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

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

View File

@@ -20,10 +20,8 @@ package org.alfresco.repo.remote;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.nio.charset.Charset;
import java.util.List;
import org.alfresco.repo.content.encoding.ContentCharsetFinder;
import org.alfresco.repo.model.filefolder.FileFolderServiceImpl;
import org.alfresco.repo.security.authentication.AuthenticationUtil;
import org.alfresco.repo.transaction.RetryingTransactionHelper;
@@ -55,7 +53,6 @@ public class FileFolderRemoteServer implements FileFolderRemote
private RetryingTransactionHelper retryingTransactionHelper;
private AuthenticationService authenticationService;
private FileFolderService fileFolderService;
private MimetypeService mimetypeService;
/**
* @param transactionService provides transactional support and retrying
@@ -82,11 +79,11 @@ public class FileFolderRemoteServer implements FileFolderRemote
}
/**
* @param mimetypeService used to determine the character encoding
* @deprecated The mimetype service is no longer needed.
*/
@Deprecated
public void setMimetypeService(MimetypeService mimetypeService)
{
this.mimetypeService = mimetypeService;
}
/**
@@ -552,19 +549,15 @@ public class FileFolderRemoteServer implements FileFolderRemote
{
public ContentData execute() throws Throwable
{
// Guess the mimetype
String mimetype = mimetypeService.guessMimetype(filename);
// Get a writer
ContentWriter writer = fileFolderService.getWriter(nodeRef);
// We need the mimetype and encoding finding for us
writer.guessEncoding();
writer.guessMimetype(filename);
// Make a stream
ByteArrayInputStream is = new ByteArrayInputStream(bytes);
// Guess the encoding
ContentCharsetFinder charsetFinder = mimetypeService.getContentCharsetFinder();
Charset charset = charsetFinder.getCharset(is, mimetype);
// Set metadata
writer.setEncoding(charset.name());
writer.setMimetype(mimetype);
// Write the stream
writer.putContent(is);
@@ -606,19 +599,15 @@ public class FileFolderRemoteServer implements FileFolderRemote
for (int i = 0; i < filenames.length; i++)
{
String mimetype = mimetypeService.guessMimetype(filenames[i]);
// Get a writer
ContentWriter writer = fileFolderService.getWriter(nodeRefs[i]);
// We need the mimetype and encoding finding for us
writer.guessEncoding();
writer.guessMimetype(filenames[i]);
// Make a stream
ByteArrayInputStream is = new ByteArrayInputStream(bytes[i]);
// Guess the encoding
ContentCharsetFinder charsetFinder = mimetypeService.getContentCharsetFinder();
Charset charset = charsetFinder.getCharset(is, mimetype);
// Set metadata
writer.setEncoding(charset.name());
writer.setMimetype(mimetype);
// Write the stream
writer.putContent(is);

View File

@@ -20,13 +20,11 @@ package org.alfresco.repo.remote;
import java.io.ByteArrayInputStream;
import java.io.Serializable;
import java.nio.charset.Charset;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.alfresco.model.ContentModel;
import org.alfresco.repo.content.encoding.ContentCharsetFinder;
import org.alfresco.repo.security.authentication.AuthenticationUtil;
import org.alfresco.repo.transaction.RetryingTransactionHelper;
import org.alfresco.repo.transaction.RetryingTransactionHelper.RetryingTransactionCallback;
@@ -71,7 +69,6 @@ public class LoaderRemoteServer implements LoaderRemote
private NodeService nodeService;
private FileFolderService fileFolderService;
private FileFolderRemote fileFolderRemote;
private MimetypeService mimetypeService;
private CheckOutCheckInService checkOutCheckInService;
/**
@@ -112,11 +109,11 @@ public class LoaderRemoteServer implements LoaderRemote
}
/**
* @param mimetypeService used to determine encoding, etc
* @deprecated The mimetype service is no longer needed.
*/
@Deprecated
public void setMimetypeService(MimetypeService mimetypeService)
{
this.mimetypeService = mimetypeService;
}
public void setCheckOutCheckInService(CheckOutCheckInService checkOutCheckInService)
@@ -260,18 +257,16 @@ public class LoaderRemoteServer implements LoaderRemote
results[i] = newFileInfo;
NodeRef newFileNodeRef = newFileInfo.getNodeRef();
// Guess the mimetype
String mimetype = mimetypeService.guessMimetype(filenames[i]);
// Get a writer
ContentWriter writer = fileFolderService.getWriter(newFileNodeRef);
// We need the encoding and mimetype guessing
writer.guessMimetype(filenames[i]);
writer.guessEncoding();
// Make a stream
ByteArrayInputStream is = new ByteArrayInputStream(bytes[i]);
// Guess the encoding
ContentCharsetFinder charsetFinder = mimetypeService.getContentCharsetFinder();
Charset charset = charsetFinder.getCharset(is, mimetype);
// Set metadata
writer.setEncoding(charset.name());
writer.setMimetype(mimetype);
// Write the stream
writer.putContent(is);
}