arekusuri commented on a change in pull request #2722: GOBBLIN-865: Add feature 
that enables PK-chunking in partition
URL: https://github.com/apache/incubator-gobblin/pull/2722#discussion_r325803379
 
 

 ##########
 File path: 
gobblin-salesforce/src/main/java/org/apache/gobblin/salesforce/SalesforceExtractor.java
 ##########
 @@ -144,28 +142,18 @@
   private final boolean pkChunkingSkipCountCheck;
   private final boolean bulkApiUseQueryAll;
 
+  private WorkUnitState workUnitState;
+
   public SalesforceExtractor(WorkUnitState state) {
     super(state);
-    this.sfConnector = (SalesforceConnector) this.connector;
-
-    // don't allow pk chunking if max partitions too high or have user 
specified partitions
-    if (state.getPropAsBoolean(Partitioner.HAS_USER_SPECIFIED_PARTITIONS, 
false)
-        || 
state.getPropAsInt(ConfigurationKeys.SOURCE_MAX_NUMBER_OF_PARTITIONS,
-        ConfigurationKeys.DEFAULT_MAX_NUMBER_OF_PARTITIONS) > 
PK_CHUNKING_MAX_PARTITIONS_LIMIT) {
-      if (state.getPropAsBoolean(ENABLE_PK_CHUNKING_KEY, false)) {
-        log.warn("Max partitions too high, so PK chunking is not enabled");
-      }
-
-      this.pkChunking = false;
-    } else {
-      this.pkChunking = state.getPropAsBoolean(ENABLE_PK_CHUNKING_KEY, false);
-    }
+    this.workUnitState = state;
 
+    this.sfConnector = (SalesforceConnector) this.connector;
     this.pkChunkingSize =
         Math.max(MIN_PK_CHUNKING_SIZE,
-            Math.min(MAX_PK_CHUNKING_SIZE, 
state.getPropAsInt(PK_CHUNKING_SIZE_KEY, DEFAULT_PK_CHUNKING_SIZE)));
+            Math.min(MAX_PK_CHUNKING_SIZE, 
state.getPropAsInt(PARTITION_PK_CHUNKING_SIZE, DEFAULT_PK_CHUNKING_SIZE)));
 
-    this.pkChunkingSkipCountCheck = 
state.getPropAsBoolean(PK_CHUNKING_SKIP_COUNT_CHECK, 
DEFAULT_PK_CHUNKING_SKIP_COUNT_CHECK);
+    this.pkChunkingSkipCountCheck = true;// won't be able to get count
 
 Review comment:
   removed. thanks!

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to