public void TestOffsetsWithTokenizer()
{
const string input = @"test1 <a href=""foo"">testlink</a> test2 test3";
Tokenizer t = new WhitespaceTokenizer(new HTMLStripCharFilter(CharReader.Get(new StringReader(input))));
string token = string.Empty;
List <Token> results = new List <Token>();
OffsetAttribute att = ((OffsetAttribute)t.GetAttribute(typeof(OffsetAttribute)));
t.IncrementToken();
Assert.AreEqual(0, att.StartOffset());
Assert.AreEqual(5, att.EndOffset() - att.StartOffset());
t.IncrementToken();
Assert.AreEqual(20, att.StartOffset());
Assert.AreEqual(8, att.EndOffset() - att.StartOffset());
t.IncrementToken();
Assert.AreEqual(33, att.StartOffset());
Assert.AreEqual(5, att.EndOffset() - att.StartOffset());
t.IncrementToken();
Assert.AreEqual(39, att.StartOffset());
Assert.AreEqual(5, att.EndOffset() - att.StartOffset());
}
/** 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;
}
}
/// <summary>
/// Saves this information to form the left part of a gram
/// </summary>
private void SaveTermBuffer()
{
buffer.Length = 0;
buffer.Append(termAttribute.Buffer(), 0, termAttribute.Length);
buffer.Append(SEPARATOR);
lastStartOffset = offsetAttribute.StartOffset();
lastWasCommon = Common;
}
public override bool IncrementToken()
{
while (true)
{
if (curTermBuffer == null)
{
if (!input.IncrementToken())
{
return(false);
}
else
{
curTermBuffer = termAtt.Buffer().Clone();
curTermLength = termAtt.Length();
curCodePointCount = charUtils.codePointCount(termAtt);
curGramSize = minGram;
tokStart = offsetAtt.StartOffset();
tokEnd = offsetAtt.EndOffset();
if (version.OnOrAfter(Version.LUCENE_44))
{
// Never update offsets
updateOffsets = false;
}
else
{
// if length by start + end offsets doesn't match the term text then assume
// this is a synonym and don't adjust the offsets.
updateOffsets = (tokStart + curTermLength) == tokEnd;
}
savePosIncr += posIncrAtt.PositionIncrement;
savePosLen = posLenAtt.PositionLength;
}
}
if (curGramSize <= maxGram) // if we have hit the end of our n-gram size range, quit
{
if (curGramSize <= curCodePointCount) // if the remaining input is too short, we can't generate any n-grams
{
// grab gramSize chars from front or back
int start = side == Side.FRONT ? 0 : charUtils.offsetByCodePoints(curTermBuffer, 0, curTermLength, curTermLength, -curGramSize);
int end = charUtils.offsetByCodePoints(curTermBuffer, 0, curTermLength, start, curGramSize);
ClearAttributes();
if (updateOffsets)
{
offsetAtt.SetOffset(tokStart + start, tokStart + end);
}
else
{
offsetAtt.SetOffset(tokStart, tokEnd);
}
// first ngram gets increment, others don't
if (curGramSize == minGram)
{
posIncrAtt.PositionIncrement = savePosIncr;
savePosIncr = 0;
}
else
{
posIncrAtt.PositionIncrement = 0;
}
posLenAtt.PositionLength = savePosLen;
termAtt.CopyBuffer(curTermBuffer, start, end - start);
curGramSize++;
return(true);
}
}
curTermBuffer = null;
}
}
public static void AssertTokenStreamContents(TokenStream ts, System.String[] output, int[] startOffsets, int[] endOffsets, System.String[] types, int[] posIncrements, int?finalOffset)
{
Assert.IsNotNull(output);
CheckClearAttributesAttribute checkClearAtt = (CheckClearAttributesAttribute)ts.AddAttribute(typeof(CheckClearAttributesAttribute));
Assert.IsTrue(ts.HasAttribute(typeof(TermAttribute)), "has no TermAttribute");
TermAttribute termAtt = (TermAttribute)ts.GetAttribute(typeof(TermAttribute));
OffsetAttribute offsetAtt = null;
if (startOffsets != null || endOffsets != null || finalOffset != null)
{
Assert.IsTrue(ts.HasAttribute(typeof(OffsetAttribute)), "has no OffsetAttribute");
offsetAtt = (OffsetAttribute)ts.GetAttribute(typeof(OffsetAttribute));
}
TypeAttribute typeAtt = null;
if (types != null)
{
Assert.IsTrue(ts.HasAttribute(typeof(TypeAttribute)), "has no TypeAttribute");
typeAtt = (TypeAttribute)ts.GetAttribute(typeof(TypeAttribute));
}
PositionIncrementAttribute posIncrAtt = null;
if (posIncrements != null)
{
Assert.IsTrue(ts.HasAttribute(typeof(PositionIncrementAttribute)), "has no PositionIncrementAttribute");
posIncrAtt = (PositionIncrementAttribute)ts.GetAttribute(typeof(PositionIncrementAttribute));
}
ts.Reset();
for (int i = 0; i < output.Length; i++)
{
// extra safety to enforce, that the state is not preserved and also assign bogus values
ts.ClearAttributes();
termAtt.SetTermBuffer("bogusTerm");
if (offsetAtt != null)
{
offsetAtt.SetOffset(14584724, 24683243);
}
if (typeAtt != null)
{
typeAtt.SetType("bogusType");
}
if (posIncrAtt != null)
{
posIncrAtt.SetPositionIncrement(45987657);
}
checkClearAtt.GetAndResetClearCalled(); // reset it, because we called clearAttribute() before
Assert.IsTrue(ts.IncrementToken(), "token " + i + " does not exist");
Assert.IsTrue(checkClearAtt.GetAndResetClearCalled(), "clearAttributes() was not called correctly in TokenStream chain");
Assert.AreEqual(output[i], termAtt.Term(), "term " + i);
if (startOffsets != null)
{
Assert.AreEqual(startOffsets[i], offsetAtt.StartOffset(), "startOffset " + i);
}
if (endOffsets != null)
{
Assert.AreEqual(endOffsets[i], offsetAtt.EndOffset(), "endOffset " + i);
}
if (types != null)
{
Assert.AreEqual(types[i], typeAtt.Type(), "type " + i);
}
if (posIncrements != null)
{
Assert.AreEqual(posIncrements[i], posIncrAtt.GetPositionIncrement(), "posIncrement " + i);
}
}
Assert.IsFalse(ts.IncrementToken(), "end of stream");
ts.End();
if (finalOffset.HasValue)
{
Assert.AreEqual(finalOffset, offsetAtt.EndOffset(), "finalOffset ");
}
ts.Close();
}
public override bool IncrementToken()
{
if (!Input.IncrementToken())
{
return(false);
}
int startOffset = 0;
int endOffset = 0;
int posLen = 0;
if (PosIncAtt != null)
{
Pos += PosIncAtt.PositionIncrement;
if (Pos == -1)
{
throw new Exception("first posInc must be > 0");
}
}
// System.out.println(" got token=" + termAtt + " pos=" + pos);
if (OffsetAtt != null)
{
startOffset = OffsetAtt.StartOffset();
endOffset = OffsetAtt.EndOffset();
if (OffsetsAreCorrect && OffsetAtt.StartOffset() < LastStartOffset)
{
throw new Exception(Name + ": offsets must not go backwards startOffset=" + startOffset + " is < lastStartOffset=" + LastStartOffset);
}
LastStartOffset = OffsetAtt.StartOffset();
}
posLen = PosLenAtt == null ? 1 : PosLenAtt.PositionLength;
if (OffsetAtt != null && PosIncAtt != null && OffsetsAreCorrect)
{
if (!PosToStartOffset.ContainsKey(Pos))
{
// First time we've seen a token leaving from this position:
PosToStartOffset[Pos] = startOffset;
//System.out.println(" + s " + pos + " -> " + startOffset);
}
else
{
// We've seen a token leaving from this position
// before; verify the startOffset is the same:
//System.out.println(" + vs " + pos + " -> " + startOffset);
int oldStartOffset = PosToStartOffset[Pos];
if (oldStartOffset != startOffset)
{
throw new Exception(Name + ": inconsistent startOffset at pos=" + Pos + ": " + oldStartOffset + " vs " + startOffset + "; token=" + TermAtt);
}
}
int endPos = Pos + posLen;
if (!PosToEndOffset.ContainsKey(endPos))
{
// First time we've seen a token arriving to this position:
PosToEndOffset[endPos] = endOffset;
//System.out.println(" + e " + endPos + " -> " + endOffset);
}
else
{
// We've seen a token arriving to this position
// before; verify the endOffset is the same:
//System.out.println(" + ve " + endPos + " -> " + endOffset);
int oldEndOffset = PosToEndOffset[endPos];
if (oldEndOffset != endOffset)
{
throw new Exception(Name + ": inconsistent endOffset at pos=" + endPos + ": " + oldEndOffset + " vs " + endOffset + "; token=" + TermAtt);
}
}
}
return(true);
}
/// <summary>
/// Returns the next token in the stream, or null at EOS.
/// </summary>
public override bool IncrementToken()
{
while (true)
{
if (curTermBuffer == null)
{
if (!input.IncrementToken())
{
return(false);
}
else
{
curTermBuffer = termAtt.Buffer().Clone();
curTermLength = termAtt.Length;
curCodePointCount = charUtils.CodePointCount(termAtt);
curGramSize = minGram;
curPos = 0;
curPosInc = posIncAtt.PositionIncrement;
curPosLen = posLenAtt.PositionLength;
tokStart = offsetAtt.StartOffset();
tokEnd = offsetAtt.EndOffset();
// if length by start + end offsets doesn't match the term text then assume
// this is a synonym and don't adjust the offsets.
hasIllegalOffsets = (tokStart + curTermLength) != tokEnd;
}
}
if (version.OnOrAfter(Version.LUCENE_44))
{
if (curGramSize > maxGram || (curPos + curGramSize) > curCodePointCount)
{
++curPos;
curGramSize = minGram;
}
if ((curPos + curGramSize) <= curCodePointCount)
{
ClearAttributes();
int start = charUtils.OffsetByCodePoints(curTermBuffer, 0, curTermLength, 0, curPos);
int end = charUtils.OffsetByCodePoints(curTermBuffer, 0, curTermLength, start, curGramSize);
termAtt.CopyBuffer(curTermBuffer, start, end - start);
posIncAtt.PositionIncrement = curPosInc;
curPosInc = 0;
posLenAtt.PositionLength = curPosLen;
offsetAtt.SetOffset(tokStart, tokEnd);
curGramSize++;
return(true);
}
}
else
{
while (curGramSize <= maxGram)
{
while (curPos + curGramSize <= curTermLength) // while there is input
{
ClearAttributes();
termAtt.CopyBuffer(curTermBuffer, curPos, curGramSize);
if (hasIllegalOffsets)
{
offsetAtt.SetOffset(tokStart, tokEnd);
}
else
{
offsetAtt.SetOffset(tokStart + curPos, tokStart + curPos + curGramSize);
}
curPos++;
return(true);
}
curGramSize++; // increase n-gram size
curPos = 0;
}
}
curTermBuffer = null;
}
}