feat: SourceParser 门面全量输入聚合 StructuredSource

tests/test_source_aggregator.py

@@ -0,0 +1,98 @@
+import pytest
+
+from genesis.data_models import StructuredSource
+from genesis.parsers.source_aggregator import SourceParser
+
+from tests.docx_helpers import make_rule_doc, new_document, save_document
+from tests.excel_helpers import new_workbook, save_workbook
+
+
+def _xlsx(tmp_path, name: str = "source.xlsx") -> str:
+    wb = new_workbook({"機能一覧": [["機能ID", "機能名"], ["A001", "社員登録"]]})
+    path = tmp_path / name
+    wb.save(path)
+    return str(path)
+
+
+def test_parse_full_assembly(tmp_path):
+    xlsx = _xlsx(tmp_path)
+    template = save_document(tmp_path, new_document())
+    rule = make_rule_doc(tmp_path, [("H1", "1. 機能一覧の書き方")])
+    instr = make_rule_doc(tmp_path, [("H1", "2. 機能一覧の作成手順")])
+
+    result = SourceParser().parse(
+        requirement_paths=[xlsx],
+        template_path=template,
+        write_instruction_paths=[instr],
+        rule_paths=[rule],
+    )
+
+    assert isinstance(result, StructuredSource)
+    assert len(result.tables) == 1
+    assert result.template is not None
+    assert result.template.file_name == "source.docx"
+    assert len(result.rule_docs) == 2
+    assert all(r.category == "write" for r in result.rule_docs)
+    assert result.image_analyses == []
+    assert result.existing_system is None
+
+
+def test_parse_without_template_and_rules(tmp_path):
+    xlsx = _xlsx(tmp_path)
+
+    result = SourceParser().parse(requirement_paths=[xlsx])
+
+    assert len(result.tables) == 1
+    assert result.template is None
+    assert result.rule_docs == []
+
+
+def test_parse_missing_requirement_file(tmp_path):
+    with pytest.raises(FileNotFoundError):
+        SourceParser().parse(requirement_paths=[tmp_path / "missing.xlsx"])
+
+
+def test_parse_missing_template_file(tmp_path):
+    xlsx = _xlsx(tmp_path)
+    with pytest.raises(FileNotFoundError):
+        SourceParser().parse(requirement_paths=[xlsx], template_path=tmp_path / "missing.docx")
+
+
+def test_parse_unknown_extension_in_requirements(tmp_path):
+    bad = tmp_path / "note.txt"
+    bad.write_text("hello", encoding="utf-8")
+    with pytest.raises(ValueError, match="不支持的文件类型"):
+        SourceParser().parse(requirement_paths=[bad])
+
+
+def test_parse_unknown_extension_in_rules(tmp_path):
+    bad = tmp_path / "note.txt"
+    bad.write_text("hello", encoding="utf-8")
+    with pytest.raises(ValueError, match="不支持的文件类型"):
+        SourceParser().parse(rule_paths=[bad])
+
+
+def test_parse_unknown_extension_in_template(tmp_path):
+    bad = tmp_path / "note.txt"
+    bad.write_text("hello", encoding="utf-8")
+    with pytest.raises(ValueError, match="不支持的文件类型"):
+        SourceParser().parse(template_path=bad)
+
+
+def test_parse_missing_rule_file(tmp_path):
+    with pytest.raises(FileNotFoundError):
+        SourceParser().parse(rule_paths=[tmp_path / "missing.docx"])
+
+
+def test_parse_extensionless_requirement(tmp_path):
+    bad = tmp_path / "note"
+    bad.write_text("hello", encoding="utf-8")
+    with pytest.raises(ValueError, match="无扩展名"):
+        SourceParser().parse(requirement_paths=[bad])
+
+
+def test_parse_extensionless_rule(tmp_path):
+    bad = tmp_path / "note"
+    bad.write_text("hello", encoding="utf-8")
+    with pytest.raises(ValueError, match="无扩展名"):
+        SourceParser().parse(rule_paths=[bad])