24_deb_pkg_gov/get_first_commit.py

import csv
from perceval.backends.core.git import Git
import os
import datetime as dt
from datetime import timezone
import time
import shutil 
import dateutil
from tqdm import tqdm
import math

key = os.environ.get('KKEXKEY')
temp_dir = "/data/users/mgaughan/tmp/"
temp_dir1 = "tmp/"

'''
- rate of change, rate of all/day
'''
def file_get_contribs(upstream_vcs_link, event_date):
    # if we're looking at readmes me_read is true and if not, if we're looking at contributing files, it's false
    #this is the window of days on either side of the event that we're looking at
    window = 56
    #print(upstream_vcs_link.split('/')[4])
    project_dict = {}
    project_dict['upstream_vcs_link'] = upstream_vcs_link
    #event_date = dateutil.parser.parse(event_date).astimezone(timezone.utc)
    upstream_vcs_link = upstream_vcs_link.strip()
    if "github" in upstream_vcs_link or "gitlab" in upstream_vcs_link:
        #making an evaluation that sub branches aren't being used and that people would fork if needed
        #this only looks at main
        upstream_vcs_link = "/".join(upstream_vcs_link.split("/")[0:5])
        print(upstream_vcs_link)
        full_temp_path = temp_dir + upstream_vcs_link.split('/')[4] + ".git"
    else:
        full_temp_path = temp_dir + upstream_vcs_link.split('/')[- 1] + ".git"
    print(upstream_vcs_link)
    if upstream_vcs_link == "https://gitlab.com/ubports/core" or upstream_vcs_link == "https://gitlab.freedesktop.org/xorg/lib":
        shutil.rmtree(full_temp_path, ignore_errors=True)
        return {}
    repo = Git(uri=upstream_vcs_link, gitpath=full_temp_path)
    commits = repo.fetch()
    merge_pre, merge_post = 0, 0
    #list of tuples which has date and whether it was a merge
    commit_list = []
    first_date_readme = ""
    index = 0 
    for commit in commits:
        if index == 0:
            project_dict['first_commit'] = commit['data']['CommitDate']
            break
        #print(commit['data'])
    shutil.rmtree(full_temp_path, ignore_errors=True)
    print(project_dict)
    return project_dict



def for_files():
    csv_path = "final_data/deb_contrib_did.csv"
    count = 0 
    with open(csv_path, 'r') as file:
        csv_reader = csv.DictReader(file)
        with open('062424_did_first_commit_contrib.csv', "w") as writing_file:
            # this would also have to get switched fro the cont dataset
            keys = ['upstream_vcs_link', "first_commit"]
            dict_writer = csv.DictWriter(writing_file, keys)
            dict_writer.writeheader()
            for row in csv_reader:
                count += 1
                print(row['upstream_vcs_link'])
                # this would have to get switched to false for the cont dataset
                dict_row = file_get_contribs(row['upstream_vcs_link'].strip(), row['event_date'])
                dict_writer.writerow(dict_row)
    

if __name__ == "__main__":
    for_files()
    #file_get_contribs("https://github.com/Debian/perl-cross-debian", "00-00-00")
    #file_get_pr("https://github.com/tqdm/tqdm", True)
    #file_get_pr("https://github.com/GameServerManagers/LinuxGSM", True)
    #file_get_pr("https://github.com/walling/unorm/issues/new/", True)
    #file_get_pr("https://github.com/krahets/hello-algo/tree/dev1", True)