nastra commented on code in PR #8808:
URL: https://github.com/apache/iceberg/pull/8808#discussion_r1358331014
##########
flink/v1.15/flink/src/test/java/org/apache/iceberg/flink/data/TestFlinkParquetReader.java:
##########
@@ -90,17 +92,72 @@ public void testTwoLevelList() throws IOException {
.createReaderFunc(type -> FlinkParquetReaders.buildReader(schema,
type))
.build()) {
Iterator<RowData> rows = reader.iterator();
- Assert.assertTrue("Should have at least one row", rows.hasNext());
+ assertThat(rows.hasNext()).as("Should have at least one row").isTrue();
RowData rowData = rows.next();
- Assert.assertArrayEquals(rowData.getArray(0).getBinary(0), expectedByte);
- Assert.assertArrayEquals(rowData.getBinary(1), expectedByte);
- Assert.assertFalse("Should not have more than one row", rows.hasNext());
+ assertThat(expectedByte).isEqualTo(rowData.getArray(0).getBinary(0));
+ assertThat(expectedByte).isEqualTo(rowData.getBinary(1));
+ assertThat(rows.hasNext()).as("Should not have more than one
row").isFalse();
+ }
+ }
+
+ @Test
+ public void testReadBinaryFieldAsString() throws IOException {
+ Schema schemaForWriteBinary = new Schema(optional(1, "strbytes",
Types.BinaryType.get()));
+ org.apache.avro.Schema avroSchema =
AvroSchemaUtil.convert(schemaForWriteBinary.asStruct());
+
+ File testFile = temp.newFile();
+ assertThat(testFile.delete()).isTrue();
+
+ ParquetWriter<GenericRecord> writer =
+ AvroParquetWriter.<GenericRecord>builder(new Path(testFile.toURI()))
+ .withDataModel(GenericData.get())
+ .withSchema(avroSchema)
+ .build();
+
+ String expectedString = "hello";
+
+ GenericRecordBuilder recordBuilder = new GenericRecordBuilder(avroSchema);
+ ByteBuffer expectedBinary =
ByteBuffer.wrap(expectedString.getBytes(StandardCharsets.UTF_8));
+ recordBuilder.set("strbytes", expectedBinary);
+ GenericData.Record expectedRecord = recordBuilder.build();
+
+ writer.write(expectedRecord);
+ writer.close();
Review Comment:
rather than calling `close()` manually, I think it would be better to use
`try-with-resources` here:
```
GenericRecordBuilder recordBuilder = new GenericRecordBuilder(avroSchema);
ByteBuffer expectedBinary =
ByteBuffer.wrap(expectedString.getBytes(StandardCharsets.UTF_8));
recordBuilder.set("strbytes", expectedBinary);
GenericData.Record expectedRecord = recordBuilder.build();
try (ParquetWriter<GenericRecord> writer =
AvroParquetWriter.<GenericRecord>builder(new Path(testFile.toURI()))
.withDataModel(GenericData.get())
.withSchema(avroSchema)
.build()) {
writer.write(expectedRecord);
}
```
##########
flink/v1.15/flink/src/test/java/org/apache/iceberg/flink/data/TestFlinkParquetReader.java:
##########
@@ -90,17 +92,72 @@ public void testTwoLevelList() throws IOException {
.createReaderFunc(type -> FlinkParquetReaders.buildReader(schema,
type))
.build()) {
Iterator<RowData> rows = reader.iterator();
- Assert.assertTrue("Should have at least one row", rows.hasNext());
+ assertThat(rows.hasNext()).as("Should have at least one row").isTrue();
RowData rowData = rows.next();
- Assert.assertArrayEquals(rowData.getArray(0).getBinary(0), expectedByte);
- Assert.assertArrayEquals(rowData.getBinary(1), expectedByte);
- Assert.assertFalse("Should not have more than one row", rows.hasNext());
+ assertThat(expectedByte).isEqualTo(rowData.getArray(0).getBinary(0));
+ assertThat(expectedByte).isEqualTo(rowData.getBinary(1));
+ assertThat(rows.hasNext()).as("Should not have more than one
row").isFalse();
+ }
+ }
+
+ @Test
+ public void testReadBinaryFieldAsString() throws IOException {
+ Schema schemaForWriteBinary = new Schema(optional(1, "strbytes",
Types.BinaryType.get()));
+ org.apache.avro.Schema avroSchema =
AvroSchemaUtil.convert(schemaForWriteBinary.asStruct());
+
+ File testFile = temp.newFile();
+ assertThat(testFile.delete()).isTrue();
+
+ ParquetWriter<GenericRecord> writer =
+ AvroParquetWriter.<GenericRecord>builder(new Path(testFile.toURI()))
+ .withDataModel(GenericData.get())
+ .withSchema(avroSchema)
+ .build();
+
+ String expectedString = "hello";
+
+ GenericRecordBuilder recordBuilder = new GenericRecordBuilder(avroSchema);
+ ByteBuffer expectedBinary =
ByteBuffer.wrap(expectedString.getBytes(StandardCharsets.UTF_8));
+ recordBuilder.set("strbytes", expectedBinary);
+ GenericData.Record expectedRecord = recordBuilder.build();
+
+ writer.write(expectedRecord);
+ writer.close();
Review Comment:
rather than calling `close()` manually, I think it would be better to use
`try-with-resources` here:
```
GenericRecordBuilder recordBuilder = new
GenericRecordBuilder(avroSchema);
ByteBuffer expectedBinary =
ByteBuffer.wrap(expectedString.getBytes(StandardCharsets.UTF_8));
recordBuilder.set("strbytes", expectedBinary);
GenericData.Record expectedRecord = recordBuilder.build();
try (ParquetWriter<GenericRecord> writer =
AvroParquetWriter.<GenericRecord>builder(new Path(testFile.toURI()))
.withDataModel(GenericData.get())
.withSchema(avroSchema)
.build()) {
writer.write(expectedRecord);
}
```
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
