Skip to content

ARROW-674: [Java] Support additional Timestamp timezone metadata #408

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

Closed
julienledem wants to merge 1 commit into from
Closed

ARROW-674: [Java] Support additional Timestamp timezone metadata #408

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
2 changes: 1 addition & 1 deletion java/vector/src/main/codegen/data/ArrowTypes.tdd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@
},
{
name: "Timestamp",
fields: [{name: "unit", type: short, valueType: TimeUnit}]
fields: [{name: "unit", type: short, valueType: TimeUnit}, {name: "timezone", type: String}]
},
{
name: "Interval",
Expand Down
16 changes: 8 additions & 8 deletions java/vector/src/main/java/org/apache/arrow/vector/types/Types.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,10 +109,10 @@ public class Types {
private static final Field UINT8_FIELD = new Field("", true, new Int(64, false), null);
private static final Field DATE_FIELD = new Field("", true, Date.INSTANCE, null);
private static final Field TIME_FIELD = new Field("", true, new Time(TimeUnit.MILLISECOND, 32), null);
private static final Field TIMESTAMPSEC_FIELD = new Field("", true, new Timestamp(TimeUnit.SECOND), null);
private static final Field TIMESTAMPMILLI_FIELD = new Field("", true, new Timestamp(TimeUnit.MILLISECOND), null);
private static final Field TIMESTAMPMICRO_FIELD = new Field("", true, new Timestamp(TimeUnit.MICROSECOND), null);
private static final Field TIMESTAMPNANO_FIELD = new Field("", true, new Timestamp(TimeUnit.NANOSECOND), null);
private static final Field TIMESTAMPSEC_FIELD = new Field("", true, new Timestamp(TimeUnit.SECOND, "UTC"), null);
private static final Field TIMESTAMPMILLI_FIELD = new Field("", true, new Timestamp(TimeUnit.MILLISECOND, "UTC"), null);
private static final Field TIMESTAMPMICRO_FIELD = new Field("", true, new Timestamp(TimeUnit.MICROSECOND, "UTC"), null);
private static final Field TIMESTAMPNANO_FIELD = new Field("", true, new Timestamp(TimeUnit.NANOSECOND, "UTC"), null);
private static final Field INTERVALDAY_FIELD = new Field("", true, new Interval(IntervalUnit.DAY_TIME), null);
private static final Field INTERVALYEAR_FIELD = new Field("", true, new Interval(IntervalUnit.YEAR_MONTH), null);
private static final Field FLOAT4_FIELD = new Field("", true, new FloatingPoint(FloatingPointPrecision.SINGLE), null);
Expand Down Expand Up @@ -252,7 +252,7 @@ public FieldWriter getNewFieldWriter(ValueVector vector) {
}
},
// time in second from the Unix epoch, 00:00:00.000000 on 1 January 1970, UTC.
TIMESTAMPSEC(new Timestamp(org.apache.arrow.vector.types.TimeUnit.SECOND)) {
TIMESTAMPSEC(new Timestamp(org.apache.arrow.vector.types.TimeUnit.SECOND, "UTC")) {
@Override
public Field getField() {
return TIMESTAMPSEC_FIELD;
Expand All @@ -269,7 +269,7 @@ public FieldWriter getNewFieldWriter(ValueVector vector) {
}
},
// time in millis from the Unix epoch, 00:00:00.000 on 1 January 1970, UTC.
TIMESTAMPMILLI(new Timestamp(org.apache.arrow.vector.types.TimeUnit.MILLISECOND)) {
TIMESTAMPMILLI(new Timestamp(org.apache.arrow.vector.types.TimeUnit.MILLISECOND, "UTC")) {
@Override
public Field getField() {
return TIMESTAMPMILLI_FIELD;
Expand All @@ -286,7 +286,7 @@ public FieldWriter getNewFieldWriter(ValueVector vector) {
}
},
// time in microsecond from the Unix epoch, 00:00:00.000000 on 1 January 1970, UTC.
TIMESTAMPMICRO(new Timestamp(org.apache.arrow.vector.types.TimeUnit.MICROSECOND)) {
TIMESTAMPMICRO(new Timestamp(org.apache.arrow.vector.types.TimeUnit.MICROSECOND, "UTC")) {
@Override
public Field getField() {
return TIMESTAMPMICRO_FIELD;
Expand All @@ -303,7 +303,7 @@ public FieldWriter getNewFieldWriter(ValueVector vector) {
}
},
// time in nanosecond from the Unix epoch, 00:00:00.000000000 on 1 January 1970, UTC.
TIMESTAMPNANO(new Timestamp(org.apache.arrow.vector.types.TimeUnit.NANOSECOND)) {
TIMESTAMPNANO(new Timestamp(org.apache.arrow.vector.types.TimeUnit.NANOSECOND, "UTC")) {
@Override
public Field getField() {
return TIMESTAMPNANO_FIELD;
Expand Down
2 changes: 1 addition & 1 deletion java/vector/src/test/java/org/apache/arrow/vector/pojo/TestConvert.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ public void nestedSchema() {
new Field("child4.1", true, Utf8.INSTANCE, null)
)));
childrenBuilder.add(new Field("child5", true, new Union(UnionMode.Sparse, new int[] { MinorType.TIMESTAMPMILLI.ordinal(), MinorType.FLOAT8.ordinal() } ), ImmutableList.<Field>of(
new Field("child5.1", true, new Timestamp(TimeUnit.MILLISECOND), null),
new Field("child5.1", true, new Timestamp(TimeUnit.MILLISECOND, "UTC"), null),
new Field("child5.2", true, new FloatingPoint(DOUBLE), ImmutableList.<Field>of())
)));
Schema initialSchema = new Schema(childrenBuilder.build());
Expand Down
90 changes: 56 additions & 34 deletions java/vector/src/test/java/org/apache/arrow/vector/types/pojo/TestSchema.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,20 @@
import org.apache.arrow.vector.types.IntervalUnit;
import org.apache.arrow.vector.types.TimeUnit;
import org.apache.arrow.vector.types.UnionMode;
import org.apache.arrow.vector.types.pojo.ArrowType.Binary;
import org.apache.arrow.vector.types.pojo.ArrowType.Bool;
import org.apache.arrow.vector.types.pojo.ArrowType.Date;
import org.apache.arrow.vector.types.pojo.ArrowType.Decimal;
import org.apache.arrow.vector.types.pojo.ArrowType.FloatingPoint;
import org.apache.arrow.vector.types.pojo.ArrowType.Int;
import org.apache.arrow.vector.types.pojo.ArrowType.Interval;
import org.apache.arrow.vector.types.pojo.ArrowType.List;
import org.apache.arrow.vector.types.pojo.ArrowType.Null;
import org.apache.arrow.vector.types.pojo.ArrowType.Struct;
import org.apache.arrow.vector.types.pojo.ArrowType.Time;
import org.apache.arrow.vector.types.pojo.ArrowType.Timestamp;
import org.apache.arrow.vector.types.pojo.ArrowType.Union;
import org.apache.arrow.vector.types.pojo.ArrowType.Utf8;
import org.junit.Test;

public class TestSchema {
Expand All @@ -42,46 +56,48 @@ private static Field field(String name, ArrowType type, Field... children) {
@Test
public void testComplex() throws IOException {
Schema schema = new Schema(asList(
field("a", false, new ArrowType.Int(8, true)),
field("b", new ArrowType.Struct(),
field("c", new ArrowType.Int(16, true)),
field("d", new ArrowType.Utf8())),
field("e", new ArrowType.List(), field(null, new ArrowType.Date())),
field("f", new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
field("g", new ArrowType.Timestamp(TimeUnit.MILLISECOND)),
field("h", new ArrowType.Interval(IntervalUnit.DAY_TIME))
field("a", false, new Int(8, true)),
field("b", new Struct(),
field("c", new Int(16, true)),
field("d", new Utf8())),
field("e", new List(), field(null, new Date())),
field("f", new FloatingPoint(FloatingPointPrecision.SINGLE)),
field("g", new Timestamp(TimeUnit.MILLISECOND, "UTC")),
field("h", new Timestamp(TimeUnit.MICROSECOND, null)),
field("i", new Interval(IntervalUnit.DAY_TIME))
));
roundTrip(schema);
assertEquals(
"Schema<a: Int(8, true) not null, b: Struct<c: Int(16, true), d: Utf8>, e: List<Date>, f: FloatingPoint(SINGLE), g: Timestamp(MILLISECOND), h: Interval(DAY_TIME)>",
"Schema<a: Int(8, true) not null, b: Struct<c: Int(16, true), d: Utf8>, e: List<Date>, f: FloatingPoint(SINGLE), g: Timestamp(MILLISECOND, UTC), h: Timestamp(MICROSECOND, null), i: Interval(DAY_TIME)>",
schema.toString());
}

@Test
public void testAll() throws IOException {
Schema schema = new Schema(asList(
field("a", false, new ArrowType.Null()),
field("b", new ArrowType.Struct(), field("ba", new ArrowType.Null())),
field("c", new ArrowType.List(), field("ca", new ArrowType.Null())),
field("d", new ArrowType.Union(UnionMode.Sparse, new int[] {1, 2, 3}), field("da", new ArrowType.Null())),
field("e", new ArrowType.Int(8, true)),
field("f", new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
field("g", new ArrowType.Utf8()),
field("h", new ArrowType.Binary()),
field("i", new ArrowType.Bool()),
field("j", new ArrowType.Decimal(5, 5)),
field("k", new ArrowType.Date()),
field("l", new ArrowType.Time(TimeUnit.MILLISECOND, 32)),
field("m", new ArrowType.Timestamp(TimeUnit.MILLISECOND)),
field("n", new ArrowType.Interval(IntervalUnit.DAY_TIME))
field("a", false, new Null()),
field("b", new Struct(), field("ba", new Null())),
field("c", new List(), field("ca", new Null())),
field("d", new Union(UnionMode.Sparse, new int[] {1, 2, 3}), field("da", new Null())),
field("e", new Int(8, true)),
field("f", new FloatingPoint(FloatingPointPrecision.SINGLE)),
field("g", new Utf8()),
field("h", new Binary()),
field("i", new Bool()),
field("j", new Decimal(5, 5)),
field("k", new Date()),
field("l", new Time(TimeUnit.MILLISECOND, 32)),
field("m", new Timestamp(TimeUnit.MILLISECOND, "UTC")),
field("n", new Timestamp(TimeUnit.MICROSECOND, null)),
field("o", new Interval(IntervalUnit.DAY_TIME))
));
roundTrip(schema);
}

@Test
public void testUnion() throws IOException {
Schema schema = new Schema(asList(
field("d", new ArrowType.Union(UnionMode.Sparse, new int[] {1, 2, 3}), field("da", new ArrowType.Null()))
field("d", new Union(UnionMode.Sparse, new int[] {1, 2, 3}), field("da", new Null()))
));
roundTrip(schema);
contains(schema, "Sparse");
Expand All @@ -90,20 +106,26 @@ public void testUnion() throws IOException {
@Test
public void testTS() throws IOException {
Schema schema = new Schema(asList(
field("a", new ArrowType.Timestamp(TimeUnit.SECOND)),
field("b", new ArrowType.Timestamp(TimeUnit.MILLISECOND)),
field("c", new ArrowType.Timestamp(TimeUnit.MICROSECOND)),
field("d", new ArrowType.Timestamp(TimeUnit.NANOSECOND))
field("a", new Timestamp(TimeUnit.SECOND, "UTC")),
field("b", new Timestamp(TimeUnit.MILLISECOND, "UTC")),
field("c", new Timestamp(TimeUnit.MICROSECOND, "UTC")),
field("d", new Timestamp(TimeUnit.NANOSECOND, "UTC")),
field("e", new Timestamp(TimeUnit.SECOND, null)),
field("f", new Timestamp(TimeUnit.MILLISECOND, null)),
field("g", new Timestamp(TimeUnit.MICROSECOND, null)),
field("h", new Timestamp(TimeUnit.NANOSECOND, null))
));
roundTrip(schema);
contains(schema, "SECOND", "MILLISECOND", "MICROSECOND", "NANOSECOND");
assertEquals(
"Schema<a: Timestamp(SECOND, UTC), b: Timestamp(MILLISECOND, UTC), c: Timestamp(MICROSECOND, UTC), d: Timestamp(NANOSECOND, UTC), e: Timestamp(SECOND, null), f: Timestamp(MILLISECOND, null), g: Timestamp(MICROSECOND, null), h: Timestamp(NANOSECOND, null)>",
schema.toString());
}

@Test
public void testInterval() throws IOException {
Schema schema = new Schema(asList(
field("a", new ArrowType.Interval(IntervalUnit.YEAR_MONTH)),
field("b", new ArrowType.Interval(IntervalUnit.DAY_TIME))
field("a", new Interval(IntervalUnit.YEAR_MONTH)),
field("b", new Interval(IntervalUnit.DAY_TIME))
));
roundTrip(schema);
contains(schema, "YEAR_MONTH", "DAY_TIME");
Expand All @@ -112,9 +134,9 @@ public void testInterval() throws IOException {
@Test
public void testFP() throws IOException {
Schema schema = new Schema(asList(
field("a", new ArrowType.FloatingPoint(FloatingPointPrecision.HALF)),
field("b", new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
field("c", new ArrowType.FloatingPoint(FloatingPointPrecision.DOUBLE))
field("a", new FloatingPoint(FloatingPointPrecision.HALF)),
field("b", new FloatingPoint(FloatingPointPrecision.SINGLE)),
field("c", new FloatingPoint(FloatingPointPrecision.DOUBLE))
));
roundTrip(schema);
contains(schema, "HALF", "SINGLE", "DOUBLE");
Expand Down