def for_row_type(row_type: RowType,
writer_properties: Optional[Configuration] = None,
hadoop_config: Optional[Configuration] = None) \
-> BulkWriterFactory:
"""
Create a RowDataBulkWriterFactory that writes Row records with a defined RowType into Orc
files in a batch fashion.
Example:
::
>>> row_type = DataTypes.ROW([
... DataTypes.FIELD('string', DataTypes.STRING()),
... DataTypes.FIELD('int_array', DataTypes.ARRAY(DataTypes.INT()))
... ])
>>> row_type_info = Types.ROW_NAMED(
... ['string', 'int_array'],
... [Types.STRING(), Types.LIST(Types.INT())]
... )
>>> sink = FileSink.for_bulk_format(
... OUTPUT_DIR, OrcBulkWriters.for_row_type(
... row_type=row_type,
... writer_properties=Configuration(),
... hadoop_config=Configuration(),
... )
... ).build()
>>> ds.map(lambda e: e, output_type=row_type_info).sink_to(sink)
Note that in the above example, an identity map to indicate its RowTypeInfo is necessary
before ``sink_to`` when ``ds`` is a source stream producing **RowData** records,
because RowDataBulkWriterFactory assumes the input record type is Row.
"""
if not isinstance(row_type, RowType):
raise TypeError('row_type must be an instance of RowType')
j_data_type = _to_java_data_type(row_type)
jvm = get_gateway().jvm
j_row_type = j_data_type.getLogicalType()
orc_types = to_jarray(
jvm.org.apache.flink.table.types.logical.LogicalType,
[i for i in j_row_type.getChildren()])
type_description = jvm.org.apache.flink.orc \
.OrcSplitReaderUtil.logicalTypeToOrcType(j_row_type)
if writer_properties is None:
writer_properties = Configuration()
if hadoop_config is None:
hadoop_config = Configuration()
return RowDataBulkWriterFactory(
jvm.org.apache.flink.orc.writer.OrcBulkWriterFactory(
jvm.org.apache.flink.orc.vector.RowDataVectorizer(
type_description.toString(), orc_types),
create_java_properties(writer_properties),
create_hadoop_configuration(hadoop_config)), row_type)
def _write_row_data_to_parquet_file(path: str, row_type: RowType, rows: List[Row]):
jvm = get_gateway().jvm
flink = jvm.org.apache.flink
j_output_stream = flink.core.fs.local.LocalDataOutputStream(jvm.java.io.File(path))
j_bulk_writer = flink.formats.parquet.row.ParquetRowDataBuilder.createWriterFactory(
_to_java_data_type(row_type).getLogicalType(),
create_hadoop_configuration(Configuration()),
True,
).create(j_output_stream)
row_row_converter = flink.table.data.conversion.RowRowConverter.create(
_to_java_data_type(row_type)
)
row_row_converter.open(row_row_converter.getClass().getClassLoader())
for row in rows:
j_bulk_writer.addElement(row_row_converter.toInternal(to_java_data_structure(row)))
j_bulk_writer.finish()
def __init__(self,
row_type: RowType,
hadoop_config: Optional[Configuration] = None,
batch_size: int = 2048,
is_utc_timestamp: bool = False,
is_case_sensitive: bool = True):
if not hadoop_config:
hadoop_config = Configuration()
jvm = get_gateway().jvm
j_row_type = _to_java_data_type(row_type).getLogicalType()
produced_type_info = jvm.org.apache.flink.table.runtime.typeutils. \
InternalTypeInfo.of(j_row_type)
j_parquet_columnar_format = jvm.org.apache.flink.formats.parquet. \
ParquetColumnarRowInputFormat(create_hadoop_configuration(hadoop_config),
j_row_type, produced_type_info, batch_size,
is_utc_timestamp, is_case_sensitive)
super().__init__(j_parquet_columnar_format)
def for_row_type(row_type: RowType,
hadoop_config: Optional[Configuration] = None,
utc_timestamp: bool = False) -> 'BulkWriterFactory':
"""
Create a RowDataBulkWriterFactory that writes Rows records with a defined RowType into
Parquet files in a batch fashion.
Example:
::
>>> row_type = DataTypes.ROW([
... DataTypes.FIELD('string', DataTypes.STRING()),
... DataTypes.FIELD('int_array', DataTypes.ARRAY(DataTypes.INT()))
... ])
>>> row_type_info = Types.ROW_NAMED(
... ['string', 'int_array'],
... [Types.STRING(), Types.LIST(Types.INT())]
... )
>>> sink = FileSink.for_bulk_format(
... OUTPUT_DIR, ParquetBulkWriter.for_row_type(
... row_type,
... hadoop_config=Configuration(),
... utc_timestamp=True,
... )
... ).build()
>>> ds.map(lambda e: e, output_type=row_type_info).sink_to(sink)
Note that in the above example, an identity map to indicate its RowTypeInfo is necessary
before ``sink_to`` when ``ds`` is a source stream producing **RowData** records, because
RowDataBulkWriterFactory assumes the input record type is **Row** .
"""
if not hadoop_config:
hadoop_config = Configuration()
jvm = get_gateway().jvm
JParquetRowDataBuilder = jvm.org.apache.flink.formats.parquet.row.ParquetRowDataBuilder
return RowDataBulkWriterFactory(
JParquetRowDataBuilder.createWriterFactory(
_to_java_data_type(row_type).getLogicalType(),
create_hadoop_configuration(hadoop_config), utc_timestamp),
row_type)
def for_row_type(row_type: 'RowType',
writer_properties: Optional[Configuration] = None,
hadoop_config: Optional[Configuration] = None) \
-> BulkWriterFactory:
"""
Create a :class:`~pyflink.common.serialization.BulkWriterFactory` that writes records
with a predefined schema into Orc files in a batch fashion.
:param row_type: The RowType of records, it should match the RowTypeInfo of Row records.
:param writer_properties: Orc writer options.
:param hadoop_config: Hadoop configuration.
"""
from pyflink.table.types import RowType
if not isinstance(row_type, RowType):
raise TypeError('row_type must be an instance of RowType')
from pyflink.table.types import _to_java_data_type
j_data_type = _to_java_data_type(row_type)
jvm = get_gateway().jvm
j_row_type = j_data_type.getLogicalType()
orc_types = to_jarray(
jvm.org.apache.flink.table.types.logical.LogicalType,
[i for i in j_row_type.getChildren()])
type_description = jvm.org.apache.flink.orc \
.OrcSplitReaderUtil.logicalTypeToOrcType(j_row_type)
if writer_properties is None:
writer_properties = Configuration()
if hadoop_config is None:
hadoop_config = Configuration()
return RowDataBulkWriterFactory(
jvm.org.apache.flink.orc.writer.OrcBulkWriterFactory(
jvm.org.apache.flink.orc.vector.RowDataVectorizer(
type_description.toString(), orc_types),
create_java_properties(writer_properties),
create_hadoop_configuration(hadoop_config)), row_type)
def for_row_type(row_type: 'RowType',
hadoop_config: Optional[Configuration] = None,
utc_timestamp: bool = False) -> 'BulkWriterFactory':
"""
Create a :class:`~pyflink.common.serialization.BulkWriterFactory` that writes records
with a predefined schema into Parquet files in a batch fashion.
:param row_type: The RowType of records, it should match the RowTypeInfo of Row records.
:param hadoop_config: Hadoop configuration.
:param utc_timestamp: Use UTC timezone or local timezone to the conversion between epoch
time and LocalDateTime. Hive 0.x/1.x/2.x use local timezone. But Hive 3.x use UTC
timezone.
"""
if not hadoop_config:
hadoop_config = Configuration()
from pyflink.table.types import _to_java_data_type
jvm = get_gateway().jvm
JParquetRowDataBuilder = jvm.org.apache.flink.formats.parquet.row.ParquetRowDataBuilder
return RowDataBulkWriterFactory(JParquetRowDataBuilder.createWriterFactory(
_to_java_data_type(row_type).getLogicalType(),
create_hadoop_configuration(hadoop_config),
utc_timestamp
), row_type)
