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

LUCENE-7619: don't let offsets go backwards

This commit is contained in:
Mike McCandless 2017-01-17 17:57:11 -05:00
parent 39eec660ca
commit 0bdcfc291f
1 changed files with 16 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/WordDelimiterGraphFilter.java
View File

@ -195,6 +195,7 @@ public final class WordDelimiterGraphFilter extends TokenFilter {
private int savedStartOffset;
private int savedEndOffset;
private AttributeSource.State savedState;
private int lastStartOffset;
// if length by start + end offsets doesn't match the term text then assume
// this is a synonym and don't adjust the offsets.
@ -373,12 +374,24 @@ public final class WordDelimiterGraphFilter extends TokenFilter {
int endPart = bufferedParts[4*bufferedPos+3];
bufferedPos++;
int startOffset;
int endOffset;
if (hasIllegalOffsets) {
offsetAttribute.setOffset(savedStartOffset, savedEndOffset);
startOffset = savedStartOffset;
endOffset = savedEndOffset;
} else {
offsetAttribute.setOffset(savedStartOffset + startPart, savedStartOffset + endPart);
startOffset = savedStartOffset + startPart;
endOffset = savedStartOffset + endPart;
}
// never let offsets go backwards:
startOffset = Math.max(startOffset, lastStartOffset);
endOffset = Math.max(endOffset, lastStartOffset);
offsetAttribute.setOffset(startOffset, endOffset);
lastStartOffset = startOffset;
if (termPart == null) {
termAttribute.copyBuffer(savedTermBuffer, startPart, endPart - startPart);
} else {
@ -402,6 +415,7 @@ public final class WordDelimiterGraphFilter extends TokenFilter {
super.reset();
accumPosInc = 0;
savedState = null;
lastStartOffset = 0;
concat.clear();
concatAll.clear();
}