Constructing databus client deploy command

construct_command.py

import os
import json
import urllib.parse
from datetime import datetime
import argparse
import re


def construct_string_from_json(file_path, data_folder, api_key):
    with open(file_path, 'r') as f:
        data = json.load(f)

    _, _, _, _, _, group, artifact, version = data_folder.split('/')
    base_url = f'http://downloads.dbpedia.org/repo/dbpedia/{group}/{artifact}/{version}/'

    data["versionid"] = f"https://databus.dbpedia.org/dbpedia/{group}/{artifact}/{version}"

    dataset_strings = []
    for filename in os.listdir(data_folder):
        if filename.endswith(".ttl.bz2"):
            lang = filename.split('=')[1].split('.')[0]
            encoded_filename = urllib.parse.quote_plus(filename)
            dataset_url = f'"{base_url}{encoded_filename}%7Clang={lang}"'
            dataset_strings.append(dataset_url)

    datasets = ' '.join(dataset_strings)

    command = (f'databusclient deploy --versionid {data["versionid"]} '
               f'--title "{data["title"]}" '
               f'--abstract "{data.get("abstract", "")}" '
               f'--description "{data.get("description", "")}" '
               f'--license "{data["license"]}" '
               f'--apikey {api_key} '
               f'{datasets}')

    return command


def process_latest_datasets(group_folder_path, api_key):
    for artifact in os.listdir(group_folder_path):
        artifact_path = os.path.join(group_folder_path, artifact)
        if os.path.isdir(artifact_path):
            pattern = re.compile(r'^\d{4}.\d{2}.\d{2}$')
            date_dirs = [dir_name for dir_name in os.listdir(artifact_path)
                         if os.path.isdir(os.path.join(artifact_path, dir_name))
                         and pattern.match(dir_name)]
            date_dirs.sort(key=lambda date: datetime.strptime(date, '%Y.%m.%d'), reverse=True)
            if date_dirs:
                latest_dataset_path = os.path.join(artifact_path, date_dirs[0])
                json_files = [file for file in os.listdir(artifact_path) if file.endswith('.json')]
                if json_files:
                    json_file_path = os.path.join(artifact_path, json_files[0])
                    print(construct_string_from_json(json_file_path, latest_dataset_path, api_key))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('group_folder_path', type=str)
    parser.add_argument('apikey', type=str)

    args = parser.parse_args()

    process_latest_datasets(args.group_folder_path, args.apikey)

persondata.json

{
    "title": "persondata dataset 2022.12.01",
    "description": "help needed",
    "abstract": "help needed",
    "license": "http://purl.oclc.org/NET/rdflicense/cc-by3.0"
}

To run the script use command python3 construct_command.py /path/generic api_key