/// <summary>
/// Final touch of a shingle token before it is passed on to the consumer from method {@link #next(org.apache.lucene.analysis.Token)}.
///
/// Calculates and sets type, flags, position increment, start/end offsets and weight.
/// </summary>
/// <param name="token">Shingle Token</param>
/// <param name="shingle">Tokens used to produce the shingle token.</param>
/// <param name="currentPermutationStartOffset">Start offset in parameter currentPermutationTokens</param>
/// <param name="currentPermutationRows">index to Matrix.Column.Row from the position of tokens in parameter currentPermutationTokens</param>
/// <param name="currentPermuationTokens">tokens of the current permutation of rows in the matrix. </param>
public void UpdateToken(Token token, List<Token> shingle, int currentPermutationStartOffset, List<Row> currentPermutationRows, List<Token> currentPermuationTokens)
{
token.SetType(typeof(ShingleMatrixFilter).Name);
token.SetFlags(0);
token.SetPositionIncrement(1);
token.SetStartOffset((shingle[0]).StartOffset());
token.SetEndOffset(shingle[shingle.Count - 1].EndOffset());
_settingsCodec.SetWeight(
token,
CalculateShingleWeight(token, shingle, currentPermutationStartOffset, currentPermutationRows, currentPermuationTokens)
);
}
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
reusableToken.Clear();
int length = 0;
int start = bufferIndex;
char[] buffer = reusableToken.TermBuffer();
while (true)
{
if (bufferIndex >= dataLen)
{
offset += dataLen;
dataLen = input is Lucene.Net.Index.ReusableStringReader ? ((Lucene.Net.Index.ReusableStringReader)input).Read(ioBuffer) : input.Read((System.Char[])ioBuffer, 0, ioBuffer.Length);
if (dataLen <= 0)
{
if (length > 0)
{
break;
}
else
{
return(null);
}
}
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 = reusableToken.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
}
}
reusableToken.SetTermLength(length);
reusableToken.SetStartOffset(start);
reusableToken.SetEndOffset(start + length);
return(reusableToken);
}
/// <summary>
/// The default implementation adds last prefix token end offset to the suffix token start and end offsets.
/// </summary>
/// <param name="suffixToken">a token from the suffix stream</param>
/// <param name="lastPrefixToken">the last token from the prefix stream</param>
/// <returns>consumer token</returns>
public virtual Token UpdateSuffixToken(Token suffixToken, Token lastPrefixToken)
{
suffixToken.SetStartOffset(lastPrefixToken.EndOffset() + suffixToken.StartOffset());
suffixToken.SetEndOffset(lastPrefixToken.EndOffset() + suffixToken.EndOffset());
return suffixToken;
}
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
reusableToken.Clear();
int length = 0;
int start = bufferIndex;
char[] buffer = reusableToken.TermBuffer();
while (true)
{
if (bufferIndex >= dataLen)
{
offset += dataLen;
dataLen = input is Lucene.Net.Index.ReusableStringReader ? ((Lucene.Net.Index.ReusableStringReader) input).Read(ioBuffer) : input.Read((System.Char[]) ioBuffer, 0, ioBuffer.Length);
if (dataLen <= 0)
{
if (length > 0)
break;
else
return null;
}
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 = reusableToken.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
}
reusableToken.SetTermLength(length);
reusableToken.SetStartOffset(start);
reusableToken.SetEndOffset(start + length);
return reusableToken;
}
public Token UpdateSuffixToken(Token suffixToken, Token lastInputToken)
{
suffixToken.SetStartOffset(lastInputToken.EndOffset() + suffixToken.StartOffset());
suffixToken.SetEndOffset(lastInputToken.EndOffset() + suffixToken.EndOffset());
return suffixToken;
}
public Token UpdateInputToken(Token inputToken, Token lastPrefixToken)
{
inputToken.SetStartOffset(lastPrefixToken.EndOffset() + inputToken.StartOffset());
inputToken.SetEndOffset(lastPrefixToken.EndOffset() + inputToken.EndOffset());
return inputToken;
}