""" 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()