PDF Merge & Split: a Tokeny case study
Merge multiple PDF files into one, or split by page ranges into separate files. Follow the recorded task, execution screenshots, actual files and verification notes.
By the Tokeny team · Windows · Tokeny 1.7.8 · gpt-6-sol
Prepare the inputs
Create a separate workspace in Tokeny, download and unpack the sample inputs, then select a model that supports tools. The sample uses synthetic data or the public sources named in the article.
- a.pdf
- b.pdf
Send the task to Tokeny
The original task was executed in Chinese. Copying these instructions reproduces the same task; the results below include an English report.
将输入的两份 PDF 按 A 后 B 顺序合并，再把合并结果拆成第 1–2 页和第 3–4 页，核对页数与各页文字。 交付文件：merged.pdf、pages-1-2.pdf、pages-3-4.pdf、pages.json。 验收要点： - 合并 4 页、拆分各 2 页 - 页序为 A1 A2 B1 B2 这是使用合成演示输入或指定公开资料的真实操作案例。请先读取工作空间输入，再实际生成文件并自检。所有写入、脚本与临时服务限于当前工作空间；临时服务只监听 127.0.0.1，执行后关闭；不触达外部收件人、不发布、不付款、不更改系统设置，不调用子智能体。需要公开资料时可读取给定 URL。只启用完成任务必需的工具。另写 report.md（中文）和 report.en.md（英文），简洁、完整，包含输入、处理步骤、真实结果、检查方式和局限；失败或未验证部分如实记录，不能宣称成功。最终回复用中文列出产物、关键结果与待核实项。 排版检查：Word 主标题仅出现一次，标题为黑色且与后续正文或表格保持同页；Excel 表头和长文字不能被窄列截断，合理设置列宽、换行、行高；HTML 在 390px 视口不能整页横向溢出。报告没有固定字数要求，不要为字数反复改写。
The recorded run used an isolated demonstration workspace. Review the commands and file paths before approving operations in your own workspace.
What actually ran
The task was submitted through the Tokeny input box. An online model read the inputs and executed tools. Four synthetic PDF pages exercise real merging, splitting and page-order checks.
Results and verification
Inputs
a.pdf: 2 pagesb.pdf: 2 pages
Processing
- Read both input PDFs and extract text page by page.
- Merge them in A-then-B order into
merged.pdf. - Extract pages 1–2 into
pages-1-2.pdfand pages 3–4 intopages-3-4.pdf. - Write page text, page counts, and order checks to
pages.json.
Actual results
- Merged file:
merged.pdf, 4 pages. - First split:
pages-1-2.pdf, 2 pages. - Second split:
pages-3-4.pdf, 2 pages. - Merge order check: passed; expected order is A1 A2 B1 B2.
Verification
- Reopened every output PDF with
pypdfand counted pages. - Extracted text from each page and compared it item by item with the expected input sequence.
- Detailed per-page text is recorded in
pages.json.
Limitations
Text verification depends on an embedded PDF text layer. Scanned-image pages may yield empty or incomplete extracted text. No OCR or pixel-level visual rendering comparison was performed.
Download and inspect the outputs
The archive contains the files created during this run. Use these checks when adapting the example to your own data.
- Reconcile the reported results against the downloadable sample inputs.
- Open the generated files and check the contents relevant to your task.
- Review the limitations and any unverified steps in the report.