Infra spell bot (#35224)

* feat(bot): spelling checking bot * remove a duplicate pattern * add HTTPWG * Apply suggestions from code review Co-authored-by: Brian Thomas Smith <[email protected]> * Update .github/workflows/spelling-check-bot.yml * Apply suggestions from code review Co-authored-by: Brian Thomas Smith <[email protected]> * update workflow * run sort-uniq on word files and rename them * rename files --------- Co-authored-by: Brian Thomas Smith <[email protected]>
mdn · Aug 29, 2024 · 3f4f116 · 3f4f116
1 parent 52580e9
commit 3f4f116
Show file tree

Hide file tree

Showing 4 changed files with 5,621 additions and 7 deletions.
diff --git a/.github/workflows/spelling-check-bot.yml b/.github/workflows/spelling-check-bot.yml
@@ -0,0 +1,48 @@
+name: Create an issue to report typos
+
+on:
+  schedule:
+    - cron: "0 0 * * mon"
+  workflow_dispatch:
+
+jobs:
+  sync:
+    if: github.repository == 'mdn/content'
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Node.js environment
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: yarn
+
+      - name: Run scripts
+        run: |
+          npm install
+          echo Running spelling check...
+          output=$(npx cspell --no-progress --gitignore --config .vscode/cspell.json "**/*.md" || exit 0)
+          echo "$output"
+          echo "OUTPUT<<EOF" >> $GITHUB_ENV
+          echo "$output" >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create an issue
+        if: env.OUTPUT != ''
+        uses: dacbd/create-issue-action@main
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          title: Weekly spelling check
+          body: |
+            Typos and unknown words:
+
+            ```
+            ${{ env.OUTPUT }}
+            ```
+
+            > [!TIP]
+            > To exclude words from the spellchecker, you can add valid words (web technology terms or abbreviations) to the [terms-abbreviations.txt](https://github.com/mdn/content/blob/main/.vscode/terms-abbreviations.txt) dictionary for IDE autocompletion. To ignore strings that are not words (`AABBCC` in code, for instance), you can add them to [ignore-list.txt](https://github.com/mdn/content/blob/main/.vscode/ignore-list.txt).
+        env:
+          OUTPUT: ${{ env.OUTPUT }}
diff --git a/.vscode/cspell.json b/.vscode/cspell.json
@@ -3,7 +3,10 @@
   "version": "0.2",
   "language": "en-US",
   "languageId": "*",
+  "useGitignore": true,
   "dictionaries": [
+    "terms-abbreviations",
+    "ignore-list",
     "bash",
     "css",
     "cpp",
@@ -17,7 +20,6 @@
     "markdown",
     "node",
     "npm",
-    "project-words",
     "python",
     "softwareTerms",
     "svelte",
@@ -37,10 +39,9 @@
     // TODO - add some details what these match
     "\\(#\\w*\\)",
     "\\]\\(\\S*\\)",
-    "\\]\\(\\S*\\)",
     "\\*\\*\\w\\*\\*\\w*",
     "\\*\\w\\*\\w*",
-    "#[\\w-]*",
+    "#[À-ž\\w-]*",
     "aria-activedescendant=\"(?:[^\\\"]+|\\.)*\"",
     "aria-controls=\"(?:[^\\\"]+|\\.)*\"",
     "aria-describedby=\"(?:[^\\\"]+|\\.)*\"",
@@ -55,18 +56,26 @@
     "for=\"(?:[^\\\"]+|\\.)*\"",
     "HexValues",
     "href=\"(?:[^\\\"]+|\\.)*\"",
-    "id=\"(?:[^\\\"]+|\\.)*\"",
+    "(?<=id)=\"(?:[^\\\"]+|\\.)*\"",
     "lang=\".*\">.*</",
     "src=\"(?:[^\\\"]+|\\.)*\"",
     "url\\(\"data\\:image/svg\\+xml.*\"\\)[,;]",
-    "Urls"
+    "Urls",
+    "favourite-colour",
+    "ucaf:.*\""
   ],
   "allowCompoundWords": true,
   "dictionaryDefinitions": [
     {
-      "name": "project-words",
-      "path": "./project-words.txt",
+      "name": "terms-abbreviations",
+      "path": "./terms-abbreviations.txt",
       "addWords": true
+    },
+    {
+      "name": "ignore-list",
+      "path": "./ignore-list.txt",
+      "addWords": false,
+      "noSuggest": true
     }
   ],
   "enableFiletypes": ["xml"]