const fs = require("fs");
const path = require("path");
const { PDFDocument } = require("pdf-lib");

function clean(value) {
  if (value == null) return "";
  return String(value).replace(/\0/g, "").replace(/\s+/g, " ").trim();
}

function titleFromFilename(filePath) {
  return path
    .basename(filePath, path.extname(filePath))
    .replace(/[_]+/g, " ")
    .replace(/\s+/g, " ")
    .trim();
}

function parseKeywords(value) {
  if (!value) return [];
  const list = Array.isArray(value) ? value : String(value).split(/[,;]+/);
  return [...new Set(list.map(clean).filter(Boolean))];
}

function uniqueDest(dir, originalName) {
  const ext = path.extname(originalName) || ".pdf";
  const stem =
    path
      .basename(originalName, ext)
      .replace(/[<>:"/\\|?*]+/g, "-")
      .slice(0, 80) || "document";
  let dest = path.join(dir, `${stem}${ext}`);
  let n = 2;
  while (fs.existsSync(dest)) {
    dest = path.join(dir, `${stem}-${n}${ext}`);
    n += 1;
  }
  return dest;
}

async function extractMetadata(filePath) {
  const bytes = fs.readFileSync(filePath);
  const pdf = await PDFDocument.load(bytes, {
    ignoreEncryption: true,
    updateMetadata: false,
  });
  return {
    title: clean(pdf.getTitle()) || titleFromFilename(filePath),
    author: clean(pdf.getAuthor()),
    totalPages: pdf.getPageCount(),
    notes: clean(pdf.getSubject()),
    tags: parseKeywords(pdf.getKeywords()),
  };
}

async function importPdfFiles(filePaths, destDir, existingNames) {
  fs.mkdirSync(destDir, { recursive: true });
  const known = new Set((existingNames || []).map((name) => name.toLowerCase()));
  const imported = [];
  const skipped = [];
  const errors = [];

  for (const filePath of filePaths) {
    const sourceName = path.basename(filePath);
    if (!filePath.toLowerCase().endsWith(".pdf")) {
      skipped.push({ file: sourceName, reason: "not a PDF" });
      continue;
    }
    if (known.has(sourceName.toLowerCase())) {
      skipped.push({ file: sourceName, reason: "already in catalog" });
      continue;
    }
    try {
      const meta = await extractMetadata(filePath);
      const dest = uniqueDest(destDir, sourceName);
      fs.copyFileSync(filePath, dest);
      known.add(sourceName.toLowerCase());
      imported.push({
        ...meta,
        pdfPath: dest,
        sourceName,
      });
    } catch (err) {
      errors.push({ file: sourceName, message: err.message });
    }
  }

  return { imported, skipped, errors };
}

module.exports = { importPdfFiles };