Skip to content

Commit

Permalink
fix
Browse files Browse the repository at this point in the history
  • Loading branch information
7mming7 committed Apr 22, 2024
1 parent a63c38a commit 95496a4
Showing 1 changed file with 0 additions and 30 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -129,36 +129,6 @@ class ParquetFileFormat
filters: Seq[Filter],
options: Map[String, String],
hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow] = {
hadoopConf.set(ParquetInputFormat.READ_SUPPORT_CLASS, classOf[ParquetReadSupport].getName)
hadoopConf.set(
ParquetReadSupport.SPARK_ROW_REQUESTED_SCHEMA,
requiredSchema.json)
hadoopConf.set(
ParquetWriteSupport.SPARK_ROW_SCHEMA,
requiredSchema.json)
hadoopConf.set(
SQLConf.SESSION_LOCAL_TIMEZONE.key,
sparkSession.sessionState.conf.sessionLocalTimeZone)
hadoopConf.setBoolean(
SQLConf.NESTED_SCHEMA_PRUNING_ENABLED.key,
sparkSession.sessionState.conf.nestedSchemaPruningEnabled)
hadoopConf.setBoolean(
SQLConf.CASE_SENSITIVE.key,
sparkSession.sessionState.conf.caseSensitiveAnalysis)

// Sets flags for `ParquetToSparkSchemaConverter`
hadoopConf.setBoolean(
SQLConf.PARQUET_BINARY_AS_STRING.key,
sparkSession.sessionState.conf.isParquetBinaryAsString)
hadoopConf.setBoolean(
SQLConf.PARQUET_INT96_AS_TIMESTAMP.key,
sparkSession.sessionState.conf.isParquetINT96AsTimestamp)
hadoopConf.setBoolean(
SQLConf.PARQUET_INFER_TIMESTAMP_NTZ_ENABLED.key,
sparkSession.sessionState.conf.parquetInferTimestampNTZEnabled)
hadoopConf.setBoolean(
SQLConf.LEGACY_PARQUET_NANOS_AS_LONG.key,
sparkSession.sessionState.conf.legacyParquetNanosAsLong)

// TODO: if you move this into the closure it reverts to the default values.
// If true, enable using the custom RecordReader for parquet. This only works for
Expand Down

0 comments on commit 95496a4

Please sign in to comment.