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

Author: charles-zablit

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;
 

lldb/source/Host/common/DiagnosticsRendering.cpp

@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "lldb/Host/common/DiagnosticsRendering.h"
+#include "lldb/Host/Terminal.h"
 #include <cstdint>
 
 using namespace lldb_private;
@@ -102,7 +103,7 @@ void RenderDiagnosticDetails(Stream &stream,
   // 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 (TerminalSupportsUnicode()) {
+  if (Terminal::SupportsUnicode()) {
     cursor = "˄";
     underline = "˜";
     vbar = "│";
@@ -231,20 +232,4 @@ void RenderDiagnosticDetails(Stream &stream,
       stream << detail.rendered << '\n';
     }
 }
-
-bool TerminalSupportsUnicode() {
-  static std::optional<bool> result;
-  if (result)
-    return result.value();
-#ifndef _WIN32
-  if (const char *lang_var = std::getenv("LANG"))
-    result = std::string(lang_var).find("UTF-8");
-  else
-    result = false;
-#else
-  result = std::getenv("WT_SESSION") != nullptr;
-#endif
-  return result.value();
-}
-
 } // namespace lldb_private

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);

lldb/source/Target/StackFrameList.cpp

@@ -23,7 +23,6 @@
 #include "lldb/Target/Target.h"
 #include "lldb/Target/Thread.h"
 #include "lldb/Target/Unwind.h"
-#include "lldb/Utility/DiagnosticsRendering.h"
 #include "lldb/Utility/LLDBLog.h"
 #include "lldb/Utility/Log.h"
 #include "llvm/ADT/SmallPtrSet.h"
@@ -902,8 +901,8 @@ bool StackFrameList::IsPreviousFrameHidden(lldb_private::StackFrame &frame) {
 std::wstring StackFrameList::FrameMarker(lldb::StackFrameSP frame_sp,
                                          lldb::StackFrameSP selected_frame_sp) {
   if (frame_sp == selected_frame_sp) {
-    return TerminalSupportsUnicode() ? L" * " : L"* ";
-  } else if (!TerminalSupportsUnicode()) {
+    return Terminal::SupportsUnicode() ? L" * " : L"* ";
+  } else if (!Terminal::SupportsUnicode()) {
     return L"  ";
   } else if (IsPreviousFrameHidden(*frame_sp)) {
     return L" ﹉";