Tokenizes the input into n-grams of the given size(s).

On the contrary to NGramTokenFilter, this class sets offsets so that characters between startOffset and endOffset in the original stream are the same as the term chars.

For example, "abcde" would be tokenized as (minGram=2, maxGram=3):

Termababcbcbcdcdcdede
Position increment1111111
Position length1111111
Offsets[0,2[[0,3[[1,3[[1,4[[2,4[[2,5[[3,5[

This tokenizer changed a lot in Lucene 4.4 in order to:

  • tokenize in a streaming fashion to support streams which are larger than 1024 chars (limit of the previous version),
  • count grams based on unicode code points instead of java chars (and never split in the middle of surrogate pairs),
  • give the ability to #isTokenChar(int) pre-tokenize the stream before computing n-grams.

Additionally, this class doesn't trim trailing whitespaces and emits tokens in a different order, tokens are now emitted by increasing start offsets while they used to be emitted by increasing lengths (which prevented from supporting large input streams).

Although highly discouraged, it is still possible to use the old behavior through Lucene43NGramTokenizer.

Inheritance: Tokenizer
NGramTokenizer Class Documentation
Ejemplo n.º 1
0
        public virtual void TestReset()
        {
            NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 1, 1);

            AssertTokenStreamContents(tokenizer, new string[] { "a", "b", "c", "d", "e" }, new int[] { 0, 1, 2, 3, 4 }, new int[] { 1, 2, 3, 4, 5 }, 5); // abcde
            tokenizer.Reader = new StringReader("abcde");
            AssertTokenStreamContents(tokenizer, new string[] { "a", "b", "c", "d", "e" }, new int[] { 0, 1, 2, 3, 4 }, new int[] { 1, 2, 3, 4, 5 }, 5); // abcde
        }
Ejemplo n.º 2
0
 public virtual void TestReset()
 {
     NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 1, 1);
     AssertTokenStreamContents(tokenizer, new string[] { "a", "b", "c", "d", "e" }, new int[] { 0, 1, 2, 3, 4 }, new int[] { 1, 2, 3, 4, 5 }, 5); // abcde
     tokenizer.Reader = new StringReader("abcde");
     AssertTokenStreamContents(tokenizer, new string[] { "a", "b", "c", "d", "e" }, new int[] { 0, 1, 2, 3, 4 }, new int[] { 1, 2, 3, 4, 5 }, 5); // abcde
 }
Ejemplo n.º 3
0
 public virtual void TestOversizedNgrams()
 {
     NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 6, 7);
     AssertTokenStreamContents(tokenizer, new string[0], new int[0], new int[0], 5); // abcde
 }
Ejemplo n.º 4
0
 public virtual void TestNgrams()
 {
     NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 1, 3);
     AssertTokenStreamContents(tokenizer, new string[] { "a", "ab", "abc", "b", "bc", "bcd", "c", "cd", "cde", "d", "de", "e" }, new int[] { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 4 }, new int[] { 1, 2, 3, 2, 3, 4, 3, 4, 5, 4, 5, 5 }, null, null, null, 5, false); // abcde
 }
Ejemplo n.º 5
0
 public virtual void TestBigrams()
 {
     NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 2, 2);
     AssertTokenStreamContents(tokenizer, new string[] { "ab", "bc", "cd", "de" }, new int[] { 0, 1, 2, 3 }, new int[] { 2, 3, 4, 5 }, 5); // abcde
 }
Ejemplo n.º 6
0
 public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
 {
     Tokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, reader, min, max);
     return new TokenStreamComponents(tokenizer, tokenizer);
 }
Ejemplo n.º 7
0
        public virtual void TestBigrams()
        {
            NGramTokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, input, 2, 2);

            AssertTokenStreamContents(tokenizer, new string[] { "ab", "bc", "cd", "de" }, new int[] { 0, 1, 2, 3 }, new int[] { 2, 3, 4, 5 }, 5); // abcde
        }
Ejemplo n.º 8
0
            public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
            {
                Tokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, reader, min, max);

                return(new TokenStreamComponents(tokenizer, tokenizer));
            }