shudao-main/shudao-chat-py/utils/string_match.py

from typing import List, Tuple


def levenshtein_distance(s1: str, s2: str) -> int:
    """计算两个字符串的编辑距离"""
    if len(s1) < len(s2):
        return levenshtein_distance(s2, s1)
    
    if len(s2) == 0:
        return len(s1)
    
    previous_row = range(len(s2) + 1)
    for i, c1 in enumerate(s1):
        current_row = [i + 1]
        for j, c2 in enumerate(s2):
            insertions = previous_row[j + 1] + 1
            deletions = current_row[j] + 1
            substitutions = previous_row[j] + (c1 != c2)
            current_row.append(min(insertions, deletions, substitutions))
        previous_row = current_row
    
    return previous_row[-1]


def string_similarity(s1: str, s2: str) -> float:
    """计算两个字符串的相似度 (0-1)"""
    if not s1 or not s2:
        return 0.0
    
    distance = levenshtein_distance(s1, s2)
    max_len = max(len(s1), len(s2))
    
    if max_len == 0:
        return 1.0
    
    return 1.0 - (distance / max_len)


def find_best_match(target: str, candidates: List[str]) -> Tuple[str, float]:
    """从候选列表中找到最佳匹配"""
    if not candidates:
        return "", 0.0
    
    best_match = ""
    best_score = 0.0
    
    for candidate in candidates:
        score = string_similarity(target, candidate)
        if score > best_score:
            best_score = score
            best_match = candidate
    
    return best_match, best_score