ai/world
1
0
Fork 0
Code Issues Releases Activity

fix

Browse Source
This commit is contained in:
syui
2025-05-12 05:38:44 +09:00
parent dced21c3f8
commit 6d78bfa46e
8120 changed files with 1161564 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

247
book/node_modules/parse5/dist/cjs/tokenizer/index.d.ts generated vendored Normal file
View File

@ -0,0 +1,247 @@
import { Preprocessor } from './preprocessor.js';
import { type Token, type CharacterToken, type DoctypeToken, type TagToken, type EOFToken, type CommentToken, type Attribute, type Location } from '../common/token.js';
import { EntityDecoder } from 'entities/lib/decode.js';
import { ERR, type ParserErrorHandler } from '../common/error-codes.js';
declare const enum State {
DATA = 0,
RCDATA = 1,
RAWTEXT = 2,
SCRIPT_DATA = 3,
PLAINTEXT = 4,
TAG_OPEN = 5,
END_TAG_OPEN = 6,
TAG_NAME = 7,
RCDATA_LESS_THAN_SIGN = 8,
RCDATA_END_TAG_OPEN = 9,
RCDATA_END_TAG_NAME = 10,
RAWTEXT_LESS_THAN_SIGN = 11,
RAWTEXT_END_TAG_OPEN = 12,
RAWTEXT_END_TAG_NAME = 13,
SCRIPT_DATA_LESS_THAN_SIGN = 14,
SCRIPT_DATA_END_TAG_OPEN = 15,
SCRIPT_DATA_END_TAG_NAME = 16,
SCRIPT_DATA_ESCAPE_START = 17,
SCRIPT_DATA_ESCAPE_START_DASH = 18,
SCRIPT_DATA_ESCAPED = 19,
SCRIPT_DATA_ESCAPED_DASH = 20,
SCRIPT_DATA_ESCAPED_DASH_DASH = 21,
SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN = 22,
SCRIPT_DATA_ESCAPED_END_TAG_OPEN = 23,
SCRIPT_DATA_ESCAPED_END_TAG_NAME = 24,
SCRIPT_DATA_DOUBLE_ESCAPE_START = 25,
SCRIPT_DATA_DOUBLE_ESCAPED = 26,
SCRIPT_DATA_DOUBLE_ESCAPED_DASH = 27,
SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH = 28,
SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN = 29,
SCRIPT_DATA_DOUBLE_ESCAPE_END = 30,
BEFORE_ATTRIBUTE_NAME = 31,
ATTRIBUTE_NAME = 32,
AFTER_ATTRIBUTE_NAME = 33,
BEFORE_ATTRIBUTE_VALUE = 34,
ATTRIBUTE_VALUE_DOUBLE_QUOTED = 35,
ATTRIBUTE_VALUE_SINGLE_QUOTED = 36,
ATTRIBUTE_VALUE_UNQUOTED = 37,
AFTER_ATTRIBUTE_VALUE_QUOTED = 38,
SELF_CLOSING_START_TAG = 39,
BOGUS_COMMENT = 40,
MARKUP_DECLARATION_OPEN = 41,
COMMENT_START = 42,
COMMENT_START_DASH = 43,
COMMENT = 44,
COMMENT_LESS_THAN_SIGN = 45,
COMMENT_LESS_THAN_SIGN_BANG = 46,
COMMENT_LESS_THAN_SIGN_BANG_DASH = 47,
COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH = 48,
COMMENT_END_DASH = 49,
COMMENT_END = 50,
COMMENT_END_BANG = 51,
DOCTYPE = 52,
BEFORE_DOCTYPE_NAME = 53,
DOCTYPE_NAME = 54,
AFTER_DOCTYPE_NAME = 55,
AFTER_DOCTYPE_PUBLIC_KEYWORD = 56,
BEFORE_DOCTYPE_PUBLIC_IDENTIFIER = 57,
DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED = 58,
DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED = 59,
AFTER_DOCTYPE_PUBLIC_IDENTIFIER = 60,
BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS = 61,
AFTER_DOCTYPE_SYSTEM_KEYWORD = 62,
BEFORE_DOCTYPE_SYSTEM_IDENTIFIER = 63,
DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED = 64,
DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED = 65,
AFTER_DOCTYPE_SYSTEM_IDENTIFIER = 66,
BOGUS_DOCTYPE = 67,
CDATA_SECTION = 68,
CDATA_SECTION_BRACKET = 69,
CDATA_SECTION_END = 70,
CHARACTER_REFERENCE = 71,
AMBIGUOUS_AMPERSAND = 72
}
export declare const TokenizerMode: {
readonly DATA: State.DATA;
readonly RCDATA: State.RCDATA;
readonly RAWTEXT: State.RAWTEXT;
readonly SCRIPT_DATA: State.SCRIPT_DATA;
readonly PLAINTEXT: State.PLAINTEXT;
readonly CDATA_SECTION: State.CDATA_SECTION;
};
export interface TokenizerOptions {
sourceCodeLocationInfo?: boolean;
}
export interface TokenHandler {
onComment(token: CommentToken): void;
onDoctype(token: DoctypeToken): void;
onStartTag(token: TagToken): void;
onEndTag(token: TagToken): void;
onEof(token: EOFToken): void;
onCharacter(token: CharacterToken): void;
onNullCharacter(token: CharacterToken): void;
onWhitespaceCharacter(token: CharacterToken): void;
onParseError?: ParserErrorHandler | null;
}
export declare class Tokenizer {
protected options: TokenizerOptions;
protected handler: TokenHandler;
preprocessor: Preprocessor;
protected paused: boolean;
/** Ensures that the parsing loop isn't run multiple times at once. */
protected inLoop: boolean;
/**
* Indicates that the current adjusted node exists, is not an element in the HTML namespace,
* and that it is not an integration point for either MathML or HTML.
*
* @see {@link https://html.spec.whatwg.org/multipage/parsing.html#tree-construction}
*/
inForeignNode: boolean;
lastStartTagName: string;
active: boolean;
state: State;
protected returnState: State;
/**
* We use `entities`' `EntityDecoder` to parse character references.
*
* All of the following states are handled by the `EntityDecoder`:
*
* - Named character reference state
* - Numeric character reference state
* - Hexademical character reference start state
* - Hexademical character reference state
* - Decimal character reference state
* - Numeric character reference end state
*/
protected entityDecoder: EntityDecoder;
protected entityStartPos: number;
protected consumedAfterSnapshot: number;
protected currentLocation: Location | null;
protected currentCharacterToken: CharacterToken | null;
protected currentToken: Token | null;
protected currentAttr: Attribute;
constructor(options: TokenizerOptions, handler: TokenHandler);
protected _err(code: ERR, cpOffset?: number): void;
protected getCurrentLocation(offset: number): Location | null;
protected _runParsingLoop(): void;
pause(): void;
resume(writeCallback?: () => void): void;
write(chunk: string, isLastChunk: boolean, writeCallback?: () => void): void;
insertHtmlAtCurrentPos(chunk: string): void;
protected _ensureHibernation(): boolean;
protected _consume(): number;
protected _advanceBy(count: number): void;
protected _consumeSequenceIfMatch(pattern: string, caseSensitive: boolean): boolean;
protected _createStartTagToken(): void;
protected _createEndTagToken(): void;
protected _createCommentToken(offset: number): void;
protected _createDoctypeToken(initialName: string | null): void;
protected _createCharacterToken(type: CharacterToken['type'], chars: string): void;
protected _createAttr(attrNameFirstCh: string): void;
protected _leaveAttrName(): void;
protected _leaveAttrValue(): void;
protected prepareToken(ct: Token): void;
protected emitCurrentTagToken(): void;
protected emitCurrentComment(ct: CommentToken): void;
protected emitCurrentDoctype(ct: DoctypeToken): void;
protected _emitCurrentCharacterToken(nextLocation: Location | null): void;
protected _emitEOFToken(): void;
protected _appendCharToCurrentCharacterToken(type: CharacterToken['type'], ch: string): void;
protected _emitCodePoint(cp: number): void;
protected _emitChars(ch: string): void;
protected _startCharacterReference(): void;
protected _isCharacterReferenceInAttribute(): boolean;
protected _flushCodePointConsumedAsCharacterReference(cp: number): void;
protected _callState(cp: number): void;
protected _stateData(cp: number): void;
protected _stateRcdata(cp: number): void;
protected _stateRawtext(cp: number): void;
protected _stateScriptData(cp: number): void;
protected _statePlaintext(cp: number): void;
protected _stateTagOpen(cp: number): void;
protected _stateEndTagOpen(cp: number): void;
protected _stateTagName(cp: number): void;
protected _stateRcdataLessThanSign(cp: number): void;
protected _stateRcdataEndTagOpen(cp: number): void;
protected handleSpecialEndTag(_cp: number): boolean;
protected _stateRcdataEndTagName(cp: number): void;
protected _stateRawtextLessThanSign(cp: number): void;
protected _stateRawtextEndTagOpen(cp: number): void;
protected _stateRawtextEndTagName(cp: number): void;
protected _stateScriptDataLessThanSign(cp: number): void;
protected _stateScriptDataEndTagOpen(cp: number): void;
protected _stateScriptDataEndTagName(cp: number): void;
protected _stateScriptDataEscapeStart(cp: number): void;
protected _stateScriptDataEscapeStartDash(cp: number): void;
protected _stateScriptDataEscaped(cp: number): void;
protected _stateScriptDataEscapedDash(cp: number): void;
protected _stateScriptDataEscapedDashDash(cp: number): void;
protected _stateScriptDataEscapedLessThanSign(cp: number): void;
protected _stateScriptDataEscapedEndTagOpen(cp: number): void;
protected _stateScriptDataEscapedEndTagName(cp: number): void;
protected _stateScriptDataDoubleEscapeStart(cp: number): void;
protected _stateScriptDataDoubleEscaped(cp: number): void;
protected _stateScriptDataDoubleEscapedDash(cp: number): void;
protected _stateScriptDataDoubleEscapedDashDash(cp: number): void;
protected _stateScriptDataDoubleEscapedLessThanSign(cp: number): void;
protected _stateScriptDataDoubleEscapeEnd(cp: number): void;
protected _stateBeforeAttributeName(cp: number): void;
protected _stateAttributeName(cp: number): void;
protected _stateAfterAttributeName(cp: number): void;
protected _stateBeforeAttributeValue(cp: number): void;
protected _stateAttributeValueDoubleQuoted(cp: number): void;
protected _stateAttributeValueSingleQuoted(cp: number): void;
protected _stateAttributeValueUnquoted(cp: number): void;
protected _stateAfterAttributeValueQuoted(cp: number): void;
protected _stateSelfClosingStartTag(cp: number): void;
protected _stateBogusComment(cp: number): void;
protected _stateMarkupDeclarationOpen(cp: number): void;
protected _stateCommentStart(cp: number): void;
protected _stateCommentStartDash(cp: number): void;
protected _stateComment(cp: number): void;
protected _stateCommentLessThanSign(cp: number): void;
protected _stateCommentLessThanSignBang(cp: number): void;
protected _stateCommentLessThanSignBangDash(cp: number): void;
protected _stateCommentLessThanSignBangDashDash(cp: number): void;
protected _stateCommentEndDash(cp: number): void;
protected _stateCommentEnd(cp: number): void;
protected _stateCommentEndBang(cp: number): void;
protected _stateDoctype(cp: number): void;
protected _stateBeforeDoctypeName(cp: number): void;
protected _stateDoctypeName(cp: number): void;
protected _stateAfterDoctypeName(cp: number): void;
protected _stateAfterDoctypePublicKeyword(cp: number): void;
protected _stateBeforeDoctypePublicIdentifier(cp: number): void;
protected _stateDoctypePublicIdentifierDoubleQuoted(cp: number): void;
protected _stateDoctypePublicIdentifierSingleQuoted(cp: number): void;
protected _stateAfterDoctypePublicIdentifier(cp: number): void;
protected _stateBetweenDoctypePublicAndSystemIdentifiers(cp: number): void;
protected _stateAfterDoctypeSystemKeyword(cp: number): void;
protected _stateBeforeDoctypeSystemIdentifier(cp: number): void;
protected _stateDoctypeSystemIdentifierDoubleQuoted(cp: number): void;
protected _stateDoctypeSystemIdentifierSingleQuoted(cp: number): void;
protected _stateAfterDoctypeSystemIdentifier(cp: number): void;
protected _stateBogusDoctype(cp: number): void;
protected _stateCdataSection(cp: number): void;
protected _stateCdataSectionBracket(cp: number): void;
protected _stateCdataSectionEnd(cp: number): void;
protected _stateCharacterReference(): void;
protected _stateAmbiguousAmpersand(cp: number): void;
}
export {};

2714
book/node_modules/parse5/dist/cjs/tokenizer/index.js generated vendored Normal file
View File

File diff suppressed because it is too large Load Diff

36
book/node_modules/parse5/dist/cjs/tokenizer/preprocessor.d.ts generated vendored Normal file
View File

@ -0,0 +1,36 @@
import { ERR, type ParserError, type ParserErrorHandler } from '../common/error-codes.js';
export declare class Preprocessor {
private handler;
html: string;
pos: number;
private lastGapPos;
private gapStack;
private skipNextNewLine;
lastChunkWritten: boolean;
endOfChunkHit: boolean;
bufferWaterline: number;
private isEol;
private lineStartPos;
droppedBufferSize: number;
line: number;
constructor(handler: {
onParseError?: ParserErrorHandler | null;
});
/** The column on the current line. If we just saw a gap (eg. a surrogate pair), return the index before. */
get col(): number;
get offset(): number;
getError(code: ERR, cpOffset: number): ParserError;
private lastErrOffset;
private _err;
private _addGap;
private _processSurrogate;
willDropParsedChunk(): boolean;
dropParsedChunk(): void;
write(chunk: string, isLastChunk: boolean): void;
insertHtmlAtCurrentPos(chunk: string): void;
startsWith(pattern: string, caseSensitive: boolean): boolean;
peek(offset: number): number;
advance(): number;
private _checkForProblematicCharacters;
retreat(count: number): void;
}

200
book/node_modules/parse5/dist/cjs/tokenizer/preprocessor.js generated vendored Normal file
View File

@ -0,0 +1,200 @@
"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.Preprocessor = void 0;
const unicode_js_1 = require("../common/unicode.js");
const error_codes_js_1 = require("../common/error-codes.js");
//Const
const DEFAULT_BUFFER_WATERLINE = 1 << 16;
//Preprocessor
//NOTE: HTML input preprocessing
//(see: http://www.whatwg.org/specs/web-apps/current-work/multipage/parsing.html#preprocessing-the-input-stream)
class Preprocessor {
constructor(handler) {
this.handler = handler;
this.html = '';
this.pos = -1;
// NOTE: Initial `lastGapPos` is -2, to ensure `col` on initialisation is 0
this.lastGapPos = -2;
this.gapStack = [];
this.skipNextNewLine = false;
this.lastChunkWritten = false;
this.endOfChunkHit = false;
this.bufferWaterline = DEFAULT_BUFFER_WATERLINE;
this.isEol = false;
this.lineStartPos = 0;
this.droppedBufferSize = 0;
this.line = 1;
//NOTE: avoid reporting errors twice on advance/retreat
this.lastErrOffset = -1;
}
/** The column on the current line. If we just saw a gap (eg. a surrogate pair), return the index before. */
get col() {
return this.pos - this.lineStartPos + Number(this.lastGapPos !== this.pos);
}
get offset() {
return this.droppedBufferSize + this.pos;
}
getError(code, cpOffset) {
const { line, col, offset } = this;
const startCol = col + cpOffset;
const startOffset = offset + cpOffset;
return {
code,
startLine: line,
endLine: line,
startCol,
endCol: startCol,
startOffset,
endOffset: startOffset,
};
}
_err(code) {
if (this.handler.onParseError && this.lastErrOffset !== this.offset) {
this.lastErrOffset = this.offset;
this.handler.onParseError(this.getError(code, 0));
}
}
_addGap() {
this.gapStack.push(this.lastGapPos);
this.lastGapPos = this.pos;
}
_processSurrogate(cp) {
//NOTE: try to peek a surrogate pair
if (this.pos !== this.html.length - 1) {
const nextCp = this.html.charCodeAt(this.pos + 1);
if ((0, unicode_js_1.isSurrogatePair)(nextCp)) {
//NOTE: we have a surrogate pair. Peek pair character and recalculate code point.
this.pos++;
//NOTE: add a gap that should be avoided during retreat
this._addGap();
return (0, unicode_js_1.getSurrogatePairCodePoint)(cp, nextCp);
}
}
//NOTE: we are at the end of a chunk, therefore we can't infer the surrogate pair yet.
else if (!this.lastChunkWritten) {
this.endOfChunkHit = true;
return unicode_js_1.CODE_POINTS.EOF;
}
//NOTE: isolated surrogate
this._err(error_codes_js_1.ERR.surrogateInInputStream);
return cp;
}
willDropParsedChunk() {
return this.pos > this.bufferWaterline;
}
dropParsedChunk() {
if (this.willDropParsedChunk()) {
this.html = this.html.substring(this.pos);
this.lineStartPos -= this.pos;
this.droppedBufferSize += this.pos;
this.pos = 0;
this.lastGapPos = -2;
this.gapStack.length = 0;
}
}
write(chunk, isLastChunk) {
if (this.html.length > 0) {
this.html += chunk;
}
else {
this.html = chunk;
}
this.endOfChunkHit = false;
this.lastChunkWritten = isLastChunk;
}
insertHtmlAtCurrentPos(chunk) {
this.html = this.html.substring(0, this.pos + 1) + chunk + this.html.substring(this.pos + 1);
this.endOfChunkHit = false;
}
startsWith(pattern, caseSensitive) {
// Check if our buffer has enough characters
if (this.pos + pattern.length > this.html.length) {
this.endOfChunkHit = !this.lastChunkWritten;
return false;
}
if (caseSensitive) {
return this.html.startsWith(pattern, this.pos);
}
for (let i = 0; i < pattern.length; i++) {
const cp = this.html.charCodeAt(this.pos + i) | 0x20;
if (cp !== pattern.charCodeAt(i)) {
return false;
}
}
return true;
}
peek(offset) {
const pos = this.pos + offset;
if (pos >= this.html.length) {
this.endOfChunkHit = !this.lastChunkWritten;
return unicode_js_1.CODE_POINTS.EOF;
}
const code = this.html.charCodeAt(pos);
return code === unicode_js_1.CODE_POINTS.CARRIAGE_RETURN ? unicode_js_1.CODE_POINTS.LINE_FEED : code;
}
advance() {
this.pos++;
//NOTE: LF should be in the last column of the line
if (this.isEol) {
this.isEol = false;
this.line++;
this.lineStartPos = this.pos;
}
if (this.pos >= this.html.length) {
this.endOfChunkHit = !this.lastChunkWritten;
return unicode_js_1.CODE_POINTS.EOF;
}
let cp = this.html.charCodeAt(this.pos);
//NOTE: all U+000D CARRIAGE RETURN (CR) characters must be converted to U+000A LINE FEED (LF) characters
if (cp === unicode_js_1.CODE_POINTS.CARRIAGE_RETURN) {
this.isEol = true;
this.skipNextNewLine = true;
return unicode_js_1.CODE_POINTS.LINE_FEED;
}
//NOTE: any U+000A LINE FEED (LF) characters that immediately follow a U+000D CARRIAGE RETURN (CR) character
//must be ignored.
if (cp === unicode_js_1.CODE_POINTS.LINE_FEED) {
this.isEol = true;
if (this.skipNextNewLine) {
// `line` will be bumped again in the recursive call.
this.line--;
this.skipNextNewLine = false;
this._addGap();
return this.advance();
}
}
this.skipNextNewLine = false;
if ((0, unicode_js_1.isSurrogate)(cp)) {
cp = this._processSurrogate(cp);
}
//OPTIMIZATION: first check if code point is in the common allowed
//range (ASCII alphanumeric, whitespaces, big chunk of BMP)
//before going into detailed performance cost validation.
const isCommonValidRange = this.handler.onParseError === null ||
(cp > 0x1f && cp < 0x7f) ||
cp === unicode_js_1.CODE_POINTS.LINE_FEED ||
cp === unicode_js_1.CODE_POINTS.CARRIAGE_RETURN ||
(cp > 0x9f && cp < 64976);
if (!isCommonValidRange) {
this._checkForProblematicCharacters(cp);
}
return cp;
}
_checkForProblematicCharacters(cp) {
if ((0, unicode_js_1.isControlCodePoint)(cp)) {
this._err(error_codes_js_1.ERR.controlCharacterInInputStream);
}
else if ((0, unicode_js_1.isUndefinedCodePoint)(cp)) {
this._err(error_codes_js_1.ERR.noncharacterInInputStream);
}
}
retreat(count) {
this.pos -= count;
while (this.pos < this.lastGapPos) {
this.lastGapPos = this.gapStack.pop();
this.pos--;
}
this.isEol = false;
}
}
exports.Preprocessor = Preprocessor;