fix(writer): 无锚点子章归并父章生成 + 注入后裸重复子节去重
- template_mapper: 按 design §6.5 仅 Heading level<=1 起章，H2/H3 归入
父章 sub_headings（此前每个 heading 独立成章，无 {{section:id}} 锚点的
6 个子章生成后被静默丢弃）
- models: ChapterSpec.sub_headings 字段；to_vars 暴露 sub_headings 变量
- writer_agent: prompt 新增【小节约束】（有子节时按小节顺序以 level=2
heading 组织，不得遗漏或新增）
- docx_injector: 注入后删除同章内与已生成标题同名且完全无内容的模板裸
H2/H3（保守策略：带内容的模板子节保留）
- 真实试运行验证：7 章 / 无静默丢弃告警 / 14 个 H2 无重复
This commit is contained in:
@@ -49,6 +49,7 @@ class DocxInjector:
|
||||
def inject(self, sections: dict[str, list[Block]], meta: dict[str, str]) -> DocxDocument:
|
||||
doc = Document(self._template_path)
|
||||
self._inject_sections(doc, sections)
|
||||
self._dedupe_bare_subheadings(doc)
|
||||
self._inject_inline(doc, meta)
|
||||
|
||||
# 残留检查（design §6.6 规范约束）
|
||||
@@ -57,6 +58,75 @@ class DocxInjector:
|
||||
raise DocxInjectError(f"占位符残留未替换：{residue}")
|
||||
return doc
|
||||
|
||||
# ---------- 裸子节去重（design §6.5：H2/H3 归并进父章生成后） ----------
|
||||
|
||||
@staticmethod
|
||||
def _heading_level(style_name: str | None) -> int | None:
|
||||
"""样式名 → Heading 层级；非 Heading 样式返回 None。"""
|
||||
if not style_name or not style_name.startswith("Heading"):
|
||||
return None
|
||||
tail = style_name[len("Heading"):].strip()
|
||||
try:
|
||||
return int(tail)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
def _iter_body_items(self, doc: DocxDocument):
|
||||
"""按文档顺序产出 (element, kind, text, style)。kind: "p" | "tbl"。"""
|
||||
for child in doc.element.body.iterchildren():
|
||||
if child.tag == qn("w:p"):
|
||||
para = Paragraph(child, doc)
|
||||
style = para.style.name if para.style is not None else ""
|
||||
yield child, "p", para.text.strip(), style
|
||||
elif child.tag == qn("w:tbl"):
|
||||
yield child, "tbl", "", ""
|
||||
|
||||
def _dedupe_bare_subheadings(self, doc: DocxDocument) -> None:
|
||||
"""删除「裸重复子节标题」：同一 H1 章内，与更早的同级同名标题重复、
|
||||
且其后到下一个标题/表格之间无任何实质内容的模板自带 H2/H3。
|
||||
|
||||
背景：§6.5 将 H2/H3 归并进父章生成（生成内容含小节标题），模板原有
|
||||
空 H2/H3 会与之重复。仅删完全空的重复标题（保守：模板子节下有内容则保留）。
|
||||
"""
|
||||
items = list(self._iter_body_items(doc))
|
||||
to_remove: set = set()
|
||||
last_h1_idx = -1
|
||||
for i, (_, kind, text, style) in enumerate(items):
|
||||
if kind != "p":
|
||||
continue
|
||||
level = self._heading_level(style)
|
||||
if level is None:
|
||||
continue
|
||||
if level <= 1:
|
||||
last_h1_idx = i
|
||||
continue
|
||||
# 裸判定：直到下一个标题/表格前，只有空段落
|
||||
bare = True
|
||||
for j in range(i + 1, len(items)):
|
||||
_el2, kind2, text2, style2 = items[j]
|
||||
if kind2 == "tbl":
|
||||
bare = False
|
||||
break
|
||||
if self._heading_level(style2) is not None:
|
||||
break
|
||||
if text2:
|
||||
bare = False
|
||||
break
|
||||
if not bare or text == "":
|
||||
continue
|
||||
# 同章内存在更早的同级同名标题（即注入生成的那份，带内容）
|
||||
dup = any(
|
||||
items[k][1] == "p"
|
||||
and self._heading_level(items[k][3]) == level
|
||||
and items[k][2] == text
|
||||
and last_h1_idx < k < i
|
||||
for k in range(last_h1_idx + 1, i)
|
||||
)
|
||||
if dup:
|
||||
to_remove.add(items[i][0])
|
||||
for el in to_remove:
|
||||
el.getparent().remove(el)
|
||||
|
||||
# ---------- 内部 ----------
|
||||
|
||||
def _inject_sections(self, doc: DocxDocument, sections: dict[str, list[Block]]) -> None:
|
||||
|
||||
@@ -95,6 +95,7 @@ class ChapterSpec:
|
||||
chapter_id: str
|
||||
title: str
|
||||
section_placeholder: str | None = None # 如 "{{section:db_design}}"，无则 None
|
||||
sub_headings: list[str] = field(default_factory=list) # 本章 H2/H3 子节标题（§6.5 归并）
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -120,6 +121,9 @@ class GenerationContext:
|
||||
"write_rules": "\n".join(self.write_rules),
|
||||
"design_rules": "\n".join(self.design_rules),
|
||||
"template_styles": ", ".join(sorted(self.template_styles)),
|
||||
"sub_headings": "\n".join(
|
||||
f"- {h}" for h in (getattr(tm, "sub_headings", None) or [])
|
||||
),
|
||||
"prior_state": str(self.prior_state) if self.prior_state is not None else "",
|
||||
"data": _format_chapter_data(
|
||||
self.structured_source,
|
||||
|
||||
@@ -3,6 +3,10 @@
|
||||
真实 ParsedTemplate.sections 为 ChapterMarker 列表；章节由 type=="heading" 起，
|
||||
紧随其后的 type=="placeholder" 且形如 `section:<id>` 的标记归属该章，
|
||||
用于确定 chapter_id 与 section_placeholder（语言无关、按文档顺序）。
|
||||
|
||||
design.md §6.5 映射规则：仅 Heading level<=1 起章（1 章 = 1 次生成循环）；
|
||||
level>=2 的节/小节归入当前章 sub_headings，随本章一并生成——避免无
|
||||
{{section:id}} 锚点的子章「生成后静默丢弃」。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -21,6 +25,11 @@ def map_template(parsed: ParsedTemplate) -> list[ChapterSpec]:
|
||||
for ch in getattr(parsed, "sections", []):
|
||||
t = getattr(ch, "type", None)
|
||||
if t == "heading":
|
||||
level = int(getattr(ch, "level", 1) or 1)
|
||||
if level > 1 and current is not None:
|
||||
# §6.5：节/小节归入父章，不独立成章
|
||||
current.sub_headings.append(getattr(ch, "name", ""))
|
||||
continue
|
||||
idx += 1
|
||||
current = ChapterSpec(
|
||||
chapter_id=f"chapter_{idx}", title=getattr(ch, "name", ""), section_placeholder=None
|
||||
|
||||
@@ -18,12 +18,16 @@ from genesis.writer.exceptions import WriterGenerationError
|
||||
WRITER_PROMPT_TEMPLATE = (
|
||||
"你是概要设计书撰写专家。\n"
|
||||
"章节: {{chapter_id}} {{title}}\n"
|
||||
"本章小节结构:\n{{sub_headings}}\n"
|
||||
"写入规则:\n{{write_rules}}\n"
|
||||
"设计规则:\n{{design_rules}}\n"
|
||||
"模板样式:\n{{template_styles}}\n"
|
||||
"影响调查上下文:\n{{impact}}\n"
|
||||
"参考资料（本章对应数据）:\n{{data}}\n"
|
||||
"请输出符合 schema 的章节内容 JSON。\n"
|
||||
"【小节约束】若上方「本章小节结构」非空，必须按该小节顺序组织内容，"
|
||||
"每个小节以 type=heading、level=2 的内容块开头（标题使用小节原文），随后为该小节的内容块；"
|
||||
"不得遗漏或新增小节。为空时按章节主题自行组织。\n"
|
||||
"【主题约束】本章必须且仅围绕标题「{{title}}」所对应的主题撰写，"
|
||||
"严格以「参考资料（本章对应数据）」中的要件定义数据和「影响调查上下文」为核心依据；"
|
||||
"禁止输出与本章无关的系统整体架构、通用设计说明等内容，禁止套用其他章节的主题。"
|
||||
|
||||
Reference in New Issue
Block a user