inteligr8/alfresco-community-repo
1
0
Fork 0
mirror of https://github.com/Alfresco/alfresco-community-repo.git synced 2025-07-24 17:32:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Inverted configuration of Metadata Extracters

Browse Source 
- Adding an extracter no longer requires modification to the MetadataExtracterRegistry
Fixed lack of stream closures

git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@2465 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
Derek Hulley
2006-02-22 11:11:53 +00:00
parent 47ecffb07e
commit 31d9ef768b
13 changed files with 445 additions and 445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
source/java/org/alfresco/repo/content/metadata/HtmlMetadataExtracter.java
View File

@@ -16,7 +16,6 @@
*/
package org.alfresco.repo.content.metadata;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
@@ -34,7 +33,6 @@ import javax.swing.text.html.parser.ParserDelegator;
import org.alfresco.model.ContentModel;
import org.alfresco.repo.content.MimetypeMap;
import org.alfresco.service.cmr.repository.ContentIOException;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.namespace.QName;
@@ -56,122 +54,116 @@ public class HtmlMetadataExtracter extends AbstractMetadataExtracter
super(MIMETYPES, 1.0, 1000);
}
public void extract(ContentReader reader, Map<QName, Serializable> destination) throws ContentIOException
public void extractInternal(ContentReader reader, Map<QName, Serializable> destination) throws Throwable
{
final Map<QName, Serializable> tempDestination = new HashMap<QName, Serializable>();
try
HTMLEditorKit.ParserCallback callback = new HTMLEditorKit.ParserCallback()
{
HTMLEditorKit.ParserCallback callback = new HTMLEditorKit.ParserCallback()
StringBuffer title = null;
boolean inHead = false;
public void handleText(char[] data, int pos)
{
StringBuffer title = null;
boolean inHead = false;
public void handleText(char[] data, int pos)
if (title != null)
{
if (title != null)
{
title.append(data);
}
}
public void handleComment(char[] data, int pos)
{
// Perhaps sniff for Office 9+ metadata in here?
}
public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos)
{
if (HTML.Tag.HEAD.equals(t))
{
inHead = true;
}
else if (HTML.Tag.TITLE.equals(t) && inHead)
{
title = new StringBuffer();
}
else
handleSimpleTag(t, a, pos);
}
public void handleEndTag(HTML.Tag t, int pos)
{
if (HTML.Tag.HEAD.equals(t))
{
inHead = false;
}
else if (HTML.Tag.TITLE.equals(t) && title != null)
{
trimPut(ContentModel.PROP_TITLE, title.toString(), tempDestination);
title = null;
}
}
public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos)
{
if (HTML.Tag.META.equals(t))
{
Object nameO = a.getAttribute(HTML.Attribute.NAME);
Object valueO = a.getAttribute(HTML.Attribute.CONTENT);
if (nameO == null || valueO == null)
return;
String name = nameO.toString();
if (name.equalsIgnoreCase("creator") || name.equalsIgnoreCase("author")
|| name.equalsIgnoreCase("dc.creator"))
{
trimPut(ContentModel.PROP_AUTHOR, valueO, tempDestination);
}
if (name.equalsIgnoreCase("description") || name.equalsIgnoreCase("dc.description"))
{
trimPut(ContentModel.PROP_DESCRIPTION, valueO, tempDestination);
}
}
}
public void handleError(String errorMsg, int pos)
{
}
};
String charsetGuess = "UTF-8";
int tries = 0;
while (tries < 3)
{
tempDestination.clear();
Reader r = null;
InputStream cis = null;
try
{
cis = reader.getContentInputStream();
// TODO: for now, use default charset; we should attempt to map from html meta-data
r = new InputStreamReader(cis);
HTMLEditorKit.Parser parser = new ParserDelegator();
parser.parse(r, callback, tries > 0);
destination.putAll(tempDestination);
break;
}
catch (ChangedCharSetException ccse)
{
tries++;
charsetGuess = ccse.getCharSetSpec();
int begin = charsetGuess.indexOf("charset=");
if (begin > 0)
charsetGuess = charsetGuess.substring(begin + 8, charsetGuess.length());
reader = reader.getReader();
}
finally
{
if (r != null)
r.close();
if (cis != null)
cis.close();
title.append(data);
}
}
}
catch (IOException e)
public void handleComment(char[] data, int pos)
{
// Perhaps sniff for Office 9+ metadata in here?
}
public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos)
{
if (HTML.Tag.HEAD.equals(t))
{
inHead = true;
}
else if (HTML.Tag.TITLE.equals(t) && inHead)
{
title = new StringBuffer();
}
else
handleSimpleTag(t, a, pos);
}
public void handleEndTag(HTML.Tag t, int pos)
{
if (HTML.Tag.HEAD.equals(t))
{
inHead = false;
}
else if (HTML.Tag.TITLE.equals(t) && title != null)
{
trimPut(ContentModel.PROP_TITLE, title.toString(), tempDestination);
title = null;
}
}
public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos)
{
if (HTML.Tag.META.equals(t))
{
Object nameO = a.getAttribute(HTML.Attribute.NAME);
Object valueO = a.getAttribute(HTML.Attribute.CONTENT);
if (nameO == null || valueO == null)
return;
String name = nameO.toString();
if (name.equalsIgnoreCase("creator") || name.equalsIgnoreCase("author")
|| name.equalsIgnoreCase("dc.creator"))
{
trimPut(ContentModel.PROP_AUTHOR, valueO, tempDestination);
}
if (name.equalsIgnoreCase("description") || name.equalsIgnoreCase("dc.description"))
{
trimPut(ContentModel.PROP_DESCRIPTION, valueO, tempDestination);
}
}
}
public void handleError(String errorMsg, int pos)
{
}
};
String charsetGuess = "UTF-8";
int tries = 0;
while (tries < 3)
{
throw new ContentIOException("HTML metadata extraction failed: \n" + " reader: " + reader, e);
tempDestination.clear();
Reader r = null;
InputStream cis = null;
try
{
cis = reader.getContentInputStream();
// TODO: for now, use default charset; we should attempt to map from html meta-data
r = new InputStreamReader(cis);
HTMLEditorKit.Parser parser = new ParserDelegator();
parser.parse(r, callback, tries > 0);
destination.putAll(tempDestination);
break;
}
catch (ChangedCharSetException ccse)
{
tries++;
charsetGuess = ccse.getCharSetSpec();
int begin = charsetGuess.indexOf("charset=");
if (begin > 0)
charsetGuess = charsetGuess.substring(begin + 8, charsetGuess.length());
reader = reader.getReader();
}
finally
{
if (r != null)
r.close();
if (cis != null)
cis.close();
}
}
}
}