Huge News!Announcing our $40M Series B led by Abstract Ventures.Learn More →
Socket
Sign inDemoInstall
Socket
Sign inDemoInstall

htmlparser2

Package Overview
Dependencies
Maintainers
1
Versions
76
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

htmlparser2 - npm Package Compare versions

Comparing version 8.0.2 to 9.0.0

21

lib/esm/index.d.ts

@@ -10,3 +10,3 @@ import { Parser, ParserOptions } from "./Parser.js";

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
*/

@@ -21,3 +21,3 @@ export declare function parseDocument(data: string, options?: Options): Document;

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
* @deprecated Use `parseDocument` instead.

@@ -29,11 +29,20 @@ */

*
* @param callback A callback that will be called once parsing has been completed.
* @param options Optional options for the parser and DOM builder.
* @param callback A callback that will be called once parsing has been completed, with the resulting document.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
*/
export declare function createDocumentStream(callback: (error: Error | null, document: Document) => void, options?: Options, elementCallback?: (element: Element) => void): Parser;
/**
* Creates a parser instance, with an attached DOM handler.
*
* @param callback A callback that will be called once parsing has been completed, with an array of root nodes.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
* @deprecated Use `createDocumentStream` instead.
*/
export declare function createDomStream(callback: (error: Error | null, dom: ChildNode[]) => void, options?: Options, elementCallback?: (element: Element) => void): Parser;
export { default as Tokenizer, type Callbacks as TokenizerCallbacks, } from "./Tokenizer.js";
export * as ElementType from "domelementtype";
import { Feed } from "domutils";
export { getFeed } from "domutils";
import { type Feed } from "domutils";
export { getFeed, type Feed } from "domutils";
/**

@@ -40,0 +49,0 @@ * Parse a feed.

20

lib/esm/index.js

@@ -12,3 +12,3 @@ import { Parser } from "./Parser.js";

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
*/

@@ -27,3 +27,3 @@ export function parseDocument(data, options) {

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
* @deprecated Use `parseDocument` instead.

@@ -37,6 +37,18 @@ */

*
* @param callback A callback that will be called once parsing has been completed.
* @param options Optional options for the parser and DOM builder.
* @param callback A callback that will be called once parsing has been completed, with the resulting document.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
*/
export function createDocumentStream(callback, options, elementCallback) {
const handler = new DomHandler((error) => callback(error, handler.root), options, elementCallback);
return new Parser(handler, options);
}
/**
* Creates a parser instance, with an attached DOM handler.
*
* @param callback A callback that will be called once parsing has been completed, with an array of root nodes.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
* @deprecated Use `createDocumentStream` instead.
*/
export function createDomStream(callback, options, elementCallback) {

@@ -43,0 +55,0 @@ const handler = new DomHandler(callback, options, elementCallback);

9

lib/esm/Parser.d.ts

@@ -95,2 +95,3 @@ import Tokenizer, { Callbacks, QuoteType } from "./Tokenizer.js";

private readonly stack;
/** Determines whether self-closing tags are recognized. */
private readonly foreignContext;

@@ -100,2 +101,4 @@ private readonly cbs;

private readonly lowerCaseAttributeNames;
/** We are parsing HTML. Inverse of the `xmlMode` option. */
private readonly htmlMode;
private readonly tokenizer;

@@ -112,3 +115,7 @@ private readonly buffers;

/** @internal */
ontextentity(cp: number): void;
ontextentity(cp: number, endIndex: number): void;
/**
* Checks if the current tag is a void element. Override this if you want
* to specify your own additional void elements.
*/
protected isVoidElement(name: string): boolean;

@@ -115,0 +122,0 @@ /** @internal */

95

lib/esm/Parser.js

@@ -117,3 +117,2 @@ import Tokenizer, { QuoteType } from "./Tokenizer.js";

this.stack = [];
this.foreignContext = [];
this.buffers = [];

@@ -126,6 +125,8 @@ this.bufferOffset = 0;

this.cbs = cbs !== null && cbs !== void 0 ? cbs : {};
this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : !options.xmlMode;
this.htmlMode = !this.options.xmlMode;
this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : this.htmlMode;
this.lowerCaseAttributeNames =
(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : !options.xmlMode;
(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : this.htmlMode;
this.tokenizer = new ((_c = options.Tokenizer) !== null && _c !== void 0 ? _c : Tokenizer)(this.options, this);
this.foreignContext = [!this.htmlMode];
(_e = (_d = this.cbs).onparserinit) === null || _e === void 0 ? void 0 : _e.call(_d, this);

@@ -143,15 +144,14 @@ }

/** @internal */
ontextentity(cp) {
ontextentity(cp, endIndex) {
var _a, _b;
/*
* Entities can be emitted on the character, or directly after.
* We use the section start here to get accurate indices.
*/
const index = this.tokenizer.getSectionStart();
this.endIndex = index - 1;
this.endIndex = endIndex - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, fromCodePoint(cp));
this.startIndex = index;
this.startIndex = endIndex;
}
/**
* Checks if the current tag is a void element. Override this if you want
* to specify your own additional void elements.
*/
isVoidElement(name) {
return !this.options.xmlMode && voidElements.has(name);
return this.htmlMode && voidElements.has(name);
}

@@ -171,7 +171,6 @@ /** @internal */

this.tagname = name;
const impliesClose = !this.options.xmlMode && openImpliesClose.get(name);
const impliesClose = this.htmlMode && openImpliesClose.get(name);
if (impliesClose) {
while (this.stack.length > 0 &&
impliesClose.has(this.stack[this.stack.length - 1])) {
const element = this.stack.pop();
while (this.stack.length > 0 && impliesClose.has(this.stack[0])) {
const element = this.stack.shift();
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, element, true);

@@ -181,9 +180,11 @@ }

if (!this.isVoidElement(name)) {
this.stack.push(name);
if (foreignContextElements.has(name)) {
this.foreignContext.push(true);
this.stack.unshift(name);
if (this.htmlMode) {
if (foreignContextElements.has(name)) {
this.foreignContext.unshift(true);
}
else if (htmlIntegrationElements.has(name)) {
this.foreignContext.unshift(false);
}
}
else if (htmlIntegrationElements.has(name)) {
this.foreignContext.push(false);
}
}

@@ -215,3 +216,3 @@ (_d = (_c = this.cbs).onopentagname) === null || _d === void 0 ? void 0 : _d.call(_c, name);

onclosetag(start, endIndex) {
var _a, _b, _c, _d, _e, _f;
var _a, _b, _c, _d, _e, _f, _g, _h;
this.endIndex = endIndex;

@@ -222,20 +223,17 @@ let name = this.getSlice(start, endIndex);

}
if (foreignContextElements.has(name) ||
htmlIntegrationElements.has(name)) {
this.foreignContext.pop();
if (this.htmlMode &&
(foreignContextElements.has(name) ||
htmlIntegrationElements.has(name))) {
this.foreignContext.shift();
}
if (!this.isVoidElement(name)) {
const pos = this.stack.lastIndexOf(name);
const pos = this.stack.indexOf(name);
if (pos !== -1) {
if (this.cbs.onclosetag) {
let count = this.stack.length - pos;
while (count--) {
// We know the stack has sufficient elements.
this.cbs.onclosetag(this.stack.pop(), count !== 0);
}
for (let index = 0; index <= pos; index++) {
const element = this.stack.shift();
// We know the stack has sufficient elements.
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, element, index !== pos);
}
else
this.stack.length = pos;
}
else if (!this.options.xmlMode && name === "p") {
else if (this.htmlMode && name === "p") {
// Implicit open before close

@@ -246,7 +244,7 @@ this.emitOpenTag("p");

}
else if (!this.options.xmlMode && name === "br") {
else if (this.htmlMode && name === "br") {
// 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);
(_d = (_c = this.cbs).onopentagname) === null || _d === void 0 ? void 0 : _d.call(_c, "br");
(_f = (_e = this.cbs).onopentag) === null || _f === void 0 ? void 0 : _f.call(_e, "br", {}, true);
(_h = (_g = this.cbs).onclosetag) === null || _h === void 0 ? void 0 : _h.call(_g, "br", false);
}

@@ -259,5 +257,3 @@ // Set `startIndex` for next node

this.endIndex = endIndex;
if (this.options.xmlMode ||
this.options.recognizeSelfClosing ||
this.foreignContext[this.foreignContext.length - 1]) {
if (this.options.recognizeSelfClosing || this.foreignContext[0]) {
this.closeCurrentTag(false);

@@ -277,6 +273,6 @@ // Set `startIndex` for next node

// Self-closing tags will be on the top of the stack
if (this.stack[this.stack.length - 1] === name) {
if (this.stack[0] === name) {
// If the opening tag isn't implied, the closing tag has to be implied.
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, name, !isOpenImplied);
this.stack.pop();
this.stack.shift();
}

@@ -361,3 +357,3 @@ }

const value = this.getSlice(start, endIndex - offset);
if (this.options.xmlMode || this.options.recognizeCDATA) {
if (!this.htmlMode || this.options.recognizeCDATA) {
(_b = (_a = this.cbs).oncdatastart) === null || _b === void 0 ? void 0 : _b.call(_a);

@@ -380,4 +376,5 @@ (_d = (_c = this.cbs).ontext) === null || _d === void 0 ? void 0 : _d.call(_c, value);

this.endIndex = this.startIndex;
for (let index = this.stack.length; index > 0; this.cbs.onclosetag(this.stack[--index], true))
;
for (let index = 0; index < this.stack.length; index++) {
this.cbs.onclosetag(this.stack[index], true);
}
}

@@ -401,2 +398,4 @@ (_b = (_a = this.cbs).onend) === null || _b === void 0 ? void 0 : _b.call(_a);

this.buffers.length = 0;
this.foreignContext.length = 0;
this.foreignContext.unshift(!this.htmlMode);
this.bufferOffset = 0;

@@ -403,0 +402,0 @@ this.writeIndex = 0;

30

lib/esm/Tokenizer.d.ts

@@ -22,3 +22,3 @@ export declare enum QuoteType {

ontext(start: number, endIndex: number): void;
ontextentity(codepoint: number): void;
ontextentity(codepoint: number, endIndex: number): void;
}

@@ -35,2 +35,4 @@ export default class Tokenizer {

private index;
/** The start of the last entity. */
private entityStart;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */

@@ -46,3 +48,3 @@ private baseState;

private readonly decodeEntities;
private readonly entityTrie;
private readonly entityDecoder;
constructor({ xmlMode, decodeEntities, }: {

@@ -57,10 +59,2 @@ xmlMode?: boolean;

resume(): void;
/**
* The current index within all of the written data.
*/
getIndex(): number;
/**
* The start of the current section.
*/
getSectionStart(): number;
private stateText;

@@ -117,15 +111,4 @@ private currentSequence;

private stateBeforeSpecialS;
private trieIndex;
private trieCurrent;
/** For named entities, the index of the value. For numeric entities, the code point. */
private entityResult;
private entityExcess;
private stateBeforeEntity;
private stateInNamedEntity;
private emitNamedEntity;
private stateBeforeNumericEntity;
private emitNumericEntity;
private stateInNumericEntity;
private stateInHexEntity;
private allowLegacyEntity;
private startEntity;
private stateInEntity;
/**

@@ -145,5 +128,4 @@ * Remove data that has already been consumed from the buffer.

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

273

lib/esm/Tokenizer.js

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

import { htmlDecodeTree, xmlDecodeTree, BinTrieFlags, determineBranch, replaceCodePoint, } from "entities/lib/decode.js";
import { EntityDecoder, DecodingMode, htmlDecodeTree, xmlDecodeTree, } from "entities/lib/decode.js";
var CharCodes;

@@ -64,7 +64,3 @@ (function (CharCodes) {

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["InEntity"] = 25] = "InEntity";
})(State || (State = {}));

@@ -81,5 +77,2 @@ function isWhitespace(c) {

}
function isNumber(c) {
return c >= CharCodes.Zero && c <= CharCodes.Nine;
}
function isASCIIAlpha(c) {

@@ -89,6 +82,2 @@ return ((c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||

}
function isHexDigit(c) {
return ((c >= CharCodes.UpperA && c <= CharCodes.UpperF) ||
(c >= CharCodes.LowerA && c <= CharCodes.LowerF));
}
export var QuoteType;

@@ -126,2 +115,4 @@ (function (QuoteType) {

this.index = 0;
/** The start of the last entity. */
this.entityStart = 0;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */

@@ -137,10 +128,5 @@ this.baseState = State.Text;

this.sequenceIndex = 0;
this.trieIndex = 0;
this.trieCurrent = 0;
/** 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 ? xmlDecodeTree : htmlDecodeTree;
this.entityDecoder = new EntityDecoder(xmlMode ? xmlDecodeTree : htmlDecodeTree, (cp, consumed) => this.emitCodePoint(cp, consumed));
}

@@ -175,14 +161,2 @@ reset() {

}
/**
* The current index within all of the written data.
*/
getIndex() {
return this.index;
}
/**
* The start of the current section.
*/
getSectionStart() {
return this.sectionStart;
}
stateText(c) {

@@ -198,3 +172,3 @@ if (c === CharCodes.Lt ||

else if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -246,3 +220,3 @@ }

if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -408,3 +382,2 @@ }

this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;

@@ -423,3 +396,2 @@ }

}
this.baseState = this.state;
this.sectionStart = this.index + 1;

@@ -439,3 +411,2 @@ }

this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;

@@ -498,4 +469,3 @@ this.isSpecial = false; // Reset special state, in case of self-closing special tags

else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -518,4 +488,3 @@ }

else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -581,146 +550,27 @@ }

}
stateBeforeEntity(c) {
// Start excess with 1 to include the '&'
this.entityExcess = 1;
this.entityResult = 0;
if (c === CharCodes.Number) {
this.state = State.BeforeNumericEntity;
}
else if (c === CharCodes.Amp) {
// We have two `&` characters in a row. Stay in the current state.
}
else {
this.trieIndex = 0;
this.trieCurrent = this.entityTrie[0];
this.state = State.InNamedEntity;
this.stateInNamedEntity(c);
}
startEntity() {
this.baseState = this.state;
this.state = State.InEntity;
this.entityStart = this.index;
this.entityDecoder.startEntity(this.xmlMode
? DecodingMode.Strict
: this.baseState === State.Text ||
this.baseState === State.InSpecialTag
? DecodingMode.Legacy
: DecodingMode.Attribute);
}
stateInNamedEntity(c) {
this.entityExcess += 1;
this.trieIndex = determineBranch(this.entityTrie, this.trieCurrent, this.trieIndex + 1, c);
if (this.trieIndex < 0) {
this.emitNamedEntity();
this.index--;
return;
}
this.trieCurrent = this.entityTrie[this.trieIndex];
const masked = this.trieCurrent & BinTrieFlags.VALUE_LENGTH;
// If the branch is a value, store it and continue
if (masked) {
// The mask is the number of bytes of the value, including the current byte.
const valueLength = (masked >> 14) - 1;
// If we have a legacy entity while parsing strictly, just skip the number of bytes
if (!this.allowLegacyEntity() && c !== CharCodes.Semi) {
this.trieIndex += valueLength;
stateInEntity() {
const length = this.entityDecoder.write(this.buffer, this.index - this.offset);
// 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 {
// Add 1 as we have already incremented the excess
const entityStart = this.index - this.entityExcess + 1;
if (entityStart > this.sectionStart) {
this.emitPartial(this.sectionStart, entityStart);
}
// 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;
if (valueLength === 0) {
this.emitNamedEntity();
}
}
}
}
emitNamedEntity() {
this.state = this.baseState;
if (this.entityResult === 0) {
return;
}
const valueLength = (this.entityTrie[this.entityResult] & BinTrieFlags.VALUE_LENGTH) >>
14;
switch (valueLength) {
case 1: {
this.emitCodePoint(this.entityTrie[this.entityResult] &
~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]);
}
}
}
stateBeforeNumericEntity(c) {
if ((c | 0x20) === CharCodes.LowerX) {
this.entityExcess++;
this.state = State.InHexEntity;
}
else {
this.state = State.InNumericEntity;
this.stateInNumericEntity(c);
// Mark buffer as consumed.
this.index = this.offset + this.buffer.length - 1;
}
}
emitNumericEntity(strict) {
const entityStart = this.index - this.entityExcess - 1;
const numberStart = entityStart + 2 + Number(this.state === State.InHexEntity);
if (numberStart !== this.index) {
// Emit leading data if any
if (entityStart > this.sectionStart) {
this.emitPartial(this.sectionStart, entityStart);
}
this.sectionStart = this.index + Number(strict);
this.emitCodePoint(replaceCodePoint(this.entityResult));
}
this.state = this.baseState;
}
stateInNumericEntity(c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if (isNumber(c)) {
this.entityResult = this.entityResult * 10 + (c - CharCodes.Zero);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
}
stateInHexEntity(c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
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.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
}
allowLegacyEntity() {
return (!this.xmlMode &&
(this.baseState === State.Text ||
this.baseState === State.InSpecialTag));
}
/**

@@ -853,22 +703,6 @@ * Remove data that has already been consumed from the buffer.

}
case State.InNamedEntity: {
this.stateInNamedEntity(c);
case State.InEntity: {
this.stateInEntity();
break;
}
case State.BeforeEntity: {
this.stateBeforeEntity(c);
break;
}
case State.InHexEntity: {
this.stateInHexEntity(c);
break;
}
case State.InNumericEntity: {
this.stateInNumericEntity(c);
break;
}
default: {
// `this._state === State.BeforeNumericEntity`
this.stateBeforeNumericEntity(c);
}
}

@@ -880,9 +714,7 @@ this.index++;

finish() {
if (this.state === State.InNamedEntity) {
this.emitNamedEntity();
if (this.state === State.InEntity) {
this.entityDecoder.end();
this.state = this.baseState;
}
// If there is remaining data, emit it in a reasonable way
if (this.sectionStart < this.index) {
this.handleTrailingData();
}
this.handleTrailingData();
this.cbs.onend();

@@ -893,2 +725,6 @@ }

const endIndex = this.buffer.length + this.offset;
// If there is no remaining data, we are done.
if (this.sectionStart >= endIndex) {
return;
}
if (this.state === State.InCommentLike) {

@@ -902,12 +738,2 @@ if (this.currentSequence === Sequences.CdataEnd) {

}
else if (this.state === State.InNumericEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InHexEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InTagName ||

@@ -931,18 +757,19 @@ this.state === State.BeforeAttributeName ||

}
emitPartial(start, endIndex) {
emitCodePoint(cp, consumed) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribdata(start, endIndex);
}
else {
this.cbs.ontext(start, endIndex);
}
}
emitCodePoint(cp) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
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(cp);
}
else {
this.cbs.ontextentity(cp);
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(cp, this.sectionStart);
}

@@ -949,0 +776,0 @@ }

21

lib/index.d.ts

@@ -10,3 +10,3 @@ import { Parser, ParserOptions } from "./Parser.js";

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
*/

@@ -21,3 +21,3 @@ export declare function parseDocument(data: string, options?: Options): Document;

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
* @deprecated Use `parseDocument` instead.

@@ -29,11 +29,20 @@ */

*
* @param callback A callback that will be called once parsing has been completed.
* @param options Optional options for the parser and DOM builder.
* @param callback A callback that will be called once parsing has been completed, with the resulting document.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
*/
export declare function createDocumentStream(callback: (error: Error | null, document: Document) => void, options?: Options, elementCallback?: (element: Element) => void): Parser;
/**
* Creates a parser instance, with an attached DOM handler.
*
* @param callback A callback that will be called once parsing has been completed, with an array of root nodes.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
* @deprecated Use `createDocumentStream` instead.
*/
export declare function createDomStream(callback: (error: Error | null, dom: ChildNode[]) => void, options?: Options, elementCallback?: (element: Element) => void): Parser;
export { default as Tokenizer, type Callbacks as TokenizerCallbacks, } from "./Tokenizer.js";
export * as ElementType from "domelementtype";
import { Feed } from "domutils";
export { getFeed } from "domutils";
import { type Feed } from "domutils";
export { getFeed, type Feed } from "domutils";
/**

@@ -40,0 +49,0 @@ * Parse a feed.

23

lib/index.js

@@ -29,3 +29,3 @@ "use strict";

Object.defineProperty(exports, "__esModule", { value: true });
exports.DomUtils = exports.parseFeed = exports.getFeed = exports.ElementType = exports.Tokenizer = exports.createDomStream = exports.parseDOM = exports.parseDocument = exports.DefaultHandler = exports.DomHandler = exports.Parser = void 0;
exports.DomUtils = exports.parseFeed = exports.getFeed = exports.ElementType = exports.Tokenizer = exports.createDomStream = exports.createDocumentStream = exports.parseDOM = exports.parseDocument = exports.DefaultHandler = exports.DomHandler = exports.Parser = void 0;
var Parser_js_1 = require("./Parser.js");

@@ -44,3 +44,3 @@ var Parser_js_2 = require("./Parser.js");

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
*/

@@ -60,3 +60,3 @@ function parseDocument(data, options) {

* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @param options Optional options for the parser and DOM handler.
* @deprecated Use `parseDocument` instead.

@@ -71,6 +71,19 @@ */

*
* @param callback A callback that will be called once parsing has been completed.
* @param options Optional options for the parser and DOM builder.
* @param callback A callback that will be called once parsing has been completed, with the resulting document.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
*/
function createDocumentStream(callback, options, elementCallback) {
var handler = new domhandler_1.DomHandler(function (error) { return callback(error, handler.root); }, options, elementCallback);
return new Parser_js_1.Parser(handler, options);
}
exports.createDocumentStream = createDocumentStream;
/**
* Creates a parser instance, with an attached DOM handler.
*
* @param callback A callback that will be called once parsing has been completed, with an array of root nodes.
* @param options Optional options for the parser and DOM handler.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
* @deprecated Use `createDocumentStream` instead.
*/
function createDomStream(callback, options, elementCallback) {

@@ -77,0 +90,0 @@ var handler = new domhandler_1.DomHandler(callback, options, elementCallback);

9

lib/Parser.d.ts

@@ -95,2 +95,3 @@ import Tokenizer, { Callbacks, QuoteType } from "./Tokenizer.js";

private readonly stack;
/** Determines whether self-closing tags are recognized. */
private readonly foreignContext;

@@ -100,2 +101,4 @@ private readonly cbs;

private readonly lowerCaseAttributeNames;
/** We are parsing HTML. Inverse of the `xmlMode` option. */
private readonly htmlMode;
private readonly tokenizer;

@@ -112,3 +115,7 @@ private readonly buffers;

/** @internal */
ontextentity(cp: number): void;
ontextentity(cp: number, endIndex: number): void;
/**
* Checks if the current tag is a void element. Override this if you want
* to specify your own additional void elements.
*/
protected isVoidElement(name: string): boolean;

@@ -115,0 +122,0 @@ /** @internal */

95

lib/Parser.js

@@ -144,3 +144,2 @@ "use strict";

this.stack = [];
this.foreignContext = [];
this.buffers = [];

@@ -153,6 +152,8 @@ this.bufferOffset = 0;

this.cbs = cbs !== null && cbs !== void 0 ? cbs : {};
this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : !options.xmlMode;
this.htmlMode = !this.options.xmlMode;
this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : this.htmlMode;
this.lowerCaseAttributeNames =
(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : !options.xmlMode;
(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : this.htmlMode;
this.tokenizer = new ((_c = options.Tokenizer) !== null && _c !== void 0 ? _c : Tokenizer_js_1.default)(this.options, this);
this.foreignContext = [!this.htmlMode];
(_e = (_d = this.cbs).onparserinit) === null || _e === void 0 ? void 0 : _e.call(_d, this);

@@ -170,15 +171,14 @@ }

/** @internal */
Parser.prototype.ontextentity = function (cp) {
Parser.prototype.ontextentity = function (cp, endIndex) {
var _a, _b;
/*
* Entities can be emitted on the character, or directly after.
* We use the section start here to get accurate indices.
*/
var index = this.tokenizer.getSectionStart();
this.endIndex = index - 1;
this.endIndex = endIndex - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, (0, decode_js_1.fromCodePoint)(cp));
this.startIndex = index;
this.startIndex = endIndex;
};
/**
* Checks if the current tag is a void element. Override this if you want
* to specify your own additional void elements.
*/
Parser.prototype.isVoidElement = function (name) {
return !this.options.xmlMode && voidElements.has(name);
return this.htmlMode && voidElements.has(name);
};

@@ -198,7 +198,6 @@ /** @internal */

this.tagname = name;
var impliesClose = !this.options.xmlMode && openImpliesClose.get(name);
var impliesClose = this.htmlMode && openImpliesClose.get(name);
if (impliesClose) {
while (this.stack.length > 0 &&
impliesClose.has(this.stack[this.stack.length - 1])) {
var element = this.stack.pop();
while (this.stack.length > 0 && impliesClose.has(this.stack[0])) {
var element = this.stack.shift();
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, element, true);

@@ -208,9 +207,11 @@ }

if (!this.isVoidElement(name)) {
this.stack.push(name);
if (foreignContextElements.has(name)) {
this.foreignContext.push(true);
this.stack.unshift(name);
if (this.htmlMode) {
if (foreignContextElements.has(name)) {
this.foreignContext.unshift(true);
}
else if (htmlIntegrationElements.has(name)) {
this.foreignContext.unshift(false);
}
}
else if (htmlIntegrationElements.has(name)) {
this.foreignContext.push(false);
}
}

@@ -242,3 +243,3 @@ (_d = (_c = this.cbs).onopentagname) === null || _d === void 0 ? void 0 : _d.call(_c, name);

Parser.prototype.onclosetag = function (start, endIndex) {
var _a, _b, _c, _d, _e, _f;
var _a, _b, _c, _d, _e, _f, _g, _h;
this.endIndex = endIndex;

@@ -249,20 +250,17 @@ var name = this.getSlice(start, endIndex);

}
if (foreignContextElements.has(name) ||
htmlIntegrationElements.has(name)) {
this.foreignContext.pop();
if (this.htmlMode &&
(foreignContextElements.has(name) ||
htmlIntegrationElements.has(name))) {
this.foreignContext.shift();
}
if (!this.isVoidElement(name)) {
var pos = this.stack.lastIndexOf(name);
var pos = this.stack.indexOf(name);
if (pos !== -1) {
if (this.cbs.onclosetag) {
var count = this.stack.length - pos;
while (count--) {
// We know the stack has sufficient elements.
this.cbs.onclosetag(this.stack.pop(), count !== 0);
}
for (var index = 0; index <= pos; index++) {
var element = this.stack.shift();
// We know the stack has sufficient elements.
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, element, index !== pos);
}
else
this.stack.length = pos;
}
else if (!this.options.xmlMode && name === "p") {
else if (this.htmlMode && name === "p") {
// Implicit open before close

@@ -273,7 +271,7 @@ this.emitOpenTag("p");

}
else if (!this.options.xmlMode && name === "br") {
else if (this.htmlMode && name === "br") {
// 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);
(_d = (_c = this.cbs).onopentagname) === null || _d === void 0 ? void 0 : _d.call(_c, "br");
(_f = (_e = this.cbs).onopentag) === null || _f === void 0 ? void 0 : _f.call(_e, "br", {}, true);
(_h = (_g = this.cbs).onclosetag) === null || _h === void 0 ? void 0 : _h.call(_g, "br", false);
}

@@ -286,5 +284,3 @@ // Set `startIndex` for next node

this.endIndex = endIndex;
if (this.options.xmlMode ||
this.options.recognizeSelfClosing ||
this.foreignContext[this.foreignContext.length - 1]) {
if (this.options.recognizeSelfClosing || this.foreignContext[0]) {
this.closeCurrentTag(false);

@@ -304,6 +300,6 @@ // Set `startIndex` for next node

// Self-closing tags will be on the top of the stack
if (this.stack[this.stack.length - 1] === name) {
if (this.stack[0] === name) {
// If the opening tag isn't implied, the closing tag has to be implied.
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, name, !isOpenImplied);
this.stack.pop();
this.stack.shift();
}

@@ -388,3 +384,3 @@ };

var value = this.getSlice(start, endIndex - offset);
if (this.options.xmlMode || this.options.recognizeCDATA) {
if (!this.htmlMode || this.options.recognizeCDATA) {
(_b = (_a = this.cbs).oncdatastart) === null || _b === void 0 ? void 0 : _b.call(_a);

@@ -407,4 +403,5 @@ (_d = (_c = this.cbs).ontext) === null || _d === void 0 ? void 0 : _d.call(_c, value);

this.endIndex = this.startIndex;
for (var index = this.stack.length; index > 0; this.cbs.onclosetag(this.stack[--index], true))
;
for (var index = 0; index < this.stack.length; index++) {
this.cbs.onclosetag(this.stack[index], true);
}
}

@@ -428,2 +425,4 @@ (_b = (_a = this.cbs).onend) === null || _b === void 0 ? void 0 : _b.call(_a);

this.buffers.length = 0;
this.foreignContext.length = 0;
this.foreignContext.unshift(!this.htmlMode);
this.bufferOffset = 0;

@@ -430,0 +429,0 @@ this.writeIndex = 0;

30

lib/Tokenizer.d.ts

@@ -22,3 +22,3 @@ export declare enum QuoteType {

ontext(start: number, endIndex: number): void;
ontextentity(codepoint: number): void;
ontextentity(codepoint: number, endIndex: number): void;
}

@@ -35,2 +35,4 @@ export default class Tokenizer {

private index;
/** The start of the last entity. */
private entityStart;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */

@@ -46,3 +48,3 @@ private baseState;

private readonly decodeEntities;
private readonly entityTrie;
private readonly entityDecoder;
constructor({ xmlMode, decodeEntities, }: {

@@ -57,10 +59,2 @@ xmlMode?: boolean;

resume(): void;
/**
* The current index within all of the written data.
*/
getIndex(): number;
/**
* The start of the current section.
*/
getSectionStart(): number;
private stateText;

@@ -117,15 +111,4 @@ private currentSequence;

private stateBeforeSpecialS;
private trieIndex;
private trieCurrent;
/** For named entities, the index of the value. For numeric entities, the code point. */
private entityResult;
private entityExcess;
private stateBeforeEntity;
private stateInNamedEntity;
private emitNamedEntity;
private stateBeforeNumericEntity;
private emitNumericEntity;
private stateInNumericEntity;
private stateInHexEntity;
private allowLegacyEntity;
private startEntity;
private stateInEntity;
/**

@@ -145,5 +128,4 @@ * Remove data that has already been consumed from the buffer.

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

272

lib/Tokenizer.js

@@ -67,7 +67,3 @@ "use strict";

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["InEntity"] = 25] = "InEntity";
})(State || (State = {}));

@@ -84,5 +80,2 @@ function isWhitespace(c) {

}
function isNumber(c) {
return c >= CharCodes.Zero && c <= CharCodes.Nine;
}
function isASCIIAlpha(c) {

@@ -92,6 +85,2 @@ return ((c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||

}
function isHexDigit(c) {
return ((c >= CharCodes.UpperA && c <= CharCodes.UpperF) ||
(c >= CharCodes.LowerA && c <= CharCodes.LowerF));
}
var QuoteType;

@@ -121,2 +110,3 @@ (function (QuoteType) {

var _b = _a.xmlMode, xmlMode = _b === void 0 ? false : _b, _c = _a.decodeEntities, decodeEntities = _c === void 0 ? true : _c;
var _this = this;
this.cbs = cbs;

@@ -131,2 +121,4 @@ /** The current state the tokenizer is in. */

this.index = 0;
/** The start of the last entity. */
this.entityStart = 0;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */

@@ -142,10 +134,5 @@ this.baseState = State.Text;

this.sequenceIndex = 0;
this.trieIndex = 0;
this.trieCurrent = 0;
/** 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_js_1.xmlDecodeTree : decode_js_1.htmlDecodeTree;
this.entityDecoder = new decode_js_1.EntityDecoder(xmlMode ? decode_js_1.xmlDecodeTree : decode_js_1.htmlDecodeTree, function (cp, consumed) { return _this.emitCodePoint(cp, consumed); });
}

@@ -180,14 +167,2 @@ Tokenizer.prototype.reset = function () {

};
/**
* The current index within all of the written data.
*/
Tokenizer.prototype.getIndex = function () {
return this.index;
};
/**
* The start of the current section.
*/
Tokenizer.prototype.getSectionStart = function () {
return this.sectionStart;
};
Tokenizer.prototype.stateText = function (c) {

@@ -203,3 +178,3 @@ if (c === CharCodes.Lt ||

else if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -251,3 +226,3 @@ };

if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -413,3 +388,2 @@ }

this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;

@@ -428,3 +402,2 @@ }

}
this.baseState = this.state;
this.sectionStart = this.index + 1;

@@ -444,3 +417,2 @@ }

this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;

@@ -503,4 +475,3 @@ this.isSpecial = false; // Reset special state, in case of self-closing special tags

else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -523,4 +494,3 @@ };

else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
this.startEntity();
}

@@ -586,146 +556,27 @@ };

};
Tokenizer.prototype.stateBeforeEntity = function (c) {
// Start excess with 1 to include the '&'
this.entityExcess = 1;
this.entityResult = 0;
if (c === CharCodes.Number) {
this.state = State.BeforeNumericEntity;
}
else if (c === CharCodes.Amp) {
// We have two `&` characters in a row. Stay in the current state.
}
else {
this.trieIndex = 0;
this.trieCurrent = this.entityTrie[0];
this.state = State.InNamedEntity;
this.stateInNamedEntity(c);
}
Tokenizer.prototype.startEntity = function () {
this.baseState = this.state;
this.state = State.InEntity;
this.entityStart = this.index;
this.entityDecoder.startEntity(this.xmlMode
? decode_js_1.DecodingMode.Strict
: this.baseState === State.Text ||
this.baseState === State.InSpecialTag
? decode_js_1.DecodingMode.Legacy
: decode_js_1.DecodingMode.Attribute);
};
Tokenizer.prototype.stateInNamedEntity = function (c) {
this.entityExcess += 1;
this.trieIndex = (0, decode_js_1.determineBranch)(this.entityTrie, this.trieCurrent, this.trieIndex + 1, c);
if (this.trieIndex < 0) {
this.emitNamedEntity();
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 (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 !== CharCodes.Semi) {
this.trieIndex += valueLength;
Tokenizer.prototype.stateInEntity = function () {
var length = this.entityDecoder.write(this.buffer, this.index - this.offset);
// 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 {
// Add 1 as we have already incremented the excess
var entityStart = this.index - this.entityExcess + 1;
if (entityStart > this.sectionStart) {
this.emitPartial(this.sectionStart, entityStart);
}
// 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;
if (valueLength === 0) {
this.emitNamedEntity();
}
}
}
};
Tokenizer.prototype.emitNamedEntity = function () {
this.state = this.baseState;
if (this.entityResult === 0) {
return;
}
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) === CharCodes.LowerX) {
this.entityExcess++;
this.state = State.InHexEntity;
}
else {
this.state = State.InNumericEntity;
this.stateInNumericEntity(c);
// Mark buffer as consumed.
this.index = this.offset + this.buffer.length - 1;
}
};
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.sectionStart, entityStart);
}
this.sectionStart = this.index + Number(strict);
this.emitCodePoint((0, decode_js_1.replaceCodePoint)(this.entityResult));
}
this.state = this.baseState;
};
Tokenizer.prototype.stateInNumericEntity = function (c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if (isNumber(c)) {
this.entityResult = this.entityResult * 10 + (c - CharCodes.Zero);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
};
Tokenizer.prototype.stateInHexEntity = function (c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
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.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
};
Tokenizer.prototype.allowLegacyEntity = function () {
return (!this.xmlMode &&
(this.baseState === State.Text ||
this.baseState === State.InSpecialTag));
};
/**

@@ -858,22 +709,6 @@ * Remove data that has already been consumed from the buffer.

}
case State.InNamedEntity: {
this.stateInNamedEntity(c);
case State.InEntity: {
this.stateInEntity();
break;
}
case State.BeforeEntity: {
this.stateBeforeEntity(c);
break;
}
case State.InHexEntity: {
this.stateInHexEntity(c);
break;
}
case State.InNumericEntity: {
this.stateInNumericEntity(c);
break;
}
default: {
// `this._state === State.BeforeNumericEntity`
this.stateBeforeNumericEntity(c);
}
}

@@ -885,9 +720,7 @@ this.index++;

Tokenizer.prototype.finish = function () {
if (this.state === State.InNamedEntity) {
this.emitNamedEntity();
if (this.state === State.InEntity) {
this.entityDecoder.end();
this.state = this.baseState;
}
// If there is remaining data, emit it in a reasonable way
if (this.sectionStart < this.index) {
this.handleTrailingData();
}
this.handleTrailingData();
this.cbs.onend();

@@ -898,2 +731,6 @@ };

var endIndex = this.buffer.length + this.offset;
// If there is no remaining data, we are done.
if (this.sectionStart >= endIndex) {
return;
}
if (this.state === State.InCommentLike) {

@@ -907,12 +744,2 @@ if (this.currentSequence === Sequences.CdataEnd) {

}
else if (this.state === State.InNumericEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InHexEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InTagName ||

@@ -936,18 +763,19 @@ this.state === State.BeforeAttributeName ||

};
Tokenizer.prototype.emitPartial = function (start, endIndex) {
Tokenizer.prototype.emitCodePoint = function (cp, consumed) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribdata(start, endIndex);
}
else {
this.cbs.ontext(start, endIndex);
}
};
Tokenizer.prototype.emitCodePoint = function (cp) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
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(cp);
}
else {
this.cbs.ontextentity(cp);
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(cp, this.sectionStart);
}

@@ -954,0 +782,0 @@ };

26

package.json
{
"name": "htmlparser2",
"description": "Fast & forgiving HTML/XML parser",
"version": "8.0.2",
"version": "9.0.0",
"author": "Felix Boehm <me@feedic.com>",

@@ -66,18 +66,18 @@ "funding": [

"domhandler": "^5.0.3",
"domutils": "^3.0.1",
"entities": "^4.4.0"
"domutils": "^3.1.0",
"entities": "^4.5.0"
},
"devDependencies": {
"@types/jest": "^29.5.0",
"@types/node": "^18.15.5",
"@typescript-eslint/eslint-plugin": "^5.56.0",
"@typescript-eslint/parser": "^5.56.0",
"eslint": "^8.36.0",
"@types/jest": "^29.5.1",
"@types/node": "^20.1.1",
"@typescript-eslint/eslint-plugin": "^5.59.5",
"@typescript-eslint/parser": "^5.59.5",
"eslint": "^8.40.0",
"eslint-config-prettier": "^8.8.0",
"eslint-plugin-n": "^15.6.1",
"eslint-plugin-unicorn": "^46.0.0",
"eslint-plugin-n": "^15.7.0",
"eslint-plugin-unicorn": "^47.0.0",
"jest": "^29.5.0",
"prettier": "^2.8.6",
"ts-jest": "^29.0.5",
"typescript": "^4.9.5"
"prettier": "^2.8.8",
"ts-jest": "^29.1.0",
"typescript": "^5.0.4"
},

@@ -84,0 +84,0 @@ "jest": {

7

README.md

@@ -120,4 +120,6 @@ # htmlparser2

## Parsing RSS/RDF/Atom Feeds
## Parsing Feeds
`htmlparser2` makes it easy to parse RSS, RDF and Atom feeds, by providing a `parseFeed` method:
```javascript

@@ -127,5 +129,2 @@ const feed = htmlparser2.parseFeed(content, options);

Note: While the provided feed handler works for most feeds,
you might want to use [danmactough/node-feedparser](https://github.com/danmactough/node-feedparser), which is much better tested and actively maintained.
## Performance

@@ -132,0 +131,0 @@ 

lib/esm/index.d.ts.map

Sorry, the diff of this file is not supported yet

lib/esm/index.js.map

Sorry, the diff of this file is not supported yet

lib/esm/Parser.d.ts.map

Sorry, the diff of this file is not supported yet

lib/esm/Parser.js.map

Sorry, the diff of this file is not supported yet

lib/esm/Tokenizer.d.ts.map

Sorry, the diff of this file is not supported yet

lib/esm/Tokenizer.js.map

Sorry, the diff of this file is not supported yet

lib/esm/WritableStream.d.ts.map

Sorry, the diff of this file is not supported yet

lib/esm/WritableStream.js.map

Sorry, the diff of this file is not supported yet

lib/index.d.ts.map

Sorry, the diff of this file is not supported yet

lib/index.js.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/Parser.js.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/Tokenizer.js.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

lib/WritableStream.js.map

Sorry, the diff of this file is not supported yet

SocketSocket SOC 2 Logo

Product

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

About

Packages

npm

Go

Maven

PyPI

Rubygems

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc