ihuzenko commented on a change in pull request #1829: DRILL-7096: Develop
vector for canonical Map<K,V>
URL: https://github.com/apache/drill/pull/1829#discussion_r318078722
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/ParquetTableMetadataUtils.java
##########
@@ -573,19 +585,30 @@ public static OriginalType
getOriginalType(MetadataBase.ParquetTableMetadataBase
for (MetadataBase.ParquetFileMetadata file :
parquetTableMetadata.getFiles()) {
// row groups in the file have the same schema, so using the first one
Map<SchemaPath, TypeProtos.MajorType> fileColumns =
getFileFields(parquetTableMetadata, file);
- fileColumns.forEach((columnPath, type) -> {
- TypeProtos.MajorType majorType = columns.get(columnPath);
- if (majorType == null) {
- columns.put(columnPath, type);
- } else {
- TypeProtos.MinorType leastRestrictiveType =
TypeCastRules.getLeastRestrictiveType(Arrays.asList(majorType.getMinorType(),
type.getMinorType()));
- if (leastRestrictiveType != majorType.getMinorType()) {
- columns.put(columnPath, type);
- }
- }
- });
+ fileColumns.forEach((columnPath, type) -> putType(columns, columnPath,
type));
+ }
+ return columns;
+ }
+
+ static Map<SchemaPath, TypeProtos.MajorType>
resolveIntermediateFields(MetadataBase.ParquetTableMetadataBase
parquetTableMetadata) {
+ LinkedHashMap<SchemaPath, TypeProtos.MajorType> columns = new
LinkedHashMap<>();
+ for (MetadataBase.ParquetFileMetadata file :
parquetTableMetadata.getFiles()) {
+ // row groups in the file have the same schema, so using the first one
+ Map<SchemaPath, TypeProtos.MajorType> fileColumns =
getIntermediateFields(parquetTableMetadata,
file.getRowGroups().iterator().next());
+ fileColumns.forEach((columnPath, type) -> putType(columns, columnPath,
type));
}
return columns;
}
+ static void putType(Map<SchemaPath, TypeProtos.MajorType> columns,
SchemaPath columnPath, TypeProtos.MajorType type) {
Review comment:
Please make it private, add javadoc and reuse it inside
```getIntermediateFields``` method
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
