lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-583] Code Cleanup, remove redundant code, and other changes (#1237)

Browse Source
This commit is contained in:
Suneel Marthi
2020-02-02 11:03:44 +01:00
committed by GitHub
parent f27c7a16c6
commit 5b7bb142dc
69 changed files with 447 additions and 582 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
hudi-spark/src/main/java/org/apache/hudi/DataSourceUtils.java
View File

@@ -43,7 +43,7 @@ import org.apache.spark.api.java.JavaSparkContext;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
@@ -127,7 +127,7 @@ public class DataSourceUtils {
}
public static void checkRequiredProperties(TypedProperties props, List<String> checkPropNames) {
checkPropNames.stream().forEach(prop -> {
checkPropNames.forEach(prop -> {
if (!props.containsKey(prop)) {
throw new HoodieNotSupportedException("Required property " + prop + " is missing");
}
@@ -182,19 +182,13 @@ public class DataSourceUtils {
@SuppressWarnings("unchecked")
public static JavaRDD<HoodieRecord> dropDuplicates(JavaSparkContext jssc, JavaRDD<HoodieRecord> incomingHoodieRecords,
HoodieWriteConfig writeConfig, Option<EmbeddedTimelineService> timelineService) {
HoodieReadClient client = null;
try {
client = new HoodieReadClient<>(jssc, writeConfig, timelineService);
try (HoodieReadClient client = new HoodieReadClient<>(jssc, writeConfig, timelineService)) {
return client.tagLocation(incomingHoodieRecords)
.filter(r -> !((HoodieRecord<HoodieRecordPayload>) r).isCurrentLocationKnown());
} catch (TableNotFoundException e) {
// this will be executed when there is no hoodie table yet
// so no dups to drop
return incomingHoodieRecords;
} finally {
if (null != client) {
client.close();
}
}
}
@@ -207,12 +201,12 @@ public class DataSourceUtils {
}
public static HiveSyncConfig buildHiveSyncConfig(TypedProperties props, String basePath) {
checkRequiredProperties(props, Arrays.asList(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY()));
checkRequiredProperties(props, Collections.singletonList(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY()));
HiveSyncConfig hiveSyncConfig = new HiveSyncConfig();
hiveSyncConfig.basePath = basePath;
hiveSyncConfig.usePreApacheInputFormat =
props.getBoolean(DataSourceWriteOptions.HIVE_USE_PRE_APACHE_INPUT_FORMAT_OPT_KEY(),
Boolean.valueOf(DataSourceWriteOptions.DEFAULT_USE_PRE_APACHE_INPUT_FORMAT_OPT_VAL()));
Boolean.parseBoolean(DataSourceWriteOptions.DEFAULT_USE_PRE_APACHE_INPUT_FORMAT_OPT_VAL()));
hiveSyncConfig.databaseName = props.getString(DataSourceWriteOptions.HIVE_DATABASE_OPT_KEY(),
DataSourceWriteOptions.DEFAULT_HIVE_DATABASE_OPT_VAL());
hiveSyncConfig.tableName = props.getString(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY());

4
hudi-spark/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
View File

@@ -52,7 +52,7 @@ object AvroConversionUtils {
}
def createRddForDeletes(df: DataFrame, rowField: String, partitionField: String): RDD[HoodieKey] = {
df.rdd.map(row => (new HoodieKey(row.getAs[String](rowField), row.getAs[String](partitionField))))
df.rdd.map(row => new HoodieKey(row.getAs[String](rowField), row.getAs[String](partitionField)))
}
def createDataFrame(rdd: RDD[GenericRecord], schemaStr: String, ss: SparkSession): Dataset[Row] = {
@@ -67,7 +67,7 @@ object AvroConversionUtils {
val convertor = AvroConversionHelper.createConverterToRow(schema, dataType)
records.map { x => convertor(x).asInstanceOf[Row] }
}
}, convertAvroSchemaToStructType(new Schema.Parser().parse(schemaStr))).asInstanceOf[Dataset[Row]]
}, convertAvroSchemaToStructType(new Schema.Parser().parse(schemaStr)))
}
}

2
hudi-spark/src/main/scala/org/apache/hudi/DefaultSource.scala
View File

@@ -63,7 +63,7 @@ class DefaultSource extends RelationProvider
sqlContext.sparkContext.hadoopConfiguration.setClass(
"mapreduce.input.pathFilter.class",
classOf[HoodieROTablePathFilter],
classOf[org.apache.hadoop.fs.PathFilter]);
classOf[org.apache.hadoop.fs.PathFilter])
log.info("Constructing hoodie (as parquet) data source with options :" + parameters)
log.warn("Snapshot view not supported yet via data source, for MERGE_ON_READ tables. " +

4
hudi-spark/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala
View File

@@ -77,7 +77,7 @@ private[hudi] object HoodieSparkSqlWriter {
val jsc = new JavaSparkContext(sparkContext)
val basePath = new Path(parameters("path"))
val commitTime = HoodieActiveTimeline.createNewInstantTime();
val commitTime = HoodieActiveTimeline.createNewInstantTime()
val fs = basePath.getFileSystem(sparkContext.hadoopConfiguration)
var exists = fs.exists(new Path(basePath, HoodieTableMetaClient.METAFOLDER_NAME))
@@ -282,7 +282,7 @@ private[hudi] object HoodieSparkSqlWriter {
client.close()
commitSuccess && syncHiveSucess
} else {
log.error(s"$operation failed with ${errorCount} errors :");
log.error(s"$operation failed with $errorCount errors :")
if (log.isTraceEnabled) {
log.trace("Printing out the top 100 errors")
writeStatuses.rdd.filter(ws => ws.hasErrors)