ZenBrowserMirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/zen-browser/pdf.js.git synced 2025-07-08 09:20:06 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cache the normalized unicode-value on the Glyph-instance

Browse source 
Currently, during text-extraction, we're repeatedly normalizing and (when necessary) reversing the unicode-values every time. This seems a little unnecessary, since the result won't change, hence this patch moves that into the `Glyph`-instance and makes it *lazily* initialized.

Taking the `tracemonkey.pdf` document as an example: When extracting the text-content there's a total of 69236 characters but only 595 unique `Glyph`-instances, which mean a 99.1 percent cache hit-rate. Generally speaking, the longer a PDF document is the more beneficial this should be.

*Please note:* The old code is fast enough that it unfortunately seems difficult to measure a (clear) performance improvement with this patch, so I completely understand if it's deemed an unnecessary change.
This commit is contained in:
Jonas Jenwald 2022-11-03 10:20:18 +01:00
parent eda51d1dcc
commit c33b8d7692
3 changed files with 24 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/shared/util.js
View file

@ -498,7 +498,7 @@ function createValidAbsoluteUrl(url, baseUrl = null, options = null) {
return null;
}
function shadow(obj, prop, value) {
function shadow(obj, prop, value, nonSerializable = false) {
if (
typeof PDFJSDev === "undefined" ||
PDFJSDev.test("!PRODUCTION || TESTING")
@ -510,7 +510,7 @@ function shadow(obj, prop, value) {
}
Object.defineProperty(obj, prop, {
value,
enumerable: true,
enumerable: !nonSerializable,
configurable: true,
writable: false,
});