KurtYoung commented on a change in pull request #9994: [FLINK-14322][table-api]
Add watermark information in TableSchema
URL: https://github.com/apache/flink/pull/9994#discussion_r340463970
##########
File path:
flink-table/flink-table-common/src/main/java/org/apache/flink/table/api/TableSchema.java
##########
@@ -54,44 +58,70 @@
private final DataType[] fieldDataTypes;
- private final Map<String, Integer> fieldNameToIndex;
+ /** Mapping from qualified field name to (nested) field type. */
+ private final Map<String, DataType> typesByName;
- private TableSchema(String[] fieldNames, DataType[] fieldDataTypes) {
+ private final List<WatermarkSpec> watermarkSpecs;
+
+ private TableSchema(String[] fieldNames, DataType[] fieldDataTypes,
List<WatermarkSpec> watermarkSpecs) {
this.fieldNames = Preconditions.checkNotNull(fieldNames);
this.fieldDataTypes =
Preconditions.checkNotNull(fieldDataTypes);
+ this.watermarkSpecs =
Preconditions.checkNotNull(watermarkSpecs);
if (fieldNames.length != fieldDataTypes.length) {
- throw new TableException(
+ throw new ValidationException(
"Number of field names and field data types
must be equal.\n" +
"Number of names is " +
fieldNames.length + ", number of data types is " + fieldDataTypes.length +
".\n" +
"List of field names: " +
Arrays.toString(fieldNames) + "\n" +
"List of field data types: " +
Arrays.toString(fieldDataTypes));
}
- // validate and create name to index mapping
- fieldNameToIndex = new HashMap<>();
- final Set<String> duplicateNames = new HashSet<>();
- final Set<String> uniqueNames = new HashSet<>();
+ // validate and create name to type mapping
+ typesByName = new HashMap<>();
for (int i = 0; i < fieldNames.length; i++) {
// check for null
- Preconditions.checkNotNull(fieldDataTypes[i]);
- final String fieldName =
Preconditions.checkNotNull(fieldNames[i]);
-
- // collect indices
- fieldNameToIndex.put(fieldName, i);
+ DataType fieldType =
Preconditions.checkNotNull(fieldDataTypes[i]);
+ String fieldName =
Preconditions.checkNotNull(fieldNames[i]);
+ validateAndCreateNameTypeMapping(fieldName, fieldType,
Collections.emptyList());
+ }
- // check uniqueness of field names
- if (uniqueNames.contains(fieldName)) {
- duplicateNames.add(fieldName);
- } else {
- uniqueNames.add(fieldName);
+ // validate watermark and rowtime attribute
+ Preconditions.checkState(
+ watermarkSpecs.size() <= 1,
+ "Multiple watermark definition is not supported yet.");
+ for (WatermarkSpec watermark : watermarkSpecs) {
+ String rowtimeAttribute =
watermark.getRowtimeAttribute();
+ DataType rowtimeType =
getFieldDataType(rowtimeAttribute)
+ .orElseThrow(() -> new
ValidationException(String.format(
+ "Rowtime attribute '%s' is not defined
in schema.", rowtimeAttribute)));
+ if (rowtimeType.getLogicalType().getTypeRoot() !=
TIMESTAMP_WITHOUT_TIME_ZONE) {
+ throw new ValidationException(String.format(
+ "Rowtime attribute '%s' must be of type
TIMESTAMP but is of type '%s'.",
+ rowtimeAttribute, rowtimeType));
+ }
+ LogicalType watermarkOutputType =
watermark.getWatermarkStrategy()
+ .getOutputDataType().getLogicalType();
+ if (watermarkOutputType.getTypeRoot() !=
TIMESTAMP_WITHOUT_TIME_ZONE &&
+ watermarkOutputType.getTypeRoot() != BIGINT) {
Review comment:
why relaxing BIGINT?
----------------------------------------------------------------
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
With regards,
Apache Git Services
