arina-ielchiieva commented on a change in pull request #1370: DRILL-5797: Use Parquet new reader in all non-complex column queries URL: https://github.com/apache/drill/pull/1370#discussion_r201677035
########## File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/ParquetReaderUtility.java ########## @@ -525,4 +599,57 @@ public static long getDateTimeValueFromBinary(Binary binaryTimeStampValue, boole } } + /** + * Check whether any of columns in the given list is either nested or repetitive. + * + * @param footer Parquet file schema + * @param columns list of query SchemaPath objects + */ + public static boolean containsComplexColumn(ParquetMetadata footer, List<SchemaPath> columns) { + + MessageType schema = footer.getFileMetaData().getSchema(); + + if (Utilities.isStarQuery(columns)) { + for (Type type : schema.getFields()) { + if (!type.isPrimitive()) { + return true; + } + } + for (ColumnDescriptor col : schema.getColumns()) { + if (col.getMaxRepetitionLevel() > 0) { + return true; + } + } + return false; + } else { + Map<String, ColumnDescriptor> colDescMap = ParquetReaderUtility.getColNameToColumnDescriptorMapping(footer); + Map<String, SchemaElement> schemaElements = ParquetReaderUtility.getColNameToSchemaElementMapping(footer); + + for (SchemaPath schemaPath : columns) { + // Schema path which is non-leaf is complex column + if (!schemaPath.isLeaf()) { + logger.debug("rowGroupScan contains complex column: {}", schemaPath.getUnIndexed().toString()); Review comment: trace? ---------------------------------------------------------------- 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