mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-25 09:38:06 +02:00
Code Activity

Add basic validation of the 'trailer' dictionary candidates in XRef.indexObjects (issue 9418)

Browse source 
This patch avoids choosing a (possible) 'trailer' dictionary that `XRef.parse` and/or the `Catalog` constructor/methods will reject anyway.
Since `XRef.indexObjects` is already parsing the entire PDF file, the extra dictionary look-ups added here shouldn't matter much. Besides, this is a fallback code-path that only applies to corrupt PDF files anyway.
This commit is contained in:
Jonas Jenwald 2018-06-19 11:31:31 +02:00
parent 346810e02a
commit 56e3648b65
4 changed files with 28 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

25
src/core/obj.js
View file

@ -1260,7 +1260,7 @@ var XRef = (function XRefClosure() {
this.readXRef(/* recoveryMode */ true);
}
// finding main trailer
var dict;
let trailerDict;
for (i = 0, ii = trailers.length; i < ii; ++i) {
stream.pos = trailers[i];
var parser = new Parser(new Lexer(stream), /* allowStreams = */ true,
@ -1270,18 +1270,33 @@ var XRef = (function XRefClosure() {
continue;
}
// read the trailer dictionary
dict = parser.getObj();
let dict = parser.getObj();
if (!isDict(dict)) {
continue;
}
// Do some basic validation of the trailer/root dictionary candidate.
let rootDict;
try {
rootDict = dict.get('Root');
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
continue;
}
if (!isDict(rootDict) || !rootDict.has('Pages')) {
continue;
}
// taking the first one with 'ID'
if (dict.has('ID')) {
return dict;
}
// The current dictionary is a candidate, but continue searching.
trailerDict = dict;
}
// no tailer with 'ID', taking last one (if exists)
if (dict) {
return dict;
// No trailer with 'ID', taking last one (if exists).
if (trailerDict) {
return trailerDict;
}
// nothing helps
throw new InvalidPDFException('Invalid PDF structure');