config_loader.py

import json
import os
from functools import lru_cache
from pathlib import Path


DEFAULT_CONFIG_FILES = (
    "openalex_config.local.json",
)


@lru_cache(maxsize=1)
def load_local_config():
    """Load local config values without overriding existing environment variables."""
    config_file = os.environ.get("OPENALEX_CONFIG_FILE")
    candidate_paths = [Path(config_file)] if config_file else [Path(name) for name in DEFAULT_CONFIG_FILES]

    loaded = {}
    for path in candidate_paths:
        if not path.exists():
            continue

        with path.open("r", encoding="utf-8") as handle:
            loaded = json.load(handle)

        if not isinstance(loaded, dict):
            raise ValueError(f"Config file {path} must contain a JSON object at the top level.")

        for key, value in loaded.items():
            if key not in os.environ and value is not None:
                os.environ[key] = str(value)
        break

    return loaded