IS
Т.е. он накинет предикат уже после чтения csv
Size: a a a
IS
ПФ
NN
t
GP
t
org.apache.spark.sql.execution.datasources.csv
CSVFileFormat
extends TextBasedFileFormat
with DataSourceRegister {
buildReader(
sparkSession: SparkSession,
dataSchema: StructType,
partitionSchema: StructType,
requiredSchema: StructType,
filters: Seq[Filter],
options: Map[String, String],
hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow]
t
IS
IS
GP
t
t
IS
t
IS
PK
GP