/// <summary>
/// Rerurns up to maxEncodings codpages that are assumed to be apropriate
/// </summary>
/// <param name="input">array containing the raw data</param>
/// <param name="maxEncodings">maxiumum number of encodings to detect</param>
/// <returns>an array of Encoding with assumed encodings</returns>
public static Encoding[] DetectInputCodepages(byte[] input, int maxEncodings)
{
StopWatch.Start("DetectInputCodepages_" + Thread.CurrentThread.ManagedThreadId);
if (maxEncodings < 1)
{
throw new ArgumentOutOfRangeException("at least one encoding must be returend", "maxEncodings");
}
if (input == null)
{
throw new ArgumentNullException("input");
}
// empty strings can always be encoded as ASCII
if (input.Length == 0)
{
return new Encoding[] { Encoding.ASCII }
}
;
// expand the string to be at least 256 bytes
if (input.Length < 256)
{
byte[] newInput = new byte[256];
int steps = 256 / input.Length;
for (int i = 0; i < steps; i++)
{
Array.Copy(input, 0, newInput, input.Length * i, input.Length);
}
int rest = 256 % input.Length;
if (rest > 0)
{
Array.Copy(input, 0, newInput, steps * input.Length, rest);
}
input = newInput;
}
List <Encoding> result = new List <Encoding>();
// get the IMultiLanguage" interface
IMultiLanguage2 multilang2 = new CMultiLanguageClass();
if (multilang2 == null)
{
throw new System.Runtime.InteropServices.COMException("Failed to get IMultilang2");
}
try
{
DetectEncodingInfo[] detectedEncdings = new DetectEncodingInfo[maxEncodings];
int scores = detectedEncdings.Length;
int srcLen = input.Length;
// setup options (none)
MLDETECTCP options = MLDETECTCP.MLDETECTCP_NONE;
StopWatch.Start("multilang2.DetectInputCodepage_" + Thread.CurrentThread.ManagedThreadId);
// finally... call to DetectInputCodepage
multilang2.DetectInputCodepage(options, 0,
ref input[0], ref srcLen, ref detectedEncdings[0], ref scores);
StopWatch.Stop("multilang2.DetectInputCodepage_" + Thread.CurrentThread.ManagedThreadId);
// get result
if (scores > 0)
{
for (int i = 0; i < scores; i++)
{
// add the result
result.Add(Encoding.GetEncoding((int)detectedEncdings[i].nCodePage));
}
}
}
finally
{
Marshal.FinalReleaseComObject(multilang2);
}
StopWatch.Stop("DetectInputCodepages_" + Thread.CurrentThread.ManagedThreadId);
// nothing found
return(result.ToArray());
}
public virtual extern void DetectInputCodepage([In] MLDETECTCP flags, [In] uint dwPrefWinCodePage,
[In] ref byte pSrcStr, [In, Out] ref int pcSrcSize,
[In, Out] ref DetectEncodingInfo lpEncoding,
[In, Out] ref int pnScores);
public virtual extern void IMultiLanguage3_DetectInputCodepage([In] uint dwFlag, [In] uint dwPrefWinCodePage, [In] ref sbyte pSrcStr, [In, Out] ref int pcSrcSize, [In, Out] ref DetectEncodingInfo lpEncoding, [In, Out] ref int pnScores);
public virtual extern void DetectCodepageInIStream([In] MLDETECTCP flags,
[In] uint dwPrefWinCodePage,
[In, MarshalAs(UnmanagedType.Interface)] IStream pstmIn,
[In, Out] ref DetectEncodingInfo lpEncoding,
[In, Out] ref int pnScores);
public virtual extern void IMultiLanguage3_DetectCodepageInIStream([In] uint dwFlag, [In] uint dwPrefWinCodePage, [In, MarshalAs(UnmanagedType.Interface)] IStream pstmIn, [In, Out] ref DetectEncodingInfo lpEncoding, [In, Out] ref int pnScores);
