"""Phase 5 自檢：BM25 檢索排序、MCP search_wiki / read_page、
路徑跳脫防護（信任邊界）、token 上限截斷。

執行：.venv/Scripts/python tools/selfcheck_search.py
"""
import os
import pathlib
import shutil
import sys
import tempfile

sys.path.insert(0, str(pathlib.Path(__file__).parent))
import kb
import search

CFG = """ollama: {base_url: "http://localhost:11434", timeout_seconds: 5}
tasks:
  ingest: {model: "fake:test", temperature: 0.2, max_retries: 2}
  lint: {model: "fake:test", temperature: 0.1, max_retries: 2}
  fallback: {model: "fake:fb"}
limits: {mcp_response_max_tokens: 100, ingest_chunk_max_chars: 12000}
"""


def page(root, rel, title, desc, tags, body):
    meta = {"type": {"summaries": "summary", "entities": "entity",
                     "concepts": "concept"}[rel.split("/")[1]],
            "title": title, "description": desc, "tags": tags,
            "timestamp": "2026-07-14", "sources": ["raw/converted/x.md#abcd1234"],
            "status": "draft"}
    (root / rel).write_text(kb.dump_page(meta, body), encoding="utf-8")


def main():
    tmp = pathlib.Path(tempfile.mkdtemp(prefix="ppqa-search-"))
    try:
        root = tmp / "repo"
        for sub in ("config", "wiki/summaries", "wiki/entities", "wiki/concepts"):
            (root / sub).mkdir(parents=True)
        (root / "config/models.yaml").write_text(CFG, encoding="utf-8")
        page(root, "wiki/entities/payment-gateway.md", "支付閘道", "支付閘道模組",
             ["gateway"], "壓力測試時出現逾時缺陷，重試機制未生效。")
        page(root, "wiki/concepts/aml-testing.md", "AML 測試準則", "可疑交易監控測試綜合",
             ["aml", "compliance"], "大額交易與分散交易樣態的監控測試要求。")
        page(root, "wiki/summaries/long-doc.md", "長文件摘要", "截斷測試用",
             ["test"], "逾時。" * 500)
        # 與 payment-gateway 共用核心詞「支付閘道」→ df=2, N=4，正是 BM25Okapi
        # 原式 idf 歸零的配置；沒有這頁就測不出核心詞落空的 bug
        page(root, "wiki/summaries/gateway-report.md", "支付閘道版本沿革", "支付閘道改版紀錄",
             ["gateway"], "支付閘道於 2026 年改版，新增分期付款。")

        hits = search.search(root, "支付閘道 逾時")
        assert hits and hits[0]["path"] == "wiki/entities/payment-gateway.md", hits
        assert all(h["score"] > 0 for h in hits)
        hits2 = search.search(root, "可疑交易監控")
        assert hits2[0]["path"] == "wiki/concepts/aml-testing.md", hits2
        assert search.search(root, "zzz-nonexistent-term") == []
        print("PASS: BM25 檢索排序（繁中 bigram）")

        # 核心詞（出現在多頁）不得因 idf <= 0 被整批濾掉
        core = search.search(root, "支付閘道")
        paths = {h["path"] for h in core}
        assert {"wiki/entities/payment-gateway.md",
                "wiki/summaries/gateway-report.md"} <= paths, core
        assert all(h["score"] > 0 for h in core), core
        print("PASS: 核心詞跨頁共用仍可檢索（idf 恆正）")

        os.environ["PP_QA_ROOT"] = str(root)
        import importlib
        sys.path.insert(0, str(pathlib.Path(__file__).parents[1] / "mcp"))
        server = importlib.import_module("server")
        res = server.search_wiki("支付閘道 逾時", top_k=99)  # top_k 超限 → 收斂為 10
        assert res[0]["path"] == "wiki/entities/payment-gateway.md"
        pg = server.read_page("wiki/entities/payment-gateway.md")
        assert pg["frontmatter"]["title"] == "支付閘道" and not pg["truncated"]
        assert pg["source_refs"] == ["raw/converted/x.md#abcd1234"]
        long = server.read_page("wiki/summaries/long-doc.md")
        assert long["truncated"] and len(long["body"]) <= 150 and long["source_refs"]
        print("PASS: MCP search_wiki + read_page（含 token 截斷、source_refs 保留）")

        for bad in ("../AGENTS.md", "wiki/../config/models.yaml", "wiki/entities/x.txt"):
            try:
                server.read_page(bad)
                raise AssertionError(f"應拒絕：{bad}")
            except (ValueError, FileNotFoundError) as e:
                assert isinstance(e, ValueError), f"{bad} 應為 ValueError"
        try:
            server.read_page("wiki/entities/no-such.md")
            raise AssertionError("應拋 FileNotFoundError")
        except FileNotFoundError:
            pass
        print("PASS: 路徑跳脫防護（信任邊界）")
        print("ALL PASS")
    finally:
        os.environ.pop("PP_QA_ROOT", None)
        shutil.rmtree(tmp, ignore_errors=True)


if __name__ == "__main__":
    main()