# Example of common data processing tasks
import re
import json

# Text processing with regex
text = "Contact us at info@company.com or call (555) 123-4567"
emails = re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)
phones = re.findall(r'\(\d{3}\) \d{3}-\d{4}', text)

print(f"Found emails: {emails}")
print(f"Found phones: {phones}")

# JSON data processing
data = {
    "users": [
        {"name": "Alice", "score": 95},
        {"name": "Bob", "score": 87},
        {"name": "Charlie", "score": 92}
    ]
}

# Filter and transform data
high_scorers = [user for user in data["users"] if user["score"] > 90]
json_output = json.dumps(high_scorers, indent=2)

print(f"\nHigh scorers: {json_output}")

import re
import json

# Text processing pipeline
def process_log_entry(log_line):
    # Extract timestamp, level, and message
    pattern = r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) \[(\w+)\] (.+)'
    match = re.match(pattern, log_line)
    
    if match:
        return {
            'timestamp': match.group(1),
            'level': match.group(2),
            'message': match.group(3)
        }
    return None

# Sample data processing
log_lines = [
    "2024-01-15 10:30:45 [INFO] User login successful",
    "2024-01-15 10:31:12 [ERROR] Database connection failed",
    "2024-01-15 10:31:45 [INFO] User logout"
]

processed_logs = []
for line in log_lines:
    parsed = process_log_entry(line)
    if parsed:
        processed_logs.append(parsed)

print("Processed log entries:")
for log in processed_logs:
    print(f"  {log['level']}: {log['message']}")

# Data transformation
error_count = sum(1 for log in processed_logs if log['level'] == 'ERROR')
info_count = sum(1 for log in processed_logs if log['level'] == 'INFO')

summary = {
    'total_entries': len(processed_logs),
    'errors': error_count,
    'info': info_count
}

print(f"\nLog summary: {json.dumps(summary, indent=2)}")