webforai 1.2.2 → 1.3.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 inaridiy
+
+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.

package/README.md

@@ -1,74 +1,74 @@
-# Web for AI
-
-![LOGO](https://github.com/inaridiy/webforai/blob/main/images/logo.webp)
-
-A library that provides a web interface for AI
-
-## Features
-
-- Ultra-precise HTML2Markdown conversion
-- Ultra-precise Markdown segmentation based on AST
-- Ultra-precise HTML retrieval functions using headless browsers
-- The core functionality is edge-native (runs on Cloudflare Workers!!!)
-
-## Demo
-
-There is a demo API for Html2Markdown deployed on CloudflareWorker. Please access the following link
-
-- [https://webforai.inaridiy.workers.dev/?url=https://www.npmjs.com/package/webforai](https://webforai.inaridiy.workers.dev/?url=https://www.npmjs.com/package/webforai)
-- [https://webforai.inaridiy.workers.dev/?html=%3Ch1%3EHello%20World%3C/h1%3E](https://webforai.inaridiy.workers.dev/?html=%3Ch1%3EHello%20World%3C/h1%3E)
-
-## Quick Start
-
-Just install and execute scripts
-
-```bash
-pnpm i webforai playwright
-```
-
-```js
-import { promises as fs } from "fs";
-import { htmlToMarkdown, htmlToMdast } from "webforai";
-import { loadHtml } from "webforai/loaders/playwright";
-
-const url = "https://www.npmjs.com/package/webforai";
-const html = await loadHtml(url);
-
-const markdown = htmlToMarkdown(html, { solveLinks: url });
-
-await fs.writeFile("output.md", markdown);
-```
-
-other examples are in [examples](./examples/simple/src/index.ts)
-
-## Usage
-
-### Main Functions
-
-**`htmlToMarkdown(html: string, options?: HtmlToMarkdownOptions): string`**  
-Convert HTML to Markdown. By default, unnecessary HTML is excluded and processed.
-If `solveLinks` is specified, the relative links in the Mdast will be resolved.
-This function just calls htmlToMdast and mdastToMarkdown in that order internally.
-
-**`htmlToMdast(html: string, options?: HtmlToMdastOptions): Mdast`**  
-This project uses Hast and Mdast as defined by syntax-tree internally.
-This function converts HTML to Mdast, an intermediate representation, which is required when using `mdastSplitter`, etc.
-
-**`mdastToMarkdown(mdast: Mdast | RootContent[], options?: { solveLinks?: string }): string`**  
-Convert Mdast to Markdown. If `solveLinks` is specified, the relative links in the Mdast will be resolved.
-
-### Loader Functions
-
-**`loadHtml(url: string, options?: LoadHtmlOptions): Promise<string>`**  
-Load HTML from the specified URL. This function uses Playwright internally.
-
-## Early Users
-
-### Voice Genius - Explanatory video generation by AI
-
-<img src="https://github.com/inaridiy/webforai/blob/main/images/voice-genius.png" width="300px">
-
-by [@moons14](https://twitter.com/moons_dev)
-
-AI can be used to automatically generate highly accurate commentary videos.
-Supports conversations and presentations using synthesized voice, embedding of images in videos, etc.
+# Web for AI
+
+![LOGO](https://github.com/inaridiy/webforai/blob/main/images/logo.webp)
+
+A library that provides a web interface for AI
+
+## Features
+
+- Ultra-precise HTML2Markdown conversion
+- Ultra-precise Markdown segmentation based on AST
+- Ultra-precise HTML retrieval functions using headless browsers
+- The core functionality is edge-native (runs on Cloudflare Workers!!!)
+
+## Demo
+
+There is a demo API for Html2Markdown deployed on CloudflareWorker. Please access the following link
+
+- [https://webforai.inaridiy.workers.dev/?url=https://www.npmjs.com/package/webforai](https://webforai.inaridiy.workers.dev/?url=https://www.npmjs.com/package/webforai)
+- [https://webforai.inaridiy.workers.dev/?html=%3Ch1%3EHello%20World%3C/h1%3E](https://webforai.inaridiy.workers.dev/?html=%3Ch1%3EHello%20World%3C/h1%3E)
+
+## Quick Start
+
+Just install and execute scripts
+
+```bash
+pnpm i webforai playwright
+```
+
+```js
+import { promises as fs } from "fs";
+import { htmlToMarkdown, htmlToMdast } from "webforai";
+import { loadHtml } from "webforai/loaders/playwright";
+
+const url = "https://www.npmjs.com/package/webforai";
+const html = await loadHtml(url);
+
+const markdown = htmlToMarkdown(html, { solveLinks: url });
+
+await fs.writeFile("output.md", markdown);
+```
+
+other examples are in [examples](./examples/simple/src/index.ts)
+
+## Usage
+
+### Main Functions
+
+**`htmlToMarkdown(html: string, options?: HtmlToMarkdownOptions): string`**  
+Convert HTML to Markdown. By default, unnecessary HTML is excluded and processed.
+If `solveLinks` is specified, the relative links in the Mdast will be resolved.
+This function just calls htmlToMdast and mdastToMarkdown in that order internally.
+
+**`htmlToMdast(html: string, options?: HtmlToMdastOptions): Mdast`**  
+This project uses Hast and Mdast as defined by syntax-tree internally.
+This function converts HTML to Mdast, an intermediate representation, which is required when using `mdastSplitter`, etc.
+
+**`mdastToMarkdown(mdast: Mdast | RootContent[], options?: { solveLinks?: string }): string`**  
+Convert Mdast to Markdown. If `solveLinks` is specified, the relative links in the Mdast will be resolved.
+
+### Loader Functions
+
+**`loadHtml(url: string, options?: LoadHtmlOptions): Promise<string>`**  
+Load HTML from the specified URL. This function uses Playwright internally.
+
+## Early Users
+
+### Voice Genius - Explanatory video generation by AI
+
+<img src="https://github.com/inaridiy/webforai/blob/main/images/voice-genius.png" width="300px">
+
+by [@moons14](https://twitter.com/moons_dev)
+
+AI can be used to automatically generate highly accurate commentary videos.
+Supports conversations and presentations using synthesized voice, embedding of images in videos, etc.

package/dist/cjs/extract-hast/index.js

@@ -3,6 +3,10 @@ var __defProp = Object.defineProperty;
 var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
 var __getOwnPropNames = Object.getOwnPropertyNames;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
 var __copyProps = (to, from, except, desc) => {
   if (from && typeof from === "object" || typeof from === "function") {
     for (let key of __getOwnPropNames(from))
@@ -11,12 +15,40 @@ var __copyProps = (to, from, except, desc) => {
   }
   return to;
 };
-var __reExport = (target, mod, secondTarget) => (__copyProps(target, mod, "default"), secondTarget && __copyProps(secondTarget, mod, "default"));
 var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
 var extract_hast_exports = {};
+__export(extract_hast_exports, {
+  DEFAULT_EXTRACT_HAST: () => DEFAULT_EXTRACT_HAST,
+  PRESET_EXTRACT_HAST: () => PRESET_EXTRACT_HAST,
+  extractHast: () => extractHast
+});
 module.exports = __toCommonJS(extract_hast_exports);
-__reExport(extract_hast_exports, require("./strongly"), module.exports);
+var import_readability = require("./readability");
+var import_strongly = require("./strongly");
+const PRESET_EXTRACT_HAST = {
+  strongly: import_strongly.stronglyExtractHast,
+  readability: import_readability.readabilityExtractHast
+};
+const DEFAULT_EXTRACT_HAST = ["readability"];
+const extractHast = (hast, extractors = DEFAULT_EXTRACT_HAST) => {
+  const _extractors = Array.isArray(extractors) ? extractors : [extractors];
+  const extracted = _extractors.reduce((acc, extractor) => {
+    if (extractor === false) {
+      return acc;
+    }
+    if (typeof extractor === "string" && extractor in PRESET_EXTRACT_HAST) {
+      return PRESET_EXTRACT_HAST[extractor](acc);
+    }
+    if (typeof extractor === "function") {
+      return extractor(acc);
+    }
+    throw new Error(`Invalid extractor: ${extractor}`);
+  }, hast) || hast;
+  return extracted;
+};
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
-  ...require("./strongly")
+  DEFAULT_EXTRACT_HAST,
+  PRESET_EXTRACT_HAST,
+  extractHast
 });

package/dist/cjs/extract-hast/readability.js

@@ -31,7 +31,7 @@ const REGEXPS = {
   hidden: /hidden|invisible|fallback-image/i,
   byline: /byline|author|dateline|writtenby|p-author/i,
   unlikelyCandidates: /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|footer|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote|speechify-ignore/i,
-  okMaybeItsACandidate: /and|article|body|column|content|main|shadow|code/i
+  okMaybeItsaCandidate: /and|article|body|column|content|main|shadow|code/i
 };
 const BODY_SELECTORS = ["article", "#article", ".article_body", ".article-body", "#content", ".entry", "main"];
 const PARAGRAPH_TAGS = ["p", "div", "section", "article", "main", "ul", "ol", "li"];
@@ -40,60 +40,79 @@ const BASE_MINIMAL_LENGTH = {
   en: 500
 };
 const tryGetLang = (node) => {
-  if (node.type !== "element")
+  if (node.type !== "element") {
     return;
+  }
   const element = node;
-  if (element.tagName !== "html")
+  if (element.tagName !== "html") {
     return;
+  }
   const langAttr = element.properties.lang || element.properties["xml:lang"];
-  if (langAttr)
+  if (langAttr) {
     return langAttr;
+  }
 };
 const metadataFilter = (node) => !["comment", "doctype"].includes(node.type);
 const universalElementFilter = (node) => {
-  if (node.type !== "element")
+  if (node.type !== "element") {
     return true;
+  }
   const element = node;
-  if (["script", "aside"].includes(element.tagName))
+  if (["script", "aside"].includes(element.tagName)) {
     return false;
-  if (["hidden", "aria-hidden"].some((key) => element.properties[key]))
+  }
+  if (["hidden", "aria-hidden"].some((key) => element.properties[key])) {
     return false;
-  if ((0, import_utils.classnames)(element).some((classname) => REGEXPS.hidden.test(classname)))
+  }
+  if ((0, import_utils.classnames)(element).some((classname) => REGEXPS.hidden.test(classname))) {
     return false;
-  if (element.tagName === "dialog")
+  }
+  if (element.tagName === "dialog") {
     return false;
-  if (element.properties.role === "dialog" && element.properties["aria-modal"])
+  }
+  if (element.properties.role === "dialog" && element.properties["aria-modal"]) {
     return false;
-  if (element.properties.rel === "author" && (0, import_utils.isStrInclude)(element.properties.itemprop, "author"))
+  }
+  if (element.properties.rel === "author" && (0, import_utils.isStrInclude)(element.properties.itemprop, "author")) {
     return false;
-  if (REGEXPS.byline.test((0, import_utils.matchString)(element)))
+  }
+  if (REGEXPS.byline.test((0, import_utils.matchString)(element))) {
     return false;
-  if (element.properties.role && UNLIKELY_ROLES.includes(element.properties.role))
+  }
+  if (element.properties.role && UNLIKELY_ROLES.includes(element.properties.role)) {
     return false;
+  }
   return true;
 };
 const unlikelyElementFilter = (node) => {
-  if (node.type !== "element")
+  if (node.type !== "element") {
     return true;
+  }
   const element = node;
   const match = (0, import_utils.matchString)(element);
-  if (["body", "article", "main", "section", "a"].includes(element.tagName))
+  if (["body", "article", "main", "section", "a"].includes(element.tagName)) {
     return true;
-  if ((0, import_utils.hasAncestors)(element, ["table", "code"], 3))
+  }
+  if ((0, import_utils.hasAncestors)(element, ["table", "code"], 3)) {
     return true;
-  if (REGEXPS.unlikelyCandidates.test(match) && !REGEXPS.okMaybeItsACandidate.test(match))
+  }
+  if (REGEXPS.unlikelyCandidates.test(match) && !REGEXPS.okMaybeItsaCandidate.test(match)) {
     return false;
+  }
   return true;
 };
 const removeEmptyFilter = (node) => {
-  if (node.type !== "element")
+  if (node.type !== "element") {
     return true;
+  }
   const element = node;
-  if (!PARAGRAPH_TAGS.includes(element.tagName))
+  if (!PARAGRAPH_TAGS.includes(element.tagName)) {
     return true;
+  }
   const text = (0, import_hast_util_to_string.toString)(element);
-  if (text.length < 10)
+  if (text.length < 10) {
     return false;
+  }
   return true;
 };
 const readabilityExtractHast = (hast) => {
@@ -101,45 +120,54 @@ const readabilityExtractHast = (hast) => {
   const body = (0, import_hast_util_select.select)("body", hast) ?? hast;
   const proxiedHast = (0, import_unist_util_parents.parents)(body);
   let baseFilterd = (0, import_unist_util_filter.filter)(proxiedHast, (node) => {
-    if (!metadataFilter(node))
+    if (!metadataFilter(node)) {
       return false;
-    if (!universalElementFilter(node))
+    }
+    if (!universalElementFilter(node)) {
       return false;
+    }
     return true;
   });
-  if (!baseFilterd)
+  if (!baseFilterd) {
     return { type: "root", children: [] };
+  }
   const baseText = (0, import_hast_util_to_string.toString)(baseFilterd);
   let minimalLength = lang in BASE_MINIMAL_LENGTH ? BASE_MINIMAL_LENGTH[lang] : 500;
   if (baseText.length > minimalLength) {
     const filterd = (0, import_unist_util_filter.filter)(baseFilterd, (node) => {
-      if (!unlikelyElementFilter(node))
+      if (!unlikelyElementFilter(node)) {
         return false;
+      }
       return true;
     });
-    if (filterd)
+    if (filterd) {
       baseFilterd = filterd;
-  } else
+    }
+  } else {
     minimalLength = Math.max(0, baseText.length - 200);
+  }
   let bodyTree = baseFilterd;
   for (const selector of BODY_SELECTORS) {
     const body2 = { type: "root", children: (0, import_hast_util_select.selectAll)(selector, baseFilterd) };
     const bodyText = (0, import_hast_util_to_string.toString)(body2);
-    if (bodyText.length < 25)
+    if (bodyText.length < 25) {
       continue;
+    }
     const links = (0, import_hast_util_select.selectAll)("a", body2);
     const linkText = links.map((link) => (0, import_hast_util_to_string.toString)(link)).join("");
     const linkDensity = linkText.length / bodyText.length;
-    if (linkDensity > 0.4)
+    if (linkDensity > 0.4) {
       continue;
+    }
     if (bodyText.length > minimalLength) {
       bodyTree = body2;
       break;
     }
   }
   const finalTree = (0, import_unist_util_filter.filter)(bodyTree, (node) => {
-    if (!removeEmptyFilter(node))
+    if (!removeEmptyFilter(node)) {
       return false;
+    }
     return true;
   });
   return finalTree;

package/dist/cjs/extract-hast/strongly.js

@@ -35,14 +35,17 @@ const stronglyExtractHast = (hast) => {
     }
   }
   const removedElements = (0, import_unist_util_filter.filter)(selectedElement, (node) => {
-    if (node.type === "comment")
+    if (node.type === "comment") {
       return false;
-    if (node.type !== "element")
+    }
+    if (node.type !== "element") {
       return true;
+    }
     const element = node;
     const elementName = `${element.tagName} ${element.properties.id} ${element.properties.className}`;
-    if (REMOVE_REGEX.test(elementName))
+    if (REMOVE_REGEX.test(elementName)) {
       return false;
+    }
     return true;
   });
   return removedElements;

package/dist/cjs/extract-hast/utils.js

@@ -26,22 +26,26 @@ __export(utils_exports, {
 module.exports = __toCommonJS(utils_exports);
 const matchString = (element) => `${element.tagName} ${element.properties.id} ${classnames(element).join(" ")} }`;
 const classnames = (element) => {
-  if (Array.isArray(element.properties.className))
+  if (Array.isArray(element.properties.className)) {
     return element.properties.className;
+  }
   return [];
 };
 const isStrInclude = (value, match) => {
-  if (typeof value === "string")
+  if (typeof value === "string") {
     return value.includes(match);
+  }
   return false;
 };
 const hasAncestors = (element, tagNames, depth = 3) => {
   let parent = element.parent;
   for (let i = 0; i < depth; i++) {
-    if (!parent || parent.type !== "element")
+    if (!parent || parent.type !== "element") {
       return false;
-    if (tagNames.includes(parent.tagName))
+    }
+    if (tagNames.includes(parent.tagName)) {
       return true;
+    }
     parent = parent.parent;
   }
   return false;

package/dist/cjs/html-to-markdown.js

@@ -23,9 +23,10 @@ __export(html_to_markdown_exports, {
 module.exports = __toCommonJS(html_to_markdown_exports);
 var import_html_to_mdast = require("./html-to-mdast");
 var import_mdast_to_markdown = require("./mdast-to-markdown");
-const htmlToMarkdown = (html, options) => {
-  const mdast = (0, import_html_to_mdast.htmlToMdast)(html, options);
-  const markdown = (0, import_mdast_to_markdown.mdastToMarkdown)(mdast, options);
+const htmlToMarkdown = (htmlOrHast, options) => {
+  const { baseUrl, formatting: toMarkdownOptions, ...toMdastOptions } = options || {};
+  const mdast = (0, import_html_to_mdast.htmlToMdast)(htmlOrHast, toMdastOptions);
+  const markdown = (0, import_mdast_to_markdown.mdastToMarkdown)(mdast, { baseUrl, ...toMarkdownOptions });
   return markdown;
 };
 // Annotate the CommonJS export names for ESM import in node:

package/dist/cjs/html-to-mdast.js

@@ -24,39 +24,26 @@ module.exports = __toCommonJS(html_to_mdast_exports);
 var import_hast_util_from_html = require("hast-util-from-html");
 var import_hast_util_to_mdast = require("hast-util-to-mdast");
 var import_extract_hast = require("./extract-hast");
-var import_readability = require("./extract-hast/readability");
 var import_custom_a_handler = require("./mdast-handlers/custom-a-handler");
+var import_custom_code_handler = require("./mdast-handlers/custom-code-handler");
 var import_custom_div_handler = require("./mdast-handlers/custom-div-handler");
 var import_custom_img_handler = require("./mdast-handlers/custom-img-handler");
 var import_custom_table_handler = require("./mdast-handlers/custom-table-handler");
+var import_empty_handler = require("./mdast-handlers/empty-handler");
 var import_math_handler = require("./mdast-handlers/math-handler");
-const PRESET_EXTRACT_HAST = {
-  strongly: import_extract_hast.stronglyExtractHast,
-  readability: import_readability.readabilityExtractHast
-};
-const DEFAULT_EXTRACT_HAST = ["readability"];
-const htmlToMdast = (html, options) => {
-  const { extractHast = DEFAULT_EXTRACT_HAST } = options || {};
-  const _extractHast = Array.isArray(extractHast) ? extractHast : [extractHast];
-  const hast = (0, import_hast_util_from_html.fromHtml)(html, { fragment: true });
-  const extractedHast = _extractHast.reduce((acc, extractHast2) => {
-    if (extractHast2 === false)
-      return acc;
-    if (typeof extractHast2 === "string" && extractHast2 in PRESET_EXTRACT_HAST)
-      return PRESET_EXTRACT_HAST[extractHast2](acc);
-    if (typeof extractHast2 === "function")
-      return extractHast2(acc);
-    throw new Error(`Invalid extractHast: ${extractHast2}`);
-  }, hast) || hast;
+const htmlToMdast = (htmlOrHast, options) => {
+  const { extractors } = options || {};
+  const hast = typeof htmlOrHast === "string" ? (0, import_hast_util_from_html.fromHtml)(htmlOrHast, { fragment: true }) : htmlOrHast;
+  const extractedHast = (0, import_extract_hast.extractHast)(hast, extractors);
   const mdast = (0, import_hast_util_to_mdast.toMdast)(extractedHast, {
     handlers: {
       math: import_math_handler.mathHandler,
       div: import_custom_div_handler.customDivHandler,
+      pre: import_custom_code_handler.customCodeHandler,
       a: (0, import_custom_a_handler.customAHandler)({ asText: options?.linkAsText }),
       img: (0, import_custom_img_handler.customImgHandler)({ hideImage: options?.hideImage }),
       table: (0, import_custom_table_handler.customTableHandler)({ asText: options?.tableAsText }),
-      br: () => {
-      }
+      br: import_empty_handler.emptyHandler
     }
   });
   return mdast;

package/dist/cjs/index.js

@@ -3,6 +3,10 @@ var __defProp = Object.defineProperty;
 var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
 var __getOwnPropNames = Object.getOwnPropertyNames;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
 var __copyProps = (to, from, except, desc) => {
   if (from && typeof from === "object" || typeof from === "function") {
     for (let key of __getOwnPropNames(from))
@@ -11,18 +15,23 @@ var __copyProps = (to, from, except, desc) => {
   }
   return to;
 };
-var __reExport = (target, mod, secondTarget) => (__copyProps(target, mod, "default"), secondTarget && __copyProps(secondTarget, mod, "default"));
 var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
 var src_exports = {};
+__export(src_exports, {
+  htmlToMarkdown: () => import_html_to_markdown.htmlToMarkdown,
+  htmlToMdast: () => import_html_to_mdast.htmlToMdast,
+  mdastSplitter: () => import_md_splitter.mdastSplitter,
+  mdastToMarkdown: () => import_mdast_to_markdown.mdastToMarkdown
+});
 module.exports = __toCommonJS(src_exports);
-__reExport(src_exports, require("./html-to-markdown"), module.exports);
-__reExport(src_exports, require("./md-splitter"), module.exports);
-__reExport(src_exports, require("./html-to-mdast"), module.exports);
-__reExport(src_exports, require("./mdast-to-markdown"), module.exports);
+var import_html_to_markdown = require("./html-to-markdown");
+var import_md_splitter = require("./md-splitter");
+var import_html_to_mdast = require("./html-to-mdast");
+var import_mdast_to_markdown = require("./mdast-to-markdown");
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
-  ...require("./html-to-markdown"),
-  ...require("./md-splitter"),
-  ...require("./html-to-mdast"),
-  ...require("./mdast-to-markdown")
+  htmlToMarkdown,
+  htmlToMdast,
+  mdastSplitter,
+  mdastToMarkdown
 });

package/dist/cjs/link-replacer.js

@@ -24,8 +24,9 @@ module.exports = __toCommonJS(link_replacer_exports);
 const linkReplacer = (markdown, link) => {
   const regex = /(!?\[.*?\]\()(.+?)(\))/g;
   return markdown.replace(regex, (match, pre, thisUrl, post) => {
-    if (thisUrl.startsWith("http") || thisUrl.startsWith("#"))
+    if (thisUrl.startsWith("http") || thisUrl.startsWith("#")) {
       return match;
+    }
     return `${pre}${new URL(thisUrl, link).href}${post}`;
   });
 };

package/dist/cjs/loaders/playwright.js

@@ -1,9 +1,7 @@
 "use strict";
-var __create = Object.create;
 var __defProp = Object.defineProperty;
 var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
 var __getOwnPropNames = Object.getOwnPropertyNames;
-var __getProtoOf = Object.getPrototypeOf;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
 var __export = (target, all) => {
   for (var name in all)
@@ -17,37 +15,31 @@ var __copyProps = (to, from, except, desc) => {
   }
   return to;
 };
-var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
-  // If the importer is in node compatibility mode or this is not an ESM
-  // file that has been converted to a CommonJS file using a Babel-
-  // compatible transform (i.e. "__esModule" has not been set), then set
-  // "default" to the CommonJS "module.exports" for node compatibility.
-  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
-  mod
-));
 var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
 var playwright_exports = {};
 __export(playwright_exports, {
   loadHtml: () => loadHtml
 });
 module.exports = __toCommonJS(playwright_exports);
-var playwright = __toESM(require("playwright"), 1);
+var import_playwright = require("playwright");
 const sleep = (ms) => new Promise((resolve) => setTimeout(resolve, ms));
 const loadHtml = async (url, context) => {
   let _browser = null;
   let _context;
-  if (!context) {
-    _browser = await playwright.chromium.launch({ headless: true });
-    _context = await _browser.newContext();
-  } else
+  if (context) {
     _context = context;
+  } else {
+    _browser = await import_playwright.chromium.launch({ headless: true });
+    _context = await _browser.newContext();
+  }
   const page = await _context.newPage();
   await page.goto(url);
   await Promise.race([page.waitForLoadState("networkidle"), sleep(1e4)]);
   const html = await page.content();
   await page.close();
-  if (_browser)
+  if (_browser) {
     await _browser.close();
+  }
   return html;
 };
 // Annotate the CommonJS export names for ESM import in node:

package/dist/cjs/md-splitter.js

@@ -26,14 +26,16 @@ var import_common = require("./utils/common");
 var import_mdast_utils = require("./utils/mdast-utils");
 const PRIORITY_SPLITTERS = ["h1", "h2", "h3", "h4", "h5", "h6", "list", "table", "code"];
 const getSplitterGenerator = function* () {
-  for (const splitter of PRIORITY_SPLITTERS)
+  for (const splitter of PRIORITY_SPLITTERS) {
     yield splitter;
+  }
 };
 const _mdastSplitter = async (contents, checker, splitterGenerator) => {
   const splitter = splitterGenerator.next().value;
   const markdown = (0, import_mdast_to_markdown.mdastToMarkdown)((0, import_mdast_utils.warpRoot)(contents));
-  if (await checker(markdown) || contents.length === 1)
+  if (await checker(markdown) || contents.length === 1) {
     return [contents];
+  }
   const chunked = splitter ? contents.reduce((acc, content) => {
     if ((0, import_mdast_utils.internalType)(content) === splitter || acc.length === 0) {
       acc.push([content]);
@@ -45,7 +47,7 @@ const _mdastSplitter = async (contents, checker, splitterGenerator) => {
   const splitting = chunked.map((chunk2) => _mdastSplitter(chunk2, checker, splitterGenerator));
   return Promise.all(splitting).then((chunks) => chunks.flat());
 };
-const mdastSplitter = async (mdast, checker, options) => {
+const mdastSplitter = (mdast, checker, _options) => {
   return _mdastSplitter((0, import_mdast_utils.unwarpRoot)(mdast), checker, getSplitterGenerator());
 };
 // Annotate the CommonJS export names for ESM import in node: