Change encoding/decoding binary data to use base64 vs utf-8 to prevent bad characters in the oracle string encoding.

game/server/application/SwgDatabaseServer/src/shared/queries/MessageQuery.cpp

@@ -12,6 +12,126 @@
 #include "serverDatabase/DatabaseProcess.h"
 #include "sharedLog/Log.h"
 
+/*
+   base64.cpp and base64.h
+
+   Copyright (C) 2004-2008 René Nyffenegger
+
+   This source code is provided 'as-is', without any express or implied
+   warranty. In no event will the author be held liable for any damages
+   arising from the use of this software.
+
+   Permission is granted to anyone to use this software for any purpose,
+   including commercial applications, and to alter it and redistribute it
+   freely, subject to the following restrictions:
+
+   1. The origin of this source code must not be misrepresented; you must not
+      claim that you wrote the original source code. If you use this source code
+      in a product, an acknowledgment in the product documentation would be
+      appreciated but is not required.
+
+   2. Altered source versions must be plainly marked as such, and must not be
+      misrepresented as being the original source code.
+
+   3. This notice may not be removed or altered from any source distribution.
+
+   René Nyffenegger [email protected]
+*/
+
+static const std::string base64_chars =
+		"ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+				"abcdefghijklmnopqrstuvwxyz"
+				"0123456789+/";
+
+
+static inline bool is_base64(unsigned char c) {
+	return (isalnum(c) || (c == '+') || (c == '/'));
+}
+
+std::string base64_encode(unsigned char const* bytes_to_encode, unsigned int in_len) {
+	std::string ret;
+	int i = 0;
+	int j = 0;
+	unsigned char char_array_3[3];
+	unsigned char char_array_4[4];
+
+	while (in_len--) {
+		char_array_3[i++] = *(bytes_to_encode++);
+		if (i == 3) {
+			char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
+			char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
+			char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
+			char_array_4[3] = char_array_3[2] & 0x3f;
+
+			for(i = 0; (i <4) ; i++)
+				ret += base64_chars[char_array_4[i]];
+			i = 0;
+		}
+	}
+
+	if (i)
+	{
+		for(j = i; j < 3; j++)
+			char_array_3[j] = '\0';
+
+		char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
+		char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
+		char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
+		char_array_4[3] = char_array_3[2] & 0x3f;
+
+		for (j = 0; (j < i + 1); j++)
+			ret += base64_chars[char_array_4[j]];
+
+		while((i++ < 3))
+			ret += '=';
+
+	}
+
+	return ret;
+
+}
+
+std::string base64_decode(std::string const& encoded_string) {
+	int in_len = encoded_string.size();
+	int i = 0;
+	int j = 0;
+	int in_ = 0;
+	unsigned char char_array_4[4], char_array_3[3];
+	std::string ret;
+
+	while (in_len-- && ( encoded_string[in_] != '=') && is_base64(encoded_string[in_])) {
+		char_array_4[i++] = encoded_string[in_]; in_++;
+		if (i ==4) {
+			for (i = 0; i <4; i++)
+				char_array_4[i] = base64_chars.find(char_array_4[i]);
+
+			char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
+			char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
+			char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
+
+			for (i = 0; (i < 3); i++)
+				ret += char_array_3[i];
+			i = 0;
+		}
+	}
+
+	if (i) {
+		for (j = i; j <4; j++)
+			char_array_4[j] = 0;
+
+		for (j = 0; j <4; j++)
+			char_array_4[j] = base64_chars.find(char_array_4[j]);
+
+		char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
+		char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
+		char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
+
+		for (j = 0; (j < i - 1); j++) ret += char_array_3[j];
+	}
+
+	return ret;
+}
+
 //TODO:  don't save non-guaranteed messages
 
 // ======================================================================
@@ -145,25 +265,7 @@ void SaveMessageQuery::getSQL(std::string &sql)
 
 void SaveMessageQuery::convertMessageToUTF8(const std::vector<int8> & messageData, std::string & utf8Data) const
 {
-	int count = messageData.size();
-	utf8Data.resize(0);
-	utf8Data.reserve(count * 2);
-	uint8 c;
-	for (int i = 0; i < count; ++i)
-	{
-		c = messageData[i];
-		if (c >= 0x01 && c <= 0x7f)
-		{
-			// store the data as one byte
-			utf8Data += c;
-		}
-		else
-		{
-			// store the data as two bytes
-			utf8Data += static_cast<char>(0xc0 | ((c >> 6) & 0x1f));
-			utf8Data += static_cast<char>(0x80 | (c & 0x3f));
-		}
-	}
+	utf8Data = base64_encode(reinterpret_cast<const unsigned char*>(messageData.data()), messageData.size());
 }
 
 // ----------------------------------------------------------------------
@@ -326,24 +428,8 @@ void LoadMessagesQuery::getSQL(std::string &sql)
 
 void LoadMessagesQuery::convertUTF8ToMessage(const std::string & utf8Data, std::vector<int8> & messageData) const
 {
-	int count = utf8Data.size();
-	messageData.resize(0);
-	messageData.reserve(count);
-	uint8 c;
-	for (int i = 0; i < count; ++i)
-	{
-		c = utf8Data[i];
-		if ((c & 0xc0) == 0xc0)
-		{
-			// data is stored in 2 bytes
-			messageData.push_back(static_cast<char>(((c & 0x1f) << 6) + (utf8Data[++i] & 0x3f)));
-		}
-		else
-		{
-			// data is stored in 1 byte
-			messageData.push_back(c);
-		}
-	}
+	auto tmp = base64_decode(utf8Data);
+	messageData.insert(std::begin(messageData), std::begin(tmp), std::end(tmp));
 }
 
 // ======================================================================