spark: add verification test for wordcount.py

wizard-work/spark/test_wordcount.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+"""Test script to verify wordcount.py matches wc output."""
+import subprocess
+import json
+
+# Get wordcount.py output
+result = subprocess.run(
+    ['python3', 'wordcount.py', 'test_words.txt'],
+    capture_output=True, text=True
+)
+wc_result = json.loads(result.stdout)
+wordcount_words = wc_result['words']
+
+# Get wc output
+wc_output = subprocess.run(
+    ['wc', '-w', 'test_words.txt'],
+    capture_output=True, text=True
+)
+wc_words = int(wc_output.stdout.strip().split()[0])
+
+print(f"wordcount.py: {wordcount_words} words")
+print(f"wc: {wc_words} words")
+
+if wordcount_words == wc_words:
+    print("PASS: Outputs match")
+    exit(0)
+else:
+    print("FAIL: Outputs differ")
+    exit(1)