feat: SourceParser 门面全量输入聚合 StructuredSource

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,
+        )