/// <summary>
/// returns possible languages of text passed or empty sequence if too uncertain
/// </summary>
/// <param name="text">text language of which should be identified</param>
/// <param name="languageModelsDirectory"></param>
/// <param name="maximumSizeOfDistribution"></param>
/// <param name="settings">null for default settings</param>
/// <returns></returns>
public static IEnumerable <Tuple <LanguageInfo, double> > ClassifyText(
string text,
string languageModelsDirectory = LanguageModelsDirectoryDefault,
int maximumSizeOfDistribution = MaximumSizeOfDistributionDefault,
LanguageIdentifierSettings settings = null
)
{
var languageIdentifier = new LanguageIdentifier(languageModelsDirectory, maximumSizeOfDistribution);
return(languageIdentifier.ClassifyText(text, settings));
}
/// <summary>
/// returns possible languages of text contained in <paramref name="input"/> or empty sequence if too uncertain.
/// </summary>
/// <param name="input"></param>
/// <param name="encoding">encoding of text contained in stream or null if encoding is unknown beforehand.
/// <para> When encoding is not null, for performance and quality reasons
/// make sure that <paramref name="languageModelsDirectory"/> points to models
/// built from UTF8 encoded files (Wikipedia-Experimental-UTF8Only)</para></param>
/// <param name="languageModelsDirectory"></param>
/// <param name="maximumSizeOfDistribution"></param>
/// <param name="settings">null for default settings</param>
/// <returns></returns>
public static IEnumerable <Tuple <LanguageInfo, double> > ClassifyBytes(
Stream input,
Encoding encoding = null,
string languageModelsDirectory = LanguageModelsDirectoryDefault,
int maximumSizeOfDistribution = MaximumSizeOfDistributionDefault,
LanguageIdentifierSettings settings = null
)
{
var languageIdentifier = new LanguageIdentifier(languageModelsDirectory, maximumSizeOfDistribution);
return(languageIdentifier.ClassifyBytes(input, encoding, settings));
}
