/// <summary>
/// Returns a <see cref="StemmerOverrideMap"/> to be used with the <see cref="StemmerOverrideFilter"/> </summary>
/// <returns> a <see cref="StemmerOverrideMap"/> to be used with the <see cref="StemmerOverrideFilter"/> </returns>
/// <exception cref="IOException"> if an <see cref="IOException"/> occurs; </exception>
public virtual StemmerOverrideMap Build()
{
ByteSequenceOutputs outputs = ByteSequenceOutputs.Singleton;
Builder <BytesRef> builder = new Builder <BytesRef>(FST.INPUT_TYPE.BYTE4, outputs);
int[] sort = hash.Sort(BytesRef.UTF8SortedAsUnicodeComparer);
Int32sRef intsSpare = new Int32sRef();
int size = hash.Count;
for (int i = 0; i < size; i++)
{
int id = sort[i];
BytesRef bytesRef = hash.Get(id, spare);
UnicodeUtil.UTF8toUTF32(bytesRef, intsSpare);
builder.Add(intsSpare, new BytesRef(outputValues[id]));
}
return(new StemmerOverrideMap(builder.Finish(), ignoreCase));
}
/// <summary>
/// Returns an <seealso cref="StemmerOverrideMap"/> to be used with the <seealso cref="StemmerOverrideFilter"/> </summary>
/// <returns> an <seealso cref="StemmerOverrideMap"/> to be used with the <seealso cref="StemmerOverrideFilter"/> </returns>
/// <exception cref="IOException"> if an <seealso cref="IOException"/> occurs; </exception>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public StemmerOverrideMap build() throws java.io.IOException
public virtual StemmerOverrideMap build()
{
ByteSequenceOutputs outputs = ByteSequenceOutputs.Singleton;
org.apache.lucene.util.fst.Builder <BytesRef> builder = new org.apache.lucene.util.fst.Builder <BytesRef>(FST.INPUT_TYPE.BYTE4, outputs);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int[] sort = hash.sort(org.apache.lucene.util.BytesRef.getUTF8SortedAsUnicodeComparator());
int[] sort = hash.sort(BytesRef.UTF8SortedAsUnicodeComparator);
IntsRef intsSpare = new IntsRef();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int size = hash.size();
int size = hash.size();
for (int i = 0; i < size; i++)
{
int id = sort[i];
BytesRef bytesRef = hash.get(id, spare);
UnicodeUtil.UTF8toUTF32(bytesRef, intsSpare);
builder.add(intsSpare, new BytesRef(outputValues[id]));
}
return(new StemmerOverrideMap(builder.finish(), ignoreCase));
}
[MethodImpl(MethodImplOptions.NoOptimization)] // LUCENENET specific: comparing float equality fails in x86 on .NET Framework with optimizations enabled. Fixes TestTokenLengthOpt.
#endif
protected override sealed AcceptStatus Accept(BytesRef term)
{
if (StringHelper.StartsWith(term, prefixBytesRef))
{
UnicodeUtil.UTF8toUTF32(term, utf32);
int distance = CalcDistance(utf32.Int32s, outerInstance.m_realPrefixLength, utf32.Length - outerInstance.m_realPrefixLength);
//Integer.MIN_VALUE is the sentinel that Levenshtein stopped early
if (distance == int.MinValue)
{
return(AcceptStatus.NO);
}
//no need to calc similarity, if raw is true and distance > maxEdits
if (outerInstance.m_raw == true && distance > outerInstance.m_maxEdits)
{
return(AcceptStatus.NO);
}
float similarity = CalcSimilarity(distance, (utf32.Length - outerInstance.m_realPrefixLength), text.Length);
//if raw is true, then distance must also be <= maxEdits by now
//given the previous if statement
if (outerInstance.m_raw == true ||
(outerInstance.m_raw == false && similarity > outerInstance.MinSimilarity))
{
boostAtt.Boost = (similarity - outerInstance.MinSimilarity) * outerInstance.m_scaleFactor;
return(AcceptStatus.YES);
}
else
{
return(AcceptStatus.NO);
}
}
else
{
return(AcceptStatus.END);
}
}
