import fs from "fs";
import path from "path";
import pdfParse from "pdf-parse";

const [inputPath, outputPath, mode = "all"] = process.argv.slice(2);

if (!inputPath || !outputPath) {
  console.error("Usage: inputPath outputPath [mode]");
  process.exit(1);
}

try {
  console.log(`Reading PDF: ${inputPath}...`);
  const dataBuffer = fs.readFileSync(inputPath);

  const data = await pdfParse(dataBuffer);

  let result;

  if (mode === "text") {
    result = { text: data.text };
  } else if (mode === "metadata") {
    result = {
      pages: data.numpages,
      info: data.info,
      metadata: data.metadata,
    };
  } else {
    // mode === "all"
    result = {
      text: data.text,
      pages: data.numpages,
      info: data.info,
      metadata: data.metadata,
    };
  }

  // Ensure output directory exists
  const dir = path.dirname(outputPath);
  if (dir && dir !== ".") {
    fs.mkdirSync(dir, { recursive: true });
  }

  fs.writeFileSync(outputPath, JSON.stringify(result, null, 2));

  console.log(`\n✓ Extracted PDF content`);
  console.log(`  Pages: ${data.numpages}`);
  console.log(`  Text length: ${data.text.length} characters`);
  console.log(`  Mode: ${mode}`);
  console.log(`  Written to: ${outputPath}`);

  console.log(
    JSON.stringify({
      success: true,
      inputPath,
      outputPath,
      pages: data.numpages,
      textLength: data.text.length,
      mode,
    })
  );
} catch (error) {
  console.error("Error:", error.message);
  process.exit(1);
}