[
https://issues.apache.org/jira/browse/GOBBLIN-1774?focusedWorklogId=844870&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-844870
]
ASF GitHub Bot logged work on GOBBLIN-1774:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 10/Feb/23 20:17
Start Date: 10/Feb/23 20:17
Worklog Time Spent: 10m
Work Description: vikrambohra commented on code in PR #3632:
URL: https://github.com/apache/gobblin/pull/3632#discussion_r1103195419
##########
gobblin-hive-registration/src/main/java/org/apache/gobblin/hive/metastore/HiveMetaStoreUtils.java:
##########
@@ -256,6 +262,71 @@ public static SerDeInfo getSerDeInfo(HiveRegistrationUnit
unit) {
return si;
}
+ public static boolean containsNonOptionalUnionTypeColumn(Table t) {
+ return containsNonOptionalUnionTypeColumn(getHiveTable(t));
+ }
+
+ /**
+ * Util for detecting if a hive table has a non-optional union (aka complex
unions) column types. A non optional
+ * union is defined as a uniontype with n >= 2 non-null subtypes
+ *
+ * @param hiveTable Hive table
+ * @return if hive table contains non-optional uniontype columns
+ */
+ public static boolean containsNonOptionalUnionTypeColumn(HiveTable
hiveTable) {
+ if (hiveTable.getProps().contains("avro.schema.literal")) {
Review Comment:
use AvroSerdeUtils.SCHEMA_LITERAL
##########
gobblin-hive-registration/src/main/java/org/apache/gobblin/hive/metastore/HiveMetaStoreUtils.java:
##########
@@ -256,6 +262,71 @@ public static SerDeInfo getSerDeInfo(HiveRegistrationUnit
unit) {
return si;
}
+ public static boolean containsNonOptionalUnionTypeColumn(Table t) {
+ return containsNonOptionalUnionTypeColumn(getHiveTable(t));
+ }
+
+ /**
+ * Util for detecting if a hive table has a non-optional union (aka complex
unions) column types. A non optional
+ * union is defined as a uniontype with n >= 2 non-null subtypes
+ *
+ * @param hiveTable Hive table
+ * @return if hive table contains non-optional uniontype columns
+ */
+ public static boolean containsNonOptionalUnionTypeColumn(HiveTable
hiveTable) {
+ if (hiveTable.getProps().contains("avro.schema.literal")) {
+ Schema.Parser parser = new Schema.Parser();
+ Schema schema =
parser.parse(hiveTable.getProps().getProp("avro.schema.literal"));
Review Comment:
use AvroSerdeUtils.SCHEMA_LITERAL
##########
gobblin-hive-registration/src/main/java/org/apache/gobblin/hive/metastore/HiveMetaStoreUtils.java:
##########
@@ -256,6 +262,71 @@ public static SerDeInfo getSerDeInfo(HiveRegistrationUnit
unit) {
return si;
}
+ public static boolean containsNonOptionalUnionTypeColumn(Table t) {
+ return containsNonOptionalUnionTypeColumn(getHiveTable(t));
+ }
+
+ /**
+ * Util for detecting if a hive table has a non-optional union (aka complex
unions) column types. A non optional
+ * union is defined as a uniontype with n >= 2 non-null subtypes
+ *
+ * @param hiveTable Hive table
+ * @return if hive table contains non-optional uniontype columns
+ */
+ public static boolean containsNonOptionalUnionTypeColumn(HiveTable
hiveTable) {
+ if (hiveTable.getProps().contains("avro.schema.literal")) {
+ Schema.Parser parser = new Schema.Parser();
+ Schema schema =
parser.parse(hiveTable.getProps().getProp("avro.schema.literal"));
+ return isNonOptionalUnion(schema);
+ }
+
+ if (isNonAvroFormat(hiveTable)) {
+ return hiveTable.getColumns().stream()
+ .map(HiveRegistrationUnit.Column::getType)
+ .filter(type -> type.contains("uniontype"))
+ .map(type -> TypeDescription.fromString(type))
+ .anyMatch(type -> isNonOptionalUnion(type));
+ }
+
+ throw new RuntimeException("Avro based Hive tables without
\"avro.schema.literal\" are not supported");
+ }
+
+ private static boolean isNonOptionalUnion(Schema schema) {
+ switch (schema.getType()) {
+ case UNION:
+ Stream<Schema.Type> nonNullSubTypes = schema.getTypes().stream()
+ .map(Schema::getType).filter(t -> !t.equals(Schema.Type.NULL));
+ if (nonNullSubTypes.count() >= 2) {
+ return true;
+ }
+ return schema.getTypes().stream().anyMatch(s -> isNonOptionalUnion(s));
+ case MAP: // key is a string and doesn't need to be checked
+ return isNonOptionalUnion(schema.getValueType());
+ case ARRAY:
+ return isNonOptionalUnion(schema.getElementType());
+ case RECORD:
+ return
schema.getFields().stream().map(Schema.Field::schema).anyMatch(s ->
isNonOptionalUnion(s));
+ default:
+ return false;
+ }
+ }
+
+ private static boolean isNonOptionalUnion(TypeDescription description) {
Review Comment:
Useful method. can be made public
##########
gobblin-hive-registration/src/main/java/org/apache/gobblin/hive/metastore/HiveMetaStoreUtils.java:
##########
@@ -256,6 +262,71 @@ public static SerDeInfo getSerDeInfo(HiveRegistrationUnit
unit) {
return si;
}
+ public static boolean containsNonOptionalUnionTypeColumn(Table t) {
+ return containsNonOptionalUnionTypeColumn(getHiveTable(t));
+ }
+
+ /**
+ * Util for detecting if a hive table has a non-optional union (aka complex
unions) column types. A non optional
+ * union is defined as a uniontype with n >= 2 non-null subtypes
+ *
+ * @param hiveTable Hive table
+ * @return if hive table contains non-optional uniontype columns
+ */
+ public static boolean containsNonOptionalUnionTypeColumn(HiveTable
hiveTable) {
+ if (hiveTable.getProps().contains("avro.schema.literal")) {
+ Schema.Parser parser = new Schema.Parser();
+ Schema schema =
parser.parse(hiveTable.getProps().getProp("avro.schema.literal"));
+ return isNonOptionalUnion(schema);
+ }
+
+ if (isNonAvroFormat(hiveTable)) {
+ return hiveTable.getColumns().stream()
+ .map(HiveRegistrationUnit.Column::getType)
+ .filter(type -> type.contains("uniontype"))
+ .map(type -> TypeDescription.fromString(type))
+ .anyMatch(type -> isNonOptionalUnion(type));
+ }
+
+ throw new RuntimeException("Avro based Hive tables without
\"avro.schema.literal\" are not supported");
+ }
+
+ private static boolean isNonOptionalUnion(Schema schema) {
Review Comment:
Useful method. can be made public
Issue Time Tracking
-------------------
Worklog Id: (was: 844870)
Time Spent: 2h 20m (was: 2h 10m)
> Add utility method for GMIP, MR compaction, and Incremental to skip override
> hive schema on topics with complex union
> ---------------------------------------------------------------------------------------------------------------------
>
> Key: GOBBLIN-1774
> URL: https://issues.apache.org/jira/browse/GOBBLIN-1774
> Project: Apache Gobblin
> Issue Type: Improvement
> Reporter: Matthew Ho
> Priority: Major
> Time Spent: 2h 20m
> Remaining Estimate: 0h
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
