test: 真实样本 Word 解析集成测试（模板/规则/说明书画属write）

tests/test_real_samples.py

@@ -3,10 +3,17 @@ 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
 
@@ -57,4 +64,60 @@ def test_mixed_sample_segments_detected():
     # 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 "")
+    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)