public LanguageDetectModule(LanguageDetector languageDetector)
: base("/language-detector")
{
Get["/"] = _ =>
{
return(View[LanguageDetectionViewName, new DetectedLanguageResponse()]);
};
Post["/"] = _ =>
{
var model = this.Bind <LanguageDetectRequest>();
if (ModelIsInvalid(model))
{
return(BadRequest());
}
DetectedLanguageResponse detectedLanguageResponse = languageDetector.DetectLanguage(model);
//return Response.AsXml(detectedLanguageResponse);
return(Negotiate
.WithContentType("text/html; charset=utf-8")
.WithModel(detectedLanguageResponse)
.WithView(LanguageDetectionViewName));
};
}
private string DetectLanguage(byte[] bytes)
{
try
{
return(LanguageDetector.DetectLanguage(Encoding.UTF8.GetString(bytes)));
}
catch (NLangDetectException ex)
{
}
try
{
return(LanguageDetector.DetectLanguage(Encoding.ASCII.GetString(bytes)));
}
catch (NLangDetectException ex)
{
}
try
{
return(LanguageDetector.DetectLanguage(Encoding.Unicode.GetString(bytes)));
}
catch (NLangDetectException ex)
{
}
return(null);
}
private string DetectLanguage(byte[] bytes, int index, int count)
{
try
{
return(LanguageDetector.DetectLanguage(Encoding.UTF8.GetString(bytes, index, count)));
}
catch (NLangDetectException ex)
{
_logger.LogDebug(ex, "LanguageDetector.DetectLanguage threw a NLangDetectException.");
}
try
{
return(LanguageDetector.DetectLanguage(Encoding.ASCII.GetString(bytes, index, count)));
}
catch (NLangDetectException ex)
{
_logger.LogDebug(ex, "LanguageDetector.DetectLanguage threw a NLangDetectException.");
}
try
{
return(LanguageDetector.DetectLanguage(Encoding.Unicode.GetString(bytes, index, count)));
}
catch (NLangDetectException ex)
{
_logger.LogDebug(ex, "LanguageDetector.DetectLanguage threw a NLangDetectException.");
}
return(null);
}
public void TestDetectLanguage(string text, string language)
{
var detector = new LanguageDetector(generateConfig());
var result = detector.DetectLanguage(new Lyric {
Text = text
});
Assert.AreEqual(result, new CultureInfo(language));
}
public void AutoDetectLyricLanguage()
{
var lyrics = beatmap.HitObjects.OfType <Lyric>().ToList();
if (!lyrics.Any())
{
return;
}
// todo : should get the config from setting.
var config = new LanguageDetectorConfig();
var detector = new LanguageDetector(config);
changeHandler?.BeginChange();
foreach (var lyric in lyrics)
{
var detectedLanguage = detector.DetectLanguage(lyric);
lyric.Language = detectedLanguage;
}
changeHandler?.EndChange();
}
public /*protected*/ override void ProcessDocument(Document document)
{
string contentType = document.Features.GetFeatureValue("contentType");
if (contentType != "Text")
{
return;
}
StringBuilder strBuilder = new StringBuilder();
try
{
TextBlock[] blocks = document.GetAnnotatedBlocks(mBlockSelector);
foreach (TextBlock block in blocks)
{
strBuilder.AppendLine(block.Text);
}
string text = strBuilder.ToString();
if (text.Length >= mMinTextLen)
{
LanguageProfile langProfile = mLanguageDetector.DetectLanguage(text);
if (langProfile != null)
{
document.Features.SetFeatureValue("detectedLanguage", langProfile.Language.ToString());
}
}
if (text.Length > 0)
{
document.Features.SetFeatureValue("detectedCharRange", TextMiningUtils.GetCharRange(text));
}
}
catch (Exception exception)
{
mLogger.Error("ProcessDocument", exception);
}
}
public virtual Language DetectLanguage(string text)
{
return(LanguageDetector.DetectLanguage(text));
}
