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
|
/*
* Copyright (C) 2001-2013 Michael Fuchs
*
* This file is part of herold.
*
* herold is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* herold is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with herold. If not, see <http://www.gnu.org/licenses/>.
*/
package org.dbdoclet.html.tokenizer;
import java.text.ParseException;
import java.util.ArrayList;
import org.dbdoclet.html.tokenizer.parser.HtmlTokenizer;
import org.dbdoclet.html.tokenizer.parser.TokenMgrError;
import org.dbdoclet.progress.ProgressListener;
/**
* Die Klasse <code>Tokenizer</code> implementiert einen Tokenizer für HTML.
*
* @author Michael Fuchs
* @version 1.0
*/
public class Tokenizer {
private ArrayList<Token> tokens;
private Token currentToken;
private StringBuffer buffer = null;
private int tokenPosition = 0;
private ArrayList<ProgressListener> listeners;
/**
* Creates a new <code>MLTokenizer</code> instance.
*
* @param data
* {@link String (String)}
*/
public Tokenizer(String data) {
buffer = new StringBuffer(data);
}
public void tokenize() throws TokenizerException {
tokenPosition = 0;
tokens = parse();
}
/* ======================================================================== */
/* PUBLIC METHODS */
/* ======================================================================== */
/**
* The method <code>hasNext</code> returns true if there are still tokens to
* be fetched.
*
* @return True if another token exists.
*/
public boolean hasNext() {
if (tokenPosition < tokens.size()) {
return true;
} else {
return false;
}
}
/**
* The method <code>next</code> returns the next token.
*
* If there are no more tokens left, a null value is returned.
*
* @return The next token or null {@link Token (MLToken)}.
*/
public Token next() {
if (tokenPosition >= tokens.size()) {
return null;
}
currentToken = tokens.get(tokenPosition);
tokenPosition++;
return currentToken;
}
public int size() {
if (tokens == null) {
throw new IllegalStateException("Variable tokens is null!");
}
return tokens.size();
}
public int position() {
return tokenPosition;
}
/* ======================================================================== */
/* PRIVATE METHODS */
/* ======================================================================== */
/**
* The method <code>parse</code> parses the buffer and adds all tokens into
* an object of the type <code>ArrayList</code>, which is returned in the
* end.
*
* @return {@link java.util.ArrayList (ArrayList)}
* @exception TokenizerException
* if an error occurs
*/
private ArrayList<Token> parse() throws TokenizerException {
HtmlTokenizer parser;
try {
parser = new HtmlTokenizer(buffer.toString(), "UTF-8");
parser.setProgressListeners(listeners);
return parser.parse();
} catch (Throwable oops) {
String msg = "Tokenizer Error";
if (oops instanceof TokenMgrError || oops instanceof ParseException) {
msg = "Parse error " + oops.getMessage() + " while parsing \""
+ buffer.toString() + "\".";
}
throw new TokenizerException(msg, oops);
}
}
public void setProgressListeners(ArrayList<ProgressListener> listeners) {
this.listeners = listeners;
}
}
|
