Last active
May 3, 2017 15:18
-
-
Save tkMageztik/442de2f94662cd199b4c2700378b1e03 to your computer and use it in GitHub Desktop.
Determinar el encoding de un documento, lectura de bytes.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/// <summary> | |
/// Determina el encoding de un archivo de texto analizando su bytes order mark (BOM). | |
/// Usa el encoding por defecto del SO cuando la detección del endianes archivo de texto falla. | |
/// </summary> | |
/// <param name="filename">La ruta del archivo a analizar.</param> | |
/// <returns>El encoding detectado.</returns> | |
public static Encoding GetEncoding(string filename) | |
{ | |
// Leyendo el BOM | |
var bom = new byte[4]; | |
using (var file = new FileStream(filename, FileMode.Open, FileAccess.Read)) | |
{ | |
file.Read(bom, 0, 4); | |
} | |
// Analizando el BOM | |
if (bom[0] == 0x2b && bom[1] == 0x2f && bom[2] == 0x76) return Encoding.UTF7; | |
if (bom[0] == 0xef && bom[1] == 0xbb && bom[2] == 0xbf) return Encoding.UTF8; | |
if (bom[0] == 0xff && bom[1] == 0xfe) return Encoding.Unicode; //UTF-16LE | |
if (bom[0] == 0xfe && bom[1] == 0xff) return Encoding.BigEndianUnicode; //UTF-16BE | |
if (bom[0] == 0 && bom[1] == 0 && bom[2] == 0xfe && bom[3] == 0xff) return Encoding.UTF32; | |
return Encoding.Default; | |
} | |
//28591 iso-8859-1 ISO 8859-1 Latin 1; Western European (ISO) - FUNCIONA | |
//1252 windows-1252 ANSI Latin 1; Western European (Windows) - FUNCIONA |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment