Skip to content

[Spanner Change Stream] Fix Change Streams PostgreSQL metadata queries #40755

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
jiangzzhu wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[Spanner Change Stream] Fix Change Streams PostgreSQL metadata queries #40755

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
55 changes: 31 additions & 24 deletions .../main/java/org/apache/beam/sdk/io/gcp/spanner/changestreams/dao/PartitionMetadataDao.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,6 @@
import java.util.List;
import java.util.Map;
import java.util.function.Function;
import java.util.stream.Collectors;
import javax.annotation.Nullable;
import org.apache.beam.sdk.io.gcp.spanner.changestreams.model.PartitionMetadata;
import org.apache.beam.sdk.io.gcp.spanner.changestreams.model.PartitionMetadata.State;
Expand Down Expand Up @@ -83,13 +82,23 @@ public class PartitionMetadataDao {
* @return true if the table exists, false if the table does not exist.
*/
public boolean tableExists() {
final String checkTableExistsStmt =
"SELECT t.table_name FROM information_schema.tables AS t "
+ "WHERE t.table_catalog = '' AND "
+ "t.table_schema = '' AND "
+ "t.table_name = '"
+ metadataTableName
+ "'";
final String checkTableExistsStmt;
if (this.isPostgres()) {
checkTableExistsStmt =
"SELECT t.table_name FROM information_schema.tables AS t "
+ "WHERE t.table_schema = 'public' AND "
+ "t.table_name = '"
+ metadataTableName
+ "'";
} else {
checkTableExistsStmt =
"SELECT t.table_name FROM information_schema.tables AS t "
+ "WHERE t.table_catalog = '' AND "
+ "t.table_schema = '' AND "
+ "t.table_name = '"
+ metadataTableName
+ "'";
}
try (ResultSet queryResultSet =
databaseClient
.singleUseReadOnlyTransaction()
Expand Down Expand Up @@ -681,22 +690,20 @@ private Statement getPartitionsMatchingState(
List<String> composedPartitionTokens, State state) {
Statement statement;
if (this.dialect == Dialect.POSTGRESQL) {
StringBuilder sqlStringBuilder =
new StringBuilder("SELECT * FROM \"" + metadataTableName + "\"");
sqlStringBuilder.append(" WHERE \"");
sqlStringBuilder.append(COLUMN_STATE + "\" = " + "'" + state.toString() + "'");
if (!composedPartitionTokens.isEmpty()) {
sqlStringBuilder.append(" AND \"");
sqlStringBuilder.append(COLUMN_PARTITION_TOKEN);
sqlStringBuilder.append("\"");
sqlStringBuilder.append(" = ANY (Array[");
sqlStringBuilder.append(
composedPartitionTokens.stream()
.map(s -> "'" + s + "'")
.collect(Collectors.joining(",")));
sqlStringBuilder.append("])");
}
statement = Statement.newBuilder(sqlStringBuilder.toString()).build();
statement =
Statement.newBuilder(
"SELECT * FROM \""
+ metadataTableName
+ "\" WHERE \""
+ COLUMN_STATE
+ "\" = $1 AND \""
+ COLUMN_PARTITION_TOKEN
+ "\" = ANY ($2)")

@scwhittle scwhittle Oct 27, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems to change the behavior for empty composedPartitionTokens array.
Previously it wouldn't check COLUMN_PARTITION_TOKEN but now I think that it will do ANY() which evaluates to false.

Maybe have a branch on if composedPartitionTokens is empty and have two statements you bind to?

.bind("p1")
.to(state.toString())
.bind("p2")
.to(Value.stringArray(new ArrayList<>(composedPartitionTokens)))
.build();
} else {
statement =
Statement.newBuilder(
Expand Down
81 changes: 81 additions & 0 deletions ...t/java/org/apache/beam/sdk/io/gcp/spanner/changestreams/dao/PartitionMetadataDaoTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,10 @@
package org.apache.beam.sdk.io.gcp.spanner.changestreams.dao;

import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertNull;
import static org.junit.Assert.assertTrue;
import static org.mockito.ArgumentMatchers.any;
import static org.mockito.Mockito.doNothing;
import static org.mockito.Mockito.mock;
Expand All @@ -31,7 +33,9 @@
import com.google.cloud.spanner.DatabaseClient;
import com.google.cloud.spanner.Dialect;
import com.google.cloud.spanner.Mutation;
import com.google.cloud.spanner.ReadOnlyTransaction;
import com.google.cloud.spanner.ResultSet;
import com.google.cloud.spanner.Statement;
import com.google.cloud.spanner.Struct;
import com.google.cloud.spanner.TransactionContext;
import com.google.cloud.spanner.TransactionRunner;
Expand Down Expand Up @@ -406,4 +410,81 @@ public void testExtractTvfName() {
assertEquals("tvf", PartitionMetadataDao.extractTvfName("partitionToken123#tvf"));
assertEquals("", PartitionMetadataDao.extractTvfName("partitionToken123"));
}

@Test
public void testTableExistsGoogleSql() {
ReadOnlyTransaction readOnlyTx = mock(ReadOnlyTransaction.class);
ResultSet resultSet = mock(ResultSet.class);
when(databaseClient.singleUseReadOnlyTransaction()).thenReturn(readOnlyTx);
when(readOnlyTx.executeQuery(any(Statement.class), any())).thenReturn(resultSet);
when(resultSet.next()).thenReturn(true);

assertTrue(partitionMetadataDao.tableExists());

ArgumentCaptor<Statement> statementCaptor = ArgumentCaptor.forClass(Statement.class);
verify(readOnlyTx).executeQuery(statementCaptor.capture(), any());
assertEquals(
"SELECT t.table_name FROM information_schema.tables AS t "
+ "WHERE t.table_catalog = '' AND "
+ "t.table_schema = '' AND "
+ "t.table_name = '"
+ METADATA_TABLE_NAME
+ "'",
statementCaptor.getValue().getSql());
}

@Test
public void testTableExistsPostgres() {
ReadOnlyTransaction readOnlyTx = mock(ReadOnlyTransaction.class);
ResultSet resultSet = mock(ResultSet.class);
when(databaseClient.singleUseReadOnlyTransaction()).thenReturn(readOnlyTx);
when(readOnlyTx.executeQuery(any(Statement.class), any())).thenReturn(resultSet);
when(resultSet.next()).thenReturn(true).thenReturn(false);

PartitionMetadataDao pgDao =
new PartitionMetadataDao(METADATA_TABLE_NAME, databaseClient, Dialect.POSTGRESQL);
assertTrue(pgDao.tableExists());
assertFalse(pgDao.tableExists());

ArgumentCaptor<Statement> statementCaptor = ArgumentCaptor.forClass(Statement.class);
verify(readOnlyTx, times(2)).executeQuery(statementCaptor.capture(), any());
assertEquals(
"SELECT t.table_name FROM information_schema.tables AS t "
+ "WHERE t.table_schema = 'public' AND "
+ "t.table_name = '"
+ METADATA_TABLE_NAME
+ "'",
statementCaptor.getValue().getSql());
}

@Test
public void testInTransactionContextUpdateToScheduledPostgres() {
PartitionMetadataDao.InTransactionContext pgTransactionContext =
new PartitionMetadataDao.InTransactionContext(
METADATA_TABLE_NAME, transaction, Dialect.POSTGRESQL);
ResultSet resultSet = mock(ResultSet.class);
when(transaction.executeQuery(any(), any())).thenReturn(resultSet);
when(resultSet.next()).thenReturn(true).thenReturn(false);
when(resultSet.getString(any())).thenReturn(PARTITION_TOKEN);

ArgumentCaptor<Statement> statementCaptor = ArgumentCaptor.forClass(Statement.class);
ArgumentCaptor<ImmutableList<Mutation>> mutations =
ArgumentCaptor.forClass(ImmutableList.class);
doNothing().when(transaction).buffer(mutations.capture());

assertNull(pgTransactionContext.updateToScheduled(Collections.singletonList(PARTITION_TOKEN)));

@scwhittle scwhittle Oct 27, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add test coverage of 0 and multiple tokens as well


verify(transaction).executeQuery(statementCaptor.capture(), any());
Statement captured = statementCaptor.getValue();
assertEquals(
"SELECT * FROM \""
+ METADATA_TABLE_NAME
+ "\" WHERE \"State\" = $1 AND \"PartitionToken\" = ANY ($2)",
captured.getSql());
assertEquals(State.CREATED.toString(), captured.getParameters().get("p1").getString());
assertEquals(
Collections.singletonList(PARTITION_TOKEN),
captured.getParameters().get("p2").getStringArray());
assertEquals(1, mutations.getValue().size());
}
}
Loading