difin commented on code in PR #5529:
URL: https://github.com/apache/hive/pull/5529#discussion_r1860831983


##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/IcebergTableUtil.java:
##########
@@ -458,6 +458,52 @@ public static List<DeleteFile> getDeleteFiles(Table table, 
String partitionPath)
         t -> ((PositionDeletesScanTask) t).file()));
   }
 
+  public static float getFileSizeRatio(Table table, String partitionPath, long 
fileSizeInBytesThreshold) {
+    long uncompactedFilesCount = getDataFileCount(table, partitionPath, 
fileSizeInBytesThreshold, true);
+    long compactedFilesCount = getDataFileCount(table, partitionPath, 
fileSizeInBytesThreshold, false);
+
+    if (uncompactedFilesCount == 0) {
+      return 0;
+    } else if (compactedFilesCount == 0) {
+      return 1;
+    } else {
+      return uncompactedFilesCount * 1.0f / (uncompactedFilesCount + 
compactedFilesCount);
+    }
+  }
+
+  private static long getDataFileCount(Table table, String partitionPath, long 
fileSizeInBytesThreshold,
+      boolean isLess) {
+    CloseableIterable<FileScanTask> fileScanTasks =
+        
table.newScan().useSnapshot(table.currentSnapshot().snapshotId()).ignoreResiduals().planFiles();
+    CloseableIterable<FileScanTask> filteredFileScanTasks =
+        CloseableIterable.filter(fileScanTasks, t -> {
+          DataFile file = t.asFileScanTask().file();
+          return (!table.spec().isPartitioned() ||
+              partitionPath == null && file.specId() != table.spec().specId() 
||
+              partitionPath != null &&
+                  
table.specs().get(file.specId()).partitionToPath(file.partition()).equals(partitionPath))
 &&
+              (isLess ? file.fileSizeInBytes() < fileSizeInBytesThreshold :
+                  file.fileSizeInBytes() >= fileSizeInBytesThreshold);
+        });
+    return Lists.newArrayList(filteredFileScanTasks).size();
+  }
+
+  public static long countDeleteRecords(Table table, String partitionPath) {
+    Table deletesTable =
+        MetadataTableUtils.createMetadataTableInstance(table, 
MetadataTableType.POSITION_DELETES);
+    CloseableIterable<ScanTask> deletesScanTasks = 
deletesTable.newBatchScan().planFiles();
+    CloseableIterable<ScanTask> filteredDeletesScanTasks =
+        CloseableIterable.filter(deletesScanTasks, t -> {
+          DeleteFile file = ((PositionDeletesScanTask) t).file();
+          return !table.spec().isPartitioned() ||

Review Comment:
   Hi @deniskuzZ, can you please provide your view on this topic, should we add 
parenthesis here or not?
   Currently it follows the recommendation from this review comment:
   https://github.com/apache/hive/pull/5389#discussion_r1711415417



-- 
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.

To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For additional commands, e-mail: gitbox-h...@hive.apache.org

Reply via email to