|
1
2
3
4
5
6
7
8
9
|
package is2.util;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
|
|
10
11
12
13
14
|
import java.io.Reader;
import java.nio.channels.Channels;
import java.nio.channels.FileChannel;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
|
|
15
16
17
18
19
20
21
|
import java.util.StringTokenizer;
public class Split2 {
/**
* Splits a tokenized sentences into one word per line format:
*
|
|
22
23
24
25
26
27
28
29
30
|
* Input
* > I am an text .
* > Sentence two ...
*
* Output:
* I _ _ _ ...
* am _ _ _ ...
* ...
*
|
|
31
32
33
34
35
|
* @param args
* @throws IOException
*/
public static void main(String args[]) throws IOException {
|
|
36
|
if (args.length<1) {
|
|
37
38
39
|
System.out.println("Please provide a file name.");
System.exit(0);
}
|
|
40
41
42
43
44
45
|
BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(args[0]),"UTF-8"),32768);
BufferedWriter write = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(args[1]),"ISO-8859-1"));
|
|
46
|
String s;
|
|
47
|
int cnt=0;
|
|
48
49
|
while ((s = reader.readLine()) != null) {
StringTokenizer t = new StringTokenizer(s);
|
|
50
51
52
53
|
while(t.hasMoreTokens()) {
String tk =t.nextToken();
for(int c : tk.toCharArray()) {
if (c<0 && c>=255) System.out.println("contain sign "+c+" "+cnt);
|
|
54
55
56
57
58
59
60
61
62
63
|
}
write.write(tk);
write.newLine();
cnt++;
}
write.newLine();
}
reader.close();
write.flush();
write.close();
|
|
64
65
66
|
|
|
67
|
}
|
|
68
69
|
|
|
70
|
}
|