ioutilstest.java

Heritrix是一个开源,可扩展的web爬虫项目。Heritrix设计成严格按照robots.txt文件的排除指示和META robots标签。

/* IoUtilsTest
 * 
 * $Id: IoUtilsTest.java 3715 2005-07-20 19:48:12Z stack-sf $
 *
 * Created on Jun 9, 2005
 * 
 * Copyright (C) 2003 Internet Archive.
 *
 * This file is part of the Heritrix web crawler (crawler.archive.org).
 *
 * Heritrix is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser Public License as published by
 * the Free Software Foundation; either version 2.1 of the License, or
 * any later version.
 *
 * Heritrix 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 Lesser Public License for more details.
 *
 * You should have received a copy of the GNU Lesser Public License
 * along with Heritrix; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */
package org.archive.crawler.util;

import java.io.File;
import java.io.IOException;

import org.archive.util.TmpDirTestCase;

/**
 * Test IoUtils.
 * @author stack
 */
public class IoUtilsTest extends TmpDirTestCase {
    public void testGetInputStreamFileFileString() throws IOException {
        File f = new File(getTmpDir(), this.getName() + ".txt");
        f.createNewFile();
        assertNotNull(f + " doesn't return inputstream",
            IoUtils.getInputStream(f.getParentFile(), f.getName()));
        // Comment out test that requires net.
        // assertNotNull(IoUtils.getInputStream("http://www.archive.org/"));
    }
}