"""
  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

  import re
  import hanlp

  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",
          keywords: str = "",
          token_count: int = 0,
          is_short_query: bool = False,
          is_long_query: bool = False

      ):
          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

          # Query analysis fields
          self.keywords = keywords
          self.token_count = token_count
          self.is_short_query = is_short_query
          self.is_long_query = is_long_query

  
      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)

          
          # Initialize HanLP components at startup
          logger.info("Initializing HanLP components...")
          self._tok = hanlp.load(hanlp.pretrained.tok.CTB9_TOK_ELECTRA_BASE_CRF)
          self._tok.config.output_spans = True
          self._pos_tag = hanlp.load(hanlp.pretrained.pos.CTB9_POS_ELECTRA_SMALL)
          logger.info("HanLP components initialized")

  
      @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 _extract_keywords(self, query: str) -> str:
          """Extract keywords (nouns with length > 1) from query."""
          tok_result = self._tok(query)
          if not tok_result:
              return ""
          
          words = [x[0] for x in tok_result]
          pos_tags = self._pos_tag(words)
          
          keywords = []
          for word, pos in zip(words, pos_tags):
              if len(word) > 1 and pos.startswith('N'):
                  keywords.append(word)
          
          return " ".join(keywords)
      
      def _get_token_count(self, query: str) -> int:
          """Get token count using HanLP."""
          tok_result = self._tok(query)
          return len(tok_result) if tok_result else 0
      
      def _analyze_query_type(self, query: str, token_count: int) -> tuple:
          """Analyze query type: (is_short_query, is_long_query)."""
          is_quoted = query.startswith('"') and query.endswith('"')
          is_short = is_quoted or ((token_count <= 2 or len(query) <= 4) and ' ' not in query)
          is_long = token_count >= 4
          return is_short, is_long

      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 (async mode - only returns cached results, missing ones translated in background)

          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:

                      # Use e-commerce context for better disambiguation

                      translation_context = self.config.query_config.translation_context
                      # For query translation, we use a general prompt (not language-specific)
                      # Since translate_multi uses same prompt for all languages, we use default
                      query_prompt = self.config.query_config.translation_prompts.get('query_zh') or \
                                    self.config.query_config.translation_prompts.get('default_zh')

                      # Use async mode: returns cached translations immediately, missing ones translated in background

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

                          source_lang=detected_lang,

                          context=translation_context,

                          async_mode=True,
                          prompt=query_prompt

                      )

                      # Filter out None values (missing translations that are being processed async)
                      translations = {k: v for k, v in translations.items() if v is not None}
                      
                      if translations:
                          log_info(f"翻译完成（缓存命中） | 结果: {translations}")
                      else:
                          log_debug(f"翻译未命中缓存，异步翻译中...")
                      

                      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: Query analysis (keywords, token count, query type)
          keywords = self._extract_keywords(query_text)
          token_count = self._get_token_count(query_text)
          is_short_query, is_long_query = self._analyze_query_type(query_text, token_count)
          
          log_debug(f"查询分析 | 关键词: {keywords} | token数: {token_count} | "
                   f"短查询: {is_short_query} | 长查询: {is_long_query}")
          if context:
              context.store_intermediate_result('keywords', keywords)
              context.store_intermediate_result('token_count', token_count)
              context.store_intermediate_result('is_short_query', is_short_query)
              context.store_intermediate_result('is_long_query', is_long_query)
          
          # Stage 6: Text embedding (only for non-short queries)

          query_vector = None

          should_generate_embedding = (
              generate_vector and

              self.config.query_config.enable_text_embedding and

              domain == "default" and
              not is_short_query
          )
          
          if should_generate_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,
              keywords=keywords,
              token_count=token_count,
              is_short_query=is_short_query,
              is_long_query=is_long_query

          )
  

          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()