src/dataset.py

from __future__ import annotations

import json
from pathlib import Path
from typing import Any


def load_demo_cases(path: Path) -> list[dict[str, Any]]:
    with path.open("r", encoding="utf-8") as file:
        return [json.loads(line) for line in file if line.strip()]


def get_demo_case(cases: list[dict[str, Any]], case_id: str) -> dict[str, Any]:
    for case in cases:
        if case.get("case_id") == case_id:
            return case
    available = ", ".join(case["case_id"] for case in cases)
    raise KeyError(f"Unknown case_id '{case_id}'. Available case IDs: {available}")


def resolve_demo_image_path(raw_path: str, dataset_root: Path) -> Path:
    return dataset_root / raw_path.lstrip("/")


def resolve_case_images(case: dict[str, Any], dataset_root: Path) -> list[Path]:
    raw_paths = case.get("images", [])
    if not raw_paths:
        raise ValueError(f"Case '{case.get('case_id')}' has no images.")

    resolved_paths: list[Path] = []
    missing_paths: list[Path] = []

    for raw_path in raw_paths:
        resolved = resolve_demo_image_path(raw_path, dataset_root)
        if resolved.exists():
            resolved_paths.append(resolved)
        else:
            missing_paths.append(resolved)

    if missing_paths:
        missing_list = "\n".join(f"  - {path}" for path in missing_paths)
        raise FileNotFoundError(
            f"Resolved demo image(s) not found for case "
            f"'{case.get('case_id')}'. Check --dataset-root.\n{missing_list}"
        )

    return resolved_paths