init

node_modules/parse5-sax-parser/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2013-2019 Ivan Nikulin (ifaaan@gmail.com, https://github.com/inikulin)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

node_modules/parse5-sax-parser/README.md

@@ -0,0 +1,34 @@
+<p align="center">
+    <a href="https://github.com/inikulin/parse5">
+        <img src="https://raw.github.com/inikulin/parse5/master/media/logo.png" alt="parse5" />
+    </a>
+</p>
+
+<div align="center">
+<h1>parse5-sax-parser</h1>
+<i><b>Streaming <a href="https://en.wikipedia.org/wiki/Simple_API_for_XML">SAX</a>-style HTML parser.</b></i>
+</div>
+<br>
+
+<div align="center">
+<code>npm install --save parse5-sax-parser</code>
+</div>
+<br>
+
+<p align="center">
+  📖 <a href="https://parse5.js.org/modules/parse5-sax-parser.html"><b>Documentation</b></a> 📖
+</p>
+
+---
+
+<p align="center">
+  <a href="https://github.com/inikulin/parse5/tree/master/docs/list-of-packages.md">List of parse5 toolset packages</a>
+</p>
+
+<p align="center">
+    <a href="https://github.com/inikulin/parse5">GitHub</a>
+</p>
+
+<p align="center">
+    <a href="https://github.com/inikulin/parse5/releases">Changelog</a>
+</p>

node_modules/parse5-sax-parser/dist/dev-null-stream.d.ts

@@ -0,0 +1,4 @@
+import { Writable } from 'node:stream';
+export declare class DevNullStream extends Writable {
+    _write(_chunk: string, _encoding: string, cb: () => void): void;
+}

node_modules/parse5-sax-parser/dist/dev-null-stream.js

@@ -0,0 +1,6 @@
+import { Writable } from 'node:stream';
+export class DevNullStream extends Writable {
+    _write(_chunk, _encoding, cb) {
+        cb();
+    }
+}

node_modules/parse5-sax-parser/dist/index.d.ts

@@ -0,0 +1,153 @@
+import { Transform } from 'node:stream';
+import type { Tokenizer, TokenHandler, Token } from 'parse5';
+import { ParserFeedbackSimulator } from './parser-feedback-simulator.js';
+export interface SAXParserOptions {
+    /**
+     * Enables source code location information for tokens.
+     *
+     * When enabled, each token will have a `sourceCodeLocation` property.
+     */
+    sourceCodeLocationInfo?: boolean;
+}
+/**
+ * Streaming [SAX](https://en.wikipedia.org/wiki/Simple_API_for_XML)-style HTML parser.
+ * A [transform stream](https://nodejs.org/api/stream.html#stream_class_stream_transform) (which means you can pipe _through_ it, see example).
+ *
+ * @example
+ *
+ * ```js
+ *     const SAXParser = require('parse5-sax-parser');
+ *     const http = require('http');
+ *     const fs = require('fs');
+ *
+ *     const file = fs.createWriteStream('/home/google.com.html');
+ *     const parser = new SAXParser();
+ *
+ *     parser.on('text', text => {
+ *        // Handle page text content
+ *        ...
+ *     });
+ *
+ *     http.get('http://google.com', res => {
+ *        // `SAXParser` is the `Transform` stream, which means you can pipe
+ *        // through it. So, you can analyze the page content and, e.g., save it
+ *        // to the file at the same time:
+ *        res.pipe(parser).pipe(file);
+ *     });
+ * ```
+ */
+export declare class SAXParser extends Transform implements TokenHandler {
+    protected options: SAXParserOptions;
+    /** @internal */
+    protected parserFeedbackSimulator: ParserFeedbackSimulator;
+    private pendingText;
+    private lastChunkWritten;
+    private stopped;
+    protected tokenizer: Tokenizer;
+    /**
+     * @param options Parsing options.
+     */
+    constructor(options?: SAXParserOptions);
+    _transform(chunk: string, _encoding: string, callback: (error?: Error | null, data?: string) => void): void;
+    _final(callback: (error?: Error | null, data?: string) => void): void;
+    /**
+     * Stops parsing. Useful if you want the parser to stop consuming CPU time
+     * once you've obtained the desired info from the input stream. Doesn't
+     * prevent piping, so that data will flow through the parser as usual.
+     *
+     * @example
+     *
+     * ```js
+     * const SAXParser = require('parse5-sax-parser');
+     * const http = require('http');
+     * const fs = require('fs');
+     *
+     * const file = fs.createWriteStream('google.com.html');
+     * const parser = new SAXParser();
+     *
+     * parser.on('doctype', ({ name, publicId, systemId }) => {
+     *     // Process doctype info and stop parsing
+     *     ...
+     *     parser.stop();
+     * });
+     *
+     * http.get('http://google.com', res => {
+     *     // Despite the fact that parser.stop() was called whole
+     *     // content of the page will be written to the file
+     *     res.pipe(parser).pipe(file);
+     * });
+     * ```
+     */
+    stop(): void;
+    protected _transformChunk(chunk: string): string;
+    /** @internal */
+    onCharacter({ chars, location }: Token.CharacterToken): void;
+    /** @internal */
+    onWhitespaceCharacter(token: Token.CharacterToken): void;
+    /** @internal */
+    onNullCharacter(token: Token.CharacterToken): void;
+    /** @internal */
+    onEof(): void;
+    /** @internal */
+    onStartTag(token: Token.TagToken): void;
+    /** @internal */
+    onEndTag(token: Token.TagToken): void;
+    /** @internal */
+    onDoctype(token: Token.DoctypeToken): void;
+    /** @internal */
+    onComment(token: Token.CommentToken): void;
+    protected emitIfListenerExists(eventName: string, token: SaxToken): boolean;
+    protected _emitToken(eventName: string, token: SaxToken): void;
+    private _emitPendingText;
+}
+export interface SaxToken {
+    /** Source code location info. Available if location info is enabled via {@link SAXParserOptions}. */
+    sourceCodeLocation?: Token.Location | null;
+}
+export interface StartTag extends SaxToken {
+    /** Tag name */
+    tagName: string;
+    /** List of attributes */
+    attrs: Token.Attribute[];
+    /** Indicates if the tag is self-closing */
+    selfClosing: boolean;
+}
+export interface EndTag extends SaxToken {
+    /** Tag name */
+    tagName: string;
+}
+export interface Text extends SaxToken {
+    /** Text content. */
+    text: string;
+}
+export interface Comment extends SaxToken {
+    /** Comment text. */
+    text: string;
+}
+export interface Doctype extends SaxToken {
+    /** Document type name. */
+    name: string | null;
+    /** Document type public identifier. */
+    publicId: string | null;
+    /** Document type system identifier. */
+    systemId: string | null;
+}
+export interface SAXParser {
+    /** Raised when the parser encounters a start tag. */
+    on(event: 'startTag', listener: (startTag: StartTag) => void): this;
+    /** Raised when the parser encounters an end tag. */
+    on(event: 'endTag', listener: (endTag: EndTag) => void): this;
+    /** Raised when the parser encounters a comment. */
+    on(event: 'comment', listener: (comment: Comment) => void): this;
+    /** Raised when the parser encounters text content. */
+    on(event: 'text', listener: (text: Text) => void): this;
+    /** Raised when the parser encounters a [document type declaration](https://en.wikipedia.org/wiki/Document_type_declaration) */
+    on(event: 'doctype', listener: (doctype: Doctype) => void): this;
+    /**
+     * Base event handler.
+     *
+     * @param event Name of the event
+     * @param handler Event handler
+     */
+    on(event: string, handler: (...args: any[]) => void): this;
+}

node_modules/parse5-sax-parser/dist/index.js

@@ -0,0 +1,191 @@
+import { Transform } from 'node:stream';
+import { DevNullStream } from './dev-null-stream.js';
+import { ParserFeedbackSimulator } from './parser-feedback-simulator.js';
+/**
+ * Streaming [SAX](https://en.wikipedia.org/wiki/Simple_API_for_XML)-style HTML parser.
+ * A [transform stream](https://nodejs.org/api/stream.html#stream_class_stream_transform) (which means you can pipe _through_ it, see example).
+ *
+ * @example
+ *
+ * ```js
+ *     const SAXParser = require('parse5-sax-parser');
+ *     const http = require('http');
+ *     const fs = require('fs');
+ *
+ *     const file = fs.createWriteStream('/home/google.com.html');
+ *     const parser = new SAXParser();
+ *
+ *     parser.on('text', text => {
+ *        // Handle page text content
+ *        ...
+ *     });
+ *
+ *     http.get('http://google.com', res => {
+ *        // `SAXParser` is the `Transform` stream, which means you can pipe
+ *        // through it. So, you can analyze the page content and, e.g., save it
+ *        // to the file at the same time:
+ *        res.pipe(parser).pipe(file);
+ *     });
+ * ```
+ */
+export class SAXParser extends Transform {
+    /**
+     * @param options Parsing options.
+     */
+    constructor(options = {}) {
+        super({ encoding: 'utf8', decodeStrings: false });
+        this.pendingText = null;
+        this.lastChunkWritten = false;
+        this.stopped = false;
+        this.options = {
+            sourceCodeLocationInfo: false,
+            ...options,
+        };
+        this.parserFeedbackSimulator = new ParserFeedbackSimulator(this.options, this);
+        this.tokenizer = this.parserFeedbackSimulator.tokenizer;
+        // NOTE: always pipe the stream to the /dev/null stream to avoid
+        // the `highWaterMark` to be hit even if we don't have consumers.
+        // (see: https://github.com/inikulin/parse5/issues/97#issuecomment-171940774)
+        this.pipe(new DevNullStream());
+    }
+    //`Transform` implementation
+    _transform(chunk, _encoding, callback) {
+        if (typeof chunk !== 'string') {
+            throw new TypeError('Parser can work only with string streams.');
+        }
+        callback(null, this._transformChunk(chunk));
+    }
+    _final(callback) {
+        this.lastChunkWritten = true;
+        callback(null, this._transformChunk(''));
+    }
+    /**
+     * Stops parsing. Useful if you want the parser to stop consuming CPU time
+     * once you've obtained the desired info from the input stream. Doesn't
+     * prevent piping, so that data will flow through the parser as usual.
+     *
+     * @example
+     *
+     * ```js
+     * const SAXParser = require('parse5-sax-parser');
+     * const http = require('http');
+     * const fs = require('fs');
+     *
+     * const file = fs.createWriteStream('google.com.html');
+     * const parser = new SAXParser();
+     *
+     * parser.on('doctype', ({ name, publicId, systemId }) => {
+     *     // Process doctype info and stop parsing
+     *     ...
+     *     parser.stop();
+     * });
+     *
+     * http.get('http://google.com', res => {
+     *     // Despite the fact that parser.stop() was called whole
+     *     // content of the page will be written to the file
+     *     res.pipe(parser).pipe(file);
+     * });
+     * ```
+     */
+    stop() {
+        this.stopped = true;
+        this.tokenizer.pause();
+    }
+    //Internals
+    _transformChunk(chunk) {
+        if (!this.stopped) {
+            this.tokenizer.write(chunk, this.lastChunkWritten);
+        }
+        return chunk;
+    }
+    /** @internal */
+    onCharacter({ chars, location }) {
+        if (this.pendingText === null) {
+            this.pendingText = { text: chars, sourceCodeLocation: location };
+        }
+        else {
+            this.pendingText.text += chars;
+            if (location && this.pendingText.sourceCodeLocation) {
+                const { endLine, endCol, endOffset } = location;
+                this.pendingText.sourceCodeLocation = {
+                    ...this.pendingText.sourceCodeLocation,
+                    endLine,
+                    endCol,
+                    endOffset,
+                };
+            }
+        }
+        if (this.tokenizer.preprocessor.willDropParsedChunk()) {
+            this._emitPendingText();
+        }
+    }
+    /** @internal */
+    onWhitespaceCharacter(token) {
+        this.onCharacter(token);
+    }
+    /** @internal */
+    onNullCharacter(token) {
+        this.onCharacter(token);
+    }
+    /** @internal */
+    onEof() {
+        this._emitPendingText();
+        this.stopped = true;
+    }
+    /** @internal */
+    onStartTag(token) {
+        this._emitPendingText();
+        const startTag = {
+            tagName: token.tagName,
+            attrs: token.attrs,
+            selfClosing: token.selfClosing,
+            sourceCodeLocation: token.location,
+        };
+        this.emitIfListenerExists('startTag', startTag);
+    }
+    /** @internal */
+    onEndTag(token) {
+        this._emitPendingText();
+        const endTag = {
+            tagName: token.tagName,
+            sourceCodeLocation: token.location,
+        };
+        this.emitIfListenerExists('endTag', endTag);
+    }
+    /** @internal */
+    onDoctype(token) {
+        this._emitPendingText();
+        const doctype = {
+            name: token.name,
+            publicId: token.publicId,
+            systemId: token.systemId,
+            sourceCodeLocation: token.location,
+        };
+        this.emitIfListenerExists('doctype', doctype);
+    }
+    /** @internal */
+    onComment(token) {
+        this._emitPendingText();
+        const comment = {
+            text: token.data,
+            sourceCodeLocation: token.location,
+        };
+        this.emitIfListenerExists('comment', comment);
+    }
+    emitIfListenerExists(eventName, token) {
+        if (this.listenerCount(eventName) === 0) {
+            return false;
+        }
+        this._emitToken(eventName, token);
+        return true;
+    }
+    _emitToken(eventName, token) {
+        this.emit(eventName, token);
+    }
+    _emitPendingText() {
+        if (this.pendingText !== null) {
+            this.emitIfListenerExists('text', this.pendingText);
+            this.pendingText = null;
+        }
+    }
+}

node_modules/parse5-sax-parser/dist/parser-feedback-simulator.d.ts

@@ -0,0 +1,31 @@
+import { Tokenizer, type TokenizerOptions, type TokenHandler, Token } from 'parse5';
+/**
+ * Simulates adjustments of the Tokenizer which are performed by the standard parser during tree construction.
+ */
+export declare class ParserFeedbackSimulator implements TokenHandler {
+    private handler;
+    private namespaceStack;
+    inForeignContent: boolean;
+    skipNextNewLine: boolean;
+    tokenizer: Tokenizer;
+    constructor(options: TokenizerOptions, handler: TokenHandler);
+    /** @internal */
+    onNullCharacter(token: Token.CharacterToken): void;
+    /** @internal */
+    onWhitespaceCharacter(token: Token.CharacterToken): void;
+    /** @internal */
+    onCharacter(token: Token.CharacterToken): void;
+    /** @internal */
+    onComment(token: Token.CommentToken): void;
+    /** @internal */
+    onDoctype(token: Token.DoctypeToken): void;
+    /** @internal */
+    onEof(token: Token.EOFToken): void;
+    private _enterNamespace;
+    private _leaveCurrentNamespace;
+    private _ensureTokenizerMode;
+    /** @internal */
+    onStartTag(token: Token.TagToken): void;
+    /** @internal */
+    onEndTag(token: Token.TagToken): void;
+}

node_modules/parse5-sax-parser/dist/parser-feedback-simulator.js

@@ -0,0 +1,183 @@
+import { Tokenizer, TokenizerMode, Token, foreignContent, html, } from 'parse5';
+const $ = html.TAG_ID;
+const REPLACEMENT_CHARACTER = '\uFFFD';
+const LINE_FEED_CODE_POINT = 0x0a;
+/**
+ * Simulates adjustments of the Tokenizer which are performed by the standard parser during tree construction.
+ */
+export class ParserFeedbackSimulator {
+    constructor(options, handler) {
+        this.handler = handler;
+        this.namespaceStack = [];
+        this.inForeignContent = false;
+        this.skipNextNewLine = false;
+        this.tokenizer = new Tokenizer(options, this);
+        this._enterNamespace(html.NS.HTML);
+    }
+    /** @internal */
+    onNullCharacter(token) {
+        this.skipNextNewLine = false;
+        if (this.inForeignContent) {
+            this.handler.onCharacter({
+                type: Token.TokenType.CHARACTER,
+                chars: REPLACEMENT_CHARACTER,
+                location: token.location,
+            });
+        }
+        else {
+            this.handler.onNullCharacter(token);
+        }
+    }
+    /** @internal */
+    onWhitespaceCharacter(token) {
+        if (this.skipNextNewLine && token.chars.charCodeAt(0) === LINE_FEED_CODE_POINT) {
+            this.skipNextNewLine = false;
+            if (token.chars.length === 1) {
+                return;
+            }
+            token.chars = token.chars.substr(1);
+        }
+        this.handler.onWhitespaceCharacter(token);
+    }
+    /** @internal */
+    onCharacter(token) {
+        this.skipNextNewLine = false;
+        this.handler.onCharacter(token);
+    }
+    /** @internal */
+    onComment(token) {
+        this.skipNextNewLine = false;
+        this.handler.onComment(token);
+    }
+    /** @internal */
+    onDoctype(token) {
+        this.skipNextNewLine = false;
+        this.handler.onDoctype(token);
+    }
+    /** @internal */
+    onEof(token) {
+        this.skipNextNewLine = false;
+        this.handler.onEof(token);
+    }
+    //Namespace stack mutations
+    _enterNamespace(namespace) {
+        this.namespaceStack.unshift(namespace);
+        this.inForeignContent = namespace !== html.NS.HTML;
+        this.tokenizer.inForeignNode = this.inForeignContent;
+    }
+    _leaveCurrentNamespace() {
+        this.namespaceStack.shift();
+        this.inForeignContent = this.namespaceStack[0] !== html.NS.HTML;
+        this.tokenizer.inForeignNode = this.inForeignContent;
+    }
+    //Token handlers
+    _ensureTokenizerMode(tn) {
+        switch (tn) {
+            case $.TEXTAREA:
+            case $.TITLE: {
+                this.tokenizer.state = TokenizerMode.RCDATA;
+                break;
+            }
+            case $.PLAINTEXT: {
+                this.tokenizer.state = TokenizerMode.PLAINTEXT;
+                break;
+            }
+            case $.SCRIPT: {
+                this.tokenizer.state = TokenizerMode.SCRIPT_DATA;
+                break;
+            }
+            case $.STYLE:
+            case $.IFRAME:
+            case $.XMP:
+            case $.NOEMBED:
+            case $.NOFRAMES:
+            case $.NOSCRIPT: {
+                this.tokenizer.state = TokenizerMode.RAWTEXT;
+                break;
+            }
+            default:
+            // Do nothing
+        }
+    }
+    /** @internal */
+    onStartTag(token) {
+        let tn = token.tagID;
+        switch (tn) {
+            case $.SVG: {
+                this._enterNamespace(html.NS.SVG);
+                break;
+            }
+            case $.MATH: {
+                this._enterNamespace(html.NS.MATHML);
+                break;
+            }
+            default:
+            // Do nothing
+        }
+        if (this.inForeignContent) {
+            if (foreignContent.causesExit(token)) {
+                this._leaveCurrentNamespace();
+            }
+            else {
+                const currentNs = this.namespaceStack[0];
+                if (currentNs === html.NS.MATHML) {
+                    foreignContent.adjustTokenMathMLAttrs(token);
+                }
+                else if (currentNs === html.NS.SVG) {
+                    foreignContent.adjustTokenSVGTagName(token);
+                    foreignContent.adjustTokenSVGAttrs(token);
+                }
+                foreignContent.adjustTokenXMLAttrs(token);
+                tn = token.tagID;
+                if (!token.selfClosing && foreignContent.isIntegrationPoint(tn, currentNs, token.attrs)) {
+                    this._enterNamespace(html.NS.HTML);
+                }
+            }
+        }
+        else {
+            switch (tn) {
+                case $.PRE:
+                case $.TEXTAREA:
+                case $.LISTING: {
+                    this.skipNextNewLine = true;
+                    break;
+                }
+                case $.IMAGE: {
+                    token.tagName = html.TAG_NAMES.IMG;
+                    token.tagID = $.IMG;
+                    break;
+                }
+                default:
+                // Do nothing
+            }
+            this._ensureTokenizerMode(tn);
+        }
+        this.handler.onStartTag(token);
+    }
+    /** @internal */
+    onEndTag(token) {
+        let tn = token.tagID;
+        if (!this.inForeignContent) {
+            const previousNs = this.namespaceStack[1];
+            if (previousNs === html.NS.SVG) {
+                const adjustedTagName = foreignContent.SVG_TAG_NAMES_ADJUSTMENT_MAP.get(token.tagName);
+                if (adjustedTagName) {
+                    tn = html.getTagID(adjustedTagName);
+                }
+            }
+            //NOTE: check for exit from integration point
+            if (foreignContent.isIntegrationPoint(tn, previousNs, token.attrs)) {
+                this._leaveCurrentNamespace();
+            }
+        }
+        else if ((tn === $.SVG && this.namespaceStack[0] === html.NS.SVG) ||
+            (tn === $.MATH && this.namespaceStack[0] === html.NS.MATHML)) {
+            this._leaveCurrentNamespace();
+        }
+        // NOTE: adjust end tag name as well for consistency
+        if (this.namespaceStack[0] === html.NS.SVG) {
+            foreignContent.adjustTokenSVGTagName(token);
+        }
+        this.handler.onEndTag(token);
+    }
+}

node_modules/parse5-sax-parser/package.json

@@ -0,0 +1,37 @@
+{
+    "name": "parse5-sax-parser",
+    "type": "module",
+    "description": "Streaming SAX-style HTML parser.",
+    "version": "8.0.0",
+    "author": "Ivan Nikulin <ifaaan@gmail.com> (https://github.com/inikulin)",
+    "contributors": "https://github.com/inikulin/parse5/graphs/contributors",
+    "homepage": "https://parse5.js.org",
+    "funding": "https://github.com/inikulin/parse5?sponsor=1",
+    "keywords": [
+        "parse5",
+        "parser",
+        "stream",
+        "streaming",
+        "SAX"
+    ],
+    "license": "MIT",
+    "main": "dist/index.js",
+    "module": "dist/index.js",
+    "types": "dist/index.d.ts",
+    "exports": {
+        ".": {
+            "default": "./dist/index.js"
+        }
+    },
+    "dependencies": {
+        "parse5": "^8.0.0"
+    },
+    "repository": {
+        "type": "git",
+        "url": "git://github.com/inikulin/parse5.git"
+    },
+    "files": [
+        "dist/**/*.js",
+        "dist/**/*.d.ts"
+    ]
+}