You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@doris.apache.org by ji...@apache.org on 2023/06/21 03:06:49 UTC
[doris-thirdparty] branch clucene updated: [fix](jiebafix ) cut word greater than 225 heap-use-after-free (#96)
This is an automated email from the ASF dual-hosted git repository.
jianliangqi pushed a commit to branch clucene
in repository https://gitbox.apache.org/repos/asf/doris-thirdparty.git
The following commit(s) were added to refs/heads/clucene by this push:
new 103e88a8 [fix](jiebafix ) cut word greater than 225 heap-use-after-free (#96)
103e88a8 is described below
commit 103e88a8a3b24da9ae2a0d9908a3ceb3f7808a61
Author: zzzxl <33...@users.noreply.github.com>
AuthorDate: Wed Jun 21 11:06:44 2023 +0800
[fix](jiebafix ) cut word greater than 225 heap-use-after-free (#96)
---
src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.cpp | 2 +-
src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.cpp b/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.cpp
index bf4ea1db..e6acd64f 100644
--- a/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.cpp
+++ b/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.cpp
@@ -8,7 +8,7 @@ CL_NS_USE(analysis)
CL_NS_USE(util)
ChineseTokenizer::ChineseTokenizer(lucene::util::Reader *reader, AnalyzerMode m) : Tokenizer(reader), mode(m) {
- buffer[0] = 0;
+ memset(buffer, 0, LUCENE_MAX_WORD_LEN + 1);
}
void ChineseTokenizer::init(const std::string &dictPath) {
diff --git a/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.h b/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.h
index d94e9b1c..48de52b1 100644
--- a/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.h
+++ b/src/contribs-lib/CLucene/analysis/jieba/ChineseTokenizer.h
@@ -44,7 +44,7 @@ private:
* character buffer, store the characters which are used to compose <br>
* the returned Token
*/
- TCHAR buffer[LUCENE_MAX_WORD_LEN]{};
+ TCHAR buffer[LUCENE_MAX_WORD_LEN + 1]{};
/**
* I/O buffer, used to store the content of the input(one of the <br>
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org