From 7e852851fd2e99a8ceccfb7a5a9394bc6d591c25 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Sun, 29 May 2022 16:37:18 +0200
Subject: [PATCH] A small memory-usage improvement for PDF documents opened
from TypedArray-data
This patch contains a small optimization specifically for the case when `getDocument` is called with TypedArray-data. In that case we'll still hold onto that data, which could obviously be large, even after the "GetDocRequest"-message has been sent to the worker-thread.
In practice this will most likely not affect memory usage in any noticeable way, since the application calling `getDocument` will probably also be keeping a reference to the TypedArray-data. However, it seems like a good idea to ensure that the PDF.js API *itself* won't unnecessarily keep this data alive.
---
src/display/api.js | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/src/display/api.js b/src/display/api.js
index 3b36f18e0..fba542a87 100644
--- a/src/display/api.js
+++ b/src/display/api.js
@@ -513,6 +513,12 @@ async function _fetchDocument(worker, source, pdfDataRangeTransport, docId) {
}
);
+ // Release the TypedArray data, when it exists, since it's no longer needed
+ // on the main-thread *after* it's been sent to the worker-thread.
+ if (source.data) {
+ source.data = null;
+ }
+
if (worker.destroyed) {
throw new Error("Worker was destroyed");
}
@@ -953,8 +959,8 @@ class PDFDocumentProxy {
}
/**
- * @returns {Promise<TypedArray>} A promise that is resolved with a
- * {TypedArray} that has the raw data from the PDF.
+ * @returns {Promise<Uint8Array>} A promise that is resolved with a
+ * {Uint8Array} that has the raw data from the PDF.
*/
getData() {
return this._transport.getData();