2026Technology-Competition/tests/test_word_template_parser.py

from genesis.data_models import ChapterMarker, ParsedTemplate
from genesis.parsers._word_common import heading_level
from genesis.parsers.word_template_parser import WordTemplateParser

from tests.docx_helpers import new_document, save_document


def test_heading_level_parses_numeric_suffix():
    assert heading_level("Heading 1") == 1
    assert heading_level("Heading 2") == 2
    assert heading_level("Heading 3") == 3


def test_heading_level_fallback_on_invalid():
    # 兜底分支（非数字 / 无后缀）→ 1，分支覆盖必须命中
    assert heading_level("Heading X") == 1
    assert heading_level("Heading") == 1


def test_parse_extracts_heading_levels(tmp_path):
    doc = new_document()
    doc.add_heading("1. はじめに", level=1)
    doc.add_heading("2.1 画面遷移図", level=2)
    doc.add_heading("2.1.1 詳細", level=3)
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert isinstance(result, ParsedTemplate)
    headings = [s for s in result.sections if s.type == "heading"]
    assert [(s.name, s.level) for s in headings] == [
        ("1. はじめに", 1),
        ("2.1 画面遷移図", 2),
        ("2.1.1 詳細", 3),
    ]


def test_parse_extracts_bookmark(tmp_path):
    from docx.oxml.ns import qn
    doc = new_document()
    para = doc.add_paragraph("アンカー")
    bm_start = para._p.makeelement(qn("w:bookmarkStart"), {qn("w:id"): "0", qn("w:name"): "template_start"})
    para._p.insert(0, bm_start)
    # 无 name 的书签：覆盖 if name 假分支，应被跳过
    bm_anon = para._p.makeelement(qn("w:bookmarkStart"), {qn("w:id"): "1"})
    para._p.insert(1, bm_anon)
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    bookmarks = [s for s in result.sections if s.type == "bookmark"]
    assert [s.name for s in bookmarks] == ["template_start"]


def test_parse_extracts_placeholders(tmp_path):
    doc = new_document()
    doc.add_paragraph("{{doc_title}}")
    doc.add_paragraph("{{section:introduction}}")
    doc.add_paragraph("{{section:function_list}}")
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert result.placeholders == {
        "doc_title": "{{doc_title}}",
        "section:introduction": "{{section:introduction}}",
        "section:function_list": "{{section:function_list}}",
    }
    ph = [s for s in result.sections if s.type == "placeholder"]
    assert [s.name for s in ph] == ["doc_title", "section:introduction", "section:function_list"]


def test_parse_invalid_placeholder_kept_as_text(tmp_path):
    doc = new_document()
    doc.add_paragraph("{{ invalid }}")
    doc.add_paragraph("ただの {text}")
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert result.placeholders == {}
    assert [s for s in result.sections if s.type == "placeholder"] == []


def test_parse_empty_document(tmp_path):
    doc = new_document()
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert result.sections == []
    assert result.placeholders == {}
    assert "Normal" in result.styles["defined"]


def test_parse_styles_collected(tmp_path):
    doc = new_document()
    doc.add_heading("章", level=1)
    doc.add_paragraph("本文")
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert "Heading 1" in result.styles["used"]
    assert "Normal" in result.styles["used"]
    assert "Heading 1" in result.styles["defined"]


def test_parse_extracts_placeholder_case_insensitive(tmp_path):
    # 宽容：键名大小写不敏感 → 归一为小写 section:id
    doc = new_document()
    doc.add_paragraph("{{Section:2}}")
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert result.placeholders == {"section:2": "{{Section:2}}"}
    ph = [s for s in result.sections if s.type == "placeholder"]
    assert [s.name for s in ph] == ["section:2"]


def test_parse_extracts_placeholder_fullwidth_colon(tmp_path):
    # 宽容：全角冒号（：）也视为分隔符 → 归一为半角 section:id
    doc = new_document()
    doc.add_paragraph("{{section：2}}")
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    assert result.placeholders == {"section:2": "{{section：2}}"}
    ph = [s for s in result.sections if s.type == "placeholder"]
    assert [s.name for s in ph] == ["section:2"]


# ---------- P2-1：表格单元格内的占位符（此前漏检 → 静默丢章） ----------

def _doc_with_cell_placeholder():
    """H1 → 表格(单元格内含锚点) → H1。锚点必须归属其前的 H1。"""
    doc = new_document()
    doc.add_heading("1. はじめに", level=1)
    tbl = doc.add_table(rows=1, cols=1)
    tbl.rows[0].cells[0].paragraphs[0].text = "{{section:introduction}}"
    doc.add_heading("2. 機能一覧", level=1)
    doc.add_paragraph("{{section:function_list}}")
    return doc


def test_parse_placeholder_inside_table_cell(tmp_path):
    path = save_document(tmp_path, _doc_with_cell_placeholder())
    result = WordTemplateParser().parse(path)
    assert "section:introduction" in result.placeholders
    ph = [s.name for s in result.sections if s.type == "placeholder"]
    assert "section:introduction" in ph


def test_parse_table_placeholder_keeps_document_order(tmp_path):
    """单元格锚点须按文档顺序落位（在其前的 H1 与在其后的 H1 之间），不得错绑。"""
    path = save_document(tmp_path, _doc_with_cell_placeholder())
    result = WordTemplateParser().parse(path)
    names = [(s.type, s.name) for s in result.sections]
    i_intro = names.index(("heading", "1. はじめに"))
    i_ph = names.index(("placeholder", "section:introduction"))
    i_func = names.index(("heading", "2. 機能一覧"))
    assert i_intro < i_ph < i_func


def test_parse_merged_cell_placeholder_not_duplicated(tmp_path):
    """合并单元格的 row.cells 会重复指向同一 tc → 不得重复收集。"""
    doc = new_document()
    doc.add_heading("1. 章", level=1)
    tbl = doc.add_table(rows=1, cols=2)
    tbl.rows[0].cells[0].merge(tbl.rows[0].cells[1])
    tbl.rows[0].cells[0].paragraphs[0].text = "{{section:db_design}}"
    path = save_document(tmp_path, doc)

    result = WordTemplateParser().parse(path)

    ph = [s.name for s in result.sections if s.type == "placeholder"]
    assert ph.count("section:db_design") == 1