analyzer.py

from collections import Counter
import csv
import re

LOG_FILE = "sample.log"
OUTPUT_FILE = "output/log_summary.csv"

def analyze_log_file(file_path):
    counts = Counter()
    error_messages = []

    log_pattern = re.compile(r"^\S+\s+\S+\s+(INFO|WARNING|ERROR)\s+(.*)$")

    with open(file_path, "r") as file:
        for line in file:
            match = log_pattern.match(line.strip())
            if match:
                level = match.group(1)
                message = match.group(2)

                counts[level] += 1

                if level == "ERROR":
                    error_messages.append(message)

    return counts, Counter(error_messages)

def save_summary_to_csv(counts, error_counter, output_file):
    with open(output_file, "w", newline="") as csvfile:
        writer = csv.writer(csvfile)

        writer.writerow(["Metric", "Value"])
        writer.writerow(["INFO Count", counts.get("INFO", 0)])
        writer.writerow(["WARNING Count", counts.get("WARNING", 0)])
        writer.writerow(["ERROR Count", counts.get("ERROR", 0)])
        writer.writerow([])
        writer.writerow(["Top Error Message", "Occurrences"])

        for error, count in error_counter.most_common(5):
            writer.writerow([error, count])

def main():
    counts, error_counter = analyze_log_file(LOG_FILE)

    print("Log Analysis Summary")
    print("--------------------")
    print(f"INFO count: {counts.get('INFO', 0)}")
    print(f"WARNING count: {counts.get('WARNING', 0)}")
    print(f"ERROR count: {counts.get('ERROR', 0)}")

    print("\nTop Errors:")
    for error, count in error_counter.most_common(5):
        print(f"{error} -> {count}")

    save_summary_to_csv(counts, error_counter, OUTPUT_FILE)
    print(f"\nSummary saved to {OUTPUT_FILE}")

if __name__ == "__main__":
    main()