@focusconsulting/auto-a11y/dist/sanitize-html.js

A powerful tool that combines AI with accessibility-first element selection for Playwright tests

"use strict";
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 () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.simplifyHtml = simplifyHtml;
exports.extractBodyContent = extractBodyContent;
const cheerio = __importStar(require("cheerio"));
const sanitize_html_1 = __importDefault(require("sanitize-html"));
/**
 * Simplifies HTML by keeping only essential elements and attributes
 * @param html The HTML content to simplify
 * @returns Simplified HTML string
 */
function simplifyHtml(html) {
    return (0, sanitize_html_1.default)(html, {
        allowedTags: [
            "a",
            "button",
            "input",
            "select",
            "textarea",
            "label",
            "h1",
            "h2",
            "h3",
            "h4",
            "h5",
            "h6",
            "p",
            "img",
        ],
        exclusiveFilter: (frame) => {
            // TODO: check how this function works
            return (frame.tag === "div" || frame.tag === "span") && Object.keys(frame.attribs).includes("role");
        },
        allowedAttributes: {
            "*": ["checked", "aria-*", "name", "data-testid", "role", "region", "value"]
        }
    });
}
/**
 * Extracts and sanitizes the body content from HTML
 * @param html The full HTML content
 * @param description The element description to help focus the extraction
 * @returns Sanitized body content
 */
function extractBodyContent(html) {
    try {
        const cleaned = (0, sanitize_html_1.default)(html, {
            allowedTags: sanitize_html_1.default.defaults.allowedTags.concat(["img"]),
            allowedAttributes: {
                "*": ["checked", "aria-*", "name", "data-testid", "role", "region", "value"]
            }
        });
        const $ = cheerio.load(cleaned);
        // Simplify deeply nested structures
        $("div > div:only-child").each((_, el) => {
            const $el = $(el);
            const $parent = $el.parent();
            if ($parent.children().length === 1 &&
                !$el.is("button, a, input, select, textarea")) {
                // Replace the parent with its children
                const $children = $el.children();
                $el.replaceWith($children);
            }
        });
        // Remove empty containers
        $("div:empty, span:empty").remove();
        // If no relevant elements found or context extraction failed,
        // get the body content and truncate if necessary
        let bodyContent = $("body").html() || $.html();
        if (bodyContent.length > 8192) {
            console.warn("Body content might be too large for the context window");
        }
        return bodyContent.trim();
    }
    catch (error) {
        console.warn(`Error extracting body content: ${error}`);
        return html.length > 20000
            ? html.substring(0, 10000) + "..." + html.substring(html.length - 10000)
            : html;
    }
}