src/utils/io_utils.py

import git
import os
from pathlib import Path
from enum import Enum
from typing import List, Tuple, Optional
import pandas as pd
from dataclasses import dataclass
import os 
import yaml
from dataclasses import dataclass
from typing import Dict, Optional, List
import pandas as pd
import yaml
from pyalex import Works
import json


try:
    PROJECT_ROOT = Path(
        git.Repo(Path.cwd(), search_parent_directories=True).working_dir
    )
except git.exc.InvalidGitRepositoryError:
    PROJECT_ROOT = Path.cwd()

os.environ["PROJECT_ROOT"] = str(PROJECT_ROOT)

def get_profile_information() -> Dict[str, str]:
    """
    Get the email and the api_key from the profile file
    """

    # create the path to the profile file 
    profile = f"{PROJECT_ROOT}/user_information/profile.yaml"

    # check if the profile exists and if you are running inside the correct folder
    assert str(PROJECT_ROOT).split("/")[-1] == "MatchingPubs", "Please run this script in the github repo folder "
    assert os.path.exists(profile), "create a profile.yaml with your email (email:) and your api key (api_key:). Go here to get one https://dev.elsevier.com/"

    # load the profile file
    with open(profile, "r") as f:
        profile = yaml.safe_load(f)
    
    # access the email and the api_key
    email = profile["email"]
    api_key = profile["api_key"].strip() # remove the spaces
    return {"email": email, "api_key": api_key}