pdf.js.mirror/src/core/image_utils.js
Jonas Jenwald dda6626f40 Attempt to cache repeated images at the document, rather than the page, level (issue 11878)
Currently image resources, as opposed to e.g. font resources, are handled exclusively on a page-specific basis. Generally speaking this makes sense, since pages are separate from each other, however there's PDF documents where many (or even all) pages actually references exactly the same image resources (through the XRef table). Hence, in some cases, we're decoding the *same* images over and over for every page which is obviously slow and wasting both CPU and memory resources better used elsewhere.[1]

Obviously we cannot simply treat all image resources as-if they're used throughout the entire PDF document, since that would end up increasing memory usage too much.[2]
However, by introducing a `GlobalImageCache` in the worker we can track image resources that appear on more than one page. Hence we can switch image resources from being page-specific to being document-specific, once the image resource has been seen on more than a certain number of pages.

In many cases, such as e.g. the referenced issue, this patch will thus lead to reduced memory usage for image resources. Scrolling through all pages of the document, there's now only a few main-thread copies of the same image data, as opposed to one for each rendered page (i.e. there could theoretically be *twenty* copies of the image data).
While this obviously benefit both CPU and memory usage in this case, for *very* large image data this patch *may* possibly increase persistent main-thread memory usage a tiny bit. Thus to avoid negatively affecting memory usage too much in general, particularly on the main-thread, the `GlobalImageCache` will *only* cache a certain number of image resources at the document level and simply fallback to the default behaviour.

Unfortunately the asynchronous nature of the code, with ranged/streamed loading of data, actually makes all of this much more complicated than if all data could be assumed to be immediately available.[3]

*Please note:* The patch will lead to *small* movement in some existing test-cases, since we're now using the built-in PDF.js JPEG decoder more. This was done in order to simplify the overall implementation, especially on the main-thread, by limiting it to only the `OPS.paintImageXObject` operator.

---
[1] There's e.g. PDF documents that use the same image as background on all pages.

[2] Given that data stored in the `commonObjs`, on the main-thread, are only cleared manually through `PDFDocumentProxy.cleanup`. This as opposed to data stored in the `objs` of each page, which is automatically removed when the page is cleaned-up e.g. by being evicted from the cache in the default viewer.

[3] If the latter case were true, we could simply check for repeat images *before* parsing started and thus avoid handling *any* duplicate image resources.
2020-05-21 18:13:45 +02:00

209 lines
5.4 KiB
JavaScript

/* Copyright 2019 Mozilla Foundation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/* eslint no-var: error */
import { assert, info, shadow } from "../shared/util.js";
import { ColorSpace } from "./colorspace.js";
import { JpegStream } from "./jpeg_stream.js";
import { RefSetCache } from "./primitives.js";
import { Stream } from "./stream.js";
class NativeImageDecoder {
constructor({
xref,
resources,
handler,
forceDataSchema = false,
pdfFunctionFactory,
}) {
this.xref = xref;
this.resources = resources;
this.handler = handler;
this.forceDataSchema = forceDataSchema;
this.pdfFunctionFactory = pdfFunctionFactory;
}
canDecode(image) {
return (
image instanceof JpegStream &&
image.maybeValidDimensions &&
NativeImageDecoder.isDecodable(
image,
this.xref,
this.resources,
this.pdfFunctionFactory
)
);
}
decode(image) {
// For natively supported JPEGs send them to the main thread for decoding.
const dict = image.dict;
let colorSpace = dict.get("ColorSpace", "CS");
colorSpace = ColorSpace.parse(
colorSpace,
this.xref,
this.resources,
this.pdfFunctionFactory
);
return this.handler
.sendWithPromise("JpegDecode", [
image.getIR(this.forceDataSchema),
colorSpace.numComps,
])
.then(function ({ data, width, height }) {
return new Stream(data, 0, data.length, dict);
});
}
/**
* Checks if the image can be decoded and displayed by the browser without any
* further processing such as color space conversions.
*/
static isSupported(image, xref, res, pdfFunctionFactory) {
const dict = image.dict;
if (dict.has("DecodeParms") || dict.has("DP")) {
return false;
}
const cs = ColorSpace.parse(
dict.get("ColorSpace", "CS"),
xref,
res,
pdfFunctionFactory
);
// isDefaultDecode() of DeviceGray and DeviceRGB needs no `bpc` argument.
return (
(cs.name === "DeviceGray" || cs.name === "DeviceRGB") &&
cs.isDefaultDecode(dict.getArray("Decode", "D"))
);
}
/**
* Checks if the image can be decoded by the browser.
*/
static isDecodable(image, xref, res, pdfFunctionFactory) {
const dict = image.dict;
if (dict.has("DecodeParms") || dict.has("DP")) {
return false;
}
const cs = ColorSpace.parse(
dict.get("ColorSpace", "CS"),
xref,
res,
pdfFunctionFactory
);
const bpc = dict.get("BitsPerComponent", "BPC") || 1;
return (
(cs.numComps === 1 || cs.numComps === 3) &&
cs.isDefaultDecode(dict.getArray("Decode", "D"), bpc)
);
}
}
class GlobalImageCache {
static get NUM_PAGES_THRESHOLD() {
return shadow(this, "NUM_PAGES_THRESHOLD", 2);
}
static get MAX_IMAGES_TO_CACHE() {
return shadow(this, "MAX_IMAGES_TO_CACHE", 10);
}
constructor() {
if (
typeof PDFJSDev === "undefined" ||
PDFJSDev.test("!PRODUCTION || TESTING")
) {
assert(
GlobalImageCache.NUM_PAGES_THRESHOLD > 1,
"GlobalImageCache - invalid NUM_PAGES_THRESHOLD constant."
);
}
this._refCache = new RefSetCache();
this._imageCache = new RefSetCache();
}
shouldCache(ref, pageIndex) {
const pageIndexSet = this._refCache.get(ref);
const numPages = pageIndexSet
? pageIndexSet.size + (pageIndexSet.has(pageIndex) ? 0 : 1)
: 1;
if (numPages < GlobalImageCache.NUM_PAGES_THRESHOLD) {
return false;
}
if (
!this._imageCache.has(ref) &&
this._imageCache.size >= GlobalImageCache.MAX_IMAGES_TO_CACHE
) {
return false;
}
return true;
}
addPageIndex(ref, pageIndex) {
let pageIndexSet = this._refCache.get(ref);
if (!pageIndexSet) {
pageIndexSet = new Set();
this._refCache.put(ref, pageIndexSet);
}
pageIndexSet.add(pageIndex);
}
getData(ref, pageIndex) {
if (!this._refCache.has(ref)) {
return null;
}
const pageIndexSet = this._refCache.get(ref);
if (pageIndexSet.size < GlobalImageCache.NUM_PAGES_THRESHOLD) {
return null;
}
if (!this._imageCache.has(ref)) {
return null;
}
// Ensure that we keep track of all pages containing the image reference.
pageIndexSet.add(pageIndex);
return this._imageCache.get(ref);
}
setData(ref, data) {
if (!this._refCache.has(ref)) {
throw new Error(
'GlobalImageCache.setData - expected "addPageIndex" to have been called.'
);
}
if (this._imageCache.has(ref)) {
return;
}
if (this._imageCache.size >= GlobalImageCache.MAX_IMAGES_TO_CACHE) {
info(
"GlobalImageCache.setData - ignoring image above MAX_IMAGES_TO_CACHE."
);
return;
}
this._imageCache.put(ref, data);
}
clear() {
this._refCache.clear();
this._imageCache.clear();
}
}
export { NativeImageDecoder, GlobalImageCache };