Author: kwright
Date: Wed Jul 16 13:18:31 2014
New Revision: 1610996
URL: http://svn.apache.org/r1610996
Log:
Fix for CONNECTORS-995.
Modified:
manifoldcf/trunk/CHANGES.txt
manifoldcf/trunk/connectors/filesystem/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/filesystem/FileConnector.java
manifoldcf/trunk/connectors/hdfs/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/hdfs/HDFSRepositoryConnector.java
manifoldcf/trunk/connectors/livelink/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/livelink/LivelinkConnector.java
manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SharePointRepository.java
Modified: manifoldcf/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/CHANGES.txt?rev=1610996&r1=1610995&r2=1610996&view=diff
==============================================================================
--- manifoldcf/trunk/CHANGES.txt (original)
+++ manifoldcf/trunk/CHANGES.txt Wed Jul 16 13:18:31 2014
@@ -3,6 +3,11 @@ $Id$
======================= 1.7-dev =====================
+CONNECTORS-995: Connectors dealing with non-indexable documents
+such as directories should call noDocument() on those documents if they
+want incremental behavior.
+(Karl Wright)
+
CONNECTORS-993: Pipeline code not handling "no document" case properly.
This problem was an oversight of the new pipeline code. Essentially,
transformation connectors could choose not to send a document onward
Modified:
manifoldcf/trunk/connectors/filesystem/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/filesystem/FileConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/filesystem/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/filesystem/FileConnector.java?rev=1610996&r1=1610995&r2=1610996&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/filesystem/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/filesystem/FileConnector.java
(original)
+++
manifoldcf/trunk/connectors/filesystem/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/filesystem/FileConnector.java
Wed Jul 16 13:18:31 2014
@@ -289,6 +289,7 @@ public class FileConnector extends org.a
{
if (file.isDirectory())
{
+ activities.noDocument(documentIdentifier,version);
// Queue up stuff for directory
long startTime = System.currentTimeMillis();
String errorCode = "OK";
Modified:
manifoldcf/trunk/connectors/hdfs/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/hdfs/HDFSRepositoryConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/hdfs/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/hdfs/HDFSRepositoryConnector.java?rev=1610996&r1=1610995&r2=1610996&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/hdfs/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/hdfs/HDFSRepositoryConnector.java
(original)
+++
manifoldcf/trunk/connectors/hdfs/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/hdfs/HDFSRepositoryConnector.java
Wed Jul 16 13:18:31 2014
@@ -414,6 +414,7 @@ public class HDFSRepositoryConnector ext
}
if (fileStatus.isDirectory()) {
+ activities.noDocument(documentIdentifier,version);
/*
* Queue up stuff for directory
*/
Modified:
manifoldcf/trunk/connectors/livelink/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/livelink/LivelinkConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/livelink/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/livelink/LivelinkConnector.java?rev=1610996&r1=1610995&r2=1610996&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/livelink/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/livelink/LivelinkConnector.java
(original)
+++
manifoldcf/trunk/connectors/livelink/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/livelink/LivelinkConnector.java
Wed Jul 16 13:18:31 2014
@@ -1450,7 +1450,10 @@ public class LivelinkConnector extends o
{
// Since each livelink access is time-consuming, be sure that we abort
if the job has gone inactive
activities.checkJobStillActive();
+
String documentIdentifier = documentIdentifiers[i];
+ String version = versions[i];
+
boolean doScanOnly = scanOnly[i];
boolean isFolder = documentIdentifier.startsWith("F");
@@ -1470,6 +1473,7 @@ public class LivelinkConnector extends o
if (isFolder)
{
+ activities.noDocument(documentIdentifier,version);
if (Logging.connectors.isDebugEnabled())
Logging.connectors.debug("Livelink: Processing folder
"+Integer.toString(vol)+":"+Integer.toString(objID));
@@ -1579,7 +1583,7 @@ public class LivelinkConnector extends o
Logging.connectors.debug("Livelink: Decided to ingest document
"+Integer.toString(vol)+":"+Integer.toString(objID));
// Grab the access tokens for this file from the version string,
inside ingest method.
-
ingestFromLiveLink(llc,documentIdentifiers[i],versions[i],activities,desc,sDesc);
+
ingestFromLiveLink(llc,documentIdentifiers[i],version,activities,desc,sDesc);
}
else
{
Modified:
manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SharePointRepository.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SharePointRepository.java?rev=1610996&r1=1610995&r2=1610996&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SharePointRepository.java
(original)
+++
manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SharePointRepository.java
Wed Jul 16 13:18:31 2014
@@ -1266,6 +1266,8 @@ public class SharePointRepository extend
// === List style identifier ===
if (dListSeparatorIndex == documentIdentifier.length() - 3)
{
+ activities.noDocument(documentIdentifier,version);
+
String siteListPath =
documentIdentifier.substring(0,documentIdentifier.length()-3);
int listCutoff = siteListPath.lastIndexOf( "/" );
String site = siteListPath.substring(0,listCutoff);
@@ -1608,6 +1610,8 @@ public class SharePointRepository extend
if (dLibSeparatorIndex == documentIdentifier.length() - 2)
{
// It's a library.
+ activities.noDocument(documentIdentifier,version);
+
String siteLibPath =
documentIdentifier.substring(0,documentIdentifier.length()-2);
int libCutoff = siteLibPath.lastIndexOf( "/" );
String site = siteLibPath.substring(0,libCutoff);
@@ -1784,6 +1788,8 @@ public class SharePointRepository extend
else
{
// === Site-style identifier ===
+ activities.noDocument(documentIdentifier,version);
+
// Strip off the trailing "/" to get the site name.
String decodedSitePath =
documentIdentifier.substring(0,documentIdentifier.length()-1);