jerqi commented on code in PR #8313:
URL: https://github.com/apache/iceberg/pull/8313#discussion_r1308114522
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkWriteConf.java:
##########
@@ -418,4 +424,95 @@ public String branch() {
return branch;
}
+
+ public String parquetCompressionCodec() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_CODEC)
+ .sessionConf(SparkSQLProperties.COMPRESSION_CODEC)
+ .tableProperty(TableProperties.PARQUET_COMPRESSION)
+ .defaultValue(TableProperties.PARQUET_COMPRESSION_DEFAULT)
+ .parse();
+ }
+
+ public String parquetCompressionLevel() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_LEVEL)
+ .sessionConf(SparkSQLProperties.COMPRESSION_LEVEL)
+ .tableProperty(TableProperties.PARQUET_COMPRESSION_LEVEL)
+ .defaultValue(TableProperties.PARQUET_COMPRESSION_LEVEL_DEFAULT)
+ .parseOptional();
+ }
+
+ public String avroCompressionCodec() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_CODEC)
+ .sessionConf(SparkSQLProperties.COMPRESSION_CODEC)
+ .tableProperty(TableProperties.AVRO_COMPRESSION)
+ .defaultValue(TableProperties.AVRO_COMPRESSION_DEFAULT)
+ .parse();
+ }
+
+ public String avroCompressionLevel() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_LEVEL)
+ .sessionConf(SparkSQLProperties.COMPRESSION_LEVEL)
+ .tableProperty(TableProperties.AVRO_COMPRESSION_LEVEL)
+ .defaultValue(TableProperties.AVRO_COMPRESSION_LEVEL_DEFAULT)
+ .parseOptional();
+ }
+
+ public String orcCompressionCodec() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_CODEC)
+ .sessionConf(SparkSQLProperties.COMPRESSION_CODEC)
+ .tableProperty(TableProperties.ORC_COMPRESSION)
+ .defaultValue(TableProperties.ORC_COMPRESSION_DEFAULT)
+ .parse();
+ }
+
+ public String orcCompressionStrategy() {
+ return confParser
+ .stringConf()
+ .option(SparkWriteOptions.COMPRESSION_STRATEGY)
+ .sessionConf(SparkSQLProperties.COMPRESSION_STRATEGY)
+ .tableProperty(TableProperties.ORC_COMPRESSION_STRATEGY)
+ .defaultValue(TableProperties.ORC_COMPRESSION_STRATEGY_DEFAULT)
+ .parse();
+ }
+
+ public Map<String, String> writeProperties(FileFormat format) {
+ Map<String, String> writeProperties = Maps.newHashMap();
+
+ switch (format) {
+ case PARQUET:
+ writeProperties.put(PARQUET_COMPRESSION, parquetCompressionCodec());
+ String parquetCompressionLevel = parquetCompressionLevel();
+ if (parquetCompressionLevel != null) {
+ writeProperties.put(PARQUET_COMPRESSION_LEVEL,
parquetCompressionLevel);
+ }
+
+ break;
+ case AVRO:
+ writeProperties.put(AVRO_COMPRESSION, avroCompressionCodec());
+ String avroCompressionLevel = avroCompressionLevel();
+ if (avroCompressionLevel != null) {
+ writeProperties.put(AVRO_COMPRESSION_LEVEL, avroCompressionLevel());
+ }
+
+ break;
+ case ORC:
+ writeProperties.put(ORC_COMPRESSION, orcCompressionCodec());
+ writeProperties.put(ORC_COMPRESSION_STRATEGY,
orcCompressionStrategy());
+ break;
+ default:
+ throw new IllegalArgumentException(String.format("Unknown file format
%s", format));
Review Comment:
I refer to the Flink's implement. Flink choose to fail the query. Is it
better to find it as soon as we can if we use wrong parameter?
--
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]
