ModernUO/Projects/UOContent/Network/Packets/IncomingMessagePackets.cs
Kamron Batman 0404251638
feat: Adds Latin1 text support (#2317)
## Summary

- Adds proper Latin1 encoding support, replacing CP1252 usage throughout the codebase
- Adds specialized, optimized string decoding methods with safe string filtering for each encoding type
- Filters invalid Unicode characters (C0/C1 control codes, non-characters) by removal rather than replacement since
the UO client renders nothing for these characters
- Fixes UTF-16 null terminator position handling to correctly advance by 2 bytes

## Changes

TextEncoding.cs

- Added SearchValues-based invalid byte/char detection for efficient filtering
- Added encoding-specific GetString methods: GetStringAscii, GetStringLatin1, GetStringUtf8, GetStringBigUni,
GetStringLittleUni
- Each method supports a safeString parameter for filtering invalid characters
- Little-endian UTF-16 uses direct memory cast for zero-copy decoding on LE systems
- Invalid characters are removed (not replaced with U+FFFD) since the client renders nothing for them

SpanReader.cs

- Added ReadLatin1() and ReadLatin1Safe() methods
- Rewrote encoding-specific read methods to use optimized TextEncoding.GetString* methods
- Fixed UTF-16 null terminator handling: position now correctly advances by byteLength (2) instead of 1

SpanWriter.cs

- Added WriteLatin1 and WriteLatin1Null methods

## Packet Updates

- Updated all packet code to use Latin1 encoding instead of CP1252
- Affected: account packets, equipment packets, menu packets, message packets, mobile packets, player packets, secure
trade packets, vendor packets, gump packets, book packets, mahjong packets

## Filtering Behavior

Invalid characters filtered in safe mode:
```
┌───────────────┬────────────────────────┐
│     Range     │      Description       │
├───────────────┼────────────────────────┤
│ 0x00-0x1F     │ C0 control codes       │
├───────────────┼────────────────────────┤
│ 0x7F          │ DEL                    │
├───────────────┼────────────────────────┤
│ 0x80-0x9F     │ C1 control codes       │
├───────────────┼────────────────────────┤
│ 0xFFFE-0xFFFF │ Unicode non-characters │
└───────────────┴────────────────────────┘
```

Note: Surrogate pairs (0xD800-0xDFFF) are not filtered because proper validation requires context checking for paired
vs unpaired surrogates. The UO client renders nothing for these anyway.

## Test Plan

- All 631 Server.Tests pass
- Verified client rendering behavior using TestUnicodeGump command (pages 1-5)
- Confirmed U+FFFD, unpaired surrogates, and non-characters all render as blank in client
- Verified Latin1 characters (0xA0-0xFF) display correctly
- Verified C1 control codes (0x80-0x9F) are filtered and don't display
2026-01-22 15:51:00 -08:00

141 lines
3.9 KiB
C#

/*************************************************************************
* ModernUO *
* Copyright 2019-2023 - ModernUO Development Team *
* Email: hi@modernuo.com *
* File: IncomingMessagePackets.cs *
* *
* 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. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program. If not, see <http://www.gnu.org/licenses/>. *
*************************************************************************/
using System;
using System.Buffers;
namespace Server.Network;
public static class IncomingMessagePackets
{
private static readonly KeywordList m_KeywordList = new();
public static unsafe void Configure()
{
IncomingPackets.Register(0x03, 0, true, &AsciiSpeech);
IncomingPackets.Register(0xAD, 0, true, &UnicodeSpeech);
}
public static void AsciiSpeech(NetState state, SpanReader reader)
{
var from = state.Mobile;
if (from == null)
{
return;
}
var type = (MessageType)reader.ReadByte();
int hue = reader.ReadInt16();
reader.ReadInt16(); // font
var text = reader.ReadLatin1Safe().Trim();
if (text.Length is <= 0 or > 128)
{
return;
}
if (!Enum.IsDefined(typeof(MessageType), type))
{
type = MessageType.Regular;
}
from.DoSpeech(text, Array.Empty<int>(), type, Utility.ClipDyedHue(hue));
}
public static void UnicodeSpeech(NetState state, SpanReader reader)
{
var from = state.Mobile;
if (from == null)
{
return;
}
var type = (MessageType)reader.ReadByte();
int hue = reader.ReadInt16();
reader.ReadInt16(); // font
var lang = reader.ReadAscii(4);
string text;
var isEncoded = (type & MessageType.Encoded) != 0;
int[] keywords;
if (isEncoded)
{
int value = reader.ReadInt16();
var count = (value & 0xFFF0) >> 4;
var hold = value & 0xF;
if (count is < 0 or > 50)
{
return;
}
var keyList = m_KeywordList;
for (var i = 0; i < count; ++i)
{
int speechID;
if ((i & 1) == 0)
{
hold <<= 8;
hold |= reader.ReadByte();
speechID = hold;
hold = 0;
}
else
{
value = reader.ReadInt16();
speechID = (value & 0xFFF0) >> 4;
hold = value & 0xF;
}
if (!keyList.Contains(speechID))
{
keyList.Add(speechID);
}
}
text = reader.ReadUTF8Safe();
keywords = keyList.ToArray();
}
else
{
text = reader.ReadBigUniSafe();
keywords = Array.Empty<int>();
}
text = text.Trim();
if (text.Length is <= 0 or > 128)
{
return;
}
type &= ~MessageType.Encoded;
if (!Enum.IsDefined(typeof(MessageType), type))
{
type = MessageType.Regular;
}
from.Language = lang;
from.DoSpeech(text, keywords, type, Utility.ClipDyedHue(hue));
}
}