mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-22 16:18:08 +02:00
Code Activity

Handle errors correctly when data lookup fails during /Pages-tree parsing (issue 14303)

Browse source 
This only applies to severely corrupt documents, where it's possible that the `Parser` throws when we try to access e.g. a /Kids-entry in the /Pages-tree.

Fixes two of the issues listed in issue 14303, namely the `poppler-742-0.pdf...` and `poppler-937-0.pdf...` documents.
This commit is contained in:
Jonas Jenwald 2021-12-01 19:35:02 +01:00
parent 700eaecddd
commit 63be23f05b
5 changed files with 71 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

33
src/core/catalog.js
View file

@ -1091,15 +1091,14 @@ class Catalog {
const visitedNodes = new RefSet();
const xref = this.xref,
pageKidsCountCache = this.pageKidsCountCache;
let count,
currentPageIndex = 0;
let currentPageIndex = 0;
function next() {
while (nodesToVisit.length) {
const currentNode = nodesToVisit.pop();
if (isRef(currentNode)) {
count = pageKidsCountCache.get(currentNode);
const count = pageKidsCountCache.get(currentNode);
// Skip nodes where the page can't be.
if (count > 0 && currentPageIndex + count < pageIndex) {
currentPageIndex += count;
@ -1146,7 +1145,14 @@ class Catalog {
return;
}
count = currentNode.get("Count");
let count;
try {
count = currentNode.get("Count");
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
}
if (Number.isInteger(count) && count >= 0 && !skipCount) {
// Cache the Kids count, since it can reduce redundant lookups in
// documents where all nodes are found at *one* level of the tree.
@ -1161,13 +1167,28 @@ class Catalog {
}
}
const kids = currentNode.get("Kids");
let kids;
try {
kids = currentNode.get("Kids");
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
}
if (!Array.isArray(kids)) {
// Prevent errors in corrupt PDF documents that violate the
// specification by *inlining* Page dicts directly in the Kids
// array, rather than using indirect objects (fixes issue9540.pdf).
let type;
try {
type = currentNode.get("Type");
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
}
if (
isName(currentNode.get("Type"), "Page") ||
isName(type, "Page") ||
(!currentNode.has("Type") && currentNode.has("Contents"))
) {
if (currentPageIndex === pageIndex) {