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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
|
/**
* Copyright (c) 2001, Sergey A. Samokhodkin
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification,
* are permitted provided that the following conditions are met:
*
* - Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* - Redistributions in binary form
* must reproduce the above copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials provided with the distribution.
* - Neither the name of jregex nor the names of its contributors may be used
* to endorse or promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
* INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
* OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY
* WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* @version 1.2_01
*/
package jregex;
import java.io.*;
import java.util.*;
/**
* The Tokenizer class suggests a methods to break a text into tokens using
* occurences of a pattern as delimiters.
* There are two ways to obtain a text tokenizer for some pattern:<pre>
* Pattern p=new Pattern("\\s+"); //any number of space characters
* String text="blah blah blah";
* //by factory method
* RETokenizer tok1=p.tokenizer(text);
* //or by constructor
* RETokenizer tok2=new RETokenizer(p,text);
* </pre>
* Now the one way is to use the tokenizer as a token enumeration/iterator:<pre>
* while(tok1.hasMore()) System.out.println(tok1.nextToken());
* </pre>
* and another way is to split it into a String array:<pre>
* String[] arr=tok2.split();
* for(int i=0;i<tok2.length;i++) System.out.println(arr[i]);
* </pre>
* @see Pattern#tokenizer(java.lang.String)
*/
public class RETokenizer implements Enumeration{
private Matcher matcher;
private boolean checked;
private boolean hasToken;
private String token;
private int pos=0;
private boolean endReached=false;
private boolean emptyTokensEnabnled=false;
public RETokenizer(Pattern pattern,String text){
this(pattern.matcher(text),false);
}
public RETokenizer(Pattern pattern,char[] chars,int off,int len){
this(pattern.matcher(chars,off,len),false);
}
public RETokenizer(Pattern pattern,Reader r,int len) throws IOException{
this(pattern.matcher(r,len),false);
}
public RETokenizer(Matcher m, boolean emptyEnabled){
matcher=m;
emptyTokensEnabnled=emptyEnabled;
}
public void setEmptyEnabled(boolean b){
emptyTokensEnabnled=b;
}
public boolean isEmptyEnabled(){
return emptyTokensEnabnled;
}
public boolean hasMore(){
if(!checked) check();
return hasToken;
}
public String nextToken(){
if(!checked) check();
if(!hasToken) throw new NoSuchElementException();
checked=false;
return token;
}
public String[] split(){
return collect(this,null,0);
}
public void reset(){
matcher.setPosition(0);
}
private static final String[] collect(RETokenizer tok,String[] arr,int count){
if(tok.hasMore()){
String s=tok.nextToken();
//System.out.println("collect(,,"+count+"): token="+s);
arr=collect(tok,arr,count+1);
arr[count]=s;
}
else{
arr=new String[count];
}
return arr;
}
private void check(){
final boolean emptyOk=this.emptyTokensEnabnled;
checked=true;
if(endReached){
hasToken=false;
return;
}
Matcher m=matcher;
boolean hasMatch=false;
while(m.find()){
if(m.start()>0){
hasMatch=true;
break;
}
else if(m.end()>0){
if(emptyOk){
hasMatch=true;
break;
}
else m.setTarget(m,MatchResult.SUFFIX);
}
}
if(!hasMatch){
endReached=true;
if(m.length(m.TARGET)==0 && !emptyOk){
hasToken=false;
}
else{
hasToken=true;
token=m.target();
}
return;
}
//System.out.println(m.target()+": "+m.groupv());
//System.out.println("prefix: "+m.prefix());
//System.out.println("suffix: "+m.suffix());
hasToken=true;
token=m.prefix();
m.setTarget(m,MatchResult.SUFFIX);
//m.setTarget(m.suffix());
}
public boolean hasMoreElements(){
return hasMore();
}
/**
* @return a next token as a String
*/
public Object nextElement(){
return nextToken();
}
/*
public static void main(String[] args){
RETokenizer rt=new RETokenizer(new Pattern("/").matcher("/a//b/c/"),false);
while(rt.hasMore()){
System.out.println("<"+rt.nextToken()+">");
}
}
*/
}
|
