[HUDI-1357] Added a check to validate records are not lost during merges. (#2216)

- Turned off by default

hudi-common/src/main/java/org/apache/hudi/common/util/ParquetUtils.java

@@ -39,6 +39,7 @@ import org.apache.parquet.avro.AvroReadSupport;
 import org.apache.parquet.avro.AvroSchemaConverter;
 import org.apache.parquet.hadoop.ParquetFileReader;
 import org.apache.parquet.hadoop.ParquetReader;
+import org.apache.parquet.hadoop.metadata.BlockMetaData;
 import org.apache.parquet.hadoop.metadata.ParquetMetadata;
 import org.apache.parquet.schema.MessageType;
 
@@ -261,6 +262,22 @@ public class ParquetUtils {
     return records;
   }
 
+  /**
+   * Returns the number of records in the parquet file.
+   *
+   * @param conf Configuration
+   * @param parquetFilePath path of the file
+   */
+  public static long getRowCount(Configuration conf, Path parquetFilePath) {
+    ParquetMetadata footer;
+    long rowCount = 0;
+    footer = readMetadata(conf, parquetFilePath);
+    for (BlockMetaData b : footer.getBlocks()) {
+      rowCount += b.getRowCount();
+    }
+    return rowCount;
+  }
+
   static class RecordKeysFilterFunction implements Function<String, Boolean> {
 
     private final Set<String> candidateKeys;

hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieParquetReader.java

@@ -74,7 +74,6 @@ public class HoodieParquetReader<R extends IndexedRecord> implements HoodieFileR
 
   @Override
   public long getTotalRecords() {
-    // TODO Auto-generated method stub
-    return 0;
+    return ParquetUtils.getRowCount(conf, path);
   }
 }