csv_analyzer.py

import pandas as pd
import re

def extract_features(query):
    query = str(query)
    features = {
        'length': len(query),
        'single_quotes': query.count("'"),
        'double_quotes': query.count('"'),
        'dashes': query.count('--'),
        'semicolons': query.count(';'),
        'asterisks': query.count('*'),
        'spaces': query.count(' '),
        'keywords': len(re.findall(r'(SELECT|UNION|INSERT|DELETE|UPDATE|DROP|WHERE|AND|OR|FROM|SLEEP|HEX|CHR)', query, re.I))
    }
    return features

# Load your dataset
print("Loading BCCC-SFU-SQLInj-2023.csv...")
df = pd.read_csv('BCCC-SFU-SQLInj-2023.csv')

# Extract features
print("Analyzing data and extracting features...")
feature_list = df['Data'].apply(extract_features).apply(pd.Series)

# Combine original data with new features
result = pd.concat([df, feature_list], axis=1)

# Save the results
output_file = 'analyzed_dataset.csv'
result.to_csv(output_file, index=False)

print(f"Analysis complete! Results saved to {output_file}")
print("\nFirst 5 rows of analysis:")
print(result[['Data', 'length', 'single_quotes', 'keywords']].head())