mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-26 01:58:06 +02:00
Code Activity

[Regression] Eagerly fetch/parse the entire /Pages-tree in corrupt documents (issue 14303, PR 14311 follow-up)

Browse source 
*Please note:* This is similar to the method that existed prior to PR 3848, but the new method will *only* be used as a fallback when parsing of corrupt PDF documents.

The implementation in PR 14311 unfortunately turned out to be *way* too simplistic, as evident by the recently added test-files in issue 14303, since it may *cause* infinite loops in `PDFDocument.checkLastPage` for some corrupt PDF documents.[1]
To avoid this, the easiest solution that I could come up with was to fallback to eagerly parsing the *entire* /Pages-tree when the /Count-entry validation fails during document initialization.

Fixes *at least* two of the issues listed in issue 14303, namely the `poppler-395-0.pdf...` and `GHOSTSCRIPT-698804-1.pdf...` documents.

---
[1] The whole point of PR 14311 was obviously to *get rid of* infinte loops during document initialization, not to introduce any more of those.
This commit is contained in:
Jonas Jenwald 2021-12-02 01:40:52 +01:00
parent f61b74e38e
commit 1fac6371d3
7 changed files with 504 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

73
src/core/document.js
View file

@ -50,7 +50,6 @@ import {
getInheritableProperty,
isWhiteSpace,
MissingDataException,
PageDictMissingException,
validateCSSFont,
XRefEntryException,
XRefParseException,
@ -1354,14 +1353,16 @@ class PDFDocument {
}
async checkLastPage(recoveryMode = false) {
this.catalog.setActualNumPages(); // Ensure that it's always reset.
const { catalog, pdfManager } = this;
catalog.setActualNumPages(); // Ensure that it's always reset.
let numPages;
try {
await Promise.all([
this.pdfManager.ensureDoc("xfaFactory"),
this.pdfManager.ensureDoc("linearization"),
this.pdfManager.ensureCatalog("numPages"),
pdfManager.ensureDoc("xfaFactory"),
pdfManager.ensureDoc("linearization"),
pdfManager.ensureCatalog("numPages"),
]);
if (this.xfaFactory) {
@ -1369,13 +1370,13 @@ class PDFDocument {
} else if (this.linearization) {
numPages = this.linearization.numPages;
} else {
numPages = this.catalog.numPages;
numPages = catalog.numPages;
}
if (numPages === 1) {
return;
} else if (!Number.isInteger(numPages)) {
if (!Number.isInteger(numPages)) {
throw new FormatError("Page count is not an integer.");
} else if (numPages <= 1) {
return;
}
await this.getPage(numPages - 1);
} catch (reason) {
@ -1385,24 +1386,48 @@ class PDFDocument {
// subsequent `this.getPage` calls.
await this.cleanup();
let pageIndex = 1; // The first page was already loaded.
while (true) {
try {
await this.getPage(pageIndex);
} catch (reasonLoop) {
if (reasonLoop instanceof PageDictMissingException) {
break;
}
if (reasonLoop instanceof XRefEntryException) {
if (!recoveryMode) {
throw new XRefParseException();
}
break;
let pagesTree;
try {
pagesTree = await pdfManager.ensureCatalog("getAllPageDicts");
} catch (reasonAll) {
if (reasonAll instanceof XRefEntryException) {
if (!recoveryMode) {
throw new XRefParseException();
}
}
pageIndex++;
catalog.setActualNumPages(1);
return;
}
this.catalog.setActualNumPages(pageIndex);
for (const [pageIndex, [pageDict, ref]] of pagesTree) {
let promise;
if (pageDict instanceof Error) {
promise = Promise.reject(pageDict);
// Prevent "uncaught exception: Object"-messages in the console.
promise.catch(() => {});
} else {
promise = Promise.resolve(
new Page({
pdfManager,
xref: this.xref,
pageIndex,
pageDict,
ref,
globalIdFactory: this._globalIdFactory,
fontCache: catalog.fontCache,
builtInCMapCache: catalog.builtInCMapCache,
standardFontDataCache: catalog.standardFontDataCache,
globalImageCache: catalog.globalImageCache,
nonBlendModesSet: catalog.nonBlendModesSet,
xfaFactory: null,
})
);
}
this._pagePromises.set(pageIndex, promise);
}
catalog.setActualNumPages(pagesTree.size);
}
}