"""
  Query parser - main module for query processing.
  
  Handles query rewriting, translation, and embedding generation.
  """
  
  from typing import Dict, List, Optional, Any
  import numpy as np

  import logging

  from embeddings import BgeEncoder

  from config import SearchConfig

  from .language_detector import LanguageDetector
  from .translator import Translator
  from .query_rewriter import QueryRewriter, QueryNormalizer
  

  logger = logging.getLogger(__name__)
  

  
  class ParsedQuery:
      """Container for parsed query results."""
  
      def __init__(
          self,
          original_query: str,
          normalized_query: str,
          rewritten_query: Optional[str] = None,
          detected_language: str = "unknown",
          translations: Dict[str, str] = None,
          query_vector: Optional[np.ndarray] = None,
          domain: str = "default"
      ):
          self.original_query = original_query
          self.normalized_query = normalized_query
          self.rewritten_query = rewritten_query or normalized_query
          self.detected_language = detected_language
          self.translations = translations or {}
          self.query_vector = query_vector
          self.domain = domain
  
      def to_dict(self) -> Dict[str, Any]:
          """Convert to dictionary representation."""
          result = {
              "original_query": self.original_query,
              "normalized_query": self.normalized_query,
              "rewritten_query": self.rewritten_query,
              "detected_language": self.detected_language,
              "translations": self.translations,
              "domain": self.domain,
              "has_vector": self.query_vector is not None
          }
          return result
  
  
  class QueryParser:
      """
      Main query parser that processes queries through multiple stages:
      1. Normalization
      2. Query rewriting (brand/category mappings, synonyms)
      3. Language detection
      4. Translation to target languages
      5. Text embedding generation (for semantic search)
      """
  
      def __init__(
          self,

          config: SearchConfig,

          text_encoder: Optional[BgeEncoder] = None,
          translator: Optional[Translator] = None
      ):
          """
          Initialize query parser.
  
          Args:

              config: SearchConfig instance

              text_encoder: Text embedding encoder (lazy loaded if not provided)
              translator: Translator instance (lazy loaded if not provided)
          """

          self.config = config

          self._text_encoder = text_encoder
          self._translator = translator
  
          # Initialize components
          self.normalizer = QueryNormalizer()
          self.language_detector = LanguageDetector()

          self.rewriter = QueryRewriter(config.query_config.rewrite_dictionary)

  
      @property
      def text_encoder(self) -> BgeEncoder:
          """Lazy load text encoder."""

          if self._text_encoder is None and self.config.query_config.enable_text_embedding:

              logger.info("Initializing text encoder (lazy load)...")

              self._text_encoder = BgeEncoder()
          return self._text_encoder
  
      @property
      def translator(self) -> Translator:
          """Lazy load translator."""

          if self._translator is None and self.config.query_config.enable_translation:

              logger.info("Initializing translator (lazy load)...")

              self._translator = Translator(

                  api_key=self.config.query_config.translation_api_key,

                  use_cache=True,

                  glossary_id=self.config.query_config.translation_glossary_id,
                  translation_context=self.config.query_config.translation_context

              )
          return self._translator
  

      def parse(self, query: str, generate_vector: bool = True, context: Optional[Any] = None) -> ParsedQuery:

          """
          Parse query through all processing stages.
  
          Args:
              query: Raw query string
              generate_vector: Whether to generate query embedding

              context: Optional request context for tracking and logging

  
          Returns:
              ParsedQuery object with all processing results
          """

          # Initialize logger if context provided
          logger = context.logger if context else None
          if logger:
              logger.info(
                  f"开始查询解析 | 原查询: '{query}' | 生成向量: {generate_vector}",
                  extra={'reqid': context.reqid, 'uid': context.uid}
              )
  

          def log_info(msg):

              if context and hasattr(context, 'logger'):
                  context.logger.info(msg, extra={'reqid': context.reqid, 'uid': context.uid})

              else:

                  logger.info(msg)

  
          def log_debug(msg):

              if context and hasattr(context, 'logger'):
                  context.logger.debug(msg, extra={'reqid': context.reqid, 'uid': context.uid})

              else:

                  logger.debug(msg)

  
          # Stage 1: Normalize
          normalized = self.normalizer.normalize(query)

          log_debug(f"标准化完成 | '{query}' -> '{normalized}'")
          if context:
              context.store_intermediate_result('normalized_query', normalized)

  
          # Extract domain if present (e.g., "brand:Nike" -> domain="brand", query="Nike")
          domain, query_text = self.normalizer.extract_domain_query(normalized)

          log_debug(f"域提取 | 域: '{domain}', 查询: '{query_text}'")
          if context:
              context.store_intermediate_result('extracted_domain', domain)
              context.store_intermediate_result('domain_query', query_text)

  
          # Stage 2: Query rewriting
          rewritten = None

          if self.config.query_config.rewrite_dictionary:  # Enable rewrite if dictionary exists

              rewritten = self.rewriter.rewrite(query_text)
              if rewritten != query_text:

                  log_info(f"查询重写 | '{query_text}' -> '{rewritten}'")

                  query_text = rewritten

                  if context:
                      context.store_intermediate_result('rewritten_query', rewritten)
                      context.add_warning(f"查询被重写: {query_text}")

  
          # Stage 3: Language detection
          detected_lang = self.language_detector.detect(query_text)

          log_info(f"语言检测 | 检测到语言: {detected_lang}")
          if context:
              context.store_intermediate_result('detected_language', detected_lang)

  
          # Stage 4: Translation
          translations = {}

          if self.config.query_config.enable_translation:

              try:
                  # Determine target languages for translation

                  # Simplified: always translate to Chinese and English
                  target_langs_for_translation = ['zh', 'en']

  
                  target_langs = self.translator.get_translation_needs(
                      detected_lang,
                      target_langs_for_translation
                  )
  
                  if target_langs:
                      log_info(f"开始翻译 | 源语言: {detected_lang} | 目标语言: {target_langs}")

                      # Use e-commerce context for better disambiguation

                      translation_context = 'e-commerce product search'

                      translations = self.translator.translate_multi(
                          query_text,
                          target_langs,

                          source_lang=detected_lang,
                          context=translation_context

                      )
                      log_info(f"翻译完成 | 结果: {translations}")
                      if context:
                          context.store_intermediate_result('translations', translations)
                          for lang, translation in translations.items():
                              if translation:
                                  context.store_intermediate_result(f'translation_{lang}', translation)
  
              except Exception as e:
                  error_msg = f"翻译失败 | 错误: {str(e)}"
                  log_info(error_msg)
                  if context:
                      context.add_warning(error_msg)

  
          # Stage 5: Text embedding
          query_vector = None
          if (generate_vector and

              self.config.query_config.enable_text_embedding and

              domain == "default"):  # Only generate vector for default domain

              # Get thresholds from config
              chinese_limit = self.config.query_config.embedding_disable_chinese_char_limit
              english_limit = self.config.query_config.embedding_disable_english_word_limit
              
              # Check if embedding should be disabled for short queries
              should_disable_embedding = False
              disable_reason = None
              
              if detected_lang == 'zh':
                  # For Chinese: disable embedding if character count <= threshold
                  char_count = len(query_text.strip())
                  if char_count <= chinese_limit:
                      should_disable_embedding = True
                      disable_reason = f"中文查询字数({char_count}) <= {chinese_limit}，禁用向量搜索"
                      log_info(disable_reason)
                      if context:
                          context.store_intermediate_result('embedding_disabled_reason', disable_reason)
              else:
                  # For English: disable embedding if word count <= threshold
                  word_count = len(query_text.strip().split())
                  if word_count <= english_limit:
                      should_disable_embedding = True
                      disable_reason = f"英文查询单词数({word_count}) <= {english_limit}，禁用向量搜索"
                      log_info(disable_reason)
                      if context:
                          context.store_intermediate_result('embedding_disabled_reason', disable_reason)
              
              if not should_disable_embedding:
                  try:
                      log_debug("开始生成查询向量")
                      query_vector = self.text_encoder.encode([query_text])[0]
                      log_debug(f"查询向量生成完成 | 形状: {query_vector.shape}")
                      if context:
                          context.store_intermediate_result('query_vector_shape', query_vector.shape)
                  except Exception as e:
                      error_msg = f"查询向量生成失败 | 错误: {str(e)}"
                      log_info(error_msg)
                      if context:
                          context.add_warning(error_msg)

  
          # Build result
          result = ParsedQuery(
              original_query=query,
              normalized_query=normalized,
              rewritten_query=rewritten,
              detected_language=detected_lang,
              translations=translations,
              query_vector=query_vector,
              domain=domain
          )
  

          if context and hasattr(context, 'logger'):
              context.logger.info(

                  f"查询解析完成 | 原查询: '{query}' | 最终查询: '{rewritten or query_text}' | "
                  f"语言: {detected_lang} | 域: {domain} | "
                  f"翻译数量: {len(translations)} | 向量: {'是' if query_vector is not None else '否'}",
                  extra={'reqid': context.reqid, 'uid': context.uid}
              )
          else:

              logger.info(
                  f"查询解析完成 | 原查询: '{query}' | 最终查询: '{rewritten or query_text}' | "
                  f"语言: {detected_lang} | 域: {domain}"
              )

          return result
  
      def get_search_queries(self, parsed_query: ParsedQuery) -> List[str]:
          """
          Get list of queries to search (original + translations).
  
          Args:
              parsed_query: Parsed query object
  
          Returns:
              List of query strings to search
          """
          queries = [parsed_query.rewritten_query]
  
          # Add translations
          for lang, translation in parsed_query.translations.items():
              if translation and translation != parsed_query.rewritten_query:
                  queries.append(translation)
  
          return queries
  
      def update_rewrite_rules(self, rules: Dict[str, str]) -> None:
          """
          Update query rewrite rules.
  
          Args:
              rules: Dictionary of pattern -> replacement mappings
          """
          for pattern, replacement in rules.items():
              self.rewriter.add_rule(pattern, replacement)
  
      def get_rewrite_rules(self) -> Dict[str, str]:
          """Get current rewrite rules."""
          return self.rewriter.get_rules()