"""

  Text embedding encoder using network service.

  Generates embeddings via HTTP API service (default localhost:6005).

  """
  
  import sys

  import requests

  import time
  import threading

  import numpy as np

  import pickle
  import redis

  import os

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

  import logging

  
  logger = logging.getLogger(__name__)

  from config.services_config import get_embedding_base_url
  

  # Try to import REDIS_CONFIG, but allow import to fail
  try:
      from config.env_config import REDIS_CONFIG
  except ImportError:
      REDIS_CONFIG = {}
  

  
  class BgeEncoder:
      """

      Singleton text encoder using network service.

      Thread-safe singleton pattern ensures only one instance exists.

      """
      _instance = None
      _lock = threading.Lock()
  

      def __new__(cls, service_url: Optional[str] = None):

          with cls._lock:
              if cls._instance is None:
                  cls._instance = super(BgeEncoder, cls).__new__(cls)

                  resolved_url = service_url or os.getenv("EMBEDDING_SERVICE_URL") or get_embedding_base_url()

                  logger.info(f"Creating BgeEncoder instance with service URL: {resolved_url}")
                  cls._instance.service_url = resolved_url
                  cls._instance.endpoint = f"{resolved_url}/embed/text"

                  
                  # Initialize Redis cache
                  try:
                      cls._instance.redis_client = redis.Redis(
                          host=REDIS_CONFIG.get('host', 'localhost'),
                          port=REDIS_CONFIG.get('port', 6479),
                          password=REDIS_CONFIG.get('password'),
                          decode_responses=False,  # Keep binary data as is
                          socket_timeout=REDIS_CONFIG.get('socket_timeout', 1),
                          socket_connect_timeout=REDIS_CONFIG.get('socket_connect_timeout', 1),
                          retry_on_timeout=REDIS_CONFIG.get('retry_on_timeout', False),
                          health_check_interval=10  # 避免复用坏连接
                      )
                      # Test connection
                      cls._instance.redis_client.ping()
                      cls._instance.expire_time = timedelta(days=REDIS_CONFIG.get('cache_expire_days', 180))
                      logger.info("Redis cache initialized for embeddings")
                  except Exception as e:
                      logger.warning(f"Failed to initialize Redis cache for embeddings: {e}, continuing without cache")
                      cls._instance.redis_client = None

          return cls._instance
  

      def _call_service(self, request_data: List[str]) -> List[Any]:

          """
          Call the embedding service API.
  
          Args:

              request_data: List of texts

  
          Returns:

              List of embeddings (list[float]) or nulls (None), aligned to input order

          """
          try:
              response = requests.post(
                  self.endpoint,
                  json=request_data,
                  timeout=60
              )
              response.raise_for_status()
              return response.json()
          except requests.exceptions.RequestException as e:
              logger.error(f"BgeEncoder service request failed: {e}", exc_info=True)
              raise
  

      def encode(
          self,
          sentences: Union[str, List[str]],
          normalize_embeddings: bool = True,

          device: str = 'cpu',

          batch_size: int = 32
      ) -> np.ndarray:
          """

          Encode text into embeddings via network service with Redis caching.

  
          Args:
              sentences: Single string or list of strings to encode

              normalize_embeddings: Whether to normalize embeddings (ignored for service)
              device: Device parameter ignored for service compatibility
              batch_size: Batch size for processing (used for service requests)

  
          Returns:

              numpy array of dtype=object, where each element is either:
              - np.ndarray (valid embedding vector) or
              - None (no embedding available for that text)

          """

          # Convert single string to list
          if isinstance(sentences, str):
              sentences = [sentences]

          # Check cache first

          uncached_indices: List[int] = []
          uncached_texts: List[str] = []

          # Process response
          # Each element can be np.ndarray or None (表示该文本没有可用的向量）
          embeddings: List[Optional[np.ndarray]] = [None] * len(sentences)
  
          for i, text in enumerate(sentences):
              cached = self._get_cached_embedding(text, 'en')  # Use 'en' as default language for title embedding
              if cached is not None:
                  embeddings[i] = cached
              else:
                  uncached_indices.append(i)
                  uncached_texts.append(text)
          
          # Prepare request data for uncached texts (after cache check)

          request_data = list(uncached_texts)

          
          # If there are uncached texts, call service
          if uncached_texts:
              try:
                  # Call service
                  response_data = self._call_service(request_data)
  
                  # Process response
                  for i, text in enumerate(uncached_texts):
                      original_idx = uncached_indices[i]

                      if response_data and i < len(response_data):
                          embedding = response_data[i]
                      else:

                          embedding = None

  
                      if embedding is not None:
                          embedding_array = np.array(embedding, dtype=np.float32)
                          # Validate embedding from service - if invalid, treat as no result
                          if self._is_valid_embedding(embedding_array):
                              embeddings[original_idx] = embedding_array
                              # Cache the embedding
                              self._set_cached_embedding(text, 'en', embedding_array)

                          else:

                              logger.warning(
                                  f"Invalid embedding returned from service for text {original_idx} "
                                  f"(contains NaN/Inf or invalid shape), treating as no result. "
                                  f"Text preview: {text[:50]}..."
                              )

                              embeddings[original_idx] = None

                      else:

                          logger.warning(f"No embedding found for text {original_idx}: {text[:50]}...")

                          embeddings[original_idx] = None

  
              except Exception as e:
                  logger.error(f"Failed to encode texts: {e}", exc_info=True)

                  # 出错时不要生成兜底全零向量，保持为 None
                  pass

          # 返回 numpy 数组（dtype=object），元素为 np.ndarray 或 None
          return np.array(embeddings, dtype=object)

  
      def encode_batch(
          self,
          texts: List[str],
          batch_size: int = 32,

          device: str = 'cpu'

      ) -> np.ndarray:
          """

          Encode a batch of texts efficiently via network service.

  
          Args:
              texts: List of texts to encode
              batch_size: Batch size for processing

              device: Device parameter ignored for service compatibility

  
          Returns:
              numpy array of embeddings
          """
          return self.encode(texts, batch_size=batch_size, device=device)

      
      def _get_cache_key(self, query: str, language: str) -> str:
          """Generate a cache key for the query"""
          return f"embedding:{language}:{query}"
      

      def _is_valid_embedding(self, embedding: np.ndarray) -> bool:
          """
          Check if embedding is valid (not None, correct shape, no NaN/Inf).
          
          Args:
              embedding: Embedding array to validate
              
          Returns:
              True if valid, False otherwise
          """
          if embedding is None:
              return False
          if not isinstance(embedding, np.ndarray):
              return False
          if embedding.size == 0:
              return False
          # Check for NaN or Inf values
          if not np.isfinite(embedding).all():
              return False
          return True
      

      def _get_cached_embedding(self, query: str, language: str) -> Optional[np.ndarray]:
          """Get embedding from cache if exists (with sliding expiration)"""
          if not self.redis_client:
              return None
              
          try:
              cache_key = self._get_cache_key(query, language)
              cached_data = self.redis_client.get(cache_key)
              if cached_data:

                  embedding = pickle.loads(cached_data)
                  # Validate cached embedding - if invalid, ignore cache and return None
                  if self._is_valid_embedding(embedding):
                      logger.debug(f"Cache hit for embedding: {query}")
                      # Update expiration time on access (sliding expiration)
                      self.redis_client.expire(cache_key, self.expire_time)
                      return embedding
                  else:
                      logger.warning(
                          f"Invalid embedding found in cache (contains NaN/Inf or invalid shape), "
                          f"ignoring cache for query: {query[:50]}..."
                      )
                      # Delete invalid cache entry
                      try:
                          self.redis_client.delete(cache_key)
                      except Exception as e:
                          logger.debug(f"Failed to delete invalid cache entry: {e}")
                      return None

              return None
          except Exception as e:
              logger.error(f"Error retrieving embedding from cache: {e}")
              return None
      
      def _set_cached_embedding(self, query: str, language: str, embedding: np.ndarray) -> bool:
          """Store embedding in cache"""
          if not self.redis_client:
              return False
              
          try:
              cache_key = self._get_cache_key(query, language)
              serialized_data = pickle.dumps(embedding)
              self.redis_client.setex(
                  cache_key,
                  self.expire_time,
                  serialized_data
              )
              logger.debug(f"Successfully cached embedding for query: {query}")
              return True
          except (redis.exceptions.BusyLoadingError, redis.exceptions.ConnectionError, 
                  redis.exceptions.TimeoutError, redis.exceptions.RedisError) as e:
              logger.warning(f"Redis error storing embedding in cache: {e}")
              return False
          except Exception as e:
              logger.error(f"Error storing embedding in cache: {e}")
              return False