vdiravka commented on a change in pull request #1466: DRILL-6381: Add support 
for index based planning and execution
URL: https://github.com/apache/drill/pull/1466#discussion_r223651337
 
 

 ##########
 File path: 
contrib/format-maprdb/src/main/java/org/apache/drill/exec/store/mapr/db/json/JsonTableGroupScan.java
 ##########
 @@ -179,16 +295,126 @@ public MapRDBSubScan getSpecificScan(int 
minorFragmentId) {
     assert minorFragmentId < endpointFragmentMapping.size() : String.format(
         "Mappings length [%d] should be greater than minor fragment id [%d] 
but it isn't.", endpointFragmentMapping.size(),
         minorFragmentId);
-    return new MapRDBSubScan(getUserName(), formatPlugin, 
endpointFragmentMapping.get(minorFragmentId), columns, TABLE_JSON);
+    return new MapRDBSubScan(getUserName(), formatPlugin, 
endpointFragmentMapping.get(minorFragmentId), columns, maxRecordsToRead, 
TABLE_JSON);
   }
 
   @Override
   public ScanStats getScanStats() {
-    //TODO: look at stats for this.
-    long rowCount = (long) ((scanSpec.getSerializedFilter() != null ? .5 : 1) 
* totalRowCount);
-    int avgColumnSize = 10;
-    int numColumns = (columns == null || columns.isEmpty()) ? 100 : 
columns.size();
-    return new ScanStats(GroupScanProperty.NO_EXACT_ROW_COUNT, rowCount, 1, 
avgColumnSize * numColumns * rowCount);
+    if (isIndexScan()) {
+      return indexScanStats();
+    }
+    return fullTableScanStats();
+  }
+
+  private ScanStats fullTableScanStats() {
+    PluginCost pluginCostModel = formatPlugin.getPluginCostModel();
+    final int avgColumnSize = pluginCostModel.getAverageColumnSize(this);
+    final int numColumns = (columns == null || columns.isEmpty()) ? STAR_COLS 
: columns.size();
+    // index will be NULL for FTS
+    double rowCount = stats.getRowCount(scanSpec.getCondition(), null);
+    // rowcount based on _id predicate. If NO _id predicate present in 
condition, then the
+    // rowcount should be same as totalRowCount. Equality b/w the two 
rowcounts should not be
+    // construed as NO _id predicate since stats are approximate.
+    double leadingRowCount = stats.getLeadingRowCount(scanSpec.getCondition(), 
null);
+    double avgRowSize = stats.getAvgRowSize(null, true);
+    double totalRowCount = stats.getRowCount(null, null);
+    logger.debug("GroupScan {} with stats {}: rowCount={}, condition={}, 
totalRowCount={}, fullTableRowCount={}",
+            System.identityHashCode(this), System.identityHashCode(stats), 
rowCount,
+            scanSpec.getCondition()==null?"null":scanSpec.getCondition(),
 
 Review comment:
   formatting

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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