--- lbbs/src/str_process.c	2025/10/18 12:06:10	1.21
+++ lbbs/src/str_process.c	2025/12/18 02:56:01	1.33
@@ -1,27 +1,32 @@
-/***************************************************************************
-						  str_process.c  -  description
-							 -------------------
-	Copyright            : (C) 2004-2025 by Leaflet
-	Email                : leaflet@leafok.com
- ***************************************************************************/
-
-/***************************************************************************
- *                                                                         *
- *   This program is free software; you can redistribute it and/or modify  *
- *   it under the terms of the GNU General Public License as published by  *
- *   the Free Software Foundation; either version 3 of the License, or     *
- *   (at your option) any later version.                                   *
- *                                                                         *
- ***************************************************************************/
+/* SPDX-License-Identifier: GPL-3.0-or-later */
+/*
+ * str_process
+ *   - common string processing features with UTF-8 support
+ *
+ * Copyright (C) 2004-2025  Leaflet <leaflet@leafok.com>
+ */
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
 
 #include "common.h"
 #include "log.h"
 #include "str_process.h"
+#include <ctype.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
+#include <wchar.h>
+
+int UTF8_fixed_width = 1;
 
 int str_length(const char *str, int skip_ctrl_seq)
 {
+	int str_len;
+	char input_str[5];
+	wchar_t wcs[2];
+	int wc_len;
 	int i;
 	char c;
 	int ret = 0;
@@ -37,25 +42,50 @@ int str_length(const char *str, int skip
 
 		if (skip_ctrl_seq && c == '\033' && str[i + 1] == '[') // Skip control sequence
 		{
-			i += 2;
-			while (str[i] != '\0' && str[i] != 'm')
+			for (i = i + 2; isdigit((int)str[i]) || str[i] == ';' || str[i] == '?'; i++)
+				;
+
+			if (str[i] == 'm') // valid
 			{
-				i++;
+				// skip
+			}
+			else if (isalpha((int)str[i]))
+			{
+				// unsupported ANSI CSI command
+			}
+			else
+			{
+				i--;
 			}
+
 			continue;
 		}
 
 		// Process UTF-8 Chinese characters
 		if (c & 0x80) // head of multi-byte character
 		{
-			c = (c & 0x70) << 1;
+			str_len = 0;
+			c = (char)(c & 0xf0);
 			while (c & 0x80)
 			{
-				i++;
+				input_str[str_len] = str[i + str_len];
+				str_len++;
 				c = (c & 0x7f) << 1;
 			}
+			input_str[str_len] = '\0';
 
-			ret += 2;
+			if (mbstowcs(wcs, input_str, 1) == (size_t)-1)
+			{
+				log_debug("mbstowcs(%s) error\n", input_str);
+				wc_len = (UTF8_fixed_width ? 2 : 1); // Fallback
+			}
+			else
+			{
+				wc_len = (UTF8_fixed_width ? 2 : wcwidth(wcs[0]));
+			}
+
+			i += (str_len - 1);
+			ret += wc_len;
 		}
 		else
 		{
@@ -72,6 +102,10 @@ int split_line(const char *buffer, int m
 	*p_eol = 0;
 	*p_display_len = 0;
 	char c;
+	int str_len;
+	char input_str[5];
+	wchar_t wcs[2];
+	int wc_len;
 
 	for (i = 0; buffer[i] != '\0'; i++)
 	{
@@ -94,19 +128,33 @@ int split_line(const char *buffer, int m
 
 		if (c & 0x80) // head of multi-byte character
 		{
-			if (*p_display_len + 2 > max_display_len)
+			str_len = 0;
+			c = (char)(c & 0xf0);
+			while (c & 0x80)
 			{
-				break;
+				input_str[str_len] = buffer[i + str_len];
+				str_len++;
+				c = (c & 0x7f) << 1;
 			}
+			input_str[str_len] = '\0';
 
-			c = (c & 0x70) << 1;
-			while (c & 0x80)
+			if (mbstowcs(wcs, input_str, 1) == (size_t)-1)
 			{
-				i++;
-				c = (c & 0x7f) << 1;
+				log_debug("mbstowcs(%s) error\n", input_str);
+				wc_len = (UTF8_fixed_width ? 2 : 1); // Fallback
+			}
+			else
+			{
+				wc_len = (UTF8_fixed_width ? 2 : wcwidth(wcs[0]));
+			}
+
+			if (*p_display_len + wc_len > max_display_len)
+			{
+				break;
 			}
 
-			(*p_display_len) += 2;
+			i += (str_len - 1);
+			(*p_display_len) += wc_len;
 		}
 		else
 		{
@@ -151,14 +199,14 @@ long split_data_lines(const char *p_buf,
 		// Exceed max_line_cnt
 		if (line_cnt + 1 >= line_offsets_count)
 		{
-			// log_error("Line count %d reaches limit %d\n", line_cnt + 1, line_offsets_count);
+			log_debug("Line count %d reaches limit %d\n", line_cnt + 1, line_offsets_count);
 			return line_cnt;
 		}
 
 		p_line_offsets[line_cnt + 1] = p_line_offsets[line_cnt] + len;
 		line_cnt++;
 		p_buf += len;
-	} while (p_buf[0] != '\0');
+	} while (p_buf[0] != '\0' || end_of_line);
 
 	return line_cnt;
 }