aokolnychyi commented on code in PR #6012:
URL: https://github.com/apache/iceberg/pull/6012#discussion_r1125362664
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/BaseProcedure.java:
##########
@@ -144,6 +148,12 @@ protected SparkTable loadSparkTable(Identifier ident) {
}
}
+ protected Dataset<Row> loadDataSetFromTable(Identifier tableIdent,
Map<String, String> options) {
Review Comment:
Is there a shorter yet descriptive name? Like `loadRows`, `loadContent`, etc?
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/CreateChangelogViewProcedure.java:
##########
@@ -0,0 +1,266 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.iceberg.spark.procedures;
+
+import java.util.Arrays;
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.MetadataColumns;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.spark.ChangelogIterator;
+import org.apache.iceberg.spark.source.SparkChangelogTable;
+import org.apache.spark.api.java.function.MapPartitionsFunction;
+import org.apache.spark.sql.Column;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.catalyst.encoders.RowEncoder;
+import org.apache.spark.sql.connector.catalog.Identifier;
+import org.apache.spark.sql.connector.catalog.TableCatalog;
+import org.apache.spark.sql.connector.iceberg.catalog.ProcedureParameter;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+import org.apache.spark.unsafe.types.UTF8String;
+import scala.runtime.BoxedUnit;
+
+/**
+ * A procedure that creates a view for changed rows.
+ *
+ * <p>The procedure removes the carry-over rows by default. If you want to
keep them, you can set
+ * "remove_carryovers" to be false in the options.
+ *
+ * <p>The procedure doesn't compute the pre/post update images by default. If
you want to compute
+ * them, you can set "compute_updates" to be true in the options.
+ *
+ * <p>Carry-over rows are the result of a removal and insertion of the same
row within an operation
+ * because of the copy-on-write mechanism. For example, given a file which
contains row1 (id=1,
+ * data='a') and row2 (id=2, data='b'). A copy-on-write delete of row2 would
require erasing this
+ * file and preserving row1 in a new file. The changelog table would report
this as (id=1, data='a',
+ * op='DELETE') and (id=1, data='a', op='INSERT'), despite it not being an
actual change to the
+ * table. The procedure finds the carry-over rows and removes them from the
result.
+ *
+ * <p>Pre/post update images are converted from a pair of a delete row and an
insert row. Identifier
+ * columns are used for determining whether an insert and a delete record
refer to the same row. If
+ * the two records share the same values for the identity columns they are
considered to be before
+ * and after states of the same row. You can either set identifier fields in
the table schema or
+ * input them as the procedure parameters. Here is an example of pre/post
update images with an
+ * identifier column(id). A pair of a delete row and an insert row with the
same id:
+ *
+ * <ul>
+ * <li>(id=1, data='a', op='DELETE')
+ * <li>(id=1, data='b', op='INSERT')
+ * </ul>
+ *
+ * <p>will be marked as pre/post update images:
+ *
+ * <ul>
+ * <li>(id=1, data='a', op='UPDATE_BEFORE')
+ * <li>(id=1, data='b', op='UPDATE_AFTER')
+ * </ul>
+ */
+public class CreateChangelogViewProcedure extends BaseProcedure {
+
+ private static final ProcedureParameter[] PARAMETERS =
+ new ProcedureParameter[] {
+ ProcedureParameter.required("table", DataTypes.StringType),
+ ProcedureParameter.optional("changelog_view", DataTypes.StringType),
+ ProcedureParameter.optional("options", STRING_MAP),
+ ProcedureParameter.optional("compute_updates", DataTypes.BooleanType),
+ ProcedureParameter.optional("remove_carryovers",
DataTypes.BooleanType),
+ ProcedureParameter.optional("identifier_columns", STRING_ARRAY),
+ };
+
+ private static final int TABLE_NAME_ORDINAL = 0;
+ private static final int CHANGELOG_VIEW_NAME_ORDINAL = 1;
+ private static final int OPTIONS_ORDINAL = 2;
+ private static final int COMPUTE_UPDATES_ORDINAL = 3;
+ private static final int REMOVE_CARRYOVERS_ORDINAL = 4;
+ private static final int IDENTIFIER_COLUMNS_ORDINAL = 5;
+
+ private static final StructType OUTPUT_TYPE =
+ new StructType(
+ new StructField[] {
+ new StructField("changelog_view", DataTypes.StringType, false,
Metadata.empty())
+ });
+
+ public static SparkProcedures.ProcedureBuilder builder() {
+ return new BaseProcedure.Builder<CreateChangelogViewProcedure>() {
+ @Override
+ protected CreateChangelogViewProcedure doBuild() {
+ return new CreateChangelogViewProcedure(tableCatalog());
+ }
+ };
+ }
+
+ private CreateChangelogViewProcedure(TableCatalog tableCatalog) {
+ super(tableCatalog);
+ }
+
+ @Override
+ public ProcedureParameter[] parameters() {
+ return PARAMETERS;
+ }
+
+ @Override
+ public StructType outputType() {
+ return OUTPUT_TYPE;
+ }
+
+ @Override
+ public InternalRow[] call(InternalRow args) {
+ Identifier tableIdent =
+ toIdentifier(args.getString(TABLE_NAME_ORDINAL),
PARAMETERS[TABLE_NAME_ORDINAL].name());
+
+ // load insert and deletes from the changelog table
+ Identifier changelogTableIdent = changelogTableIdent(tableIdent);
+ Dataset<Row> df = loadDataSetFromTable(changelogTableIdent, options(args));
+
+ if (shouldComputeUpdateImages(args)) {
+ df = computeUpdateImages(identifierColumns(args, tableIdent), df);
+ } else if (shouldRemoveCarryoverRows(args)) {
+ df = removeCarryoverRows(df);
+ }
+
+ String viewName = viewName(args, tableIdent.name());
+
+ df.createOrReplaceTempView(viewName);
+
+ return toOutputRows(viewName);
+ }
+
+ private Dataset<Row> computeUpdateImages(String[] identifierColumns,
Dataset<Row> df) {
+ Preconditions.checkArgument(
+ identifierColumns.length > 0,
+ "Cannot compute the update-rows because identifier columns are not
set");
+
+ Column[] repartitionColumns = new Column[identifierColumns.length + 1];
Review Comment:
nit: We sometimes call it `repartitionColumns` and sometimes
`repartitionSpec`.
I'd probably use `repartitionSpec` everywhere since it is shorter (this
statement would fit on 1 line?) and matches `sortSpec` used in other methods.
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/BaseProcedure.java:
##########
@@ -144,6 +148,12 @@ protected SparkTable loadSparkTable(Identifier ident) {
}
}
+ protected Dataset<Row> loadDataSetFromTable(Identifier tableIdent,
Map<String, String> options) {
+ String tableName = Spark3Util.quotedFullIdentifier(tableCatalog().name(),
tableIdent);
+ // no need to validate the read options here since the reader will
validate them
Review Comment:
I don't think we need this comment anymore since it is a pretty generic
method now.
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/CreateChangelogViewProcedure.java:
##########
@@ -0,0 +1,266 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.iceberg.spark.procedures;
+
+import java.util.Arrays;
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.MetadataColumns;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.spark.ChangelogIterator;
+import org.apache.iceberg.spark.source.SparkChangelogTable;
+import org.apache.spark.api.java.function.MapPartitionsFunction;
+import org.apache.spark.sql.Column;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.catalyst.encoders.RowEncoder;
+import org.apache.spark.sql.connector.catalog.Identifier;
+import org.apache.spark.sql.connector.catalog.TableCatalog;
+import org.apache.spark.sql.connector.iceberg.catalog.ProcedureParameter;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+import org.apache.spark.unsafe.types.UTF8String;
+import scala.runtime.BoxedUnit;
+
+/**
+ * A procedure that creates a view for changed rows.
+ *
+ * <p>The procedure removes the carry-over rows by default. If you want to
keep them, you can set
+ * "remove_carryovers" to be false in the options.
+ *
+ * <p>The procedure doesn't compute the pre/post update images by default. If
you want to compute
+ * them, you can set "compute_updates" to be true in the options.
+ *
+ * <p>Carry-over rows are the result of a removal and insertion of the same
row within an operation
+ * because of the copy-on-write mechanism. For example, given a file which
contains row1 (id=1,
+ * data='a') and row2 (id=2, data='b'). A copy-on-write delete of row2 would
require erasing this
+ * file and preserving row1 in a new file. The changelog table would report
this as (id=1, data='a',
+ * op='DELETE') and (id=1, data='a', op='INSERT'), despite it not being an
actual change to the
+ * table. The procedure finds the carry-over rows and removes them from the
result.
+ *
+ * <p>Pre/post update images are converted from a pair of a delete row and an
insert row. Identifier
+ * columns are used for determining whether an insert and a delete record
refer to the same row. If
+ * the two records share the same values for the identity columns they are
considered to be before
+ * and after states of the same row. You can either set identifier fields in
the table schema or
+ * input them as the procedure parameters. Here is an example of pre/post
update images with an
+ * identifier column(id). A pair of a delete row and an insert row with the
same id:
+ *
+ * <ul>
+ * <li>(id=1, data='a', op='DELETE')
+ * <li>(id=1, data='b', op='INSERT')
+ * </ul>
+ *
+ * <p>will be marked as pre/post update images:
+ *
+ * <ul>
+ * <li>(id=1, data='a', op='UPDATE_BEFORE')
+ * <li>(id=1, data='b', op='UPDATE_AFTER')
+ * </ul>
+ */
+public class CreateChangelogViewProcedure extends BaseProcedure {
+
+ private static final ProcedureParameter[] PARAMETERS =
+ new ProcedureParameter[] {
+ ProcedureParameter.required("table", DataTypes.StringType),
+ ProcedureParameter.optional("changelog_view", DataTypes.StringType),
+ ProcedureParameter.optional("options", STRING_MAP),
+ ProcedureParameter.optional("compute_updates", DataTypes.BooleanType),
+ ProcedureParameter.optional("remove_carryovers",
DataTypes.BooleanType),
+ ProcedureParameter.optional("identifier_columns", STRING_ARRAY),
+ };
+
+ private static final int TABLE_NAME_ORDINAL = 0;
+ private static final int CHANGELOG_VIEW_NAME_ORDINAL = 1;
+ private static final int OPTIONS_ORDINAL = 2;
+ private static final int COMPUTE_UPDATES_ORDINAL = 3;
+ private static final int REMOVE_CARRYOVERS_ORDINAL = 4;
+ private static final int IDENTIFIER_COLUMNS_ORDINAL = 5;
+
+ private static final StructType OUTPUT_TYPE =
+ new StructType(
+ new StructField[] {
+ new StructField("changelog_view", DataTypes.StringType, false,
Metadata.empty())
+ });
+
+ public static SparkProcedures.ProcedureBuilder builder() {
+ return new BaseProcedure.Builder<CreateChangelogViewProcedure>() {
+ @Override
+ protected CreateChangelogViewProcedure doBuild() {
+ return new CreateChangelogViewProcedure(tableCatalog());
+ }
+ };
+ }
+
+ private CreateChangelogViewProcedure(TableCatalog tableCatalog) {
+ super(tableCatalog);
+ }
+
+ @Override
+ public ProcedureParameter[] parameters() {
+ return PARAMETERS;
+ }
+
+ @Override
+ public StructType outputType() {
+ return OUTPUT_TYPE;
+ }
+
+ @Override
+ public InternalRow[] call(InternalRow args) {
+ Identifier tableIdent =
+ toIdentifier(args.getString(TABLE_NAME_ORDINAL),
PARAMETERS[TABLE_NAME_ORDINAL].name());
+
+ // load insert and deletes from the changelog table
+ Identifier changelogTableIdent = changelogTableIdent(tableIdent);
+ Dataset<Row> df = loadDataSetFromTable(changelogTableIdent, options(args));
+
+ if (shouldComputeUpdateImages(args)) {
+ df = computeUpdateImages(identifierColumns(args, tableIdent), df);
+ } else if (shouldRemoveCarryoverRows(args)) {
+ df = removeCarryoverRows(df);
+ }
+
+ String viewName = viewName(args, tableIdent.name());
+
+ df.createOrReplaceTempView(viewName);
+
+ return toOutputRows(viewName);
+ }
+
+ private Dataset<Row> computeUpdateImages(String[] identifierColumns,
Dataset<Row> df) {
+ Preconditions.checkArgument(
+ identifierColumns.length > 0,
+ "Cannot compute the update-rows because identifier columns are not
set");
Review Comment:
nit: `update-rows` -> `update images`?
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
