"""解析器契约测试。

除 brief 给定的 7 条契约外，另有一条**对真实源文件**的计数测试：`RAG-` 前缀
只覆盖 62/105 条，漏掉全部 43 条 `NF-*`（真实文件里共 12 种前缀）。真实源文件是
工作区外的交付物，缺失时 skip（不算失败），存在时按期望值强校验。
"""

from __future__ import annotations

import hashlib
from dataclasses import FrozenInstanceError
from pathlib import Path

import pytest

from tools.qa_source_parser import (
    EXPECTED_RECORD_COUNT,
    QaRecord,
    normalize_phrase,
    parse_qa_source,
    phrase_hash,
)

SAMPLE = """
[RAG-PER-001]
问题：你是谁？
相似问法：你是人工吗？|你是真人客服吗？
回答：我是奶龙基金智能助手。

[NF-SVC-001]
问题：怎么联系你们？
相似问法：客服入口在哪？
回答：您可通过官网获取服务。
"""

#: 已审核源文件的实际位置（工作区外）。用于验证"11 种前缀"这一前提是否成立。
REAL_SOURCE = Path(
    r"C:\Users\Windows\Desktop\DSH开发智能助手\胜宇前期资料"
    r"\客服Agent知识库_QA问答对_v5_RAG发布候选版.txt"
)


def test_expected_count_is_105() -> None:
    assert EXPECTED_RECORD_COUNT == 105


def test_parser_accepts_both_id_prefixes() -> None:
    records = parse_qa_source(SAMPLE, expected_count=None)
    assert [r.qa_id for r in records] == ["RAG-PER-001", "NF-SVC-001"]


def test_parser_splits_synonyms_on_pipe() -> None:
    records = parse_qa_source(SAMPLE, expected_count=None)
    assert records[0].synonyms == ("你是人工吗？", "你是真人客服吗？")


def test_parser_keeps_answer_verbatim() -> None:
    records = parse_qa_source(SAMPLE, expected_count=None)
    assert records[0].answer == "我是奶龙基金智能助手。"


def test_parser_rejects_record_without_synonyms() -> None:
    with pytest.raises(ValueError, match="相似问法"):
        parse_qa_source("[RAG-PER-001]\n问题：问？\n回答：答。\n", expected_count=None)


def test_parser_rejects_wrong_record_count_by_default() -> None:
    with pytest.raises(ValueError, match="记录数不符"):
        parse_qa_source(SAMPLE)


def test_phrase_hash_is_sha256_of_normalized_phrase() -> None:
    value = "你是人工吗？"
    assert phrase_hash(value) == hashlib.sha256(
        normalize_phrase(value).encode("utf-8")).hexdigest()
    assert len(phrase_hash(value)) == 64


def test_record_is_frozen_dataclass() -> None:
    record = parse_qa_source(SAMPLE, expected_count=None)[0]
    assert isinstance(record, QaRecord)
    assert isinstance(record.synonyms, tuple)
    with pytest.raises(FrozenInstanceError):
        record.question = "改不了"  # type: ignore[misc]


def test_parser_rejects_duplicate_synonym_within_record_after_normalization() -> None:
    """`uk_faq_synonym (knowledge_id, phrase_hash)` 只认归一化后的哈希。"""
    text = "[RAG-PER-001]\n问题：你是谁？\n相似问法：你是谁？| 你是谁？ |你 是 谁？\n回答：答。\n"
    synonyms = parse_qa_source(text, expected_count=None)[0].synonyms
    assert len({phrase_hash(item) for item in synonyms}) == len(synonyms)


@pytest.mark.skipif(not REAL_SOURCE.exists(), reason="已审核 QA 源文件不在本机")
def test_parser_counts_real_source_file() -> None:
    records = parse_qa_source(REAL_SOURCE.read_text(encoding="utf-8"))
    assert len(records) == EXPECTED_RECORD_COUNT
    rag = [r for r in records if r.qa_id.startswith("RAG-")]
    nf = [r for r in records if r.qa_id.startswith("NF-")]
    assert (len(rag), len(nf)) == (62, 43)
    assert all(r.question and r.answer and r.synonyms for r in records)
    assert sum(len(r.synonyms) for r in records) == 421
    # 前缀多于"RAG-"/"NF-"两类：只按 RAG- 解析会静默丢掉 NF-* 全部记录。
    assert len([r for r in records if not r.qa_id.startswith(("RAG-", "NF-"))]) == 0