Socket
Socket
Sign inDemoInstall

htmlparser2

Package Overview
Dependencies
5
Maintainers
1
Versions
76
Alerts
File Explorer

Advanced tools

npm Scripts

Install Socket

Detect and block malicious and high-risk dependencies

Install

Comparing version 7.2.0 to 8.0.0

lib/esm/index.d.ts
lib/esm/index.d.ts.map
lib/esm/index.js
lib/esm/index.js.map
lib/esm/package.json
lib/esm/Parser.d.ts
lib/esm/Parser.d.ts.map
lib/esm/Parser.js
lib/esm/Parser.js.map
lib/esm/Tokenizer.d.ts
lib/esm/Tokenizer.d.ts.map
lib/esm/Tokenizer.js
lib/esm/Tokenizer.js.map
lib/esm/WritableStream.d.ts
lib/esm/WritableStream.d.ts.map
lib/esm/WritableStream.js
lib/esm/WritableStream.js.map
lib/index.js.map
lib/Parser.js.map
lib/Tokenizer.js.map
lib/WritableStream.js.map

25

lib/index.d.ts

@@ -1,5 +0,5 @@

import { Parser, ParserOptions } from "./Parser";
export { Parser, ParserOptions };
import { DomHandler, DomHandlerOptions, Node, Element, Document } from "domhandler";
export { DomHandler, DomHandlerOptions };
import { Parser, ParserOptions } from "./Parser.js";
export { Parser, type ParserOptions };
import { DomHandler, DomHandlerOptions, ChildNode, Element, Document } from "domhandler";
export { DomHandler, type DomHandlerOptions };
declare type Options = ParserOptions & DomHandlerOptions;

@@ -23,3 +23,3 @@ /**

*/
export declare function parseDOM(data: string, options?: Options): Node[];
export declare function parseDOM(data: string, options?: Options): ChildNode[];
/**

@@ -32,10 +32,17 @@ * Creates a parser instance, with an attached DOM handler.

*/
export declare function createDomStream(cb: (error: Error | null, dom: Node[]) => void, options?: Options, elementCb?: (element: Element) => void): Parser;
export { default as Tokenizer, Callbacks as TokenizerCallbacks, } from "./Tokenizer";
export declare function createDomStream(cb: (error: Error | null, dom: ChildNode[]) => void, options?: Options, elementCb?: (element: Element) => void): Parser;
export { default as Tokenizer, type Callbacks as TokenizerCallbacks, } from "./Tokenizer.js";
import * as ElementType from "domelementtype";
export { ElementType };
export * from "./FeedHandler";
import { getFeed, Feed } from "domutils";
export { getFeed };
/**
* Parse a feed.
*
* @param feed The feed that should be parsed, as a string.
* @param options Optionally, options for parsing. When using this, you should set `xmlMode` to `true`.
*/
export declare function parseFeed(feed: string, options?: ParserOptions & DomHandlerOptions): Feed | null;
export * as DomUtils from "domutils";
export { DomHandler as DefaultHandler };
export { FeedHandler as RssHandler } from "./FeedHandler";
//# sourceMappingURL=index.d.ts.map

44

lib/index.js
"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
Object.defineProperty(o, k2, { enumerable: true, get: function() { return m[k]; } });
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {

@@ -21,5 +25,2 @@ if (k2 === undefined) k2 = k;

};
var __exportStar = (this && this.__exportStar) || function(m, exports) {
for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
};
var __importDefault = (this && this.__importDefault) || function (mod) {

@@ -29,5 +30,5 @@ return (mod && mod.__esModule) ? mod : { "default": mod };

Object.defineProperty(exports, "__esModule", { value: true });
exports.RssHandler = exports.DefaultHandler = exports.DomUtils = exports.ElementType = exports.Tokenizer = exports.createDomStream = exports.parseDOM = exports.parseDocument = exports.DomHandler = exports.Parser = void 0;
var Parser_1 = require("./Parser");
Object.defineProperty(exports, "Parser", { enumerable: true, get: function () { return Parser_1.Parser; } });
exports.DefaultHandler = exports.DomUtils = exports.parseFeed = exports.getFeed = exports.ElementType = exports.Tokenizer = exports.createDomStream = exports.parseDOM = exports.parseDocument = exports.DomHandler = exports.Parser = void 0;
var Parser_js_1 = require("./Parser.js");
Object.defineProperty(exports, "Parser", { enumerable: true, get: function () { return Parser_js_1.Parser; } });
var domhandler_1 = require("domhandler");

@@ -45,3 +46,3 @@ Object.defineProperty(exports, "DomHandler", { enumerable: true, get: function () { return domhandler_1.DomHandler; } });

var handler = new domhandler_1.DomHandler(undefined, options);
new Parser_1.Parser(handler, options).end(data);
new Parser_js_1.Parser(handler, options).end(data);
return handler.root;

@@ -73,9 +74,7 @@ }

var handler = new domhandler_1.DomHandler(cb, options, elementCb);
return new Parser_1.Parser(handler, options);
return new Parser_js_1.Parser(handler, options);
}
exports.createDomStream = createDomStream;
var Tokenizer_1 = require("./Tokenizer");
Object.defineProperty(exports, "Tokenizer", { enumerable: true, get: function () { return __importDefault(Tokenizer_1).default; } });
var ElementType = __importStar(require("domelementtype"));
exports.ElementType = ElementType;
var Tokenizer_js_1 = require("./Tokenizer.js");
Object.defineProperty(exports, "Tokenizer", { enumerable: true, get: function () { return __importDefault(Tokenizer_js_1).default; } });
/*

@@ -85,5 +84,18 @@ * All of the following exports exist for backwards-compatibility.

*/
__exportStar(require("./FeedHandler"), exports);
var ElementType = __importStar(require("domelementtype"));
exports.ElementType = ElementType;
var domutils_1 = require("domutils");
Object.defineProperty(exports, "getFeed", { enumerable: true, get: function () { return domutils_1.getFeed; } });
/**
* Parse a feed.
*
* @param feed The feed that should be parsed, as a string.
* @param options Optionally, options for parsing. When using this, you should set `xmlMode` to `true`.
*/
function parseFeed(feed, options) {
if (options === void 0) { options = { xmlMode: true }; }
return (0, domutils_1.getFeed)(parseDOM(feed, options));
}
exports.parseFeed = parseFeed;
exports.DomUtils = __importStar(require("domutils"));
var FeedHandler_1 = require("./FeedHandler");
Object.defineProperty(exports, "RssHandler", { enumerable: true, get: function () { return FeedHandler_1.FeedHandler; } });
//# sourceMappingURL=index.js.map

42

lib/Parser.d.ts

@@ -1,2 +0,2 @@

import Tokenizer from "./Tokenizer";
import Tokenizer, { Callbacks, QuoteType } from "./Tokenizer.js";
export interface ParserOptions {

@@ -79,3 +79,3 @@ /**

}
export declare class Parser {
export declare class Parser implements Callbacks {
private readonly options;

@@ -101,35 +101,43 @@ /** The start index of the last event. */

private readonly tokenizer;
private readonly buffers;
private bufferOffset;
/** The index of the last written buffer. Used when resuming after a `pause()`. */
private writeIndex;
/** Indicates whether the parser has finished running / `.end` has been called. */
private ended;
constructor(cbs?: Partial<Handler> | null, options?: ParserOptions);
/** @internal */
ontext(data: string): void;
ontext(start: number, endIndex: number): void;
/** @internal */
ontextentity(cp: number): void;
protected isVoidElement(name: string): boolean;
/** @internal */
onopentagname(name: string): void;
onopentagname(start: number, endIndex: number): void;
private emitOpenTag;
private endOpenTag;
/** @internal */
onopentagend(): void;
onopentagend(endIndex: number): void;
/** @internal */
onclosetag(name: string): void;
onclosetag(start: number, endIndex: number): void;
/** @internal */
onselfclosingtag(): void;
onselfclosingtag(endIndex: number): void;
private closeCurrentTag;
/** @internal */
onattribname(name: string): void;
onattribname(start: number, endIndex: number): void;
/** @internal */
onattribdata(value: string): void;
onattribdata(start: number, endIndex: number): void;
/** @internal */
onattribend(quote: string | undefined | null): void;
onattribentity(cp: number): void;
/** @internal */
onattribend(quote: QuoteType, endIndex: number): void;
private getInstructionName;
/** @internal */
ondeclaration(value: string): void;
ondeclaration(start: number, endIndex: number): void;
/** @internal */
onprocessinginstruction(value: string): void;
onprocessinginstruction(start: number, endIndex: number): void;
/** @internal */
oncomment(value: string): void;
oncomment(start: number, endIndex: number, offset: number): void;
/** @internal */
oncdata(value: string): void;
oncdata(start: number, endIndex: number, offset: number): void;
/** @internal */
onerror(err: Error): void;
/** @internal */
onend(): void;

@@ -147,2 +155,4 @@ /**

parseComplete(data: string): void;
private getSlice;
private shiftBuffer;
/**

@@ -149,0 +159,0 @@ * Parses a chunk of data and calls the corresponding callbacks.

216

lib/Parser.js
"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
__setModuleDefault(result, mod);
return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.Parser = void 0;
var Tokenizer_1 = __importDefault(require("./Tokenizer"));
var Tokenizer_js_1 = __importStar(require("./Tokenizer.js"));
var decode_js_1 = require("entities/lib/decode.js");
var formTags = new Set([

@@ -124,2 +145,8 @@ "input",

this.foreignContext = [];
this.buffers = [];
this.bufferOffset = 0;
/** The index of the last written buffer. Used when resuming after a `pause()`. */
this.writeIndex = 0;
/** Indicates whether the parser has finished running / `.end` has been called. */
this.ended = false;
this.cbs = cbs !== null && cbs !== void 0 ? cbs : {};

@@ -129,3 +156,3 @@ this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : !options.xmlMode;

(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : !options.xmlMode;
this.tokenizer = new ((_c = options.Tokenizer) !== null && _c !== void 0 ? _c : Tokenizer_1.default)(this.options, this);
this.tokenizer = new ((_c = options.Tokenizer) !== null && _c !== void 0 ? _c : Tokenizer_js_1.default)(this.options, this);
(_e = (_d = this.cbs).onparserinit) === null || _e === void 0 ? void 0 : _e.call(_d, this);

@@ -135,7 +162,19 @@ }

/** @internal */
Parser.prototype.ontext = function (data) {
Parser.prototype.ontext = function (start, endIndex) {
var _a, _b;
var idx = this.tokenizer.getAbsoluteIndex();
var data = this.getSlice(start, endIndex);
this.endIndex = endIndex - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, data);
this.startIndex = endIndex;
};
/** @internal */
Parser.prototype.ontextentity = function (cp) {
var _a, _b;
/*
* Entities can be emitted on the character, or directly after.
* We use the section start here to get accurate indices.
*/
var idx = this.tokenizer.getSectionStart();
this.endIndex = idx - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, data);
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, (0, decode_js_1.fromCodePoint)(cp));
this.startIndex = idx;

@@ -147,4 +186,5 @@ };

/** @internal */
Parser.prototype.onopentagname = function (name) {
this.endIndex = this.tokenizer.getAbsoluteIndex();
Parser.prototype.onopentagname = function (start, endIndex) {
this.endIndex = endIndex;
var name = this.getSlice(start, endIndex);
if (this.lowerCaseTagNames) {

@@ -183,3 +223,2 @@ name = name.toLowerCase();

this.startIndex = this.openTagStart;
this.endIndex = this.tokenizer.getAbsoluteIndex();
if (this.attribs) {

@@ -195,11 +234,13 @@ (_b = (_a = this.cbs).onopentag) === null || _b === void 0 ? void 0 : _b.call(_a, this.tagname, this.attribs, isImplied);

/** @internal */
Parser.prototype.onopentagend = function () {
Parser.prototype.onopentagend = function (endIndex) {
this.endIndex = endIndex;
this.endOpenTag(false);
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onclosetag = function (name) {
Parser.prototype.onclosetag = function (start, endIndex) {
var _a, _b, _c, _d, _e, _f;
this.endIndex = this.tokenizer.getAbsoluteIndex();
this.endIndex = endIndex;
var name = this.getSlice(start, endIndex);
if (this.lowerCaseTagNames) {

@@ -226,3 +267,4 @@ name = name.toLowerCase();

else if (!this.options.xmlMode && name === "p") {
this.emitOpenTag(name);
// Implicit open before close
this.emitOpenTag("p");
this.closeCurrentTag(true);

@@ -232,12 +274,13 @@ }

else if (!this.options.xmlMode && name === "br") {
// We can't go through `emitOpenTag` here, as `br` would be implicitly closed.
(_b = (_a = this.cbs).onopentagname) === null || _b === void 0 ? void 0 : _b.call(_a, name);
(_d = (_c = this.cbs).onopentag) === null || _d === void 0 ? void 0 : _d.call(_c, name, {}, true);
(_f = (_e = this.cbs).onclosetag) === null || _f === void 0 ? void 0 : _f.call(_e, name, false);
// We can't use `emitOpenTag` for implicit open, as `br` would be implicitly closed.
(_b = (_a = this.cbs).onopentagname) === null || _b === void 0 ? void 0 : _b.call(_a, "br");
(_d = (_c = this.cbs).onopentag) === null || _d === void 0 ? void 0 : _d.call(_c, "br", {}, true);
(_f = (_e = this.cbs).onclosetag) === null || _f === void 0 ? void 0 : _f.call(_e, "br", false);
}
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onselfclosingtag = function () {
Parser.prototype.onselfclosingtag = function (endIndex) {
this.endIndex = endIndex;
if (this.options.xmlMode ||

@@ -248,7 +291,7 @@ this.options.recognizeSelfClosing ||

// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
}
else {
// Ignore the fact that the tag is self-closing.
this.onopentagend();
this.onopentagend(endIndex);
}

@@ -268,18 +311,28 @@ };

/** @internal */
Parser.prototype.onattribname = function (name) {
this.startIndex = this.tokenizer.getAbsoluteSectionStart();
if (this.lowerCaseAttributeNames) {
name = name.toLowerCase();
}
this.attribname = name;
Parser.prototype.onattribname = function (start, endIndex) {
this.startIndex = start;
var name = this.getSlice(start, endIndex);
this.attribname = this.lowerCaseAttributeNames
? name.toLowerCase()
: name;
};
/** @internal */
Parser.prototype.onattribdata = function (value) {
this.attribvalue += value;
Parser.prototype.onattribdata = function (start, endIndex) {
this.attribvalue += this.getSlice(start, endIndex);
};
/** @internal */
Parser.prototype.onattribend = function (quote) {
Parser.prototype.onattribentity = function (cp) {
this.attribvalue += (0, decode_js_1.fromCodePoint)(cp);
};
/** @internal */
Parser.prototype.onattribend = function (quote, endIndex) {
var _a, _b;
this.endIndex = this.tokenizer.getAbsoluteIndex();
(_b = (_a = this.cbs).onattribute) === null || _b === void 0 ? void 0 : _b.call(_a, this.attribname, this.attribvalue, quote);
this.endIndex = endIndex;
(_b = (_a = this.cbs).onattribute) === null || _b === void 0 ? void 0 : _b.call(_a, this.attribname, this.attribvalue, quote === Tokenizer_js_1.QuoteType.Double
? '"'
: quote === Tokenizer_js_1.QuoteType.Single
? "'"
: quote === Tokenizer_js_1.QuoteType.NoValue
? undefined
: null);
if (this.attribs &&

@@ -289,3 +342,2 @@ !Object.prototype.hasOwnProperty.call(this.attribs, this.attribname)) {

}
this.attribname = "";
this.attribvalue = "";

@@ -302,34 +354,37 @@ };

/** @internal */
Parser.prototype.ondeclaration = function (value) {
this.endIndex = this.tokenizer.getAbsoluteIndex();
Parser.prototype.ondeclaration = function (start, endIndex) {
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex);
if (this.cbs.onprocessinginstruction) {
var name_1 = this.getInstructionName(value);
this.cbs.onprocessinginstruction("!" + name_1, "!" + value);
var name = this.getInstructionName(value);
this.cbs.onprocessinginstruction("!".concat(name), "!".concat(value));
}
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onprocessinginstruction = function (value) {
this.endIndex = this.tokenizer.getAbsoluteIndex();
Parser.prototype.onprocessinginstruction = function (start, endIndex) {
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex);
if (this.cbs.onprocessinginstruction) {
var name_2 = this.getInstructionName(value);
this.cbs.onprocessinginstruction("?" + name_2, "?" + value);
var name = this.getInstructionName(value);
this.cbs.onprocessinginstruction("?".concat(name), "?".concat(value));
}
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.oncomment = function (value) {
Parser.prototype.oncomment = function (start, endIndex, offset) {
var _a, _b, _c, _d;
this.endIndex = this.tokenizer.getAbsoluteIndex();
(_b = (_a = this.cbs).oncomment) === null || _b === void 0 ? void 0 : _b.call(_a, value);
this.endIndex = endIndex;
(_b = (_a = this.cbs).oncomment) === null || _b === void 0 ? void 0 : _b.call(_a, this.getSlice(start, endIndex - offset));
(_d = (_c = this.cbs).oncommentend) === null || _d === void 0 ? void 0 : _d.call(_c);
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.oncdata = function (value) {
Parser.prototype.oncdata = function (start, endIndex, offset) {
var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k;
this.endIndex = this.tokenizer.getAbsoluteIndex();
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex - offset);
if (this.options.xmlMode || this.options.recognizeCDATA) {

@@ -341,14 +396,9 @@ (_b = (_a = this.cbs).oncdatastart) === null || _b === void 0 ? void 0 : _b.call(_a);

else {
(_h = (_g = this.cbs).oncomment) === null || _h === void 0 ? void 0 : _h.call(_g, "[CDATA[" + value + "]]");
(_h = (_g = this.cbs).oncomment) === null || _h === void 0 ? void 0 : _h.call(_g, "[CDATA[".concat(value, "]]"));
(_k = (_j = this.cbs).oncommentend) === null || _k === void 0 ? void 0 : _k.call(_j);
}
// Set `startIndex` for next node
this.startIndex = this.endIndex + 1;
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onerror = function (err) {
var _a, _b;
(_b = (_a = this.cbs).onerror) === null || _b === void 0 ? void 0 : _b.call(_a, err);
};
/** @internal */
Parser.prototype.onend = function () {

@@ -374,6 +424,10 @@ var _a, _b;

this.attribs = null;
this.stack = [];
this.stack.length = 0;
this.startIndex = 0;
this.endIndex = 0;
(_d = (_c = this.cbs).onparserinit) === null || _d === void 0 ? void 0 : _d.call(_c, this);
this.buffers.length = 0;
this.bufferOffset = 0;
this.writeIndex = 0;
this.ended = false;
};

@@ -390,2 +444,18 @@ /**

};
Parser.prototype.getSlice = function (start, end) {
while (start - this.bufferOffset >= this.buffers[0].length) {
this.shiftBuffer();
}
var str = this.buffers[0].slice(start - this.bufferOffset, end - this.bufferOffset);
while (end - this.bufferOffset > this.buffers[0].length) {
this.shiftBuffer();
str += this.buffers[0].slice(0, end - this.bufferOffset);
}
return str;
};
Parser.prototype.shiftBuffer = function () {
this.bufferOffset += this.buffers[0].length;
this.writeIndex--;
this.buffers.shift();
};
/**

@@ -397,3 +467,12 @@ * Parses a chunk of data and calls the corresponding callbacks.

Parser.prototype.write = function (chunk) {
this.tokenizer.write(chunk);
var _a, _b;
if (this.ended) {
(_b = (_a = this.cbs).onerror) === null || _b === void 0 ? void 0 : _b.call(_a, new Error(".write() after done!"));
return;
}
this.buffers.push(chunk);
if (this.tokenizer.running) {
this.tokenizer.write(chunk);
this.writeIndex++;
}
};

@@ -406,3 +485,11 @@ /**

Parser.prototype.end = function (chunk) {
this.tokenizer.end(chunk);
var _a, _b;
if (this.ended) {
(_b = (_a = this.cbs).onerror) === null || _b === void 0 ? void 0 : _b.call(_a, Error(".end() after done!"));
return;
}
if (chunk)
this.write(chunk);
this.ended = true;
this.tokenizer.end();
};

@@ -420,2 +507,8 @@ /**

this.tokenizer.resume();
while (this.tokenizer.running &&
this.writeIndex < this.buffers.length) {
this.tokenizer.write(this.buffers[this.writeIndex++]);
}
if (this.ended)
this.tokenizer.end();
};

@@ -443,1 +536,2 @@ /**

exports.Parser = Parser;
//# sourceMappingURL=Parser.js.map

98

lib/Tokenizer.d.ts

@@ -1,48 +0,23 @@

/** All the states the tokenizer can be in. */
declare const enum State {
Text = 1,
BeforeTagName = 2,
InTagName = 3,
InSelfClosingTag = 4,
BeforeClosingTagName = 5,
InClosingTagName = 6,
AfterClosingTagName = 7,
BeforeAttributeName = 8,
InAttributeName = 9,
AfterAttributeName = 10,
BeforeAttributeValue = 11,
InAttributeValueDq = 12,
InAttributeValueSq = 13,
InAttributeValueNq = 14,
BeforeDeclaration = 15,
InDeclaration = 16,
InProcessingInstruction = 17,
BeforeComment = 18,
CDATASequence = 19,
InSpecialComment = 20,
InCommentLike = 21,
BeforeSpecialS = 22,
SpecialStartSequence = 23,
InSpecialTag = 24,
BeforeEntity = 25,
BeforeNumericEntity = 26,
InNamedEntity = 27,
InNumericEntity = 28,
InHexEntity = 29
export declare enum QuoteType {
NoValue = 0,
Unquoted = 1,
Single = 2,
Double = 3
}
export interface Callbacks {
onattribdata(value: string): void;
onattribend(quote: string | undefined | null): void;
onattribname(name: string): void;
oncdata(data: string): void;
onclosetag(name: string): void;
oncomment(data: string): void;
ondeclaration(content: string): void;
onattribdata(start: number, endIndex: number): void;
onattribentity(codepoint: number): void;
onattribend(quote: QuoteType, endIndex: number): void;
onattribname(start: number, endIndex: number): void;
oncdata(start: number, endIndex: number, endOffset: number): void;
onclosetag(start: number, endIndex: number): void;
oncomment(start: number, endIndex: number, endOffset: number): void;
ondeclaration(start: number, endIndex: number): void;
onend(): void;
onerror(error: Error, state?: State): void;
onopentagend(): void;
onopentagname(name: string): void;
onprocessinginstruction(instruction: string): void;
onselfclosingtag(): void;
ontext(value: string): void;
onopentagend(endIndex: number): void;
onopentagname(start: number, endIndex: number): void;
onprocessinginstruction(start: number, endIndex: number): void;
onselfclosingtag(endIndex: number): void;
ontext(start: number, endIndex: number): void;
ontextentity(codepoint: number): void;
}

@@ -52,14 +27,9 @@ export default class Tokenizer {

/** The current state the tokenizer is in. */
private _state;
private state;
/** The read buffer. */
private buffer;
/** The beginning of the section that is currently being read. */
sectionStart: number;
private sectionStart;
/** The index within the buffer that we are currently looking at. */
private _index;
/**
* Data that has already been processed will be removed from the buffer occasionally.
* `_bufferOffset` keeps track of how many characters have been removed, to make sure position information is accurate.
*/
private bufferOffset;
private index;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */

@@ -70,5 +40,5 @@ private baseState;

/** Indicates whether the tokenizer has been paused. */
private running;
/** Indicates whether the tokenizer has finished running / `.end` has been called. */
private ended;
running: boolean;
/** The offset of the current buffer. */
private offset;
private readonly xmlMode;

@@ -83,13 +53,13 @@ private readonly decodeEntities;

write(chunk: string): void;
end(chunk?: string): void;
end(): void;
pause(): void;
resume(): void;
/**
* The start of the current section.
* The current index within all of the written data.
*/
getAbsoluteSectionStart(): number;
getIndex(): number;
/**
* The current index within all of the written data.
* The start of the current section.
*/
getAbsoluteIndex(): number;
getSectionStart(): number;
private stateText;

@@ -148,3 +118,4 @@ private currentSequence;

private trieCurrent;
private trieResult;
/** For named entities, the index of the value. For numeric entities, the code point. */
private entityResult;
private entityExcess;

@@ -155,3 +126,3 @@ private stateBeforeEntity;

private stateBeforeNumericEntity;
private decodeNumericEntity;
private emitNumericEntity;
private stateInNumericEntity;

@@ -174,6 +145,5 @@ private stateInHexEntity;

private handleTrailingData;
private getSection;
private emitPartial;
private emitCodePoint;
}
export {};
//# sourceMappingURL=Tokenizer.d.ts.map

729

lib/Tokenizer.js
"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
var decode_codepoint_1 = __importDefault(require("entities/lib/decode_codepoint"));
var decode_1 = require("entities/lib/decode");
exports.QuoteType = void 0;
var decode_js_1 = require("entities/lib/decode.js");
var CharCodes;
(function (CharCodes) {
CharCodes[CharCodes["Tab"] = 9] = "Tab";
CharCodes[CharCodes["NewLine"] = 10] = "NewLine";
CharCodes[CharCodes["FormFeed"] = 12] = "FormFeed";
CharCodes[CharCodes["CarriageReturn"] = 13] = "CarriageReturn";
CharCodes[CharCodes["Space"] = 32] = "Space";
CharCodes[CharCodes["ExclamationMark"] = 33] = "ExclamationMark";
CharCodes[CharCodes["Num"] = 35] = "Num";
CharCodes[CharCodes["Amp"] = 38] = "Amp";
CharCodes[CharCodes["SingleQuote"] = 39] = "SingleQuote";
CharCodes[CharCodes["DoubleQuote"] = 34] = "DoubleQuote";
CharCodes[CharCodes["Dash"] = 45] = "Dash";
CharCodes[CharCodes["Slash"] = 47] = "Slash";
CharCodes[CharCodes["Zero"] = 48] = "Zero";
CharCodes[CharCodes["Nine"] = 57] = "Nine";
CharCodes[CharCodes["Semi"] = 59] = "Semi";
CharCodes[CharCodes["Lt"] = 60] = "Lt";
CharCodes[CharCodes["Eq"] = 61] = "Eq";
CharCodes[CharCodes["Gt"] = 62] = "Gt";
CharCodes[CharCodes["Questionmark"] = 63] = "Questionmark";
CharCodes[CharCodes["UpperA"] = 65] = "UpperA";
CharCodes[CharCodes["LowerA"] = 97] = "LowerA";
CharCodes[CharCodes["UpperF"] = 70] = "UpperF";
CharCodes[CharCodes["LowerF"] = 102] = "LowerF";
CharCodes[CharCodes["UpperZ"] = 90] = "UpperZ";
CharCodes[CharCodes["LowerZ"] = 122] = "LowerZ";
CharCodes[CharCodes["LowerX"] = 120] = "LowerX";
CharCodes[CharCodes["OpeningSquareBracket"] = 91] = "OpeningSquareBracket";
})(CharCodes || (CharCodes = {}));
/** All the states the tokenizer can be in. */
var State;
(function (State) {
State[State["Text"] = 1] = "Text";
State[State["BeforeTagName"] = 2] = "BeforeTagName";
State[State["InTagName"] = 3] = "InTagName";
State[State["InSelfClosingTag"] = 4] = "InSelfClosingTag";
State[State["BeforeClosingTagName"] = 5] = "BeforeClosingTagName";
State[State["InClosingTagName"] = 6] = "InClosingTagName";
State[State["AfterClosingTagName"] = 7] = "AfterClosingTagName";
// Attributes
State[State["BeforeAttributeName"] = 8] = "BeforeAttributeName";
State[State["InAttributeName"] = 9] = "InAttributeName";
State[State["AfterAttributeName"] = 10] = "AfterAttributeName";
State[State["BeforeAttributeValue"] = 11] = "BeforeAttributeValue";
State[State["InAttributeValueDq"] = 12] = "InAttributeValueDq";
State[State["InAttributeValueSq"] = 13] = "InAttributeValueSq";
State[State["InAttributeValueNq"] = 14] = "InAttributeValueNq";
// Declarations
State[State["BeforeDeclaration"] = 15] = "BeforeDeclaration";
State[State["InDeclaration"] = 16] = "InDeclaration";
// Processing instructions
State[State["InProcessingInstruction"] = 17] = "InProcessingInstruction";
// Comments & CDATA
State[State["BeforeComment"] = 18] = "BeforeComment";
State[State["CDATASequence"] = 19] = "CDATASequence";
State[State["InSpecialComment"] = 20] = "InSpecialComment";
State[State["InCommentLike"] = 21] = "InCommentLike";
// Special tags
State[State["BeforeSpecialS"] = 22] = "BeforeSpecialS";
State[State["SpecialStartSequence"] = 23] = "SpecialStartSequence";
State[State["InSpecialTag"] = 24] = "InSpecialTag";
State[State["BeforeEntity"] = 25] = "BeforeEntity";
State[State["BeforeNumericEntity"] = 26] = "BeforeNumericEntity";
State[State["InNamedEntity"] = 27] = "InNamedEntity";
State[State["InNumericEntity"] = 28] = "InNumericEntity";
State[State["InHexEntity"] = 29] = "InHexEntity";
})(State || (State = {}));
function isWhitespace(c) {
return (c === 32 /* Space */ ||
c === 10 /* NewLine */ ||
c === 9 /* Tab */ ||
c === 12 /* FormFeed */ ||
c === 13 /* CarriageReturn */);
return (c === CharCodes.Space ||
c === CharCodes.NewLine ||
c === CharCodes.Tab ||
c === CharCodes.FormFeed ||
c === CharCodes.CarriageReturn);
}
function isEndOfTagSection(c) {
return c === 47 /* Slash */ || c === 62 /* Gt */ || isWhitespace(c);
return c === CharCodes.Slash || c === CharCodes.Gt || isWhitespace(c);
}
function isNumber(c) {
return c >= 48 /* Zero */ && c <= 57 /* Nine */;
return c >= CharCodes.Zero && c <= CharCodes.Nine;
}
function isASCIIAlpha(c) {
return ((c >= 97 /* LowerA */ && c <= 122 /* LowerZ */) ||
(c >= 65 /* UpperA */ && c <= 90 /* UpperZ */));
return ((c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||
(c >= CharCodes.UpperA && c <= CharCodes.UpperZ));
}
function isHexDigit(c) {
return ((c >= CharCodes.UpperA && c <= CharCodes.UpperF) ||
(c >= CharCodes.LowerA && c <= CharCodes.LowerF));
}
var QuoteType;
(function (QuoteType) {
QuoteType[QuoteType["NoValue"] = 0] = "NoValue";
QuoteType[QuoteType["Unquoted"] = 1] = "Unquoted";
QuoteType[QuoteType["Single"] = 2] = "Single";
QuoteType[QuoteType["Double"] = 3] = "Double";
})(QuoteType = exports.QuoteType || (exports.QuoteType = {}));
/**

@@ -32,10 +108,8 @@ * Sequences used to match longer strings.

var Sequences = {
Cdata: new Uint16Array([0x43, 0x44, 0x41, 0x54, 0x41, 0x5b]),
CdataEnd: new Uint16Array([0x5d, 0x5d, 0x3e]),
CommentEnd: new Uint16Array([0x2d, 0x2d, 0x3e]),
ScriptEnd: new Uint16Array([
0x3c, 0x2f, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74,
]),
StyleEnd: new Uint16Array([0x3c, 0x2f, 0x73, 0x74, 0x79, 0x6c, 0x65]),
TitleEnd: new Uint16Array([0x3c, 0x2f, 0x74, 0x69, 0x74, 0x6c, 0x65]), // `</title`
Cdata: new Uint8Array([0x43, 0x44, 0x41, 0x54, 0x41, 0x5b]),
CdataEnd: new Uint8Array([0x5d, 0x5d, 0x3e]),
CommentEnd: new Uint8Array([0x2d, 0x2d, 0x3e]),
ScriptEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74]),
StyleEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x74, 0x79, 0x6c, 0x65]),
TitleEnd: new Uint8Array([0x3c, 0x2f, 0x74, 0x69, 0x74, 0x6c, 0x65]), // `</title`
};

@@ -47,3 +121,3 @@ var Tokenizer = /** @class */ (function () {

/** The current state the tokenizer is in. */
this._state = 1 /* Text */;
this.state = State.Text;
/** The read buffer. */

@@ -54,10 +128,5 @@ this.buffer = "";

/** The index within the buffer that we are currently looking at. */
this._index = 0;
/**
* Data that has already been processed will be removed from the buffer occasionally.
* `_bufferOffset` keeps track of how many characters have been removed, to make sure position information is accurate.
*/
this.bufferOffset = 0;
this.index = 0;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
this.baseState = 1 /* Text */;
this.baseState = State.Text;
/** For special parsing behavior inside of script and style tags. */

@@ -67,36 +136,30 @@ this.isSpecial = false;

this.running = true;
/** Indicates whether the tokenizer has finished running / `.end` has been called. */
this.ended = false;
/** The offset of the current buffer. */
this.offset = 0;
this.sequenceIndex = 0;
this.trieIndex = 0;
this.trieCurrent = 0;
this.trieResult = null;
/** For named entities, the index of the value. For numeric entities, the code point. */
this.entityResult = 0;
this.entityExcess = 0;
this.xmlMode = xmlMode;
this.decodeEntities = decodeEntities;
this.entityTrie = xmlMode ? decode_1.xmlDecodeTree : decode_1.htmlDecodeTree;
this.entityTrie = xmlMode ? decode_js_1.xmlDecodeTree : decode_js_1.htmlDecodeTree;
}
Tokenizer.prototype.reset = function () {
this._state = 1 /* Text */;
this.state = State.Text;
this.buffer = "";
this.sectionStart = 0;
this._index = 0;
this.bufferOffset = 0;
this.baseState = 1 /* Text */;
this.index = 0;
this.baseState = State.Text;
this.currentSequence = undefined;
this.running = true;
this.ended = false;
this.offset = 0;
};
Tokenizer.prototype.write = function (chunk) {
if (this.ended)
return this.cbs.onerror(Error(".write() after done!"));
this.buffer += chunk;
this.offset += this.buffer.length;
this.buffer = chunk;
this.parse();
};
Tokenizer.prototype.end = function (chunk) {
if (this.ended)
return this.cbs.onerror(Error(".end() after done!"));
if (chunk)
this.write(chunk);
this.ended = true;
Tokenizer.prototype.end = function () {
if (this.running)

@@ -110,32 +173,29 @@ this.finish();

this.running = true;
if (this._index < this.buffer.length) {
if (this.index < this.buffer.length + this.offset) {
this.parse();
}
if (this.ended) {
this.finish();
}
};
/**
* The start of the current section.
* The current index within all of the written data.
*/
Tokenizer.prototype.getAbsoluteSectionStart = function () {
return this.sectionStart + this.bufferOffset;
Tokenizer.prototype.getIndex = function () {
return this.index;
};
/**
* The current index within all of the written data.
* The start of the current section.
*/
Tokenizer.prototype.getAbsoluteIndex = function () {
return this.bufferOffset + this._index;
Tokenizer.prototype.getSectionStart = function () {
return this.sectionStart;
};
Tokenizer.prototype.stateText = function (c) {
if (c === 60 /* Lt */ ||
(!this.decodeEntities && this.fastForwardTo(60 /* Lt */))) {
if (this._index > this.sectionStart) {
this.cbs.ontext(this.getSection());
if (c === CharCodes.Lt ||
(!this.decodeEntities && this.fastForwardTo(CharCodes.Lt))) {
if (this.index > this.sectionStart) {
this.cbs.ontext(this.sectionStart, this.index);
}
this._state = 2 /* BeforeTagName */;
this.sectionStart = this._index;
this.state = State.BeforeTagName;
this.sectionStart = this.index;
}
else if (this.decodeEntities && c === 38 /* Amp */) {
this._state = 25 /* BeforeEntity */;
else if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
}

@@ -158,3 +218,3 @@ };

this.sequenceIndex = 0;
this._state = 3 /* InTagName */;
this.state = State.InTagName;
this.stateInTagName(c);

@@ -165,10 +225,10 @@ };

if (this.sequenceIndex === this.currentSequence.length) {
if (c === 62 /* Gt */ || isWhitespace(c)) {
var endOfText = this._index - this.currentSequence.length;
if (c === CharCodes.Gt || isWhitespace(c)) {
var endOfText = this.index - this.currentSequence.length;
if (this.sectionStart < endOfText) {
// Spoof the index so that reported locations match up.
var actualIndex = this._index;
this._index = endOfText;
this.cbs.ontext(this.getSection());
this._index = actualIndex;
var actualIndex = this.index;
this.index = endOfText;
this.cbs.ontext(this.sectionStart, endOfText);
this.index = actualIndex;
}

@@ -188,7 +248,7 @@ this.isSpecial = false;

// We have to parse entities in <title> tags.
if (this.decodeEntities && c === 38 /* Amp */) {
this._state = 25 /* BeforeEntity */;
if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
}
}
else if (this.fastForwardTo(60 /* Lt */)) {
else if (this.fastForwardTo(CharCodes.Lt)) {
// Outside of <title> tags, we can fast-forward.

@@ -200,3 +260,3 @@ this.sequenceIndex = 1;

// If we see a `<`, set the sequence index to 1; useful for eg. `<</script>`.
this.sequenceIndex = Number(c === 60 /* Lt */);
this.sequenceIndex = Number(c === CharCodes.Lt);
}

@@ -207,6 +267,6 @@ };

if (++this.sequenceIndex === Sequences.Cdata.length) {
this._state = 21 /* InCommentLike */;
this.state = State.InCommentLike;
this.currentSequence = Sequences.CdataEnd;
this.sequenceIndex = 0;
this.sectionStart = this._index + 1;
this.sectionStart = this.index + 1;
}

@@ -216,3 +276,3 @@ }

this.sequenceIndex = 0;
this._state = 16 /* InDeclaration */;
this.state = State.InDeclaration;
this.stateInDeclaration(c); // Reconsume the character

@@ -228,4 +288,4 @@ }

Tokenizer.prototype.fastForwardTo = function (c) {
while (++this._index < this.buffer.length) {
if (this.buffer.charCodeAt(this._index) === c) {
while (++this.index < this.buffer.length + this.offset) {
if (this.buffer.charCodeAt(this.index - this.offset) === c) {
return true;

@@ -240,3 +300,3 @@ }

*/
this._index = this.buffer.length - 1;
this.index = this.buffer.length + this.offset - 1;
return false;

@@ -255,13 +315,11 @@ };

if (++this.sequenceIndex === this.currentSequence.length) {
// Remove 2 trailing chars
var section = this.buffer.slice(this.sectionStart, this._index - 2);
if (this.currentSequence === Sequences.CdataEnd) {
this.cbs.oncdata(section);
this.cbs.oncdata(this.sectionStart, this.index, 2);
}
else {
this.cbs.oncomment(section);
this.cbs.oncomment(this.sectionStart, this.index, 2);
}
this.sequenceIndex = 0;
this.sectionStart = this._index + 1;
this._state = 1 /* Text */;
this.sectionStart = this.index + 1;
this.state = State.Text;
}

@@ -293,16 +351,16 @@ }

this.sequenceIndex = offset;
this._state = 23 /* SpecialStartSequence */;
this.state = State.SpecialStartSequence;
};
Tokenizer.prototype.stateBeforeTagName = function (c) {
if (c === 33 /* ExclamationMark */) {
this._state = 15 /* BeforeDeclaration */;
this.sectionStart = this._index + 1;
if (c === CharCodes.ExclamationMark) {
this.state = State.BeforeDeclaration;
this.sectionStart = this.index + 1;
}
else if (c === 63 /* Questionmark */) {
this._state = 17 /* InProcessingInstruction */;
this.sectionStart = this._index + 1;
else if (c === CharCodes.Questionmark) {
this.state = State.InProcessingInstruction;
this.sectionStart = this.index + 1;
}
else if (this.isTagStartChar(c)) {
var lower = c | 0x20;
this.sectionStart = this._index;
this.sectionStart = this.index;
if (!this.xmlMode && lower === Sequences.TitleEnd[2]) {

@@ -312,13 +370,13 @@ this.startSpecial(Sequences.TitleEnd, 3);

else {
this._state =
this.state =
!this.xmlMode && lower === Sequences.ScriptEnd[2]
? 22 /* BeforeSpecialS */
: 3 /* InTagName */;
? State.BeforeSpecialS
: State.InTagName;
}
}
else if (c === 47 /* Slash */) {
this._state = 5 /* BeforeClosingTagName */;
else if (c === CharCodes.Slash) {
this.state = State.BeforeClosingTagName;
}
else {
this._state = 1 /* Text */;
this.state = State.Text;
this.stateText(c);

@@ -329,5 +387,5 @@ }

if (isEndOfTagSection(c)) {
this.cbs.onopentagname(this.getSection());
this.cbs.onopentagname(this.sectionStart, this.index);
this.sectionStart = -1;
this._state = 8 /* BeforeAttributeName */;
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);

@@ -340,17 +398,17 @@ }

}
else if (c === 62 /* Gt */) {
this._state = 1 /* Text */;
else if (c === CharCodes.Gt) {
this.state = State.Text;
}
else {
this._state = this.isTagStartChar(c)
? 6 /* InClosingTagName */
: 20 /* InSpecialComment */;
this.sectionStart = this._index;
this.state = this.isTagStartChar(c)
? State.InClosingTagName
: State.InSpecialComment;
this.sectionStart = this.index;
}
};
Tokenizer.prototype.stateInClosingTagName = function (c) {
if (c === 62 /* Gt */ || isWhitespace(c)) {
this.cbs.onclosetag(this.getSection());
if (c === CharCodes.Gt || isWhitespace(c)) {
this.cbs.onclosetag(this.sectionStart, this.index);
this.sectionStart = -1;
this._state = 7 /* AfterClosingTagName */;
this.state = State.AfterClosingTagName;
this.stateAfterClosingTagName(c);

@@ -361,38 +419,38 @@ }

// Skip everything until ">"
if (c === 62 /* Gt */ || this.fastForwardTo(62 /* Gt */)) {
this._state = 1 /* Text */;
this.sectionStart = this._index + 1;
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.state = State.Text;
this.sectionStart = this.index + 1;
}
};
Tokenizer.prototype.stateBeforeAttributeName = function (c) {
if (c === 62 /* Gt */) {
this.cbs.onopentagend();
if (c === CharCodes.Gt) {
this.cbs.onopentagend(this.index);
if (this.isSpecial) {
this._state = 24 /* InSpecialTag */;
this.state = State.InSpecialTag;
this.sequenceIndex = 0;
}
else {
this._state = 1 /* Text */;
this.state = State.Text;
}
this.baseState = this._state;
this.sectionStart = this._index + 1;
this.baseState = this.state;
this.sectionStart = this.index + 1;
}
else if (c === 47 /* Slash */) {
this._state = 4 /* InSelfClosingTag */;
else if (c === CharCodes.Slash) {
this.state = State.InSelfClosingTag;
}
else if (!isWhitespace(c)) {
this._state = 9 /* InAttributeName */;
this.sectionStart = this._index;
this.state = State.InAttributeName;
this.sectionStart = this.index;
}
};
Tokenizer.prototype.stateInSelfClosingTag = function (c) {
if (c === 62 /* Gt */) {
this.cbs.onselfclosingtag();
this._state = 1 /* Text */;
this.baseState = 1 /* Text */;
this.sectionStart = this._index + 1;
if (c === CharCodes.Gt) {
this.cbs.onselfclosingtag(this.index);
this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;
this.isSpecial = false; // Reset special state, in case of self-closing special tags
}
else if (!isWhitespace(c)) {
this._state = 8 /* BeforeAttributeName */;
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);

@@ -402,6 +460,6 @@ }

Tokenizer.prototype.stateInAttributeName = function (c) {
if (c === 61 /* Eq */ || isEndOfTagSection(c)) {
this.cbs.onattribname(this.getSection());
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.onattribname(this.sectionStart, this.index);
this.sectionStart = -1;
this._state = 10 /* AfterAttributeName */;
this.state = State.AfterAttributeName;
this.stateAfterAttributeName(c);

@@ -411,28 +469,28 @@ }

Tokenizer.prototype.stateAfterAttributeName = function (c) {
if (c === 61 /* Eq */) {
this._state = 11 /* BeforeAttributeValue */;
if (c === CharCodes.Eq) {
this.state = State.BeforeAttributeValue;
}
else if (c === 47 /* Slash */ || c === 62 /* Gt */) {
this.cbs.onattribend(undefined);
this._state = 8 /* BeforeAttributeName */;
else if (c === CharCodes.Slash || c === CharCodes.Gt) {
this.cbs.onattribend(QuoteType.NoValue, this.index);
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
else if (!isWhitespace(c)) {
this.cbs.onattribend(undefined);
this._state = 9 /* InAttributeName */;
this.sectionStart = this._index;
this.cbs.onattribend(QuoteType.NoValue, this.index);
this.state = State.InAttributeName;
this.sectionStart = this.index;
}
};
Tokenizer.prototype.stateBeforeAttributeValue = function (c) {
if (c === 34 /* DoubleQuote */) {
this._state = 12 /* InAttributeValueDq */;
this.sectionStart = this._index + 1;
if (c === CharCodes.DoubleQuote) {
this.state = State.InAttributeValueDq;
this.sectionStart = this.index + 1;
}
else if (c === 39 /* SingleQuote */) {
this._state = 13 /* InAttributeValueSq */;
this.sectionStart = this._index + 1;
else if (c === CharCodes.SingleQuote) {
this.state = State.InAttributeValueSq;
this.sectionStart = this.index + 1;
}
else if (!isWhitespace(c)) {
this.sectionStart = this._index;
this._state = 14 /* InAttributeValueNq */;
this.sectionStart = this.index;
this.state = State.InAttributeValueNq;
this.stateInAttributeValueNoQuotes(c); // Reconsume token

@@ -444,74 +502,76 @@ }

(!this.decodeEntities && this.fastForwardTo(quote))) {
this.cbs.onattribdata(this.getSection());
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = -1;
this.cbs.onattribend(String.fromCharCode(quote));
this._state = 8 /* BeforeAttributeName */;
this.cbs.onattribend(quote === CharCodes.DoubleQuote
? QuoteType.Double
: QuoteType.Single, this.index);
this.state = State.BeforeAttributeName;
}
else if (this.decodeEntities && c === 38 /* Amp */) {
this.baseState = this._state;
this._state = 25 /* BeforeEntity */;
else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
}
};
Tokenizer.prototype.stateInAttributeValueDoubleQuotes = function (c) {
this.handleInAttributeValue(c, 34 /* DoubleQuote */);
this.handleInAttributeValue(c, CharCodes.DoubleQuote);
};
Tokenizer.prototype.stateInAttributeValueSingleQuotes = function (c) {
this.handleInAttributeValue(c, 39 /* SingleQuote */);
this.handleInAttributeValue(c, CharCodes.SingleQuote);
};
Tokenizer.prototype.stateInAttributeValueNoQuotes = function (c) {
if (isWhitespace(c) || c === 62 /* Gt */) {
this.cbs.onattribdata(this.getSection());
if (isWhitespace(c) || c === CharCodes.Gt) {
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = -1;
this.cbs.onattribend(null);
this._state = 8 /* BeforeAttributeName */;
this.cbs.onattribend(QuoteType.Unquoted, this.index);
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
else if (this.decodeEntities && c === 38 /* Amp */) {
this.baseState = this._state;
this._state = 25 /* BeforeEntity */;
else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
}
};
Tokenizer.prototype.stateBeforeDeclaration = function (c) {
if (c === 91 /* OpeningSquareBracket */) {
this._state = 19 /* CDATASequence */;
if (c === CharCodes.OpeningSquareBracket) {
this.state = State.CDATASequence;
this.sequenceIndex = 0;
}
else {
this._state =
c === 45 /* Dash */
? 18 /* BeforeComment */
: 16 /* InDeclaration */;
this.state =
c === CharCodes.Dash
? State.BeforeComment
: State.InDeclaration;
}
};
Tokenizer.prototype.stateInDeclaration = function (c) {
if (c === 62 /* Gt */ || this.fastForwardTo(62 /* Gt */)) {
this.cbs.ondeclaration(this.getSection());
this._state = 1 /* Text */;
this.sectionStart = this._index + 1;
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.ondeclaration(this.sectionStart, this.index);
this.state = State.Text;
this.sectionStart = this.index + 1;
}
};
Tokenizer.prototype.stateInProcessingInstruction = function (c) {
if (c === 62 /* Gt */ || this.fastForwardTo(62 /* Gt */)) {
this.cbs.onprocessinginstruction(this.getSection());
this._state = 1 /* Text */;
this.sectionStart = this._index + 1;
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.onprocessinginstruction(this.sectionStart, this.index);
this.state = State.Text;
this.sectionStart = this.index + 1;
}
};
Tokenizer.prototype.stateBeforeComment = function (c) {
if (c === 45 /* Dash */) {
this._state = 21 /* InCommentLike */;
if (c === CharCodes.Dash) {
this.state = State.InCommentLike;
this.currentSequence = Sequences.CommentEnd;
// Allow short comments (eg. <!-->)
this.sequenceIndex = 2;
this.sectionStart = this._index + 1;
this.sectionStart = this.index + 1;
}
else {
this._state = 16 /* InDeclaration */;
this.state = State.InDeclaration;
}
};
Tokenizer.prototype.stateInSpecialComment = function (c) {
if (c === 62 /* Gt */ || this.fastForwardTo(62 /* Gt */)) {
this.cbs.oncomment(this.getSection());
this._state = 1 /* Text */;
this.sectionStart = this._index + 1;
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.oncomment(this.sectionStart, this.index, 0);
this.state = State.Text;
this.sectionStart = this.index + 1;
}

@@ -528,3 +588,3 @@ };

else {
this._state = 3 /* InTagName */;
this.state = State.InTagName;
this.stateInTagName(c); // Consume the token again

@@ -536,6 +596,7 @@ }

this.entityExcess = 1;
if (c === 35 /* Num */) {
this._state = 26 /* BeforeNumericEntity */;
this.entityResult = 0;
if (c === CharCodes.Num) {
this.state = State.BeforeNumericEntity;
}
else if (c === 38 /* Amp */) {
else if (c === CharCodes.Amp) {
// We have two `&` characters in a row. Stay in the current state.

@@ -546,4 +607,3 @@ }

this.trieCurrent = this.entityTrie[0];
this.trieResult = null;
this._state = 27 /* InNamedEntity */;
this.state = State.InNamedEntity;
this.stateInNamedEntity(c);

@@ -554,29 +614,32 @@ }

this.entityExcess += 1;
this.trieIndex = (0, decode_1.determineBranch)(this.entityTrie, this.trieCurrent, this.trieIndex + 1, c);
this.trieIndex = (0, decode_js_1.determineBranch)(this.entityTrie, this.trieCurrent, this.trieIndex + 1, c);
if (this.trieIndex < 0) {
this.emitNamedEntity();
this._index--;
this.index--;
return;
}
this.trieCurrent = this.entityTrie[this.trieIndex];
var masked = this.trieCurrent & decode_js_1.BinTrieFlags.VALUE_LENGTH;
// If the branch is a value, store it and continue
if (this.trieCurrent & decode_1.BinTrieFlags.HAS_VALUE) {
if (masked) {
// The mask is the number of bytes of the value, including the current byte.
var valueLength = (masked >> 14) - 1;
// If we have a legacy entity while parsing strictly, just skip the number of bytes
if (!this.allowLegacyEntity() && c !== 59 /* Semi */) {
// No need to consider multi-byte values, as the legacy entity is always a single byte
this.trieIndex += 1;
if (!this.allowLegacyEntity() && c !== CharCodes.Semi) {
this.trieIndex += valueLength;
}
else {
// Add 1 as we have already incremented the excess
var entityStart = this._index - this.entityExcess + 1;
var entityStart = this.index - this.entityExcess + 1;
if (entityStart > this.sectionStart) {
this.emitPartial(this.buffer.substring(this.sectionStart, entityStart));
this.emitPartial(this.sectionStart, entityStart);
}
// If this is a surrogate pair, combine the higher bits from the node with the next byte
this.trieResult =
this.trieCurrent & decode_1.BinTrieFlags.MULTI_BYTE
? String.fromCharCode(this.entityTrie[++this.trieIndex], this.entityTrie[++this.trieIndex])
: String.fromCharCode(this.entityTrie[++this.trieIndex]);
// If this is a surrogate pair, consume the next two bytes
this.entityResult = this.trieIndex;
this.trieIndex += valueLength;
this.entityExcess = 0;
this.sectionStart = this._index + 1;
this.sectionStart = this.index + 1;
if (valueLength === 0) {
this.emitNamedEntity();
}
}

@@ -586,73 +649,90 @@ }

Tokenizer.prototype.emitNamedEntity = function () {
if (this.trieResult) {
this.emitPartial(this.trieResult);
this.state = this.baseState;
if (this.entityResult === 0) {
return;
}
this._state = this.baseState;
var valueLength = (this.entityTrie[this.entityResult] & decode_js_1.BinTrieFlags.VALUE_LENGTH) >>
14;
switch (valueLength) {
case 1:
this.emitCodePoint(this.entityTrie[this.entityResult] &
~decode_js_1.BinTrieFlags.VALUE_LENGTH);
break;
case 2:
this.emitCodePoint(this.entityTrie[this.entityResult + 1]);
break;
case 3: {
this.emitCodePoint(this.entityTrie[this.entityResult + 1]);
this.emitCodePoint(this.entityTrie[this.entityResult + 2]);
}
}
};
Tokenizer.prototype.stateBeforeNumericEntity = function (c) {
if ((c | 0x20) === 120 /* LowerX */) {
if ((c | 0x20) === CharCodes.LowerX) {
this.entityExcess++;
this._state = 29 /* InHexEntity */;
this.state = State.InHexEntity;
}
else {
this._state = 28 /* InNumericEntity */;
this.state = State.InNumericEntity;
this.stateInNumericEntity(c);
}
};
Tokenizer.prototype.decodeNumericEntity = function (base, strict) {
var entityStart = this._index - this.entityExcess - 1;
var numberStart = entityStart + 2 + (base >> 4);
if (numberStart !== this._index) {
Tokenizer.prototype.emitNumericEntity = function (strict) {
var entityStart = this.index - this.entityExcess - 1;
var numberStart = entityStart + 2 + Number(this.state === State.InHexEntity);
if (numberStart !== this.index) {
// Emit leading data if any
if (entityStart > this.sectionStart) {
this.emitPartial(this.buffer.substring(this.sectionStart, entityStart));
this.emitPartial(this.sectionStart, entityStart);
}
// Parse entity
var entity = this.buffer.substring(numberStart, this._index);
var parsed = parseInt(entity, base);
this.emitPartial((0, decode_codepoint_1.default)(parsed));
this.sectionStart = this._index + Number(strict);
this.sectionStart = this.index + Number(strict);
this.emitCodePoint((0, decode_js_1.replaceCodePoint)(this.entityResult));
}
this._state = this.baseState;
this.state = this.baseState;
};
Tokenizer.prototype.stateInNumericEntity = function (c) {
if (c === 59 /* Semi */) {
this.decodeNumericEntity(10, true);
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if (!isNumber(c)) {
else if (isNumber(c)) {
this.entityResult = this.entityResult * 10 + (c - CharCodes.Zero);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.decodeNumericEntity(10, false);
this.emitNumericEntity(false);
}
else {
this._state = this.baseState;
this.state = this.baseState;
}
this._index--;
this.index--;
}
else {
this.entityExcess++;
}
};
Tokenizer.prototype.stateInHexEntity = function (c) {
if (c === 59 /* Semi */) {
this.decodeNumericEntity(16, true);
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if ((c < 97 /* LowerA */ || c > 102 /* LowerF */) &&
(c < 65 /* UpperA */ || c > 70 /* UpperF */) &&
!isNumber(c)) {
else if (isNumber(c)) {
this.entityResult = this.entityResult * 16 + (c - CharCodes.Zero);
this.entityExcess++;
}
else if (isHexDigit(c)) {
this.entityResult =
this.entityResult * 16 + ((c | 0x20) - CharCodes.LowerA + 10);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.decodeNumericEntity(16, false);
this.emitNumericEntity(false);
}
else {
this._state = this.baseState;
this.state = this.baseState;
}
this._index--;
this.index--;
}
else {
this.entityExcess++;
}
};
Tokenizer.prototype.allowLegacyEntity = function () {
return (!this.xmlMode &&
(this.baseState === 1 /* Text */ ||
this.baseState === 24 /* InSpecialTag */));
(this.baseState === State.Text ||
this.baseState === State.InSpecialTag));
};

@@ -663,23 +743,19 @@ /**

Tokenizer.prototype.cleanup = function () {
// If we are inside of text, emit what we already have.
if (this.running &&
this.sectionStart !== this._index &&
(this._state === 1 /* Text */ ||
(this._state === 24 /* InSpecialTag */ &&
this.sequenceIndex === 0))) {
// TODO: We could emit attribute data here as well.
this.cbs.ontext(this.buffer.substr(this.sectionStart));
this.sectionStart = this._index;
// If we are inside of text or attributes, emit what we already have.
if (this.running && this.sectionStart !== this.index) {
if (this.state === State.Text ||
(this.state === State.InSpecialTag && this.sequenceIndex === 0)) {
this.cbs.ontext(this.sectionStart, this.index);
this.sectionStart = this.index;
}
else if (this.state === State.InAttributeValueDq ||
this.state === State.InAttributeValueSq ||
this.state === State.InAttributeValueNq) {
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = this.index;
}
}
var start = this.sectionStart < 0 ? this._index : this.sectionStart;
this.buffer =
start === this.buffer.length ? "" : this.buffer.substr(start);
this._index -= start;
this.bufferOffset += start;
if (this.sectionStart > 0) {
this.sectionStart = 0;
}
};
Tokenizer.prototype.shouldContinue = function () {
return this._index < this.buffer.length && this.running;
return this.index < this.buffer.length + this.offset && this.running;
};

@@ -693,85 +769,85 @@ /**

while (this.shouldContinue()) {
var c = this.buffer.charCodeAt(this._index);
if (this._state === 1 /* Text */) {
var c = this.buffer.charCodeAt(this.index - this.offset);
if (this.state === State.Text) {
this.stateText(c);
}
else if (this._state === 23 /* SpecialStartSequence */) {
else if (this.state === State.SpecialStartSequence) {
this.stateSpecialStartSequence(c);
}
else if (this._state === 24 /* InSpecialTag */) {
else if (this.state === State.InSpecialTag) {
this.stateInSpecialTag(c);
}
else if (this._state === 19 /* CDATASequence */) {
else if (this.state === State.CDATASequence) {
this.stateCDATASequence(c);
}
else if (this._state === 12 /* InAttributeValueDq */) {
else if (this.state === State.InAttributeValueDq) {
this.stateInAttributeValueDoubleQuotes(c);
}
else if (this._state === 9 /* InAttributeName */) {
else if (this.state === State.InAttributeName) {
this.stateInAttributeName(c);
}
else if (this._state === 21 /* InCommentLike */) {
else if (this.state === State.InCommentLike) {
this.stateInCommentLike(c);
}
else if (this._state === 20 /* InSpecialComment */) {
else if (this.state === State.InSpecialComment) {
this.stateInSpecialComment(c);
}
else if (this._state === 8 /* BeforeAttributeName */) {
else if (this.state === State.BeforeAttributeName) {
this.stateBeforeAttributeName(c);
}
else if (this._state === 3 /* InTagName */) {
else if (this.state === State.InTagName) {
this.stateInTagName(c);
}
else if (this._state === 6 /* InClosingTagName */) {
else if (this.state === State.InClosingTagName) {
this.stateInClosingTagName(c);
}
else if (this._state === 2 /* BeforeTagName */) {
else if (this.state === State.BeforeTagName) {
this.stateBeforeTagName(c);
}
else if (this._state === 10 /* AfterAttributeName */) {
else if (this.state === State.AfterAttributeName) {
this.stateAfterAttributeName(c);
}
else if (this._state === 13 /* InAttributeValueSq */) {
else if (this.state === State.InAttributeValueSq) {
this.stateInAttributeValueSingleQuotes(c);
}
else if (this._state === 11 /* BeforeAttributeValue */) {
else if (this.state === State.BeforeAttributeValue) {
this.stateBeforeAttributeValue(c);
}
else if (this._state === 5 /* BeforeClosingTagName */) {
else if (this.state === State.BeforeClosingTagName) {
this.stateBeforeClosingTagName(c);
}
else if (this._state === 7 /* AfterClosingTagName */) {
else if (this.state === State.AfterClosingTagName) {
this.stateAfterClosingTagName(c);
}
else if (this._state === 22 /* BeforeSpecialS */) {
else if (this.state === State.BeforeSpecialS) {
this.stateBeforeSpecialS(c);
}
else if (this._state === 14 /* InAttributeValueNq */) {
else if (this.state === State.InAttributeValueNq) {
this.stateInAttributeValueNoQuotes(c);
}
else if (this._state === 4 /* InSelfClosingTag */) {
else if (this.state === State.InSelfClosingTag) {
this.stateInSelfClosingTag(c);
}
else if (this._state === 16 /* InDeclaration */) {
else if (this.state === State.InDeclaration) {
this.stateInDeclaration(c);
}
else if (this._state === 15 /* BeforeDeclaration */) {
else if (this.state === State.BeforeDeclaration) {
this.stateBeforeDeclaration(c);
}
else if (this._state === 18 /* BeforeComment */) {
else if (this.state === State.BeforeComment) {
this.stateBeforeComment(c);
}
else if (this._state === 17 /* InProcessingInstruction */) {
else if (this.state === State.InProcessingInstruction) {
this.stateInProcessingInstruction(c);
}
else if (this._state === 27 /* InNamedEntity */) {
else if (this.state === State.InNamedEntity) {
this.stateInNamedEntity(c);
}
else if (this._state === 25 /* BeforeEntity */) {
else if (this.state === State.BeforeEntity) {
this.stateBeforeEntity(c);
}
else if (this._state === 29 /* InHexEntity */) {
else if (this.state === State.InHexEntity) {
this.stateInHexEntity(c);
}
else if (this._state === 28 /* InNumericEntity */) {
else if (this.state === State.InNumericEntity) {
this.stateInNumericEntity(c);

@@ -783,3 +859,3 @@ }

}
this._index++;
this.index++;
}

@@ -789,7 +865,7 @@ this.cleanup();

Tokenizer.prototype.finish = function () {
if (this._state === 27 /* InNamedEntity */) {
if (this.state === State.InNamedEntity) {
this.emitNamedEntity();
}
// If there is remaining data, emit it in a reasonable way
if (this.sectionStart < this._index) {
if (this.sectionStart < this.index) {
this.handleTrailingData();

@@ -801,30 +877,30 @@ }

Tokenizer.prototype.handleTrailingData = function () {
var data = this.buffer.substr(this.sectionStart);
if (this._state === 21 /* InCommentLike */) {
var endIndex = this.buffer.length + this.offset;
if (this.state === State.InCommentLike) {
if (this.currentSequence === Sequences.CdataEnd) {
this.cbs.oncdata(data);
this.cbs.oncdata(this.sectionStart, endIndex, 0);
}
else {
this.cbs.oncomment(data);
this.cbs.oncomment(this.sectionStart, endIndex, 0);
}
}
else if (this._state === 28 /* InNumericEntity */ &&
else if (this.state === State.InNumericEntity &&
this.allowLegacyEntity()) {
this.decodeNumericEntity(10, false);
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this._state === 29 /* InHexEntity */ &&
else if (this.state === State.InHexEntity &&
this.allowLegacyEntity()) {
this.decodeNumericEntity(16, false);
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this._state === 3 /* InTagName */ ||
this._state === 8 /* BeforeAttributeName */ ||
this._state === 11 /* BeforeAttributeValue */ ||
this._state === 10 /* AfterAttributeName */ ||
this._state === 9 /* InAttributeName */ ||
this._state === 13 /* InAttributeValueSq */ ||
this._state === 12 /* InAttributeValueDq */ ||
this._state === 14 /* InAttributeValueNq */ ||
this._state === 6 /* InClosingTagName */) {
else if (this.state === State.InTagName ||
this.state === State.BeforeAttributeName ||
this.state === State.BeforeAttributeValue ||
this.state === State.AfterAttributeName ||
this.state === State.InAttributeName ||
this.state === State.InAttributeValueSq ||
this.state === State.InAttributeValueDq ||
this.state === State.InAttributeValueNq ||
this.state === State.InClosingTagName) {
/*

@@ -836,15 +912,21 @@ * If we are currently in an opening or closing tag, us not calling the

else {
this.cbs.ontext(data);
this.cbs.ontext(this.sectionStart, endIndex);
}
};
Tokenizer.prototype.getSection = function () {
return this.buffer.substring(this.sectionStart, this._index);
Tokenizer.prototype.emitPartial = function (start, endIndex) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribdata(start, endIndex);
}
else {
this.cbs.ontext(start, endIndex);
}
};
Tokenizer.prototype.emitPartial = function (value) {
if (this.baseState !== 1 /* Text */ &&
this.baseState !== 24 /* InSpecialTag */) {
this.cbs.onattribdata(value);
Tokenizer.prototype.emitCodePoint = function (cp) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribentity(cp);
}
else {
this.cbs.ontext(value);
this.cbs.ontextentity(cp);
}

@@ -855,1 +937,2 @@ };

exports.default = Tokenizer;
//# sourceMappingURL=Tokenizer.js.map

2

lib/WritableStream.d.ts
/// <reference types="node" />
import { Handler, ParserOptions } from "./Parser";
import { Handler, ParserOptions } from "./Parser.js";
import { Writable } from "stream";

@@ -4,0 +4,0 @@ /**

5

lib/WritableStream.js

@@ -19,3 +19,3 @@ "use strict";

exports.WritableStream = void 0;
var Parser_1 = require("./Parser");
var Parser_js_1 = require("./Parser.js");
/*

@@ -41,3 +41,3 @@ * NOTE: If either of these two imports produces a type error,

_this._decoder = new string_decoder_1.StringDecoder();
_this._parser = new Parser_1.Parser(cbs, options);
_this._parser = new Parser_js_1.Parser(cbs, options);
return _this;

@@ -56,1 +56,2 @@ }

exports.WritableStream = WritableStream;
//# sourceMappingURL=WritableStream.js.map

45

package.json
{
"name": "htmlparser2",
"description": "Fast & forgiving HTML/XML parser",
"version": "7.2.0",
"version": "8.0.0",
"author": "Felix Boehm <me@feedic.com>",

@@ -34,2 +34,7 @@ "funding": [

"types": "lib/index.d.ts",
"module": "lib/esm/index.js",
"exports": {
"require": "./lib/index.js",
"import": "./lib/esm/index.js"
},
"files": [

@@ -48,26 +53,32 @@ "lib/**/*"

"format:prettier:raw": "prettier '**/*.{ts,md,json,yml}'",
"build": "tsc",
"build": "npm run build:cjs && npm run build:esm",
"build:cjs": "tsc --sourceRoot https://raw.githubusercontent.com/fb55/htmlparser2/$(git rev-parse HEAD)/src/",
"build:esm": "npm run build:cjs -- --module esnext --target es2019 --outDir lib/esm && echo '{\"type\":\"module\"}' > lib/esm/package.json",
"prepare": "npm run build"
},
"dependencies": {
"domelementtype": "^2.0.1",
"domhandler": "^4.2.2",
"domutils": "^2.8.0",
"entities": "^3.0.1"
"domelementtype": "^2.3.0",
"domhandler": "^5.0.2",
"domutils": "^3.0.1",
"entities": "^4.3.0"
},
"devDependencies": {
"@types/jest": "^27.0.2",
"@types/node": "^16.11.7",
"@typescript-eslint/eslint-plugin": "^5.3.1",
"@typescript-eslint/parser": "^5.3.1",
"eslint": "^8.2.0",
"eslint-config-prettier": "^8.1.0",
"jest": "^27.3.1",
"prettier": "^2.4.1",
"ts-jest": "^27.0.7",
"typescript": "^4.4.4"
"@types/jest": "^27.4.1",
"@types/node": "^17.0.25",
"@typescript-eslint/eslint-plugin": "^5.20.0",
"@typescript-eslint/parser": "^5.20.0",
"eslint": "^8.13.0",
"eslint-config-prettier": "^8.5.0",
"jest": "^27.5.1",
"prettier": "^2.6.2",
"ts-jest": "^27.1.4",
"typescript": "^4.6.3"
},
"jest": {
"preset": "ts-jest",
"testEnvironment": "node"
"testEnvironment": "node",
"coverageProvider": "v8",
"moduleNameMapper": {
"^(.*)\\.js$": "$1"
}
},

@@ -74,0 +85,0 @@ "prettier": {

2

README.md

@@ -10,2 +10,4 @@ # htmlparser2

_htmlparser2 is [the fastest HTML parser](#performance), and takes some shortcuts to get there. If you need strict HTML spec compliance, have a look at [parse5](https://github.com/inikulin/parse5)._
## Installation

@@ -12,0 +14,0 @@ 

lib/FeedHandler.d.ts
lib/FeedHandler.d.ts.map
lib/FeedHandler.js
lib/index.d.ts.map

Sorry, the diff of this file is not supported yet

lib/Parser.d.ts.map

Sorry, the diff of this file is not supported yet

lib/Tokenizer.d.ts.map

Sorry, the diff of this file is not supported yet

lib/WritableStream.d.ts.map

Sorry, the diff of this file is not supported yet

SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap

About

Packages

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc