Tjekke Text encoding

Dit problem er principielt uloeseligt. Der kan godt eksistere en byte sekvens som er valid i 2 forskellige encodings bare med forskellig tekst.

Hvis du ved at sproget er dansk kan du lave et kvalificeret gaet udfra filens indhold.

Eksempel i C#:

using System;
using System.IO;

public class CharSetGuesser
{
    public static string Guess(string filename)
    {
        int[] freq = new int[256];
        Stream stm = new FileStream(filename, FileMode.Open, FileAccess.Read);
        int c;
        while((c = stm.ReadByte()) >= 0)
        {
            freq[c]++;
        }
        stm.Close();
        if((freq[197] + freq[198] + freq[200] +
            freq[201] + freq[203] + freq[216] +
            freq[229] + freq[230] + freq[232] +
            freq[233] + freq[235] + freq[248]) >
          (freq[133] + freq[134] + freq[136] +
            freq[137] + freq[139] + freq[152] +
            freq[165] + freq[166] + freq[168] +
            freq[169] + freq[171] + freq[184] +
            freq[195]))
        {
            return "ISO-8859-1";
        }
        else
        {
            return "UTF-8";
        }
    }
    public static void Main(string[] args)
    {
        Console.WriteLine(Guess("C:\\iso-8859-1.txt"));
        Console.WriteLine(Guess("C:\\utf-8.txt"));
    }
}

Oversat til VB.NET:

Imports System
Imports System.IO

Public Class CharSetGuesser
    Public Shared Function Guess(filename As String) As String
        Dim freq As Integer() = New Integer(255) {}
        Dim stm As Stream = New FileStream(filename, FileMode.Open, FileAccess.Read)
        Dim c As Integer
        While (c = stm.ReadByte()) >= 0
            freq(c) += 1
        End While
        stm.Close()
        If (freq(197) + freq(198) + freq(200) + freq(201) + _
            freq(203) + freq(216) + freq(229) + freq(230) + _
            freq(232) + freq(233) + freq(235) + freq(248)) > _
            (freq(133) + freq(134) + freq(136) + freq(137) + _
            freq(139) + freq(152) + freq(165) + freq(166) + _
            freq(168) + freq(169) + freq(171) + freq(184) + freq(195)) Then
            Return "ISO-8859-1"
        Else
            Return "UTF-8"
        End If
    End Function
    Public Shared Sub Main(args As String())
        Console.WriteLine(Guess("C:\iso-8859-1.txt"))
        Console.WriteLine(Guess("C:\utf-8.txt"))
    End Sub
End Class

Tak skal du have. Smider du lige et svar?

Kommer her.

Saa mangler du bare at acceptere svaret.