[lldb] improve the heuristics for checking if a terminal supports Unicode

Author: charles-zablit

lldb/include/lldb/Host/Terminal.h

@@ -169,6 +169,17 @@ class TerminalState {
   lldb::pid_t m_process_group = -1;       ///< Cached process group information.
 };
 
+/// 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";
+///
+/// On Windows, we check that we are running from the Windows Terminal
+/// application.
+bool TerminalSupportsUnicode();
+
 } // namespace lldb_private
 
 #endif // LLDB_HOST_TERMINAL_H

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 (TerminalSupportsUnicode()) {
     cursor = "˄";
     underline = "˜";
     vbar = "│";

lldb/source/Host/common/Terminal.cpp

@@ -472,3 +472,18 @@ bool TerminalState::TTYStateIsValid() const { return bool(m_data); }
 bool TerminalState::ProcessGroupIsValid() const {
   return static_cast<int32_t>(m_process_group) != -1;
 }
+
+bool lldb_private::TerminalSupportsUnicode() {
+  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();
+}