Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix ord bounds check to check maxOrd (not number of docs), and document bug in 4.0 codec 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1438129 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2013-01-24 19:10:35 +00:00
parent e6dbf827db
commit ff3e225780
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
lucene/core/src/java/org/apache/lucene/index/CheckIndex.java
View File

@ -1305,11 +1305,13 @@ public class CheckIndex {
// check sorted bytes
SortedSource sortedValues = values.asSortedSource();
Comparator<BytesRef> comparator = sortedValues.getComparator();
int maxOrd = sortedValues.getValueCount() - 1;
FixedBitSet seenOrds = new FixedBitSet(sortedValues.getValueCount());
int lastOrd = -1;
BytesRef lastBytes = new BytesRef();
for (int i = 0; i < expectedDocs; i++) {
int ord = sortedValues.ord(i);
if (ord < 0 || ord > expectedDocs) {
if (ord < 0 || ord > maxOrd) {
throw new RuntimeException("field: " + fieldName + " ord is out of bounds: " + ord);
}
BytesRef bytes = new BytesRef();
@ -1323,6 +1325,13 @@ public class CheckIndex {
}
lastOrd = ord;
lastBytes = bytes;
seenOrds.set(ord);
}
if (seenOrds.cardinality() != sortedValues.getValueCount()) {
// TODO: find the bug here and figure out a workaround (we can implement in LUCENE-4547's back compat layer maybe)
// basically ord 0 is unused by any docs: so the sortedbytes ords are all off-by-one
// does it always happen? e.g. maybe only if there are missing values? or a bug in its merge optimizations?
// throw new RuntimeException("dv for field: " + fieldName + " has holes in its ords, valueCount=" + sortedValues.getValueCount() + " but only used: " + seenOrds.cardinality());
}
}
}