danny0405 commented on code in PR #5445:
URL: https://github.com/apache/hudi/pull/5445#discussion_r868790677
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/sink/ITTestDataStreamWrite.java:
##########
@@ -248,8 +221,129 @@ private void testWriteToHoodie(
// wait for the streaming job to finish
client.getJobExecutionResult().get();
}
+ }
- TestData.checkWrittenFullData(tempFile, expected);
+ public DataStream dataStreamGen(StreamExecutionEnvironment execEnv, boolean
isMor, RowType rowType, Option<Transformer> transformer, int checkpoints) {
+
+ JsonRowDataDeserializationSchema deserializationSchema = new
JsonRowDataDeserializationSchema(
+ rowType,
+ InternalTypeInfo.of(rowType),
+ false,
+ true,
+ TimestampFormat.ISO_8601
+ );
+ String sourcePath = Objects.requireNonNull(Thread.currentThread()
+
.getContextClassLoader().getResource("test_source.data")).toString();
+
+ DataStream<RowData> dataStream;
+ if (isMor) {
+ TextInputFormat format = new TextInputFormat(new Path(sourcePath));
+ format.setFilesFilter(FilePathFilter.createDefaultFilter());
+ TypeInformation<String> typeInfo = BasicTypeInfo.STRING_TYPE_INFO;
+ format.setCharsetName("UTF-8");
+
+ dataStream = execEnv
+ // use PROCESS_CONTINUOUSLY mode to trigger checkpoint
+ .readFile(format, sourcePath,
FileProcessingMode.PROCESS_CONTINUOUSLY, 1000, typeInfo)
+ .map(record ->
deserializationSchema.deserialize(record.getBytes(StandardCharsets.UTF_8)))
+ .setParallelism(1);
+ } else {
+ dataStream = execEnv
+ // use continuous file source to trigger checkpoint
+ .addSource(new ContinuousFileSource.BoundedSourceFunction(new
Path(sourcePath), checkpoints))
+ .name("continuous_file_source")
+ .setParallelism(1)
+ .map(record ->
deserializationSchema.deserialize(record.getBytes(StandardCharsets.UTF_8)))
+ .setParallelism(4);
+ }
+ if (transformer.isPresent()) {
+ dataStream = transformer.get().apply(dataStream);
+ }
+ return dataStream;
+ }
+
+ @Test
+ public void testSource() throws Exception {
+ //create a StreamExecutionEnvironment instance.
+ StreamExecutionEnvironment execEnv =
StreamExecutionEnvironment.getExecutionEnvironment();
+ execEnv.getConfig().disableObjectReuse();
+ execEnv.setParallelism(1);
+ // set up checkpoint interval
+ execEnv.enableCheckpointing(4000, CheckpointingMode.EXACTLY_ONCE);
+ execEnv.getCheckpointConfig().setMaxConcurrentCheckpoints(1);
+ Configuration conf =
TestConfigurations.getDefaultConf(tempFile.getAbsolutePath());
+ conf.setString(FlinkOptions.TABLE_NAME, "t1");
+ conf.setString(FlinkOptions.TABLE_TYPE, "MERGE_ON_READ");
+
+ // write 3 batches of data set
+ TestData.writeData(TestData.dataSetInsert(1, 2), conf);
+ TestData.writeData(TestData.dataSetInsert(3, 4), conf);
+ TestData.writeData(TestData.dataSetInsert(5, 6), conf);
+
+ String latestCommit =
TestUtils.getLastCompleteInstant(tempFile.getAbsolutePath());
+
+ Map<String, String> options = new HashMap<>();
+ options.put(FlinkOptions.PATH.key(), tempFile.getAbsolutePath());
+ options.put(FlinkOptions.READ_START_COMMIT.key(), latestCommit);
+
+ //read a hoodie table use low-level source api.
+ HoodiePipeline.Builder builder = HoodiePipeline.builder("test_source")
+ .column("uuid string not null")
+ .column("name string")
+ .column("age int")
+ .column("`ts` timestamp(3)")
+ .column("`partition` string")
+ .pk("uuid")
+ .partition("partition")
+ .options(options);
+ DataStream<RowData> rowDataDataStream = builder.source(execEnv);
+ List<RowData> result = new ArrayList<>();
+ rowDataDataStream.executeAndCollect().forEachRemaining(result::add);
+ TimeUnit.SECONDS.sleep(2);//sleep 2 second for collect data
+ assertRowDataEquals(result, TestData.dataSetInsert(5, 6));
+ }
+
+ @Test
+ public void testSink() throws Exception {
+ StreamExecutionEnvironment execEnv =
StreamExecutionEnvironment.getExecutionEnvironment();
Review Comment:
`testPipelineBuilderSink()`
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/sink/ITTestDataStreamWrite.java:
##########
@@ -57,13 +59,16 @@
import java.io.File;
import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Objects;
import java.util.concurrent.TimeUnit;
+import static org.apache.hudi.utils.TestData.assertRowDataEquals;
+
Review Comment:
Can we avoid to import static methods and use `TestData.assertRowDataEquals`
directly ?
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/sink/ITTestDataStreamWrite.java:
##########
@@ -248,8 +221,129 @@ private void testWriteToHoodie(
// wait for the streaming job to finish
client.getJobExecutionResult().get();
}
+ }
- TestData.checkWrittenFullData(tempFile, expected);
+ public DataStream dataStreamGen(StreamExecutionEnvironment execEnv, boolean
isMor, RowType rowType, Option<Transformer> transformer, int checkpoints) {
+
+ JsonRowDataDeserializationSchema deserializationSchema = new
JsonRowDataDeserializationSchema(
+ rowType,
+ InternalTypeInfo.of(rowType),
+ false,
+ true,
+ TimestampFormat.ISO_8601
+ );
+ String sourcePath = Objects.requireNonNull(Thread.currentThread()
+
.getContextClassLoader().getResource("test_source.data")).toString();
+
+ DataStream<RowData> dataStream;
+ if (isMor) {
+ TextInputFormat format = new TextInputFormat(new Path(sourcePath));
+ format.setFilesFilter(FilePathFilter.createDefaultFilter());
+ TypeInformation<String> typeInfo = BasicTypeInfo.STRING_TYPE_INFO;
+ format.setCharsetName("UTF-8");
+
+ dataStream = execEnv
+ // use PROCESS_CONTINUOUSLY mode to trigger checkpoint
+ .readFile(format, sourcePath,
FileProcessingMode.PROCESS_CONTINUOUSLY, 1000, typeInfo)
+ .map(record ->
deserializationSchema.deserialize(record.getBytes(StandardCharsets.UTF_8)))
+ .setParallelism(1);
+ } else {
+ dataStream = execEnv
+ // use continuous file source to trigger checkpoint
+ .addSource(new ContinuousFileSource.BoundedSourceFunction(new
Path(sourcePath), checkpoints))
+ .name("continuous_file_source")
+ .setParallelism(1)
+ .map(record ->
deserializationSchema.deserialize(record.getBytes(StandardCharsets.UTF_8)))
+ .setParallelism(4);
+ }
+ if (transformer.isPresent()) {
+ dataStream = transformer.get().apply(dataStream);
+ }
+ return dataStream;
+ }
+
+ @Test
+ public void testSource() throws Exception {
+ //create a StreamExecutionEnvironment instance.
Review Comment:
`testPipelineBuilderSource()`
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/HoodiePipeline.java:
##########
@@ -0,0 +1,270 @@
+/*
+ * 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.hudi.util;
+
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.table.HoodieTableFactory;
+
+import org.apache.flink.configuration.ConfigOption;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
+import org.apache.flink.table.api.EnvironmentSettings;
+import org.apache.flink.table.api.internal.TableEnvironmentImpl;
+import org.apache.flink.table.catalog.Catalog;
+import org.apache.flink.table.catalog.ObjectIdentifier;
+import org.apache.flink.table.catalog.ObjectPath;
+import org.apache.flink.table.catalog.ResolvedCatalogTable;
+import org.apache.flink.table.catalog.exceptions.TableNotExistException;
+import org.apache.flink.table.connector.sink.DataStreamSinkProvider;
+import org.apache.flink.table.connector.source.DataStreamScanProvider;
+import org.apache.flink.table.connector.source.ScanTableSource;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.factories.FactoryUtil;
+import
org.apache.flink.table.runtime.connector.sink.SinkRuntimeProviderContext;
+import
org.apache.flink.table.runtime.connector.source.ScanRuntimeProviderContext;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+/**
+ * A tool class to construct hoodie flink pipeline.
+ *
+ * <p>How to use ?</p>
+ * Method {@link #builder(String)} returns a pipeline builder. The builder
+ * can then define the hudi table columns, primary keys and partitions.
+ *
+ * <p>An example:</p>
+ * <pre>
+ * HoodiePipeline.Builder builder = HoodiePipeline.builder("myTable");
+ * DataStreamSink<?> sinkStream = builder
+ * .column("f0 int")
+ * .column("f1 varchar(10)")
+ * .column("f2 varchar(20)")
+ * .pk("f0,f1")
+ * .partition("f2")
+ * .sink(input, false);
+ * </pre>
+ */
+public class HoodiePipeline {
+
+ private static final Logger LOG = LogManager.getLogger(HoodiePipeline.class);
+
+ /**
+ * Returns the builder for hoodie pipeline construction.
+ */
+ public static Builder builder(String tableName) {
+ return new Builder(tableName);
+ }
+
+ /**
+ * Builder for hudi source/sink pipeline construction.
+ */
+ public static class Builder {
+ private final String tableName;
+ private final List<String> columns;
+ private final Map<String, String> options;
+
+ private String pk;
+ private List<String> partitions;
+
+ private Builder(String tableName) {
+ this.tableName = tableName;
+ this.columns = new ArrayList<>();
+ this.options = new HashMap<>();
+ this.partitions = new ArrayList<>();
+ }
+
+ /**
+ * Add a table column definition.
+ *
+ * @param column the column format should be in the form like 'f0 int'
+ */
+ public Builder column(String column) {
+ this.columns.add(column);
+ return this;
+ }
+
+ /**
+ * Add primary keys.
+ */
+ public Builder pk(String... pks) {
+ this.pk = String.join(",", pks);
+ return this;
+ }
+
+ /**
+ * Add partition fields.
+ */
+ public Builder partition(String... partitions) {
+ this.partitions = new ArrayList<>(Arrays.asList(partitions));
+ return this;
+ }
+
+ /**
+ * Add a config option.
+ */
+ public Builder option(ConfigOption<?> option, Object val) {
+ this.options.put(option.key(), val.toString());
+ return this;
+ }
+
+ public Builder option(String key, Object val) {
+ this.options.put(key, val.toString());
+ return this;
+ }
+
+ public Builder options(Map<String, String> options) {
+ this.options.putAll(options);
+ return this;
+ }
+
+ public DataStreamSink<?> sink(DataStream<RowData> input, boolean bounded) {
+ TableDescriptor tableDescriptor = getTableDescriptor();
+ return HoodiePipeline.sink(input, tableDescriptor.getTableId(),
tableDescriptor.getResolvedCatalogTable(), bounded);
+ }
+
+ public TableDescriptor getTableDescriptor() {
+ EnvironmentSettings environmentSettings = EnvironmentSettings
+ .newInstance()
+ .build();
+ TableEnvironmentImpl tableEnv =
TableEnvironmentImpl.create(environmentSettings);
+ String sql = getCreateHoodieTableDDL(this.tableName, this.columns,
this.options, this.pk, this.partitions);
+ tableEnv.executeSql(sql);
+ String currentCatalog = tableEnv.getCurrentCatalog();
+ ResolvedCatalogTable catalogTable = null;
+ String defaultDatabase = null;
+ try {
+ Catalog catalog = tableEnv.getCatalog(currentCatalog).get();
+ defaultDatabase = catalog.getDefaultDatabase();
+ catalogTable = (ResolvedCatalogTable) catalog.getTable(new
ObjectPath(defaultDatabase, this.tableName));
+ } catch (TableNotExistException e) {
+ throw new HoodieException("Create table " + this.tableName + "
exception", e);
+ }
+ ObjectIdentifier tableId = ObjectIdentifier.of(currentCatalog,
defaultDatabase, this.tableName);
+ return new TableDescriptor(tableId, catalogTable);
+ }
+
+ public DataStream<RowData> source(StreamExecutionEnvironment execEnv) {
+ TableDescriptor tableDescriptor = getTableDescriptor();
+ return HoodiePipeline.source(execEnv, tableDescriptor.tableId,
tableDescriptor.getResolvedCatalogTable());
+ }
+ }
+
+ private static String getCreateHoodieTableDDL(
+ String tableName,
+ List<String> fields,
+ Map<String, String> options,
+ String pkField,
+ List<String> partitionField) {
+ StringBuilder builder = new StringBuilder();
+ builder.append("create table ")
+ .append(tableName)
+ .append("(\n");
+ for (String field : fields) {
+ builder.append(" ")
+ .append(field)
+ .append(",\n");
+ }
+ builder.append(" PRIMARY KEY(")
+ .append(pkField)
+ .append(") NOT ENFORCED\n")
+ .append(")\n");
+ if (!partitionField.isEmpty()) {
+ String partitons = partitionField
+ .stream()
+ .map(partitionName -> "`" + partitionName + "`")
+ .collect(Collectors.joining(","));
+ builder.append("PARTITIONED BY (")
+ .append(partitons)
+ .append(")\n");
+ }
+ builder.append("with ('connector' = 'hudi'");
+ options.forEach((k, v) -> builder
+ .append(",\n")
+ .append(" '")
+ .append(k)
+ .append("' = '")
+ .append(v)
+ .append("'"));
+ builder.append("\n)");
+ return builder.toString();
+ }
+
+ /**
+ * Returns the data stream sink with given catalog table.
+ * @param input The input datastream
Review Comment:
Put an empty line between `Returns the data` and `@param input`
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/HoodiePipeline.java:
##########
@@ -0,0 +1,263 @@
+/*
+ * 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.hudi.util;
+
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.table.HoodieTableFactory;
+
+import org.apache.flink.configuration.ConfigOption;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
+import org.apache.flink.table.api.EnvironmentSettings;
+import org.apache.flink.table.api.internal.TableEnvironmentImpl;
+import org.apache.flink.table.catalog.Catalog;
+import org.apache.flink.table.catalog.ObjectIdentifier;
+import org.apache.flink.table.catalog.ObjectPath;
+import org.apache.flink.table.catalog.ResolvedCatalogTable;
+import org.apache.flink.table.catalog.exceptions.TableNotExistException;
+import org.apache.flink.table.connector.sink.DataStreamSinkProvider;
+import org.apache.flink.table.connector.source.DataStreamScanProvider;
+import org.apache.flink.table.connector.source.ScanTableSource;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.factories.FactoryUtil;
+import
org.apache.flink.table.runtime.connector.sink.SinkRuntimeProviderContext;
+import
org.apache.flink.table.runtime.connector.source.ScanRuntimeProviderContext;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+/**
+ * A tool class to construct hoodie flink pipeline.
+ *
+ * <p>How to use ?</p>
+ * Method {@link #builder(String)} returns a pipeline builder. The builder
+ * can then define the hudi table columns, primary keys and partitions.
+ *
+ * <p>An example:</p>
+ * <pre>
+ * HoodiePipeline.Builder builder = HoodiePipeline.builder("myTable");
+ * DataStreamSink<?> sinkStream = builder
+ * .column("f0 int")
+ * .column("f1 varchar(10)")
+ * .column("f2 varchar(20)")
+ * .pk("f0,f1")
+ * .partition("f2")
+ * .sink(input, false);
+ * </pre>
+ */
+public class HoodiePipeline {
+
+ private static final Logger LOG = LogManager.getLogger(HoodiePipeline.class);
+
+ /**
+ * Returns the builder for hoodie pipeline construction.
+ */
+ public static Builder builder(String tableName) {
+ return new Builder(tableName);
+ }
+
+ /**
+ * Builder for hudi source/sink pipeline construction.
+ */
+ public static class Builder {
+ private final String tableName;
+ private final List<String> columns;
+ private final Map<String, String> options;
+
+ private String pk;
+ private List<String> partitions;
+
+ public Builder self() {
+ return this;
+ }
+
+ private Builder(String tableName) {
+ this.tableName = tableName;
+ this.columns = new ArrayList<>();
+ this.options = new HashMap<>();
+ this.partitions = new ArrayList<>();
+ }
+
+ /**
+ * Add a table column definition.
+ *
+ * @param column the column format should be in the form like 'f0 int'
+ */
+ public Builder column(String column) {
+ this.columns.add(column);
+ return self();
+ }
+
+ /**
+ * Add primary keys.
+ */
+ public Builder pk(String... pks) {
+ this.pk = String.join(",", pks);
+ return self();
+ }
+
+ /**
+ * Add partition fields.
+ */
+ public Builder partition(String... partitions) {
+ this.partitions = new ArrayList<>(Arrays.asList(partitions));
+ return self();
+ }
+
+ /**
+ * Add a config option.
+ */
+ public Builder option(ConfigOption<?> option, Object val) {
+ this.options.put(option.key(), val.toString());
+ return self();
+ }
+
+ public Builder option(String key, Object val) {
+ this.options.put(key, val.toString());
+ return self();
+ }
+
+ public Builder options(Map<String, String> options) {
+ this.options.putAll(options);
+ return self();
+ }
+
+ public DataStreamSink<?> sink(DataStream<RowData> input, boolean bounded) {
+ TableDescriptor tableDescriptor = getTableDescriptor();
+ return HoodiePipeline.sink(input, tableDescriptor.getTableId(),
tableDescriptor.getResolvedCatalogTable(), bounded);
+ }
+
+ public TableDescriptor getTableDescriptor() {
+ EnvironmentSettings environmentSettings = EnvironmentSettings
+ .newInstance()
+ .build();
+ TableEnvironmentImpl tableEnv =
TableEnvironmentImpl.create(environmentSettings);
+ String sql = getCreateHoodieTableDDL(this.tableName, this.columns,
this.options, this.pk, this.partitions);
+ tableEnv.executeSql(sql);
+ String currentCatalog = tableEnv.getCurrentCatalog();
+ ResolvedCatalogTable catalogTable = null;
+ String defaultDatabase = null;
+ try {
+ Catalog catalog = tableEnv.getCatalog(currentCatalog).get();
+ defaultDatabase = catalog.getDefaultDatabase();
+ catalogTable = (ResolvedCatalogTable) catalog.getTable(new
ObjectPath(defaultDatabase, this.tableName));
+ } catch (TableNotExistException e) {
+ throw new HoodieException("Create table " + this.tableName + "
exception", e);
+ }
+ ObjectIdentifier tableId = ObjectIdentifier.of(currentCatalog,
defaultDatabase, this.tableName);
+ return new TableDescriptor(tableId, catalogTable);
+ }
+
+ public DataStream<RowData> source(StreamExecutionEnvironment execEnv) {
+ TableDescriptor tableDescriptor = getTableDescriptor();
+ return HoodiePipeline.source(execEnv, tableDescriptor.tableId,
tableDescriptor.getResolvedCatalogTable());
+ }
+ }
+
+ private static String getCreateHoodieTableDDL(
+ String tableName,
+ List<String> fields,
+ Map<String, String> options,
+ String pkField,
+ List<String> partitionField) {
+ StringBuilder builder = new StringBuilder();
+ builder.append("create table ").append(tableName).append("(\n");
+ for (String field : fields) {
+ builder.append(" ").append(field).append(",\n");
+ }
+ builder.append(" PRIMARY KEY(").append(pkField).append(") NOT ENFORCED\n")
+ .append(")\n");
+ if (!partitionField.isEmpty()) {
+ String partitons = partitionField
+ .stream()
+ .map(partitionName -> "`" + partitionName + "`")
+ .collect(Collectors.joining(","));
+ builder.append("PARTITIONED BY (").append(partitons).append(")\n");
+ }
+ builder.append("with (\n"
+ + " 'connector' = 'hudi'");
+ options.forEach((k, v) -> builder.append(",\n")
+ .append(" '").append(k).append("' = '").append(v).append("'"));
+ builder.append("\n)");
+ return builder.toString();
+ }
+
+ /**
+ * low-level sink api for insert a datastream to hoodie table described by
options and schema
+ * @param input The Input DataStream
+ * @param tablePath The tablePath to search a hoodie table in catalog
+ * @param catalogTable The catalog table to describe hoodie table schema
+ * @param isBouned The flag to indicate whether a batch execution mode
+ * @return The data stream sink return by insert a data stream to hoodie
table
+ */
+ private static DataStreamSink<?> sink(DataStream<RowData> input,
ObjectIdentifier tablePath, ResolvedCatalogTable catalogTable, boolean
isBouned) {
+ FactoryUtil.DefaultDynamicTableContext context = new
FactoryUtil.DefaultDynamicTableContext(tablePath, catalogTable,
+ Configuration.fromMap(catalogTable.getOptions()),
Thread.currentThread().getContextClassLoader(), false);
+ HoodieTableFactory hoodieTableFactory = new HoodieTableFactory();
+ return ((DataStreamSinkProvider)
hoodieTableFactory.createDynamicTableSink(context)
+ .getSinkRuntimeProvider(new SinkRuntimeProviderContext(isBouned)))
+ .consumeDataStream(input);
+ }
+
+ /**
+ * low-level source api for read a hoodie table who described by options and
schema as a datastream source
+ * @param execEnv The flink stream execute environment
+ * @param tablePath The tablePath to search a hoodie table in catalog
+ * @param catalogTable The catalog table to describe hoodie table schema
+ * @return the source data stream read from a hoodie table
+ */
+ private static DataStream<RowData> source(StreamExecutionEnvironment
execEnv, ObjectIdentifier tablePath, ResolvedCatalogTable catalogTable) {
+ FactoryUtil.DefaultDynamicTableContext context = new
FactoryUtil.DefaultDynamicTableContext(tablePath, catalogTable,
+ Configuration.fromMap(catalogTable.getOptions()),
Thread.currentThread().getContextClassLoader(), false);
+ HoodieTableFactory hoodieTableFactory = new HoodieTableFactory();
+ DataStreamScanProvider dataStreamScanProvider = (DataStreamScanProvider)
((ScanTableSource) hoodieTableFactory
+ .createDynamicTableSource(context))
+ .getScanRuntimeProvider(new ScanRuntimeProviderContext());
+ return dataStreamScanProvider.produceDataStream(execEnv);
+ }
+
+ /***
+ * a table descriptor for tableId and resolvedCatalogTable.
+ */
Review Comment:
`resolvedCatalogTable..` -> `resolvedCatalogTable.`
--
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]
