PDF parsing toolkit for DeepSeek Harness
zhtx2024/dsh-pdf · skills
PDF parsing toolkit for DeepSeek Harness: pdfinfo, pdfextracttext, pdfrenderpage with hybrid pdfjs/built-in engines and system-font rendering for non-embedded CJK PDFs.
★ 3GitHub stars
0Forks
2026-08-31Last updated
JavaScriptLanguage
MITLicense
Key features
- Tagsdsh-plugin · pdf · pdfjs · canvas · schematic · tools
- pdfjs engine — used when all fonts are embedded (standard PDFs).
- lib/index.js — cordis plugin entry (name, inject, apply)
- sysfont engine — a built-in content-stream renderer that decodes the PDF text operators (BT/ET, Tf, Tm, Td, Tj, TJ) itself, maps UniGB-UCS2-H/UTF-16BE strings to Unicode, and draws them with system fonts (SimSun, SimHei, Microsoft YaHei, …) via @napi-rs/canvas.
- registers the three tools as native tool objects (plain JSON-Schema parameters and output — no @deepseek-ai/dsh-tools dependency needed) and injects the agent guidance block (systemPrompt.section, order 160).
Requirements
- Scanned/image-only PDFs have no text layer — extraction returns nothing (rendering still works, as a plain image).
- The sysfont renderer assumes Type0 CID codes equal Unicode code points (true for UniGB-UCS2-H exports)
Install command
dsh plugin --profile web add github:zhtx2024/dsh-pdf