page-markdown 0.0.0-stage → 0.1.3

package/README.md

@@ -1,3 +1,133 @@
-# Temporary Holding Version
-
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+# page-markdown
+
+Faithful page-to-Markdown for humans and agents. Give it a web page's DOM and
+it returns clean Markdown plus metadata. It is written for browsers, for
+example an extension's content script, and runs in Node with a DOM library.
+So far it is tested only in Node (see [Known limits](#known-limits-v01)). It
+was built for WATT3D's browser extensions.
+
+```
+live Document
+  → sanitize      inert clone; open shadow DOM inlined within limits; scripts, styles, ads removed
+  → standardize   <pre> → fenced code with language; heading wrappers unwrapped; empty and
+                  javascript: links removed; absolute links and images; lazy images resolved
+  → extract       Mozilla Readability on a copy; full-page fallback when it finds too little;
+                  a dropped lead paragraph restored; a clean title heading
+  → convert       Turndown + GitHub-flavoured tables, strikethrough and task lists; never raw HTML
+  → clean         fence-safe; keeps short lines and <br> hard breaks; never cuts text
+  → hidden text   opt-in (removeHiddenText): tag-character text, variation-selector runs and
+                  invisible operators removed, fenced code included; counted in omissions
+  → { markdown, metadata, extraction, omissions, warnings, stats }
+```
+
+The live page is only read, never modified.
+
+## Install
+
+```sh
+npm install page-markdown
+```
+
+## Usage
+
+```js
+import { pageToMarkdown } from "page-markdown";
+
+// In a browser (e.g. an extension content script)
+const result = pageToMarkdown(document);
+result.markdown;            // "# Title\n\n…"
+result.metadata;            // { url, canonicalUrl, title, author, published, siteName, lang, … }
+result.extraction.method;   // "readability" | "full_page"
+
+// In Node, with any DOM implementation (linkedom shown)
+import { parseHTML } from "linkedom";
+const { document: doc } = parseHTML(html);
+pageToMarkdown(doc, { url: "https://example.com/article" });
+```
+
+### Options
+
+| Option | Default | Meaning |
+|---|---|---|
+| `url` | the document's URL | Base for absolute links and images |
+| `extract` | `"readable"` | `"readable"` (Readability, full-page fallback), `"full"`, or a function `(docCopy) => { html, method }` |
+| `minExtractChars` | `100` | Below this, readable extraction falls back to the full page |
+| `includeFullPage` | `false` | Also return `fullPageMarkdown` |
+| `includeTitle` | `true` | Start readable output with `# <headline>`: the page's H1, else its title without the site name |
+| `recoverLead` | `true` | Restore a lead paragraph the extractor dropped, when it matches the meta description |
+| `pageFacts` | `false` | Append `## Page facts`: short label/value pairs outside the article (a sidebar's version or license, spec rows, infobox rows) that the extractor dropped. `extraction.pageFacts` counts them |
+| `removeHiddenText` | `false` | Remove text hidden from people but read by models: runs of tag characters, variation selectors and invisible operators, found by [text-sanctifier](https://github.com/iWhatty/text-sanctifier)'s `findHiddenRuns`. Applies to `markdown` (fenced code included), `fullPageMarkdown` and `metadata`. The England, Scotland and Wales flags and a lone emoji or text presentation selector are kept. `omissions` gets one entry per kind (`hidden_tag`, `hidden_variation_selector`, `hidden_invisible_operator`) with `count` runs and `chars` code points removed from `markdown` |
+| `mode` | `"full"` | `"no_links"` keeps link text; `"text_only"` also drops structure. Fenced code is never changed |
+| `sanitize` | see `DEFAULT_SANITIZE_OPTIONS` | `stripAds`, `extraStripSelectors` (e.g. `["[data-app-overlay]"]`), shadow limits |
+| `readability` | `{}` | Passed to Readability |
+
+The stages are also exported for advanced use: `sanitizeToInertDocument`,
+`standardizeDocument`, `extractContent`, `htmlToMarkdown`, `cleanMarkdown`,
+`applyMode`, `collectMetadata`, `collectPageFacts` and `removeHiddenText`.
+
+### Recipes
+
+```js
+// Keep both views: the readable article and the whole page.
+const { markdown, fullPageMarkdown } = pageToMarkdown(document, { includeFullPage: true });
+
+// For agents answering questions: keep facts from asides (version, price, specs).
+pageToMarkdown(document, { pageFacts: true });
+
+// Drop your own UI before capture.
+pageToMarkdown(document, { sanitize: { extraStripSelectors: ["#my-extension-panel"] } });
+
+// Plain text for prompts; code blocks stay intact.
+pageToMarkdown(document, { mode: "text_only" });
+
+// Markdown bound for a model: drop hidden instructions, and see what was dropped.
+const { markdown: safe, omissions } = pageToMarkdown(document, { removeHiddenText: true });
+```
+
+## Quality
+
+`npm test` runs the contract suite. It covers:
+- golden outputs for 26 fixtures;
+- regressions for known converter bugs, including dropped lead paragraphs,
+  raw HTML tables, flattened code in tables, site-suffixed titles and
+  unescaped table pipes;
+- modes, metadata, JSON-LD and the full-page fallback;
+- the shadow DOM limits and their omission notice;
+- leaving the live page unmodified.
+
+`npm run bench` scores the package against a naive baseline (Turndown over the
+page body). It runs 15 fixture checks and 17 probes on five real pages, which
+`node bench/fetch-pages.mjs` fetches first. See
+[bench/RESULTS.md](bench/RESULTS.md): currently **32/32 against 11/32**.
+
+Browser bundle: about 65 KB minified, 23 KB gzip (`npm run size`, ceiling 66 KB
+minified). Readability is most of it.
+
+`npm run ci` runs the contract suite and the size check, and must exit 0
+before a commit. It runs locally; the repo deliberately has no cloud CI.
+
+## Known limits (v0.1)
+
+- **Node only so far.** Tested in Node with linkedom, not yet in a browser. The
+  open shadow DOM path is exercised only with a stand-in host in tests.
+- **Some legacy markup loses paragraph breaks.** Readability can drop runs of
+  `<br>` between inline elements in old HTML. The text survives; a paragraph
+  break may not.
+- **Hidden content stays.** The pipeline reads the static DOM, so elements
+  hidden only by CSS remain unless extraction drops them.
+- **`removeHiddenText` covers hidden runs only.** Zero-width spaces, bidi
+  controls and look-alike spaces pass through. It also removes runs that are
+  legitimate in some scripts: ideographic variation selectors in CJK names and
+  the Mongolian free variation selectors.
+- **Iframes and closed shadow roots are not captured.**
+
+## Licence
+
+page-markdown is under the WATT3D Source License: AGPL-3.0 with the Additional
+Terms in [ADDITIONAL_TERMS.md](ADDITIONAL_TERMS.md) (see [LICENSE](LICENSE)).
+[robots.txt](robots.txt) states the AI-crawler policy.
+
+It bundles text-sanctifier's run finder (same licence) and Mozilla Readability
+(Apache-2.0) and Turndown (MIT), whose licences are in
+[THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md). Those notices must accompany
+any distribution.

package/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,264 @@
+# Third-party notices
+
+page-markdown's own code is under the WATT3D Source License (AGPL-3.0 with the
+Additional Terms in ADDITIONAL_TERMS.md; see LICENSE). It bundles the
+following third-party software, which remains under its own licence terms below.
+These notices must accompany any distribution of page-markdown or a bundle built from it.
+
+It also bundles part of text-sanctifier (https://github.com/iWhatty/text-sanctifier),
+which is WATT3D's own and under the same WATT3D Source License, so it needs no
+separate notice.
+
+## @mozilla/readability 0.6.0 — Apache License 2.0
+
+Source: https://github.com/mozilla/readability
+
+```
+Copyright (c) 2010 Arc90 Inc
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+   http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+```
+
+## turndown 7.2.4 — MIT
+
+Source: https://github.com/mixmark-io/turndown
+
+```
+MIT License
+
+Copyright (c) 2017 Dom Christie
+
+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.
+```
+
+## Apache License, Version 2.0 (full text, for @mozilla/readability)
+
+```
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+```

package/package.json

@@ -1,6 +1,56 @@
 {
   "name": "page-markdown",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.3",
+  "description": "Faithful page-to-Markdown for humans and agents: sanitize, extract the readable article, convert with GFM, and clean without losing content.",
+  "type": "module",
+  "exports": {
+    ".": "./src/index.js"
+  },
+  "files": [
+    "src",
+    "LICENSE",
+    "ADDITIONAL_TERMS.md",
+    "THIRD_PARTY_NOTICES.md",
+    "README.md",
+    "CHANGELOG.md",
+    "robots.txt"
+  ],
+  "sideEffects": false,
+  "packageManager": "pnpm@10.33.0",
+  "engines": {
+    "node": ">=20"
+  },
+  "scripts": {
+    "test": "node --test \"test/**/*.test.mjs\"",
+    "size": "node bench/size.mjs",
+    "ci": "npm test && npm run size",
+    "bench": "node bench/compare.mjs"
+  },
+  "keywords": [
+    "markdown",
+    "readability",
+    "html-to-markdown",
+    "reader-mode",
+    "web-clipper",
+    "browser-extension"
+  ],
+  "author": "WATT3D <WATT3D@protonmail.com>",
+  "license": "SEE LICENSE IN LICENSE",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/iWhatty/page-markdown.git"
+  },
+  "homepage": "https://github.com/iWhatty/page-markdown#readme",
+  "bugs": {
+    "url": "https://github.com/iWhatty/page-markdown/issues"
+  },
+  "dependencies": {
+    "@mozilla/readability": "0.6.0",
+    "text-sanctifier": "1.3.3",
+    "turndown": "7.2.4"
+  },
+  "devDependencies": {
+    "esbuild": "0.27.0",
+    "linkedom": "0.18.12"
+  }
+}

package/robots.txt

@@ -0,0 +1,79 @@
+# WATT3D — AI scraping policy
+#
+# This file enumerates known AI / LLM training and inference crawlers
+# that the WATT3D AI Training Rider does not consent to. See
+# ./ADDITIONAL_TERMS.md for the legal scope and definitions.
+#
+# Honoring robots.txt is voluntary. The rider applies whether or not
+# a bot respects this file. The enumeration is non-exhaustive — bots
+# not listed here are still bound by the rider if they perform
+# Training Use as defined in ADDITIONAL_TERMS.md §1.
+
+User-agent: GPTBot
+Disallow: /
+
+User-agent: ChatGPT-User
+Disallow: /
+
+User-agent: OAI-SearchBot
+Disallow: /
+
+User-agent: anthropic-ai
+Disallow: /
+
+User-agent: ClaudeBot
+Disallow: /
+
+User-agent: Claude-Web
+Disallow: /
+
+User-agent: Claude-SearchBot
+Disallow: /
+
+User-agent: Google-Extended
+Disallow: /
+
+User-agent: Applebot-Extended
+Disallow: /
+
+User-agent: Meta-ExternalAgent
+Disallow: /
+
+User-agent: Meta-ExternalFetcher
+Disallow: /
+
+User-agent: FacebookBot
+Disallow: /
+
+User-agent: CCBot
+Disallow: /
+
+User-agent: PerplexityBot
+Disallow: /
+
+User-agent: Perplexity-User
+Disallow: /
+
+User-agent: cohere-ai
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+User-agent: Amazonbot
+Disallow: /
+
+User-agent: Omgilibot
+Disallow: /
+
+User-agent: AI2Bot
+Disallow: /
+
+User-agent: Diffbot
+Disallow: /
+
+# Everyone else: full access. Search engines and human-driven crawlers
+# remain welcome.
+
+User-agent: *
+Allow: /

package/src/clean.js

@@ -0,0 +1,111 @@
+// Stage 5: tidy Markdown without losing content. Code fences are never
+// touched. Short lines (table cells, list items, numbers) are kept, and no
+// regex spans lines, so text is never cut.
+
+/**
+ * Applies `transform` to the prose between fenced code blocks only.
+ * A shorter embedded fence does not close a block; an unterminated fence
+ * keeps the rest verbatim.
+ * @param {string} markdown
+ * @param {(prose: string) => string} transform
+ */
+export function mapOutsideFences(markdown, transform) {
+  const blocks = [];
+  let lines = [];
+  let fence = null;
+  const flush = (isCode) => {
+    if (!lines.length) return;
+    const text = lines.join("\n");
+    blocks.push(isCode ? text : transform(text));
+    lines = [];
+  };
+  for (const line of String(markdown).split("\n")) {
+    const match = line.match(/^ {0,3}(`{3,}|~{3,})(.*)$/);
+    if (!fence && match && !(match[1][0] === "`" && match[2].includes("`"))) {
+      flush(false);
+      fence = match[1];
+      lines.push(line);
+    } else if (fence && match && match[1][0] === fence[0] && match[1].length >= fence.length && !match[2].trim()) {
+      lines.push(line);
+      flush(true);
+      fence = null;
+    } else {
+      lines.push(line);
+    }
+  }
+  flush(Boolean(fence));
+  return blocks.join("\n");
+}
+
+// A single prose line holding a large, valid JSON document (embedded app
+// state). Bounded to one line and verified by parsing, so text is never cut.
+const MIN_JSON_LINE = 2000;
+
+function isJsonLine(line) {
+  const s = line.trim();
+  if (s.length < MIN_JSON_LINE || !/^[[{]/.test(s)) return false;
+  try {
+    JSON.parse(s);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * @param {string} markdown
+ * @returns {{ markdown: string, removedJsonLines: number }}
+ */
+export function cleanMarkdown(markdown) {
+  let removedJsonLines = 0;
+  const cleaned = mapOutsideFences(markdown, (prose) => prose
+    .split("\n")
+    .filter((line) => {
+      if (isJsonLine(line)) {
+        removedJsonLines += 1;
+        return false;
+      }
+      return true;
+    })
+    // Trim trailing whitespace, but keep a two-space hard break (<br>) on a
+    // line with text; whitespace-only lines become empty.
+    .map((line) => (/\S {2,}$/.test(line) ? line.replace(/[ \t]+$/, "  ") : line.replace(/[ \t]+$/, "")))
+    .join("\n")
+    .replace(/\n{3,}/g, "\n\n")
+    // Blocks are joined with "\n": one blank line at most beside a fence.
+    .replace(/^\n+/, "\n")
+    .replace(/\n+$/, "\n"));
+  return { markdown: cleaned.replace(/^\n+|\n+$/g, ""), removedJsonLines };
+}
+
+// Link text may hold escaped brackets and whole images: [![alt](img)](href)
+// keeps the image, not "![alt" pointing at href.
+const LINK_TARGET = String.raw`\((?:[^()\s]|\([^()]*\))+(?:\s+"[^"]*")?\)`;
+const INLINE_LINK = new RegExp(String.raw`(!?)\[((?:\\.|!\[[^\]]*\]${LINK_TARGET}|[^\[\]\\])*)\]${LINK_TARGET}`, "g");
+const stripInlineLinks = (md) => md.replace(INLINE_LINK, (all, bang, text) => (bang ? all : text));
+const dropReferenceDefs = (md) => md.replace(/^\s{0,3}\[[^\]]+]:\s+\S+.*$/gm, "");
+const stripStructure = (md) => md
+  .replace(/^\s{0,3}#{1,6}\s+/gm, "")
+  .replace(/^\s*[-+*]\s+/gm, "")
+  .replace(/^\s*\d+\.\s+/gm, "")
+  .replace(/^\s{0,3}>\s?/gm, "")
+  .replace(/^\s*([-_*])\s*(?:\1\s*){2,}$/gm, "");
+const stripEmphasis = (md) => md.replace(/(\*\*|__)(.+?)\1/g, "$2").replace(/(?<![\w*])([*_])(?!\s)(.+?)(?<!\s)\1(?![\w*])/g, "$2");
+const stripImages = (md) => md.replace(/!\[([^\]]*)\]\([^)]*\)/g, "$1");
+
+/**
+ * Output modes. "no_links" keeps link text. "text_only" also drops headings,
+ * list markers, emphasis and images. Both leave fenced code verbatim.
+ * @param {string} markdown
+ * @param {"full"|"no_links"|"text_only"} mode
+ */
+export function applyMode(markdown, mode = "full") {
+  if (mode === "no_links") return mapOutsideFences(markdown, stripInlineLinks);
+  if (mode === "text_only") {
+    // Blank-line collapsing stays inside the prose transform: code keeps its own.
+    return mapOutsideFences(markdown, (prose) => stripEmphasis(stripStructure(stripImages(dropReferenceDefs(stripInlineLinks(prose)))))
+      .replace(/\n{3,}/g, "\n\n"))
+      .trim();
+  }
+  return markdown;
+}