import requests
import csv


# config
OWNER = "numpy"  # Chosen repo (this is just an example)
REPO = "numpy"
# -----------------------

API_URL = f"https://api.github.com/repos/{OWNER}/{REPO}/contributors?per_page=100"

def get_contributors():
    contributors = []
    page = 1
    while True:
        response = requests.get(f"{API_URL}&page={page}")
        if response.status_code != 200:
            print("Error fetching data:", response.status_code)
            break
        data = response.json()
        if not data:
            break
        for c in data:
            contributors.append({"login": c["login"], "commits": c["contributions"]})
        page += 1
    return contributors

def calculate_bus_factor(contributors):
    sorted_contribs = sorted(contributors, key=lambda x: x["commits"], reverse=True)
    total_commits = sum(c["commits"] for c in sorted_contribs)
    running_total = 0
    bus_factor = 0
    for c in sorted_contribs:
        running_total += c["commits"]
        bus_factor += 1
        if running_total >= total_commits * 0.5:
            break
    return bus_factor, sorted_contribs

def save_contributors_csv(contributors_sorted):
    with open("contributors.csv", "w", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=["login", "commits"])
        writer.writeheader()
        writer.writerows(contributors_sorted)
    print("Saved contributors.csv")

def main():
    contributors = get_contributors()
    if not contributors:
        print("No contributors found or error fetching data.")
        return
    bus_factor, sorted_contribs = calculate_bus_factor(contributors)
    print(f"Estimated Bus Factor for {OWNER}/{REPO}: {bus_factor}")
    save_contributors_csv(sorted_contribs)

if __name__ == "__main__":
    main()