nssalian commented on code in PR #16327:
URL: https://github.com/apache/iceberg/pull/16327#discussion_r3314200846
##########
parquet/src/test/java/org/apache/iceberg/parquet/TestParquetDataWriter.java:
##########
@@ -543,4 +546,69 @@ protected int resolveColumnIndex(Void engineSchema, String
columnName) {
variantSchema.asStruct(), variantRecords.get(i),
writtenRecords.get(i));
}
}
+
+ @ParameterizedTest
+ @ValueSource(strings = {"gzip", "snappy", "zstd", "uncompressed"})
+ public void testRowGroupSizeEnforcedWhenCompressionEnabled(String codec)
throws IOException {
+ // With uncompressed tracking, row groups split at the configured target
+ DataFile dataFile = writeCompressibleRecords(codec, true);
+
+ assertThat(dataFile.recordCount()).as("Record count should
match").isEqualTo(100);
+ assertThat(dataFile.splitOffsets().size())
+ .as("Row group count should reflect enforcement of the 8 MB target")
+ .isGreaterThanOrEqualTo(4);
+ }
+
+ @Test
+ public void testDefaultPathUsesCompressedSize() throws IOException {
+ // Without uncompressed tracking, compressed bytes never hit the target
+ DataFile dataFile = writeCompressibleRecords("gzip", false);
Review Comment:
Used snappy instead
--
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]
