"""查询难度估计器（启发式，纯标准库）。

依据：RouterArena 用 Bloom 分类法把问题分为 easy/medium/hard。
这里用查询长度、指令动词、数学/推理标记做轻量估计。
"""
from __future__ import annotations

import re
from typing import Tuple

# 触发 hard 的指令动词 / 推理标记
_HARD_MARKERS = [
    "证明", "推导", "为什么", "如何", "对比", "比较", "分析", "评估", "设计", "优化",
    "复杂度", "时间复杂度", "空间复杂度", "原理", "机制", "优缺点", "区别", "推论", "定理",
    "proof", "prove", "derive", "explain why", "why", "how", "compare", "contrast",
    "analy", "evaluate", "design", "optimize", "refactor", "architect",
    "implement", "debug", "review", "plan", "synthesize",
    "int", "sum", "sqrt", "lim", "log", "derivative", "integral",
]
# 触发 medium 的标记
_MEDIUM_MARKERS = [
    "用", "写", "计算", "求解", "生成", "翻译", "总结", "解释",
    "注意", "建议", "是否", "实现", "步骤",
    "write", "code", "function", "script", "calculate", "solve", "summarize",
    "translate", "fix", "explain", "describe", "list",
]


def _compile_markers(markers):
    """标记表编译：英文标记用词边界正则，中文标记保持子串匹配。

    T-R3（采纳 llmrouter 词边界思想，super_hard 先于 hard 的同理）：
    纯子串匹配会让 "int" 误命中 "print"/"point"、"log" 误命中 "logic"、
    "list" 误命中 "listen"——英文必须整词命中才计数。
    """
    substr, words = [], []
    for m in markers:
        (words if m.isascii() else substr).append(m)
    pattern = re.compile(r"\b(?:%s)\b" % "|".join(re.escape(w) for w in words)) \
        if words else None
    return substr, pattern


_HARD_SUBSTR, _HARD_RE = _compile_markers(_HARD_MARKERS)
_MEDIUM_SUBSTR, _MEDIUM_RE = _compile_markers(_MEDIUM_MARKERS)

# 预编译正则（模块级一次，避免每次调用走 re 内部缓存查找）
_RE_CODE_EXPR = re.compile(r"\b(def|class|function|import)\b")
_RE_ARITH_EXPR = re.compile(r"[0-9]+\s*[+\-*/^=]\s*[0-9xya-z]")


def _hit_count(substr, pattern, q: str) -> int:
    """中文子串命中数 + 英文整词命中数。"""
    n = sum(1 for m in substr if m in q)
    if pattern is not None:
        n += len(pattern.findall(q))
    return n


def estimate_difficulty(query: str) -> Tuple[str, float]:
    """返回 (difficulty, score)，score 属于 [0,1]。"""
    q = query.lower()
    hard_hits = _hit_count(_HARD_SUBSTR, _HARD_RE, q)
    medium_hits = _hit_count(_MEDIUM_SUBSTR, _MEDIUM_RE, q)
    length = len(query)

    score = 0.0
    score += min(0.30, length / 600.0)          # 长度贡献
    score += min(0.55, hard_hits * 0.25)        # 推理标记贡献
    score += min(0.30, medium_hits * 0.08)      # 一般指令贡献

    # 额外：代码 / 数学表达式（多步骤信号）
    if "```" in query or _RE_CODE_EXPR.search(q):
        score += 0.15
    if _RE_ARITH_EXPR.search(q):
        score += 0.15

    score = max(0.0, min(1.0, score))
    if score >= 0.55:
        return "hard", score
    if score >= 0.25:
        return "medium", score
    return "easy", score