blob: 280039a67e8259b2971653ebbaa34f16dc606ea7 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.apache.tuscany.sca.domain.search.impl;
import java.io.IOException;
import java.io.Reader;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.Tokenizer;
/**
*
* @version $Rev$ $Date$
*/
public class NamingTokenizer extends Tokenizer {
private int offset = 0, bufferIndex = 0, dataLen = 0;
private static final int MAX_WORD_LEN = 255;
private static final int IO_BUFFER_SIZE = 4096;
private final char[] ioBuffer = new char[IO_BUFFER_SIZE];
public NamingTokenizer(Reader reader) {
super(reader);
}
@Override
public Token next(Token reusableToken) throws IOException {
assert reusableToken != null;
reusableToken.clear();
int length = 0;
int start = bufferIndex;
char[] buffer = reusableToken.termBuffer();
boolean lowercaseCharFound = false;
boolean digitFound = false;
while (true) {
if (bufferIndex >= dataLen) {
offset += dataLen;
int incr;
if (lowercaseCharFound || length == 0) {
incr = 0;
} else {
incr = 2;
ioBuffer[0] = ioBuffer[bufferIndex - 1];
ioBuffer[1] = ioBuffer[bufferIndex];
}
dataLen = input.read(ioBuffer, incr, ioBuffer.length - incr);
if (dataLen == -1) {
if (length > 0)
break;
else
return null;
}
bufferIndex = incr;
dataLen += incr;
}
final char c = ioBuffer[bufferIndex++];
boolean breakChar = true;
if (Character.isDigit(c)) {
if (digitFound || length == 0) {
breakChar = false;
digitFound = true;
} else {
bufferIndex--;
}
// TODO: normalize accent, it does not index accents for now
} else if (c >= 65 && c <= 90 || c >= 97 && c <= 122) {
if (digitFound) {
bufferIndex--;
} else if (Character.isLowerCase(c)) {
if (!(lowercaseCharFound || length <= 1)) {
length--;
bufferIndex -= 2;
} else {
lowercaseCharFound = true;
breakChar = false;
}
} else if (!lowercaseCharFound) { // && uppercase
breakChar = false;
} else {
bufferIndex--;
}
}
if (!breakChar) {
if (length == 0) // start of token
start = offset + bufferIndex - 1;
else if (length == buffer.length)
buffer = reusableToken.resizeTermBuffer(1 + length);
buffer[length++] = Character.toLowerCase(c); // buffer it,
// normalized
if (length == MAX_WORD_LEN) // buffer overflow!
break;
} else if (length > 0) {// at non-Letter w/ chars
break; // return 'em
}
}
reusableToken.setTermLength(length);
reusableToken.setStartOffset(start);
reusableToken.setEndOffset(start + length);
return reusableToken;
}
}
|
