Sakurai/pdf.js
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improve caching of empty /XObjects in the PartialEvaluator.getTextContent method

Browse Source 
It turns out that `getTextContent` suffers from *similar* problems with repeated images as `getOperatorList`; please see the previous patch.

While only `/XObject` resources of the `Form`-type will actually be *parsed* in `PartialEvaluator.getTextContent`, since those are the only ones that may contain text, we're still forced to fetch repeated image resources where the name differs (but not the reference).
Obviously it's less bad in this case, since we're not actually parsing `/XObject`s of e.g. the `Image`-type. However, you still want to avoid even fetching the data whenever possible, since `Stream`s are not cached on the `XRef` instance (given their potential size) and the lookup can thus be somewhat expensive in general.

To address these issues, we can simply replace the exiting name-only caching in `PartialEvaluator.getTextContent` with a new cache backed by `LocalImageCache` instead.
This commit is contained in:
Jonas Jenwald 2020-05-26 09:47:59 +02:00
parent d62c9181bd
commit 4ef547f400
1 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/core/evaluator.js
View File

@ -1724,7 +1724,7 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
// The xobj is parsed iff it's needed, e.g. if there is a `DO` cmd.
var xobjs = null;
var skipEmptyXObjs = Object.create(null);
const emptyXObjectCache = new LocalImageCache();
var preprocessor = new EvaluatorPreprocessor(stream, xref, stateManager);
@ -2200,7 +2200,7 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
}
var name = args[0].name;
if (name && skipEmptyXObjs[name] !== undefined) {
if (name && emptyXObjectCache.getByName(name)) {
break;
}
@ -2212,7 +2212,16 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
);
}
const xobj = xobjs.get(name);
let xobj = xobjs.getRaw(name);
if (xobj instanceof Ref) {
if (emptyXObjectCache.getByRef(xobj)) {
resolveXObject();
return;
}
xobj = xref.fetch(xobj);
}
if (!xobj) {
resolveXObject();
return;
@ -2227,7 +2236,8 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
}
if (type.name !== "Form") {
skipEmptyXObjs[name] = true;
emptyXObjectCache.set(name, xobj.dict.objId, true);
resolveXObject();
return;
}
@ -2278,7 +2288,7 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
})
.then(function () {
if (!sinkWrapper.enqueueInvoked) {
skipEmptyXObjs[name] = true;
emptyXObjectCache.set(name, xobj.dict.objId, true);
}
resolveXObject();
}, rejectXObject);