from __future__ import annotations

from typing import Any, Dict, List

import pandas as pd

from indexer.document_transformer import SPUDocumentTransformer


def test_fill_llm_attributes_batch_calls_analyze_in_batches(monkeypatch):
    seen_calls: List[Dict[str, Any]] = []

    def _fake_analyze_products(products, target_lang="zh", batch_size=None, tenant_id=None):
        # should always request batch_size=20 and pass full list; internal splitter handles >20
        seen_calls.append(
            {
                "n": len(products),
                "target_lang": target_lang,
                "batch_size": batch_size,
                "tenant_id": tenant_id,
            }
        )
        return [
            {
                "id": p["id"],
                "lang": target_lang,
                "title_input": p["title"],
                "tags": "t1,t2",
                "anchor_text": f"{target_lang}-anchor-{p['id']}",
            }
            for p in products
        ]

    import indexer.document_transformer as doc_tr

    monkeypatch.setattr(doc_tr, "analyze_products", _fake_analyze_products)

    transformer = SPUDocumentTransformer(
        category_id_to_name={},
        searchable_option_dimensions=[],
        tenant_config={"index_languages": ["zh", "en"], "primary_language": "zh"},
        translator=None,
        encoder=None,
        enable_title_embedding=False,
        image_encoder=None,
        enable_image_embedding=False,
    )

    docs: List[Dict[str, Any]] = []
    rows: List[pd.Series] = []
    for i in range(45):
        docs.append({"tenant_id": "162", "spu_id": str(i)})
        rows.append(pd.Series({"id": i, "title": f"title-{i}"}))

    transformer.fill_llm_attributes_batch(docs, rows)

    # called once per language, with full list; analyze_products handles splitting
    assert seen_calls == [
        {"n": 45, "target_lang": "zh", "batch_size": 20, "tenant_id": "162"},
        {"n": 45, "target_lang": "en", "batch_size": 20, "tenant_id": "162"},
    ]

    assert docs[0]["qanchors"]["zh"] == "zh-anchor-0"
    assert docs[0]["qanchors"]["en"] == "en-anchor-0"