"""BFCL v3 (Berkeley Function Calling Leaderboard).

Official release: github.com/gorilla-llm/Berkeley-Function-Calling-Leaderboard.
We load the ModelScope mirror (AI-ModelScope/bfcl_v3, parquet) with columns
``id / turns / tools / test_category / ground_truth``. Filter by
``metadata.test_category`` at eval time (simple / irrelevance / multi_turn /
parallel / java / javascript / ...).
"""

import json

from ..sample import ChatMessage, Sample, ToolInfo
from ..registry import register_dataset
from ..spec import DatasetSpec


@register_dataset(
    DatasetSpec(
        name='bfcl_v3',
        source='AI-ModelScope/bfcl_v3',  # ModelScope mirror of the official GitHub data
        split='train',  # the mirror ships a single split
        task_type='fc',
        tags=['function_calling', 'tool_use'],
        description='BFCL v3 function calling (official content, ModelScope mirror).',
        params={'hub': 'modelscope'},
    )
)
def bfcl_v3():
    def _parse(v):
        if isinstance(v, str):
            try:
                return json.loads(v)
            except (ValueError, TypeError):
                return v
        return v

    def to_sample(record: dict) -> Sample:
        messages = []
        for turn in _parse(record.get('turns')) or []:
            messages.extend(turn if isinstance(turn, list) else [turn])
        tools = []
        for t in _parse(record.get('tools')) or []:
            spec = t.get('function') if isinstance(t, dict) and 'function' in t else t
            if isinstance(spec, dict) and spec.get('name'):
                tools.append(ToolInfo(name=spec['name'], description=spec.get('description'),
                                      parameters=spec.get('parameters') or {}))
        return Sample(
            input=[ChatMessage(role=m.get('role', 'user'), content=m['content'] if isinstance(m.get('content'), str)
                               else json.dumps(m['content'], ensure_ascii=False))
                   for m in messages if isinstance(m, dict)] or record.get('id', ''),
            target=json.dumps(_parse(record.get('ground_truth')), ensure_ascii=False)
            if record.get('ground_truth') is not None else '',
            tools=tools or None,
            metadata={
                'id': record.get('id'),
                'test_category': record.get('test_category'),
                'multi_turn': record.get('multi_turn'),
                'language': record.get('language'),
                'functions': _parse(record.get('functions')),
            },
        )

    return to_sample