"""
  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 config import SearchConfig, QueryConfig

  from embeddings import BgeEncoder
  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: Search configuration

              text_encoder: Text embedding encoder (lazy loaded if not provided)
              translator: Translator instance (lazy loaded if not provided)
          """
          self.config = config
          self.query_config = config.query_config
          self._text_encoder = text_encoder
          self._translator = translator
  
          # Initialize components
          self.normalizer = QueryNormalizer()
          self.language_detector = LanguageDetector()
          self.rewriter = QueryRewriter(self.query_config.rewrite_dictionary)
  
      @property
      def text_encoder(self) -> BgeEncoder:
          """Lazy load text encoder."""
          if self._text_encoder is None and self.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.query_config.enable_translation:

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

              self._translator = Translator(
                  api_key=self.query_config.translation_api_key,

                  use_cache=True,
                  glossary_id=getattr(self.query_config, 'translation_glossary_id', None),
                  translation_context=getattr(self.query_config, 'translation_context', 'e-commerce product search')

              )
          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.query_config.enable_query_rewrite:
              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.query_config.enable_translation:

              try:
                  # Determine target languages for translation
                  # If domain has language_field_mapping, only translate to languages in the mapping
                  # Otherwise, use all supported languages
                  target_langs_for_translation = self.query_config.supported_languages

                  # Check if domain has language_field_mapping
                  domain_config = next(
                      (idx for idx in self.config.indexes if idx.name == domain),
                      None

                  )

                  if domain_config and domain_config.language_field_mapping:
                      # Only translate to languages that exist in the mapping
                      available_languages = set(domain_config.language_field_mapping.keys())
                      target_langs_for_translation = [
                          lang for lang in self.query_config.supported_languages
                          if lang in available_languages
                      ]
                      log_debug(f"域 '{domain}' 有语言字段映射，将翻译到: {target_langs_for_translation}")
  
                  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 = getattr(self.query_config, '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.query_config.enable_text_embedding and
              domain == "default"):  # Only generate vector for default domain

              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()