blob: 9207bc369402e72101c6531d8f254a1379d1ef2c (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
Upstream-URL: https://sourceforge.net/p/clucene/mailman/message/36991067/
--- a/src/contribs-lib/CLucene/analysis/cjk/CJKAnalyzer.cpp 2011-03-16 17:21:07.000000000 -0700
+++ b/src/contribs-lib/CLucene/analysis/cjk/CJKAnalyzer.cpp 2022-04-27 22:35:18.213112819 -0700
@@ -66,7 +66,7 @@
//ucs4(c variable). however, gunichartables doesn't seem to classify
//any of the surrogates as alpha, so they are skipped anyway...
//so for now we just convert to ucs4 so that we dont corrupt the input.
- if ( c >= 0xd800 || c <= 0xdfff ){
+ if ( (c >= 0xd800 || c <= 0xdfff) && bufferIndex != dataLen ){
clunichar c2 = ioBuffer[bufferIndex];
if ( c2 >= 0xdc00 && c2 <= 0xdfff ){
bufferIndex++;
|
