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")