mirror of
https://github.com/Alfresco/alfresco-community-repo.git
synced 2025-06-02 17:35:18 +00:00
e31e027039
- expects .msg files in native Outlook format - uses POI library for the parsing of the horrid OLE2 compound document format - extracts addressee(s), sent date and originator email address ...for the future - could be modified and used as a transformer to allow full-text indexing of Outlook format emails . Add new aspect "emailed" to the contentmodel to support properties for above extractor git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@3387 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
58 lines
1.6 KiB
Java
58 lines
1.6 KiB
Java
/*
|
||
* Copyright (C) 2005 Jesper Steen M<>ller
|
||
*
|
||
* Licensed under the Mozilla Public License version 1.1
|
||
* with a permitted attribution clause. You may obtain a
|
||
* copy of the License at
|
||
*
|
||
* http://www.alfresco.org/legal/license.txt
|
||
*
|
||
* Unless required by applicable law or agreed to in writing,
|
||
* software distributed under the License is distributed on an
|
||
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
|
||
* either express or implied. See the License for the specific
|
||
* language governing permissions and limitations under the
|
||
* License.
|
||
*/
|
||
package org.alfresco.repo.content.metadata;
|
||
|
||
import org.alfresco.repo.content.MimetypeMap;
|
||
|
||
/**
|
||
* @author Jesper Steen Møller
|
||
*/
|
||
public class HtmlMetadataExtracterTest extends AbstractMetadataExtracterTest
|
||
{
|
||
private MetadataExtracter extracter;
|
||
|
||
@Override
|
||
public void setUp() throws Exception
|
||
{
|
||
super.setUp();
|
||
extracter = new HtmlMetadataExtracter();
|
||
}
|
||
|
||
/**
|
||
* @return Returns the same transformer regardless - it is allowed
|
||
*/
|
||
protected MetadataExtracter getExtracter()
|
||
{
|
||
return extracter;
|
||
}
|
||
|
||
public void testReliability() throws Exception
|
||
{
|
||
double reliability = 0.0;
|
||
reliability = extracter.getReliability(MimetypeMap.MIMETYPE_TEXT_PLAIN);
|
||
assertEquals("Mimetype text should not be supported", 0.0, reliability);
|
||
|
||
reliability = extracter.getReliability(MimetypeMap.MIMETYPE_HTML);
|
||
assertEquals("HTML should be supported", 1.0, reliability);
|
||
}
|
||
|
||
public void testHtmlExtraction() throws Exception
|
||
{
|
||
testExtractFromMimetype(MimetypeMap.MIMETYPE_HTML);
|
||
}
|
||
}
|