Example: parsing a PDF file from a URL

[adrienjoly]

FYI, this example is going to be removed from README.md.

const get = (url) =>
  new Promise((resolve, reject) =>
    https
      .get(url, (res) => {
        const data = [];
        res
          .on("data", (chunk) => data.push(chunk))
          .on("end", () => resolve(Buffer.concat(data)));
      })
      .on("error", reject)
  );

function addTextToLines(textLines, item) {
  const existingLine = textLines.find(({ y }) => y === item.y);
  if (existingLine) {
    existingLine.text += " " + item.text;
  } else {
    textLines.push(item);
  }
}

const parseLinesPerPage = (buffer) =>
  new Promise((resolve, reject) => {
    const linesPerPage = [];
    let pageNumber = 0;
    new PdfReader().parseBuffer(buffer, (err, item) => {
      if (err) reject(err);
      else if (!item) {
        resolve(linesPerPage.map((page) => page.map((line) => line.text)));
      } else if (item.page) {
        pageNumber = item.page - 1;
        linesPerPage[pageNumber] = [];
      } else if (item.text) {
        addTextToLines(linesPerPage[pageNumber], item);
      }
    });
  });

const url = new URL(
  "https://raw.githubusercontent.com/adrienjoly/npm-pdfreader/master/test/sample.pdf"
);
const buffer = get(url)
  .then((buffer) => parseLinesPerPage(buffer))
  .then((linesPerPage) => console.log(linesPerPage));