"""Development-only Mock knowledge documents and Milvus importer."""
from __future__ import annotations

from dataclasses import dataclass
from pathlib import Path
from uuid import uuid5, NAMESPACE_URL

from rag.chunk_config import resolve_chunk_config
from rag.chunking import chunk_document
from rag.cleaning import clean_document_text
from rag.document_parser import parse_document
from rag.embedding import embed_texts


_ROOT = Path(__file__).resolve().parent.parent
MOCK_DATA_DIR = _ROOT / "data" / "mock_knowledge"


@dataclass(frozen=True)
class MockDocument:
    doc_id: str
    title: str
    collection: str
    strategy: str
    path: Path


MOCK_DOCUMENTS = (
    MockDocument("mock-faq-001", "常见问题示例", "fin_faq", "qa_pair", MOCK_DATA_DIR / "faq.md"),
    MockDocument("mock-fund-doc-001", "基金产品说明示例", "fin_fund_doc", "chapter_semantic", MOCK_DATA_DIR / "fund_product.md"),
    MockDocument("mock-policy-001", "政策法规示例", "fin_policy", "chapter_semantic", MOCK_DATA_DIR / "policy.md"),
)


async def ingest_mock_documents(milvus_client, *, embedder=embed_texts) -> None:
    """Import all checked-in Markdown samples into their Milvus collections."""
    config = resolve_chunk_config()
    for document in MOCK_DOCUMENTS:
        result = chunk_document(
            clean_document_text(parse_document(document.path)).text,
            document.strategy,
            config=config,
        )
        vectors = await embedder([chunk.text for chunk in result.chunks])
        rows = []
        for index, (chunk, vector) in enumerate(zip(result.chunks, vectors)):
            chunk_id = str(uuid5(NAMESPACE_URL, f"{document.doc_id}:{index}"))
            rows.append(
                {
                    "chunk_id": chunk_id,
                    "doc_id": document.doc_id,
                    "title": document.title,
                    "section_title": chunk.section_title or "",
                    "text": chunk.text,
                    "strategy": document.strategy,
                    "vector": vector,
                }
            )
        await milvus_client.insert(collection_name=document.collection, data=rows)