"""품셈 PDF → 절별 md 도구(`_pipeline/pum_md_tool.py`) — 순수 함수 · 산림 차례 개수.

규칙: `resources/knowledge/original/원가계산/_품셈md_작성규칙.md`.
"""

import sys
from pathlib import Path

import pytest

ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "resources/knowledge/original/_pipeline"))

import pum_md_tool as tool  # noqa: E402


def test_parse_toc_strips_leaders_and_reads_appendix():
    lines = ["제1장", "적용기준 ·········", "1", "1-1", "일반사항 ·····", "1", "부록 ······", "204"]
    got = tool.parse_toc(lines)
    assert [(e.ident, e.name, e.page) for e in got] == [
        ("제1장", "적용기준", 1),
        ("1-1", "일반사항", 1),
        ("부록", "", 204),
    ]
    with pytest.raises(ValueError):
        tool.parse_toc(["엉뚱한 줄", "1"])


def test_key_ignores_spaces_dot_after_number_and_middle_dots():
    assert tool.key("9-5. 발파암") == tool.key("9-5 발파암")
    assert tool.key("[부록1]할인") == tool.key("부록1 할인")
    assert tool.key("보수·복구") == tool.key("보수․복구")


def test_heading_pattern_by_number_only():
    sec = tool.heading_pattern("7-1")
    assert sec.match("7-1. 벌도")
    assert not sec.match("7-11. 동력상하차기")  # 번호가 앞머리만 같음
    assert not sec.match("7-1-1. 항")
    assert tool.heading_pattern("제1장").match("제1장적용기준")
    assert not tool.heading_pattern("제1장").match("제10장자재")
    assert tool.heading_pattern("부록1").match("[부록1]할인")
    assert not tool.heading_pattern("부록1").match("[부록10]x")


def test_respace_takes_toc_spacing_but_body_glyphs():
    toc = "임산물 운반로 신설 및 보수․복구"
    assert tool.respace("임산물운반로신설및보수·복구", toc) == "임산물 운반로 신설 및 보수·복구"
    # 차례 오타(조림 ≠ 조립) — 본문 그대로
    assert tool.respace("철근현장가공및조립", "철근 현장가공 및 조림") == "철근현장가공및조립"


def test_heading_text_keeps_number_dot():
    entry = tool.Entry("4-5", "벌도 위험목 점검", 51)
    assert tool.heading_text(entry, "4-5. 벌도위험목점검") == "4-5. 벌도 위험목 점검"
    assert tool.section_name(entry, "4-5. 벌도위험목점검") == "벌도 위험목 점검"
    chapter = tool.Entry("제2장", "소요재료 및 기계손료", 28)
    assert tool.heading_text(chapter, "제2장소요재료및기계손료") == "제2장 소요재료 및 기계손료"


def test_section_file_name():
    chapter = tool.Entry("제10장", "자재․장비 운반", 143)
    section = tool.Entry("10-5", "목재 운반/적재", 150)
    got = tool.section_file(Path("본문"), chapter, section)
    assert got.as_posix() == "본문/제10장_자재․장비_운반/10-05_목재_운반적재.md"


def test_head_round_trip(tmp_path):
    path = tmp_path / "a.md"
    path.write_text(
        tool.head_text({"절": "9-5. 발파암", "상태": "대기"}) + "\n본문\n", encoding="utf-8"
    )
    head = tool.read_head(path)
    assert list(head) == list(tool.HEAD_KEYS)
    assert head["절"] == "9-5. 발파암" and head["상태"] == "대기" and head["작성"] == ""


def test_forest_toc_counts():
    """산림 차례 — 14장 · 189절(PDF 3~12쪽)."""
    pymupdf = pytest.importorskip("pymupdf")
    book = tool.BOOKS["산림"]
    with pymupdf.open(book["pdf"]) as doc:
        entries = tool.toc_entries(doc, *book["toc"])
    assert sum(e.ident.startswith("제") for e in entries) == 14
    assert sum(e.ident.count("-") == 1 for e in entries) == 189