Created
October 13, 2013 11:22
-
-
Save georgiosd/6961114 to your computer and use it in GitHub Desktop.
Porter stemming analyzer for RavenDB
This file contains 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
public class PorterAnalyzer : Analyzer | |
{ | |
/// <summary>An unmodifiable set containing some common English words that are usually not | |
/// useful for searching. | |
/// </summary> | |
public static readonly ISet<string> StopWordsSet = StopAnalyzer.ENGLISH_STOP_WORDS_SET; | |
/// <summary>Default maximum allowed token length </summary> | |
public const int DefaultMaxTokenLength = 255; | |
private readonly ISet<string> stopSet; | |
private readonly Version matchVersion; | |
/// <summary> Set maximum allowed token length. If a token is seen | |
/// that exceeds this length then it is discarded. This | |
/// setting only takes effect the next time tokenStream or | |
/// reusableTokenStream is called. | |
/// </summary> | |
public int MaxTokenLength { get; set; } | |
/// <summary>Builds an analyzer with the default stop words (<see cref="StopWordsSet" />). | |
/// </summary> | |
/// <param name="matchVersion">Lucene version to match see <see cref="Version">above</see></param> | |
public PorterAnalyzer(Version matchVersion) | |
: this(matchVersion, StopWordsSet) | |
{ } | |
/// <summary>Builds an analyzer with the given stop words.</summary> | |
/// <param name="matchVersion">Lucene version to match See <see cref="Version">above</see> /></param> | |
/// <param name="stopSet">stop words | |
/// </param> | |
public PorterAnalyzer(Version matchVersion, ISet<string> stopSet) | |
{ | |
this.stopSet = stopSet; | |
this.matchVersion = matchVersion; | |
MaxTokenLength = DefaultMaxTokenLength; | |
} | |
/// <summary>Builds an analyzer with the stop words from the given file.</summary> | |
/// <seealso cref="WordlistLoader.GetWordSet(System.IO.FileInfo)"> | |
/// </seealso> | |
/// <param name="matchVersion">Lucene version to match See <see cref="Version">above</see> /> | |
/// | |
/// </param> | |
/// <param name="stopwords">File to read stop words from | |
/// </param> | |
public PorterAnalyzer(Version matchVersion, System.IO.FileInfo stopwords) | |
: this(matchVersion, WordlistLoader.GetWordSet(stopwords)) | |
{ | |
} | |
/// <summary>Builds an analyzer with the stop words from the given reader.</summary> | |
/// <seealso cref="WordlistLoader.GetWordSet(System.IO.TextReader)"> | |
/// </seealso> | |
/// <param name="matchVersion">Lucene version to match See <see cref="Version">above</see> /> | |
/// | |
/// </param> | |
/// <param name="stopwords">Reader to read stop words from | |
/// </param> | |
public PorterAnalyzer(Version matchVersion, System.IO.TextReader stopwords) | |
: this(matchVersion, WordlistLoader.GetWordSet(stopwords)) | |
{ } | |
private SavedStreams CreateTokenStream(System.IO.TextReader reader) | |
{ | |
StandardTokenizer tokenStream = new StandardTokenizer(matchVersion, reader) | |
{ | |
MaxTokenLength = MaxTokenLength | |
}; | |
return new SavedStreams | |
{ | |
TokenStream = tokenStream, | |
FilteredTokenStream = new PorterStemFilter( | |
new StopFilter(true, | |
new ASCIIFoldingFilter( | |
new LowerCaseFilter( | |
new StandardFilter(tokenStream) | |
) | |
) | |
, stopSet)) | |
}; | |
} | |
/// <summary>Constructs a <see cref="StandardTokenizer" /> filtered by a <see cref="StandardFilter" /> | |
///, a <see cref="LowerCaseFilter" /> and a <see cref="StopFilter" />. | |
/// </summary> | |
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader) | |
{ | |
return CreateTokenStream(reader).FilteredTokenStream; | |
} | |
public override TokenStream ReusableTokenStream(System.String fieldName, System.IO.TextReader reader) | |
{ | |
SavedStreams streams = (SavedStreams)PreviousTokenStream; | |
if (streams == null) | |
PreviousTokenStream = streams = CreateTokenStream(reader); | |
else | |
streams.TokenStream.Reset(reader); | |
streams.TokenStream.MaxTokenLength = MaxTokenLength; | |
return streams.FilteredTokenStream; | |
} | |
private sealed class SavedStreams | |
{ | |
internal StandardTokenizer TokenStream; | |
internal TokenStream FilteredTokenStream; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment