Unicode improvements and version bump.

- Added full UTF-8 support for terminal rendering, including multi-width character handling.
- Improved font handling in ImGui with expanded glyph support (Greek, Mathematical Operators).
- Updated locale initialization to enable proper character rendering.
- Bumped version to 1.5.8.

CMakeLists.txt

@@ -4,7 +4,7 @@ project(kte)
 include(GNUInstallDirs)
 
 set(CMAKE_CXX_STANDARD 20)
-set(KTE_VERSION "1.5.7")
+set(KTE_VERSION "1.5.8")
 
 # Default to terminal-only build to avoid SDL/OpenGL dependency by default.
 # Enable with -DBUILD_GUI=ON when SDL2/OpenGL/Freetype are available.

ImGuiFrontend.cc

@@ -357,14 +357,43 @@ GUIFrontend::LoadGuiFont_(const char * /*path*/, const float size_px)
 {
 	const ImGuiIO &io = ImGui::GetIO();
 	io.Fonts->Clear();
-	const ImFont *font = io.Fonts->AddFontFromMemoryCompressedTTF(
+
+	ImFontConfig config;
+	config.MergeMode = false;
+
+	// Load Basic Latin + Latin Supplement
+	io.Fonts->AddFontFromMemoryCompressedTTF(
 		kte::Fonts::DefaultFontData,
 		kte::Fonts::DefaultFontSize,
-		size_px);
+		size_px,
-	if (!font) {
+		&config,
-		font = io.Fonts->AddFontDefault();
+		io.Fonts->GetGlyphRangesDefault());
-	}
+
-	(void) font;
+	// Merge Greek and Coptic
+	config.MergeMode                    = true;
+	static const ImWchar greek_ranges[] = {
+		0x0370, 0x03FF, // Greek and Coptic
+		0,
+	};
+	io.Fonts->AddFontFromMemoryCompressedTTF(
+		kte::Fonts::DefaultFontData,
+		kte::Fonts::DefaultFontSize,
+		size_px,
+		&config,
+		greek_ranges);
+
+	// Merge Mathematical Operators
+	static const ImWchar math_ranges[] = {
+		0x2200, 0x22FF, // Mathematical Operators
+		0,
+	};
+	io.Fonts->AddFontFromMemoryCompressedTTF(
+		kte::Fonts::DefaultFontData,
+		kte::Fonts::DefaultFontSize,
+		size_px,
+		&config,
+		math_ranges);
+
 	io.Fonts->Build();
 	return true;
 }

TerminalRenderer.cc

@@ -1,3 +1,6 @@
+#include <clocale>
+#define _XOPEN_SOURCE_EXTENDED 1
+#include <cwchar>
 #include <algorithm>
 #include <cstdio>
 #include <filesystem>
@@ -177,15 +180,32 @@ TerminalRenderer::Draw(Editor &ed)
 					}
 				};
 				while (written < cols) {
-					char ch       = ' ';
 					bool from_src = false;
+					wchar_t wch   = L' ';
+					int wch_len   = 1;
+					int disp_w    = 1;
+
 					if (src_i < line.size()) {
-						unsigned char c = static_cast<unsigned char>(line[src_i]);
+						// Decode UTF-8
-						if (c == '\t') {
+						std::mbstate_t state = std::mbstate_t();
+						size_t res           = std::mbrtowc(
+							&wch, &line[src_i], line.size() - src_i, &state);
+						if (res == (size_t) -1 || res == (size_t) -2) {
+							// Invalid or incomplete; treat as single byte
+							wch     = static_cast<unsigned char>(line[src_i]);
+							wch_len = 1;
+						} else if (res == 0) {
+							wch     = L'\0';
+							wch_len = 1;
+						} else {
+							wch_len = static_cast<int>(res);
+						}
+
+						if (wch == L'\t') {
 							std::size_t next_tab = tabw - (render_col % tabw);
 							if (render_col + next_tab <= coloffs) {
 								render_col += next_tab;
-								++src_i;
+								src_i      += wch_len;
 								continue;
 							}
 							// Emit spaces for tab
@@ -233,23 +253,34 @@ TerminalRenderer::Draw(Editor &ed)
 								++render_col;
 								--next_tab;
 							}
-							++src_i;
+							src_i += wch_len;
 							continue;
 						} else {
 							// normal char
+							disp_w = wcwidth(wch);
+							if (disp_w < 0)
+								disp_w = 1; // non-printable or similar
+
 							if (render_col < coloffs) {
-								++render_col;
+								render_col += disp_w;
-								++src_i;
+								src_i      += wch_len;
 								continue;
 							}
-							ch       = static_cast<char>(c);
 							from_src = true;
 						}
 					} else {
 						// beyond EOL, fill spaces
-						ch       = ' ';
+						wch      = L' ';
+						wch_len  = 1;
+						disp_w   = 1;
 						from_src = false;
 					}
+
+					if (written + disp_w > cols) {
+						// would overflow, just break
+						break;
+					}
+
 					bool in_hl  = search_mode && from_src && is_src_in_hl(src_i);
 					bool in_cur =
 						has_current && li == cur_my && from_src && src_i >= cur_mx && src_i <
@@ -273,11 +304,20 @@ TerminalRenderer::Draw(Editor &ed)
 					if (!in_hl && from_src) {
 						apply_token_attr(token_at(src_i));
 					}
-					addch(static_cast<unsigned char>(ch));
+
-					++written;
+					if (from_src) {
-					++render_col;
+						cchar_t cch;
+						wchar_t warr[2] = {wch, L'\0'};
+						setcchar(&cch, warr, A_NORMAL, 0, nullptr);
+						add_wch(&cch);
+					} else {
+						addch(' ');
+					}
+
+					written    += disp_w;
+					render_col += disp_w;
 					if (from_src)
-						++src_i;
+						src_i += wch_len;
 					if (src_i >= line.size() && written >= cols)
 						break;
 				}
@@ -306,14 +346,26 @@ TerminalRenderer::Draw(Editor &ed)
 			std::size_t src_i_cur             = 0;
 			std::size_t render_col_cur        = 0;
 			while (src_i_cur < line_for_cursor.size() && src_i_cur < cx) {
-				unsigned char ccur = static_cast<unsigned char>(line_for_cursor[src_i_cur]);
+				std::mbstate_t state = std::mbstate_t();
-				if (ccur == '\t') {
+				wchar_t wch;
+				size_t res = std::mbrtowc(
+					&wch, &line_for_cursor[src_i_cur], line_for_cursor.size() - src_i_cur,
+					&state);
+
+				if (res == (size_t) -1 || res == (size_t) -2) {
+					render_col_cur += 1;
+					src_i_cur      += 1;
+				} else if (res == 0) {
+					src_i_cur += 1;
+				} else {
+					if (wch == L'\t') {
 						std::size_t next_tab = tabw - (render_col_cur % tabw);
 						render_col_cur       += next_tab;
-					++src_i_cur;
 					} else {
-					++render_col_cur;
+						int dw         = wcwidth(wch);
-					++src_i_cur;
+						render_col_cur += (dw < 0) ? 1 : dw;
+					}
+					src_i_cur += res;
 				}
 			}
 			rx_recomputed = render_col_cur;

fonts/Font.cc

@@ -8,16 +8,43 @@ Font::Load(const float size) const
 {
 	const ImGuiIO &io = ImGui::GetIO();
 	io.Fonts->Clear();
-	const ImFont *font = io.Fonts->AddFontFromMemoryCompressedTTF(
+
+	ImFontConfig config;
+	config.MergeMode = false;
+
+	// Load Basic Latin + Latin Supplement
+	io.Fonts->AddFontFromMemoryCompressedTTF(
 		this->data_,
 		this->size_,
-		size);
+		size,
+		&config,
+		io.Fonts->GetGlyphRangesDefault());
 
-	if (!font) {
+	// Merge Greek and Coptic
-		font = io.Fonts->AddFontDefault();
+	config.MergeMode                    = true;
-	}
+	static const ImWchar greek_ranges[] = {
+		0x0370, 0x03FF, // Greek and Coptic
+		0,
+	};
+	io.Fonts->AddFontFromMemoryCompressedTTF(
+		this->data_,
+		this->size_,
+		size,
+		&config,
+		greek_ranges);
+
+	// Merge Mathematical Operators
+	static const ImWchar math_ranges[] = {
+		0x2200, 0x22FF, // Mathematical Operators
+		0,
+	};
+	io.Fonts->AddFontFromMemoryCompressedTTF(
+		this->data_,
+		this->size_,
+		size,
+		&config,
+		math_ranges);
 
-	(void) font;
 	io.Fonts->Build();
 }
 } // namespace kte::Fonts

main.cc

@@ -1,3 +1,4 @@
+#include <clocale>
 #include <cctype>
 #include <cerrno>
 #include <cstdio>
@@ -113,6 +114,8 @@ RunStressHighlighter(unsigned seconds)
 int
 main(int argc, const char *argv[])
 {
+	std::setlocale(LC_ALL, "");
+
 	Editor editor;
 
 	// CLI parsing using getopt_long