danny0405 commented on code in PR #7978:
URL: https://github.com/apache/hudi/pull/7978#discussion_r1119846515
##########
hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/io/storage/row/TestHoodieInternalRowParquetWriter.java:
##########
@@ -123,6 +125,45 @@ public void testProperWriting(boolean
parquetWriteLegacyFormatEnabled) throws Ex
});
}
+ @Test
+ @Timeout(value = 60)
+ public void testFileSizeCheck() throws Exception {
+ HoodieWriteConfig.Builder writeConfigBuilder =
+ SparkDatasetTestUtils.getConfigBuilder(basePath, timelineServicePort);
+
+ HoodieRowParquetWriteSupport writeSupport =
getWriteSupport(writeConfigBuilder, hadoopConf, true);
+ HoodieWriteConfig cfg = writeConfigBuilder.build();
+
+ // Make the written records could exceed maxRowCountForSizeCheck
+ cfg.setValue(HoodieStorageConfig.PARQUET_MAX_FILE_SIZE, String.valueOf(5 *
1024 * 1024));
+ HoodieParquetConfig<HoodieRowParquetWriteSupport> parquetConfig = new
HoodieParquetConfig<>(writeSupport,
+ CompressionCodecName.SNAPPY, cfg.getParquetBlockSize(),
cfg.getParquetPageSize(), cfg.getParquetMaxFileSize(),
+ writeSupport.getHadoopConf(), cfg.getParquetCompressionRatio(),
cfg.parquetDictionaryEnabled());
+
+ Path filePath = new Path(basePath + "/check_file_size.parquet");
+
+ try (HoodieInternalRowParquetWriter writer = new
HoodieInternalRowParquetWriter(filePath, parquetConfig)) {
+
+ while (writer.canWrite()) {
+ Dataset<Row> inputRows =
SparkDatasetTestUtils.getRandomRows(sqlContext, 100,
+ HoodieTestDataGenerator.DEFAULT_FIRST_PARTITION_PATH, false);
+ StructType schema = inputRows.schema();
+ List<InternalRow> rows =
SparkDatasetTestUtils.toInternalRows(inputRows, SparkDatasetTestUtils.ENCODER);
+ for (InternalRow row : rows) {
+ if (writer.canWrite()) {
+
writer.writeRow(row.getUTF8String(schema.fieldIndex("record_key")), row);
+ } else {
+ break;
+ }
+ }
+ }
+
+ long avgRecordSize = writer.getDataSize() /
writer.getWrittenRecordCount();
+ assertTrue(writer.getDataSize() > cfg.getParquetMaxFileSize() -
avgRecordSize * 2,
+ "The writer stops write new records while the file doesn't hint the
max file size limit");
+ }
Review Comment:
Do you mean doesn't reach for phrase `doesn't hint` ?
--
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]
