[Github] Fetch all commits in PR for code formatting checks (#69766)

This patch makes a couple changes to the PR code formatting check:
- Moves the `changed-files` action to before the checkout to make sure
that it pulls
information from the Github API rather than by running `git diff` to
alleviate some
performance problems.
- Checkout the head of the pull request head instead of the base of the
pull request
to ensure that we have the PR commits inside the checkout.
- Add an additional sparse checkout of the necessary LLVM tools to run
the action
to alleviate security problems introduced by checking out the head of
the pull
request. Only code from the base of the pull request runs.
- Adjust the commit references to be based on `HEAD` as Github doesn't
give
exact commit SHAs for the first commit in the PR.

Author: boomanaiden154

.github/workflows/pr-code-format.yml

@@ -7,17 +7,37 @@ jobs:
   code_formatter:
     runs-on: ubuntu-latest
     steps:
-      - name: Fetch LLVM sources
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-
+      # Get changed files before checking out the repository to force the action
+      # to analyze the diff from the Github API rather than looking at the
+      # shallow clone and erroring out, which is significantly more prone to
+      # failure.
       - name: Get changed files
         id: changed-files
         uses: tj-actions/changed-files@v39
         with:
           separator: ","
-          fetch_depth: 100 # Fetches only the last 10 commits
+
+      - name: Calculate number of commits to fetch
+        run: echo "PR_FETCH_DEPTH=$(( ${{ github.event.pull_request.commits }} + 1 ))" >> "${GITHUB_ENV}"
+
+      - name: Fetch PR sources
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          fetch-depth: ${{ env.PR_FETCH_DEPTH }}
+          path: pr-sources
+
+      # We need to make sure that we aren't executing/using any code from the
+      # PR for security reasons as we're using pull_request_target. Checkout
+      # the target branch with the necessary files.
+      - name: Fetch LLVM Sources
+        uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            llvm/utils/git/requirements_formatting.txt
+            llvm/utils/git/code-format-helper.py
+          sparse-checkout-cone-mode: false
+          path: llvm-sources
 
       - name: "Listed files"
         run: |
@@ -34,21 +54,21 @@ jobs:
         with:
           python-version: '3.11'
           cache: 'pip'
-          cache-dependency-path: 'llvm/utils/git/requirements_formatting.txt'
+          cache-dependency-path: 'llvm-sources/llvm/utils/git/requirements_formatting.txt'
 
       - name: Install python dependencies
-        run: pip install -r llvm/utils/git/requirements_formatting.txt
+        run: pip install -r llvm-sources/llvm/utils/git/requirements_formatting.txt
 
       - name: Run code formatter
         env:
           GITHUB_PR_NUMBER: ${{ github.event.pull_request.number }}
-          START_REV: ${{ github.event.pull_request.base.sha }}
-          END_REV: ${{ github.event.pull_request.head.sha }}
+          PR_DEPTH: ${{ github.event.pull_request.commits }}
           CHANGED_FILES: ${{ steps.changed-files.outputs.all_changed_files }}
+        working-directory: ./pr-sources
         run: |
-          python llvm/utils/git/code-format-helper.py \
+          python ../llvm-sources/llvm/utils/git/code-format-helper.py \
             --token ${{ secrets.GITHUB_TOKEN }} \
             --issue-number $GITHUB_PR_NUMBER \
-            --start-rev $START_REV \
-            --end-rev $END_REV \
+            --start-rev HEAD~$PR_DEPTH \
+            --end-rev HEAD \
             --changed-files "$CHANGED_FILES"