[clang-tools-extra] [clang-tidy] Fix OOB access in `FormatStringConverter` with signed chars (PR #169215)

[via cfe-commits]

https://github.com/zeyi2 updated https://github.com/llvm/llvm-project/pull/169215

>From 65513c1712bf0d62ec02b6f7c8fae723b9d0f877 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Sun, 23 Nov 2025 22:15:15 +0800
Subject: [PATCH 1/7] [clang-tidy] Fix OOB access in `FormatStringConverter`
 with signed chars

---
 .../clang-tidy/utils/FormatStringConverter.cpp             | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp b/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
index 23dae04916e9b..a3af9504e6542 100644
--- a/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
+++ b/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
@@ -700,6 +700,7 @@ void FormatStringConverter::finalizeFormatText() {
 /// Append literal parts of the format text, reinstating escapes as required.
 void FormatStringConverter::appendFormatText(const StringRef Text) {
   for (const char Ch : Text) {
+    const unsigned char UCh = static_cast<unsigned char>(Ch);
     if (Ch == '\a')
       StandardFormatString += "\\a";
     else if (Ch == '\b')
@@ -724,10 +725,10 @@ void FormatStringConverter::appendFormatText(const StringRef Text) {
     } else if (Ch == '}') {
       StandardFormatString += "}}";
       FormatStringNeededRewriting = true;
-    } else if (Ch < 32) {
+    } else if (UCh < 32) {
       StandardFormatString += "\\x";
-      StandardFormatString += llvm::hexdigit(Ch >> 4, true);
-      StandardFormatString += llvm::hexdigit(Ch & 0xf, true);
+      StandardFormatString += llvm::hexdigit(UCh >> 4, true);
+      StandardFormatString += llvm::hexdigit(UCh & 0xf, true);
     } else
       StandardFormatString += Ch;
   }

>From 785cf305295e09e4838a9b1514397d176f8f6b24 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Sun, 23 Nov 2025 22:30:55 +0800
Subject: [PATCH 2/7] ~

---
 clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp b/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
index a3af9504e6542..d210b000dfd33 100644
--- a/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
+++ b/clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp
@@ -700,7 +700,7 @@ void FormatStringConverter::finalizeFormatText() {
 /// Append literal parts of the format text, reinstating escapes as required.
 void FormatStringConverter::appendFormatText(const StringRef Text) {
   for (const char Ch : Text) {
-    const unsigned char UCh = static_cast<unsigned char>(Ch);
+    const auto UCh = static_cast<unsigned char>(Ch);
     if (Ch == '\a')
       StandardFormatString += "\\a";
     else if (Ch == '\b')

>From 574e84a3a2fdb39fa9e89118f99d43e05055e792 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Sun, 23 Nov 2025 23:03:19 +0800
Subject: [PATCH 3/7] Add testcase and release notes

---
 clang-tools-extra/docs/ReleaseNotes.rst            |  7 ++++---
 .../checkers/modernize/use-std-print.cpp           | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/clang-tools-extra/docs/ReleaseNotes.rst b/clang-tools-extra/docs/ReleaseNotes.rst
index a6f80e3721db1..644c5cb573cf7 100644
--- a/clang-tools-extra/docs/ReleaseNotes.rst
+++ b/clang-tools-extra/docs/ReleaseNotes.rst
@@ -69,7 +69,7 @@ Potentially Breaking Changes
   - `CharTypdefsToIgnore` to `CharTypedefsToIgnore` in
     :doc:`bugprone-signed-char-misuse
     <clang-tidy/checks/bugprone/signed-char-misuse>`
-  
+
 - Modified the custom message format of :doc:`bugprone-unsafe-functions
   <clang-tidy/checks/bugprone/unsafe-functions>` by assigning a special meaning
   to the character ``>`` at the start of the value of the option
@@ -394,7 +394,7 @@ Changes in existing checks
   <clang-tidy/checks/bugprone/unhandled-self-assignment>` check by adding
   an additional matcher that generalizes the copy-and-swap idiom pattern
   detection.
-  
+
 - Improved :doc:`bugprone-unsafe-functions
   <clang-tidy/checks/bugprone/unsafe-functions>` check by hiding the default
   suffix when the reason starts with the character `>` in the `CustomFunctions`
@@ -497,7 +497,8 @@ Changes in existing checks
 - Improved :doc:`modernize-use-std-print
   <clang-tidy/checks/modernize/use-std-print>` check to correctly match
   when the format string is converted to a different type by an implicit
-  constructor call.
+  constructor call, and fixed a crash when handling format strings
+  containing non-ASCII characters.
 
 - Improved :doc:`performance-unnecessary-copy-initialization
   <clang-tidy/checks/performance/unnecessary-copy-initialization>` by printing
diff --git a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
index ec37f077df7fc..a48f4dcb98b86 100644
--- a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
+++ b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
@@ -54,6 +54,13 @@ void printf_deceptive_newline() {
   // CHECK-FIXES: std::println("Hello");
 }
 
+void printf_utf8_text() {
+  // Non-ASCII UTF-8 in format string should not crash.
+  printf("你好世界\n");
+  // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'printf' [modernize-use-std-print]
+  // CHECK-FIXES: std::println("你好世界");
+}
+
 void printf_crlf_newline() {
   printf("Hello\r\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::print' instead of 'printf' [modernize-use-std-print]
@@ -303,6 +310,13 @@ void fprintf_simple() {
   // CHECK-FIXES: std::print(stderr, "Hello");
 }
 
+void fprintf_utf8_text() {
+  // Non-ASCII UTF-8 in format string should not crash.
+  fprintf(stderr, "你好世界\n");
+  // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'fprintf' [modernize-use-std-print]
+  // CHECK-FIXES: std::println(stderr, "你好世界");
+}
+
 void std_printf_simple() {
   std::printf("std::Hello");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::print' instead of 'printf' [modernize-use-std-print]

>From 88e6348cf7bd3e0cc78fca2008ae202a258b2e11 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Sun, 23 Nov 2025 23:35:07 +0800
Subject: [PATCH 4/7] Fix encoding

---
 .../clang-tidy/checkers/modernize/use-std-print.cpp  | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
index a48f4dcb98b86..8c62d90f5dacc 100644
--- a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
+++ b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
@@ -55,10 +55,10 @@ void printf_deceptive_newline() {
 }
 
 void printf_utf8_text() {
-  // Non-ASCII UTF-8 in format string should not crash.
-  printf("你好世界\n");
+  // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
+  printf("\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'printf' [modernize-use-std-print]
-  // CHECK-FIXES: std::println("你好世界");
+  // CHECK-FIXES: std::println("{{.+}}");
 }
 
 void printf_crlf_newline() {
@@ -311,10 +311,10 @@ void fprintf_simple() {
 }
 
 void fprintf_utf8_text() {
-  // Non-ASCII UTF-8 in format string should not crash.
-  fprintf(stderr, "你好世界\n");
+  // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
+  fprintf(stderr, "\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'fprintf' [modernize-use-std-print]
-  // CHECK-FIXES: std::println(stderr, "你好世界");
+  // CHECK-FIXES: std::println(stderr, "{{.+}}");
 }
 
 void std_printf_simple() {

>From 855d4b5ca096fa6826d92309c47fba26416177e0 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Wed, 26 Nov 2025 15:36:45 +0800
Subject: [PATCH 5/7] Try skipping the test on Windows

---
 .../test/clang-tidy/checkers/modernize/use-std-print.cpp    | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
index 8c62d90f5dacc..7ffe662adc67f 100644
--- a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
+++ b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
@@ -55,10 +55,11 @@ void printf_deceptive_newline() {
 }
 
 void printf_utf8_text() {
+  // UNSUPPORTED: system-windows
   // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
   printf("\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'printf' [modernize-use-std-print]
-  // CHECK-FIXES: std::println("{{.+}}");
+  // CHECK-FIXES: std::println("你好世界");
 }
 
 void printf_crlf_newline() {
@@ -311,10 +312,11 @@ void fprintf_simple() {
 }
 
 void fprintf_utf8_text() {
+  // UNSUPPORTED: system-windows
   // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
   fprintf(stderr, "\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'fprintf' [modernize-use-std-print]
-  // CHECK-FIXES: std::println(stderr, "{{.+}}");
+  // CHECK-FIXES: std::println(stderr, "你好世界");
 }
 
 void std_printf_simple() {

>From 021c34f4a1e08020ac6ba07662fbc1531a016818 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Wed, 26 Nov 2025 15:48:34 +0800
Subject: [PATCH 6/7] ~

---
 .../test/clang-tidy/checkers/modernize/use-std-print.cpp    | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
index 7ffe662adc67f..97a2bb07e5608 100644
--- a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
+++ b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
@@ -56,8 +56,7 @@ void printf_deceptive_newline() {
 
 void printf_utf8_text() {
   // UNSUPPORTED: system-windows
-  // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
-  printf("\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
+  printf("你好世界\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'printf' [modernize-use-std-print]
   // CHECK-FIXES: std::println("你好世界");
 }
@@ -313,8 +312,7 @@ void fprintf_simple() {
 
 void fprintf_utf8_text() {
   // UNSUPPORTED: system-windows
-  // Hex encodes U+4F60 U+597D U+4E16 U+754C (Hello world) in UTF-8
-  fprintf(stderr, "\xE4\xBD\xA0\xE5\xA5\xBD\xE4\xB8\x96\xE7\x95\x8C\n");
+  fprintf(stderr, "你好世界\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'fprintf' [modernize-use-std-print]
   // CHECK-FIXES: std::println(stderr, "你好世界");
 }

>From 89c4bfc61dace860730cc5823494f088ec03b258 Mon Sep 17 00:00:00 2001
From: mtx <mitchell.xu2 at gmail.com>
Date: Fri, 28 Nov 2025 20:39:31 +0800
Subject: [PATCH 7/7] Try to make CI happy

---
 clang-tools-extra/test/clang-tidy/check_clang_tidy.py           | 2 ++
 .../test/clang-tidy/checkers/modernize/use-std-print.cpp        | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/clang-tools-extra/test/clang-tidy/check_clang_tidy.py b/clang-tools-extra/test/clang-tidy/check_clang_tidy.py
index 183b33f135be8..94bab9239f942 100755
--- a/clang-tools-extra/test/clang-tidy/check_clang_tidy.py
+++ b/clang-tools-extra/test/clang-tidy/check_clang_tidy.py
@@ -398,6 +398,8 @@ def parse_arguments() -> Tuple[argparse.Namespace, List[str]]:
 
 
 def main() -> None:
+    sys.stdout.reconfigure(encoding='utf-8')
+    sys.stderr.reconfigure(encoding='utf-8')
     args, extra_args = parse_arguments()
 
     abbreviated_stds = args.std
diff --git a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
index 97a2bb07e5608..63972cc0fd25e 100644
--- a/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
+++ b/clang-tools-extra/test/clang-tidy/checkers/modernize/use-std-print.cpp
@@ -55,7 +55,6 @@ void printf_deceptive_newline() {
 }
 
 void printf_utf8_text() {
-  // UNSUPPORTED: system-windows
   printf("你好世界\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'printf' [modernize-use-std-print]
   // CHECK-FIXES: std::println("你好世界");
@@ -311,7 +310,6 @@ void fprintf_simple() {
 }
 
 void fprintf_utf8_text() {
-  // UNSUPPORTED: system-windows
   fprintf(stderr, "你好世界\n");
   // CHECK-MESSAGES: [[@LINE-1]]:3: warning: use 'std::println' instead of 'fprintf' [modernize-use-std-print]
   // CHECK-FIXES: std::println(stderr, "你好世界");