123 lines
4.3 KiB
Python
123 lines
4.3 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from genesis.parsers.excel_parser import ExcelParser
|
|
from genesis.parsers.word_template_parser import WordTemplateParser
|
|
from genesis.parsers.rule_doc_parser import RuleDocParser
|
|
from genesis.parsers.source_aggregator import SourceParser
|
|
|
|
SAMPLES = Path(__file__).resolve().parents[1] / "samples"
|
|
|
|
|
|
def _d(name: str) -> Path:
|
|
return SAMPLES / name
|
|
|
|
|
|
def _x(name: str) -> Path:
|
|
return SAMPLES / name
|
|
|
|
|
|
def test_new_dev_sample_has_tables():
|
|
p = _x("要件定義_新規開発.xlsx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = ExcelParser().parse(p)
|
|
by_name = {t.name: t for t in result.tables}
|
|
assert "機能一覧" in by_name
|
|
assert by_name["機能一覧"].rows
|
|
assert any(t.name == "DB定義" for t in result.tables)
|
|
|
|
|
|
def test_additional_modification_has_tables():
|
|
p = _x("要件定義_追加改修.xlsx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = ExcelParser().parse(p)
|
|
assert result.tables
|
|
assert any(t.rows for t in result.tables)
|
|
|
|
|
|
def test_free_text_sample_detected():
|
|
p = _x("要件定義_自由記述.xlsx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = ExcelParser().parse(p)
|
|
assert any(t.extraction_method == "llm_from_free_text" for t in result.tables)
|
|
|
|
|
|
def test_mixed_sample_segments_detected():
|
|
p = _x("要件定義_混合型.xlsx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = ExcelParser().parse(p)
|
|
by_name = {t.name: t for t in result.tables}
|
|
assert "機能一覧" in by_name
|
|
assert result.mixed, "混合样本应产出段落"
|
|
mixed = result.mixed[0]
|
|
assert len(mixed.paragraphs) == 2 # 表格段 + 碎片段（・/■ 连续）
|
|
assert [p.kind for p in mixed.paragraphs] == ["table", "free_text"]
|
|
# 表格段无碎片污染
|
|
table = [p.table for p in mixed.paragraphs if p.kind == "table"][0]
|
|
assert table.rows[0]["機能ID"].value == "F101"
|
|
assert len(table.rows) == 3
|
|
# 碎片段含 ・ 与 ■ 两行文本
|
|
ft = [p for p in mixed.paragraphs if p.kind == "free_text"][0]
|
|
assert "改修ポイント" in (ft.text or "")
|
|
assert "対象期間" in (ft.text or "")
|
|
|
|
|
|
def test_word_template_sample_chapters_and_placeholders():
|
|
p = _d("概要設計書テンプレート.docx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = WordTemplateParser().parse(p)
|
|
headings = [s for s in result.sections if s.type == "heading"]
|
|
h1 = [h for h in headings if h.level == 1]
|
|
assert len(h1) == 7
|
|
assert h1[0].name == "1. はじめに"
|
|
assert h1[-1].name == "7. バッチ一覧"
|
|
assert "section:introduction" in result.placeholders
|
|
assert "doc_title" in result.placeholders
|
|
bookmarks = [s for s in result.sections if s.type == "bookmark"]
|
|
assert len(bookmarks) == 1
|
|
assert bookmarks[0].name == "template_start"
|
|
|
|
|
|
def test_rule_doc_sample_markdown_and_category():
|
|
p = _d("記入規則.docx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = RuleDocParser().parse(p, category="write")
|
|
assert result.category == "write"
|
|
assert result.file_type == "word"
|
|
assert "# 1. 機能一覧の書き方" in result.markdown_content
|
|
assert "- 機能ID は F001 から連番で付与する。" in result.markdown_content
|
|
|
|
|
|
def test_write_instruction_sample_category_write():
|
|
p = _d("概要設計做成説明書.docx")
|
|
if not p.exists():
|
|
pytest.skip("样本缺失")
|
|
result = RuleDocParser().parse(p, category="write")
|
|
assert result.category == "write"
|
|
assert "# 2. 機能一覧" in result.markdown_content
|
|
|
|
|
|
def test_source_parser_full_sample_assembly():
|
|
xlsx = _x("要件定義_新規開発.xlsx")
|
|
template = _d("概要設計書テンプレート.docx")
|
|
rule = _d("記入規則.docx")
|
|
instr = _d("概要設計做成説明書.docx")
|
|
if not all(p.exists() for p in [xlsx, template, rule, instr]):
|
|
pytest.skip("样本缺失")
|
|
result = SourceParser().parse(
|
|
requirement_paths=[xlsx],
|
|
template_path=template,
|
|
write_instruction_paths=[instr],
|
|
rule_paths=[rule],
|
|
)
|
|
assert result.tables
|
|
assert result.template is not None
|
|
assert len(result.rule_docs) == 2
|
|
assert all(r.category == "write" for r in result.rule_docs) |