// LUCENE-1441
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testOffsets() throws Exception
public virtual void testOffsets()
{
TokenStream stream = (new KeywordAnalyzer()).tokenStream("field", new StringReader("abcd"));
try
{
OffsetAttribute offsetAtt = stream.addAttribute(typeof(OffsetAttribute));
stream.reset();
assertTrue(stream.incrementToken());
assertEquals(0, offsetAtt.startOffset());
assertEquals(4, offsetAtt.endOffset());
assertFalse(stream.incrementToken());
stream.end();
}
finally
{
IOUtils.closeWhileHandlingException(stream);
}
}
public PrefixAwareTokenFilter(TokenStream prefix, TokenStream suffix) : base(suffix)
{
this.suffix = suffix;
this.prefix = prefix;
prefixExhausted = false;
termAtt = addAttribute(typeof(CharTermAttribute));
posIncrAtt = addAttribute(typeof(PositionIncrementAttribute));
payloadAtt = addAttribute(typeof(PayloadAttribute));
offsetAtt = addAttribute(typeof(OffsetAttribute));
typeAtt = addAttribute(typeof(TypeAttribute));
flagsAtt = addAttribute(typeof(FlagsAttribute));
p_termAtt = prefix.addAttribute(typeof(CharTermAttribute));
p_posIncrAtt = prefix.addAttribute(typeof(PositionIncrementAttribute));
p_payloadAtt = prefix.addAttribute(typeof(PayloadAttribute));
p_offsetAtt = prefix.addAttribute(typeof(OffsetAttribute));
p_typeAtt = prefix.addAttribute(typeof(TypeAttribute));
p_flagsAtt = prefix.addAttribute(typeof(FlagsAttribute));
}
public PrefixAwareTokenFilter(TokenStream prefix, TokenStream suffix) : base(suffix)
{
this.suffix = suffix;
this.prefix = prefix;
prefixExhausted = false;
termAtt = addAttribute(typeof(CharTermAttribute));
posIncrAtt = addAttribute(typeof(PositionIncrementAttribute));
payloadAtt = addAttribute(typeof(PayloadAttribute));
offsetAtt = addAttribute(typeof(OffsetAttribute));
typeAtt = addAttribute(typeof(TypeAttribute));
flagsAtt = addAttribute(typeof(FlagsAttribute));
p_termAtt = prefix.addAttribute(typeof(CharTermAttribute));
p_posIncrAtt = prefix.addAttribute(typeof(PositionIncrementAttribute));
p_payloadAtt = prefix.addAttribute(typeof(PayloadAttribute));
p_offsetAtt = prefix.addAttribute(typeof(OffsetAttribute));
p_typeAtt = prefix.addAttribute(typeof(TypeAttribute));
p_flagsAtt = prefix.addAttribute(typeof(FlagsAttribute));
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test() throws java.io.IOException
public virtual void test()
{
string test = "The quick red fox jumped over the lazy brown dogs";
TokenOffsetPayloadTokenFilter nptf = new TokenOffsetPayloadTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
int count = 0;
PayloadAttribute payloadAtt = nptf.getAttribute(typeof(PayloadAttribute));
OffsetAttribute offsetAtt = nptf.getAttribute(typeof(OffsetAttribute));
nptf.reset();
while (nptf.incrementToken())
{
BytesRef pay = payloadAtt.Payload;
assertTrue("pay is null and it shouldn't be", pay != null);
sbyte[] data = pay.bytes;
int start = PayloadHelper.decodeInt(data, 0);
assertTrue(start + " does not equal: " + offsetAtt.startOffset(), start == offsetAtt.startOffset());
int end = PayloadHelper.decodeInt(data, 4);
assertTrue(end + " does not equal: " + offsetAtt.endOffset(), end == offsetAtt.endOffset());
count++;
}
assertTrue(count + " does not equal: " + 10, count == 10);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public boolean incrementToken() throws java.io.IOException
public override bool incrementToken()
{
if (hasMoreTokensInClone)
{
int start = breaker.current();
int end = breaker.next();
if (end != BreakIterator.DONE)
{
clonedToken.copyTo(this);
termAtt.copyBuffer(clonedTermAtt.buffer(), start, end - start);
if (hasIllegalOffsets)
{
offsetAtt.setOffset(clonedOffsetAtt.startOffset(), clonedOffsetAtt.endOffset());
}
else
{
offsetAtt.setOffset(clonedOffsetAtt.startOffset() + start, clonedOffsetAtt.startOffset() + end);
}
if (handlePosIncr)
{
posAtt.PositionIncrement = 1;
}
return true;
}
hasMoreTokensInClone = false;
}
if (!input.incrementToken())
{
return false;
}
if (termAtt.length() == 0 || char.UnicodeBlock.of(termAtt.charAt(0)) != char.UnicodeBlock.THAI)
{
return true;
}
hasMoreTokensInClone = true;
// 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 = offsetAtt.endOffset() - offsetAtt.startOffset() != termAtt.length();
// we lazy init the cloned token, as in ctor not all attributes may be added
if (clonedToken == null)
{
clonedToken = cloneAttributes();
clonedTermAtt = clonedToken.getAttribute(typeof(CharTermAttribute));
clonedOffsetAtt = clonedToken.getAttribute(typeof(OffsetAttribute));
}
else
{
this.copyTo(clonedToken);
}
// reinit CharacterIterator
charIterator.setText(clonedTermAtt.buffer(), 0, clonedTermAtt.length());
breaker.Text = charIterator;
int end = breaker.next();
if (end != BreakIterator.DONE)
{
termAtt.Length = end;
if (hasIllegalOffsets)
{
offsetAtt.setOffset(clonedOffsetAtt.startOffset(), clonedOffsetAtt.endOffset());
}
else
{
offsetAtt.setOffset(clonedOffsetAtt.startOffset(), clonedOffsetAtt.startOffset() + end);
}
// position increment keeps as it is for first token
return true;
}
return false;
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void reset() throws java.io.IOException
public override void reset()
{
base.reset();
hasMoreTokensInClone = false;
clonedToken = null;
clonedTermAtt = null;
clonedOffsetAtt = null;
}
public TokenStreamAnonymousInnerClassHelper(TestRemoveDuplicatesTokenFilter outerInstance, IEnumerator<Token> toks)
{
this.outerInstance = outerInstance;
this.toks = toks;
termAtt = addAttribute(typeof(CharTermAttribute));
offsetAtt = addAttribute(typeof(OffsetAttribute));
posIncAtt = addAttribute(typeof(PositionIncrementAttribute));
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: static void testNGrams(int minGram, int maxGram, String s, final String nonTokenChars, boolean edgesOnly) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
internal static void testNGrams(int minGram, int maxGram, string s, string nonTokenChars, bool edgesOnly)
{
// convert the string to code points
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int[] codePoints = toCodePoints(s);
int[] codePoints = toCodePoints(s);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int[] offsets = new int[codePoints.length + 1];
int[] offsets = new int[codePoints.Length + 1];
for (int i = 0; i < codePoints.Length; ++i)
{
offsets[i + 1] = offsets[i] + char.charCount(codePoints[i]);
}
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.TokenStream grams = new NGramTokenizer(TEST_VERSION_CURRENT, new java.io.StringReader(s), minGram, maxGram, edgesOnly)
TokenStream grams = new NGramTokenizerAnonymousInnerClassHelper(TEST_VERSION_CURRENT, new StringReader(s), minGram, maxGram, edgesOnly, nonTokenChars);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.CharTermAttribute termAtt = grams.addAttribute(org.apache.lucene.analysis.tokenattributes.CharTermAttribute.class);
CharTermAttribute termAtt = grams.addAttribute(typeof(CharTermAttribute));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute posIncAtt = grams.addAttribute(org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute.class);
PositionIncrementAttribute posIncAtt = grams.addAttribute(typeof(PositionIncrementAttribute));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute posLenAtt = grams.addAttribute(org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute.class);
PositionLengthAttribute posLenAtt = grams.addAttribute(typeof(PositionLengthAttribute));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.OffsetAttribute offsetAtt = grams.addAttribute(org.apache.lucene.analysis.tokenattributes.OffsetAttribute.class);
OffsetAttribute offsetAtt = grams.addAttribute(typeof(OffsetAttribute));
grams.reset();
for (int start = 0; start < codePoints.Length; ++start)
{
for (int end = start + minGram; end <= start + maxGram && end <= codePoints.Length; ++end)
{
if (edgesOnly && start > 0 && isTokenChar(nonTokenChars, codePoints[start - 1]))
{
// not on an edge
goto nextGramContinue;
}
for (int j = start; j < end; ++j)
{
if (!isTokenChar(nonTokenChars, codePoints[j]))
{
goto nextGramContinue;
}
}
assertTrue(grams.incrementToken());
assertArrayEquals(Arrays.copyOfRange(codePoints, start, end), toCodePoints(termAtt));
assertEquals(1, posIncAtt.PositionIncrement);
assertEquals(1, posLenAtt.PositionLength);
assertEquals(offsets[start], offsetAtt.startOffset());
assertEquals(offsets[end], offsetAtt.endOffset());
nextGramContinue :;
}
nextGramBreak :;
}
assertFalse(grams.incrementToken());
grams.end();
assertEquals(s.Length, offsetAtt.startOffset());
assertEquals(s.Length, offsetAtt.endOffset());
}
