davisusanibar commented on code in PR #35570:
URL: https://github.com/apache/arrow/pull/35570#discussion_r1326496961
##########
java/dataset/src/test/java/org/apache/arrow/dataset/substrait/TestAceroSubstraitConsumer.java:
##########
@@ -204,4 +205,170 @@ public void testRunBinaryQueryNamedTableNation() throws
Exception {
}
}
}
+
+ @Test
+ public void testBaseParquetReadWithExtendedExpressionsFilter() throws
Exception {
+ final Schema schema = new Schema(Arrays.asList(
+ Field.nullable("id", new ArrowType.Int(32, true)),
+ Field.nullable("name", new ArrowType.Utf8())
+ ), null);
+ // Substrait Extended Expression: Filter:
+ // Expression 01: WHERE ID < 20
+ String base64EncodedSubstraitFilter =
"Ch4IARIaL2Z1bmN0aW9uc19jb21wYXJpc29uLnlhbWwSEhoQCAIQAhoKbHQ6YW55X2F" +
+
"ueRo3ChwaGggCGgQKAhABIggaBhIECgISACIGGgQKAigUGhdmaWx0ZXJfaWRfbG93ZXJfdGhhbl8yMCIaCgJJRAoETkFNRRIOCgQqAhA"
+
+ "BCgRiAhABGAI=";
+ ByteBuffer substraitExpressionFilter =
getByteBuffer(base64EncodedSubstraitFilter);
+ ParquetWriteSupport writeSupport = ParquetWriteSupport
+ .writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 19, "value_19", 1,
"value_1",
+ 11, "value_11", 21, "value_21", 45, "value_45");
+ ScanOptions options = new ScanOptions.Builder(/*batchSize*/ 32768)
+ .columns(Optional.empty())
+ .substraitFilter(substraitExpressionFilter)
+ .build();
+ try (
+ DatasetFactory datasetFactory = new
FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
+ FileFormat.PARQUET, writeSupport.getOutputURI());
+ 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()) {
+ rowcount += reader.getVectorSchemaRoot().getRowCount();
+
assertTrue(reader.getVectorSchemaRoot().getVector("id").toString().equals("[19,
1, 11]"));
+ assertTrue(reader.getVectorSchemaRoot().getVector("name").toString()
+ .equals("[value_19, value_1, value_11]"));
Review Comment:
Just filled https://github.com/apache/arrow/issues/37728
--
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]
