from config import FunctionScoreConfig, IndexConfig, QueryConfig, RerankConfig, SPUConfig, SearchConfig
from query.query_parser import QueryParser


class _DummyTranslator:
    def translate(self, text, target_lang, source_lang, scene, model_name):
        return f"{text}-{target_lang}"


def _tokenizer(text):
    return str(text).split()


def test_pure_english_word_token_length_and_script():
    assert QueryParser._is_pure_english_word_token("ab") is False
    assert QueryParser._is_pure_english_word_token("abc") is True
    assert QueryParser._is_pure_english_word_token("wi-fi") is True
    assert QueryParser._is_pure_english_word_token("连衣裙") is False
    assert QueryParser._is_pure_english_word_token("ab12") is False


def _build_config() -> SearchConfig:
    return SearchConfig(
        es_index_name="test_products",
        field_boosts={"title.en": 3.0, "title.zh": 3.0},
        indexes=[IndexConfig(name="default", label="default", fields=["title.en", "title.zh"])],
        query_config=QueryConfig(
            enable_text_embedding=False,
            enable_query_rewrite=False,
            supported_languages=["en", "zh"],
            default_language="zh",
        ),
        function_score=FunctionScoreConfig(),
        rerank=RerankConfig(),
        spu_config=SPUConfig(enabled=False),
    )


def test_parse_adds_en_fields_for_mixed_chinese_query_with_meaningful_english(monkeypatch):
    parser = QueryParser(_build_config(), translator=_DummyTranslator(), tokenizer=_tokenizer)
    monkeypatch.setattr(parser.language_detector, "detect", lambda text: "zh")

    result = parser.parse(
        "法式 dress 连衣裙",
        tenant_id="162",
        generate_vector=False,
        target_languages=["zh", "en"],
    )

    assert result.detected_language == "zh"
    assert result.contains_chinese is True
    assert result.contains_english is True
    assert result.translations == {"en": "法式 dress 连衣裙-en"}
    assert result.query_tokens == ["法式", "dress", "连衣裙"]
    assert not hasattr(result, "query_text_by_lang")
    assert not hasattr(result, "search_langs")


def test_parse_adds_zh_fields_for_english_query_when_cjk_present(monkeypatch):
    parser = QueryParser(_build_config(), translator=_DummyTranslator(), tokenizer=_tokenizer)
    monkeypatch.setattr(parser.language_detector, "detect", lambda text: "en")

    result = parser.parse(
        "red 连衣裙",
        tenant_id="0",
        generate_vector=False,
        target_languages=["en", "zh"],
    )

    assert result.detected_language == "en"
    assert result.contains_chinese is True
    assert result.contains_english is True
    assert result.translations == {"zh": "red 连衣裙-zh"}
    assert result.query_tokens == ["red", "连衣裙"]


def test_parse_waits_for_translation_when_source_in_index_languages(monkeypatch):
    """en 在 index_languages 内时仍应等待并采纳 en->zh 翻译结果（与向量共用预算）。"""
    parser = QueryParser(_build_config(), translator=_DummyTranslator(), tokenizer=_tokenizer)
    monkeypatch.setattr(parser.language_detector, "detect", lambda text: "en")

    result = parser.parse(
        "off shoulder top",
        tenant_id="0",
        generate_vector=False,
        target_languages=["en", "zh"],
    )

    assert result.detected_language == "en"
    assert result.contains_chinese is False
    assert result.contains_english is True
    assert result.translations.get("zh") == "off shoulder top-zh"
    assert not hasattr(result, "source_in_index_languages")