import csv 
import os 
import json 
import pandas as pd


def csv_count():
    with open("cleaned_0118_uni_constrib.csv", "w") as writefile:
        keys = ["project_name", "project_owner", "api_contrib_count", "issue_contrib_count", "file_contrib_count", "wiki_contrib_count"]
        writer = csv.writer(writefile)
        writer.writerow(keys)
        with open("011824_uni_contrib.csv", "r") as file:
            reader = csv.reader(file)
            true_rep_counter = 0
            for i, line in enumerate(reader):
                if line[2] == line[3] == line[4] == line[5] == '0':
                    print("zeroes")
                else:
                    writer.writerow(line)
                    print(line)
                    true_rep_counter += 1
            print(true_rep_counter)

def checking_cross():
    with open("cleaned_0118_uni_constrib.csv", "r") as readfile:
        reader = csv.reader(readfile)
        checking_sum = 0
        for i, line in enumerate(reader):
            if os.path.exists("/data/users/mgaughan/kkex_contrib_files_122023/contribute_inst/" + line[0] + "_inst.md" ):
                checking_sum += 1
            if os.path.exists("/data/users/mgaughan/kkex_contrib_files_122023/contribute_inst/" + line[0] + ".git_inst.md" ):
                checking_sum += 1
        print(checking_sum)

def consolidate_csv():
    contributor_count_csv = pd.read_csv("cleaned_0118_uni_contrib.csv")
    print(contributor_count_csv.head())
    total_underprod_csv = pd.read_csv("expanded_data_final.csv")
    print(total_underprod_csv.head())
    columns = list(total_underprod_csv.columns)
    columns.extend(["api_contrib_count", "issue_contrib_count", "file_contrib_count", "wiki_contrib_count"])
    list_of_links = total_underprod_csv["upstream_vcs_link"].tolist()
    count = 0
    with open("octo_data_total.csv", 'w', newline='') as output_file:
        writer = csv.writer(output_file, columns)
        writer.writerow(columns)
        for index, row in contributor_count_csv.iterrows():
            row_value = []
            string_value = row['project_owner'] + "/" + row['project_name']
            for item in list_of_links:
                if string_value in item:
                    row_value = total_underprod_csv.loc[total_underprod_csv["upstream_vcs_link"] == item].values.tolist()[0] 
            row_value.extend([row["api_contrib_count"], row["issue_contrib_count"], row["file_contrib_count"], row["wiki_contrib_count"]])
            print(row_value)
            if len(row_value) > 4:
                writer.writerow(row_value)
                count += 1
        print(count)



if __name__ == "__main__":
    consolidate_csv()