Update check-spelling (#14873)

* Updating advice

Copying 18764e6cbb/.github/actions/spelling/advice.md

* Update exclusions

* sort exclusions
* exclude .filters files based on updated engine suggestions
* exclude src/modules/previewpane/UnitTests-MarkdownPreviewHandler/HelperFiles/MarkdownWithHTMLImageTag.txt based on updated engine suggestions

* Upgrade check-spelling to v0.0.20-alpha3

Updates patterns to better handle guids
closes #14854

Adds a couple of other patterns:
* publicKeyToken
* @sha256:
* std::wregex

Co-authored-by: Josh Soref <jsoref@users.noreply.github.com>
Co-authored-by: Jaime Bernardo <jaime@janeasystems.com>

.github/actions/spell-check/advice.md

@@ -1,27 +1,25 @@
 <!-- See https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-advice --> <!-- markdownlint-disable MD033 MD041 -->
-<details><summary>If you see a bunch of garbage</summary>
+<details><summary>If the flagged items do not appear to be text</summary>
 
-If it relates to a ...
+If items relate to a ...
-<details><summary>well-formed pattern</summary>
+* well-formed pattern.
 
-See if there's a [pattern](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns) that would match it.
+  If you can write a [pattern](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns) that would match it,
+  try adding it to the `patterns.txt` file.
 
-If not, try writing one and adding it to the `patterns.txt` file.
+  Patterns are Perl 5 Regular Expressions - you can [test](
-
-Patterns are Perl 5 Regular Expressions - you can [test](
 https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your lines.
 
-Note that patterns can't match multiline strings.
+  Note that patterns can't match multiline strings.
-</details>
-<details><summary>binary-ish string</summary>
 
-Please add a file path to the `excludes.txt` file instead of just accepting the garbage.
+* binary file.
 
-File paths are Perl 5 Regular Expressions - you can [test](
+  Please add a file path to the `excludes.txt` file matching the containing file.
+
+  File paths are Perl 5 Regular Expressions - you can [test](
 https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your files.
 
-`^` refers to the file's path from the root of the repository, so `^README\.md$` would exclude [README.md](
+  `^` refers to the file's path from the root of the repository, so `^README\.md$` would exclude [README.md](
 ../tree/HEAD/README.md) (on whichever branch you're using).
-</details>
 
 </details>

.github/actions/spell-check/excludes.txt

@@ -3,6 +3,7 @@
 (?:^|/)(?i)LICEN[CS]E
 (?:^|/)package(?:-lock)\.json$
 (?:^|/)vendor/
+(?:^|/)WindowsSettings\.json$
 /package(?:-lock|)\.json$
 /pinyindb/
 /settings-html/
@@ -12,6 +13,7 @@ ignore$
 \.bmp$
 \.dat$
 \.dll$
+\.filters$
 \.gcode$
 \.gif$
 \.gitignore$
@@ -38,8 +40,8 @@ ignore$
 ^src/modules/powerrename/UWPui/pch\.h$
 ^src/modules/powerrename/UWPui/PowerRenameUWPUI\.vcxproj\.filters$
 ^src/modules/previewpane/PreviewPaneUnitTests/HelperFiles/MarkdownWithHTMLImageTag\.txt$
+^src/modules/previewpane/UnitTests-MarkdownPreviewHandler/HelperFiles/MarkdownWithHTMLImageTag.txt$
 ^tools/CleanUp_tool/CleanUp_tool\.vcxproj\.filters$
 ^\.github/
 ^\.github/actions/spell-check/
 ^\.gitmodules$
-(?:^|/)WindowsSettings\.json$

.github/actions/spell-check/patterns.txt

@@ -12,11 +12,24 @@ https?://(?:(?:www\.|)youtube\.com|youtu.be)/[-a-zA-Z0-9?&=]*
 # msdn
 \b(?:download\.visualstudio|docs|msdn)\.microsoft\.com/[-_a-zA-Z0-9()=./]*
 
-data:[a-zA-Z=;,/0-9+-]+
+publicKeyToken=(['"]|)[0-9a-f]+\g{-1}
-0x[0-9a-fA-F](?:\.[0-9a-fA-F]*|)[pP]
+\@sha256:[0-9a-f]{64}\b
-(?:0[Xx]|U\+|#)[a-f0-9A-FGgRr]{2,}[Uu]?[Ll]{0,2}\b
+
+# data urls
+(['"])data:.*?\g{-1}
+data:[-a-zA-Z=;:/0-9+]*,\S*
+
 # uuid:
-[-<({"'>][0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12}[<'"})>]
+L?(["']|[-<({>]|\b)[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12}(?:\g{-1}|[<})>])
+
+# c99 hex digits (not the full format, just one I've seen)
+0x[0-9a-fA-F](?:\.[0-9a-fA-F]*|)[pP]
+
+# wregex
+std::wregex\(L"[^"]*"\)
+
+# hex digits including css/html color classes:
+(?:[\\0][xX]|\\u|[uU]\+|#x?|\%23|L")[0-9a-fA-FgGrR_]{2,}(?:[uU]?[lL]{0,2}|u\d+)\b
 
 # ignore long runs of a single character:
 \b([A-Za-z])\g{-1}{3,}\b

.github/workflows/spelling2.yml

@@ -3,11 +3,23 @@ name: Spell checking
 on:
   pull_request_target:
   push:
+    branches: ["**"]
+    tags-ignore: ["**"]
 
 jobs:
   spelling:
     name: Spell checking
+    permissions:
+      contents: read
+      pull-requests: read
+    outputs:
+      internal_state_directory: ${{ steps.spelling.outputs.internal_state_directory }}
     runs-on: ubuntu-latest
+    if: "contains(github.event_name, 'pull_request') || github.event_name == 'push'"
+    concurrency:
+      group: spelling-${{ github.event.pull_request.number || github.ref }}
+      # note: If you use only_check_changed_files, you do not want cancel-in-progress
+      cancel-in-progress: true
     steps:
     - name: checkout-merge
       if: "contains(github.event_name, 'pull_request')"
@@ -15,8 +27,50 @@ jobs:
       with:
         ref: refs/pull/${{github.event.pull_request.number}}/merge
     - name: checkout
-      if: "!contains(github.event_name, 'pull_request')"
+      if: github.event_name == 'push'
       uses: actions/checkout@v2
-    - uses: check-spelling/check-spelling@v0.0.19
+    - name: check-spelling
+      id: spelling
+      uses: check-spelling/check-spelling@v0.0.20-alpha3
       with:
         config: .github/actions/spell-check
+        suppress_push_for_open_pull_request: 1
+        post_comment: 0
+        extra_dictionaries:
+          cspell:filetypes/filetypes.txt
+          cspell:html/html.txt
+          cspell:css/css.txt
+        check_extra_dictionaries: ''
+    - name: store-comment
+      if: failure()
+      uses: actions/upload-artifact@v2
+      with:
+        retention-days: 1
+        name: "check-spelling-comment-${{ github.run_id }}"
+        path: |
+          ${{ steps.spelling.outputs.internal_state_directory }}
+
+  comment:
+    name: Comment
+    runs-on: ubuntu-latest
+    needs: spelling
+    permissions:
+      contents: write
+      pull-requests: write
+    if: always() && needs.spelling.result == 'failure' && needs.spelling.outputs.internal_state_directory
+    steps:
+    - name: checkout
+      uses: actions/checkout@v2
+    - name: set up
+      run: |
+        mkdir /tmp/data
+    - name: retrieve-comment
+      uses: actions/download-artifact@v2
+      with:
+        name: "check-spelling-comment-${{ github.run_id }}"
+        path: /tmp/data
+    - name: comment
+      uses: check-spelling/check-spelling@v0.0.20-alpha3
+      with:
+        custom_task: comment
+        internal_state_directory: /tmp/data