big-rag-rus

/**
 * Generate test fixture files for all supported document formats.
 * Run: node test-fixtures/generate-fixtures.js
 */
const fs = require("fs");
const path = require("path");
const JSZip = require("jszip");
const XLSX = require("xlsx");

const OUT_DIR = path.join(__dirname);

async function generateDocx() {
  const zip = new JSZip();

  // [Content_Types].xml
  zip.file("[Content_Types].xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">' +
    '<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>' +
    '<Default Extension="xml" ContentType="application/xml"/>' +
    '<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>' +
    '</Types>'
  );

  // _rels/.rels
  zip.file("_rels/.rels",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">' +
    '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>' +
    '</Relationships>'
  );

  // word/document.xml
  zip.file("word/document.xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">' +
    '<w:body>' +
    '<w:p><w:r><w:t>Big RAG DOCX test paragraph one.</w:t></w:r></w:p>' +
    '<w:p><w:r><w:t>Second paragraph with more content for testing.</w:t></w:r></w:p>' +
    '</w:body>' +
    '</w:document>'
  );

  const buf = await zip.generateAsync({ type: "nodebuffer" });
  fs.writeFileSync(path.join(OUT_DIR, "sample.docx"), buf);
  console.log("✅ sample.docx");
}

async function generatePptx() {
  const zip = new JSZip();

  // [Content_Types].xml
  zip.file("[Content_Types].xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">' +
    '<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>' +
    '<Default Extension="xml" ContentType="application/xml"/>' +
    '<Override PartName="/ppt/presentation.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.presentation.main+xml"/>' +
    '<Override PartName="/ppt/slides/slide1.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>' +
    '<Override PartName="/ppt/slides/slide2.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>' +
    '</Types>'
  );

  // _rels/.rels
  zip.file("_rels/.rels",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">' +
    '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="ppt/presentation.xml"/>' +
    '</Relationships>'
  );

  // ppt/_rels/presentation.xml.rels
  zip.file("ppt/_rels/presentation.xml.rels",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">' +
    '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>' +
    '<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide2.xml"/>' +
    '</Relationships>'
  );

  // ppt/presentation.xml
  zip.file("ppt/presentation.xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<p:presentation xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">' +
    '<p:sldIdLst>' +
    '<p:sldId id="256" r:id="rId1"/>' +
    '<p:sldId id="257" r:id="rId2"/>' +
    '</p:sldIdLst>' +
    '</p:presentation>'
  );

  // ppt/slides/slide1.xml
  zip.file("ppt/slides/slide1.xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<p:sld xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">' +
    '<p:cSld><p:spTree><p:nvGrpSpPr><p:cNvPr id="1" name=""/></p:nvGrpSpPr>' +
    '<p:sp><p:txBody><a:p><a:r><a:t>Big RAG PPTX slide one content for testing.</a:t></a:r></a:p></p:txBody></p:sp>' +
    '</p:spTree></p:cSld>' +
    '</p:sld>'
  );

  // ppt/slides/slide2.xml
  zip.file("ppt/slides/slide2.xml",
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>' +
    '<p:sld xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">' +
    '<p:cSld><p:spTree><p:nvGrpSpPr><p:cNvPr id="1" name=""/></p:nvGrpSpPr>' +
    '<p:sp><p:txBody><a:p><a:r><a:t>Second slide with additional text data.</a:t></a:r></a:p></p:txBody></p:sp>' +
    '</p:spTree></p:cSld>' +
    '</p:sld>'
  );

  const buf = await zip.generateAsync({ type: "nodebuffer" });
  fs.writeFileSync(path.join(OUT_DIR, "sample.pptx"), buf);
  console.log("✅ sample.pptx");
}

function generateXlsx() {
  const wb = XLSX.utils.book_new();
  const data = [
    ["Name", "Value", "Description"],
    ["Test Row 1", "100", "First test row for Big RAG"],
    ["Test Row 2", "200", "Second test row for parsing"],
  ];
  const ws = XLSX.utils.aoa_to_sheet(data);
  XLSX.utils.book_append_sheet(wb, ws, "Sheet1");
  XLSX.writeFile(wb, path.join(OUT_DIR, "sample.xlsx"));
  console.log("✅ sample.xlsx");
}

function generateCsv() {
  const csv = [
    "Name,Value,Description",
    "CSV Row 1,100,First CSV test row",
    "CSV Row 2,200,Second CSV test row",
  ].join("\n");
  fs.writeFileSync(path.join(OUT_DIR, "sample.csv"), csv, "utf-8");
  console.log("✅ sample.csv");
}

async function main() {
  console.log("Generating test fixtures...");
  await generateDocx();
  await generatePptx();
  generateXlsx();
  generateCsv();
  console.log("\nAll fixtures generated in test-fixtures/");
}

main().catch((err) => {
  console.error("Error generating fixtures:", err);
  process.exit(1);
});