[Lldb-commits] [lldb] [lldb] improve the heuristics for checking if a terminal supports Unicode (PR #168603)
Charles Zablit via lldb-commits
lldb-commits at lists.llvm.org
Mon Nov 24 10:03:07 PST 2025
https://github.com/charles-zablit updated https://github.com/llvm/llvm-project/pull/168603
>From 65126c7ebb94bcee69ac513ec97e0227f4f2e1aa Mon Sep 17 00:00:00 2001
From: Charles Zablit <c_zablit at apple.com>
Date: Tue, 18 Nov 2025 22:41:43 +0100
Subject: [PATCH 1/3] [lldb] improve the heuristics for checking if a terminal
supports Unicode
---
lldb/include/lldb/Host/Terminal.h | 11 +++++++++++
lldb/source/Host/common/DiagnosticsRendering.cpp | 8 +++-----
lldb/source/Host/common/Terminal.cpp | 15 +++++++++++++++
3 files changed, 29 insertions(+), 5 deletions(-)
diff --git a/lldb/include/lldb/Host/Terminal.h b/lldb/include/lldb/Host/Terminal.h
index da0d05e8bd265..6da5d45644b28 100644
--- a/lldb/include/lldb/Host/Terminal.h
+++ b/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
diff --git a/lldb/source/Host/common/DiagnosticsRendering.cpp b/lldb/source/Host/common/DiagnosticsRendering.cpp
index f2cd3968967fb..c7e083573c631 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 (TerminalSupportsUnicode()) {
cursor = "˄";
underline = "˜";
vbar = "│";
diff --git a/lldb/source/Host/common/Terminal.cpp b/lldb/source/Host/common/Terminal.cpp
index 436dfd8130d9b..825e9e0aee78e 100644
--- a/lldb/source/Host/common/Terminal.cpp
+++ b/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();
+}
>From 6fc6b567ba158d9867561b45ac68a3601c28c67e Mon Sep 17 00:00:00 2001
From: Charles Zablit <c_zablit at apple.com>
Date: Wed, 19 Nov 2025 15:01:23 +0100
Subject: [PATCH 2/3] fixup! [lldb] improve the heuristics for checking if a
terminal supports Unicode
---
lldb/include/lldb/Host/Terminal.h | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/lldb/include/lldb/Host/Terminal.h b/lldb/include/lldb/Host/Terminal.h
index 6da5d45644b28..bfcd66b13ded8 100644
--- a/lldb/include/lldb/Host/Terminal.h
+++ b/lldb/include/lldb/Host/Terminal.h
@@ -174,10 +174,11 @@ class TerminalState {
/// The value is cached after the first computation.
///
/// On POSIX systems, we check if the LANG environment variable contains the
-/// substring "UTF-8";
+/// substring "UTF-8", case insensitive.
///
-/// On Windows, we check that we are running from the Windows Terminal
-/// application.
+/// 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.
bool TerminalSupportsUnicode();
} // namespace lldb_private
>From 19cad716e620256a06be2ac03351b0a5116380ee Mon Sep 17 00:00:00 2001
From: Charles Zablit <c_zablit at apple.com>
Date: Mon, 24 Nov 2025 18:02:45 +0000
Subject: [PATCH 3/3] fixup! fixup! [lldb] improve the heuristics for checking
if a terminal supports Unicode
---
lldb/include/lldb/Host/Terminal.h | 24 +++++++++++-----------
lldb/source/Host/common/Terminal.cpp | 30 ++++++++++++++--------------
2 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/lldb/include/lldb/Host/Terminal.h b/lldb/include/lldb/Host/Terminal.h
index bfcd66b13ded8..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;
@@ -169,18 +181,6 @@ 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", 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.
-bool TerminalSupportsUnicode();
-
} // namespace lldb_private
#endif // LLDB_HOST_TERMINAL_H
diff --git a/lldb/source/Host/common/Terminal.cpp b/lldb/source/Host/common/Terminal.cpp
index 825e9e0aee78e..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);
@@ -472,18 +487,3 @@ 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();
-}
More information about the lldb-commits
mailing list