gostyan/docx-skill-4-cn-paper/docx-editor-cn

python scripts/office/soffice.py --headless --convert-to docx document.doc

# Text extraction with tracked changes
pandoc --track-changes=all document.docx -o output.md
 
# Raw XML access
python scripts/office/unpack.py document.docx unpacked/

python scripts/office/soffice.py --headless --convert-to pdf document.docx
pdftoppm -jpeg -r 150 document.pdf page

python scripts/accept_changes.py input.docx output.docx

const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun,
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
        TableOfContents, HeadingLevel, BorderStyle, WidthType, ShadingType,
        VerticalAlign, PageNumber, PageBreak } = require('docx');
const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer));

python scripts/office/validate.py doc.docx

// Chinese academic papers use A4 with 2.5cm margins on all sides
sections: [{
  properties: {
    page: {
      size: {
        width: 11906,   // A4 width in DXA
        height: 16838   // A4 height in DXA
      },
      margin: { top: 1418, right: 1418, bottom: 1418, left: 1418 } // 2.5cm = 1418 DXA
    }
  },
  children: [/* content */]
}]

size: {
  width: 12240,   // Pass SHORT edge as width
  height: 15840,  // Pass LONG edge as height
  orientation: PageOrientation.LANDSCAPE  // docx-js swaps them in the XML
},
// Content width = 15840 - left margin - right margin (uses the long edge)

# Copy the template, edit the CONTENT section, then run:
node scripts/new_doc.js
# Outputs output.docx with all styles, numbering, and page setup pre-configured.
# Change OUTPUT_PATH inside the script if needed.

// ❌ WRONG - never manually insert bullet characters
new Paragraph({ children: [new TextRun("• Item")] })  // BAD
new Paragraph({ children: [new TextRun("\u2022 Item")] })  // BAD
// ✅ CORRECT - use numbering config with LevelFormat.BULLET
const doc = new Document({
  numbering: {
    config: [
      { reference: "bullets",
        levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
      { reference: "numbers",
        levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
    ]
  },
  sections: [{
    children: [
      new Paragraph({ numbering: { reference: "bullets", level: 0 },
        children: [new TextRun("Bullet item")] }),
      new Paragraph({ numbering: { reference: "numbers", level: 0 },
        children: [new TextRun("Numbered item")] }),
    ]
  }]
});
// ⚠️ Each reference creates INDEPENDENT numbering
// Same reference = continues (1,2,3 then 4,5,6)
// Different reference = restarts (1,2,3 then 1,2,3)

// Inside the CONTENT array:
tableCaption('符号说明'),
threeLineTable(
  ['符号', '说明'],                       // headers
  [['S', '状态空间'], ['A', '动作空间']], // data rows
  [1800, 7270]                            // DXA column widths; must sum to 9070
),

# Insert after paragraph containing anchor text:
python scripts/table.py unpacked/ "1-1" "符号说明" \\
    --headers "符号,说明" \\
    --rows '[["S","状态空间"],["A","动作空间"]]' \\
    --anchor "以下是符号说明"
 
# Custom column widths (must sum to 9070):
python scripts/table.py unpacked/ "2-1" "参数" \\
    --headers "参数,取值,说明" \\
    --rows '[["lr","0.001","学习率"]]' \\
    --widths "1800,1500,5770"
 
# Print XML snippet only (no file modification):
python scripts/table.py --caption "示例" \\
    --headers "列1,列2" --rows '[["a","b"]]'

// CRITICAL: type parameter is REQUIRED
new Paragraph({
  children: [new ImageRun({
    type: "png", // Required: png, jpg, jpeg, gif, bmp, svg
    data: fs.readFileSync("image.png"),
    transformation: { width: 200, height: 150 },
    altText: { title: "Title", description: "Desc", name: "Name" } // All three required
  })]
})

// CRITICAL: PageBreak must be inside a Paragraph
new Paragraph({ children: [new PageBreak()] })
// Or use pageBreakBefore
new Paragraph({ pageBreakBefore: true, children: [new TextRun("New page")] })

// The overridden Heading1/2/3 styles (defined in paragraphStyles above) include outlineLevel,
// which TableOfContents uses to build the TOC. Using heading: HeadingLevel.HEADING_X on
// each paragraph applies that overridden style automatically — giving both TOC support AND
// the custom SimHei/size formatting. Do NOT skip paragraphStyles and rely on built-in styles.
new TableOfContents("目录", { hyperlink: true, headingStyleRange: "1-3" })
// Apply to heading paragraphs — heading property applies the overridden style:
new Paragraph({
  heading: HeadingLevel.HEADING_1, // → w:pStyle "Heading1" (SimHei 16pt, outlineLevel:0)
  children: [new TextRun("一、引言")]
})
new Paragraph({
  heading: HeadingLevel.HEADING_2, // → w:pStyle "Heading2" (SimHei 14pt, outlineLevel:1)
  children: [new TextRun("1.1 研究背景")]
})

sections: [{
  properties: {
    page: { margin: { top: 1418, right: 1418, bottom: 1418, left: 1418 } } // 2.5cm = 1418 DXA
  },
  headers: {
    default: new Header({ children: [new Paragraph({ children: [new TextRun("Header")] })] })
  },
  footers: {
    default: new Footer({ children: [new Paragraph({
      children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] })]
    })] })
  },
  children: [/* content */]
}]

// H1 — Chinese numerals in text (no Word numbering)
h1Chinese('一、引言')   // → "一、引言"  (Heading1 style)