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

Always parse the entire startXRefQueue in XRef.readXRef (issue 15833)

Browse source 
Previously we'd abort all parsing if an Error was encountered, despite the fact that multiple `startXRefQueue`-entries may be available and that continued parsing could thus eventually be able to find usable data.

Note that in the referenced PDF document the `startxref`-operator, at the end of the file, points to a position in the middle of an arbitrary `stream` which is why things break.
This commit is contained in:
Jonas Jenwald 2022-12-15 13:35:39 +01:00
parent 8587ce6afd
commit 26135b0313
3 changed files with 19 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

22
src/core/xref.js
View file

@ -665,8 +665,8 @@ class XRef {
// circular dependency between tables (fixes bug1393476.pdf).
const startXRefParsedCache = new Set();
try {
while (this.startXRefQueue.length) {
while (this.startXRefQueue.length) {
try {
const startXRef = this.startXRefQueue[0];
if (startXRefParsedCache.has(startXRef)) {
@ -734,20 +734,18 @@ class XRef {
// This is a fallback for non-compliant PDFs, i.e. "/Prev NNN 0 R"
this.startXRefQueue.push(obj.num);
}
this.startXRefQueue.shift();
} catch (e) {
if (e instanceof MissingDataException) {
throw e;
}
info("(while reading XRef): " + e);
}
return this.topDict;
} catch (e) {
if (e instanceof MissingDataException) {
throw e;
}
info("(while reading XRef): " + e);
this.startXRefQueue.shift();
}
if (this.topDict) {
return this.topDict;
}
if (recoveryMode) {
return undefined;
}