Source code for lalandre_rag.retrieval.query_utils

"""
Query pre-processing utilities for retrieval.

Small, pure helpers for preparing user queries before they hit the search
backends (BM25, semantic, etc.).
"""

import logging

from lalandre_core.config import get_config

logger = logging.getLogger(__name__)




def truncate_lexical_query(query: str, max_chars: int | None = None) -> str:
    """Truncate *query* for BM25-based search modes.

    Preserves full words by cutting at the last whitespace boundary.
    Returns the original query unchanged if it is short enough.

    If *max_chars* is not provided, uses ``search.max_lexical_query_chars``
    from the central config.
    """
    if max_chars is None:
        max_chars = get_config().search.max_lexical_query_chars
    if len(query) <= max_chars:
        return query
    truncated = query[:max_chars]
    last_space = truncated.rfind(" ")
    result = truncated[:last_space].rstrip() if last_space > 0 else truncated
    logger.debug("Query truncated: %d → %d chars", len(query), len(result))
    return result