blob: 92ed96dac152994bc3452ce2f9a7369d228f1c1b (
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
|
/*
* Copyright (C) 2011 Arunesh Mathur
*
* This file is a part of zimreader-java.
*
* zimreader-java is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License version 3.0 as
* published by the Free Software Foundation.
*
* zimreader-java 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 Lesser General Public License
* along with zimreader-java. If not, see <http://www.gnu.org/licenses/>.
*/
package org.openzim;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.Iterator;
import org.openzim.ZIMReader.DirectoryEntry;
public class ZIMTest {
public static void main(final String[] args) {
if(args.length!=1) {
System.out.println("Usage: java ZIMTest <ZIM_FILE>");
System.exit(0);
}
try {
// args[0] is the Zim File's location
final ZIMFile file = new ZIMFile(args[0]);
// Associate the Zim File with a Reader
final ZIMReader zReader = new ZIMReader(file);
// print a list of urls and titles
int c = Math.min(10, file.header_entryCount);
for (int i = 0; i < c; i++) {
System.out.println("URL by URL " + i + ": " + zReader.getURLByURLOrder(i));
System.out.println("URL by Title " + i + ": " + zReader.getURLByTitleOrder(i));
DirectoryEntry entry = zReader.getDirectoryInfo(i);
System.out.println("URL by Pos " + i + ": " + entry.url);
System.out.println("Title by Pos " + i + ": " + entry.title);
System.out.println("Namespace by Pos " + i + ": " + entry.namespace);
}
// print article c-1
DirectoryEntry directory_entry = zReader.getDirectoryInfo(c - 1);
byte[] articleBytes = zReader.getArticleData(directory_entry);
String article = articleBytes == null ? "NULL" : new String(articleBytes, StandardCharsets.UTF_8);
System.out.println(article);
// iterate over all entries
Iterator<ZIMReader.ArticleBlobEntry> i = zReader.new ClusterIterator();
int count = 0;
while (i.hasNext()) {
ZIMReader.ArticleBlobEntry entry = i.next();
System.out.println(entry.article.url);
count++;
}
System.out.println("Number of articles extracted: " + count);
System.out.println("Number of articles expected: " + file.header_entryCount);
} catch (final IOException e) {
e.printStackTrace();
}
}
}
|
