Redact Skill#

Privacy redaction toolkit using PPStructureV3 OCR for text detection and replacement.

Scripts#

ScriptFormatCommandread.pyImages / PDF / Word / PowerPointread.py <input> [--info] [--mode json]``redact-image.pyImages (png, jpg, etc.)redact-image.py <input> <rules.csv> <output>``redact-pdf.pyPDFredact-pdf.py <input> <rules.csv> <output>``redact-document.pyWord (docx, doc)redact-document.py <input> <rules.csv> <output>``redact-presentation.pyPowerPoint (pptx, ppt)redact-presentation.py <input> <rules.csv> <output>

CSV Rules Format#

csv

target_text,replacement_text
张三,李四
手机号,
身份证号,

RuleEffect原文本,新文本Replace with new text原文本,Empty = mask with █ (documents) or solid color block (images/PDF)

Masking Behavior#

FormatEmpty ReplacementImages, PDFSolid color block overlayWord, PowerPoint█ characters (same length as target)

Read Features#

read.py supports:

• Reading text from images, PDF, Word, and PowerPoint files

• OCR for image files and embedded images

• Page-aware output for PDF / Word / PowerPoint

• --info structured output:

  • <page index="...">
  • <image format='markdown' type='ocr'>...</image> for OCR text extracted from images

JSON Output#

Document-like files ( pdf, docx, doc, pptx) output:

json

{
  "type": "pptx",
  "pages": [
    {
      "page_index": 1,
      "content": [
        { "type": "text", "text": "..." },
        { "type": "image", "text": "ocr text..." }
      ]
    }
  ]
}

Image files output:

json

{
  "type": "image",
  "content": "..."
}

Features#

FeatureImagePDFDocumentPresentationRead text✅✅✅✅JSON output✅✅✅✅Text replacement✅✅✅✅Solid color mask✅✅--█ character mask--✅✅OCR detection✅✅✅ (images)✅ (images)Tables-✅✅✅Headers/Footers-✅✅-Embedded images-✅✅✅

Environment Setup#

使用 uv 安装依赖：

bash

# 进入 skill 目录
cd skills/redact

# 同步依赖（自动创建虚拟环境并安装）
uv sync

Dependencies#

• Python 3.10+
• PaddleOCR / PPStructureV3
• python-docx, python-pptx, PyMuPDF, Pillow