Download src/engine/data_loader.py from YGCXLab/ux-research-agent-slackbot: direct link, hf CLI and curl.
- Browser
- Download file 2.36 kB
-
https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/src/engine/data_loader.py
- Command line
-
hf download hf://spaces/YGCXLab/ux-research-agent-slackbot/src/engine/data_loader.py
-
curl -L -o data_loader.py https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/src/engine/data_loader.py
2.36 kB
| import json | |
| import logging | |
| from pathlib import Path | |
| from typing import List, Dict, Any, Callable, Optional | |
| from .config import DATA_DIR | |
| logger = logging.getLogger("DataLoader") | |
| INTERNAL_REPORT_PATH = DATA_DIR / 'research_report.json' | |
| BAYMARD_PATH = DATA_DIR / 'baymard_unified_database_v2.json' | |
| NNG_PATH = DATA_DIR / 'nng_articles.json' | |
| def _load_json_file( | |
| path: Path, | |
| label: str, | |
| flatten_fn: Optional[Callable[[Any], List[Dict[str, Any]]]] = None, | |
| ) -> List[Dict[str, Any]]: | |
| """Load a JSON file with standard error handling. | |
| Args: | |
| path: Path to the JSON file. | |
| label: Human-readable label for log messages. | |
| flatten_fn: Optional function to transform raw data into a flat list. | |
| If None, the raw data is returned as-is (must already be a list). | |
| """ | |
| try: | |
| with open(path, 'r', encoding='utf-8') as f: | |
| data = json.load(f) | |
| items = flatten_fn(data) if flatten_fn else data | |
| logger.info(f"Loaded {len(items)} {label} items.") | |
| return items | |
| except FileNotFoundError: | |
| logger.error(f"{label} file not found: {path}") | |
| return [] | |
| except json.JSONDecodeError as e: | |
| logger.error(f"Invalid JSON in {label} file: {e}") | |
| return [] | |
| def _flatten_collections(data: Any) -> List[Dict[str, Any]]: | |
| """Flatten {collections: {name: {guidelines: [...]}}} structure.""" | |
| items: List[Dict[str, Any]] = [] | |
| if 'collections' in data: | |
| for _name, collection_data in data['collections'].items(): | |
| if 'guidelines' in collection_data: | |
| items.extend(collection_data['guidelines']) | |
| return items | |
| def load_internal_research() -> List[Dict[str, Any]]: | |
| """Loads internal research reports from JSON.""" | |
| return _load_json_file(INTERNAL_REPORT_PATH, "internal research") | |
| def load_baymard_guidelines() -> List[Dict[str, Any]]: | |
| """Loads Baymard guidelines from JSON.""" | |
| return _load_json_file(BAYMARD_PATH, "Baymard", flatten_fn=_flatten_collections) | |
| def load_nng_articles() -> List[Dict[str, Any]]: | |
| """Loads NN/g articles from JSON.""" | |
| return _load_json_file(NNG_PATH, "NN/g", flatten_fn=_flatten_collections) | |
| if __name__ == "__main__": | |
| # Test loading | |
| internal = load_internal_research() | |
| baymard = load_baymard_guidelines() | |
| nng = load_nng_articles() | |