refactor(string): Add srcLen parameter to conversion functions to avoid double string scan

Author: bobtista

Core/GameEngine/Source/Common/System/AsciiString.cpp

@@ -276,12 +276,15 @@ void AsciiString::translate(const UnicodeString& stringSrc)
 	// TheSuperHackers @fix bobtista 02/04/2026 Implement UTF-8 conversion replacing 7-bit ASCII only implementation
 	clear();
 	const WideChar* src = stringSrc.str();
-	size_t size = Get_Utf8_Size(src);
+	size_t srcLen = wcslen(src);
+	size_t size = Get_Utf8_Size(src, srcLen);
 	if (size == 0)
 		return;
 	char* buf = getBufferForRead((Int)size);
-	if (!Unicode_To_Utf8(buf, src, size + 1))
+	if (!Unicode_To_Utf8(buf, src, srcLen, size))
 		clear();
+	else
+		buf[size] = '\0';
 	validate();
 }
 

Core/GameEngine/Source/Common/System/UnicodeString.cpp

@@ -225,12 +225,15 @@ void UnicodeString::translate(const AsciiString& stringSrc)
 	// TheSuperHackers @fix bobtista 02/04/2026 Implement UTF-8 conversion replacing 7-bit ASCII only implementation
 	clear();
 	const char* src = stringSrc.str();
-	size_t size = Get_Unicode_Size(src);
+	size_t srcLen = strlen(src);
+	size_t size = Get_Unicode_Size(src, srcLen);
 	if (size == 0)
 		return;
 	WideChar* buf = getBufferForRead((Int)size);
-	if (!Utf8_To_Unicode(buf, src, size + 1))
+	if (!Utf8_To_Unicode(buf, src, srcLen, size))
 		clear();
+	else
+		buf[size] = L'\0';
 	validate();
 }
 

Core/GameEngine/Source/GameNetwork/GameSpy/Thread/ThreadUtils.cpp

@@ -35,11 +35,12 @@
 // TheSuperHackers @refactor bobtista 02/04/2026 Use WWLib UTF-8 functions instead of raw Win32 API calls
 std::wstring MultiByteToWideCharSingleLine( const char *orig )
 {
-	size_t size = Get_Unicode_Size(orig);
+	size_t srcLen = strlen(orig);
+	size_t size = Get_Unicode_Size(orig, srcLen);
 	if (size == 0)
 		return std::wstring();
 	std::wstring ret(size, L'\0');
-	Utf8_To_Unicode(&ret[0], orig, size + 1);
+	Utf8_To_Unicode(&ret[0], orig, srcLen, size);
 	WideChar *c = nullptr;
 	do
 	{
@@ -65,11 +66,12 @@ std::wstring MultiByteToWideCharSingleLine( const char *orig )
 
 std::string WideCharStringToMultiByte( const WideChar *orig )
 {
-	size_t size = Get_Utf8_Size(orig);
+	size_t srcLen = wcslen(orig);
+	size_t size = Get_Utf8_Size(orig, srcLen);
 	if (size == 0)
 		return std::string();
 	std::string ret(size, '\0');
-	Unicode_To_Utf8(&ret[0], orig, size + 1);
+	Unicode_To_Utf8(&ret[0], orig, srcLen, size);
 	return ret;
 }
 

Core/Libraries/Source/WWVegas/WWLib/utf8.cpp

@@ -84,33 +84,33 @@ bool Utf8_Validate(const char* str, size_t length)
 	return true;
 }
 
-size_t Get_Utf8_Size(const wchar_t* src)
+size_t Get_Utf8_Size(const wchar_t* src, size_t srcLen)
 {
-	int bytes = WideCharToMultiByte(CP_UTF8, 0, src, -1, nullptr, 0, nullptr, nullptr);
-	return (bytes > 1) ? (size_t)(bytes - 1) : 0;
+	int bytes = WideCharToMultiByte(CP_UTF8, 0, src, (int)srcLen, nullptr, 0, nullptr, nullptr);
+	return (bytes > 0) ? (size_t)bytes : 0;
 }
 
-size_t Get_Unicode_Size(const char* src)
+size_t Get_Unicode_Size(const char* src, size_t srcLen)
 {
-	int wchars = MultiByteToWideChar(CP_UTF8, 0, src, -1, nullptr, 0);
-	return (wchars > 1) ? (size_t)(wchars - 1) : 0;
+	int wchars = MultiByteToWideChar(CP_UTF8, 0, src, (int)srcLen, nullptr, 0);
+	return (wchars > 0) ? (size_t)wchars : 0;
 }
 
-bool Unicode_To_Utf8(char* dest, const wchar_t* src, size_t dest_size)
+bool Unicode_To_Utf8(char* dest, const wchar_t* src, size_t srcLen, size_t dest_size)
 {
 	if (dest_size == 0)
 		return false;
-	int result = WideCharToMultiByte(CP_UTF8, 0, src, -1, dest, (int)dest_size, nullptr, nullptr);
+	int result = WideCharToMultiByte(CP_UTF8, 0, src, (int)srcLen, dest, (int)dest_size, nullptr, nullptr);
 	if (result == 0)
 		dest[0] = '\0';
 	return result != 0;
 }
 
-bool Utf8_To_Unicode(wchar_t* dest, const char* src, size_t dest_size)
+bool Utf8_To_Unicode(wchar_t* dest, const char* src, size_t srcLen, size_t dest_size)
 {
 	if (dest_size == 0)
 		return false;
-	int result = MultiByteToWideChar(CP_UTF8, 0, src, -1, dest, (int)dest_size);
+	int result = MultiByteToWideChar(CP_UTF8, 0, src, (int)srcLen, dest, (int)dest_size);
 	if (result == 0)
 		dest[0] = L'\0';
 	return result != 0;

Core/Libraries/Source/WWVegas/WWLib/utf8.h

@@ -33,18 +33,20 @@ size_t Utf8_Trailing_Invalid_Bytes(const char* str, size_t length);
 bool Utf8_Validate(const char* str);
 bool Utf8_Validate(const char* str, size_t length);
 
-// Returns the number of bytes in the UTF-8 representation of src, excluding the
-// null terminator. Returns 0 on failure or if src is empty.
-size_t Get_Utf8_Size(const wchar_t* src);
+// Returns the number of bytes in the UTF-8 representation of srcLen wide characters
+// from src. Returns 0 on failure or if srcLen is 0.
+size_t Get_Utf8_Size(const wchar_t* src, size_t srcLen);
 
 // Returns the number of wchar_t elements in the wide character representation of
-// the UTF-8 string src, excluding the null terminator. Returns 0 on failure or if src is empty.
-size_t Get_Unicode_Size(const char* src);
-
-// Converts a wide character string to UTF-8. dest_size is in bytes.
-// Returns true on success, false on failure. On failure, dest[0] is set to '\0'.
-bool Unicode_To_Utf8(char* dest, const wchar_t* src, size_t dest_size);
-
-// Converts a UTF-8 string to wide characters. dest_size is in wchar_t elements.
-// Returns true on success, false on failure. On failure, dest[0] is set to L'\0'.
-bool Utf8_To_Unicode(wchar_t* dest, const char* src, size_t dest_size);
+// srcLen bytes from the UTF-8 string src. Returns 0 on failure or if srcLen is 0.
+size_t Get_Unicode_Size(const char* src, size_t srcLen);
+
+// Converts srcLen wide characters from src to UTF-8. dest_size is in bytes.
+// Does not write a null terminator. Returns true on success, false on failure.
+// On failure, dest[0] is set to '\0'.
+bool Unicode_To_Utf8(char* dest, const wchar_t* src, size_t srcLen, size_t dest_size);
+
+// Converts srcLen bytes from the UTF-8 string src to wide characters. dest_size is in wchar_t elements.
+// Does not write a null terminator. Returns true on success, false on failure.
+// On failure, dest[0] is set to L'\0'.
+bool Utf8_To_Unicode(wchar_t* dest, const char* src, size_t srcLen, size_t dest_size);