remove LFS from codebase (#33777)

.devcontainer/devcontainer.json

@@ -17,7 +17,6 @@
 
 	// Install features. Type 'feature' in the VS Code command palette for a full list.
 	"features": {
-		"git-lfs": "latest",
 		"sshd": "latest"
 	 },
 
@@ -42,7 +41,7 @@
 	},
 
 	// Use 'postCreateCommand' to run commands after the container is created.
-	"postCreateCommand": "git lfs pull && npm ci",
+	"postCreateCommand": "npm ci",
 
 	// Comment out connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
 	"remoteUser": "node"

.github/actions-scripts/enterprise-server-issue-templates/release-issue.md

@@ -101,7 +101,7 @@ This file should be automatically updated, but you can also run `script/update-e
 
 ### 🚢 🛳️ 🚢 Shipping the release branch
 
-- [ ] The megabranch creator should push the search index LFS objects for the public `github/docs` repo. The LFS objects were already pushed for the internal repo after the `sync-english-index-for-<PLAN@RELEASE>` was added to the megabranch. To push the LFS objects to the public repo:
+- [ ] Sync the search indices for the new release:
   1. First navigate to the [sync search indices workflow](https://github.com/github/docs-internal/actions/workflows/sync-search-indices.yml). 
   2. Then, to run the workflow with parameters, click on `Run workflow` button. 
   3. A modal will pop up where you will set the following inputs:

.github/workflows/azure-preview-env-deploy.yml

@@ -91,7 +91,6 @@ jobs:
         with:
           ref: 'main'
           persist-credentials: 'false'
-          lfs: 'true'
 
       - if: ${{ env.IS_INTERNAL_BUILD == 'true' }}
         name: Check out PR code
@@ -100,10 +99,6 @@ jobs:
           ref: ${{ env.COMMIT_REF }}
           # To prevent issues with cloning early access content later
           persist-credentials: 'false'
-          lfs: 'true'
-
-      - name: Check out LFS objects
-        run: git lfs checkout
 
       - name: Get preview app info
         env:

.github/workflows/azure-staging-build-deploy.yml

@@ -65,10 +65,6 @@ jobs:
           ref: ${{ env.COMMIT_REF }}
           # To prevent issues with cloning early access content later
           persist-credentials: 'false'
-          lfs: 'true'
-
-      - name: Check out LFS objects
-        run: git lfs checkout
 
       - name: 'Set env vars'
         run: |

.github/workflows/browser-test.yml

@@ -50,11 +50,6 @@ jobs:
 
       - name: Checkout
         uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8
-        with:
-          lfs: true
-
-      - name: Checkout LFS objects
-        run: git lfs checkout
 
       - name: Setup Node
         uses: actions/setup-node@8c91899e586c5b171469028077307d293428b516

.github/workflows/main-preview-docker-cache.yml

@@ -49,10 +49,6 @@ jobs:
         with:
           # To prevent issues with cloning early access content later
           persist-credentials: 'false'
-          lfs: 'true'
-
-      - name: Check out LFS objects
-        run: git lfs checkout
 
       - if: ${{ env.ENABLE_EARLY_ACCESS }}
         name: Clone docs-early-access

.github/workflows/repo-sync.yml

@@ -100,7 +100,10 @@ jobs:
       - name: Check out repo
         uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8
 
-      # Set up npm and run npm ci to run husky to get githooks for LFS
+      # Set up npm and run npm ci to get custom husky githooks error
+      # messages if they exist. We could also remove these two steps
+      # because currently we have no hooks with customer error messages.
+      # See pull #32064 where they were removed.
       - name: Setup node
         uses: actions/setup-node@8c91899e586c5b171469028077307d293428b516
         with:

.github/workflows/test.yml

@@ -66,15 +66,6 @@ jobs:
       # Even if if doesn't do anything
       - name: Check out repo
         uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8
-        with:
-          # Not all test suites need the LFS files. So instead, we opt to
-          # NOT clone them initially and instead, include them manually
-          # only for the test groups that we know need the files.
-          lfs: ${{ matrix.test-group == 'content' }}
-          # Enables cloning the Early Access repo later with the relevant PAT
-          # persist-credentials: 'false'
-          # ->> Do we really need this? actions/checkout doesn't use it for the nested example:
-          # https://github.com/actions/checkout#checkout-multiple-repos-nested
 
       - name: Setup node
         uses: actions/setup-node@8c91899e586c5b171469028077307d293428b516
@@ -172,11 +163,6 @@ jobs:
           token: ${{ secrets.DOCUBOT_REPO_PAT }}
           path: translations/ko-kr
 
-      # This is necessary when LFS files where cloned but does nothing
-      # if actions/checkout was run with `lfs:false`.
-      - name: Checkout LFS objects
-        run: git lfs checkout
-
       - name: Gather files changed
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

CONTRIBUTING.md

@@ -48,9 +48,7 @@ For more information about using a codespace for working on GitHub documentation
 
 #### Make changes locally
 
-1. [Install Git LFS](https://docs.github.com/en/github/managing-large-files/versioning-large-files/installing-git-large-file-storage).
+1. Fork the repository.
-
-2. Fork the repository.
 - Using GitHub Desktop:
   - [Getting started with GitHub Desktop](https://docs.github.com/en/desktop/installing-and-configuring-github-desktop/getting-started-with-github-desktop) will guide you through setting up Desktop.
   - Once Desktop is set up, you can use it to [fork the repo](https://docs.github.com/en/desktop/contributing-and-collaborating-using-github-desktop/cloning-and-forking-repositories-from-github-desktop)!
@@ -58,9 +56,9 @@ For more information about using a codespace for working on GitHub documentation
 - Using the command line:
   - [Fork the repo](https://docs.github.com/en/github/getting-started-with-github/fork-a-repo#fork-an-example-repository) so that you can make your changes without affecting the original project until you're ready to merge them.
 
-3. Install or update to **Node.js v16**. For more information, see [the development guide](contributing/development.md).
+2. Install or update to **Node.js v16**. For more information, see [the development guide](contributing/development.md).
 
-4. Create a working branch and start with your changes!
+3. Create a working branch and start with your changes!
 
 ### Commit your update
 

contributing/development.md

@@ -10,9 +10,7 @@ It runs on macOS, Windows, and Linux environments.
 
 You'll need Node.js version 16 to run the site. To install Node.js, [download the "LTS" installer from nodejs.org](https://nodejs.org). If you're using [`nodenv`](https://github.com/nodenv/nodenv), read the [`nodenv` docs](https://github.com/nodenv/nodenv#readme) for instructions on switching Node.js versions.
 
-You'll want to [install Git LFS](https://docs.github.com/en/github/managing-large-files/versioning-large-files/installing-git-large-file-storage).
+Once you've installed Node.js (which includes the popular `npm` package manager), open Terminal and run the following:
-
-Once you've installed Node.js (which includes the popular `npm` package manager) and Git LFS, open Terminal and run the following:
 
 ```sh
 git clone https://github.com/github/docs

lib/search/config.js

@@ -1,9 +1,5 @@
 export const namePrefix = 'github-docs'
-export const maxContentLength = 5000
 
 export default {
-  // to reduce the size of our enormous search index, we limit the
-  // content and record size for translated articles
-  maxContentLength,
   namePrefix,
 }

script/copy-to-test-repo.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Copies certain directories over to docs-internal-test and pushes. Useful for debugging actions
-# Doesn't copy over git lfs files (.json.br), content/, and data/ directories
+# Doesn't copy over content/ and data/ directories
 
 echo "Make sure to run this script in the root path of docs-internal!"
 

script/search/parse-page-sections-into-records.js

@@ -1,8 +1,6 @@
 #!/usr/bin/env node
 import { render } from 'cheerio-to-text'
 
-import { maxContentLength } from '../../lib/search/config.js'
-
 // This module takes cheerio page object and divides it into sections
 // using H1,H2 heading elements as section delimiters. The text
 // that follows each heading becomes the content of the search record.
@@ -10,7 +8,7 @@ import { maxContentLength } from '../../lib/search/config.js'
 const ignoredHeadingSlugs = ['in-this-article', 'further-reading', 'prerequisites']
 
 export default function parsePageSectionsIntoRecords(page) {
-  const { href, $, languageCode } = page
+  const { href, $ } = page
   const title = $('h1').first().text().trim()
   const breadcrumbsArray = $('[data-search=breadcrumbs] nav.breadcrumbs a')
     .map((i, el) => {
@@ -81,15 +79,6 @@ export default function parsePageSectionsIntoRecords(page) {
     console.warn(`${objectID} has no body and no intro.`)
   }
 
-  // These below lines can be deleted (along with the `maxContentLength`
-  // config) once we've stopped generating Lunr indexes on disk that
-  // we store as Git LFS.
-  if (!process.env.ELASTICSEARCH_URL) {
-    if (languageCode !== 'en' && body.length > maxContentLength) {
-      body = body.slice(0, maxContentLength)
-    }
-  }
-
   const content =
     intro && !body.includes(intro.trim()) ? `${intro.trim()}\n${body.trim()}`.trim() : body.trim()