Revision: 18437
http://sourceforge.net/p/gate/code/18437
Author: ian_roberts
Date: 2014-11-06 19:10:57 +0000 (Thu, 06 Nov 2014)
Log Message:
-----------
Skip unparseable documents.
Modified Paths:
--------------
gcp/trunk/src/gate/cloud/io/json/JSONStreamingInputHandler.java
Modified: gcp/trunk/src/gate/cloud/io/json/JSONStreamingInputHandler.java
===================================================================
--- gcp/trunk/src/gate/cloud/io/json/JSONStreamingInputHandler.java
2014-11-06 19:03:45 UTC (rev 18436)
+++ gcp/trunk/src/gate/cloud/io/json/JSONStreamingInputHandler.java
2014-11-06 19:10:57 UTC (rev 18437)
@@ -20,6 +20,8 @@
import gate.Document;
import gate.Factory;
import gate.FeatureMap;
+import gate.GateConstants;
+import gate.Utils;
import gate.cloud.batch.Batch;
import gate.cloud.batch.DocumentID;
import gate.cloud.io.DocumentData;
@@ -275,10 +277,16 @@
if(mimeType != null) {
docParams.put(Document.DOCUMENT_MIME_TYPE_PARAMETER_NAME, mimeType);
}
- Document gateDoc =
- (Document)Factory.createResource("gate.corpora.DocumentImpl",
- docParams, Factory.newFeatureMap(), id);
- return new DocumentData(gateDoc, docId);
+ try {
+ Document gateDoc =
+ (Document)Factory.createResource("gate.corpora.DocumentImpl",
+ docParams, Utils.featureMap(
+ GateConstants.THROWEX_FORMAT_PROPERTY_NAME,
Boolean.TRUE),
+ id);
+ return new DocumentData(gateDoc, docId);
+ } catch(Exception e) {
+ logger.warn("Error encountered while parsing object with ID " + id +
" - skipped", e);
+ }
}
}
return null;
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs