Extracted html-to-plaintext shared lib into package

refs https://github.com/TryGhost/Toolbox/issues/363

- this shared library is standalone, and it used in various places of
  Ghost core, so we can pull it out to keep it easier to reason about
- we also use the `html-to-text` dependency in another package but it's
  outdated and could now switch to this new package

ghost/core/core/server/api/endpoints/utils/serializers/output/utils/post-gating.js

@@ -1,5 +1,5 @@
 const membersService = require('../../../../../../services/members');
-const htmlToPlaintext = require('../../../../../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 
 // @TODO: reconsider the location of this - it's part of members and adds a property to the API
 const forPost = (attrs, frame) => {

ghost/core/core/server/data/migrations/versions/4.0/23-regenerate-posts-html.js

@@ -1,7 +1,7 @@
 const logging = require('@tryghost/logging');
 const {createIrreversibleMigration} = require('../../utils');
 const mobiledocLib = require('../../../../lib/mobiledoc');
-const htmlToPlaintext = require('../../../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 
 module.exports = createIrreversibleMigration(async (knex) => {
     logging.info('Starting re-generation of posts html.');

ghost/core/core/server/data/migrations/versions/4.9/05-fix-missed-mobiledoc-url-transforms.js

@@ -1,6 +1,6 @@
 const logging = require('@tryghost/logging');
 const urlUtils = require('../../../../../shared/url-utils');
-const htmlToPlaintext = require('../../../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 const mobiledocLib = require('../../../../lib/mobiledoc');
 const {createTransactionalMigration} = require('../../utils');
 

ghost/core/core/server/data/migrations/versions/5.0/2022-05-21-00-00-regenerate-posts-html.js

@@ -1,7 +1,7 @@
 const logging = require('@tryghost/logging');
 const {createIrreversibleMigration} = require('../../utils');
 const mobiledocLib = require('../../../../lib/mobiledoc');
-const htmlToPlaintext = require('../../../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 
 module.exports = createIrreversibleMigration(async (knex) => {
     logging.info(`Starting regeneration of posts HTML`);

ghost/core/core/server/models/post.js

@@ -7,7 +7,7 @@ const {sequence} = require('@tryghost/promise');
 const tpl = require('@tryghost/tpl');
 const errors = require('@tryghost/errors');
 const nql = require('@tryghost/nql');
-const htmlToPlaintext = require('../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 const ghostBookshelf = require('./base');
 const config = require('../../shared/config');
 const settingsCache = require('../../shared/settings-cache');

ghost/core/core/server/services/comments/emails.js

@@ -1,7 +1,7 @@
 const {promises: fs} = require('fs');
 const path = require('path');
 const moment = require('moment');
-const htmlToPlaintext = require('../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 
 class CommentsServiceEmails {
     constructor({config, logging, models, mailer, settingsCache, urlService, urlUtils}) {

ghost/core/core/server/services/mega/post-email-serializer.js

@@ -8,7 +8,7 @@ const api = require('../../api').endpoints;
 const apiShared = require('../../api').shared;
 const {URL} = require('url');
 const mobiledocLib = require('../../lib/mobiledoc');
-const htmlToPlaintext = require('../../../shared/html-to-plaintext');
+const htmlToPlaintext = require('@tryghost/html-to-plaintext');
 const membersService = require('../members');
 const {isUnsplashImage, isLocalContentImage} = require('@tryghost/kg-default-cards/lib/utils');
 const {textColorForBackgroundColor, darkenToContrastThreshold} = require('@tryghost/color-utils');

ghost/core/package.json

@@ -73,6 +73,7 @@
     "@tryghost/errors": "1.2.14",
     "@tryghost/express-dynamic-redirects": "0.0.0",
     "@tryghost/helpers": "1.1.71",
+    "@tryghost/html-to-plaintext": "0.0.0",
     "@tryghost/image-transform": "1.2.1",
     "@tryghost/job-manager": "0.0.0",
     "@tryghost/kg-card-factory": "3.1.3",
@@ -145,7 +146,6 @@
     "glob": "8.0.3",
     "got": "9.6.0",
     "gscan": "4.34.0",
-    "html-to-text": "8.2.0",
     "human-number": "2.0.0",
     "image-size": "1.0.2",
     "intl": "1.2.5",

ghost/html-to-plaintext/.eslintrc.js

@@ -0,0 +1,6 @@
+module.exports = {
+    plugins: ['ghost'],
+    extends: [
+        'plugin:ghost/node'
+    ]
+};

ghost/html-to-plaintext/README.md

@@ -0,0 +1,21 @@
+# Html To Plaintext
+
+
+## Usage
+
+
+## Develop
+
+This is a monorepo package.
+
+Follow the instructions for the top-level repo.
+1. `git clone` this repo & `cd` into it as usual
+2. Run `yarn` to install top-level dependencies.
+
+
+
+## Test
+
+- `yarn lint` run just eslint
+- `yarn test` run lint and tests
+

ghost/html-to-plaintext/index.js

@@ -0,0 +1 @@
+module.exports = require('./lib/html-to-plaintext');

ghost/html-to-plaintext/package.json

@@ -0,0 +1,23 @@
+{
+  "name": "@tryghost/html-to-plaintext",
+  "version": "0.0.0",
+  "repository": "https://github.com/TryGhost/Ghost/tree/main/packages/html-to-plaintext",
+  "author": "Ghost Foundation",
+  "private": true,
+  "main": "index.js",
+  "scripts": {
+    "dev": "echo \"Implement me!\"",
+    "test": "NODE_ENV=testing c8 --all --check-coverage --reporter text --reporter cobertura mocha './test/**/*.test.js'",
+    "lint:code": "eslint *.js lib/ --ext .js --cache",
+    "lint": "yarn lint:code && yarn lint:test",
+    "lint:test": "eslint -c test/.eslintrc.js test/ --ext .js --cache"
+  },
+  "devDependencies": {
+    "c8": "7.12.0",
+    "mocha": "10.0.0"
+  },
+  "dependencies": {
+    "html-to-text": "8.2.1",
+    "lodash": "4.17.21"
+  }
+}

ghost/html-to-plaintext/test/.eslintrc.js

@@ -0,0 +1,6 @@
+module.exports = {
+    plugins: ['ghost'],
+    extends: [
+        'plugin:ghost/test'
+    ]
+};

ghost/html-to-plaintext/test/html-to-plaintext.test.js

@@ -1,5 +1,5 @@
 const assert = require('assert');
-const htmlToPlaintext = require('../../../core/shared/html-to-plaintext');
+const htmlToPlaintext = require('../');
 
 describe('Html to Plaintext', function () {
     function getEmailandExcert(input) {
@@ -74,7 +74,7 @@ describe('Html to Plaintext', function () {
     describe('Special cases', function () {
         it('Instagram (blockquotes)', function () {
             // This is an instagram embed, but with all the style attributes & svg content removed for brevity
-            const html = '<p>Some text in a paragraph.</p><!--kg-card-begin: html--><blockquote class=\"instagram-media\" data-instgrm-captioned data-instgrm-permalink=\"https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading\" data-instgrm-version=\"14\"><div> <a href=\"https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading\" target=\"_blank\"><div><div></div><div><div></div><div></div></div></div><div></div><div><svg width=\"50px\" height=\"50px\" viewBox=\"0 0 60 60\" version=\"1.1\" xmlns=\"https://www.w3.org/2000/svg\" xmlns:xlink=\"https://www.w3.org/1999/xlink\"><!-- svg stuff --></svg></div><div><div>View this post on Instagram</div></div><div></div><div><div><div></div><div></div><div></div></div><div><div></div><div><div></div><div></div><div></div></div></div><div><div></div><div></div></div></a><p><a href=\"https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading\" target=\"_blank\">A post shared by Some Dude (@somedude)</a></p></div></blockquote><script async src=\"//www.instagram.com/embed.js\"></script><!--kg-card-end: html-->';
+            const html = '<p>Some text in a paragraph.</p><!--kg-card-begin: html--><blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14"><div> <a href="https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading" target="_blank"><div><div></div><div><div></div><div></div></div></div><div></div><div><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><!-- svg stuff --></svg></div><div><div>View this post on Instagram</div></div><div></div><div><div><div></div><div></div><div></div></div><div><div></div><div><div></div><div></div><div></div></div></div><div><div></div><div></div></div></a><p><a href="https://www.instagram.com/p/AbC123dEf/?utm_source=ig_embed&amp;utm_campaign=loading" target="_blank">A post shared by Some Dude (@somedude)</a></p></div></blockquote><script async src="//www.instagram.com/embed.js"></script><!--kg-card-end: html-->';
             const expected = 'Some text in a paragraph.\n\nView this post on Instagram\n\nA post shared by Some Dude (@somedude)';
             const {excerpt} = getEmailandExcert(html);
             assert.equal(excerpt, expected);

yarn.lock

@@ -13273,10 +13273,10 @@ html-to-text@5.1.1:
     lodash "^4.17.11"
     minimist "^1.2.0"
 
-html-to-text@8.2.0:
-  version "8.2.0"
-  resolved "https://registry.yarnpkg.com/html-to-text/-/html-to-text-8.2.0.tgz#8b35e280ba7fc27710b7aa76d4500aab30731924"
-  integrity sha512-CLXExYn1b++Lgri+ZyVvbUEFwzkLZppjjZOwB7X1qv2jIi8MrMEvxWX5KQ7zATAzTvcqgmtO00M2kCRMtEdOKQ==
+html-to-text@8.2.1:
+  version "8.2.1"
+  resolved "https://registry.yarnpkg.com/html-to-text/-/html-to-text-8.2.1.tgz#4a75b8a1b646149bd71c50527adb568990bf459b"
+  integrity sha512-aN/3JvAk8qFsWVeE9InWAWueLXrbkoVZy0TkzaGhoRBC2gCFEeRLDDJN3/ijIGHohy6H+SZzUQWN/hcYtaPK8w==
   dependencies:
     "@selderee/plugin-htmlparser2" "^0.6.0"
     deepmerge "^4.2.2"