vibhatha commented on code in PR #43503:
URL: https://github.com/apache/arrow/pull/43503#discussion_r1701171780
##########
java/dataset/src/test/java/org/apache/arrow/dataset/TestFragmentScanOptions.java:
##########
@@ -102,30 +119,38 @@ public void testCsvConvertOptionsDelimiterNotSet() throws
Exception {
String path = "file://" + getClass().getResource("/").getPath() +
"/data/student.csv";
BufferAllocator allocator = new RootAllocator(Long.MAX_VALUE);
try (ArrowSchema cSchema = ArrowSchema.allocateNew(allocator);
+ ArrowSchema cSchema2 = ArrowSchema.allocateNew(allocator);
CDataDictionaryProvider provider = new CDataDictionaryProvider()) {
Data.exportSchema(allocator, schema, provider, cSchema);
- CsvConvertOptions convertOptions = new
CsvConvertOptions(ImmutableMap.of());
- convertOptions.setArrowSchema(cSchema);
- CsvFragmentScanOptions fragmentScanOptions =
- new CsvFragmentScanOptions(convertOptions, ImmutableMap.of(),
ImmutableMap.of());
+ Data.exportSchema(allocator, schema, provider, cSchema2);
+ CsvFragmentScanOptions fragmentScanOptions1 =
+ create(cSchema, ImmutableMap.of(), ImmutableMap.of(),
ImmutableMap.of());
+ CsvFragmentScanOptions fragmentScanOptions2 =
+ create(cSchema2, ImmutableMap.of(), ImmutableMap.of(),
ImmutableMap.of());
ScanOptions options =
new ScanOptions.Builder(/*batchSize*/ 32768)
.columns(Optional.empty())
- .fragmentScanOptions(fragmentScanOptions)
+ .fragmentScanOptions(fragmentScanOptions1)
.build();
try (DatasetFactory datasetFactory =
new FileSystemDatasetFactory(
- allocator, NativeMemoryPool.getDefault(), FileFormat.CSV,
path);
+ allocator,
+ NativeMemoryPool.getDefault(),
+ FileFormat.CSV,
+ path,
+ Optional.of(fragmentScanOptions2));
Dataset dataset = datasetFactory.finish();
Scanner scanner = dataset.newScan(options);
ArrowReader reader = scanner.scanBatches()) {
-
- assertEquals(schema.getFields(),
reader.getVectorSchemaRoot().getSchema().getFields());
int rowCount = 0;
while (reader.loadNextBatch()) {
- final ValueIterableVector<Integer> idVector =
- (ValueIterableVector<Integer>)
reader.getVectorSchemaRoot().getVector("Id");
- assertThat(idVector.getValueIterable(),
IsIterableContainingInOrder.contains(1, 2, 3));
+ final ValueIterableVector<Text> idVector =
+ (ValueIterableVector<Text>)
+ reader.getVectorSchemaRoot().getVector("Id;Name;Language");
Review Comment:
Is this change necessary?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
