spark: add word counter utility with tests

wizard-work/spark/test_json_diff.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+# Test script for json_diff.py
+import subprocess
+import sys
+
+# Test 1: Compare identical files
+result = subprocess.run(
+    [sys.executable, '/root/.hermes/wizard-outputs/spark/json_diff.py', 'sample_valid.json', 'sample_valid.json'],
+    capture_output=True,
+    text=True,
+    cwd='/root/.hermes/wizard-outputs/spark'
+)
+print(f"Test 1 (identical files): Exit code = {result.returncode}")
+print(f"  stdout: {result.stdout.strip()}")
+print(f"  stderr: {result.stderr.strip()}")
+
+# Test 2: Compare different files
+result2 = subprocess.run(
+    [sys.executable, '/root/.hermes/wizard-outputs/spark/json_diff.py', 'sample_valid.json', 'sample_invalid.json'],
+    capture_output=True,
+    text=True,
+    cwd='/root/.hermes/wizard-outputs/spark'
+)
+print(f"Test 2 (different files): Exit code = {result2.returncode}")
+print(f"  stdout: {result2.stdout.strip()}")
+print(f"  stderr: {result2.stderr.strip()}")
+
+# Test 3: JSON key order test (create temp files)
+import json
+import tempfile
+import os
+
+with tempfile.TemporaryDirectory() as tmp:
+    # File 1: keys in order a, b, c
+    with open(os.path.join(tmp, 'f1.json'), 'w') as f:
+        json.dump({'c': 3, 'a': 1, 'b': 2}, f)
+    # File 2: keys in order c, b, a (but same values)
+    with open(os.path.join(tmp, 'f2.json'), 'w') as f:
+        json.dump({'a': 1, 'b': 2, 'c': 3}, f)
+    
+    result3 = subprocess.run(
+        [sys.executable, '/root/.hermes/wizard-outputs/spark/json_diff.py', 
+         os.path.join(tmp, 'f1.json'), os.path.join(tmp, 'f2.json')],
+        capture_output=True,
+        text=True
+    )
+    print(f"Test 3 (same content, different key order): Exit code = {result3.returncode}")
+    print(f"  stdout: {result3.stdout.strip()}")
+    print(f"  stderr: {result3.stderr.strip()}")