Skip to content

resolve saveToEs saves case classes fields with NULL values #998 #1478

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.

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

Merged
merged 3 commits into from
Jan 6, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -27,11 +27,13 @@
import org.elasticsearch.hadoop.serialization.field.FieldFilter;
import org.elasticsearch.hadoop.serialization.field.FieldFilter.NumberedInclude;
import org.elasticsearch.hadoop.util.StringUtils;
import static org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_SPARK_DATAFRAME_WRITE_NULL_VALUES_DEFAULT;

public abstract class FilteringValueWriter<T> implements ValueWriter<T>, SettingsAware {

private List<NumberedInclude> includes;
private List<String> excludes;
private Boolean writeNullValues = Boolean.parseBoolean(ES_SPARK_DATAFRAME_WRITE_NULL_VALUES_DEFAULT);

@Override
public void setSettings(Settings settings) {
Expand All @@ -41,10 +43,15 @@ public void setSettings(Settings settings) {
includes.add(new NumberedInclude(include));
}
excludes = StringUtils.tokenize(settings.getMappingExcludes());
writeNullValues = settings.getDataFrameWriteNullValues();
}

protected boolean shouldKeep(String parentField, String name) {
name = StringUtils.hasText(parentField) ? parentField + "." + name : name;
return FieldFilter.filter(name, includes, excludes).matched;
}

protected boolean hasWriteNullValues() {
return writeNullValues;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -61,10 +61,12 @@ class ScalaValueWriter(writeUnknownTypes: Boolean = false) extends JdkValueWrite
generator.writeBeginObject()
for ((k, v) <- m) {
if (shouldKeep(parentField, k.toString)) {
generator.writeFieldName(k.toString)
val result = doWrite(v, generator, k.toString)
if (!result.isSuccesful) {
return result
if (v != None && v!= null && v != () || hasWriteNullValues) {
generator.writeFieldName(k.toString)
val result = doWrite(v, generator, k.toString)
if (!result.isSuccesful) {
return result
}
}
}
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,58 @@ class ScalaValueWriterTest {
println(serialize(node1))
}

@Test
def testCaseClassWithNone(): Unit = {

case class TestCaseClass(option : Option[String])
val caseClass = TestCaseClass(None)

assertEquals("""{}""", serialize(caseClass))
}

@Test
def testCaseClassWithSome(): Unit = {

case class TestCaseClass(option : Option[String])
val caseClass = TestCaseClass(Some("value"))

assertEquals("""{"option":"value"}""", serialize(caseClass))
}


@Test
def testCaseClassWithSomeAndNone(): Unit = {

case class TestCaseClass(option1 : Option[String], option2 : Option[String])
val caseClass = TestCaseClass(None, Some("value2"))

assertEquals("""{"option2":"value2"}""", serialize(caseClass))
}


@Test
def testCaseClassWithInnerObject(): Unit = {

case class TestCaseClass(option1 : Option[String], option2 : Option[TestCaseClassInner])
case class TestCaseClassInner(option1 : Option[String], option2 : Option[String])
val caseClass = TestCaseClass(None, Some(TestCaseClassInner(option1 = Some("value1") , option2 = None)))

assertEquals("""{"option2":{"option1":"value1"}}""", serialize(caseClass))
}

@Test
def testCaseClassWithInnerObjectAndNullSetting(): Unit = {

case class TestCaseClass(option1: Option[String], option2: Option[TestCaseClassInner])
case class TestCaseClassInner(option1: Option[String], option2: Option[String])
val caseClass = TestCaseClass(None, Some(TestCaseClassInner(option1 = Some("value1"), option2 = None)))

val settings = new TestSettings()
settings.setProperty(ConfigurationOptions.ES_SPARK_DATAFRAME_WRITE_NULL_VALUES, "true")

assertEquals("""{"option1":null,"option2":{"option1":"value1","option2":null}}""", serialize(caseClass, settings))
}

@Test
def testDate(): Unit = {
val date = new Date(1420114230123l)
Expand Down