public void Detect_encoding_for_XML_file_with_UTF8_JP()
{
const string resource = "xml-utf-8-jp.txt";
using(var stream = GetResourceStream(resource)) {
var detector = new CharacterEncodingDetector();
var encoding = detector.Detect(stream);
var offset = stream.Position;
Assert.IsNotNull(encoding, "encoding detection failed");
Assert.AreEqual(0, offset, "wrong stream position");
string text;
using(var reader = new StreamReader(stream, encoding)) {
text = reader.ReadToEnd();
}
Assert.AreEqual("Unicode (UTF-8)", encoding.EncodingName);
AssertEncoding(text, resource, Encoding.UTF8, offset);
_log.DebugFormat("Detected encoding: {0}", encoding.EncodingName);
}
}
public void Detect_encoding_for_XML_file_with_Shift_JIS()
{
const string resource = "xml-shift-jis.txt";
using(var stream = GetResourceStream(resource)) {
var detector = new CharacterEncodingDetector();
var encoding = detector.Detect(stream);
var offset = stream.Position;
Assert.IsNotNull(encoding, "encoding detection failed");
Assert.AreEqual(0, offset, "wrong stream position");
string text;
using(var reader = new StreamReader(stream, encoding)) {
text = reader.ReadToEnd();
}
Assert.AreEqual("Japanese (Shift-JIS)", encoding.EncodingName);
AssertEncoding(text, resource, Encoding.GetEncoding("shift_jis"), offset);
_log.DebugFormat("Detected encoding: {0}", encoding.EncodingName);
}
}
public void Detect_encoding_for_XML_file_with_LE_JP()
{
if(SysUtil.IsMono) {
Assert.Ignore();
return;
}
const string resource = "xml-little-endian-jp.txt";
using(var stream = GetResourceStream(resource)) {
var detector = new CharacterEncodingDetector();
var encoding = detector.Detect(stream);
var offset = stream.Position;
Assert.IsNotNull(encoding, "encoding detection failed");
Assert.AreEqual(0, offset, "wrong stream position");
string text;
using(var reader = new StreamReader(stream, encoding)) {
text = reader.ReadToEnd();
}
Assert.AreEqual("Unicode", encoding.EncodingName);
AssertEncoding(text, resource, Encoding.Unicode, offset);
_log.DebugFormat("Detected encoding: {0}", encoding.EncodingName);
}
}
public void Detect_encoding_for_XML_file_with_EUC_JP()
{
// BUGBUGBUG (steveb): for some reason, CharDet estimates EUC-JP to be the worst fit. :(
const string resource = "xml-euc-jp.txt";
using(var stream = GetResourceStream(resource)) {
var detector = new CharacterEncodingDetector();
var encoding = detector.Detect(stream);
var offset = stream.Position;
Assert.IsNotNull(encoding, "encoding detection failed");
Assert.AreEqual(0, offset, "wrong stream position");
string text;
using(var reader = new StreamReader(stream, encoding)) {
text = reader.ReadToEnd();
}
Assert.AreEqual("EUC-JP", encoding.EncodingName);
AssertEncoding(text, resource, Encoding.GetEncoding("EUC-JP"), offset);
_log.DebugFormat("Detected encoding: {0}", encoding.EncodingName);
}
}
public void Detect_encoding_for_XML_file_with_GB2312()
{
const string resource = "xml-gb2312.txt";
using(var stream = GetResourceStream(resource)) {
var detector = new CharacterEncodingDetector();
var encoding = detector.Detect(stream);
var offset = stream.Position;
Assert.IsNotNull(encoding, "encoding detection failed");
string text;
using(var reader = new StreamReader(stream, encoding)) {
text = reader.ReadToEnd();
}
Assert.AreEqual("Chinese Simplified (GB2312)", encoding.EncodingName);
AssertEncoding(text, resource, Encoding.GetEncoding("GB2312"), offset);
_log.DebugFormat("Detected encoding: {0}", encoding.EncodingName);
}
}
