ZenBrowserMirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/zen-browser/pdf.js.git synced 2025-07-09 09:45:42 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Improve memory usage around the BasePdfManager.docBaseUrl parameter (PR 7689 follow-up)

Browse source 
While there is nothing *outright* wrong with the existing implementation, it can however lead to increased memory usage in one particular case (that I completely overlooked when implementing this):
For "data:"-URLs, which by definition contains the entire PDF document and can thus be arbitrarily large, we obviously want to avoid sending, storing, and/or logging the "raw" docBaseUrl in that case.

To address this, this patch makes the following changes:
 - Ignore any non-string in the `docBaseUrl` option passed to `getDocument`, since those are unsupported anyway, already on the main-thread.

 - Ignore "data:"-URLs in the `docBaseUrl` option passed to `getDocument`, to avoid having to send what could potentially be a *very* long string to the worker-thread.

 - Parse the `docBaseUrl` option *directly* in the `BasePdfManager`-constructors, on the worker-thread, to avoid having to store the "raw" docBaseUrl in the first place.
This commit is contained in:
Jonas Jenwald 2021-03-16 11:56:39 +01:00
parent bd9dee1544
commit c4c7216171
3 changed files with 26 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/display/api.js
View file

@ -40,6 +40,7 @@ import {
deprecated,
DOMCanvasFactory,
DOMCMapReaderFactory,
isDataScheme,
loadScript,
PageViewport,
RenderingCancelledException,
@ -285,6 +286,15 @@ function getDocument(src) {
params.fontExtraProperties = params.fontExtraProperties === true;
params.pdfBug = params.pdfBug === true;
if (
typeof params.docBaseUrl !== "string" ||
isDataScheme(params.docBaseUrl)
) {
// Ignore "data:"-URLs, since they can't be used to recover valid absolute
// URLs anyway. We want to avoid sending them to the worker-thread, since
// they contain the *entire* PDF document and can thus be arbitrarily long.
params.docBaseUrl = null;
}
if (!Number.isInteger(params.maxImageSize)) {
params.maxImageSize = -1;
}