"""site_import 骨架模板与 few-shot 语料守卫（Task 4）。"""
import json
import re
from pathlib import Path

TPL_DIR = Path(__file__).resolve().parents[1] / "app" / "platform" / "site_import" / "template"
FS = Path(__file__).resolve().parents[1] / "app" / "platform" / "site_import" / "fewshot" / "fewshot_excerpts.md"
JIANCAI_SYSTEM = Path(__file__).resolve().parents[1] / "seed_profiles" / "jiancai" / "prompts" / "system.md"

# 行业专属词黑名单（jiancai 管道 / yotai 储能 / televics 炉辊三行业的专属词；
# WhatsApp、manager、quotation 等通用外贸词不在其列）
INDUSTRY_WORDS = [
    "管道", "pipe", "HESUPIPE", "储能", "storage", "炉辊", "roller",
    "TELEVIC", "YOTAI", "HDPE", "PVC", "PE100", "SDR", "DN110",
    "给水", "燃气", "排污", "灌溉", "波纹管", "球墨铸铁",
]

# 双要分叉豁免清单（2026-11-02，spec docs/superpowers/specs/
# 2026-11-02-jiancai-dual-contact-ask-design.md §3.4）：jiancai system.md
# 已演化到"双渠道一次要齐"话术，生成器模板按 spec 决策**有意保持**"分步双要"
# 出厂默认——联系方式引导话术族的行级分叉是已归档的合规分叉，按行特征子串
# 豁免不计 missing；其余行仍受 ≤8 阈值守护（防未归档漂移）。
DUAL_ASK_DIVERGED = (
    '互留句 "Drop yours too..."',                        # 模板句族行（L7 同构）
    "I'll connect you with our manager to arrange that — drop your WhatsApp",  # 转接句
    "Tell me your WhatsApp and our manager",            # 预算后引导句
    "drop your WhatsApp and our manager will reply within 12 hours",  # 磨价应对句
    "记录里确有号码",                                    # 已留资确认句
    "4. 拿到联系方式后",                                 # 对话流程尾括注
    "What's your WhatsApp number with the country code",  # en 池①
    "who handles [country] market",                     # en 池②
    "Drop your WhatsApp or email?",                     # en 池③
    "Want me to get you a full quotation?",             # en 池④
    "你WhatsApp多少？带上国家代码",                      # zh 池①
    "我让负责[国家]市场的同事加你",                      # zh 池②
    "留个WhatsApp或者邮箱吧",                            # zh 池③
    "你给我个联系方式，我让客户经理",                    # zh 池④
    "**分步双要，一次只问一个**",                        # 双渠道原则行
    '"Drop your WhatsApp and our manager',              # App 反向留资句
    "【互留】",                                          # 互留句
    '提醒说"已提供"时',                                  # 系统提醒配合行
    "拿到后说一句",                                      # 注意节尾括注
)


class TestTemplatePurity:
    def test_骨架无行业残留(self):
        for fname in ("system", "extractor", "evaluator"):
            t = (TPL_DIR / f"{fname}_template.md").read_text(encoding="utf-8")
            low = t.lower()
            for w in INDUSTRY_WORDS:
                assert w.lower() not in low, f"{fname}_template.md 行业残留: {w}"

    def test_占位符与清单一致(self):
        ph = json.loads((TPL_DIR / "placeholders.json").read_text(encoding="utf-8"))
        assert set(ph) == {"system", "extractor", "evaluator"}
        for fname, keys in ph.items():
            t = (TPL_DIR / f"{fname}_template.md").read_text(encoding="utf-8")
            for k in keys:
                assert "{{" + k + "}}" in t, f"{fname} 缺占位符 {k}"
        # 反向：模板中每个 {{xxx}} 都在清单
        for fname, keys in ph.items():
            t = (TPL_DIR / f"{fname}_template.md").read_text(encoding="utf-8")
            found = set(re.findall(r"\{\{([^}]+)\}\}", t))
            assert found == set(keys), f"{fname} 占位符不对称: {found ^ set(keys)}"

    def test_红线段锚点齐全(self):
        t = (TPL_DIR / "system_template.md").read_text(encoding="utf-8")
        for anchor in ["语言规则（最高优先级）", "职能边界", "红线（任何情况下不可违反）",
                       "不能出现任何价格数字", "施压", "禁止说的话", "联系方式引导策略",
                       "12 hours", "国家代码"]:
            assert anchor in t, f"缺锚点: {anchor}"

    def test_固定段行级来源(self):
        """非占位行应逐字存在于 jiancai 原文（允许空行/标题差异 ±5% 行）。

        双要改版后联系方式话术族的分叉按 DUAL_ASK_DIVERGED 豁免（见其注）。
        """
        j = JIANCAI_SYSTEM.read_text(encoding="utf-8").splitlines()
        jset = set(l.strip() for l in j)
        t = (TPL_DIR / "system_template.md").read_text(encoding="utf-8").splitlines()
        missing = [l.strip() for l in t
                   if l.strip() and "{{" not in l and "#" not in l[:2]
                   and l.strip() not in jset
                   and not any(m in l for m in DUAL_ASK_DIVERGED)]
        # 允许少量结构性改写（拆段标题等）——阈值 ≤8 行，且打印出来人工可核
        assert len(missing) <= 8, f"来源外行过多: {missing}"


class TestFewshot:
    def test_尺寸上限(self):
        assert len(FS.read_bytes()) <= 18000

    def test_两租户都在(self):
        s = FS.read_text(encoding="utf-8")
        assert "yotaienergys" in s and "televicsic" in s

    def test_用途段落齐(self):
        s = FS.read_text(encoding="utf-8")
        for sec in ["身份", "追问", "好差", "事实卡", "提取器", "评估器"]:
            assert sec in s, f"fewshot 缺用途段: {sec}"