2026Technology-Competition/tests/test_excel_parser.py

from genesis.data_models import SheetType
from genesis.parsers.excel_parser import ExcelParseResult, ExcelParser

from tests.excel_helpers import new_workbook, save_workbook


def test_parse_skips_empty_sheet(tmp_path):
    # 空 sheet → skipped 不进入（L skips 分支）
    wb = new_workbook({"空白": [[]]})
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    assert "空白" in result.skipped
    assert result.tables == []


def test_parse_mixed_formatting_outside_table_segment(tmp_path):
    # 碎片段（free_text 段）存在取消线格式 → seg_fmt_map 构建时该行不在表格段 [s,e] 内，被跳过（66-65 分支）
    from copy import copy
    from openpyxl import Workbook
    wb = Workbook()
    ws = wb.active
    ws.title = "混合"
    data = [
        ["機能ID", "機能名"], ["F101", "社員登録"],
        [],
        ["・改述ポイント"],
    ]
    for r, row in enumerate(data, start=1):
        for c, v in enumerate(row, start=1):
            if v:
                ws.cell(row=r, column=c, value=v)
    font = copy(ws.cell(row=4, column=1).font)  # 碎片段行（物理行 4）
    font.strike = True
    ws.cell(row=4, column=1).font = font
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    ms = result.mixed[0]
    tbl = [p.table for p in ms.paragraphs if p.kind == "table"][0]
    # 表格段数据行不应带上碎片段的取消线格式
    assert tbl.rows[0]["機能ID"].formatting is None
    assert len(tbl.rows) == 1


def test_parse_table_sheets(tmp_path):
    wb = new_workbook({
        "機能一覧": [["機能ID", "機能名"], ["A001", "社員登録"]],
        "バッチ一覧": [["バッチID", "処理名"], ["B1", "夜間集計"]],
    })
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    assert isinstance(result, ExcelParseResult)
    by_name = {t.name: t for t in result.tables}
    assert by_name["機能一覧"].detected_type == SheetType.FUNCTION
    assert len(by_name["機能一覧"].rows) == 1
    assert by_name["バッチ一覧"].detected_type == SheetType.BATCH


def test_parse_free_text_sheet(tmp_path):
    wb = new_workbook({"メモ": [["新入社員を登録"], [], [], [], []]})
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    assert len(result.tables) == 1
    assert result.tables[0].extraction_method == "llm_from_free_text"


def test_parse_uses_detected_header_row(tmp_path):
    # 标题行（单格）在首行，真实表头在第二行
    wb = new_workbook({
        "機能一覧": [["機能一覧"], ["機能ID", "機能名"], ["A001", "社員登録"]],
    })
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    t = result.tables[0]
    assert t.headers == ["機能ID", "機能名"]
    assert len(t.rows) == 1
    assert t.rows[0]["機能ID"].value == "A001"


def test_parse_attaches_strikethrough_formatting(tmp_path):
    from copy import copy
    from openpyxl import Workbook
    wb = Workbook()
    ws = wb.active
    ws.title = "機能一覧"
    ws["A1"] = "機能ID"
    ws["B1"] = "機能名"
    ws["A2"] = "A001"
    ws["B2"] = "社員登録"
    font = copy(ws["A2"].font)
    font.strike = True
    ws["A2"].font = font
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    cv = result.tables[0].rows[0]["機能ID"]
    assert cv.formatting is not None
    assert cv.formatting.strikethrough is True


from genesis.data_models import MixedParagraph, MixedSheet
from genesis.parsers.excel_parser import ExcelParseResult


def test_excel_parse_result_has_mixed_default():
    r = ExcelParseResult(file_name="f.xlsx")
    assert r.mixed == []


def test_mixed_paragraph_defaults():
    p = MixedParagraph(kind="table")
    assert p.table is None
    assert p.text is None
    assert p.source_range is None


def test_mixed_sheet_holds_paragraphs():
    p1 = MixedParagraph(kind="table")
    p2 = MixedParagraph(kind="free_text", text="备注")
    ms = MixedSheet(name="混合", paragraphs=[p1, p2])
    assert ms.name == "混合"
    assert [p.kind for p in ms.paragraphs] == ["table", "free_text"]


def test_parse_mixed_sheet_segmented(tmp_path):
    wb = new_workbook({
        "混合": [
            ["機能ID", "機能名"],
            ["F101", "社員登録"],
            ["F102", "退職処理"],
            [],
            ["・改修ポイント：F102 追加バリデーション"],
            ["■対象画面：SC001"],
        ],
    })
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    assert result.mixed, "混合 sheet 应产产出 mixed 段落"
    ms = result.mixed[0]
    assert ms.name == "混合"
    kinds = [p.kind for p in ms.paragraphs]
    assert "table" in kinds and "free_text" in kinds
    # 表格段无碎片污染：table 段应含 2 数据行，机能ID 首行为 F101
    tbl = [p.table for p in ms.paragraphs if p.kind == "table"][0]
    assert tbl is not None and len(tbl.rows) == 2
    assert tbl.rows[0]["機能ID"].value == "F101"
    # 自由文本段捕获碎片
    ft = [p for p in ms.paragraphs if p.kind == "free_text"][0]
    assert "改修ポイント" in (ft.text or "")


def test_parse_mixed_sheet_formatting_in_mid_segment(tmp_path):
    # 表格段不在物理行 0（自由文本段在前），数据行 F101 设取消线 —— 锁住 formatting_map 坐标错位
    from copy import copy
    from openpyxl import Workbook
    wb = Workbook()
    ws = wb.active
    ws.title = "混合"
    data = [
        ["■はじめに"], ["前提説明"], [],
        ["機能ID", "機能名"], ["F101", "社員登録"], ["F102", "退職処理"],
        [], ["・改修ポイント"],
    ]
    for r, row in enumerate(data, start=1):
        for c, v in enumerate(row, start=1):
            if v:
                ws.cell(row=r, column=c, value=v)
    font = copy(ws.cell(row=5, column=1).font)  # F101 所在物理行（第 5 行）
    font.strike = True
    ws.cell(row=5, column=1).font = font
    path = save_workbook(tmp_path, wb)
    result = ExcelParser().parse(path)
    ms = result.mixed[0]
    tbl = [p.table for p in ms.paragraphs if p.kind == "table"][0]
    cv = tbl.rows[0]["機能ID"]  # F101
    assert cv.formatting is not None
    assert cv.formatting.strikethrough is True