// Tokenizes the fields of a document into Postings.
private void InvertDocument(Document doc)
{
foreach (Field field in doc.Fields())
{
System.String fieldName = field.Name();
int fieldNumber = fieldInfos.FieldNumber(fieldName);
int length = fieldLengths[fieldNumber]; // length of Field
int position = fieldPositions[fieldNumber]; // position in Field
if (field.IsIndexed())
{
if (!field.IsTokenized())
{
// un-tokenized Field
AddPosition(fieldName, field.StringValue(), position++);
length++;
}
else
{
System.IO.TextReader reader; // find or make Reader
if (field.ReaderValue() != null)
{
reader = field.ReaderValue();
}
else if (field.StringValue() != null)
{
reader = new System.IO.StringReader(field.StringValue());
}
else
{
throw new System.ArgumentException("Field must have either String or Reader value");
}
// Tokenize Field and add to postingTable
TokenStream stream = analyzer.TokenStream(fieldName, reader);
try
{
for (Token t = stream.Next(); t != null; t = stream.Next())
{
position += (t.GetPositionIncrement() - 1);
AddPosition(fieldName, t.TermText(), position++);
if (++length > maxFieldLength)
{
break;
}
}
}
finally
{
stream.Close();
}
}
fieldLengths[fieldNumber] = length; // save Field length
fieldPositions[fieldNumber] = position; // save Field position
fieldBoosts[fieldNumber] *= field.GetBoost();
}
}
}
public QueryTermVector(System.String queryString, Analyzer analyzer)
{
if (analyzer != null)
{
TokenStream stream = analyzer.TokenStream("", new System.IO.StringReader(queryString));
if (stream != null)
{
Token next = null;
System.Collections.ArrayList terms = new System.Collections.ArrayList();
try
{
while ((next = stream.Next()) != null)
{
terms.Add(next.TermText());
}
ProcessTerms((System.String[])terms.ToArray(typeof(System.String)));
}
catch (System.IO.IOException)
{
}
}
}
}
/// <summary> Builds a GermanStemFilter that uses an exclusiontable.</summary>
/// <deprecated> Use {@link #GermanStemFilter(Monodoc.Lucene.Net.Analysis.TokenStream, java.util.Set)} instead.
/// </deprecated>
public GermanStemFilter(TokenStream in_Renamed, System.Collections.Hashtable exclusiontable) : this(in_Renamed)
{
exclusionSet = new System.Collections.Hashtable(new System.Collections.Hashtable(exclusiontable));
}
public GermanStemFilter(TokenStream in_Renamed) : base(in_Renamed)
{
stemmer = new GermanStemmer();
}
/// <summary> Builds a GermanStemFilter that uses an exclusiontable.</summary>
/// <deprecated> Use {@link #GermanStemFilter(Monodoc.Lucene.Net.Analysis.TokenStream, java.util.Set)} instead.
/// </deprecated>
public GermanStemFilter(TokenStream in_Renamed, System.Collections.Hashtable exclusiontable):this(in_Renamed)
{
exclusionSet = new System.Collections.Hashtable(new System.Collections.Hashtable(exclusiontable));
}
public GermanStemFilter(TokenStream in_Renamed) : base(in_Renamed)
{
stemmer = new GermanStemmer();
}
public RussianStemFilter(TokenStream in_Renamed, char[] charset):base(in_Renamed)
{
stemmer = new RussianStemmer(charset);
}
public RussianLowerCaseFilter(TokenStream in_Renamed, char[] charset):base(in_Renamed)
{
this.charset = charset;
}
public RussianStemFilter(TokenStream in_Renamed, char[] charset) : base(in_Renamed)
{
stemmer = new RussianStemmer(charset);
}
public RussianLowerCaseFilter(TokenStream in_Renamed, char[] charset) : base(in_Renamed)
{
this.charset = charset;
}