nastra commented on code in PR #11247:
URL: https://github.com/apache/iceberg/pull/11247#discussion_r1796746194
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/parquet/vectorized/TestParquetDictionaryEncodedVectorizedReads.java:
##########
@@ -93,4 +125,64 @@ public void testMixedDictionaryNonDictionaryReads() throws
IOException {
true,
BATCH_SIZE);
}
+
+ @Test
+ public void testBinaryNotAllPagesDictionaryEncoded() throws IOException {
+ Schema schema = new Schema(Types.NestedField.required(1, "bytes",
Types.BinaryType.get()));
+ File parquetFile = File.createTempFile("junit", null, temp.toFile());
+ assertThat(parquetFile.delete()).as("Delete should succeed").isTrue();
+
+ Iterable<GenericData.Record> records =
RandomData.generateFallbackData(schema, 500, 0L, 100);
+ try (FileAppender<GenericData.Record> writer =
+ Parquet.write(Files.localOutput(parquetFile))
+ .schema(schema)
+ .set(PARQUET_DICT_SIZE_BYTES, "4096")
+ .set(PARQUET_PAGE_ROW_LIMIT, "100")
+ .build()) {
+ writer.addAll(records);
+ }
+ // After this, parquetFile contains one column chunk of binary data in
five pages,
+ // the first two RLE dictionary encoded, and the remaining three plain
encoded.
+
Review Comment:
```suggestion
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
