inteligr8/alfresco-community-repo
1
0
Fork 0
mirror of https://github.com/Alfresco/alfresco-community-repo.git synced 2025-08-07 17:49:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update to use latest version of text mining lib.

Browse Source 
git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@11073 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
Mark Rogers
2008-09-29 14:54:01 +00:00
parent 8fedd638a6
commit 57b26d1146
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
source/java/org/alfresco/repo/content/transform/TextMiningContentTransformer.java
View File

@@ -31,7 +31,8 @@ import org.alfresco.repo.content.MimetypeMap;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.ContentWriter;
import org.alfresco.service.cmr.repository.TransformationOptions;
import org.textmining.text.extraction.WordExtractor;
import org.textmining.extraction.TextExtractor;
import org.textmining.extraction.word.WordTextExtractorFactory;
/**
* Makes use of the {@link http://www.textmining.org/ TextMining} library to
@@ -41,11 +42,11 @@ import org.textmining.text.extraction.WordExtractor;
*/
public class TextMiningContentTransformer extends AbstractContentTransformer2
{
private WordExtractor wordExtractor;
private WordTextExtractorFactory wordExtractorFactory;
public TextMiningContentTransformer()
{
this.wordExtractor = new WordExtractor();
this.wordExtractorFactory = new WordTextExtractorFactory();
}
/**
@@ -73,7 +74,8 @@ public class TextMiningContentTransformer extends AbstractContentTransformer2
try
{
is = reader.getContentInputStream();
text = wordExtractor.extractText(is);
TextExtractor te = wordExtractorFactory.textExtractor(is);
text = te.getText();
}
catch (IOException e)
{