"""
  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

  from concurrent.futures import Future, ThreadPoolExecutor, as_completed

  from embeddings.text_encoder import TextEmbeddingEncoder

  from config import SearchConfig

  from .language_detector import LanguageDetector

  from providers import create_translation_provider

  from .query_rewriter import QueryRewriter, QueryNormalizer
  

  logger = logging.getLogger(__name__)
  

  try:
      import hanlp  # type: ignore
  except Exception:  # pragma: no cover
      hanlp = None

  
  class ParsedQuery:
      """Container for parsed query results."""
  
      def __init__(
          self,
          original_query: str,

          query_normalized: 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,

          query_tokens: Optional[List[str]] = None

      ):
          self.original_query = original_query

          self.query_normalized = query_normalized
          self.rewritten_query = rewritten_query or query_normalized

          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.query_tokens = query_tokens or []

  
      def to_dict(self) -> Dict[str, Any]:
          """Convert to dictionary representation."""
          result = {
              "original_query": self.original_query,

              "query_normalized": self.query_normalized,

              "rewritten_query": self.rewritten_query,
              "detected_language": self.detected_language,
              "translations": self.translations,

              "domain": self.domain

          }
          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[TextEmbeddingEncoder] = None,

          translator: Optional[Any] = None

      ):
          """
          Initialize query parser.
  
          Args:

              config: SearchConfig instance

              text_encoder: Text embedding encoder (initialized at startup if not provided)
              translator: Translator instance (initialized at startup 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)

          # Optional HanLP components (heavy). If unavailable, fall back to a lightweight tokenizer.
          self._tok = None
          self._pos_tag = None
          if hanlp is not None:
              try:
                  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")
              except Exception as e:
                  logger.warning(f"HanLP init failed, falling back to simple tokenizer: {e}")
                  self._tok = None
                  self._pos_tag = None
          else:
              logger.info("HanLP not installed; using simple tokenizer")

          # Eager initialization (startup-time failure visibility, no lazy init in request path)
          if self.config.query_config.enable_text_embedding and self._text_encoder is None:
              logger.info("Initializing text encoder at QueryParser construction...")
              self._text_encoder = TextEmbeddingEncoder()
          if self._translator is None:
              from config.services_config import get_translation_config
              cfg = get_translation_config()
              logger.info("Initializing translator at QueryParser construction (provider=%s)...", cfg.provider)
              self._translator = create_translation_provider(self.config.query_config)
  

      @property

      def text_encoder(self) -> TextEmbeddingEncoder:

          """Return pre-initialized text encoder."""

          return self._text_encoder
  
      @property

      def translator(self) -> Any:

          """Return pre-initialized translator."""

          return self._translator

  
      def _simple_tokenize(self, text: str) -> List[str]:
          """
          Lightweight tokenizer fallback.
  
          - Groups consecutive CJK chars as a token
          - Groups consecutive latin/digits/underscore/dash as a token
          """
          if not text:
              return []
          pattern = re.compile(r"[\u4e00-\u9fff]+|[A-Za-z0-9_]+(?:-[A-Za-z0-9_]+)*")
          return pattern.findall(text)

      
      def _extract_keywords(self, query: str) -> str:
          """Extract keywords (nouns with length > 1) from query."""

          if self._tok is not None and self._pos_tag is not None:
              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 isinstance(pos, str) and pos.startswith("N"):
                      keywords.append(word)
              return " ".join(keywords)
  
          # Fallback: treat tokens with length > 1 as "keywords"
          tokens = self._simple_tokenize(query)
          keywords = [t for t in tokens if len(t) > 1]

          return " ".join(keywords)
      
      def _get_token_count(self, query: str) -> int:

          """Get token count (HanLP if available, otherwise simple)."""
          if self._tok is not None:
              tok_result = self._tok(query)
              return len(tok_result) if tok_result else 0
          return len(self._simple_tokenize(query))

  
      def _get_query_tokens(self, query: str) -> List[str]:

          """Get token list (HanLP if available, otherwise simple)."""
          if self._tok is not None:
              tok_result = self._tok(query)
              return [x[0] for x in tok_result] if tok_result else []
          return self._simple_tokenize(query)

      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

          active_logger = context.logger if context else logger
          if context and hasattr(context, "logger"):
              context.logger.info(

                  f"Starting query parsing | Original query: '{query}' | Generate vector: {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:

                  active_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:

                  active_logger.debug(msg)

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

          log_debug(f"Normalization completed | '{query}' -> '{normalized}'")

          if context:

              context.store_intermediate_result('query_normalized', 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"Domain extraction | Domain: '{domain}', Query: '{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"Query rewritten | '{query_text}' -> '{rewritten}'")

                  query_text = rewritten

                  if context:
                      context.store_intermediate_result('rewritten_query', rewritten)

                      context.add_warning(f"Query was rewritten: {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"Language detection | Detected language: {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:

              # 根据租户配置的 index_languages 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")

              index_langs = tenant_cfg.get("index_languages") or ["en", "zh"]

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

              if target_langs_for_translation:

                  target_langs = 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)

                      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 not in index_languages, we must wait for translation
                      need_wait_translation = detected_lang not in index_langs

                      
                      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"Translation completed (cache hit) | Query text: '{query_text}' | Results: {translations}")

                      if translation_futures:

                          log_debug(f"Translation in progress, waiting for results... | Query text: '{query_text}' | Languages: {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"Translation failed | Error: {str(e)}"

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

          # Stage 5: Query analysis (keywords, token count, query_tokens)

          keywords = self._extract_keywords(query_text)

          query_tokens = self._get_query_tokens(query_text)
          token_count = len(query_tokens)

          log_debug(f"Query analysis | Keywords: {keywords} | Token count: {token_count} | "

                   f"Query tokens: {query_tokens}")

          if context:
              context.store_intermediate_result('keywords', keywords)
              context.store_intermediate_result('token_count', token_count)

              context.store_intermediate_result('query_tokens', query_tokens)

          # 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"

          )
          

          encoding_executor = None

          if should_generate_embedding:
              try:

                  if self.text_encoder is None:
                      raise RuntimeError("Text embedding is enabled but text encoder is not initialized")

                  log_debug("Starting query vector generation (async)")

                  # Submit encoding task to thread pool for async execution
                  encoding_executor = ThreadPoolExecutor(max_workers=1)

                  def _encode_query_vector() -> Optional[np.ndarray]:
                      arr = self.text_encoder.encode([query_text])
                      if arr is None or len(arr) == 0:
                          return None
                      vec = arr[0]
                      return vec if isinstance(vec, np.ndarray) else None

                  embedding_future = encoding_executor.submit(

                      _encode_query_vector

                  )

              except Exception as e:

                  error_msg = f"Query vector generation task submission failed | Error: {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("Waiting for async tasks to complete...")

              
              # 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"Translation completed | Query text: '{query_text}' | Target language: {lang} | Translation result: '{result}'")

                              if context:
                                  context.store_intermediate_result(f'translation_{lang}', result)
                      elif task_type == 'embedding':
                          query_vector = result

                          if query_vector is not None:

                              log_debug(f"Query vector generation completed | Shape: {query_vector.shape}")

                              if context:
                                  context.store_intermediate_result('query_vector_shape', query_vector.shape)
                          else:

                              log_info("Query vector generation completed but result is None, will process without vector")

                  except Exception as e:
                      if task_type == 'translation':

                          error_msg = f"Translation failed | Language: {lang} | Error: {str(e)}"

                      else:

                          error_msg = f"Query vector generation failed | Error: {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,

              query_normalized=normalized,

              rewritten_query=rewritten,
              detected_language=detected_lang,
              translations=translations,
              query_vector=query_vector,

              domain=domain,
              keywords=keywords,
              token_count=token_count,

              query_tokens=query_tokens

          )
  

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

                  f"Query parsing completed | Original query: '{query}' | Final query: '{rewritten or query_text}' | "
                  f"Language: {detected_lang} | Domain: {domain} | "
                  f"Translation count: {len(translations)} | Vector: {'yes' if query_vector is not None else 'no'}",

                  extra={'reqid': context.reqid, 'uid': context.uid}
              )
          else:

              logger.info(

                  f"Query parsing completed | Original query: '{query}' | Final query: '{rewritten or query_text}' | "
                  f"Language: {detected_lang} | Domain: {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()