marton-bod commented on a change in pull request #2418:
URL: https://github.com/apache/hive/pull/2418#discussion_r663975175
##########
File path:
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergMetaHook.java
##########
@@ -474,6 +480,43 @@ private static PartitionSpec spec(Configuration
configuration, Schema schema, Pr
}
}
+ private void handleReplaceColumns(org.apache.hadoop.hive.metastore.api.Table
hmsTable) throws MetaException {
+ HiveSchemaUtil.SchemaDifference schemaDifference =
HiveSchemaUtil.getSchemaDiff(hmsTable.getSd().getCols(),
+ HiveSchemaUtil.convert(icebergTable.schema()), true);
+ if (!schemaDifference.isEmpty()) {
+ updateSchema = icebergTable.updateSchema();
+ } else {
+ // we should get here if the user restated the exactly the existing
columns in the REPLACE COLUMNS command
+ LOG.info("Found no difference between new and old schema for ALTER TABLE
REPLACE COLUMNS for" +
+ " table: {}. There will be no Iceberg commit.",
hmsTable.getTableName());
Review comment:
Done
##########
File path:
iceberg/iceberg-catalog/src/main/java/org/apache/iceberg/hive/HiveSchemaUtil.java
##########
@@ -138,22 +137,88 @@ public static Type convert(TypeInfo typeInfo) {
}
/**
- * Produces the difference of two FieldSchema lists by only taking into
account the field name and type.
+ * Returns a SchemaDifference containing those fields which are present in
only one of the collections, as well as
+ * those fields which are present in both (in terms of the name) but their
type or comment has changed.
* @param minuendCollection Collection of fields to subtract from
* @param subtrahendCollection Collection of fields to subtract
- * @return the result list of difference
+ * @param bothDirections Whether or not to compute the missing fields from
the minuendCollection as well
+ * @return the difference between the two schemas
*/
- public static Collection<FieldSchema> schemaDifference(
- Collection<FieldSchema> minuendCollection, Collection<FieldSchema>
subtrahendCollection) {
+ public static SchemaDifference getSchemaDiff(Collection<FieldSchema>
minuendCollection,
+ Collection<FieldSchema>
subtrahendCollection, boolean bothDirections) {
+ SchemaDifference difference = new SchemaDifference();
- Function<FieldSchema, FieldSchema> unsetCommentFunc = fs -> new
FieldSchema(fs.getName(), fs.getType(), null);
- Set<FieldSchema> subtrahendWithoutComment =
-
subtrahendCollection.stream().map(unsetCommentFunc).collect(Collectors.toSet());
+ for (FieldSchema first : minuendCollection) {
+ boolean found = false;
+ for (FieldSchema second : subtrahendCollection) {
+ if (first.getName().equals(second.getName())) {
+ found = true;
+ if (!Objects.equals(first.getType(), second.getType())) {
+ difference.typeChanged(first);
+ }
+ if (!Objects.equals(first.getComment(), second.getComment())) {
+ difference.commentChanged(first);
+ }
+ }
+ }
+ if (!found) {
+ difference.missingFromSecond(first);
+ }
+ }
+
+ if (bothDirections) {
+ SchemaDifference otherWay = getSchemaDiff(subtrahendCollection,
minuendCollection, false);
+ otherWay.missingFromSecond().forEach(difference::missingFromFirst);
+ }
- return minuendCollection.stream()
- .filter(fs ->
!subtrahendWithoutComment.contains(unsetCommentFunc.apply(fs))).collect(Collectors.toList());
+ return difference;
}
+ public static class SchemaDifference {
+ private final List<FieldSchema> missingFromFirst = new ArrayList<>();
+ private final List<FieldSchema> missingFromSecond = new ArrayList<>();
+ private final List<FieldSchema> typeChanged = new ArrayList<>();
+ private final List<FieldSchema> commentChanged = new ArrayList<>();
+
+ public List<FieldSchema> missingFromFirst() {
Review comment:
Good point, renamed the methods
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
