harvest_issues/generate_issues.py

import os
import csv
import re
from dotenv import load_dotenv
import requests

load_dotenv()
FORGEJO_API_TOKEN = os.getenv("FORGEJO_API_TOKEN")

forgejo_issue_api_string = "https://git.agaric.com/api/v1/repos/{owner}/{repo}/issues/{index}"

"""
projects = {
    'harvest_project': ('owner', 'repo name')
}
"""
projects = {
    "MASS Continuous Improvement": ('mass', 'mass'),
    "Housing Works": ("housingworks", "app-housingworks-net"),
}


def test_parse_notes_section():
    if (parse_notes_section('Resolved Issue #4, #5 and Issue 6') == ['4', '5', '6']):
        print("TEST PARSE NOTES SECTION PASSED")
    else:
        print("TEST PARSE NOTES SECTION FAILED")

def test_get_issue_title_and_url():
    solution = [
        "Little slow downs are happening - these often signal that the server memory is getting overwhelmed?",
        "https://git.agaric.com/housingworks/app-housingworks-net/issues/363"
    ]
    if get_issue_title_and_url(363) == solution:
        print("TEST GET ISSUE TITLE AND URL PASSED")
    else:
        print("TEST GET ISSUE TITLE AND URL FAILED")

def parse_notes_section(notes):
    regex_pattern = r"[Ii]ssue\s*(?:#)?\d+|#\d+"
    matches = re.findall(regex_pattern, notes)[:3]
    issue_numbers = []
    for match in matches:
        match = re.search(r"\d+", match).group()
        issue_numbers.append(match)
    return issue_numbers

def get_issue_title_and_url(issue_number):
    global issues_and_urls
    issues_and_urls = []
    owner = projects["Housing Works"][0]
    repo = projects["Housing Works"][1]
    issue_url = forgejo_issue_api_string.format(owner=owner, repo=repo, index=issue_number)
    response = requests.get(issue_url, params={"access_token": FORGEJO_API_TOKEN})
    json_response = response.json()
    issue_title = json_response['title']
    issue_url = json_response['html_url']
    issues_and_urls += [issue_title, issue_url]
    return [issue_title, issue_url]

def prompt_for_file(file):
    file = input("Enter harvest report: ")
    if not os.path.exists(file):
        print("THAT FILE DOES NOT EXIST, EXITING PROGRAM")
        quit()

    print(file)
    return file

def parse_harvest_csv(file=None):
    global issues_and_urls

    if file is None:
        file = prompt_for_file(file)

    print('Beginning parsing for issues')

    issue_fields = [
        "First Issue Title",
        "First Issue URL",
        "Second Issue Title",
        "Second Issue URL",
        "Third Issue Title",
        "Third Issue URL"
    ]


    with open(file, 'r') as f:
        csv_reader = csv.DictReader(f)
        rows = list(csv_reader)
        original_fieldnames = csv_reader.fieldnames
        modified_fieldnames = original_fieldnames + issue_fields

    f.close()

    with open('modified_report.csv', 'w', newline='') as csvfile:
        issues_and_urls = []
        writer = csv.DictWriter(csvfile, fieldnames = modified_fieldnames)
        writer.writeheader()
        row_count = 0
        for row in rows:
            issues = parse_notes_section(row['Notes'])
            for issue in issues:
                get_issue_title_and_url(issue)
            issues_dict = dict(zip(issue_fields, issues_and_urls))
            row.update(issues_dict)
            issues_and_urls = []
            writer.writerow(row)
        

def run_program():
    parse_harvest_csv()

test_parse_notes_section()
test_get_issue_title_and_url()
run_program()