Skip to content

[Improvement] Schema Diff Skip Logic #85

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[Improvement] Schema Diff Skip Logic #85

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
daf6054
[improvement] Skip all nested struct subfield to lower SQL executions
ekawinataa May 28, 2025
06b8da0
Merge branch 'main' of github.com:goto/depot into improvement-skip-logic
ekawinataa May 28, 2025
d848796
[chore] bump depot version
ekawinataa May 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion build.gradle
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ plugins {
}

group 'com.gotocompany'
version '0.10.19'
version '0.10.20'

repositories {
mavenLocal()
Expand Down
16 changes: 11 additions & 5 deletions src/main/java/com/gotocompany/depot/maxcompute/schema/SchemaDifferenceUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,18 +53,24 @@ private static List<MaxComputeColumnDetail> getMaxComputeColumnDetailDifference(
if (Objects.isNull(oldMetadata)) { //handle new column / struct field
changedMetadata.add(entry.getValue());
if (isStructType(entry.getValue().getTypeInfo()) || isStructArrayType(entry.getValue().getTypeInfo())) {
skipStructFields(entry, newMaxComputeColumnDetailIterator);
StructTypeInfo structTypeInfo = isStructType(entry.getValue().getTypeInfo()) ? (StructTypeInfo) entry.getValue().getTypeInfo() : ((StructTypeInfo) ((ArrayTypeInfo) entry.getValue().getTypeInfo()).getElementTypeInfo());
skipStructFields(structTypeInfo, newMaxComputeColumnDetailIterator);
}
}
}
return changedMetadata;
}

private static void skipStructFields(Map.Entry<String, MaxComputeColumnDetail> entry, Iterator<Map.Entry<String, MaxComputeColumnDetail>> newMaxComputeColumnDetailIterator) {
StructTypeInfo structTypeInfo = isStructType(entry.getValue().getTypeInfo()) ? (StructTypeInfo) entry.getValue().getTypeInfo()
: ((StructTypeInfo) ((ArrayTypeInfo) entry.getValue().getTypeInfo()).getElementTypeInfo());
private static void skipStructFields(StructTypeInfo structTypeInfo, Iterator<Map.Entry<String, MaxComputeColumnDetail>> newMaxComputeColumnDetailIterator) {
for (int i = 0; i < structTypeInfo.getFieldCount(); i++) {
newMaxComputeColumnDetailIterator.next();
TypeInfo currentTypeInfo = structTypeInfo.getFieldTypeInfos().get(i);
if (isPrimitiveType(currentTypeInfo) || isPrimitiveArrayType(currentTypeInfo)) {
newMaxComputeColumnDetailIterator.next();
} else if (isStructType(currentTypeInfo) || isStructArrayType(currentTypeInfo)) {
newMaxComputeColumnDetailIterator.next();
StructTypeInfo currentStructTypeInfo = isStructType(currentTypeInfo) ? (StructTypeInfo) currentTypeInfo : ((StructTypeInfo) ((ArrayTypeInfo) currentTypeInfo).getElementTypeInfo());
skipStructFields(currentStructTypeInfo, newMaxComputeColumnDetailIterator);
}
}
}

Expand Down
8 changes: 3 additions & 5 deletions src/test/java/com/gotocompany/depot/maxcompute/util/SchemaDifferenceUtilsTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,18 +44,16 @@ public void testGetSchemaDifferenceDdl() {
.build();
Set<String> expectedMetadataColumns = new HashSet<>(Arrays.asList(
"alter table test_schema.test_table add column if not exists `col3`.`f3` array<string>;",
"alter table test_schema.test_table add column if not exists `metadata_2` string;",
"alter table test_schema.test_table add column if not exists `col4`.element.`f42` struct<`f421`:string>;",
"alter table test_schema.test_table add column if not exists `col5` array<struct<`f51`:int>>;",
"alter table test_schema.test_table add column if not exists `col6` struct<`f61`:string>;",
"alter table test_schema.test_table add column if not exists `metadata_2` string;",
"alter table test_schema.test_table add column if not exists `col7` struct<`order`:struct<`f711`:string,`f712`:int>,`end`:string>;",
"alter table test_schema.test_table add column if not exists `col7`.`order`.`f711` string;",
"alter table test_schema.test_table add column if not exists `col7`.`order`.`f712` int;"
"alter table test_schema.test_table add column if not exists `col7` struct<`order`:struct<`f711`:string,`f712`:int>,`end`:string>;"
));

Set<String> actualMetadataColumns = new HashSet<>(SchemaDifferenceUtils.getSchemaDifferenceSql(oldTableSchema, newTableSchema, "test_schema", "test_table"));

assertEquals(actualMetadataColumns.size(), expectedMetadataColumns.size());
assertEquals(expectedMetadataColumns.size(), actualMetadataColumns.size());
assertTrue(expectedMetadataColumns.containsAll(actualMetadataColumns));
}

Expand Down