Add CI step to check for too-large files and lfs files

.github/workflows/misc.yml

@@ -1,6 +1,7 @@
 name: CI (Misc)
 
 on:
+  workflow_dispatch:
   pull_request:
   push:
     branches:
@@ -25,3 +26,7 @@ jobs:
       - name: Rerun lints
         run: |
           ./scripts/lint.py
+
+      - name: Check for too large files
+        run: |
+          ./scripts/check_large_files.sh

scripts/check_large_files.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+# Check for files that are too large to be checked into the repository.
+# Whenever we want to make an exception, we add it to `check_large_files_allow_list.txt`
+set -eu
+
+#find . -type f -size +300k | grep -vnE -f ./scripts/check_large_files_allow_list.txt
+
+maximum_size=$((1024 * 300))
+
+result=0
+while read -d '' -r file; do
+    if [[ -f "$file" ]]; then
+        actualsize=$(wc -c <"$file")
+        if [ $actualsize -ge $maximum_size ]; then
+            if ! grep -qx "$file" ./scripts/check_large_files_allow_list.txt; then
+                echo $file is larger than $maximum_size bytes
+                result=1
+            fi
+        fi
+    fi
+done < <(git ls-files -z --empty-directory)
+
+exit $result

scripts/check_large_files_allow_list.txt

@@ -0,0 +1 @@
+rerun_py/rerun_sdk/rerun_demo/demo.rrd