public override bool IncrementToken()
{
if (!input.IncrementToken())
{
return(false);
}
bool bufferUpdated = true;
char[] buffer = termAtt.TermBuffer();
int bufferLength = termAtt.TermLength();
String type = typeAtt.Type;
if (type == APOSTROPHE_TYPE && bufferLength >= 2 && buffer[bufferLength - 2] == '\'' && (buffer[bufferLength - 1] == 's' || buffer[bufferLength - 1] == 'S'))
{
for (int i = 0; i < bufferLength - 2; i++)
{
buffer[i] = ToLower(buffer[i]);
}
// Strip last 2 characters off
termAtt.SetTermLength(bufferLength - 2);
}
else if (type == ACRONYM_TYPE)
{
// remove dots
int upto = 0;
for (int i = 0; i < bufferLength; i++)
{
char c = buffer[i];
if (c != '.')
{
buffer[upto++] = ToLower(c);
}
}
termAtt.SetTermLength(upto);
}
else
{
do
{
//If we consumed a stop word we need to update the buffer and its length.
if (!bufferUpdated)
{
bufferLength = termAtt.TermLength();
buffer = termAtt.TermBuffer();
}
for (int i = 0; i < bufferLength; i++)
{
buffer[i] = ToLower(buffer[i]);
}
if (!stopWords.Contains(buffer, 0, bufferLength))
{
return(true);
}
bufferUpdated = false;
} while (input.IncrementToken());
return(false);
}
return(true);
}
/// <summary>
/// Basically is called on each token
/// </summary>
/// <returns></returns>
public override bool IncrementToken()
{
if (input.IncrementToken())
{
string term = new String(termAtt.TermBuffer(), 0, termAtt.TermLength());
string replaceterm = BestBetsWordForms.ResourceManager.GetString(term);
if (!String.IsNullOrEmpty(replaceterm))
{
//Replace Term was a match, so we need to replace this item.
termAtt.SetTermBuffer(replaceterm);
}
char[] buffer = termAtt.TermBuffer();
/*
* int length = termAtt.TermLength();
* for (int i = 0; i < length; i++)
* buffer[i] = System.Char.ToLower(buffer[i]);
*/
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (state != null)
{
RestoreState(state);
payloadAtt.Payload = null;
posIncrAtt.PositionIncrement = 0;
termAtt.SetTermBuffer(new char[]{'b'}, 0, 1);
state = null;
return true;
}
bool hasNext = input.IncrementToken();
if (!hasNext)
return false;
if (System.Char.IsDigit(termAtt.TermBuffer()[0]))
{
posIncrAtt.PositionIncrement = termAtt.TermBuffer()[0] - '0';
}
if (first)
{
// set payload on first position only
payloadAtt.Payload = new Payload(new byte[]{100});
first = false;
}
// index a "synonym" for every token
state = CaptureState();
return true;
}
public override Boolean IncrementToken()
{
if (_buffer.Any())
{
var nextStem = _buffer.Dequeue();
RestoreState(_savedState);
_posIncAtt.PositionIncrement = 0;
_termAtt.SetTermBuffer(nextStem.Stem, 0, nextStem.StemLength);
return(true);
}
if (!input.IncrementToken())
{
return(false);
}
var newTerms = _dedup
? _stemmer.UniqueStems(_termAtt.Term)
: _stemmer.Stem(_termAtt.Term);
foreach (var newTerm in newTerms)
{
_buffer.Enqueue(newTerm);
}
if (_buffer.Count == 0)
{
// originaly: we do not know this word, return it unchanged
// changed: apply SlovakStemmer on words not found in dictionary (possible named entities)
var currentTerm = new string(_termAtt.TermBuffer(), 0, _termAtt.TermLength());
if (!string.IsNullOrEmpty(currentTerm))
{
_slovakStemmer.Stem(_termAtt.TermBuffer(), _termAtt.TermLength(), out char[] newTerm, out var newLength);
_termAtt.SetTermBuffer(newTerm, 0, newLength);
_termAtt.SetTermLength(newLength);
}
return(true);
}
var stem = _buffer.Dequeue();
_termAtt.SetTermBuffer(stem.Stem, 0, stem.StemLength);
if (_buffer.Count > 0)
{
_savedState = CaptureState();
}
return(true);
}
public override bool IncrementToken()
{
int positionIncrement = 0;
if (_buffer == null || _offset >= _length)
{
if (!_input.IncrementToken())
{
return(false);
}
_offset = 0;
_buffer = _termAttribute.TermBuffer();
_length = _termAttribute.TermLength();
positionIncrement++;
_offsetInStream++;
}
_offsetAttribute.SetOffset(_offsetInStream, _offsetInStream + 1);
_offsetInStream++;
positionIncrement++;
_positionIncrementAttribute.PositionIncrement = positionIncrement;
_termAttribute.SetTermLength(1);
_termAttribute.SetTermBuffer(_buffer[_offset++].ToString());
return(true);
}
/* Returns the next token in the stream, or null at EOS. */
public override bool IncrementToken()
{
while (true)
{
if (curTermBuffer == null)
{
if (!input.IncrementToken())
{
return(false);
}
else
{
curTermBuffer = (char[])termAtt.TermBuffer().Clone();
curTermLength = termAtt.TermLength();
curGramSize = minGram;
curPos = 0;
tokStart = offsetAtt.StartOffset;
}
}
while (curGramSize <= maxGram)
{
while (curPos + curGramSize <= curTermLength)
{ // while there is input
ClearAttributes();
termAtt.SetTermBuffer(curTermBuffer, curPos, curGramSize);
offsetAtt.SetOffset(tokStart + curPos, tokStart + curPos + curGramSize);
curPos++;
return(true);
}
curGramSize++; // increase n-gram size
curPos = 0;
}
curTermBuffer = null;
}
}
public override bool IncrementToken()
{
while (input.IncrementToken())
{
char[] text = termAtt.TermBuffer();
int termLength = termAtt.TermLength();
// why not key off token type here assuming ChineseTokenizer comes first?
if (!stopTable.Contains(text, 0, termLength))
{
switch (char.GetUnicodeCategory(text[0]))
{
case UnicodeCategory.LowercaseLetter:
case UnicodeCategory.UppercaseLetter:
// English word/token should larger than 1 char.
if (termLength > 1)
{
return(true);
}
break;
case UnicodeCategory.OtherLetter:
// One Chinese char as one Chinese word.
// Chinese word extraction to be added later here.
return(true);
}
}
}
return(false);
}
/// <summary>Returns the next token in the stream, or null at EOS.
/// <p/>Removes <tt>'s</tt> from the end of words.
/// <p/>Removes dots from acronyms.
/// </summary>
public override bool IncrementToken()
{
if (!input.IncrementToken())
{
return(false);
}
char[] buffer = termAtt.TermBuffer();
int bufferLength = termAtt.TermLength();
System.String type = typeAtt.Type;
if ((System.Object)type == (System.Object)APOSTROPHE_TYPE && bufferLength >= 2 && buffer[bufferLength - 2] == '\'' && (buffer[bufferLength - 1] == 's' || buffer[bufferLength - 1] == 'S'))
{
// Strip last 2 characters off
termAtt.SetTermLength(bufferLength - 2);
}
else if ((System.Object)type == (System.Object)ACRONYM_TYPE)
{
// remove dots
int upto = 0;
for (int i = 0; i < bufferLength; i++)
{
char c = buffer[i];
if (c != '.')
{
buffer[upto++] = c;
}
}
termAtt.SetTermLength(upto);
}
return(true);
}
public override bool IncrementToken()
{
bool result = false;
if (input.IncrementToken())
{
char[] buffer = termAtt.TermBuffer();
int length = termAtt.TermLength();
//look for the delimiter
bool seen = false;
for (int i = 0; i < length; i++)
{
if (buffer[i] == delimiter)
{
termAtt.SetTermBuffer(buffer, 0, i);
payAtt.Payload = encoder.Encode(buffer, i + 1, (length - (i + 1)));
seen = true;
break;//at this point, we know the whole piece, so we can exit. If we don't see the delimiter, then the termAtt is the same
}
}
if (seen == false)
{
//no delimiter
payAtt.Payload = null;
}
result = true;
}
return(result);
}
public override bool IncrementToken()
{
ClearAttributes();
int length = 0;
int start = bufferIndex;
char[] buffer = termAtt.TermBuffer();
while (true)
{
if (bufferIndex >= dataLen)
{
offset += dataLen;
dataLen = input.Read(ioBuffer, 0, ioBuffer.Length);
if (dataLen <= 0)
{
dataLen = 0; // so next offset += dataLen won't decrement offset
if (length > 0)
{
break;
}
return(false);
}
bufferIndex = 0;
}
char c = ioBuffer[bufferIndex++];
if (IsTokenChar(c))
{
// if it's a token char
if (length == 0)
{
// start of token
start = offset + bufferIndex - 1;
}
else if (length == buffer.Length)
{
buffer = termAtt.ResizeTermBuffer(1 + length);
}
buffer[length++] = Normalize(c); // buffer it, normalized
if (length == MAX_WORD_LEN)
{
// buffer overflow!
break;
}
}
else if (length > 0)
{
// at non-Letter w/ chars
break; // return 'em
}
}
termAtt.SetTermLength(length);
offsetAtt.SetOffset(CorrectOffset(start), CorrectOffset(start + length));
return(true);
}
public sealed override bool IncrementToken()
{
if (tokens.Count > 0)
{
setToken((Token)tokens.First.Value);
tokens.RemoveFirst();
return(true);
}
if (input.IncrementToken() == false)
{
return(false);
}
wrapper.SetTermBuffer(termAtt.TermBuffer(), 0, termAtt.TermLength());
wrapper.StartOffset = offsetAtt.StartOffset;
wrapper.EndOffset = offsetAtt.EndOffset;
wrapper.Flags = flagsAtt.Flags;
wrapper.Type = typeAtt.Type;
wrapper.PositionIncrement = posIncAtt.PositionIncrement;
wrapper.Payload = payloadAtt.Payload;
Decompose(wrapper);
if (tokens.Count > 0)
{
setToken(tokens.First.Value);
tokens.RemoveFirst();
return(true);
}
else
{
return(false);
}
}
public override bool IncrementToken()
{
if (splittedQueue.Count > 0)
{
string splitted = splittedQueue.Dequeue();
RestoreState(currentState);
_termAttr.SetTermBuffer(splitted);
_posAttr.PositionIncrement = 0;
return(true);
}
if (!input.IncrementToken())
{
return(false);
}
var currentTerm = new string(_termAttr.TermBuffer(), 0, _termAttr.TermLength());
IEnumerable <string> synonyms = SynonymEngine.GetSynonyms(currentTerm);
if (synonyms == null)
{
return(false);
}
foreach (string syn in synonyms)
{
if (!currentTerm.Equals(syn))
{
splittedQueue.Enqueue(syn);
}
}
return(true);
}
public override bool IncrementToken()
{
if (!done)
{
ClearAttributes();
done = true;
int upto = 0;
char[] buffer = termAtt.TermBuffer();
while (true)
{
int length = input.Read(buffer, upto, buffer.Length - upto);
if (length == 0)
{
break;
}
upto += length;
if (upto == buffer.Length)
{
buffer = termAtt.ResizeTermBuffer(1 + buffer.Length);
}
}
termAtt.SetTermLength(upto);
finalOffset = CorrectOffset(upto);
offsetAtt.SetOffset(CorrectOffset(0), finalOffset);
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (!input.IncrementToken())
{
// reached EOS -- return null
return(false);
}
if (suffixByTokenType == null)
{
return(true);
}
char[] suffix;
if (!suffixByTokenType.TryGetValue(typeAtt.Type, out suffix))
{
return(true);
}
char[] buffer = termAtt.TermBuffer();
int length = termAtt.TermLength();
if (buffer.Length <= length)
{
buffer = termAtt.ResizeTermBuffer(length + suffix.Length);
}
Array.Copy(suffix, 0, buffer, length, suffix.Length);
termAtt.SetTermLength(length + suffix.Length);
return(true);
}
public override bool IncrementToken()
{
//Finchè ci sono termini nella coda ritorniamo e svuotiamo un temrine alla volta
if (splittedQueue.Count > 0)
{
var splitted = splittedQueue.Dequeue();
RestoreState(currentState);
termAtt.SetTermBuffer(splitted);
posAtt.PositionIncrement = 0;
return(true);
}
//Se siamo alla fine ci fermiamo subito
if (!input.IncrementToken())
{
return(false);
}
var currentTerm = new string(termAtt.TermBuffer(), 0, termAtt.TermLength());
if (!string.IsNullOrEmpty(currentTerm))
{
var splittedWords = GetSplittedWord(currentTerm);
//Non ci sono parole, non elaboriamo e proseguiamo
if (splittedWords == null || splittedWords.Length == 0)
{
return(true);
}
foreach (var splittedWord in splittedWords)
{
splittedQueue.Enqueue(splittedWord);
}
}
currentState = CaptureState();
return(true);
}
public override bool IncrementToken()
{
ClearAttributes();
int length = 0;
int start = _bufferIndex;
char[] buffer = _termAtt.TermBuffer();
while (true)
{
if (_bufferIndex >= _dataLen)
{
_offset += _dataLen;
_dataLen = input.Read(_ioBuffer, 0, _ioBuffer.Length);
if (_dataLen <= 0)
{
_dataLen = 0; // so next offset += dataLen won't decrement offset
if (length > 0)
{
break;
}
return(false);
}
_bufferIndex = 0;
}
char c = _ioBuffer[_bufferIndex++];
if (Helper.IsTokenChar(c))
{
// if it's a token char
if (length == 0)
{
// start of token
start = _offset + _bufferIndex - 1;
}
else if (length == buffer.Length)
{
buffer = _termAtt.ResizeTermBuffer(1 + length);
}
buffer[length++] = Helper.Normalize(c); // buffer it, normalized
}
else if (length > 0)
{
// at non-Letter w/ chars
break; // return 'em
}
}
_termAtt.SetTermLength(length);
_offsetAtt.SetOffset(CorrectOffset(start), CorrectOffset(start + length));
return(true);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
var currentTerm = new string(termAtt.TermBuffer(), 0, termAtt.TermLength());
if (!string.IsNullOrEmpty(currentTerm))
{
stemmer.Stem(termAtt.TermBuffer(), termAtt.TermLength(), out char[] newTerm, out var newLength);
termAtt.SetTermBuffer(newTerm, 0, newLength);
termAtt.SetTermLength(newLength);
}
return(true);
}
else
{
return(false);
}
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
int newlen = normalizer.Normalize(termAtt.TermBuffer(), termAtt.TermLength());
termAtt.SetTermLength(newlen);
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
var newLength = _stemmer.Stem(_termAttr.TermBuffer(), _termAttr.TermLength());
_termAttr.SetTermLength(newLength);
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
int len = termAtt.TermLength();
if (marker != NOMARKER)
{
len++;
termAtt.ResizeTermBuffer(len);
termAtt.TermBuffer()[len - 1] = marker;
}
Reverse(termAtt.TermBuffer(), len);
termAtt.SetTermLength(len);
return(true);
}
else
{
return(false);
}
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
if (stemmer.Stem(termAtt.TermBuffer(), termAtt.TermLength()))
{
termAtt.SetTermBuffer(stemmer.ToString());
}
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
typeAtt.Type = char.ToUpper(termAtt.TermBuffer()[0]).ToString();
return(true);
}
else
{
return(false);
}
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
int newlen = stemmer.Stem(termAtt.TermBuffer(), termAtt.TermLength());
termAtt.SetTermLength(newlen);
return(true);
}
else
{
return(false);
}
}
public override bool IncrementToken()
{
if (!input.IncrementToken())
{
return(false);
}
if (stemmer.Stem(termAtt.TermBuffer(), 0, termAtt.TermLength()))
{
termAtt.SetTermBuffer(stemmer.ResultBuffer, 0, stemmer.ResultLength);
}
return(true);
}
private Token GetNextPrefixInputToken(Token token)
{
if (!Prefix.IncrementToken())
{
return(null);
}
token.SetTermBuffer(_pTermAtt.TermBuffer(), 0, _pTermAtt.TermLength());
token.PositionIncrement = _pPosIncrAtt.PositionIncrement;
token.Flags = _pFlagsAtt.Flags;
token.SetOffset(_pOffsetAtt.StartOffset, _pOffsetAtt.EndOffset);
token.Type = _pTypeAtt.Type;
token.Payload = _pPayloadAtt.Payload;
return(token);
}
private Token GetNextToken(Token token)
{
if (!this.IncrementToken())
{
return(null);
}
token.SetTermBuffer(_termAtt.TermBuffer(), 0, _termAtt.TermLength());
token.PositionIncrement = _posIncrAtt.PositionIncrement;
token.Flags = _flagsAtt.Flags;
token.SetOffset(_offsetAtt.StartOffset, _offsetAtt.EndOffset);
token.Type = _typeAtt.Type;
token.Payload = _payloadAtt.Payload;
return(token);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
char[] buffer = termAtt.TermBuffer();
int bufferLength = termAtt.TermLength();
if (bufferLength >= 2 && (buffer[bufferLength - 2] == '\'' || ((buffer[bufferLength - 2] == '\u2019' || buffer[bufferLength - 2] == '\uFF07'))) && (buffer[bufferLength - 1] == 's' || buffer[bufferLength - 1] == 'S'))
{
termAtt.SetTermLength(bufferLength - 2); // Strip last 2 characters off
}
return(true);
}
return(false);
}
public override bool IncrementToken()
{
if (input.IncrementToken())
{
char[] buffer = termAtt.TermBuffer();
int length = termAtt.TermLength();
for (int i = 0; i < length; i++)
{
buffer[i] = System.Char.ToLower(buffer[i]);
}
return(true);
}
return(false);
}
/*
* Increments the {@link TokenStream} with a {@link TermAttribute} without elisioned start
*/
public override sealed bool IncrementToken()
{
if (input.IncrementToken())
{
char[] termBuffer = termAtt.TermBuffer();
int termLength = termAtt.TermLength();
int minPoz = int.MaxValue;
for (int i = 0; i < apostrophes.Length; i++)
{
char apos = apostrophes[i];
// The equivalent of String.indexOf(ch)
for (int poz = 0; poz < termLength; poz++)
{
if (termBuffer[poz] == apos)
{
minPoz = Math.Min(poz, minPoz);
break;
}
}
}
// An apostrophe has been found. If the prefix is an article strip it off.
if (minPoz != int.MaxValue &&
articles.Contains(termAtt.TermBuffer(), 0, minPoz))
{
termAtt.SetTermBuffer(termAtt.TermBuffer(), minPoz + 1, termAtt.TermLength() - (minPoz + 1));
}
return(true);
}
else
{
return(false);
}
}
private Token GetNextInputToken(Token token)
{
if (!_input.IncrementToken())
{
return(null);
}
token.SetTermBuffer(_inTermAtt.TermBuffer(), 0, _inTermAtt.TermLength());
token.PositionIncrement = _inPosIncrAtt.PositionIncrement;
token.Flags = _inFlagsAtt.Flags;
token.SetOffset(_inOffsetAtt.StartOffset, _inOffsetAtt.EndOffset);
token.Type = _inTypeAtt.Type;
token.Payload = _inPayloadAtt.Payload;
return(token);
}