mcvsubbu commented on a change in pull request #6009:
URL: https://github.com/apache/incubator-pinot/pull/6009#discussion_r488078457
##########
File path:
pinot-plugins/pinot-input-format/pinot-avro-base/src/main/java/org/apache/pinot/plugin/inputformat/avro/AvroIngestionSchemaValidator.java
##########
@@ -111,36 +112,56 @@ private void validateSchemas() {
}
}
if (nonNullSchema != null) {
+ avroColumnSchema = nonNullSchema;
avroColumnType = nonNullSchema.getType();
}
}
- if
(!fieldSpec.getDataType().name().equalsIgnoreCase(avroColumnType.toString())) {
- _dataTypeMismatch.addMismatchReason(String
- .format("The Pinot column: (%s: %s) doesn't match with the column
(%s: %s) in input %s schema.", columnName,
- fieldSpec.getDataType().name(), avroColumnSchema.getName(),
avroColumnType.toString(),
- getInputSchemaType()));
- }
-
if (fieldSpec.isSingleValueField()) {
+ // check data type mismatch
+ if
(!fieldSpec.getDataType().name().equalsIgnoreCase(avroColumnType.toString())) {
+ getDataTypeMismatchResult().addMismatchReason(String
+ .format("The Pinot column: (%s: %s) doesn't match with the
column (%s: %s) in input %s schema.", columnName,
+ fieldSpec.getDataType().name(), avroColumnName,
avroColumnType.toString(),
+ getInputSchemaType()));
+ }
+ // check single-value multi-value mismatch
if (avroColumnType.ordinal() <
org.apache.avro.Schema.Type.STRING.ordinal()) {
// the column is a complex structure
- _singleValueMultiValueFieldMismatch.addMismatchReason(String.format(
- "The Pinot column: %s is 'single-value' column but the column:
%s from input %s is 'multi-value' column.",
- columnName, avroColumnSchema.getName(), getInputSchemaType()));
+
getSingleValueMultiValueFieldMismatchResult().addMismatchReason(String
+ .format(
+ "The Pinot column: %s is 'single-value' column but the
column: %s from input %s is 'multi-value' column.",
+ columnName, avroColumnName, getInputSchemaType()));
}
} else {
+ // check data type mismatch
+ FieldSpec.DataType dataTypeForMVColumn =
AvroUtils.extractFieldDataType(avroColumnField);
+ if (fieldSpec.getDataType() != dataTypeForMVColumn) {
+ getDataTypeMismatchResult().addMismatchReason(String
+ .format("The Pinot column: (%s: %s) doesn't match with the
column (%s: %s) in input %s schema.",
+ columnName, fieldSpec.getDataType().name(), avroColumnName,
dataTypeForMVColumn.name(),
+ getInputSchemaType()));
+ }
+ // check single-value multi-value mismatch
if (avroColumnType.ordinal() >=
org.apache.avro.Schema.Type.STRING.ordinal()) {
// the column is a complex structure
- _singleValueMultiValueFieldMismatch.addMismatchReason(String.format(
- "The Pinot column: %s is 'multi-value' column but the column: %s
from input %s schema is 'single-value' column.",
- columnName, avroColumnSchema.getName(), getInputSchemaType()));
+
getSingleValueMultiValueFieldMismatchResult().addMismatchReason(String
Review comment:
Can you update the comment in line 134 to be clearer, or just remove the
comment, since the format string below says exactly what the mismatch is.
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org
