"""T21-3 build_kb 脚本单测：front-matter 解析 / 节切块 / Milvus 行构造（纯函数）。

脚本目录非包，sys.path 动态导入（同 test_demo_scripts 模式）。
不连 Ollama / Milvus / MySQL（真库联调归收尾验证步骤）。
"""

from __future__ import annotations

import sys
from pathlib import Path

import pytest

KB_DIR = Path(__file__).resolve().parents[1] / "scripts" / "kb"
sys.path.insert(0, str(KB_DIR))

from build_kb import (  # noqa: E402
    DOC_TYPES,
    build_chunk_rows,
    parse_front_matter,
    parse_kb_file,
    parse_sections,
)

PRODUCT = {"product_id": "PROD-X", "product_name": "测试产品", "min_risk_code": "R2"}

SAMPLE = """---
product_id: PROD-X
version: 2026.09
effective_date: 2026-09-01
---

# 测试产品 · 产品手册

## 【prospectus】产品概况

定位与投资范围说明。

## 【fee】费率结构

管理费 0.20%/年，托管费 0.10%/年。

## 【rule】申赎与交易规则

申购 T+1 确认。

## 【risk】风险揭示

不保本不保收益。
"""


class TestFrontMatter:
    def test_parse_meta_and_body_split(self):
        meta, body = parse_front_matter(SAMPLE)
        assert meta == {
            "product_id": "PROD-X",
            "version": "2026.09",
            "effective_date": "2026-09-01",
        }
        assert body.startswith("# 测试产品")

    def test_missing_front_matter_raises(self):
        with pytest.raises(ValueError, match="front-matter"):
            parse_front_matter("# 无 front-matter 正文")


class TestSections:
    def test_four_sections_with_types(self):
        sections = parse_sections(SAMPLE)
        assert [s["doc_type"] for s in sections] == list(DOC_TYPES)
        assert sections[0]["title"] == "产品概况"
        assert "投资范围" in sections[0]["text"]

    def test_section_text_excludes_heading_and_blank_lines(self):
        sections = parse_sections(SAMPLE)
        # 正文不含标题行、不含空行累计
        assert "【fee】" not in sections[1]["text"]
        assert sections[1]["text"].count("\n\n") == 0

    def test_illegal_doc_type_raises(self):
        bad = SAMPLE.replace("【fee】", "【rates】")
        with pytest.raises(ValueError, match="doc_type 非法"):
            parse_sections(bad)

    def test_empty_body_sections_dropped(self):
        body = "## 【fee】费率\n\n## 【risk】风险\n有内容"
        sections = parse_sections(body)
        assert len(sections) == 1
        assert sections[0]["doc_type"] == "risk"


class TestChunkRows:
    def test_row_fields_and_chunk_no(self):
        meta = {"product_id": "PROD-X", "version": "2026.09", "effective_date": "2026-09-01"}
        sections = parse_sections(SAMPLE)
        rows = build_chunk_rows(meta, sections, PRODUCT)
        assert [r["id"] for r in rows] == ["PROD-X_0", "PROD-X_1", "PROD-X_2", "PROD-X_3"]
        first = rows[0]
        # 溯源字段必填（03-milvus-collections.md §2.3）
        assert first["source_doc_id"] == "KB-PROD-X"
        assert first["source_version"] == "2026.09"
        assert first["effective_date"] == "2026-09-01"
        # product_name / risk_level 取 Core 权威（不入库文件自述值）
        assert first["product_name"] == "测试产品"
        assert first["risk_level"] == "R2"
        assert first["chunk_no"] == 0

    def test_missing_meta_field_raises(self):
        meta = {"product_id": "PROD-X", "version": "2026.09"}  # 缺 effective_date
        with pytest.raises(ValueError, match="缺少字段"):
            build_chunk_rows(meta, [{"doc_type": "fee", "title": "t", "text": "x"}], PRODUCT)

    def test_chunk_text_truncated(self):
        from build_kb import CHUNK_TEXT_MAX_CHARS

        meta = {"product_id": "PROD-X", "version": "v", "effective_date": "2026-09-01"}
        long_text = "长" * (CHUNK_TEXT_MAX_CHARS + 100)
        rows = build_chunk_rows(meta, [{"doc_type": "fee", "title": "t", "text": long_text}], PRODUCT)
        assert len(rows[0]["chunk_text"]) == CHUNK_TEXT_MAX_CHARS


class TestRealFiles:
    """真手册文件抽查：data/kb 全部文件可解析且 4 节齐。"""

    def test_all_kb_files_parse(self):
        kb_root = Path(__file__).resolve().parents[1] / "data" / "kb"
        files = sorted(kb_root.glob("*.md"))
        assert len(files) == 6
        for f in files:
            meta, sections = parse_kb_file(f)
            assert meta["product_id"] == f.stem
            assert [s["doc_type"] for s in sections] == ["prospectus", "fee", "rule", "risk"]
            assert all(len(s["text"]) > 20 for s in sections)