Add pre-commit hook to avoid duplicates (#1314)

* add pre-commit hook to avoid duplidate ipynb

* add test1

* check against local files

* skip duplicate check in ci

---------

Co-authored-by: Emma Ai <[email protected]>

Author: emmaai

.githooks/check_duplicate_ipynb.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+echo "Checking for duplicate .ipynb filenames..."
+
+# Get all existing and staged .ipynb files
+all_files=$(git ls-files | grep '\.ipynb$' || true)
+staged_files=$(git diff --cached --name-only --diff-filter=A | grep '\.ipynb$' || true)
+
+# Combine them to ensure we check for duplicates globally
+combined_files=$(echo -e "$all_files\n$staged_files" | sort -u)
+
+if [[ -z "$combined_files" ]]; then
+    exit 0  # No .ipynb files found, allow commit
+fi
+
+# Extract only filenames (ignore paths)
+filenames=$(basename -a $combined_files)
+
+# Check for duplicates
+duplicates=$(echo "$filenames" | sort | uniq -d)
+
+if [[ -n "$duplicates" ]]; then
+    echo "Duplicate .ipynb filenames detected in repository and staged changes:"
+    echo "$duplicates"
+    echo "Commit rejected! Ensure unique .ipynb filenames."
+    exit 1  # Prevent commit
+fi
+
+exit 0  # Allow commit

.pre-commit-config.yaml

@@ -0,0 +1,12 @@
+ci:
+  skip: [check-duplicate-ipynb] 
+
+repos:
+  - repo: local
+    hooks:
+      - id: check-duplicate-ipynb
+        name: Check for duplicate .ipynb filenames
+        entry: bash .githooks/check_duplicate_ipynb.sh
+        language: system
+        pass_filenames: false
+        stages: [pre-commit]