCDATA tags handling */
public inXML = false
/** For disabling interpolation parsing in v-pre */
public inVPre = false
/** Record newline positions for fast line / column calculation */
private newlines: number[] = []
private readonly entityDecoder?: EntityDecoder
public mode: ParseMode = ParseMode.BASE
public get inSFCRoot(): boolean {
return this.mode === ParseMode.SFC && this.stack.length === 0
}
constructor(
private readonly stack: ElementNode[],
private readonly cbs: Callbacks,
) {
Eif (!__BROWSER__) {
this.entityDecoder = new EntityDecoder(htmlDecodeTree, (cp, consumed) =>
this.emitCodePoint(cp, consumed),
)
}
}
public reset(): void {
this.state = State.Text
this.mode = ParseMode.BASE
this.buffer = ''
this.sectionStart = 0
this.index = 0
this.baseState = State.Text
this.inRCDATA = false
this.currentSequence = undefined!
this.newlines.length = 0
this.delimiterOpen = defaultDelimitersOpen
this.delimiterClose = defaultDelimitersClose
}
/**
* Generate Position object with line / column information using recorded
* newline positions. We know the index is always going to be an already
* processed index, so all the newlines up to this index should have been
* recorded.
*/
public getPos(index: number): Position {
let line = 1
let column = index + 1
const length = this.newlines.length
let j = -1
Iif (length > 100) {
let l = -1
let r = length
while (l + 1 < r) {
const m = (l + r) >>> 1
this.newlines[m] < index ? (l = m) : (r = m)
}
j = l
} else {
for (let i = length - 1; i >= 0; i--) {
if (index > this.newlines[i]) {
j = i
break
}
}
}
if (j >= 0) {
line = j + 2
column = index - this.newlines[j]
}
return {
column,
line,
offset: index,
}
}
private peek() {
return this.buffer.charCodeAt(this.index + 1)
}
private stateText(c: number): void {
if (c === CharCodes.Lt) {
if (this.index > this.sectionStart) {
this.cbs.ontext(this.sectionStart, this.index)
}
this.state = State.BeforeTagName
this.sectionStart = this.index
} else if (!__BROWSER__ && c === CharCodes.Amp) {
this.startEntity()
} else if (!this.inVPre && c === this.delimiterOpen[0]) {
this.state = State.InterpolationOpen
this.delimiterIndex = 0
this.stateInterpolationOpen(c)
}
}
public delimiterOpen: Uint8Array = defaultDelimitersOpen
public delimiterClose: Uint8Array = defaultDelimitersClose
private delimiterIndex = -1
private stateInterpolationOpen(c: number): void {
if (c === this.delimiterOpen[this.delimiterIndex]) {
if (this.delimiterIndex === this.delimiterOpen.length - 1) {
const start = this.index + 1 - this.delimiterOpen.length
if (start > this.sectionStart) {
this.cbs.ontext(this.sectionStart, start)
}
this.state = State.Interpolation
this.sectionStart = start
} else {
this.delimiterIndex++
}
I} else if (this.inRCDATA) {
this.state = State.InRCDATA
this.stateInRCDATA(c)
} else {
this.state = State.Text
this.stateText(c)
}
}
private stateInterpolation(c: number): void {
if (c === this.delimiterClose[0]) {
this.state = State.InterpolationClose
this.delimiterIndex = 0
this.stateInterpolationClose(c)
}
}
private stateInterpolationClose(c: number) {
if (c === this.delimiterClose[this.delimiterIndex]) {
if (this.delimiterIndex === this.delimiterClose.length - 1) {
this.cbs.oninterpolation(this.sectionStart, this.index + 1)
if (this.inRCDATA) {
this.state = State.InRCDATA
} else {
this.state = State.Text
}
this.sectionStart = this.index + 1
} else {
this.delimiterIndex++
}
} else {
this.state = State.Interpolation
this.stateInterpolation(c)
}
}
public currentSequence: Uint8Array = undefined!
private sequenceIndex = 0
private stateSpecialStartSequence(c: number): void {
const isEnd = this.sequenceIndex === this.currentSequence.length
const isMatch = isEnd
? // If we are at the end of the sequence, make sure the tag name has ended
isEndOfTagSection(c)
: // Otherwise, do a case-insensitive comparison
(c | 0x20) === this.currentSequence[this.sequenceIndex]
if (!isMatch) {
this.inRCDATA = false
} else if (!isEnd) {
this.sequenceIndex++
return
}
this.sequenceIndex = 0
this.state = State.InTagName
this.stateInTagName(c)
}
/** Look for an end tag. For <title> and <textarea>, also decode entities. */
private stateInRCDATA(c: number): void {
if (this.sequenceIndex === this.currentSequence.length) {
if (c === CharCodes.Gt || isWhitespace(c)) {
const endOfText = this.index - this.currentSequence.length
if (this.sectionStart < endOfText) {
// Spoof the index so that reported locations match up.
const actualIndex = this.index
this.index = endOfText
this.cbs.ontext(this.sectionStart, endOfText)
this.index = actualIndex
}
this.sectionStart = endOfText + 2 // Skip over the `</`
this.stateInClosingTagName(c)
this.inRCDATA = false
return // We are done; skip the rest of the function.
}
this.sequenceIndex = 0
}
if ((c | 0x20) === this.currentSequence[this.sequenceIndex]) {
this.sequenceIndex += 1
} else if (this.sequenceIndex === 0) {
if (
this.currentSequence === Sequences.TitleEnd ||
(this.currentSequence === Sequences.TextareaEnd && !this.inSFCRoot)
) {
// We have to parse entities in <title> and <textarea> tags.
if (!__BROWSER__ && c === CharCodes.Amp) {
this.startEntity()
} else if (!this.inVPre && c === this.delimiterOpen[0]) {
// We also need to handle interpolation
this.state = State.InterpolationOpen
this.delimiterIndex = 0
this.stateInterpolationOpen(c)
}
E} else if (this.fastForwardTo(CharCodes.Lt)) {
// Outside of <title> and <textarea> tags, we can fast-forward.
this.sequenceIndex = 1
}
} else {
// If we see a `<`, set the sequence index to 1; useful for eg. `<</script>`.
this.sequenceIndex = Number(c === CharCodes.Lt)
}
}
private stateCDATASequence(c: number): void {
if (c === Sequences.Cdata[this.sequenceIndex]) {
if (++this.sequenceIndex === Sequences.Cdata.length) {
this.state = State.InCommentLike
this.currentSequence = Sequences.CdataEnd
this.sequenceIndex = 0
this.sectionStart = this.index + 1
}
} else E{
this.sequenceIndex = 0
this.state = State.InDeclaration
this.stateInDeclaration(c) // Reconsume the character
}
}
/**
* When we wait for one specific character, we can speed things up
* by skipping through the buffer until we find it.
*
* @returns Whether the character was found.
*/
private fastForwardTo(c: number): boolean {
while (++this.index < this.buffer.length) {
const cc = this.buffer.charCodeAt(this.index)
if (cc === CharCodes.NewLine) {
this.newlines.push(this.index)
}
if (cc === c) {
return true
}
}
/*
* We increment the index at the end of the `parse` loop,
* so set it to `buffer.length - 1` here.
*
* TODO: Refactor `parse` to increment index before calling states.
*/
this.index = this.buffer.length - 1
return false
}
/**
* Comments and CDATA end with `-->` and `]]>`.
*
* Their common qualities are:
* - Their end sequences have a distinct character they start with.
* - That character is then repeated, so we have to check multiple repeats.
* - All characters but the start character of the sequence can be skipped.
*/
private stateInCommentLike(c: number): void {
if (c === this.currentSequence[this.sequenceIndex]) {
if (++this.sequenceIndex === this.currentSequence.length) {
if (this.currentSequence === Sequences.CdataEnd) {
this.cbs.oncdata(this.sectionStart, this.index - 2)
} else {
this.cbs.oncomment(this.sectionStart, this.index - 2)
}
this.sequenceIndex = 0
this.sectionStart = this.index + 1
this.state = State.Text
}
} else if (this.sequenceIndex === 0) {
// Fast-forward to the first character of the sequence
if (this.fastForwardTo(this.currentSequence[0])) {
this.sequenceIndex = 1
}
} else if (c !== this.currentSequence[this.sequenceIndex - 1]) {
// Allow long sequences, eg. --->, ]]]>
this.sequenceIndex = 0
}
}
private startSpecial(sequence: Uint8Array, offset: number) {
this.enterRCDATA(sequence, offset)
this.state = State.SpecialStartSequence
}
public enterRCDATA(sequence: Uint8Array, offset: number): void {
this.inRCDATA = true
this.currentSequence = sequence
this.sequenceIndex = offset
}
private stateBeforeTagName(c: number): void {
if (c === CharCodes.ExclamationMark) {
this.state = State.BeforeDeclaration
this.sectionStart = this.index + 1
} else if (c === CharCodes.Questionmark) {
this.state = State.InProcessingInstruction
this.sectionStart = this.index + 1
} else if (isTagStartChar(c)) {
this.sectionStart = this.index
if (this.mode === ParseMode.BASE) {
// no special tags in base mode
this.state = State.InTagName
} else if (this.inSFCRoot) {
// SFC mode + root level
// - everything except <template> is RAWTEXT
// - <template> with lang other than html is also RAWTEXT
this.state = State.InSFCRootTagName
} else if (!this.inXML) {
// HTML mode
// - <script>, <style> RAWTEXT
// - <title>, <textarea> RCDATA
if (c === 116 /* t */) {
this.state = State.BeforeSpecialT
} else {
this.state =
c === 115 /* s */ ? State.BeforeSpecialS : State.InTagName
}
} else {
this.state = State.InTagName
}
} else if (c === CharCodes.Slash) {
this.state = State.BeforeClosingTagName
} else {
this.state = State.Text
this.stateText(c)
}
}
private stateInTagName(c: number): void {
if (isEndOfTagSection(c)) {
this.handleTagName(c)
}
}
private stateInSFCRootTagName(c: number): void {
if (isEndOfTagSection(c)) {
const tag = this.buffer.slice(this.sectionStart, this.index)
if (tag !== 'template') {
this.enterRCDATA(toCharCodes(`</` + tag), 0)
}
this.handleTagName(c)
}
}
private handleTagName(c: number) {
this.cbs.onopentagname(this.sectionStart, this.index)
this.sectionStart = -1
this.state = State.BeforeAttrName
this.stateBeforeAttrName(c)
}
private stateBeforeClosingTagName(c: number): void {
if (isWhitespace(c)) {
// Ignore
} else if (c === CharCodes.Gt) {
Eif (__DEV__ || !__BROWSER__) {
this.cbs.onerr(ErrorCodes.MISSING_END_TAG_NAME, this.index)
}
this.state = State.Text
// Ignore
this.sectionStart = this.index + 1
} else {
this.state = isTagStartChar(c)
? State.InClosingTagName
: State.InSpecialComment
this.sectionStart = this.index
}
}
private stateInClosingTagName(c: number): void {
if (c === CharCodes.Gt || isWhitespace(c)) {
this.cbs.onclosetag(this.sectionStart, this.index)
this.sectionStart = -1
this.state = State.AfterClosingTagName
this.stateAfterClosingTagName(c)
}
}
private stateAfterClosingTagName(c: number): void {
// Skip everything until ">"
if (c === CharCodes.Gt) {
this.state = State.Text
this.sectionStart = this.index + 1
}
}
private stateBeforeAttrName(c: number): void {
if (c === CharCodes.Gt) {
this.cbs.onopentagend(this.index)
if (this.inRCDATA) {
this.state = State.InRCDATA
} else {
this.state = State.Text
}
this.sectionStart = this.index + 1
} else if (c === CharCodes.Slash) {
this.state = State.InSelfClosingTag
if ((__DEV__ || !__BROWSER__) && this.peek() !== CharCodes.Gt) {
this.cbs.onerr(ErrorCodes.UNEXPECTED_SOLIDUS_IN_TAG, this.index)
}
} else if (c === CharCodes.Lt && this.peek() === CharCodes.Slash) {
// special handling for </ appearing in open tag state
// this is different from standard HTML parsing but makes practical sense
// especially for parsing intermediate input state in IDEs.
this.cbs.onopentagend(this.index)
this.state = State.BeforeTagName
this.sectionStart = this.index
} else if (!isWhitespace(c)) {
if ((__DEV__ || !__BROWSER__) && c === CharCodes.Eq) {
this.cbs.onerr(
ErrorCodes.UNEXPECTED_EQUALS_SIGN_BEFORE_ATTRIBUTE_NAME,
this.index,
)
}
this.handleAttrStart(c)
}
}
private handleAttrStart(c: number) {
if (c === CharCodes.LowerV && this.peek() === CharCodes.Dash) {
this.state = State.InDirName
this.sectionStart = this.index
} else if (
c === CharCodes.Dot ||
c === CharCodes.Colon ||
c === CharCodes.At ||
c === CharCodes.Number
) {
this.cbs.ondirname(this.index, this.index + 1)
this.state = State.InDirArg
this.sectionStart = this.index + 1
} else {
this.state = State.InAttrName
this.sectionStart = this.index
}
}
private stateInSelfClosingTag(c: number): void {
if (c === CharCodes.Gt) {
this.cbs.onselfclosingtag(this.index)
this.state = State.Text
this.sectionStart = this.index + 1
this.inRCDATA = false // Reset special state, in case of self-closing special tags
E} else if (!isWhitespace(c)) {
this.state = State.BeforeAttrName
this.stateBeforeAttrName(c)
}
}
private stateInAttrName(c: number): void {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.onattribname(this.sectionStart, this.index)
this.handleAttrNameEnd(c)
} else if (
(__DEV__ || !__BROWSER__) &&
(c === CharCodes.DoubleQuote ||
c === CharCodes.SingleQuote ||
c === CharCodes.Lt)
) {
this.cbs.onerr(
ErrorCodes.UNEXPECTED_CHARACTER_IN_ATTRIBUTE_NAME,
this.index,
)
}
}
private stateInDirName(c: number): void {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.ondirname(this.sectionStart, this.index)
this.handleAttrNameEnd(c)
} else if (c === CharCodes.Colon) {
this.cbs.ondirname(this.sectionStart, this.index)
this.state = State.InDirArg
this.sectionStart = this.index + 1
} else if (c === CharCodes.Dot) {
this.cbs.ondirname(this.sectionStart, this.index)
this.state = State.InDirModifier
this.sectionStart = this.index + 1
}
}
private stateInDirArg(c: number): void {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.ondirarg(this.sectionStart, this.index)
this.handleAttrNameEnd(c)
} else if (c === CharCodes.LeftSquare) {
this.state = State.InDirDynamicArg
} else if (c === CharCodes.Dot) {
this.cbs.ondirarg(this.sectionStart, this.index)
this.state = State.InDirModifier
this.sectionStart = this.index + 1
}
}
private stateInDynamicDirArg(c: number): void {
if (c === CharCodes.RightSquare) {
this.state = State.InDirArg
} else if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.ondirarg(this.sectionStart, this.index + 1)
this.handleAttrNameEnd(c)
Eif (__DEV__ || !__BROWSER__) {
this.cbs.onerr(
ErrorCodes.X_MISSING_DYNAMIC_DIRECTIVE_ARGUMENT_END,
this.index,
)
}
}
}
private stateInDirModifier(c: number): void {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.ondirmodifier(this.sectionStart, this.index)
this.handleAttrNameEnd(c)
} else if (c === CharCodes.Dot) {
this.cbs.ondirmodifier(this.sectionStart, this.index)
this.sectionStart = this.index + 1
}
}
private handleAttrNameEnd(c: number): void {
this.sectionStart = this.index
this.state = State.AfterAttrName
this.cbs.onattribnameend(this.index)
this.stateAfterAttrName(c)
}
private stateAfterAttrName(c: number): void {
if (c === CharCodes.Eq) {
this.state = State.BeforeAttrValue
} else if (c === CharCodes.Slash || c === CharCodes.Gt) {
this.cbs.onattribend(QuoteType.NoValue, this.sectionStart)
this.sectionStart = -1
this.state = State.BeforeAttrName
this.stateBeforeAttrName(c)
} else if (!isWhitespace(c)) {
this.cbs.onattribend(QuoteType.NoValue, this.sectionStart)
this.handleAttrStart(c)
}
}
private stateBeforeAttrValue(c: number): void {
if (c === CharCodes.DoubleQuote) {
this.state = State.InAttrValueDq
this.sectionStart = this.index + 1
} else if (c === CharCodes.SingleQuote) {
this.state = State.InAttrValueSq
this.sectionStart = this.index + 1
} else if (!isWhitespace(c)) {
this.sectionStart = this.index
this.state = State.InAttrValueNq
this.stateInAttrValueNoQuotes(c) // Reconsume token
}
}
private handleInAttrValue(c: number, quote: number) {
if (c === quote || (__BROWSER__ && this.fastForwardTo(quote))) {
this.cbs.onattribdata(this.sectionStart, this.index)
this.sectionStart = -1
this.cbs.onattribend(
quote === CharCodes.DoubleQuote ? QuoteType.Double : QuoteType.Single,
this.index + 1,
)
this.state = State.BeforeAttrName
} else if (!__BROWSER__ && c === CharCodes.Amp) {
this.startEntity()
}
}
private stateInAttrValueDoubleQuotes(c: number): void {
this.handleInAttrValue(c, CharCodes.DoubleQuote)
}
private stateInAttrValueSingleQuotes(c: number): void {
this.handleInAttrValue(c, CharCodes.SingleQuote)
}
private stateInAttrValueNoQuotes(c: number): void {
if (isWhitespace(c) || c === CharCodes.Gt) {
this.cbs.onattribdata(this.sectionStart, this.index)
this.sectionStart = -1
this.cbs.onattribend(QuoteType.Unquoted, this.index)
this.state = State.BeforeAttrName
this.stateBeforeAttrName(c)
} else if (
((__DEV__ || !__BROWSER__) && c === CharCodes.DoubleQuote) ||
c === CharCodes.SingleQuote ||
c === CharCodes.Lt ||
c === CharCodes.Eq ||
c === CharCodes.GraveAccent
) {
this.cbs.onerr(
ErrorCodes.UNEXPECTED_CHARACTER_IN_UNQUOTED_ATTRIBUTE_VALUE,
this.index,
)
I} else if (!__BROWSER__ && c === CharCodes.Amp) {
this.startEntity()
}
}
private stateBeforeDeclaration(c: number): void {
if (c === CharCodes.LeftSquare) {
this.state = State.CDATASequence
this.sequenceIndex = 0
} else {
this.state =
c === CharCodes.Dash ? State.BeforeComment : State.InDeclaration
}
}
private stateInDeclaration(c: number): void {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
// this.cbs.ondeclaration(this.sectionStart, this.index)
this.state = State.Text
this.sectionStart = this.index + 1
}
}
private stateInProcessingInstruction(c: number): void {
Eif (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.onprocessinginstruction(this.sectionStart, this.index)
this.state = State.Text
this.sectionStart = this.index + 1
}
}
private stateBeforeComment(c: number): void {
if (c === CharCodes.Dash) {
this.state = State.InCommentLike
this.currentSequence = Sequences.CommentEnd
// Allow short comments (eg. <!-->)
this.sequenceIndex = 2
this.sectionStart = this.index + 1
} else E{
this.state = State.InDeclaration
}
}
private stateInSpecialComment(c: number): void {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.oncomment(this.sectionStart, this.index)
this.state = State.Text
this.sectionStart = this.index + 1
}
}
private stateBeforeSpecialS(c: number): void {
if (c === Sequences.ScriptEnd[3]) {
this.startSpecial(Sequences.ScriptEnd, 4)
} else if (c === Sequences.StyleEnd[3]) {
this.startSpecial(Sequences.StyleEnd, 4)
} else {
this.state = State.InTagName
this.stateInTagName(c) // Consume the token again
}
}
private stateBeforeSpecialT(c: number): void {
Iif (c === Sequences.TitleEnd[3]) {
this.startSpecial(Sequences.TitleEnd, 4)
} else if (c === Sequences.TextareaEnd[3]) {
this.startSpecial(Sequences.TextareaEnd, 4)
} else {
this.state = State.InTagName
this.stateInTagName(c) // Consume the token again
}
}
private startEntity() {
Eif (!__BROWSER__) {
this.baseState = this.state
this.state = State.InEntity
this.entityStart = this.index
this.entityDecoder!.startEntity(
this.baseState === State.Text || this.baseState === State.InRCDATA
? DecodingMode.Legacy
: DecodingMode.Attribute,
)
}
}
private stateInEntity(): void {
Eif (!__BROWSER__) {
const length = this.entityDecoder!.write(this.buffer, this.index)
// If `length` is positive, we are done with the entity.
if (length >= 0) {
this.state = this.baseState
if (length === 0) {
this.index = this.entityStart
}
} else E{
// Mark buffer as consumed.
this.index = this.buffer.length - 1
}
}
}
/**
* Iterates through the buffer, calling the function corresponding to the current state.
*
* States that are more likely to be hit are higher up, as a performance improvement.
*/
public parse(input: string): void {
this.buffer = input
while (this.index < this.buffer.length) {
const c = this.buffer.charCodeAt(this.index)
if (c === CharCodes.NewLine && this.state !== State.InEntity) {
this.newlines.push(this.index)
}
switch (this.state) {
case State.Text: {
this.stateText(c)
break
}
case State.InterpolationOpen: {
this.stateInterpolationOpen(c)
break
}
case State.Interpolation: {
this.stateInterpolation(c)
break
}
case State.InterpolationClose: {
this.stateInterpolationClose(c)
break
}
case State.SpecialStartSequence: {
this.stateSpecialStartSequence(c)
break
}
case State.InRCDATA: {
this.stateInRCDATA(c)
break
}
case State.CDATASequence: {
this.stateCDATASequence(c)
break
}
case State.InAttrValueDq: {
this.stateInAttrValueDoubleQuotes(c)
break
}
case State.InAttrName: {
this.stateInAttrName(c)
break
}
case State.InDirName: {
this.stateInDirName(c)
break
}
case State.InDirArg: {
this.stateInDirArg(c)
break
}
case State.InDirDynamicArg: {
this.stateInDynamicDirArg(c)
break
}
case State.InDirModifier: {
this.stateInDirModifier(c)
break
}
case State.InCommentLike: {
this.stateInCommentLike(c)
break
}
case State.InSpecialComment: {
this.stateInSpecialComment(c)
break
}
case State.BeforeAttrName: {
this.stateBeforeAttrName(c)
break
}
case State.InTagName: {
this.stateInTagName(c)
break
}
case State.InSFCRootTagName: {
this.stateInSFCRootTagName(c)
break
}
case State.InClosingTagName: {
this.stateInClosingTagName(c)
break
}
case State.BeforeTagName: {
this.stateBeforeTagName(c)
break
}
case State.AfterAttrName: {
this.stateAfterAttrName(c)
break
}
case State.InAttrValueSq: {
this.stateInAttrValueSingleQuotes(c)
break
}
case State.BeforeAttrValue: {
this.stateBeforeAttrValue(c)
break
}
case State.BeforeClosingTagName: {
this.stateBeforeClosingTagName(c)
break
}
case State.AfterClosingTagName: {
this.stateAfterClosingTagName(c)
break
}
case State.BeforeSpecialS: {
this.stateBeforeSpecialS(c)
break
}
case State.BeforeSpecialT: {
this.stateBeforeSpecialT(c)
break
}
case State.InAttrValueNq: {
this.stateInAttrValueNoQuotes(c)
break
}
case State.InSelfClosingTag: {
this.stateInSelfClosingTag(c)
break
}
case State.InDeclaration: {
this.stateInDeclaration(c)
break
}
case State.BeforeDeclaration: {
this.stateBeforeDeclaration(c)
break
}
case State.BeforeComment: {
this.stateBeforeComment(c)
break
}
case State.InProcessingInstruction: {
this.stateInProcessingInstruction(c)
break
}
case State.InEntity: {
this.stateInEntity()
break
}
}
this.index++
}
this.cleanup()
this.finish()
}
/**
* Remove data that has already been consumed from the buffer.
*/
private cleanup() {
// If we are inside of text or attributes, emit what we already have.
if (this.sectionStart !== this.index) {
if (
this.state === State.Text ||
(this.state === State.InRCDATA && this.sequenceIndex === 0)
) {
this.cbs.ontext(this.sectionStart, this.index)
this.sectionStart = this.index
} else if (
this.state === State.InAttrValueDq ||
this.state === State.InAttrValueSq ||
this.state === State.InAttrValueNq
) {
this.cbs.onattribdata(this.sectionStart, this.index)
this.sectionStart = this.index
}
}
}
private finish() {
Iif (!__BROWSER__ && this.state === State.InEntity) {
this.entityDecoder!.end()
this.state = this.baseState
}
this.handleTrailingData()
this.cbs.onend()
}
/** Handle any trailing data. */
private handleTrailingData() {
const endIndex = this.buffer.length
// If there is no remaining data, we are done.
if (this.sectionStart >= endIndex) {
return
}
if (this.state === State.InCommentLike) {
if (this.currentSequence === Sequences.CdataEnd) {
this.cbs.oncdata(this.sectionStart, endIndex)
} else {
this.cbs.oncomment(this.sectionStart, endIndex)
}
} else if (
this.state === State.InTagName ||
this.state === State.BeforeAttrName ||
this.state === State.BeforeAttrValue ||
this.state === State.AfterAttrName ||
this.state === State.InAttrName ||
this.state === State.InDirName ||
this.state === State.InDirArg ||
this.state === State.InDirDynamicArg ||
this.state === State.InDirModifier ||
this.state === State.InAttrValueSq ||
this.state === State.InAttrValueDq ||
this.state === State.InAttrValueNq ||
this.state === State.InClosingTagName
) {
/*
* If we are currently in an opening or closing tag, us not calling the
* respective callback signals that the tag should be ignored.
*/
} else {
this.cbs.ontext(this.sectionStart, endIndex)
}
}
private emitCodePoint(cp: number, consumed: number): void {
Eif (!__BROWSER__) {
if (this.baseState !== State.Text && this.baseState !== State.InRCDATA) {
if (this.sectionStart < this.entityStart) {
this.cbs.onattribdata(this.sectionStart, this.entityStart)
}
this.sectionStart = this.entityStart + consumed
this.index = this.sectionStart - 1
this.cbs.onattribentity(
fromCodePoint(cp),
this.entityStart,
this.sectionStart,
)
} else {
if (this.sectionStart < this.entityStart) {
this.cbs.ontext(this.sectionStart, this.entityStart)
}
this.sectionStart = this.entityStart + consumed
this.index = this.sectionStart - 1
this.cbs.ontextentity(
fromCodePoint(cp),
this.entityStart,
this.sectionStart,
)
}
}
}
}
|