diff --git a/backend/app/knowledge/parser.py b/backend/app/knowledge/parser.py index dabe73b..e343d39 100644 --- a/backend/app/knowledge/parser.py +++ b/backend/app/knowledge/parser.py @@ -190,11 +190,44 @@ def _frontmatter(markdown: str) -> tuple[str, int] | None: offset = content_start for raw in markdown[content_start:].splitlines(keepends=True): if re.fullmatch(r"(?:---|\.\.\.)[ \t]*", raw.rstrip("\r\n")): - return markdown[content_start:offset], offset + len(raw) + candidate = markdown[content_start:offset] + if not candidate.strip() or _metadata_intent(candidate): + return candidate, offset + len(raw) + return None # Ordinary Markdown between thematic breaks. offset += len(raw) + if not _metadata_intent(markdown[content_start:]): + return None raise ApiError(422, "INVALID_EMBEDDING_POLICY", "Frontmatter 未闭合，请补全独立一行的结束分隔符后再保存。") +def _metadata_intent(content: str) -> bool: + """A thematic break alone is not a declaration of YAML metadata.""" + # An explicit policy must fail closed even when other header lines are broken. + fence_marker = None + for line in content.splitlines(): + fence = _FENCE_RE.match(line) + if fence_marker is not None: + marker = fence.group(1) if fence else "" + if marker.startswith(fence_marker[0]) and len(marker) >= len(fence_marker): + fence_marker = None + continue + if fence: + fence_marker = fence.group(1) + continue + if re.match(r"(?i)^[ \t]*[\"']?embedding_local_only[\"']?[ \t]*:", line): + return True + try: + if isinstance(yaml.compose(content, Loader=yaml.SafeLoader), yaml.MappingNode): + return True + except yaml.YAMLError: + pass + first = next((line.strip() for line in content.splitlines() + if line.strip() and not line.lstrip().startswith("#")), "") + # Preserve errors for incomplete key/value headers, including flow mappings. + return bool(re.match(r"(?:[\w.-]+|[\"'][^\"']+[\"'])\s*:(?:\s|$)", first) + or (first.startswith("{") and ":" in first)) + + def _utf16_len(text: str) -> int: return len(text.encode("utf-16-le")) // 2 diff --git a/backend/tests/test_policy_and_migrations.py b/backend/tests/test_policy_and_migrations.py index 6fbc7ae..17e3f9d 100644 --- a/backend/tests/test_policy_and_migrations.py +++ b/backend/tests/test_policy_and_migrations.py @@ -165,3 +165,41 @@ def test_bom_save_and_invalid_update_never_use_remote(monkeypatch): assert (get_settings().vault_path/note.file_path).read_text(encoding='utf-8')==markdown assert (await note_service.get_note(note.note_id)).markdown==markdown asyncio.run(scenario()) + + +@pytest.mark.parametrize('markdown', ['---', '---\n\n# Title\n\nNormal body', '---\n\nNormal body\n\n---\n\nLast paragraph', '---\n\n```python\nprint(1)\n```\n---']) +def test_thematic_breaks_are_not_frontmatter(markdown): + note = parse_note(markdown=markdown,file_path='ordinary.md',folder='',created_at=datetime.now(timezone.utc),updated_at=datetime.now(timezone.utc)) + assert not note.embedding_local_only + assert note.blocks[0].content == '---' + assert any(block.content == markdown.split('\n\n')[-1] for block in note.blocks) or '```' in markdown + + +@pytest.mark.parametrize('header', ['title: Sample\nembedding_local_only: true', '"embedding_local_only": true', 'title: [broken\nembedding_local_only: true', '{embedding_local_only: true']) +def test_unclosed_metadata_still_fails_closed(header): + with pytest.raises(ApiError) as error: + parse_note(markdown='---\n'+header,file_path='private.md',folder='',created_at=datetime.now(timezone.utc),updated_at=datetime.now(timezone.utc)) + assert error.value.code == 'INVALID_EMBEDDING_POLICY' + + +def test_thematic_break_note_can_save_and_rebuild(): + import asyncio + from app.services import note_service, index_service + from app.contracts import IndexRebuildRequest + async def scenario(): + markdown='---\n\n# Title\n\nNormal body' + note=await note_service.create_note(title='Divider',markdown=markdown,folder=None,tags=[]) + assert note.blocks[0].content == '---' + assert (await index_service.rebuild(IndexRebuildRequest())).status == 'completed' + loaded=await note_service.get_note(note.note_id) + assert loaded.markdown == markdown + assert [b.content for b in loaded.blocks] == [b.content for b in note.blocks] + asyncio.run(scenario()) + + +def test_thematic_break_with_policy_example_is_ordinary_markdown(): + markdown='---\n\n```yaml\nembedding_local_only: true\n```\n\n---\n\nExplanation' + note=parse_note(markdown=markdown,file_path='example.md',folder='',created_at=datetime.now(timezone.utc),updated_at=datetime.now(timezone.utc)) + assert not note.embedding_local_only + assert any('embedding_local_only: true' in block.content for block in note.blocks) + assert note.blocks[0].content=='---' diff --git a/docs/retrospectives/阶段F-Embedding与知识库问题与解决方案.md b/docs/retrospectives/阶段F-Embedding与知识库问题与解决方案.md index 46b9dfe..9314922 100644 --- a/docs/retrospectives/阶段F-Embedding与知识库问题与解决方案.md +++ b/docs/retrospectives/阶段F-Embedding与知识库问题与解决方案.md @@ -27,6 +27,7 @@ | F-09 | 简单字符串比较忽略 YAML 语法 | 注释等合法写法可能关闭本地限制 | 解析 YAML 节点，非法策略明确拒绝 | | F-10 | 迁移 DDL 与版本号分开提交 | 中断后重启报重复列 | 原子迁移、并发重检及旧半迁移恢复 | | F-11 | BOM 与未闭合头部被当作无策略 | 本地限定正文可能进入普通 API 路由 | 统一 frontmatter 边界，异常头部拒绝保存 | +| F-12 | 普通 Markdown 分割线误判为头部 | 正常笔记保存失败、重建中止 | 按元数据声明识别头部，保留普通正文 | ## 3. F-01 / F-03：模型可用不等于索引可用 @@ -137,6 +138,16 @@ embedding_local_only: true ## 9. 工程经验 +### F-12：普通分割线与元数据头部消歧 + +F-11 修复后，`---` 和 `---\n\n# Title\n\n正文` 等合法 Markdown 被误判为未闭合 frontmatter，原先能够保存的笔记被拒绝；库中已有此类文件时全量重建也会失败。 + +实际方案：开头分隔线仅作为候选，继续判断内容是否声明元数据。YAML 映射、以键值形式开始的头部或显式 `embedding_local_only` 声明按元数据处理，缺少结束行仍报错；普通段落、标题和代码块按正文保留，包括之后再次出现分割线的情况。已有闭合空头部继续兼容。 + +显式本地策略即使与其他损坏的 YAML 行共存，也不能退成普通正文。无结束分隔符的键值头部仍视为错误；普通文章中有歧义的开头键值形式应避免紧随文件首行 `---`。回归覆盖分割线正文解析、真实保存和重建、BOM 与本地策略原有拒绝规则。 + +围栏代码块中的策略示例不算真实声明，保留为 Markdown 正文。验证记录：首批修复后全量后端 542 项通过；补充围栏示例识别后，解析、迁移与检索相关 130 项通过。本轮未修改前端，未调用真实外部模型。 + ### F-11：frontmatter 边界与 BOM 审阅通过隔离保存链路复现：普通 `---` 头部返回 `local_only=True`，加 UTF-8 BOM 或移除结束分隔线后却返回 `False`。原因是策略、元数据和正文分别使用 `startswith` 与子串查找判断头部；未识别成功时静默按无策略处理。