/// <summary>
/// Reads the file and returns its contents (autodetects encoding and fallback codepage)
/// </summary>
public static String ReadFile(String file)
{
EncodingFileInfo info = GetEncodingFileInfo(file);
return(info.Contents);
}
/// <summary>
/// Checks if the file contains BOM
/// </summary>
public static Boolean ContainsBOM(String file)
{
EncodingFileInfo info = GetEncodingFileInfo(file);
return(info.ContainsBOM);
}
/// <summary>
/// Acquires encoding related info on one read.
/// </summary>
public static EncodingFileInfo GetEncodingFileInfo(String file)
{
Int32 startIndex = 0;
EncodingFileInfo info = new EncodingFileInfo();
try
{
if (File.Exists(file))
{
Byte[] bytes = File.ReadAllBytes(file);
if (bytes.Length > 2 && (bytes[0] == 0xef && bytes[1] == 0xbb && bytes[2] == 0xbf))
{
startIndex = 3;
info.BomLength = 3;
info.ContainsBOM = true;
info.Charset = Encoding.UTF8.WebName;
info.CodePage = Encoding.UTF8.CodePage;
}
else if (bytes.Length > 3 && (bytes[0] == 0xff && bytes[1] == 0xfe && bytes[2] == 0x00 && bytes[3] == 0x00))
{
startIndex = 4;
info.BomLength = 4;
info.ContainsBOM = true;
info.Charset = Encoding.UTF32.WebName;
info.CodePage = Encoding.UTF32.CodePage;
}
else if (bytes.Length > 4 && ((bytes[0] == 0x2b && bytes[1] == 0x2f && bytes[2] == 0x76) && (bytes[3] == 0x38 || bytes[3] == 0x39 || bytes[3] == 0x2b || bytes[3] == 0x2f) && bytes[4] == 0x2D))
{
startIndex = 5;
info.BomLength = 5;
info.ContainsBOM = true;
info.Charset = Encoding.UTF7.WebName;
info.CodePage = Encoding.UTF7.CodePage;
}
else if (bytes.Length > 3 && ((bytes[0] == 0x2b && bytes[1] == 0x2f && bytes[2] == 0x76) && (bytes[3] == 0x38 || bytes[3] == 0x39 || bytes[3] == 0x2b || bytes[3] == 0x2f)))
{
startIndex = 4;
info.BomLength = 4;
info.ContainsBOM = true;
info.Charset = Encoding.UTF7.WebName;
info.CodePage = Encoding.UTF7.CodePage;
}
else if (bytes.Length > 1 && (bytes[0] == 0xff && bytes[1] == 0xfe))
{
startIndex = 2;
info.BomLength = 2;
info.ContainsBOM = true;
info.Charset = Encoding.Unicode.WebName;
info.CodePage = Encoding.Unicode.CodePage;
}
else if (bytes.Length > 1 && (bytes[0] == 0xfe && bytes[1] == 0xff))
{
startIndex = 2;
info.BomLength = 2;
info.ContainsBOM = true;
info.Charset = Encoding.BigEndianUnicode.WebName;
info.CodePage = Encoding.BigEndianUnicode.CodePage;
}
else
{
if (!ContainsInvalidUTF8Bytes(bytes))
{
info.Charset = Encoding.UTF8.WebName;
info.CodePage = Encoding.UTF8.CodePage;
}
else // Try detecting using Ude...
{
/*
* Ude.CharsetDetector detector = new Ude.CharsetDetector();
* detector.Feed(bytes, 0, bytes.Length); detector.DataEnd();
*
* if (detector.Charset != null)
* {
* Encoding encoding = Encoding.GetEncoding(detector.Charset);
* info.Charset = encoding.WebName;
* info.CodePage = encoding.CodePage;
* }
* else
* {
* info.Charset = Encoding.Default.WebName;
* info.CodePage = Encoding.Default.CodePage;
* }
*/
}
}
Int32 contentLength = bytes.Length - startIndex;
if (bytes.Length > 0 && bytes.Length > startIndex)
{
Encoding encoding = Encoding.GetEncoding(info.CodePage);
info.Contents = encoding.GetString(bytes, startIndex, contentLength);
}
}
}
catch (Exception)
{
info = new EncodingFileInfo();
}
return(info);
}
/// <summary>
/// Reads the file codepage from the file data
/// </summary>
public static Int32 GetFileCodepage(String file)
{
EncodingFileInfo info = GetEncodingFileInfo(file);
return(info.CodePage);
}
