fix(rag)

[TimeBomb2018]

replace semicolon separators with newlines in Excel parser output

Summary by Sourcery

错误修复：

• 修正 Excel 解析器的单元格拼接方式，将字段与工作表注释以换行符分隔，以改进后续处理效果。

Original summary in English

Summary by Sourcery

Bug Fixes:

• Correct Excel parser cell concatenation to separate fields and sheet annotations with newlines for improved downstream processing.

[sourcery-ai]

审阅者指南（在小型 PR 上折叠）

审阅者指南

Excel RAG 解析器现在输出多行文本，而不是用分号分隔的字段，从而提高了可读性，并在存在工作表名称时将其保留在独立的一行。

Excel 解析器行到文本格式变更的流程图

flowchart TD
  A[Read Excel sheet row] --> B[Collect values into fields list]
  B --> C{Has_header_only_or_data_rows}
  C --> D[Data rows: build fields per row]
  C --> E[Header only: use header_fields]
  D --> F[Join fields with newline separator]
  E --> F
  F --> G{Sheetname_is_generic_sheet}
  G -- Yes --> H[Append nothing]
  G -- No --> I[Append newline then em_dash then sheetname]
  H --> J[Append formatted line to result list]
  I --> J
  J --> K[Return multiline text for RAG consumption]

Loading

文件级变更

变更	详情	文件
将 Excel 解析器行/字符串格式从分号分隔输出改为换行分隔输出。	在拼接普通行的单元格字段时，将 "; ".join(...) 替换为 "\n".join(...) 对于非默认工作表名称，确保在追加工作表名称前先追加一个换行符，并将工作表名称置于新的一行 在仅有表头的情形下，也改为用换行符而不是分号来拼接表头字段，以保持一致性，同时保持工作表后缀格式不变	api/app/core/rag/deepdoc/parser/excel_parser.py

---

提示与命令

与 Sourcery 交互

• 触发新审阅： 在 pull request 上评论 @sourcery-ai review。
• 继续讨论： 直接回复 Sourcery 的审阅评论。
• 从审阅评论生成 GitHub issue： 通过回复审阅评论的方式，请求 Sourcery 从该评论创建一个 issue。你也可以回复审阅评论 @sourcery-ai issue 来从该评论创建一个 issue。
• 生成 pull request 标题： 在 pull request 标题的任意位置写上 @sourcery-ai，即可随时生成标题。你也可以在 pull request 上评论 @sourcery-ai title 来（重新）生成标题。
• 生成 pull request 摘要： 在 pull request 正文的任意位置写上 @sourcery-ai summary，即可在你想要的位置随时生成 PR 摘要。你也可以在 pull request 上评论 @sourcery-ai summary 来（重新）生成摘要。
• 生成审阅者指南： 在 pull request 上评论 @sourcery-ai guide，即可在任何时候（重新）生成审阅者指南。
• 解决所有 Sourcery 评论： 在 pull request 上评论 @sourcery-ai resolve，即可解决所有 Sourcery 评论。如果你已经处理完所有评论且不想再看到它们，这会很有用。
• 关闭所有 Sourcery 审阅： 在 pull request 上评论 @sourcery-ai dismiss，即可关闭所有现有的 Sourcery 审阅。若你想从一次全新的审阅开始，这尤其有用——别忘了评论 @sourcery-ai review 来触发新的审阅！

自定义你的使用体验

访问你的 控制面板 以：

• 启用或禁用审阅功能，例如 Sourcery 生成的 pull request 摘要、审阅者指南等。
• 更改审阅语言。
• 添加、移除或编辑自定义审阅说明。
• 调整其他审阅设置。

获取帮助

• 如有问题或反馈，请联系支持团队。
• 访问我们的文档以获取详细指南和信息。
• 通过关注我们的 X/Twitter、LinkedIn 或 GitHub 与 Sourcery 团队保持联系。

Original review guide in English

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Excel RAG parser now outputs multi-line text instead of semicolon-separated fields, improving readability and keeping sheet names on their own line when present.

Flow diagram for Excel parser row-to-text formatting change

flowchart TD
  A[Read Excel sheet row] --> B[Collect values into fields list]
  B --> C{Has_header_only_or_data_rows}
  C --> D[Data rows: build fields per row]
  C --> E[Header only: use header_fields]
  D --> F[Join fields with newline separator]
  E --> F
  F --> G{Sheetname_is_generic_sheet}
  G -- Yes --> H[Append nothing]
  G -- No --> I[Append newline then em_dash then sheetname]
  H --> J[Append formatted line to result list]
  I --> J
  J --> K[Return multiline text for RAG consumption]

Loading

File-Level Changes

Change	Details	Files
Change Excel parser row/string formatting from semicolon-separated to newline-separated output.	Replace "; ".join(...) with "\n".join(...) when joining cell fields for normal rows Ensure sheet names are appended on a new line with a preceding newline character for non-default sheet names Keep header-only case consistent by also joining header fields with newlines instead of semicolons while leaving sheet suffix formatting unchanged	api/app/core/rag/deepdoc/parser/excel_parser.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - 我在这里给出了一些整体反馈：

• 在仅包含表头的分支中，你仍然使用前置空格（" ——"）而不是换行符（"\n——"）来追加工作表名称，这与主分支不一致，并且在你切换到按行分隔输出之后，这很可能也不是你真正想要的行为。

给 AI 代理的提示

Please address the comments from this code review:

## Overall Comments
- In the header-only branch you still append the sheet name with a leading space (`" ——"`) rather than a newline (`"\n——"`), which is inconsistent with the main branch and likely not what you intended after switching to newline-separated output.

---

Sourcery 对开源项目免费——如果你觉得我们的代码审查有帮助，请考虑分享给更多人 ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{帮我变得更有用！请在每条评论上点 👍 或 👎，我会根据你的反馈来改进后续的代码审查。}

Original comment in English

Hey - I've left some high level feedback:

• In the header-only branch you still append the sheet name with a leading space (" ——") rather than a newline ("\n——"), which is inconsistent with the main branch and likely not what you intended after switching to newline-separated output.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In the header-only branch you still append the sheet name with a leading space (`" ——"`) rather than a newline (`"\n——"`), which is inconsistent with the main branch and likely not what you intended after switching to newline-separated output.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}