Change the _pagePromises cache, in the worker, from an Array to a Map

Given that not all pages necessarily are being accessed, or that the pages may be accessed out of order, using a `Map` seems like a more appropriate data-structure here.
Furthermore, this patch also adds (currently missing) caching for XFA-documents. Loading a couple of such documents in the viewer, with logging added, shows that we're currently re-creating `Page`-instances unnecessarily for XFA-documents.
This commit is contained in:
Jonas Jenwald 2021-11-26 19:47:13 +01:00
parent 2e2d049a9c
commit 080996ac68

View File

@ -655,7 +655,7 @@ class PDFDocument {
this.pdfManager = pdfManager; this.pdfManager = pdfManager;
this.stream = stream; this.stream = stream;
this.xref = new XRef(stream, pdfManager); this.xref = new XRef(stream, pdfManager);
this._pagePromises = []; this._pagePromises = new Map();
this._version = null; this._version = null;
const idCounters = { const idCounters = {
@ -1299,36 +1299,21 @@ class PDFDocument {
} }
getPage(pageIndex) { getPage(pageIndex) {
if (this._pagePromises[pageIndex] !== undefined) { const cachedPromise = this._pagePromises.get(pageIndex);
return this._pagePromises[pageIndex]; if (cachedPromise) {
return cachedPromise;
} }
const { catalog, linearization } = this; const { catalog, linearization, xfaFactory } = this;
if (this.xfaFactory) { let promise;
return Promise.resolve( if (xfaFactory) {
new Page({ promise = Promise.resolve([Dict.empty, null]);
pdfManager: this.pdfManager, } else if (linearization && linearization.pageFirst === pageIndex) {
xref: this.xref, promise = this._getLinearizationPage(pageIndex);
pageIndex, } else {
pageDict: Dict.empty, promise = catalog.getPageDict(pageIndex);
ref: null,
globalIdFactory: this._globalIdFactory,
fontCache: catalog.fontCache,
builtInCMapCache: catalog.builtInCMapCache,
standardFontDataCache: catalog.standardFontDataCache,
globalImageCache: catalog.globalImageCache,
nonBlendModesSet: catalog.nonBlendModesSet,
xfaFactory: this.xfaFactory,
})
);
} }
promise = promise.then(([pageDict, ref]) => {
const promise =
linearization && linearization.pageFirst === pageIndex
? this._getLinearizationPage(pageIndex)
: catalog.getPageDict(pageIndex);
return (this._pagePromises[pageIndex] = promise.then(([pageDict, ref]) => {
return new Page({ return new Page({
pdfManager: this.pdfManager, pdfManager: this.pdfManager,
xref: this.xref, xref: this.xref,
@ -1341,9 +1326,12 @@ class PDFDocument {
standardFontDataCache: catalog.standardFontDataCache, standardFontDataCache: catalog.standardFontDataCache,
globalImageCache: catalog.globalImageCache, globalImageCache: catalog.globalImageCache,
nonBlendModesSet: catalog.nonBlendModesSet, nonBlendModesSet: catalog.nonBlendModesSet,
xfaFactory: null, xfaFactory,
}); });
})); });
this._pagePromises.set(pageIndex, promise);
return promise;
} }
checkFirstPage() { checkFirstPage() {
@ -1352,7 +1340,7 @@ class PDFDocument {
// Clear out the various caches to ensure that we haven't stored any // Clear out the various caches to ensure that we haven't stored any
// inconsistent and/or incorrect state, since that could easily break // inconsistent and/or incorrect state, since that could easily break
// subsequent `this.getPage` calls. // subsequent `this.getPage` calls.
this._pagePromises.length = 0; this._pagePromises.clear();
await this.cleanup(); await this.cleanup();
throw new XRefParseException(); throw new XRefParseException();