Skip to content

[BEAM-4417] Support BigQuery's NUMERIC type using Java #5755

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

Merged
kennknowles merged 1 commit into from
Jun 30, 2018
Merged

[BEAM-4417] Support BigQuery's NUMERIC type using Java #5755

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
9 changes: 9 additions & 0 deletions ...e-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryAvroUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import com.google.common.io.BaseEncoding;
import java.math.BigDecimal;
import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.List;
Expand All @@ -53,13 +54,15 @@ class BigQueryAvroUtils {
.put("BYTES", Type.BYTES)
.put("INTEGER", Type.LONG)
.put("FLOAT", Type.DOUBLE)
.put("NUMERIC", Type.STRING)
.put("BOOLEAN", Type.BOOLEAN)
.put("TIMESTAMP", Type.LONG)
.put("RECORD", Type.RECORD)
.put("DATE", Type.STRING)
.put("DATETIME", Type.STRING)
.put("TIME", Type.STRING)
.build();

/**
* Formats BigQuery seconds-since-epoch into String matching JSON export. Thread-safe and
* immutable.
Expand Down Expand Up @@ -194,6 +197,12 @@ private static Object convertRequiredField(
case "FLOAT":
verify(v instanceof Double, "Expected Double, got %s", v.getClass());
return v;
case "NUMERIC":
verify(
v instanceof CharSequence || v instanceof BigDecimal,
"Expected CharSequence (String) or BigDecimal, got %s",
v.getClass());
return v.toString();
case "BOOLEAN":
verify(v instanceof Boolean, "Expected Boolean, got %s", v.getClass());
return v;
Expand Down
2 changes: 1 addition & 1 deletion ...oogle-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ public class BigQueryUtils {
.put(TypeName.INT64, StandardSQLTypeName.INT64)
.put(TypeName.FLOAT, StandardSQLTypeName.FLOAT64)
.put(TypeName.DOUBLE, StandardSQLTypeName.FLOAT64)
.put(TypeName.DECIMAL, StandardSQLTypeName.FLOAT64)
.put(TypeName.DECIMAL, StandardSQLTypeName.NUMERIC)
.put(TypeName.BOOLEAN, StandardSQLTypeName.BOOL)
.put(TypeName.ARRAY, StandardSQLTypeName.ARRAY)
.put(TypeName.ROW, StandardSQLTypeName.STRUCT)
Expand Down
2 changes: 2 additions & 0 deletions ...cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/StandardSQLTypeName.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@ enum StandardSQLTypeName {
INT64,
/** A 64-bit IEEE binary floating-point value. */
FLOAT64,
/** A decimal value with 38 digits of precision and 9 digits of scale. */
NUMERIC,
/** Variable-length character (Unicode) data. */
STRING,
/** Variable-length binary data. */
Expand Down
14 changes: 12 additions & 2 deletions ...oud-platform/src/test/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryAvroUtilsTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import com.google.common.collect.ImmutableList;
import com.google.common.collect.Lists;
import com.google.common.io.BaseEncoding;
import java.math.BigDecimal;
import java.nio.ByteBuffer;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
Expand Down Expand Up @@ -65,6 +66,7 @@ public class BigQueryAvroUtilsTest {
new TableFieldSchema().setName("quality").setType("FLOAT") /* default to NULLABLE */,
new TableFieldSchema().setName("quantity").setType("INTEGER") /* default to NULLABLE */,
new TableFieldSchema().setName("birthday").setType("TIMESTAMP").setMode("NULLABLE"),
new TableFieldSchema().setName("birthdayMoney").setType("NUMERIC").setMode("NULLABLE"),
new TableFieldSchema().setName("flighted").setType("BOOLEAN").setMode("NULLABLE"),
new TableFieldSchema().setName("sound").setType("BYTES").setMode("NULLABLE"),
new TableFieldSchema().setName("anniversaryDate").setType("DATE").setMode("NULLABLE"),
Expand Down Expand Up @@ -100,14 +102,15 @@ public void testConvertGenericRecordToTableRow() throws Exception {
}
{
// Test type conversion for:
// INTEGER, FLOAT, TIMESTAMP, BOOLEAN, BYTES, DATE, DATETIME, TIME.
// INTEGER, FLOAT, NUMERIC, TIMESTAMP, BOOLEAN, BYTES, DATE, DATETIME, TIME.
GenericRecord record = new GenericData.Record(avroSchema);
byte[] soundBytes = "chirp,chirp".getBytes(StandardCharsets.UTF_8);
ByteBuffer soundByteBuffer = ByteBuffer.wrap(soundBytes);
soundByteBuffer.rewind();
record.put("number", 5L);
record.put("quality", 5.0);
record.put("birthday", 5L);
record.put("birthdayMoney", new String("123456789.123456789"));
record.put("flighted", Boolean.TRUE);
record.put("sound", soundByteBuffer);
record.put("anniversaryDate", new Utf8("2000-01-01"));
Expand All @@ -118,6 +121,7 @@ public void testConvertGenericRecordToTableRow() throws Exception {
new TableRow()
.set("number", "5")
.set("birthday", "1970-01-01 00:00:00.000005 UTC")
.set("birthdayMoney", "123456789.123456789")
.set("quality", 5.0)
.set("associates", new ArrayList<TableRow>())
.set("flighted", Boolean.TRUE)
Expand All @@ -135,11 +139,13 @@ public void testConvertGenericRecordToTableRow() throws Exception {
GenericRecord record = new GenericData.Record(avroSchema);
record.put("number", 5L);
record.put("associates", Lists.newArrayList(nestedRecord));
record.put("birthdayMoney", new BigDecimal("987654321.987654321"));
TableRow convertedRow = BigQueryAvroUtils.convertGenericRecordToTableRow(record, tableSchema);
TableRow row =
new TableRow()
.set("associates", Lists.newArrayList(new TableRow().set("species", "other")))
.set("number", "5");
.set("number", "5")
.set("birthdayMoney", "987654321.987654321");
assertEquals(row, convertedRow);
}
}
Expand All @@ -164,6 +170,9 @@ public void testConvertBigQuerySchemaToAvroSchema() {
assertThat(
avroSchema.getField("birthday").schema(),
equalTo(Schema.createUnion(Schema.create(Type.NULL), Schema.create(Type.LONG))));
assertThat(
avroSchema.getField("birthdayMoney").schema(),
equalTo(Schema.createUnion(Schema.create(Type.NULL), Schema.create(Type.STRING))));
assertThat(
avroSchema.getField("flighted").schema(),
equalTo(Schema.createUnion(Schema.create(Type.NULL), Schema.create(Type.BOOLEAN))));
Expand Down Expand Up @@ -224,6 +233,7 @@ static class Bird {
@Nullable Double quality;
@Nullable Long quantity;
@Nullable Long birthday; // Exercises TIMESTAMP.
@Nullable String birthdayMoney; // Exercises NUMERIC.
@Nullable Boolean flighted;
@Nullable ByteBuffer sound;
@Nullable Utf8 anniversaryDate;
Expand Down