query/query_parser.py

"""
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,
        query_text_by_lang: Optional[Dict[str, str]] = None,
        search_langs: Optional[List[str]] = None,
        index_languages: Optional[List[str]] = None,
        source_in_index_languages: bool = True,
    ):
        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 []
        self.query_text_by_lang = query_text_by_lang or {}
        self.search_langs = search_langs or []
        self.index_languages = index_languages or []
        self.source_in_index_languages = bool(source_in_index_languages)
    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
        }
        result["query_text_by_lang"] = self.query_text_by_lang
        result["search_langs"] = self.search_langs
        result["index_languages"] = self.index_languages
        result["source_in_index_languages"] = self.source_in_index_languages
        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 = {}
        index_langs = ["en", "zh"]
        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")
            raw_index_langs = tenant_cfg.get("index_languages") or ["en", "zh"]
            index_langs = []
            seen_langs = set()
            for lang in raw_index_langs:
                norm_lang = str(lang or "").strip().lower()
                if not norm_lang or norm_lang in seen_langs:
                    continue
                seen_langs.add(norm_lang)
                index_langs.append(norm_lang)
            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(f"query_{detected_lang}")
                        or self.config.query_config.translation_prompts.get("query_en")
                        or self.config.query_config.translation_prompts.get("default_en")
                        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 language-scoped query plan: source language + available translations
        query_text_by_lang: Dict[str, str] = {}
        if query_text:
            query_text_by_lang[detected_lang] = query_text
        for lang, translated_text in (translations or {}).items():
            if translated_text and str(translated_text).strip():
                query_text_by_lang[str(lang).strip().lower()] = str(translated_text)
        
        source_in_index_languages = detected_lang in index_langs
        ordered_search_langs: List[str] = []
        seen_order = set()
        if detected_lang in query_text_by_lang:
            ordered_search_langs.append(detected_lang)
            seen_order.add(detected_lang)
        for lang in index_langs:
            if lang in query_text_by_lang and lang not in seen_order:
                ordered_search_langs.append(lang)
                seen_order.add(lang)
        for lang in query_text_by_lang.keys():
            if lang not in seen_order:
                ordered_search_langs.append(lang)
                seen_order.add(lang)
        
        if context:
            context.store_intermediate_result("search_langs", ordered_search_langs)
            context.store_intermediate_result("query_text_by_lang", query_text_by_lang)
        # 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,
            query_text_by_lang=query_text_by_lang,
            search_langs=ordered_search_langs,
            index_languages=index_langs,
            source_in_index_languages=source_in_index_languages,
        )
        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()