#!/usr/bin/env python3
"""Verify text_stats.py works correctly."""

import json
import subprocess
import sys

# Run the script on itself
proc = subprocess.run(
    ['python3', '/root/.hermes/wizard-outputs/spark/text_stats.py', 
     '/root/.hermes/wizard-outputs/spark/text_stats.py'],
    capture_output=True, text=True
)

# Parse output
try:
    data = json.loads(proc.stdout.strip())
except json.JSONDecodeError as e:
    print(f"FAIL: Invalid JSON output: {e}")
    sys.exit(1)

# Verify schema
errors = []
if 'path' not in data:
    errors.append("missing 'path' field")
if 'lines' not in data:
    errors.append("missing 'lines' field")
if 'words' not in data:
    errors.append("missing 'words' field")
if 'chars' not in data:
    errors.append("missing 'chars' field")

if errors:
    print(f"FAIL: {', '.join(errors)}")
    sys.exit(1)

# Verify counts match expected values (from wc and word count)
if data['lines'] != 38:
    errors.append(f"lines={data['lines']}, expected 38")
if data['words'] != 114:
    errors.append(f"words={data['words']}, expected 114")
if data['chars'] != 1030:
    errors.append(f"chars={data['chars']}, expected 1030")

if errors:
    print(f"FAIL: {', '.join(errors)}")
    sys.exit(1)

print("PASS: text_stats.py verified successfully")
print(f"  - paths: {data['path']}")
print(f"  - lines: {data['lines']}")
print(f"  - words: {data['words']}")
print(f"  - chars: {data['chars']}")