Question

我在MSSQL数据库中有一堆类似西里尔文的文本，需要在C＃中将其转换为Cyrillic。

所以...Ðàáîòàâãðìàíèè

应该成为

Работавгермании

有什么建议吗？

我应该补充说，我最接近的是？aaioa a aa？iaiee

这是我正在使用的代码：

 str = Encoding.UTF8.GetString(Encoding.GetEncoding("Windows-1251").GetBytes(drCurrent["myfield"].ToString()));
 str = Encoding.GetEncoding(1251).GetString(Encoding.Convert(Encoding.UTF8, Encoding.GetEncoding(1251), Encoding.UTF8.GetBytes(str)));

Answer 1

// To find out source and target
const string source = "Ðàáîòà â ãåðìàíèè";
const string destination = "Работа в германии";

foreach (var sourceEncoding in Encoding.GetEncodings())
{

    var bytes = sourceEncoding.GetEncoding().GetBytes(source);
    foreach (var targetEncoding in Encoding.GetEncodings())
    {
        if (targetEncoding.GetEncoding().GetString(bytes) == destination)
        {
            Console.WriteLine("Source Encoding: {0} TargetEncoding: {1}",sourceEncoding.CodePage,targetEncoding.CodePage);
        }

    }
}

// Result1: Source Encoding: 1252 TargetEncoding: 1251
// Result2: Source Encoding: 28591 TargetEncoding: 1251
// Result3: Source Encoding: 28605 TargetEncoding: 1251

// The code for you to use 
var decodedCyrillic = Encoding.GetEncoding(1251).GetString(Encoding.GetEncoding(1252).GetBytes(source));
// Result: Работа в германии

Answer 2

ADO.Net将SQL Server提供程序中的所有字符串类型公开为C＃字符串，这意味着它们已经转换为Unicode。对于非unicode源列（显然如此），如char(n)或varchar(n)，ADO.Net SQL Server提供程序使用源collation信息来确定编码。因此，如果您的非unicode SQL Server数据在.Net中以错误的编码表示，则必须使用错误的排序规则将其呈现给提供程序。为您的数据选择适当的排序规则，SQL Server的ADO.Net提供程序将使用适当的编码对其进行翻译。例如，如Collation and Code Page Architecture中所述，西里尔字母校对将导致code page 1251，这很可能是您想要的。链接的文章包含解决问题所需的所有信息。

using System;
using System.Text;
using System.Data.SqlClient;
using System.Windows.Forms;

public class Hello1
{
   public static void Main()
   {
    try
    {
        using (SqlConnection conn = new SqlConnection("server=.;integrated security=true"))
        {
            conn.Open ();

            // The .cs file must be saved as Unicode, obviously...
            //
            string s = "Работа в германии"; 

            byte[] b = Encoding.GetEncoding(1251).GetBytes (s);

            // Create a test table
            //
            SqlCommand cmd = new SqlCommand (
                @"create table #t (
                    c1 varchar(100) collate Latin1_General_CI_AS, 
                    c2 varchar(100) collate Cyrillic_General_CI_AS)", 
                conn);
            cmd.ExecuteNonQuery ();

            // Insert the same value twice, the original Unicode string
            // encoded as CP1251
            //
            cmd = new SqlCommand (
                @"insert into #t (c1, c2) values (@b, @b)", conn);
            cmd.Parameters.AddWithValue("@b", b);
            cmd.ExecuteNonQuery ();

            // Read the value as Latin collation 
            //
            cmd = new SqlCommand (
                @"select c1 from #t", conn);
            string def = (string) cmd.ExecuteScalar ();

            // Read the same value as Cyrillic collation
            //
            cmd = new SqlCommand (
                @"select c2 from #t", conn);
            string cyr = (string) cmd.ExecuteScalar ();

            // Cannot use Console.Write since the console is not Unicode
            //
            MessageBox.Show(String.Format(
                @"Original: {0}  Default collation: {1} Cyrillic collation: {2}", 
                    s, def, cyr));
        }

    }
    catch(Exception e)
    {
        Console.WriteLine (e);
    }   
   }
}

结果是：

---------------------------

---------------------------
Original: Работа в германии  Default collation: Ðàáîòà â ãåðìàíèè Cyrillic collation: Работа в германии
---------------------------
OK   
---------------------------

C＃中的西里尔语编码

2 个答案: