zhtx2024/dsh-pdf

插件Plugin 原生Native ⭐ 2 MIT 文档与写作Docs & Writing界面与主题UI & Themes

PDF解析工具包,适用于DeepSeek Harness:支持pdf_info、pdf_extract_text、pdf_render_page功能,采用pdfjs/内置混合引擎,并为非嵌入CJK PDF提供系统字体渲染。

项目介绍Project Overview

@zhtx2026/dsh-pdf 是 DeepSeek Harness 的 PDF 解析插件,提供 pdf_info、pdf_extract_text、pdf_render_page 三个工具,混合使用 pdfjs 与内置 sysfont 渲染引擎,自动选择以正确处理未嵌入字体的 PDF(如 EasyEDA/JLC EDA 原理图导出的 SimSun/SimHei CJK 字体)。适用于需要解析中文 PDF、原理图或导出页面 PNG 的场景。注意:扫描件无文本层可提取,sysfont 仅针对 UniGB-UCS2-H 编码,大文件全量入内存。

@zhtx2026/dsh-pdf is a PDF parsing plugin for DeepSeek Harness, exposing three agent tools: pdf_info, pdf_extract_text, and pdf_render_page. It pairs pdfjs with a built-in sysfont renderer, auto-selecting the engine to correctly handle PDFs with non-embedded CJK fonts, such as SimSun/SimHei Type0 exports from EasyEDA or JLC EDA schematics. Use it when parsing Chinese documents, schematic PDFs, or rendering pages to PNG. Caveats: scanned PDFs have no extractable text layer, sysfont covers UniGB-UCS2-H only, and large files are fully loaded into memory.

或使用命令行安装(适合开发者)Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add @zhtx2026/dsh-pdf

zhtx2024/dsh-pdf 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

@zhtx2026/dsh-pdf

PDF parsing toolkit for DeepSeek Harness — three agent-facing tools (pdf_info / pdf_extract_text / pdf_render_page) with hybrid engines, including system-font rendering for PDFs with non-embedded CJK fonts (e.g. EasyEDA / JLC EDA schematic exports).

English | 中文

Tags: dsh-plugin · pdf · pdfjs · canvas · schematic · tools

Install

dsh plugin --profile web add @zhtx2026/dsh-pdf

Or from a local checkout during development:

dsh plugin --profile web add link:<path-to-repo>

Then restart DSH (or open a new session) — the three tools and an agent guidance block become available.

Tools

Tool What it does
pdf_info Page count, page sizes (pt), document metadata, and the font list with per-font embedded flags.
pdf_extract_text Extracts text per page; optional page and withPosition (per-line x/y coordinates + font size).
pdf_render_page Renders one page to a PNG (local file) with configurable scale/outDir; engine auto-selection.

Why a custom renderer?

pdfjs-dist cannot render text in PDFs whose fonts are not embedded and lack a ToUnicode map — the classic case is JLC EDA / EasyEDA schematic exports (SimSun/SimHei Type0 fonts with UniGB-UCS2-H encoding): pdfjs emits translateFont failed and drops the glyphs.

dsh-pdf solves this with a two-engine design:

  • pdfjs engine — used when all fonts are embedded (standard PDFs).
  • 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.

Text extraction uses the same auto-selection: embedded fonts → pdfjs text layer; non-embedded fonts → the built-in decoder (which correctly recovers CJK text pdfjs loses).

Example

pdf_info("D:/Downloads/SCH_SA-V11A.pdf")
→ 3 pages, A3 landscape, jsPDF producer, 6 fonts (all non-embedded)

pdf_extract_text("D:/Downloads/SCH_SA-V11A.pdf", { page: 1 })
→ net names, pin numbers, and Chinese labels ("主控板", "嘉立创", …)

pdf_render_page("D:/Downloads/SCH_SA-V11A.pdf", { page: 1, scale: 2 })
→ D:/Downloads/SCH_SA-V11A-pages/page-1.png  (2396×1698, engine: sysfont)

Architecture

  • lib/index.js — cordis plugin entry (name, inject, apply); 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).
  • lib/pdf-core.js — self-contained engine: PDF object parser, font scanner, pdfjs loading with fs-based CMapReaderFactory/StandardFontDataFactory (Node 24's global fetch doesn't speak file://), the built-in text extractor, and the sysfont renderer.
  • cordis.patch.yml — the dsh.bundle.patch insert row.

Limitations

  • 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); exotic CID fonts fall back to pdfjs.
  • Large PDFs are parsed fully into memory.

License

MIT

上一个 Prev dsh-outcome-loop 下一个 Next dsh-polling