Update src/paimon/global_index/lucene/jieba_analyzer.cpp

lszskye · Copilot · web-flow · commit b23308cfe88f · 2026-02-04T16:06:12.000+08:00
Co-authored-by: Copilot &lt;175728472+Copilot@users.noreply.github.com&gt;
diff --git a/src/paimon/global_index/lucene/jieba_analyzer.cpp b/src/paimon/global_index/lucene/jieba_analyzer.cpp
@@ -98,13 +98,14 @@ void JiebaTokenizer::Normalize(const std::unordered_set<std::string>& stop_words
         // to lower case
         bool is_alphanumeric = true;
         for (const auto& c : term) {
-            if (!std::isalnum(c)) {
+            if (!std::isalnum(static_cast<unsigned char>(c))) {
                 is_alphanumeric = false;
                 break;
             }
         }
         if (is_alphanumeric && !term.empty()) {
-            std::transform(term.begin(), term.end(), term.begin(), ::tolower);
+            std::transform(term.begin(), term.end(), term.begin(),
+                           [](char ch) { return static_cast<char>(std::tolower(static_cast<unsigned char>(ch))); });
         }
         output.emplace_back(term.data(), term.length());
     }

Original file line number	Diff line number	Diff line change
`@@ -98,13 +98,14 @@ void JiebaTokenizer::Normalize(const std::unordered_set<std::string>& stop_words`
`98`	`98`	`// to lower case`
`99`	`99`	`bool is_alphanumeric = true;`
`100`	`100`	`for (const auto& c : term) {`
`101`		`- if (!std::isalnum(c)) {`
	`101`	`+ if (!std::isalnum(static_cast<unsigned char>(c))) {`
`102`	`102`	`is_alphanumeric = false;`
`103`	`103`	`break;`
`104`	`104`	`}`
`105`	`105`	`}`
`106`	`106`	`if (is_alphanumeric && !term.empty()) {`
`107`		`- std::transform(term.begin(), term.end(), term.begin(), ::tolower);`
	`107`	`+ std::transform(term.begin(), term.end(), term.begin(),`
	`108`	`+ [](char ch) { return static_cast<char>(std::tolower(static_cast<unsigned char>(ch))); });`
`108`	`109`	`}`
`109`	`110`	`output.emplace_back(term.data(), term.length());`
`110`	`111`	`}`