feat: WordTemplateParser 章构成/占位符/样式名提取

src/genesis/parsers/_word_common.py

@@ -0,0 +1,11 @@
+"""Word 解析共享小工具（WordTemplateParser / RuleDocParser 复用）。"""
+
+from __future__ import annotations
+
+
+def heading_level(style_name: str) -> int:
+    """从 Heading N 样式名解析大纲级别；非数字/无后缀兜底 1。"""
+    try:
+        return int(style_name.split()[-1])
+    except (ValueError, IndexError):
+        return 1

src/genesis/parsers/word_template_parser.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from docx import Document
+from docx.oxml.ns import qn
+
+from genesis.data_models import ChapterMarker, ParsedTemplate
+from genesis.parsers._word_common import heading_level
+
+# 统一占位符正则：{{键名}} 或 {{键名:章节名}}（spec §3.2）
+PLACEHOLDER_RE = re.compile(r"\{\{([a-z][a-z0-9_]*)(?::([a-z][a-z0-9_]*))?\}\}")
+
+
+class WordTemplateParser:
+    """概要设计模板 docx 解析：章构成 / 占位符 / 样式名提取。"""
+
+    def parse(self, path: str | Path) -> ParsedTemplate:
+        doc = Document(str(path))
+        sections: list[ChapterMarker] = []
+        placeholders: dict[str, str] = {}
+        used_styles: set[str] = set()
+
+        # 文档命名样式（定义集合）
+        defined = {s.name for s in doc.styles if s.name}
+
+        for para in doc.paragraphs:
+            style_name = para.style.name if para.style else "Normal"
+            used_styles.add(style_name)
+            text = para.text
+
+            if style_name.startswith("Heading"):
+                sections.append(ChapterMarker(
+                    type="heading", name=text, level=heading_level(style_name)
+                ))
+
+            for m in PLACEHOLDER_RE.finditer(text):
+                if m.group(2):
+                    key = f"{m.group(1)}:{m.group(2)}"
+                else:
+                    key = m.group(1)
+                placeholders[key] = text
+                sections.append(ChapterMarker(type="placeholder", name=key, level=0))
+
+        # 书签：遍历 body 中全部 bookmarkStart
+        for bm in doc.element.body.iter(qn("w:bookmarkStart")):
+            name = bm.get(qn("w:name"))
+            if name:
+                sections.append(ChapterMarker(type="bookmark", name=name, level=0))
+
+        return ParsedTemplate(
+            file_name=Path(path).name,
+            sections=sections,
+            placeholders=placeholders,
+            styles={"defined": sorted(defined), "used": sorted(used_styles)},
+        )