From b40f0cb6cba840a458ecf50bef687f0bdd6feca1 Mon Sep 17 00:00:00 2001
From: Ben Howe <bhowe@nvidia.com>
Date: Wed, 11 Mar 2026 09:55:26 -0700
Subject: [PATCH 1/2] Check for large files

Signed-off-by: Ben Howe <bhowe@nvidia.com>
Co-authored-by: Melody Ren <melodyr@nvidia.com>
---
 .github/workflows/pr_file_check.yaml | 46 ++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)
 create mode 100644 .github/workflows/pr_file_check.yaml

diff --git a/.github/workflows/pr_file_check.yaml b/.github/workflows/pr_file_check.yaml
new file mode 100644
index 00000000..c502ff83
--- /dev/null
+++ b/.github/workflows/pr_file_check.yaml
@@ -0,0 +1,46 @@
+name: Check for Large Files and Restricted Extensions
+
+on:
+  pull_request:
+    branches: 
+      - main
+    types: [opened, synchronize, reopened]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  check-files:
+    name: Check file size and type
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          set-safe-directory: true
+          fetch-depth: 1
+
+      - name: Fetch base branch
+        run: git fetch origin ${{ github.event.pull_request.base.ref }} --depth=1
+
+      - name: Check for large files
+        run: |
+          MAX_SIZE=100K  # Set max file size limit
+          LARGE_FILES=$(git diff --name-only --diff-filter=A origin/${{ github.event.pull_request.base.ref }} | xargs du -h | awk -v max="$MAX_SIZE" '$1 > max {print $2}')
+
+          if [[ ! -z "$LARGE_FILES" ]]; then
+            echo "❌ The following files exceed the allowed size of $MAX_SIZE:"
+            echo "$LARGE_FILES"
+            exit 1
+          fi
+
+      - name: Check for restricted file types
+        run: |
+          BLOCKED_EXTENSIONS="(exe|zip|tar.gz|bz2)"  # Add any forbidden extensions
+          BAD_FILES=$(git diff --name-only --diff-filter=A origin/${{ github.event.pull_request.base.ref }} | grep -E "\.($BLOCKED_EXTENSIONS)$" || true)
+          if [[ ! -z "$BAD_FILES" ]]; then
+            echo "❌ The following files have restricted extensions:"
+            echo "$BAD_FILES"
+            exit 1
+          fi

From fb229d4ba9c49d407cf5ba479cdb0217845eba54 Mon Sep 17 00:00:00 2001
From: Ben Howe <bhowe@nvidia.com>
Date: Wed, 11 Mar 2026 10:00:37 -0700
Subject: [PATCH 2/2] Fix check

Signed-off-by: Ben Howe <bhowe@nvidia.com>
---
 .github/workflows/pr_file_check.yaml | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/pr_file_check.yaml b/.github/workflows/pr_file_check.yaml
index c502ff83..3146909f 100644
--- a/.github/workflows/pr_file_check.yaml
+++ b/.github/workflows/pr_file_check.yaml
@@ -26,11 +26,21 @@ jobs:
 
       - name: Check for large files
         run: |
-          MAX_SIZE=100K  # Set max file size limit
-          LARGE_FILES=$(git diff --name-only --diff-filter=A origin/${{ github.event.pull_request.base.ref }} | xargs du -h | awk -v max="$MAX_SIZE" '$1 > max {print $2}')
+          MAX_SIZE_BYTES=102400  # 100KB
+          MAX_SIZE_HUMAN="100KB"
+          LARGE_FILES=""
+          while IFS= read -r file; do
+            if [[ -f "$file" ]]; then
+              size=$(stat --format='%s' "$file")
+              if (( size > MAX_SIZE_BYTES )); then
+                human_size=$(numfmt --to=iec "$size")
+                LARGE_FILES+="  $file ($human_size)"$'\n'
+              fi
+            fi
+          done < <(git diff --name-only --diff-filter=A origin/${{ github.event.pull_request.base.ref }})
 
-          if [[ ! -z "$LARGE_FILES" ]]; then
-            echo "❌ The following files exceed the allowed size of $MAX_SIZE:"
+          if [[ -n "$LARGE_FILES" ]]; then
+            echo "❌ The following files exceed the allowed size of $MAX_SIZE_HUMAN:"
             echo "$LARGE_FILES"
             exit 1
           fi