"""
  Translation service for multi-language query support.
  
  Supports DeepL API for high-quality translations.

  
  
  #### 官方文档：
  https://developers.deepl.com/api-reference/translate/request-translation
  #####
  
  

  """
  
  import requests

  import re

  import redis

  from concurrent.futures import ThreadPoolExecutor, Future

  from datetime import timedelta

  from typing import Dict, List, Optional, Union

  import logging
  
  logger = logging.getLogger(__name__)

  # Try to import DEEPL_AUTH_KEY and REDIS_CONFIG, but allow import to fail

  try:

      from config.env_config import DEEPL_AUTH_KEY, REDIS_CONFIG

  except ImportError:
      DEEPL_AUTH_KEY = None

      REDIS_CONFIG = {}

  
  class Translator:
      """Multi-language translator using DeepL API."""
  

      DEEPL_API_URL = "https://api.deepl.com/v2/translate"  # Pro tier

  
      # Language code mapping
      LANG_CODE_MAP = {
          'zh': 'ZH',
          'en': 'EN',
          'ru': 'RU',
          'ar': 'AR',
          'ja': 'JA',
          'es': 'ES',
          'de': 'DE',
          'fr': 'FR',
          'it': 'IT',
          'pt': 'PT',
      }
  
      def __init__(
          self,
          api_key: Optional[str] = None,
          use_cache: bool = True,

          timeout: int = 10,
          glossary_id: Optional[str] = None,
          translation_context: Optional[str] = None

      ):
          """
          Initialize translator.
  
          Args:

              api_key: DeepL API key (or None to use from config/env)

              use_cache: Whether to cache translations
              timeout: Request timeout in seconds

              glossary_id: DeepL glossary ID for custom terminology (optional)
              translation_context: Context hint for translation (e.g., "e-commerce", "product search")

          """

          # Get API key from config if not provided

          if api_key is None and DEEPL_AUTH_KEY:
              api_key = DEEPL_AUTH_KEY

          self.api_key = api_key
          self.timeout = timeout
          self.use_cache = use_cache

          self.glossary_id = glossary_id
          self.translation_context = translation_context or "e-commerce product search"

          # Initialize Redis cache if enabled

          if use_cache:

              try:
                  self.redis_client = redis.Redis(
                      host=REDIS_CONFIG.get('host', 'localhost'),
                      port=REDIS_CONFIG.get('port', 6479),
                      password=REDIS_CONFIG.get('password'),
                      decode_responses=True,  # Return str instead of bytes
                      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
                  self.redis_client.ping()
                  self.expire_time = timedelta(days=REDIS_CONFIG.get('translation_cache_expire_days', 360))
                  self.cache_prefix = REDIS_CONFIG.get('translation_cache_prefix', 'trans')
                  logger.info("Redis cache initialized for translations")
              except Exception as e:
                  logger.warning(f"Failed to initialize Redis cache: {e}, falling back to no cache")
                  self.redis_client = None
                  self.cache = None

          else:

              self.redis_client = None

              self.cache = None

          
          # Thread pool for async translation
          self.executor = ThreadPoolExecutor(max_workers=2, thread_name_prefix="translator")

  
      def translate(
          self,
          text: str,
          target_lang: str,

          source_lang: Optional[str] = None,

          context: Optional[str] = None,
          prompt: Optional[str] = None

      ) -> Optional[str]:
          """

          Translate text to target language (synchronous mode).

  
          Args:
              text: Text to translate
              target_lang: Target language code ('zh', 'en', 'ru', etc.)
              source_lang: Source language code (optional, auto-detect if None)

              context: Additional context for translation (overrides default context)

              prompt: Translation prompt/instruction (optional, for better translation quality)

  
          Returns:
              Translated text or None if translation fails
          """
          if not text or not text.strip():
              return text
  
          # Normalize language codes
          target_lang = target_lang.lower()
          if source_lang:
              source_lang = source_lang.lower()
  

          # Optimization: Skip translation if not needed
          if target_lang == 'en' and self._is_english_text(text):

              logger.info(f"[Translator] Text is already English, skipping translation: '{text[:50]}...'")

              return text
          
          if target_lang == 'zh' and (self._contains_chinese(text) or self._is_pure_number(text)):

              logger.info(
                  f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
                  f"Source language: {source_lang or 'auto'} | Result: Skip translation (contains Chinese or pure number)"
              )

              return text
  

          # Use provided context or default context
          translation_context = context or self.translation_context

          
          # Build cache key (include prompt in cache key if provided)
          cache_key_parts = [source_lang or 'auto', target_lang, translation_context]
          if prompt:
              cache_key_parts.append(prompt)
          cache_key_parts.append(text)
          cache_key = ':'.join(cache_key_parts)
  
          # Check cache (include context and prompt in cache key for accuracy)

          if self.use_cache and self.redis_client:
              cached = self._get_cached_translation_redis(text, target_lang, source_lang, translation_context, prompt)

              if cached:

                  logger.info(

                      f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
                      f"Source language: {source_lang or 'auto'} | Result: '{cached}' | Source: Cache hit"

                  )

                  return cached
  
          # If no API key, return mock translation (for testing)
          if not self.api_key:

              logger.info(
                  f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
                  f"Source language: {source_lang or 'auto'} | Result: '{text}' | Source: Mock mode (no API key)"
              )

              return text
  

          # Translate using DeepL (Pro endpoint only, no free fallback)
          logger.info(

              f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
              f"Source language: {source_lang or 'auto'} | Context: {translation_context} | "
              f"Prompt: {'yes' if prompt else 'no'} | Status: Starting translation"

          )

          result = self._translate_deepl(text, target_lang, source_lang, translation_context, prompt)

          # If still failed, return original text with warning
          if result is None:

              logger.warning(
                  f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
                  f"Source language: {source_lang or 'auto'} | Result: '{text}' | Status: Translation failed, returning original"
              )

              result = text

          else:
              logger.info(
                  f"[Translator] Translation request | Original text: '{text}' | Target language: {target_lang} | "
                  f"Source language: {source_lang or 'auto'} | Result: '{result}' | Status: Translation successful"
              )

          # Cache result

          if result and self.use_cache and self.redis_client:
              self._set_cached_translation_redis(text, target_lang, result, source_lang, translation_context, prompt)

  
          return result
  
      def _translate_deepl(
          self,
          text: str,
          target_lang: str,

          source_lang: Optional[str],

          context: Optional[str] = None,
          prompt: Optional[str] = None

      ) -> Optional[str]:

          """
          Translate using DeepL API with context and glossary support.
          
          Args:
              text: Text to translate
              target_lang: Target language code
              source_lang: Source language code (optional)
              context: Context hint for translation (e.g., "e-commerce product search")
          """

          # Map to DeepL language codes
          target_code = self.LANG_CODE_MAP.get(target_lang, target_lang.upper())
  
          headers = {
              "Authorization": f"DeepL-Auth-Key {self.api_key}",
              "Content-Type": "application/json",
          }
  

          # Use prompt as context parameter for DeepL API (not as text prefix)
          # According to DeepL API: context is "Additional context that can influence a translation but is not translated itself"
          # If prompt is provided, use it as context; otherwise use the default context
          api_context = prompt if prompt else context
          

          # For e-commerce, add context words to help DeepL understand the domain
          # This is especially important for single-word ambiguous terms like "车" (car vs rook)

          text_to_translate, needs_extraction = self._add_ecommerce_context(text, source_lang, api_context)

          payload = {

              "text": [text_to_translate],

              "target_lang": target_code,
          }
  
          if source_lang:
              source_code = self.LANG_CODE_MAP.get(source_lang, source_lang.upper())
              payload["source_lang"] = source_code
  

          # Add context parameter (prompt or default context)
          # Context influences translation but is not translated itself
          if api_context:
              payload["context"] = api_context
  

          # Add glossary if configured
          if self.glossary_id:
              payload["glossary_id"] = self.glossary_id
  

          # Note: DeepL API v2 supports "context" parameter for additional context
          # that influences translation but is not translated itself.
          # We use prompt as context parameter when provided.

          try:
              response = requests.post(
                  self.DEEPL_API_URL,
                  headers=headers,
                  json=payload,
                  timeout=self.timeout
              )
  
              if response.status_code == 200:
                  data = response.json()
                  if "translations" in data and len(data["translations"]) > 0:

                      translated_text = data["translations"][0]["text"]
                      # If we added context, extract just the term from the result
                      if needs_extraction:
                          translated_text = self._extract_term_from_translation(
                              translated_text, text, target_code
                          )

                      logger.debug(
                          f"[Translator] DeepL API response success | Original text: '{text}' | Target language: {target_code} | "
                          f"Translation result: '{translated_text}'"
                      )

                      return translated_text

              else:

                  logger.error(
                      f"[Translator] DeepL API error | Original text: '{text}' | Target language: {target_code} | "
                      f"Status code: {response.status_code} | Error message: {response.text}"
                  )

                  return None
  
          except requests.Timeout:

              logger.warning(
                  f"[Translator] DeepL API request timeout | Original text: '{text}' | Target language: {target_code} | "
                  f"Timeout: {self.timeout}s"
              )

              return None
          except Exception as e:

              logger.error(
                  f"[Translator] DeepL API request exception | Original text: '{text}' | Target language: {target_code} | "
                  f"Error: {e}", exc_info=True
              )

              return None
  

      # NOTE: _translate_deepl_free is intentionally not implemented.
      # We do not support automatic fallback to the free endpoint, to avoid
      # mixing Pro keys with https://api-free.deepl.com and related 403 errors.

      def translate_multi(
          self,
          text: str,
          target_langs: List[str],

          source_lang: Optional[str] = None,

          context: Optional[str] = None,

          async_mode: bool = True,
          prompt: Optional[str] = None

      ) -> Dict[str, Optional[str]]:
          """
          Translate text to multiple target languages.

          
          In async_mode=True (default):
          - Returns cached translations immediately if available

          - For translations that can be optimized (e.g., pure numbers, already in target language),
            returns result immediately via synchronous call
          - Launches async tasks for other missing translations (non-blocking)
          - Returns None for missing translations that require async processing

          
          In async_mode=False:
          - Waits for all translations to complete (blocking)

  
          Args:
              text: Text to translate
              target_langs: List of target language codes
              source_lang: Source language code (optional)

              context: Context hint for translation (optional)

              async_mode: If True, return cached results immediately and translate missing ones async

              prompt: Translation prompt/instruction (optional)

  
          Returns:

              Dictionary mapping language code to translated text (only cached results in async mode)

          """
          results = {}

          missing_langs = []

          async_langs = []

          
          # First, get cached translations

          for lang in target_langs:

              cached = self._get_cached_translation(text, lang, source_lang, context, prompt)

              if cached is not None:
                  results[lang] = cached
              else:
                  missing_langs.append(lang)
          

          # If async mode and there are missing translations

          if async_mode and missing_langs:

              # Check if translation can be optimized (immediate return)

              for lang in missing_langs:

                  target_lang = lang.lower()
                  # Check optimization conditions (same as in translate method)
                  can_optimize = False
                  if target_lang == 'en' and self._is_english_text(text):
                      can_optimize = True
                  elif target_lang == 'zh' and (self._contains_chinese(text) or self._is_pure_number(text)):
                      can_optimize = True
                  
                  if can_optimize:
                      # Can be optimized, call translate synchronously for immediate result
                      results[lang] = self.translate(text, lang, source_lang, context, prompt)
                  else:
                      # Requires actual translation, add to async list
                      async_langs.append(lang)
              
              # Launch async tasks for translations that require actual API calls
              if async_langs:
                  for lang in async_langs:
                      self._translate_async(text, lang, source_lang, context, prompt)
                  # Return None for async translations
                  for lang in async_langs:
                      results[lang] = None

          else:
              # Synchronous mode: wait for all translations
              for lang in missing_langs:

                  results[lang] = self.translate(text, lang, source_lang, context, prompt)

          return results

      def translate_multi_async(
          self,
          text: str,
          target_langs: List[str],
          source_lang: Optional[str] = None,
          context: Optional[str] = None,
          prompt: Optional[str] = None
      ) -> Dict[str, Union[str, Future]]:
          """
          Translate text to multiple target languages asynchronously, returning Futures that can be awaited.
          
          This method returns a dictionary where:
          - If translation is cached, the value is the translation string (immediate)
          - If translation needs to be done, the value is a Future object that can be awaited
          
          Args:
              text: Text to translate
              target_langs: List of target language codes
              source_lang: Source language code (optional)
              context: Context hint for translation (optional)
              prompt: Translation prompt/instruction (optional)
  
          Returns:
              Dictionary mapping language code to either translation string (cached) or Future object
          """
          results = {}
          missing_langs = []
          
          # First, get cached translations
          for lang in target_langs:
              cached = self._get_cached_translation(text, lang, source_lang, context, prompt)
              if cached is not None:
                  results[lang] = cached
              else:
                  missing_langs.append(lang)
          
          # For missing translations, submit async tasks and return Futures
          for lang in missing_langs:
              future = self.executor.submit(
                  self.translate,
                  text,
                  lang,
                  source_lang,
                  context,
                  prompt
              )
              results[lang] = future
          
          return results
      

      def _get_cached_translation(
          self,
          text: str,
          target_lang: str,
          source_lang: Optional[str] = None,

          context: Optional[str] = None,
          prompt: Optional[str] = None

      ) -> Optional[str]:
          """Get translation from cache if available."""

          if not self.redis_client:
              return None
          return self._get_cached_translation_redis(text, target_lang, source_lang, context, prompt)
      
      def _get_cached_translation_redis(
          self,
          text: str,
          target_lang: str,
          source_lang: Optional[str] = None,
          context: Optional[str] = None,
          prompt: Optional[str] = None
      ) -> Optional[str]:
          """Get translation from Redis cache with sliding expiration."""
          if not self.redis_client:

              return None
          

          try:
              # Build cache key: prefix:target_lang:text
              # For simplicity, we use target_lang and text as key
              # Context and prompt are not included in key to maximize cache hits
              cache_key = f"{self.cache_prefix}:{target_lang.upper()}:{text}"
              value = self.redis_client.get(cache_key)
              if value:
                  # Sliding expiration: reset expiration time on access
                  self.redis_client.expire(cache_key, self.expire_time)

                  logger.debug(
                      f"[Translator] Redis cache hit | Original text: '{text}' | Target language: {target_lang} | "
                      f"Cache key: {cache_key} | Translation result: '{value}'"

                  )

                  return value

              logger.debug(
                  f"[Translator] Redis cache miss | Original text: '{text}' | Target language: {target_lang} | "
                  f"Cache key: {cache_key}"
              )

              return None
          except Exception as e:

              logger.error(f"[Translator] Redis error during get translation cache | Original text: '{text}' | Target language: {target_lang} | Error: {e}")

              return None
      
      def _set_cached_translation_redis(
          self,
          text: str,
          target_lang: str,
          translation: str,
          source_lang: Optional[str] = None,
          context: Optional[str] = None,
          prompt: Optional[str] = None
      ) -> None:
          """Store translation in Redis cache."""
          if not self.redis_client:
              return
          
          try:
              cache_key = f"{self.cache_prefix}:{target_lang.upper()}:{text}"
              self.redis_client.setex(cache_key, self.expire_time, translation)

              logger.debug(
                  f"[Translator] Redis cache write | Original text: '{text}' | Target language: {target_lang} | "
                  f"Cache key: {cache_key} | Translation result: '{translation}'"

              )

          except Exception as e:

              logger.error(
                  f"[Translator] Redis cache write failed | Original text: '{text}' | Target language: {target_lang} | "
                  f"Error: {e}"
              )

      
      def _translate_async(
          self,
          text: str,
          target_lang: str,
          source_lang: Optional[str] = None,

          context: Optional[str] = None,
          prompt: Optional[str] = None

      ):
          """Launch async translation task."""
          def _do_translate():
              try:

                  result = self.translate(text, target_lang, source_lang, context, prompt)

                  if result:
                      logger.debug(f"Async translation completed: {text} -> {target_lang}: {result}")
              except Exception as e:
                  logger.warning(f"Async translation failed: {text} -> {target_lang}: {e}")
          
          self.executor.submit(_do_translate)

      def _add_ecommerce_context(
          self,
          text: str,
          source_lang: Optional[str],
          context: Optional[str]
      ) -> tuple:
          """
          Add e-commerce context to text for better disambiguation.
          
          For single-word ambiguous Chinese terms, we add context words that help
          DeepL understand this is an e-commerce/product search context.
          
          Args:
              text: Original text to translate
              source_lang: Source language code
              context: Context hint
              
          Returns:
              Tuple of (text_with_context, needs_extraction)
              - text_with_context: Text to send to DeepL
              - needs_extraction: Whether we need to extract the term from the result
          """
          # Only apply for e-commerce context and Chinese source
          if not context or "e-commerce" not in context.lower():
              return text, False
              
          if not source_lang or source_lang.lower() != 'zh':
              return text, False
              
          # For single-word queries, add context to help disambiguation
          text_stripped = text.strip()
          if len(text_stripped.split()) == 1 and len(text_stripped) <= 2:
              # Common ambiguous Chinese e-commerce terms like "车" (car vs rook)
              # We add a context phrase: "购买 [term]" (buy [term]) or "商品 [term]" (product [term])
              # This helps DeepL understand the e-commerce context
              # We'll need to extract just the term from the translation result
              context_phrase = f"购买 {text_stripped}"
              return context_phrase, True
          
          # For multi-word queries, DeepL usually has enough context
          return text, False
  
      def _extract_term_from_translation(
          self,
          translated_text: str,
          original_text: str,
          target_lang_code: str
      ) -> str:
          """
          Extract the actual term from a translation that included context.
          
          For example, if we translated "购买 车" (buy car) and got "buy car",
          we want to extract just "car".
          
          Args:
              translated_text: Full translation result
              original_text: Original single-word query
              target_lang_code: Target language code (EN, ZH, etc.)
              
          Returns:
              Extracted term or original translation if extraction fails
          """
          # For English target, try to extract the last word (the actual term)
          if target_lang_code == "EN":
              words = translated_text.strip().split()
              if len(words) > 1:
                  # Usually the last word is the term we want
                  # But we need to be smart - if it's "buy car", we want "car"
                  # Common context words to skip: buy, purchase, product, item, etc.
                  context_words = {"buy", "purchase", "product", "item", "commodity", "goods"}
                  # Try to find the term (not a context word)
                  for word in reversed(words):
                      word_lower = word.lower().rstrip('.,!?;:')
                      if word_lower not in context_words:
                          return word_lower
                  # If all words are context words, return the last one
                  return words[-1].lower().rstrip('.,!?;:')
          
          # For other languages or if extraction fails, return as-is
          # The user can configure a glossary for better results
          return translated_text
  

      def translate_for_indexing(
          self,
          text: str,
          shop_language: str,
          source_lang: Optional[str] = None,
          context: Optional[str] = None,

          prompt: Optional[str] = None,
          translate_to_en: bool = True,
          translate_to_zh: bool = True,

      ) -> Dict[str, Optional[str]]:
          """

          Translate text for indexing based on shop language and tenant configuration.

          Translation behavior:
          - If translate_to_zh=True and shop language is not 'zh', translate to Chinese (zh)
          - If translate_to_en=True and shop language is not 'en', translate to English (en)
          - If both flags are False, no translation is performed (returns None for both)

          
          Args:
              text: Text to translate
              shop_language: Shop's configured language (e.g., 'zh', 'en', 'ru')
              source_lang: Source language code (optional, auto-detect if None)
              context: Additional context for translation (optional)
              prompt: Translation prompt/instruction (optional)

              translate_to_en: Whether to translate to English (from tenant_config)
              translate_to_zh: Whether to translate to Chinese (from tenant_config)

              
          Returns:

              Dictionary with 'zh' and 'en' keys containing translated text (or None if not needed/not enabled)
              Example: {'zh': '中文翻译', 'en': 'English translation'} or {'zh': None, 'en': None}

          """
          if not text or not text.strip():
              return {'zh': None, 'en': None}
          
          # Skip translation for symbol-only queries
          if re.match(r'^[\d\s_-]+$', text):
              logger.info(f"[Translator] Skip translation for symbol-only query: '{text}'")
              return {'zh': None, 'en': None}
          
          results = {'zh': None, 'en': None}
          shop_lang_lower = shop_language.lower() if shop_language else ""
          

          # Determine which languages need translation based on tenant configuration

          targets = []

          if translate_to_zh and "zh" not in shop_lang_lower:

              targets.append("zh")

          if translate_to_en and "en" not in shop_lang_lower:

              targets.append("en")
          
          # If shop language is already zh and en, no translation needed
          if not targets:
              # Use original text for both languages
              if "zh" in shop_lang_lower:
                  results['zh'] = text
              if "en" in shop_lang_lower:
                  results['en'] = text
              return results
          
          # Translate to each target language
          for target_lang in targets:
              # Check cache first
              cached = self._get_cached_translation_redis(text, target_lang, source_lang, context, prompt)
              if cached:
                  results[target_lang] = cached
                  logger.debug(f"[Translator] Cache hit for indexing: '{text}' -> {target_lang}: {cached}")
                  continue
              
              # Translate synchronously for indexing (we need the result immediately)
              translated = self.translate(
                  text,
                  target_lang=target_lang,
                  source_lang=source_lang or shop_language,
                  context=context,
                  prompt=prompt
              )
              results[target_lang] = translated
          
          return results
  

      def get_translation_needs(
          self,
          detected_lang: str,
          supported_langs: List[str]
      ) -> List[str]:
          """
          Determine which languages need translation.
  
          Args:
              detected_lang: Detected query language
              supported_langs: List of supported languages
  
          Returns:
              List of language codes to translate to
          """
          # If detected language is in supported list, translate to others
          if detected_lang in supported_langs:

              return [lang for lang in supported_langs if detected_lang != lang]

  
          # Otherwise, translate to all supported languages
          return supported_langs

      
      def _is_english_text(self, text: str) -> bool:
          """
          Check if text is primarily English (ASCII letters, numbers, common punctuation).
          
          Args:
              text: Text to check
              
          Returns:
              True if text appears to be English
          """
          if not text or not text.strip():
              return True
          
          # Remove whitespace and common punctuation
          text_clean = re.sub(r'[\s\.,!?;:\-\'\"\(\)\[\]{}]', '', text)
          if not text_clean:
              return True
          
          # Check if all remaining characters are ASCII (letters, numbers)
          # This is a simple heuristic: if most characters are ASCII, it's likely English
          ascii_count = sum(1 for c in text_clean if ord(c) < 128)
          ratio = ascii_count / len(text_clean) if text_clean else 0
          
          # If more than 80% are ASCII characters, consider it English
          return ratio > 0.8
      
      def _contains_chinese(self, text: str) -> bool:
          """
          Check if text contains Chinese characters (Han characters).
          
          Args:
              text: Text to check
              
          Returns:
              True if text contains Chinese characters
          """
          if not text:
              return False
          
          # Check for Chinese characters (Unicode range: \u4e00-\u9fff)
          chinese_pattern = re.compile(r'[\u4e00-\u9fff]')
          return bool(chinese_pattern.search(text))
      
      def _is_pure_number(self, text: str) -> bool:
          """
          Check if text is purely numeric (digits, possibly with spaces, dots, commas).
          
          Args:
              text: Text to check
              
          Returns:
              True if text is purely numeric
          """
          if not text or not text.strip():
              return False
          
          # Remove whitespace, dots, commas (common number separators)
          text_clean = re.sub(r'[\s\.,]', '', text.strip())
          if not text_clean:
              return False
          
          # Check if all remaining characters are digits
          return text_clean.isdigit()