feat: RuleDocParser 规则文档 Markdown 化与分类

src/genesis/parsers/rule_doc_parser.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+import hashlib
+from pathlib import Path
+
+from docx import Document
+from docx.oxml.ns import qn
+
+from genesis.data_models import RuleDocument
+from genesis.parsers._word_common import heading_level
+
+# 列表项前缀（真实样本为 Normal 样式 + ・ 前缀，样式名通道不足以命中）
+LIST_PREFIXES = ("・", "-", "•")
+
+
+def _is_list_item(text: str, style_name: str) -> bool:
+    """双通道列表检测：List 样式或文本前缀（spec §3.3）。"""
+    if "List" in style_name:
+        return True
+    return text.startswith(LIST_PREFIXES)
+
+
+def _table_to_markdown(table) -> list[str]:
+    """docx 表格 → GFM 表格行。"""
+    lines: list[str] = []
+    for r_idx, row in enumerate(table.rows):
+        cells = [cell.text.replace("|", "\\|").strip() for cell in row.cells]
+        lines.append("| " + " | ".join(cells) + " |")
+        if r_idx == 0:
+            lines.append("| " + " | ".join(["---"] * len(cells)) + " |")
+    return lines
+
+
+class RuleDocParser:
+    """规则文档 docx 解析：Markdown 化 + 分类。"""
+
+    def parse(self, path: str | Path, category: str = "write") -> RuleDocument:
+        doc = Document(str(path))
+        md: list[str] = []
+
+        # 按文档顺序遍历段落与表格（body 级子元素）
+        for child in doc.element.body.iterchildren():
+            tag = child.tag
+            if tag == qn("w:p"):
+                from docx.text.paragraph import Paragraph
+                para = Paragraph(child, doc)
+                text = para.text
+                style_name = para.style.name if para.style else "Normal"
+                stripped = text.strip()
+                if not stripped:
+                    md.append("")
+                elif style_name.startswith("Heading"):
+                    md.append("#" * heading_level(style_name) + " " + stripped)
+                elif _is_list_item(stripped, style_name):
+                    md.append("- " + stripped.lstrip("・-•").strip())
+                else:
+                    md.append(stripped)
+            elif tag == qn("w:tbl"):
+                from docx.table import Table
+                md.extend(_table_to_markdown(Table(child, doc)))
+                md.append("")
+
+        content = "\n".join(md).strip()
+        return RuleDocument(
+            file_name=Path(path).name,
+            category=category,
+            markdown_content=content,
+            source_path=str(path),
+            file_type="word",
+            hash=hashlib.sha256(Path(path).read_bytes()).hexdigest(),
+        )