mirror of
https://github.com/hanzoai/sign.git
synced 2026-10-30 14:57:59 +00:00
zeekayandHanzo Dev
d15022d194
pdfjs-dist went from 5 to 6 and PDFDocumentProxy lost destroy(). In 5 it was one line, `return this.loadingTask.destroy()`, so the task is what there is to destroy. Three calls were left: - pdfToImages called it after rendering. The call threw before its .catch could attach, so every render ended in "pdf.destroy is not a function" and the AI features that read a document got nothing. The task it also destroyed is the same task, so that call is the one kept. - The PDF viewer called it when a new document replaced an old one, inside the load's try, so switching documents showed the load error; and in the effect's cleanup. Both now destroy the loading task, as 5 did for them. pdf-to-images.test.ts renders a two-page PDF and checks each page comes back as a letter-size JPEG in order; against the old code it fails with the TypeError. Co-authored-by: Hanzo Dev <[email protected]>
98 lines
2.5 KiB
TypeScript
98 lines
2.5 KiB
TypeScript
import pMap from 'p-map';
|
|
import * as pdfjsLib from 'pdfjs-dist/legacy/build/pdf.mjs';
|
|
import { Canvas, Image, Path2D } from 'skia-canvas';
|
|
|
|
// @ts-expect-error napi-rs/canvas satisfies the requirements
|
|
globalThis.Path2D = Path2D;
|
|
// @ts-expect-error napi-rs/canvas satisfies the requirements
|
|
globalThis.Image = Image;
|
|
|
|
class SkiaCanvasFactory {
|
|
_createCanvas(width: number, height: number) {
|
|
const canvas = new Canvas(width, height);
|
|
canvas.gpu = false;
|
|
|
|
return canvas;
|
|
}
|
|
|
|
create(width: number, height: number) {
|
|
const canvas = this._createCanvas(width, height);
|
|
|
|
return {
|
|
canvas,
|
|
context: canvas.getContext('2d'),
|
|
};
|
|
}
|
|
|
|
reset(canvasAndContext: { canvas: Canvas }, width: number, height: number) {
|
|
canvasAndContext.canvas.width = width;
|
|
canvasAndContext.canvas.height = height;
|
|
}
|
|
|
|
destroy(canvasAndContext: { canvas: Canvas | null; context: unknown }) {
|
|
if (canvasAndContext.canvas) {
|
|
canvasAndContext.canvas.width = 0;
|
|
canvasAndContext.canvas.height = 0;
|
|
}
|
|
|
|
canvasAndContext.canvas = null;
|
|
canvasAndContext.context = null;
|
|
}
|
|
}
|
|
|
|
export type PdfToImagesOptions = {
|
|
scale?: number;
|
|
};
|
|
|
|
export const pdfToImages = async (pdfBytes: Uint8Array, options: PdfToImagesOptions = {}) => {
|
|
const { scale = 2 } = options;
|
|
|
|
const task = await pdfjsLib.getDocument({
|
|
data: pdfBytes,
|
|
CanvasFactory: SkiaCanvasFactory,
|
|
});
|
|
|
|
const pdf = await task.promise;
|
|
|
|
const images = await pMap(
|
|
Array.from({ length: pdf.numPages }),
|
|
async (_, index) => {
|
|
const pageNumber = index + 1;
|
|
const page = await pdf.getPage(pageNumber);
|
|
|
|
const viewport = page.getViewport({ scale });
|
|
|
|
const canvas = new Canvas(viewport.width, viewport.height);
|
|
canvas.gpu = false;
|
|
|
|
const canvasContext = canvas.getContext('2d');
|
|
|
|
await page.render({
|
|
// @ts-expect-error napi-rs/canvas satifies the requirements
|
|
canvas,
|
|
// @ts-expect-error napi-rs/canvas satifies the requirements
|
|
canvasContext,
|
|
viewport,
|
|
}).promise;
|
|
|
|
const result = {
|
|
pageNumber,
|
|
image: await canvas.toBuffer('jpeg'),
|
|
width: Math.floor(viewport.width),
|
|
height: Math.floor(viewport.height),
|
|
mimeType: 'image/jpeg',
|
|
};
|
|
|
|
void page.cleanup();
|
|
|
|
return result;
|
|
},
|
|
{ concurrency: 10 },
|
|
);
|
|
|
|
// Destroying the loading task destroys the document it loaded.
|
|
void task.destroy().catch((e) => console.error(e));
|
|
|
|
return images;
|
|
};
|