/*
* (non-Javadoc)
*
* @see Lucene.Net.Analysis.TokenStream#next()
*/
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
int posIncr = 1;
while (true)
{
int tokenType = scanner.GetNextToken();
if (tokenType == StandardTokenizerImpl.YYEOF)
{
return(null);
}
if (scanner.Yylength() <= maxTokenLength)
{
reusableToken.Clear();
reusableToken.SetPositionIncrement(posIncr);
scanner.GetText(reusableToken);
int start = scanner.Yychar();
reusableToken.SetStartOffset(start);
reusableToken.SetEndOffset(start + reusableToken.TermLength());
// This 'if' should be removed in the next release. For now, it converts
// invalid acronyms to HOST. When removed, only the 'else' part should
// remain.
if (tokenType == StandardTokenizerImpl.ACRONYM_DEP)
{
if (replaceInvalidAcronym)
{
reusableToken.SetType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.HOST]);
reusableToken.SetTermLength(reusableToken.TermLength() - 1); // remove extra '.'
}
else
{
reusableToken.SetType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM]);
}
}
else
{
reusableToken.SetType(StandardTokenizerImpl.TOKEN_TYPES[tokenType]);
}
return(reusableToken);
}
// When we skip a too-long term, we still increment the
// position increment
else
{
posIncr++;
}
}
}
///<summary>
/// (non-Javadoc)
/// <see cref="Lucene.Net.Analysis.TokenStream.IncrementToken()" />
///</summary>
public override bool IncrementToken()
{
ClearAttributes();
int posIncr = 1;
while (true)
{
int tokenType = scanner.GetNextToken();
if (tokenType == StandardTokenizerImpl.YYEOF)
{
return(false);
}
if (scanner.Yylength() <= maxTokenLength)
{
posIncrAtt.PositionIncrement = posIncr;
scanner.GetText(termAtt);
int start = scanner.Yychar();
offsetAtt.SetOffset(CorrectOffset(start), CorrectOffset(start + termAtt.TermLength()));
// This 'if' should be removed in the next release. For now, it converts
// invalid acronyms to HOST. When removed, only the 'else' part should
// remain.
if (tokenType == StandardTokenizerImpl.ACRONYM_DEP)
{
if (replaceInvalidAcronym)
{
typeAtt.Type = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.HOST];
termAtt.SetTermLength(termAtt.TermLength() - 1); // remove extra '.'
}
else
{
typeAtt.Type = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM];
}
}
else
{
typeAtt.Type = StandardTokenizerImpl.TOKEN_TYPES[tokenType];
}
return(true);
}
// When we skip a too-long term, we still increment the
// position increment
else
{
posIncr++;
}
}
}
public static Token Next(StandardTokenizerImpl scanner)
{
int tokenType = scanner.GetNextToken();
if (tokenType == StandardTokenizerImpl.YYEOF) {
return null;
}
int startPosition = scanner.yychar();
string tokenImage = scanner.yytext();
return new Token(tokenImage, startPosition, startPosition
+ tokenImage.Length,
StandardTokenizerImpl.TOKEN_TYPES[tokenType]);
}
/// <summary>Returns the next token in the stream, or null at EOS.
/// <p>The returned token's type is set to an element of {@link
/// StandardTokenizerConstants#tokenImage}.
/// </summary>
public override Lucene.Net.Analysis.Token Next()
{
int tokenType = scanner.GetNextToken();
if (tokenType == StandardTokenizerImpl.YYEOF)
{
return(null);
}
int startPosition = scanner.yychar();
string tokenImage = scanner.yytext();
return(new Token(tokenImage, startPosition, startPosition
+ tokenImage.Length,
StandardTokenizerImpl.TOKEN_TYPES[tokenType]));
}
