feat: SourceParser 门面全量输入聚合 StructuredSource

_AI_USAGE_LOG.md

@@ -65,3 +65,4 @@
 | 2026-08-10 | Agent 实现 | Task1 补记：Word 解析测试基建。新建 tests/docx_helpers.py（new_document/save_document/make_rule_doc，make_rule_doc 支持 H1/H2/H3/List Bullet/普通段落 5 种行），供 Phase3 后续全部任务复用 | tests/docx_helpers.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
 | 2026-08-10 | Agent 实现 | Phase3 Task2 实现：WordTemplateParser 章构成/占位符/样式名提取。新建 src/genesis/parsers/_word_common.py（heading_level 共享 helper，Task2/3 复用，从 Heading N 样式名解析大纲级别，非数字/无后缀兜底 1）与 src/genesis/parsers/word_template_parser.py（PLACEHOLDER_RE 统一占位符正则 {{键名}}/{{键名:章节名}}；Heading 段落→heading 章标记、bookmarkStart→bookmark、占位符→placeholder 并写 placeholders{名:段落上下文}；styles 提取 defined/used 样式名集合去重）；tests/test_word_template_parser.py 按 brief 8 用例（6 解析 + 2 heading_level 兜底分支）；覆盖补齐：bookmark 用例增加无 name 的 bookmarkStart 覆盖 if name 假分支（98%→100%）；TDD 验证 RED（ModuleNotFoundError: No module named 'genesis.parsers._word_common'）→ GREEN（聚焦 8 passed）；pytest 全量 140 passed 覆盖 100.00%（841 stmts/200 br），fail_under=99 达标 | src/genesis/parsers/_word_common.py, src/genesis/parsers/word_template_parser.py, tests/test_word_template_parser.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
 | 2026-08-10 | Agent 实现 | Phase3 Task3 实现：RuleDocParser 规则文档 Markdown 化与分类。新建 src/genesis/parsers/rule_doc_parser.py（body 级遍历保段落/表格交错顺序；Heading N→#×N；列表双通道检测 List 样式或 ・/-/• 前缀；表格→GFM；空段→空行；file_type 固定 word、hash=sha256 hex；复用 _word_common.heading_level 无本地重复）与 tests/test_rule_doc_parser.py 按 brief 6 用例；覆盖补齐：test_parse_empty_document 增加 doc.add_paragraph("") 使空段分支（原 new_document 无任何 w:p 不进分支）达 100%；TDD 验证 RED（ModuleNotFoundError: No module named 'genesis.parsers.rule_doc_parser'）→ GREEN（聚焦 6 passed）；pytest 全量 146 passed 覆盖 100.00%（886 stmts/218 br），fail_under=99 达标 | src/genesis/parsers/rule_doc_parser.py, tests/test_rule_doc_parser.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
+| 2026-08-10 | Agent 实现 | Phase3 Task4 实现：SourceParser 门面全量输入聚合。新建 src/genesis/parsers/source_aggregator.py（角色显式传参无隐式猜测；requirements 校验 .xlsx/.xls 后缀聚合 tables/comments；template 校验 .docx 用 WordTemplateParser 解析；write_instruction+rule 校验 .docx 按 category='write' 归入 rule_docs；不存在抛 FileNotFoundError、未知扩展名抛 ValueError('不支持的文件类型: ...')；image_analyses=[]/existing_system=None 固定）与 tests/test_source_aggregator.py 按 brief 6 用例 + 补 4 用例（模板未知扩展名、规则路径文件缺失、requirements/规则无扩展名兜底 '无扩展名' 文案，覆盖 51/62 行缺失与 or 表达式分支）达 100%；TDD 验证 RED（ModuleNotFoundError: No module named 'genesis.parsers.source_aggregator'）→ GREEN（聚焦 10 passed）；pytest 全量 156 passed 覆盖 100.00%（929 stmts/236 br），fail_under=99 达标 | src/genesis/parsers/source_aggregator.py, tests/test_source_aggregator.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |

src/genesis/parsers/source_aggregator.py

@@ -0,0 +1,73 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from genesis.data_models import StructuredSource
+from genesis.parsers.excel_parser import ExcelParser
+from genesis.parsers.rule_doc_parser import RuleDocParser
+from genesis.parsers.word_template_parser import WordTemplateParser
+
+XLSX_EXTS = (".xlsx", ".xls")
+DOCX_EXT = ".docx"
+
+
+class SourceParser:
+    """全量输入门面：Excel 要件定义 + Word 模板 + Word 规则 → StructuredSource。
+
+    角色由调用方按 api-design file_type 语义显式传入（requirements/template/
+    write_instruction/rules），不做基于文件名的隐式猜测（spec §3.4）。
+    """
+
+    def __init__(self) -> None:
+        self._excel = ExcelParser()
+
+    def parse(
+        self,
+        requirement_paths: list[str | Path] | None = None,
+        template_path: str | Path | None = None,
+        write_instruction_paths: list[str | Path] | None = None,
+        rule_paths: list[str | Path] | None = None,
+    ) -> StructuredSource:
+        requirement_paths = requirement_paths or []
+        write_instruction_paths = write_instruction_paths or []
+        rule_paths = rule_paths or []
+
+        tables = []
+        comments = []
+        for p in requirement_paths:
+            path = Path(p)
+            if path.suffix.lower() not in XLSX_EXTS:
+                raise ValueError(f"不支持的文件类型: {path.suffix or '(无扩展名)'}")
+            if not path.exists():
+                raise FileNotFoundError(str(p))
+            result = self._excel.parse(path)
+            tables.extend(result.tables)
+            comments.extend(result.comments)
+
+        template = None
+        if template_path is not None:
+            tpath = Path(template_path)
+            if tpath.suffix.lower() != DOCX_EXT:
+                raise ValueError(f"不支持的文件类型: {tpath.suffix or '(无扩展名)'}")
+            if not tpath.exists():
+                raise FileNotFoundError(str(template_path))
+            template = WordTemplateParser().parse(tpath)
+
+        rule_docs = []
+        for p in [*write_instruction_paths, *rule_paths]:
+            path = Path(p)
+            if path.suffix.lower() != DOCX_EXT:
+                raise ValueError(f"不支持的文件类型: {path.suffix or '(无扩展名)'}")
+            if not path.exists():
+                raise FileNotFoundError(str(p))
+            # 做成说明书与记入规则均为 Type A 写入规则 → write（api-design §2.2）
+            rule_docs.append(RuleDocParser().parse(path, category="write"))
+
+        return StructuredSource(
+            tables=tables,
+            template=template,
+            rule_docs=rule_docs,
+            image_analyses=[],
+            existing_system=None,
+            comments=comments,
+        )

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])