Details about the known misuse from the MUBench dataset.
Description:
If segmentsSource.size() == 0 in line 4718, then end = 0 and the loop at line 4736 is skipped. Then mergeDocStores (line 4730) remains false and the branch accessing segmentsSource.info(0) at line 4790 is taken. Since segmentsSource is empty, this access causes an exception.
Fix Description:
Violation Types:
missing/condition/value_or_state
In File:
org/apache/lucene/index/IndexWriter.java
In Method:
_mergeInit(OneMerge)
Code with Misuse:
class IndexWriter {
final synchronized private void _mergeInit(MergePolicy.OneMerge merge) throws IOException {
assert testPoint("startMergeInit");
assert merge.registerDone;
assert !merge.optimize || merge.maxNumSegmentsOptimize > 0;
if (hitOOM) {
throw new IllegalStateException("this writer hit an OutOfMemoryError; cannot merge");
}
if (merge.info != null)
// mergeInit already done
return;
if (merge.isAborted())
return;
boolean changed = applyDeletes();
// If autoCommit == true then all deletes should have
// been flushed when we flushed the last segment
assert !changed || !autoCommit;
final SegmentInfos sourceSegments = merge.segments;
final int end = sourceSegments.size();
// Check whether this merge will allow us to skip
// merging the doc stores (stored field & vectors).
// This is a very substantial optimization (saves tons
// of IO) that can only be applied with
// autoCommit=false.
Directory lastDir = directory;
String lastDocStoreSegment = null;
int next = -1;
boolean mergeDocStores = false;
boolean doFlushDocStore = false;
final String currentDocStoreSegment = docWriter.getDocStoreSegment();
// Test each segment to be merged: check if we need to
// flush/merge doc stores
for (int i = 0; i < end; i++) {
SegmentInfo si = sourceSegments.info(i);
// If it has deletions we must merge the doc stores
if (si.hasDeletions())
mergeDocStores = true;
// If it has its own (private) doc stores we must
// merge the doc stores
if (-1 == si.getDocStoreOffset())
mergeDocStores = true;
// If it has a different doc store segment than
// previous segments, we must merge the doc stores
String docStoreSegment = si.getDocStoreSegment();
if (docStoreSegment == null)
mergeDocStores = true;
else if (lastDocStoreSegment == null)
lastDocStoreSegment = docStoreSegment;
else if (!lastDocStoreSegment.equals(docStoreSegment))
mergeDocStores = true;
// Segments' docScoreOffsets must be in-order,
// contiguous. For the default merge policy now
// this will always be the case but for an arbitrary
// merge policy this may not be the case
if (-1 == next)
next = si.getDocStoreOffset() + si.docCount;
else if (next != si.getDocStoreOffset())
mergeDocStores = true;
else
next = si.getDocStoreOffset() + si.docCount;
// If the segment comes from a different directory
// we must merge
if (lastDir != si.dir)
mergeDocStores = true;
// If the segment is referencing the current "live"
// doc store outputs then we must merge
if (si.getDocStoreOffset() != -1 && currentDocStoreSegment != null && si.getDocStoreSegment().equals(currentDocStoreSegment)) {
doFlushDocStore = true;
}
}
final int docStoreOffset;
final String docStoreSegment;
final boolean docStoreIsCompoundFile;
if (mergeDocStores) {
docStoreOffset = -1;
docStoreSegment = null;
docStoreIsCompoundFile = false;
} else {
SegmentInfo si = sourceSegments.info(0);
docStoreOffset = si.getDocStoreOffset();
docStoreSegment = si.getDocStoreSegment();
docStoreIsCompoundFile = si.getDocStoreIsCompoundFile();
}
if (mergeDocStores && doFlushDocStore) {
// SegmentMerger intends to merge the doc stores
// (stored fields, vectors), and at least one of the
// segments to be merged refers to the currently
// live doc stores.
// TODO: if we know we are about to merge away these
// newly flushed doc store files then we should not
// make compound file out of them...
if (infoStream != null)
message("now flush at merge");
doFlush(true, false);
}
merge.increfDone = true;
merge.mergeDocStores = mergeDocStores;
// Bind a new segment name here so even with
// ConcurrentMergePolicy we keep deterministic segment
// names.
merge.info = new SegmentInfo(newSegmentName(), 0,
directory, false, true,
docStoreOffset,
docStoreSegment,
docStoreIsCompoundFile,
false);
Map details = new HashMap();
details.put("optimize", merge.optimize+"");
details.put("mergeFactor", end+"");
details.put("mergeDocStores", mergeDocStores+"");
setDiagnostics(merge.info, "merge", details);
// Also enroll the merged segment into mergingSegments;
// this prevents it from getting selected for a merge
// after our merge is done but while we are building the
// CFS:
mergingSegments.add(merge.info);
}
}
