01: package org.apache.lucene.analysis.ngram;
02:
03: /**
04: * Licensed to the Apache Software Foundation (ASF) under one or more
05: * contributor license agreements. See the NOTICE file distributed with
06: * this work for additional information regarding copyright ownership.
07: * The ASF licenses this file to You under the Apache License, Version 2.0
08: * (the "License"); you may not use this file except in compliance with
09: * the License. You may obtain a copy of the License at
10: *
11: * http://www.apache.org/licenses/LICENSE-2.0
12: *
13: * Unless required by applicable law or agreed to in writing, software
14: * distributed under the License is distributed on an "AS IS" BASIS,
15: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16: * See the License for the specific language governing permissions and
17: * limitations under the License.
18: */
19:
20: import org.apache.lucene.analysis.Token;
21: import org.apache.lucene.analysis.Tokenizer;
22:
23: import java.io.IOException;
24: import java.io.Reader;
25:
26: /**
27: * Tokenizes the input into n-grams of the given size(s).
28: * @author Otis Gospodnetic
29: */
30: public class NGramTokenizer extends Tokenizer {
31: public static final int DEFAULT_MIN_NGRAM_SIZE = 1;
32: public static final int DEFAULT_MAX_NGRAM_SIZE = 2;
33:
34: private int minGram, maxGram;
35: private int gramSize;
36: private int pos = 0;
37: private int inLen;
38: private String inStr;
39: private boolean started = false;
40:
41: /**
42: * Creates NGramTokenizer with given min and max n-grams.
43: * @param input Reader holding the input to be tokenized
44: * @param minGram the smallest n-gram to generate
45: * @param maxGram the largest n-gram to generate
46: */
47: public NGramTokenizer(Reader input, int minGram, int maxGram) {
48: super (input);
49: if (minGram < 1) {
50: throw new IllegalArgumentException(
51: "minGram must be greater than zero");
52: }
53: if (minGram > maxGram) {
54: throw new IllegalArgumentException(
55: "minGram must not be greater than maxGram");
56: }
57: this .minGram = minGram;
58: this .maxGram = maxGram;
59: }
60:
61: /**
62: * Creates NGramTokenizer with default min and max n-grams.
63: * @param input Reader holding the input to be tokenized
64: */
65: public NGramTokenizer(Reader input) {
66: this (input, DEFAULT_MIN_NGRAM_SIZE, DEFAULT_MAX_NGRAM_SIZE);
67: }
68:
69: /** Returns the next token in the stream, or null at EOS. */
70: public final Token next() throws IOException {
71: if (!started) {
72: started = true;
73: gramSize = minGram;
74: char[] chars = new char[1024];
75: input.read(chars);
76: inStr = new String(chars).trim(); // remove any trailing empty strings
77: inLen = inStr.length();
78: }
79:
80: if (pos + gramSize > inLen) { // if we hit the end of the string
81: pos = 0; // reset to beginning of string
82: gramSize++; // increase n-gram size
83: if (gramSize > maxGram) // we are done
84: return null;
85: if (pos + gramSize > inLen)
86: return null;
87: }
88: String gram = inStr.substring(pos, pos + gramSize);
89: int oldPos = pos;
90: pos++;
91: return new Token(gram, oldPos, oldPos + gramSize);
92: }
93: }
|