inteligr8/alfresco-community-repo
1
0
Fork 0
mirror of https://github.com/Alfresco/alfresco-community-repo.git synced 2025-07-31 17:39:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merged DEV/SWIFT to HEAD (FTP Tests, Tika and Poi)

Browse Source 
26059: ALF-5900 - IMAP creates winmail.dat in attachment folder (Add support for Microsoft Transport Neutral Encapsulation Format.)
          - added attachment extraction for TNEF documents - goodbye winmail.dat !
   26063: javadoc for imap.
   26088: ALF-7408 - addition of commons-net for ftp client library.
          First test of end to end ftp.   Just a simple test of connection now, will be followed by more detailed tests.
   26176: ALF-7408 - FTP tests + disabled failing test case for ALF-7618
   26180: ALF-7618 - correction of unit test error.
   26188: ALF-7618 - added a test of paths
   26229: Added back simple '\~.*' pattern
   26288: ALF-7676 - Test to stress different user rights.
          - FTPServerTest.testTwoUserUpdate added for the FTP server.
   26304: Corrected spelling name in private class.
   26408: addming minimal package infos.
   26416: ALF-5082 / ALF-2183 / ALF-4448 - When guessing the mimetype for a file, add the option to supply a ContentReader to enhance the accuracy.
          Enable this for a few key places that do mimetype guessing,
          which should avoid issues for files with the wrong extension (either renamed accidently, or for .TMP)
   26433: Re-order the mimetype guess step to ensure that the Content Reader is always valid
   26440: Added another test for word 2003 save as.
   26441: Test resource for ContentDiskDriver
   26446: ALF-5082 - Back out a FileFolderService change to mimetype guessing, which had broken things, pending a better way to do it with ContentWriter
   26490: Small change for ContentDiskDriverTes.fileExists.  Leaky transaction causing problems in automated build.
   26497: ContentDiskDriver - commented out two of the problematic leaky transaction tests.
   26503: Add new interface methods + documentation for asking a ContentWriter to guess the mimetype and encoding for you.
          (Code will be migrated from places that currently do this themselves later)
   26504: Add an extension interface in the DataModel project for some of the extra ContentReader methods that FileContentReader provides
   26505: When ContentWriter.putContent(String) is called with no encoding specified, record what the system default encoding was that was used.
          (Prevents issues if the system default is ever changed)
   26509: When calling Tika to do file detection, if we have a file based reader then give Tika the File rather than an InputStream
   26522: More debug logging while debugging ALF-5260
   26546: Have one copy of the Tika Config in spring, rather than several places fetching their own copy of the default one (either explicitly or implicitly).
   26522: More debug logging while diagnosing ALF-5260
   26548: Add another mimetype check - ensures that truncated/corrup container files which can't be fully processed can still get the container type without failure
   26549: Implement the mimetype and encoding guessers on ContentWriter (either immediately or as a listener, as required), and update FileFolderServer to make use of this (+test this)
   26553: Replace explicit mimetype and encoding guess calls with ContentWriter requests to have the work done
   26554: Replace explicit mimetype and encoding guess calls with ContentWriter requests to have the work done
   26579: Switch the transformer to use Tika

git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@28224 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
Derek Hulley
2011-06-07 07:36:37 +00:00
parent 04aef409a8
commit e118211bd3
50 changed files with 2269 additions and 365 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
source/java/org/alfresco/repo/content/AbstractContentWriter.java
View File

@@ -29,16 +29,19 @@ import java.nio.channels.Channels;
import java.nio.channels.FileChannel;
import java.nio.channels.ReadableByteChannel;
import java.nio.channels.WritableByteChannel;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.List;
import org.alfresco.error.AlfrescoRuntimeException;
import org.alfresco.repo.content.encoding.ContentCharsetFinder;
import org.alfresco.repo.content.filestore.FileContentWriter;
import org.alfresco.service.cmr.repository.ContentAccessor;
import org.alfresco.service.cmr.repository.ContentIOException;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.ContentStreamListener;
import org.alfresco.service.cmr.repository.ContentWriter;
import org.alfresco.service.cmr.repository.MimetypeService;
import org.alfresco.util.TempFileProvider;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
@@ -62,6 +65,8 @@ public abstract class AbstractContentWriter extends AbstractContentAccessor impl
private List<ContentStreamListener> listeners;
private WritableByteChannel channel;
private ContentReader existingContentReader;
private MimetypeService mimetypeService;
private DoGuessingOnCloseListener guessingOnCloseListener;
/**
* @param contentUrl the content URL
@@ -73,6 +78,21 @@ public abstract class AbstractContentWriter extends AbstractContentAccessor impl
this.existingContentReader = existingContentReader;
listeners = new ArrayList<ContentStreamListener>(2);
// We always register our own listener as the first one
// This allows us to perform any guessing (if needed) before
// the normal listeners kick in and eg write things to the DB
guessingOnCloseListener = new DoGuessingOnCloseListener();
listeners.add(guessingOnCloseListener);
}
/**
* Supplies the Mimetype Service to be used when guessing
* encoding and mimetype information.
*/
public void setMimetypeService(MimetypeService mimetypeService)
{
this.mimetypeService = mimetypeService;
}
/**
@@ -454,7 +474,19 @@ public abstract class AbstractContentWriter extends AbstractContentAccessor impl
{
// attempt to use the correct encoding
String encoding = getEncoding();
byte[] bytes = (encoding == null) ? content.getBytes() : content.getBytes(encoding);
byte[] bytes;
if(encoding == null)
{
// Use the system default, and record what that was
bytes = content.getBytes();
setEncoding( System.getProperty("file.encoding") );
}
else
{
// Use the encoding that they specified
bytes = content.getBytes(encoding);
}
// get the stream
OutputStream os = getContentOutputStream();
ByteArrayInputStream is = new ByteArrayInputStream(bytes);
@@ -469,4 +501,108 @@ public abstract class AbstractContentWriter extends AbstractContentAccessor impl
e);
}
}
/**
* When the content has been written, attempt to guess
* the encoding of it.
*
* @see ContentWriter#guessEncoding()
*/
public void guessEncoding()
{
if (mimetypeService == null)
{
logger.warn("MimetypeService not supplied, but required for content guessing");
return;
}
if(isClosed())
{
// Content written, can do it now
doGuessEncoding();
}
else
{
// Content not yet written, wait for the
// data to be written before doing so
guessingOnCloseListener.guessEncoding = true;
}
}
private void doGuessEncoding()
{
ContentCharsetFinder charsetFinder = mimetypeService.getContentCharsetFinder();
ContentReader reader = getReader();
InputStream is = reader.getContentInputStream();
Charset charset = charsetFinder.getCharset(is, getMimetype());
try
{
is.close();
}
catch(IOException e)
{}
setEncoding(charset.name());
}
/**
* When the content has been written, attempt to guess
* the mimetype of it, using the filename and contents.
*
* @see ContentWriter#guessMimetype(String)
*/
public void guessMimetype(String filename)
{
if (mimetypeService == null)
{
logger.warn("MimetypeService not supplied, but required for content guessing");
return;
}
if(isClosed())
{
// Content written, can do it now
doGuessMimetype(filename);
}
else
{
// Content not yet written, wait for the
// data to be written before doing so
guessingOnCloseListener.guessMimetype = true;
guessingOnCloseListener.filename = filename;
}
}
private void doGuessMimetype(String filename)
{
String mimetype = mimetypeService.guessMimetype(
filename, getReader()
);
setMimetype(mimetype);
}
/**
* Our own listener that is always the first on the list,
* which lets us perform guessing operations when the
* content has been written.
*/
private class DoGuessingOnCloseListener implements ContentStreamListener
{
private boolean guessEncoding = false;
private boolean guessMimetype = false;
private String filename = null;
@Override
public void contentStreamClosed() throws ContentIOException
{
if(guessMimetype)
{
doGuessMimetype(filename);
}
if(guessEncoding)
{
doGuessEncoding();
}
}
}
}