"""
  Query parser - main module for query processing.
  
  Handles query rewriting, translation, and embedding generation.
  """
  

  from typing import Dict, List, Optional, Any, Union

  import numpy as np

  import logging

  import re
  import hanlp

  from concurrent.futures import Future, ThreadPoolExecutor, as_completed

  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: Optional[str] = None,

          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:

              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,
          tenant_id: Optional[str] = None,
          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)

          # Use default language if detection failed (None or "unknown")
          if not detected_lang or detected_lang == "unknown":
              detected_lang = self.config.query_config.default_language

          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 (with async support and conditional waiting)

          translations = {}

          translation_futures = {}

          try:
              # 根据租户配置决定翻译目标语言
              from config.tenant_config_loader import get_tenant_config_loader
              tenant_loader = get_tenant_config_loader()
              tenant_cfg = tenant_loader.get_tenant_config(tenant_id or "default")
  
              translate_to_zh = bool(tenant_cfg.get("translate_to_zh"))
              translate_to_en = bool(tenant_cfg.get("translate_to_en"))
  
              target_langs_for_translation = []
              if translate_to_zh:
                  target_langs_for_translation.append('zh')
              if translate_to_en:
                  target_langs_for_translation.append('en')
  
              # 如果该租户未开启任何翻译方向，则直接跳过翻译阶段
              if target_langs_for_translation:

                  target_langs = [lang for lang in target_langs_for_translation if detected_lang != lang]

  
                  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)

                      query_prompt = self.config.query_config.translation_prompts.get('query_zh') or \
                                    self.config.query_config.translation_prompts.get('default_zh')

                      
                      # Determine if we need to wait for translation results
                      # If detected_lang is neither 'en' nor 'zh', we must wait for translation
                      need_wait_translation = detected_lang not in ['en', 'zh']
                      
                      if need_wait_translation:
                          # Use async method that returns Futures, so we can wait for results
                          translation_results = self.translator.translate_multi_async(
                              query_text,
                              target_langs,
                              source_lang=detected_lang,
                              context=translation_context,
                              prompt=query_prompt
                          )
                          # Separate cached results and futures
                          for lang, result in translation_results.items():
                              if isinstance(result, Future):
                                  translation_futures[lang] = result
                              else:
                                  translations[lang] = result
                      else:
                          # 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}")

                      if translation_futures:
                          log_debug(f"翻译进行中，等待结果... | 语言: {list(translation_futures.keys())}")

                      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) - async execution

          query_vector = None

          embedding_future = None

          should_generate_embedding = (
              generate_vector and

              self.config.query_config.enable_text_embedding and

              domain == "default" and
              not is_short_query
          )
          

          encoding_executor = None

          if should_generate_embedding:
              try:

                  log_debug("开始生成查询向量（异步）")
                  # Submit encoding task to thread pool for async execution
                  encoding_executor = ThreadPoolExecutor(max_workers=1)
                  embedding_future = encoding_executor.submit(
                      lambda: self.text_encoder.encode([query_text])[0]
                  )

              except Exception as e:

                  error_msg = f"查询向量生成任务提交失败 | 错误: {str(e)}"

                  log_info(error_msg)
                  if context:
                      context.add_warning(error_msg)

                  encoding_executor = None
                  embedding_future = None
          
          # Wait for all async tasks to complete (translation and embedding)
          if translation_futures or embedding_future:
              log_debug("等待异步任务完成...")
              
              # Collect all futures with their identifiers
              all_futures = []
              future_to_lang = {}
              for lang, future in translation_futures.items():
                  all_futures.append(future)
                  future_to_lang[future] = ('translation', lang)
              
              if embedding_future:
                  all_futures.append(embedding_future)
                  future_to_lang[embedding_future] = ('embedding', None)
              
              # Wait for all futures to complete
              for future in as_completed(all_futures):
                  task_type, lang = future_to_lang[future]
                  try:
                      result = future.result()
                      if task_type == 'translation':
                          if result:
                              translations[lang] = result
                              log_info(f"翻译完成 | {lang}: {result}")
                              if context:
                                  context.store_intermediate_result(f'translation_{lang}', result)
                      elif task_type == 'embedding':
                          query_vector = result
                          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:
                      if task_type == 'translation':
                          error_msg = f"翻译失败 | 语言: {lang} | 错误: {str(e)}"
                      else:
                          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)
              
              # Clean up encoding executor
              if encoding_executor:
                  encoding_executor.shutdown(wait=False)
              
              # Update translations in context after all are complete
              if translations and context:
                  context.store_intermediate_result('translations', translations)

  
          # 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()