将文本转换为拉丁编码并解码越南语的问题

Question

我正在尝试将越南语转换为拉丁语。需要将字节发送到 ESC/P 打印机（请参阅 C# ESC/POS Print Vietnamese 了解原因）。

但是我的问题很简单，看这段代码：

Encoding enc = Encoding.GetEncoding(1258); //vietnamese code page
string content = "Cơm chiên với các loại gia vị truyền";
string newStr = Encoding.GetEncoding("Latin1").GetString(enc.GetBytes(content));
string origStr = enc.GetString(Encoding.GetEncoding("Latin1").GetBytes(newStr)); //origStr is becomes "Cơm chiên v?i các lo?i gia v? truy?n"

为什么 origStr 变成了 Cơm chiên v?i các lo?i gia v? truy?n 而不是包含与 content 相同的内容？但是，它工作中文或泰文。您可以测试下面的代码...

简体中文

Encoding enc = Encoding.GetEncoding(936); //chinese simplified code page
string content = "印尼炒饭";
string newStr = Encoding.GetEncoding("Latin1").GetString(enc.GetBytes(content));
string origStr = enc.GetString(Encoding.GetEncoding("Latin1").GetBytes(newStr)); //origStr is correct "印尼炒饭"

泰国语

Encoding enc = Encoding.GetEncoding(874); //Thai code page
string content = "ข้าวผัดอินโดนีเซียกับเครื่องเทศแบบดั้ง";
string newStr = Encoding.GetEncoding("Latin1").GetString(enc.GetBytes(content));
string origStr = enc.GetString(Encoding.GetEncoding("Latin1").GetBytes(newStr)); //origStr is correct "ข้าวผัดอินโดนีเซียกับเครื่องเทศแบบดั้ง"

知道为什么吗？为什么越南语不行？如何让它工作以便我可以将它发送到打印机？

感谢您的帮助:)

PS。这是我用来发送给打印机的代码

[DllImport("Winspool.drv", EntryPoint = "ClosePrinter", SetLastError = true, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool ClosePrinter(IntPtr hPrinter);

[DllImport("Winspool.drv", EntryPoint = "EndDocPrinter", SetLastError = true, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool EndDocPrinter(IntPtr hPrinter);

[DllImport("Winspool.drv", EntryPoint = "EndPagePrinter", SetLastError = true, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool EndPagePrinter(IntPtr hPrinter);

[DllImport("Winspool.drv", EntryPoint = "OpenPrinterA", SetLastError = true, CharSet = CharSet.Ansi, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool OpenPrinter([MarshalAs(UnmanagedType.LPStr)] string szPrinter, out IntPtr hPrinter, IntPtr pd);

[DllImport("Winspool.drv", EntryPoint = "StartDocPrinterA", SetLastError = true, CharSet = CharSet.Ansi, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool StartDocPrinter(IntPtr hPrinter, Int32 level, [In, MarshalAs(UnmanagedType.LPStruct)] DOCINFOA di);

[DllImport("Winspool.drv", EntryPoint = "StartPagePrinter", SetLastError = true, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool StartPagePrinter(IntPtr hPrinter);

[DllImport("Winspool.drv", EntryPoint = "WritePrinter", SetLastError = true, ExactSpelling = true, CallingConvention = CallingConvention.StdCall)]
public static extern bool WritePrinter(IntPtr hPrinter, IntPtr pBytes, Int32 dwCount, out Int32 dwWritten);

public static bool SendBytesToPrinter(string printerName, IntPtr pBytes, int dwCount, string docName = null, string dataType = "RAW")
{
    DOCINFOA di = new DOCINFOA();
    di.pDocName = string.IsNullOrWhiteSpace(docName) ? string.Empty : docName;
    di.pDataType = string.IsNullOrWhiteSpace(dataType) ? "RAW" : dataType;

    IntPtr hPrinter = new IntPtr(0); int dwError = 0, dwWritten = 0; bool bSuccess = false;
    if (OpenPrinter(printerName.Normalize(), out hPrinter, IntPtr.Zero))
    {
        if (StartDocPrinter(hPrinter, 1, di))
        {
            if (StartPagePrinter(hPrinter))
            {
                bSuccess = WritePrinter(hPrinter, pBytes, dwCount, out dwWritten);
                EndPagePrinter(hPrinter);
            }
            EndDocPrinter(hPrinter);
        }
        ClosePrinter(hPrinter);
    }

    if (bSuccess == false)
        dwError = Marshal.GetLastWin32Error();
    return bSuccess;
}

public static bool SendBytesToPrinter(string printerName, byte[] bytes, string docName)
{
    int dwCount = bytes.Length;
    IntPtr ptrBytes = Marshal.AllocCoTaskMem(Marshal.SizeOf(typeof(byte)) * bytes.Length);
    try
    {
        Marshal.Copy(bytes, 0, ptrBytes, bytes.Length);
        SendBytesToPrinter(printerName, ptrBytes, dwCount, docName);
    }
    finally { Marshal.FreeCoTaskMem(ptrBytes); }
    return true;
}

public static bool SendStringToPrinter(string printerName, string str, string docName)
{
    int dwCount = str.Length;
    IntPtr ptrBytes = Marshal.StringToCoTaskMemAnsi(str);
    try { SendBytesToPrinter(printerName, ptrBytes, dwCount, docName); }
    finally { Marshal.FreeCoTaskMem(ptrBytes); }
    return true;
}

Answer 1

当您向编码器提供代码页中不存在的数据时，通常会发生这种情况。

所以如果你愿意，例如尝试转换字节值大于 255 的字符（codepage 1258 中不存在），在这种情况下，您将得到备用字符 ?。我的猜测是，在第一种情况下，输入字符串中的数据无效（可能是看起来相同但不正确的字符）。

我的下一步是检查字符及其对应的字节值。

将文本转换为拉丁编码并解码越南语的问题

Convert text to Latin encoding and decode back problem for Vietnamese

c#

encoding

character-encoding

codepages