Serialized Form

Package org.apache.parquet.format

Class org.apache.parquet.format.AesGcmCtrV1 extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

aad_file_unique

ByteBuffer aad_file_unique

Unique file identifier part of AAD suffix *

aad_prefix

ByteBuffer aad_prefix

AAD prefix *

supply_aad_prefix

boolean supply_aad_prefix

In files encrypted with AAD prefix without storing it, readers must supply the prefix *

Class org.apache.parquet.format.AesGcmV1 extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

aad_file_unique

ByteBuffer aad_file_unique

Unique file identifier part of AAD suffix *

aad_prefix

ByteBuffer aad_prefix

AAD prefix *

supply_aad_prefix

boolean supply_aad_prefix

In files encrypted with AAD prefix without storing it, readers must supply the prefix *

Class org.apache.parquet.format.BloomFilterAlgorithm extends org.apache.thrift.TUnion<BloomFilterAlgorithm,BloomFilterAlgorithm._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.BloomFilterCompression extends org.apache.thrift.TUnion<BloomFilterCompression,BloomFilterCompression._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.BloomFilterHash extends org.apache.thrift.TUnion<BloomFilterHash,BloomFilterHash._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.BloomFilterHeader extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

algorithm

BloomFilterAlgorithm algorithm

The algorithm for setting bits. *

compression

BloomFilterCompression compression

The compression used in the Bloom filter *

hash

BloomFilterHash hash

The hash function used for Bloom filter. *

numBytes

int numBytes

The size of bitset in bytes *

Class org.apache.parquet.format.BsonType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.ColumnChunk extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

column_index_length

int column_index_length

Size of ColumnChunk's ColumnIndex, in bytes *

column_index_offset

long column_index_offset

File offset of ColumnChunk's ColumnIndex *

crypto_metadata

ColumnCryptoMetaData crypto_metadata

Crypto metadata of encrypted columns *

encrypted_column_metadata

ByteBuffer encrypted_column_metadata

Encrypted column metadata for this chunk *

file_offset

long file_offset

Byte offset in file_path to the ColumnMetaData *

file_path

String file_path

File where column data is stored. If not set, assumed to be same file as metadata. This path is relative to the current file.

meta_data

ColumnMetaData meta_data

Column metadata for this chunk. This is the same content as what is at file_path/file_offset. Having it here has it replicated in the file metadata.

offset_index_length

int offset_index_length

Size of ColumnChunk's OffsetIndex, in bytes *

offset_index_offset

long offset_index_offset

File offset of ColumnChunk's OffsetIndex *

Class org.apache.parquet.format.ColumnCryptoMetaData extends org.apache.thrift.TUnion<ColumnCryptoMetaData,ColumnCryptoMetaData._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.ColumnIndex extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

boundary_order

BoundaryOrder boundary_order

Stores whether both min_values and max_values are orderd and if so, in which direction. This allows readers to perform binary searches in both lists. Readers cannot assume that max_values[i] <= min_values[i+1], even if the lists are ordered.

See Also:

BoundaryOrder

max_values

List<ByteBuffer> max_values

min_values

List<ByteBuffer> min_values

Two lists containing lower and upper bounds for the values of each page. These may be the actual minimum and maximum values found on a page, but can also be (more compact) values that do not exist on a page. For example, instead of storing ""Blart Versenwald III", a writer may set min_values[i]="B", max_values[i]="C". Such more compact values must still be valid values within the column's logical type. Readers must make sure that list entries are populated before using them by inspecting null_pages.

null_counts

List<Long> null_counts

A list containing the number of null values for each page *

null_pages

List<Boolean> null_pages

A list of Boolean values to determine the validity of the corresponding min and max values. If true, a page contains only null values, and writers have to set the corresponding entries in min_values and max_values to byte[0], so that all lists have the same length. If false, the corresponding entries in min_values and max_values must be valid.

Class org.apache.parquet.format.ColumnMetaData extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

bloom_filter_offset

long bloom_filter_offset

Byte offset from beginning of file to Bloom filter data. *

codec

CompressionCodec codec

Compression codec *

See Also:

CompressionCodec

data_page_offset

long data_page_offset

Byte offset from beginning of file to first data page *

dictionary_page_offset

long dictionary_page_offset

Byte offset from the beginning of file to first (only) dictionary page *

encoding_stats

List<PageEncodingStats> encoding_stats

Set of all encodings used for pages in this column chunk. This information can be used to determine if all data pages are dictionary encoded for example *

encodings

List<Encoding> encodings

Set of all encodings used for this column. The purpose is to validate whether we can decode those pages. *

index_page_offset

long index_page_offset

Byte offset from beginning of file to root index page *

key_value_metadata

List<KeyValue> key_value_metadata

Optional key/value metadata *

num_values

long num_values

Number of values in this column *

path_in_schema

List<String> path_in_schema

Path in schema *

statistics

Statistics statistics

optional statistics for this column chunk

total_compressed_size

long total_compressed_size

total byte size of all compressed, and potentially encrypted, pages in this column chunk (including the headers) *

total_uncompressed_size

long total_uncompressed_size

total byte size of all uncompressed pages in this column chunk (including the headers) *

type

Type type

Type of this column *

See Also:

Type

Class org.apache.parquet.format.ColumnOrder extends org.apache.thrift.TUnion<ColumnOrder,ColumnOrder._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.DataPageHeader extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

definition_level_encoding

Encoding definition_level_encoding

Encoding used for definition levels *

See Also:

Encoding

encoding

Encoding encoding

Encoding used for this data page *

See Also:

Encoding

num_values

int num_values

Number of values, including NULLs, in this data page. *

repetition_level_encoding

Encoding repetition_level_encoding

Encoding used for repetition levels *

See Also:

Encoding

statistics

Statistics statistics

Optional statistics for the data in this page*

Class org.apache.parquet.format.DataPageHeaderV2 extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

definition_levels_byte_length

int definition_levels_byte_length

length of the definition levels

encoding

Encoding encoding

Encoding used for data in this page *

See Also:

Encoding

is_compressed

boolean is_compressed

whether the values are compressed. Which means the section of the page between definition_levels_byte_length + repetition_levels_byte_length + 1 and compressed_page_size (included) is compressed with the compression_codec. If missing it is considered compressed

num_nulls

int num_nulls

Number of NULL values, in this data page. Number of non-null = num_values - num_nulls which is also the number of values in the data section *

num_rows

int num_rows

Number of rows in this data page. which means pages change on record boundaries (r = 0) *

num_values

int num_values

Number of values, including NULLs, in this data page. *

repetition_levels_byte_length

int repetition_levels_byte_length

length of the repetition levels

statistics

Statistics statistics

optional statistics for this column chunk

Class org.apache.parquet.format.DateType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.DecimalType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

precision

int precision

scale

int scale

Class org.apache.parquet.format.DictionaryPageHeader extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

encoding

Encoding encoding

Encoding using this dictionary page *

See Also:

Encoding

is_sorted

boolean is_sorted

If true, the entries in the dictionary are sorted in ascending order *

num_values

int num_values

Number of values in the dictionary *

Class org.apache.parquet.format.EncryptionAlgorithm extends org.apache.thrift.TUnion<EncryptionAlgorithm,EncryptionAlgorithm._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.EncryptionWithColumnKey extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

key_metadata

ByteBuffer key_metadata

Retrieval metadata of column encryption key *

path_in_schema

List<String> path_in_schema

Column path in schema *

Class org.apache.parquet.format.EncryptionWithFooterKey extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.EnumType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.FileCryptoMetaData extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

encryption_algorithm

EncryptionAlgorithm encryption_algorithm

Encryption algorithm. This field is only used for files with encrypted footer. Files with plaintext footer store algorithm id inside footer (FileMetaData structure).

key_metadata

ByteBuffer key_metadata

Retrieval metadata of key used for encryption of footer, and (possibly) columns *

Class org.apache.parquet.format.FileMetaData extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

column_orders

List<ColumnOrder> column_orders

Sort order used for the min_value and max_value fields of each column in this file. Sort orders are listed in the order matching the columns in the schema. The indexes are not necessary the same though, because only leaf nodes of the schema are represented in the list of sort orders. Without column_orders, the meaning of the min_value and max_value fields is undefined. To ensure well-defined behaviour, if min_value and max_value are written to a Parquet file, column_orders must be written as well. The obsolete min and max fields are always sorted by signed comparison regardless of column_orders.

created_by

String created_by

String for application that wrote this file. This should be in the format version (build ). e.g. impala version 1.0 (build 6cf94d29b2b7115df4de2c06e2ab4326d721eb55)

encryption_algorithm

EncryptionAlgorithm encryption_algorithm

Encryption algorithm. This field is set only in encrypted files with plaintext footer. Files with encrypted footer store algorithm id in FileCryptoMetaData structure.

footer_signing_key_metadata

ByteBuffer footer_signing_key_metadata

Retrieval metadata of key used for signing the footer. Used only in encrypted files with plaintext footer.

key_value_metadata

List<KeyValue> key_value_metadata

Optional key/value metadata *

num_rows

long num_rows

Number of rows in this file *

row_groups

List<RowGroup> row_groups

Row groups in this file *

schema

List<SchemaElement> schema

Parquet schema for this file. This schema contains metadata for all the columns. The schema is represented as a tree with a single root. The nodes of the tree are flattened to a list by doing a depth-first traversal. The column metadata contains the path in the schema for that column which can be used to map columns to nodes in the schema. The first element is the root *

version

int version

Version of this file *

Class org.apache.parquet.format.IndexPageHeader extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.IntType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

bitWidth

byte bitWidth

isSigned

boolean isSigned

Class org.apache.parquet.format.JsonType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.KeyValue extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

key

String key

value

String value

Class org.apache.parquet.format.ListType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.LogicalType extends org.apache.thrift.TUnion<LogicalType,LogicalType._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.MapType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.MicroSeconds extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.MilliSeconds extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.NanoSeconds extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.NullType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.OffsetIndex extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

page_locations

List<PageLocation> page_locations

PageLocations, ordered by increasing PageLocation.offset. It is required that page_locations[i].first_row_index < page_locations[i+1].first_row_index.

Class org.apache.parquet.format.PageEncodingStats extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

count

int count

number of pages of this type with this encoding *

encoding

Encoding encoding

encoding of the page *

See Also:

Encoding

page_type

PageType page_type

the page type (data/dic/...) *

See Also:

PageType

Class org.apache.parquet.format.PageHeader extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

compressed_page_size

int compressed_page_size

Compressed (and potentially encrypted) page size in bytes, not including this header *

crc

int crc

The 32bit CRC for the page, to be be calculated as follows: - Using the standard CRC32 algorithm - On the data only, i.e. this header should not be included. 'Data' hereby refers to the concatenation of the repetition levels, the definition levels and the column value, in this exact order. - On the encoded versions of the repetition levels, definition levels and column values - On the compressed versions of the repetition levels, definition levels and column values where possible; - For v1 data pages, the repetition levels, definition levels and column values are always compressed together. If a compression scheme is specified, the CRC shall be calculated on the compressed version of this concatenation. If no compression scheme is specified, the CRC shall be calculated on the uncompressed version of this concatenation. - For v2 data pages, the repetition levels and definition levels are handled separately from the data and are never compressed (only encoded). If a compression scheme is specified, the CRC shall be calculated on the concatenation of the uncompressed repetition levels, uncompressed definition levels and the compressed column values. If no compression scheme is specified, the CRC shall be calculated on the uncompressed concatenation. If enabled, this allows for disabling checksumming in HDFS if only a few pages need to be read.

data_page_header

DataPageHeader data_page_header

data_page_header_v2

DataPageHeaderV2 data_page_header_v2

dictionary_page_header

DictionaryPageHeader dictionary_page_header

index_page_header

IndexPageHeader index_page_header

type

PageType type

the type of the page: indicates which of the *_header fields is set *

See Also:

PageType

uncompressed_page_size

int uncompressed_page_size

Uncompressed page size in bytes (not including this header) *

Class org.apache.parquet.format.PageLocation extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

compressed_page_size

int compressed_page_size

Size of the page, including header. Sum of compressed_page_size and header length

first_row_index

long first_row_index

Index within the RowGroup of the first row of the page; this means pages change on record boundaries (r = 0).

offset

long offset

Offset of the page in the file *

Class org.apache.parquet.format.RowGroup extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

columns

List<ColumnChunk> columns

Metadata for each column chunk in this row group. This list must have the same order as the SchemaElement list in FileMetaData.

file_offset

long file_offset

Byte offset from beginning of file to first page (data or dictionary) in this row group *

num_rows

long num_rows

Number of rows in this row group *

ordinal

short ordinal

Row group ordinal in the file *

sorting_columns

List<SortingColumn> sorting_columns

If set, specifies a sort ordering of the rows in this RowGroup. The sorting columns can be a subset of all the columns.

total_byte_size

long total_byte_size

Total byte size of all the uncompressed column data in this row group *

total_compressed_size

long total_compressed_size

Total byte size of all compressed (and potentially encrypted) column data in this row group *

Class org.apache.parquet.format.SchemaElement extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

converted_type

ConvertedType converted_type

When the schema is the result of a conversion from another model Used to record the original type to help with cross conversion.

See Also:

ConvertedType

field_id

int field_id

When the original schema supports field ids, this will save the original field id in the parquet schema

logicalType

LogicalType logicalType

The logical type of this SchemaElement LogicalType replaces ConvertedType, but ConvertedType is still required for some logical types to ensure forward-compatibility in format v1.

name

String name

Name of the field in the schema

num_children

int num_children

Nested fields. Since thrift does not support nested fields, the nesting is flattened to a single list by a depth-first traversal. The children count is used to construct the nested relationship. This field is not set when the element is a primitive type

precision

int precision

repetition_type

FieldRepetitionType repetition_type

repetition of the field. The root of the schema does not have a repetition_type. All other nodes must have one

See Also:

FieldRepetitionType

scale

int scale

Used when this column contains decimal data. See the DECIMAL converted type for more details.

type

Type type

Data type for this field. Not set if the current element is a non-leaf node

See Also:

Type

type_length

int type_length

If type is FIXED_LEN_BYTE_ARRAY, this is the byte length of the vales. Otherwise, if specified, this is the maximum bit length to store any of the values. (e.g. a low cardinality INT col could have this set to 3). Note that this is in the schema, and therefore fixed for the entire file.

Class org.apache.parquet.format.SortingColumn extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

column_idx

int column_idx

The column index (in this row group) *

descending

boolean descending

If true, indicates this column is sorted in descending order. *

nulls_first

boolean nulls_first

If true, nulls will come before non-null values, otherwise, nulls go at the end.

Class org.apache.parquet.format.SplitBlockAlgorithm extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.Statistics extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

distinct_count

long distinct_count

count of distinct values occurring

max

ByteBuffer max

DEPRECATED: min and max value of the column. Use min_value and max_value. Values are encoded using PLAIN encoding, except that variable-length byte arrays do not include a length prefix. These fields encode min and max values determined by signed comparison only. New files should use the correct order for a column's logical type and store the values in the min_value and max_value fields. To support older readers, these may be set when the column order is signed.

max_value

ByteBuffer max_value

Min and max values for the column, determined by its ColumnOrder. Values are encoded using PLAIN encoding, except that variable-length byte arrays do not include a length prefix.

min

ByteBuffer min

min_value

ByteBuffer min_value

null_count

long null_count

count of null value in the column

Class org.apache.parquet.format.StringType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.TimestampType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

isAdjustedToUTC

boolean isAdjustedToUTC

unit

TimeUnit unit

Class org.apache.parquet.format.TimeType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Serialized Fields

__isset_bitfield

byte __isset_bitfield

isAdjustedToUTC

boolean isAdjustedToUTC

unit

TimeUnit unit

Class org.apache.parquet.format.TimeUnit extends org.apache.thrift.TUnion<TimeUnit,TimeUnit._Fields> implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.TypeDefinedOrder extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.Uncompressed extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.UUIDType extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException

Class org.apache.parquet.format.XxHash extends Object implements Serializable

Serialization Methods

readObject

private void readObject(ObjectInputStream in)
                 throws IOException,
                        ClassNotFoundException

Throws:

IOException

ClassNotFoundException

writeObject

private void writeObject(ObjectOutputStream out)
                  throws IOException

Throws:

IOException