fix

Author: lxy-9602

src/paimon/global_index/lucene/CMakeLists.txt

@@ -42,10 +42,6 @@ if(PAIMON_ENABLE_LUCENE)
                    SHARED_LINK_FLAGS
                    ${PAIMON_VERSION_SCRIPT_FLAGS})
 
-    if(PAIMON_BUILD_TESTS)
-        target_compile_definitions(paimon_lucene_index_objlib
-                                   PRIVATE JIEBA_TEST_DICT_DIR="${JIEBA_DICT_DIR}")
-    endif()
     if(PAIMON_BUILD_TESTS)
         add_paimon_test(lucene_index_test
                         SOURCES
@@ -65,5 +61,8 @@ if(PAIMON_ENABLE_LUCENE)
                         paimon_lucene_index_static
                         "-Wl,--no-whole-archive"
                         ${GTEST_LINK_TOOLCHAIN})
+        target_compile_definitions(paimon-lucene-index-test
+                                   PUBLIC JIEBA_TEST_DICT_DIR="${JIEBA_DICT_DIR}")
+
     endif()
 endif()

src/paimon/global_index/lucene/jieba_analyzer.h

@@ -53,7 +53,7 @@ class JiebaTokenizer : public Lucene::Tokenizer {
     static void CutWithMode(const std::string& tokenize_mode, const cppjieba::Jieba* jieba,
                             const std::string& str, std::vector<std::string>* terms_ptr);
 
-    // inplace to lower to avoid data copy
+    // In-place converts each string in `input` to lowercase to avoid data copying.
     static void Normalize(const std::unordered_set<std::string>& stop_words,
                           std::vector<std::string>* input, std::vector<std::string_view>* output);