1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-25 09:38:06 +02:00

[api-minor] Replace PDFDocumentProxy.getStats with a synchronous PDFDocumentProxy.stats getter

*Please note:* These changes will primarily benefit longer documents, somewhat at the expense of e.g. one-page documents.

The existing `PDFDocumentProxy.getStats` function, which in the default viewer is called for each rendered page, requires a round-trip to the worker-thread in order to obtain the current document stats. In the default viewer, we currently make one such API-call for *every rendered* page.
This patch proposes replacing that method with a *synchronous* `PDFDocumentProxy.stats` getter instead, combined with re-factoring the worker-thread code by adding a `DocStats`-class to track Stream/Font-types and *only send* them to the main-thread *the first time* that a type is encountered.

Note that in practice most PDF documents only use a fairly limited number of Stream/Font-types, which means that in longer documents most of the `PDFDocumentProxy.getStats`-calls will return the same data.[1]
This re-factoring will obviously benefit longer document the most[2], and could actually be seen as a regression for one-page documents, since in practice there'll usually be a couple of "DocStats" messages sent during the parsing of the first page. However, if the user zooms/rotates the document (which causes re-rendering), note that even a one-page document would start to benefit from these changes.

Another benefit of having the data available/cached in the API is that unless the document stats change during parsing, repeated `PDFDocumentProxy.stats`-calls will return *the same identical* object.
This is something that we can easily take advantage of in the default viewer, by now *only* reporting "documentStats" telemetry[3] when the data actually have changed rather than once per rendered page (again beneficial in longer documents).

---
[1] Furthermore, the maximium number of `StreamType`/`FontType` are `10` respectively `12`, which means that regardless of the complexity and page count in a PDF document there'll never be more than twenty-two "DocStats" messages sent; see 41ac3f0c07/src/shared/util.js (L206-L232)

[2] One example is the `pdf.pdf` document in the test-suite, where rendering all of its 1310 pages only result in a total of seven "DocStats" messages being sent from the worker-thread.

[3] Reporting telemetry, in Firefox, includes using `JSON.stringify` on the data and then sending an event to the `PdfStreamConverter.jsm`-code.
In that code the event is handled and `JSON.parse` is used to retrieve the data, and in the "documentStats"-case we'll then iterate through the data to avoid double-reporting telemetry; see https://searchfox.org/mozilla-central/rev/8f4c180b87e52f3345ef8a3432d6e54bd1eb18dc/toolkit/components/pdfjs/content/PdfStreamConverter.jsm#515-549
This commit is contained in:
Jonas Jenwald 2021-11-11 18:14:26 +01:00
parent 41ac3f0c07
commit 6da0944fc7
10 changed files with 158 additions and 67 deletions

View file

@ -16,7 +16,9 @@
import {
assert,
BaseException,
FontType,
objectSize,
StreamType,
stringToPDFString,
warn,
} from "../shared/util.js";
@ -76,6 +78,55 @@ class XRefParseException extends BaseException {
}
}
class DocStats {
constructor(handler) {
this._handler = handler;
this._streamTypes = new Set();
this._fontTypes = new Set();
}
_send() {
const streamTypes = Object.create(null),
fontTypes = Object.create(null);
for (const type of this._streamTypes) {
streamTypes[type] = true;
}
for (const type of this._fontTypes) {
fontTypes[type] = true;
}
this._handler.send("DocStats", { streamTypes, fontTypes });
}
addStreamType(type) {
if (
typeof PDFJSDev === "undefined" ||
PDFJSDev.test("!PRODUCTION || TESTING")
) {
assert(StreamType[type] === type, 'addStreamType: Invalid "type" value.');
}
if (this._streamTypes.has(type)) {
return;
}
this._streamTypes.add(type);
this._send();
}
addFontType(type) {
if (
typeof PDFJSDev === "undefined" ||
PDFJSDev.test("!PRODUCTION || TESTING")
) {
assert(FontType[type] === type, 'addFontType: Invalid "type" value.');
}
if (this._fontTypes.has(type)) {
return;
}
this._fontTypes.add(type);
this._send();
}
}
/**
* Get the value of an inheritable property.
*
@ -481,6 +532,7 @@ function recoverJsURL(str) {
export {
collectActions,
DocStats,
encodeToXmlString,
escapePDFName,
getArrayLookupTableFactory,