"""TriviaQA (official source: mandarjoshi/trivia_qa, rc.wikipedia config).

rc.wikipedia = reading-comprehension WITH the Wikipedia evidence document
(open-book, aligned with evalscope's default); rc.nocontext is the
closed-book variant (pass --subset rc.nocontext).
"""

from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec


@register_dataset(
    DatasetSpec(
        name='trivia_qa',
        source='mandarjoshi/trivia_qa',  # official: https://huggingface.co/datasets/mandarjoshi/trivia_qa
        subset='rc.wikipedia',           # open-book (evalscope parity); --subset rc.nocontext for closed
        split='validation',
        task_type='qa',
        tags=['knowledge', 'openqa'],
        description='TriviaQA with Wikipedia evidence (open-book); any alias counts.',
    )
)
def trivia_qa():
    def to_sample(record: dict) -> Sample:
        answer = record['answer']  # {'value': ..., 'aliases': [...], ...}
        targets = [answer['value']] + list(answer.get('aliases') or [])
        # open-book: the Wikipedia evidence document (runner prepends it via
        # metadata['context'] when assembling the prompt)
        wiki = ''
        entity = record.get('entity_pages') or {}
        for doc in (entity.get('wiki_content') or [])[:1]:
            wiki = doc or ''
            break
        search = record.get('search_results') or {}
        if not wiki:
            wiki = '\n'.join((search.get('search_context') or [])[:2])
        return Sample(
            input=record['question'],
            target=targets,  # multi-target: any alias counts
            metadata={'question_id': record.get('question_id'),
                      'context': wiki or None},
        )

    return to_sample