andygrove commented on code in PR #2000:
URL: https://github.com/apache/datafusion-comet/pull/2000#discussion_r2197933479
##########
common/src/main/java/org/apache/comet/parquet/Utils.java:
##########
@@ -290,15 +290,137 @@ public static ColumnDescriptor
buildColumnDescriptor(ParquetColumnSpec columnSpe
}
String name = columnSpec.getPath()[columnSpec.getPath().length - 1];
+ // Reconstruct the logical type from parameters
+ LogicalTypeAnnotation logicalType = null;
+ if (columnSpec.getLogicalTypeName() != null) {
+ logicalType =
+ reconstructLogicalType(
+ columnSpec.getLogicalTypeName(),
columnSpec.getLogicalTypeParams());
+ }
PrimitiveType primitiveType;
if (primType == PrimitiveType.PrimitiveTypeName.FIXED_LEN_BYTE_ARRAY) {
- primitiveType = new PrimitiveType(repetition, primType,
columnSpec.getTypeLength(), name);
+ primitiveType =
+ Types.primitive(primType, repetition)
+ .length(columnSpec.getTypeLength())
+ .as(logicalType)
+ .id(columnSpec.getFieldId())
+ .named(name);
} else {
- primitiveType = new PrimitiveType(repetition, primType, name);
+ primitiveType =
+ Types.primitive(primType, repetition)
+ .as(logicalType)
+ .id(columnSpec.getFieldId())
+ .named(name);
}
- MessageType schema = new MessageType("root", primitiveType);
- return schema.getColumnDescription(columnSpec.getPath());
+ return new ColumnDescriptor(
+ columnSpec.getPath(),
+ primitiveType,
+ columnSpec.getMaxRepetitionLevel(),
+ columnSpec.getMaxDefinitionLevel());
+ }
+
+ private static LogicalTypeAnnotation reconstructLogicalType(
+ String logicalTypeName, java.util.Map<String, String> params) {
+
+ switch (logicalTypeName) {
+ // MAP
+ case "MapLogicalTypeAnnotation":
+ return LogicalTypeAnnotation.mapType();
+
+ // LIST
+ case "ListLogicalTypeAnnotation":
+ return LogicalTypeAnnotation.listType();
+
+ // STRING
+ case "StringLogicalTypeAnnotation":
+ return LogicalTypeAnnotation.stringType();
+
+ // MAP_KEY_VALUE
+ case "MapKeyValueLogicalTypeAnnotation":
+ return LogicalTypeAnnotation.MapKeyValueTypeAnnotation.getInstance();
+
+ // ENUM
+ case "EnumLogicalTypeAnnotation":
+ return LogicalTypeAnnotation.enumType();
+
+ // DECIMAL
+ case "DecimalLogicalTypeAnnotation":
+ int scale = Integer.parseInt(params.get("scale"));
Review Comment:
Should we add error handling to return a helpful error if these keys do not
exist, rather than fail with NPE?
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
