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
|
package com.wcohen.ss.tokens;
import java.util.*;
import com.wcohen.ss.api.*;
/**
* Character tokenizer implementation. Tokens are single characters of the source string.
*/
public class CharacterTokenizer implements Tokenizer
{
public static final CharacterTokenizer DEFAULT_TOKENIZER = new CharacterTokenizer(true,true);
private boolean ignorePunctuation = true;
private boolean ignoreCase = true;
public CharacterTokenizer(boolean ignorePunctuation,boolean ignoreCase) {
this.ignorePunctuation = ignorePunctuation;
this.ignoreCase = ignoreCase;
}
// parameter setting
public void setIgnorePunctuation(boolean flag) { ignorePunctuation = flag; }
public void setIgnoreCase(boolean flag) { ignoreCase = flag; }
public String toString() { return "[CharacterTokenizer "+ignorePunctuation+";"+ignoreCase+"]"; }
/** Return tokenized version of a string. Tokens are sequences
* of alphanumerics, or any single punctuation character. */
public Token[] tokenize(String input)
{
char[] stringChars = input.toCharArray();
List<Token> tokens = new ArrayList<Token>();
for (char c : stringChars) {
if(Character.isLetterOrDigit(c)){
tokens.add(internSomething(Character.toString(c)));
}
else if (!ignorePunctuation && !Character.isWhitespace(c)) {
tokens.add(internSomething(Character.toString(c)));
}
}
return (Token[]) tokens.toArray(new BasicToken[tokens.size()]);
}
private Token internSomething(String s)
{
return intern( ignoreCase ? s.toLowerCase() : s );
}
//
// 'interning' strings as tokens
//
private int nextId = 0;
private Map<String, Token> tokMap = new TreeMap<String, Token>();
public Token intern(String s)
{
Token tok = (Token)tokMap.get(s);
if (tok==null) {
tok = new BasicToken(++nextId,s);
tokMap.put(s,tok);
}
return tok;
}
public Iterator<Token> tokenIterator()
{
return tokMap.values().iterator();
}
public int maxTokenIndex()
{
return nextId;
}
/** Test routine */
public static void main(String[] argv)
{
CharacterTokenizer tokenizer = DEFAULT_TOKENIZER;
int n = 0;
for (int i=0; i<argv.length; i++) {
System.out.println("argument "+i+": '"+argv[i]+"'");
Token[] tokens = tokenizer.tokenize(argv[i]);
for (int j=0; j<tokens.length; j++) {
System.out.println("token "+(++n)+":"
+" id="+tokens[j].getIndex()
+" value: '"+tokens[j].getValue()+"'");
}
}
}
}
|
