//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testFilterPositions() throws Exception
public virtual void testFilterPositions()
{
TokenStream ts = new MockTokenizer(new StringReader("abcde vwxyz"), MockTokenizer.WHITESPACE, false);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
assertTokenStreamContents(tokenizer, new string[] { "a", "ab", "abc", "v", "vw", "vwx" }, new int[] { 0, 0, 0, 6, 6, 6 }, new int[] { 5, 5, 5, 11, 11, 11 }, null, new int[] { 1, 0, 0, 1, 0, 0 }, null, null, false);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testSmallTokenInStream() throws Exception
public virtual void testSmallTokenInStream()
{
input = new MockTokenizer(new StringReader("abc de fgh"), MockTokenizer.WHITESPACE, false);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 3, 3);
assertTokenStreamContents(tokenizer, new string[] { "abc", "fgh" }, new int[] { 0, 7 }, new int[] { 3, 10 });
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testGraphs() throws java.io.IOException
public virtual void testGraphs()
{
TokenStream tk = new LetterTokenizer(TEST_VERSION_CURRENT, new StringReader("abc d efgh ij klmno p q"));
tk = new ShingleFilter(tk);
tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, 7, 10);
assertTokenStreamContents(tk, new string[] { "efgh ij", "ij klmn", "ij klmno", "klmno p" }, new int[] { 6, 11, 11, 14 }, new int[] { 13, 19, 19, 21 }, new int[] { 3, 1, 0, 1 }, new int[] { 2, 2, 2, 2 }, 23);
}
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TokenFilter filters = new ASCIIFoldingFilter(tokenizer);
filters = new EdgeNGramTokenFilter(Version.LUCENE_43, filters, EdgeNGramTokenFilter.Side.FRONT, 2, 15);
return(new TokenStreamComponents(tokenizer, filters));
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testReset() throws Exception
public virtual void testReset()
{
WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"));
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
assertTokenStreamContents(filter, new string[] { "a", "ab", "abc" }, new int[] { 0, 0, 0 }, new int[] { 5, 5, 5 });
tokenizer.Reader = new StringReader("abcde");
assertTokenStreamContents(filter, new string[] { "a", "ab", "abc" }, new int[] { 0, 0, 0 }, new int[] { 5, 5, 5 });
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testFirstTokenPositionIncrement() throws Exception
public virtual void testFirstTokenPositionIncrement()
{
TokenStream ts = new MockTokenizer(new StringReader("a abc"), MockTokenizer.WHITESPACE, false);
ts = new PositionFilter(ts); // All but first token will get 0 position increment
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, EdgeNGramTokenFilter.Side.FRONT, 2, 3);
// The first token "a" will not be output, since it's smaller than the mingram size of 2.
// The second token on input to EdgeNGramTokenFilter will have position increment of 0,
// which should be increased to 1, since this is the first output token in the stream.
assertTokenStreamContents(filter, new string[] { "ab", "abc" }, new int[] { 2, 2 }, new int[] { 5, 5 }, new int[] { 1, 0 });
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testSupplementaryCharacters() throws java.io.IOException
public virtual void testSupplementaryCharacters()
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final String s = org.apache.lucene.util.TestUtil.randomUnicodeString(random(), 10);
string s = TestUtil.randomUnicodeString(random(), 10);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int codePointCount = s.codePointCount(0, s.length());
int codePointCount = s.codePointCount(0, s.Length);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int minGram = org.apache.lucene.util.TestUtil.nextInt(random(), 1, 3);
int minGram = TestUtil.Next(random(), 1, 3);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int maxGram = org.apache.lucene.util.TestUtil.nextInt(random(), minGram, 10);
int maxGram = TestUtil.Next(random(), minGram, 10);
TokenStream tk = new KeywordTokenizer(new StringReader(s));
tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.CharTermAttribute termAtt = tk.addAttribute(org.apache.lucene.analysis.tokenattributes.CharTermAttribute.class);
CharTermAttribute termAtt = tk.addAttribute(typeof(CharTermAttribute));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.tokenattributes.OffsetAttribute offsetAtt = tk.addAttribute(org.apache.lucene.analysis.tokenattributes.OffsetAttribute.class);
OffsetAttribute offsetAtt = tk.addAttribute(typeof(OffsetAttribute));
tk.reset();
for (int i = minGram; i <= Math.Min(codePointCount, maxGram); ++i)
{
assertTrue(tk.incrementToken());
assertEquals(0, offsetAtt.startOffset());
assertEquals(s.Length, offsetAtt.endOffset());
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int end = Character.offsetByCodePoints(s, 0, i);
int end = char.offsetByCodePoints(s, 0, i);
assertEquals(s.Substring(0, end), termAtt.ToString());
}
assertFalse(tk.incrementToken());
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testBackRangeOfNgrams() throws Exception
public virtual void testBackRangeOfNgrams()
{
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(Version.LUCENE_43, input, EdgeNGramTokenFilter.Side.BACK, 1, 3);
assertTokenStreamContents(tokenizer, new string[] { "e", "de", "cde" }, new int[] { 4, 3, 2 }, new int[] { 5, 5, 5 }, null, null, null, null, false);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testFrontRangeOfNgrams() throws Exception
public virtual void testFrontRangeOfNgrams()
{
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
assertTokenStreamContents(tokenizer, new string[] { "a", "ab", "abc" }, new int[] { 0, 0, 0 }, new int[] { 5, 5, 5 });
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testOversizedNgrams() throws Exception
public virtual void testOversizedNgrams()
{
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 6, 6);
assertTokenStreamContents(tokenizer, new string[0], new int[0], new int[0]);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testBackUnigram() throws Exception
public virtual void testBackUnigram()
{
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(Version.LUCENE_43, input, EdgeNGramTokenFilter.Side.BACK, 1, 1);
assertTokenStreamContents(tokenizer, new string[] { "e" }, new int[] { 4 }, new int[] { 5 });
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testFrontUnigram() throws Exception
public virtual void testFrontUnigram()
{
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 1, 1);
assertTokenStreamContents(tokenizer, new string[] { "a" }, new int[] { 0 }, new int[] { 5 });
}
public override TokenStream create(TokenStream input)
{
var filter = new EdgeNGramTokenFilter(input, _side ?? EdgeNGramTokenFilter.DEFAULT_SIDE, _minGram ?? EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE, _maxGram ?? EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
return(filter);
}
