Collect funder finder data from multiple repos into a single CSV. Each line is one type of a contribution to one particular repo

run_funder_finder_on_repos.py

# collect data from multiple repos into a CSV. Each line is one type of a contribution to
# one particular repo

import json
import os

def run_python_command(command):
    # Execute the command and capture the output
    output = os.popen(command).read().strip()

    # Replace single quotes with double quotes in the JSON string
    output = output.replace("'", '"')

    # in JSON, true must be lowercase
    output = output.replace("True", "true")

    # Parse the output as JSON
    result = json.loads(output)

    return result

def append_to_jsonl_file(data, file_path):
    with open(file_path, 'a') as file:
        # Convert the data to JSON string
        json_data = json.dumps(data)

        # Append the data as a new line in the file
        file.write(json_data + '\n')

if __name__ == "__main__":

    output_file = 'collect_repos_into_csv_output.jsonl'

    # delete old jsonl file
    if os.path.exists(output_file):
        with open(output_file, 'w') as file:
            file.truncate(0)
    
    # read in all repos to be analyzed
    repos = []
    with open("repos.txt", 'r') as file:
        repos = file.readlines()

    # analyze each repo
    cnt = 1
    for repo in repos:
        print(cnt)
        # Run the command and get the result
        command = f"python3 ../funderfinder/get_funders.py {repo}"
        results = run_python_command(command)
        cnt += 1

        for result in results:
            # Keep track of what contributions are associated with what repo
            result["repo_name"] = repo
            # Append result to the JSONL file
            append_to_jsonl_file(result, output_file)