[Lldb-commits] [lldb] 64e1991 - [lldb] improve the heuristics for checking if a terminal supports Unicode (#168603)

[via lldb-commits]

Author: Charles Zablit
Date: 2025-12-04T17:08:59Z
New Revision: 64e19916f9518709562ef41e236c1dba6c421782

URL: https://github.com/llvm/llvm-project/commit/64e19916f9518709562ef41e236c1dba6c421782
DIFF: https://github.com/llvm/llvm-project/commit/64e19916f9518709562ef41e236c1dba6c421782.diff

LOG: [lldb] improve the heuristics for checking if a terminal supports Unicode (#168603)

This patch improves the way lldb checks if the terminal it's opened in
(if any) supports Unicode or not.

On POSIX systems, we check if `LANG` contains `UTF-8`.

On Windows, we always return `true` since we use the `WriteToConsoleW`
api.

Added: 
    

Modified: 
    lldb/include/lldb/Host/Terminal.h
    lldb/source/Host/common/DiagnosticsRendering.cpp
    lldb/source/Host/common/Terminal.cpp

Removed: 
    


################################################################################
diff  --git a/lldb/include/lldb/Host/Terminal.h b/lldb/include/lldb/Host/Terminal.h
index da0d05e8bd265..3d66515c18812 100644
--- a/lldb/include/lldb/Host/Terminal.h
+++ b/lldb/include/lldb/Host/Terminal.h
@@ -68,6 +68,18 @@ class Terminal {
 
   llvm::Error SetHardwareFlowControl(bool enabled);
 
+  /// Returns whether or not the current terminal supports Unicode rendering.
+  ///
+  /// The value is cached after the first computation.
+  ///
+  /// On POSIX systems, we check if the LANG environment variable contains the
+  /// substring "UTF-8", case insensitive.
+  ///
+  /// On Windows, we always return true since we use the `WriteConsoleW` API
+  /// internally. Note that the default Windows codepage (437) does not support
+  /// all Unicode characters. This function does not check the codepage.
+  static bool SupportsUnicode();
+
 protected:
   struct Data;
 

diff  --git a/lldb/source/Host/common/DiagnosticsRendering.cpp b/lldb/source/Host/common/DiagnosticsRendering.cpp
index f2cd3968967fb..375d1caa99f52 100644
--- a/lldb/source/Host/common/DiagnosticsRendering.cpp
+++ b/lldb/source/Host/common/DiagnosticsRendering.cpp
@@ -7,6 +7,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "lldb/Host/common/DiagnosticsRendering.h"
+#include "lldb/Host/Terminal.h"
+
 #include <cstdint>
 
 using namespace lldb_private;
@@ -97,12 +99,8 @@ void RenderDiagnosticDetails(Stream &stream,
     return;
   }
 
-  // Since there is no other way to find this out, use the color
-  // attribute as a proxy for whether the terminal supports Unicode
-  // characters.  In the future it might make sense to move this into
-  // Host so it can be customized for a specific platform.
   llvm::StringRef cursor, underline, vbar, joint, hbar, spacer;
-  if (stream.AsRawOstream().colors_enabled()) {
+  if (Terminal::SupportsUnicode()) {
     cursor = "˄";
     underline = "˜";
     vbar = "│";

diff  --git a/lldb/source/Host/common/Terminal.cpp b/lldb/source/Host/common/Terminal.cpp
index 436dfd8130d9b..dd1dc75133f45 100644
--- a/lldb/source/Host/common/Terminal.cpp
+++ b/lldb/source/Host/common/Terminal.cpp
@@ -400,6 +400,21 @@ llvm::Error Terminal::SetHardwareFlowControl(bool enabled) {
 #endif // LLDB_ENABLE_TERMIOS
 }
 
+bool Terminal::SupportsUnicode() {
+  static std::optional<bool> result;
+  if (result)
+    return result.value();
+#ifdef _WIN32
+  return true;
+#else
+  const char *lang_var = std::getenv("LANG");
+  if (!lang_var)
+    return false;
+  result = llvm::StringRef(lang_var).lower().find("utf-8") != std::string::npos;
+#endif
+  return result.value();
+}
+
 TerminalState::TerminalState(Terminal term, bool save_process_group)
     : m_tty(term) {
   Save(term, save_process_group);