Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

PDFBOX-5283: ignore dublicate object keys when correcting xRefs #129

Open
wants to merge 4 commits into
base: trunk
Choose a base branch
from
Open

PDFBOX-5283: ignore dublicate object keys when correcting xRefs #129

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8604732
PDFBOX-5283: irgnore wrong object number in lenient mode
Schmidor Sep 23, 2021
ea0a6e0
only replace xRef with corrected entries, if the original entry was n…
Schmidor Oct 5, 2021
cd2c0ac
HashSet instead of HashMap for valid keys
Schmidor Oct 6, 2021
5ea0492
read pointers before replacing
Schmidor Mar 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 32 additions & 16 deletions pdfbox/src/main/java/org/apache/pdfbox/pdfparser/COSParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1159,6 +1159,7 @@ private boolean validateXrefOffsets(Map<COSObjectKey, Long> xrefOffset) throws I
return true;
}
Map<COSObjectKey, COSObjectKey> correctedKeys = new HashMap<>();
HashSet<COSObjectKey> validKeys = new HashSet<>();
for (Entry<COSObjectKey, Long> objectEntry : xrefOffset.entrySet())
{
COSObjectKey objectKey = objectEntry.getKey();
Expand All @@ -1178,13 +1179,24 @@ else if (foundObjectKey != objectKey)
{
// Generation was fixed - need to update map later, after iteration
correctedKeys.put(objectKey, foundObjectKey);
} else {
validKeys.add(objectKey);
}
}
}
for (Entry<COSObjectKey, COSObjectKey> correctedKeyEntry : correctedKeys.entrySet())
{
xrefOffset.put(correctedKeyEntry.getValue(),
xrefOffset.remove(correctedKeyEntry.getKey()));
Map<COSObjectKey, Long> correctedPointers = new HashMap<COSObjectKey, Long>();
for (Entry<COSObjectKey, COSObjectKey> correctedKeyEntry : correctedKeys.entrySet()) {
if (!validKeys.contains(correctedKeyEntry.getValue())) {
// Only replace entries, if the original entry does not point to a valid object
correctedPointers.put(correctedKeyEntry.getValue(), xrefOffset.get(correctedKeyEntry.getKey()));
}
}
for (Entry<COSObjectKey, COSObjectKey> correctedKeyEntry : correctedKeys.entrySet()) {
// remove old invalid, as some might not be replaced
xrefOffset.remove(correctedKeyEntry.getKey());
}
for (Entry<COSObjectKey, Long> pointer : correctedPointers.entrySet()) {
xrefOffset.put(pointer.getKey(), pointer.getValue());
}
return true;
}
Expand Down Expand Up @@ -1235,19 +1247,23 @@ private COSObjectKey findObjectKey(COSObjectKey objectKey, long offset) throws I
{
source.seek(offset);
// try to read the given object/generation number
if (objectKey.getNumber() == readObjectNumber())
long foundObjectNumber = readObjectNumber();
if(objectKey.getNumber() != foundObjectNumber){
LOG.warn("found wrong object number. expected [" + objectKey.getNumber() +"] found ["+ foundObjectNumber + "]");
if(!isLenient) return null;
else objectKey = new COSObjectKey(foundObjectNumber, objectKey.getGeneration());
}

int genNumber = readGenerationNumber();
// finally try to read the object marker
readExpectedString(OBJ_MARKER, true);
if (genNumber == objectKey.getGeneration())
{
int genNumber = readGenerationNumber();
// finally try to read the object marker
readExpectedString(OBJ_MARKER, true);
if (genNumber == objectKey.getGeneration())
{
return objectKey;
}
else if (isLenient && genNumber > objectKey.getGeneration())
{
return new COSObjectKey(objectKey.getNumber(), genNumber);
}
return objectKey;
}
else if (isLenient && genNumber > objectKey.getGeneration())
{
return new COSObjectKey(objectKey.getNumber(), genNumber);
}
}
catch (IOException exception)
Expand Down