# -*- coding: utf-8 -*-
"""
前端面板完整数据 schema，与 DB / situationData / useReplaySituation 对齐
爬虫 + AI 清洗后的数据必须符合此 schema 才能正确更新前端
"""
from typing import Any, Dict, List, Literal, Optional, Tuple

# 事件脉络
SITUATION_UPDATE_CATEGORIES = ("deployment", "alert", "intel", "diplomatic", "other")
SITUATION_UPDATE_SEVERITIES = ("low", "medium", "high", "critical")
SUMMARY_MAX_LEN = 120

# 战损
CombatLossesRow = Dict[str, Any]  # bases_destroyed, bases_damaged, personnel_killed, ...

# 时间序列（回放用）
TimeSeriesPoint = Tuple[str, int]  # (ISO time, value)

# AI 可从新闻中提取的字段
EXTRACTABLE_FIELDS = {
    "situation_update": ["summary", "category", "severity", "timestamp"],
    "combat_losses": ["personnel_killed", "personnel_wounded", "civilian_killed", "civilian_wounded", "bases_destroyed", "bases_damaged", "aircraft", "warships", "armor", "vehicles", "drones", "missiles", "helicopters", "submarines"],
    "retaliation": ["value"],  # 0-100
    "wall_street_trend": ["time", "value"],  # 0-100
    "conflict_stats": ["estimated_casualties", "estimated_strike_count"],
}


def validate_category(cat: str) -> str:
    return cat if cat in SITUATION_UPDATE_CATEGORIES else "other"


def validate_severity(sev: str) -> str:
    return sev if sev in SITUATION_UPDATE_SEVERITIES else "medium"


def validate_summary(s: str, max_len: int = SUMMARY_MAX_LEN) -> str:
    import re
    if not s or not isinstance(s, str):
        return ""
    t = re.sub(r"\s+", " ", str(s).strip())[:max_len]
    return re.sub(r"[\x00-\x1f]", "", t).rstrip()