« blib/lib/Paws/Firehose/OpenXJsonSerDe.pm
↑ Summary
blib/lib/Paws/Firehose/OutputFormatConfiguration.pm »
| 1 | # Generated by default/object.tt | ||
| 2 | package Paws::Firehose::OrcSerDe; | ||
| 3 | use Moose; | ||
| 4 | has BlockSizeBytes => (is => 'ro', isa => 'Int'); | ||
| 5 | has BloomFilterColumns => (is => 'ro', isa => 'ArrayRef[Str|Undef]'); | ||
| 6 | has BloomFilterFalsePositiveProbability => (is => 'ro', isa => 'Num'); | ||
| 7 | has Compression => (is => 'ro', isa => 'Str'); | ||
| 8 | has DictionaryKeyThreshold => (is => 'ro', isa => 'Num'); | ||
| 9 | has EnablePadding => (is => 'ro', isa => 'Bool'); | ||
| 10 | has FormatVersion => (is => 'ro', isa => 'Str'); | ||
| 11 | has PaddingTolerance => (is => 'ro', isa => 'Num'); | ||
| 12 | has RowIndexStride => (is => 'ro', isa => 'Int'); | ||
| 13 | has StripeSizeBytes => (is => 'ro', isa => 'Int'); | ||
| 14 | |||
| 15 | 1; | ||
| 16 | |||
| 17 | ### main pod documentation begin ### | ||
| 18 | |||
| 19 | =head1 NAME | ||
| 20 | |||
| 21 | Paws::Firehose::OrcSerDe | ||
| 22 | |||
| 23 | =head1 USAGE | ||
| 24 | |||
| 25 | This class represents one of two things: | ||
| 26 | |||
| 27 | =head3 Arguments in a call to a service | ||
| 28 | |||
| 29 | Use the attributes of this class as arguments to methods. You shouldn't make instances of this class. | ||
| 30 | Each attribute should be used as a named argument in the calls that expect this type of object. | ||
| 31 | |||
| 32 | As an example, if Att1 is expected to be a Paws::Firehose::OrcSerDe object: | ||
| 33 | |||
| 34 | $service_obj->Method(Att1 => { BlockSizeBytes => $value, ..., StripeSizeBytes => $value }); | ||
| 35 | |||
| 36 | =head3 Results returned from an API call | ||
| 37 | |||
| 38 | Use accessors for each attribute. If Att1 is expected to be an Paws::Firehose::OrcSerDe object: | ||
| 39 | |||
| 40 | $result = $service_obj->Method(...); | ||
| 41 | $result->Att1->BlockSizeBytes | ||
| 42 | |||
| 43 | =head1 DESCRIPTION | ||
| 44 | |||
| 45 | A serializer to use for converting data to the ORC format before | ||
| 46 | storing it in Amazon S3. For more information, see Apache ORC | ||
| 47 | (https://orc.apache.org/docs/). | ||
| 48 | |||
| 49 | =head1 ATTRIBUTES | ||
| 50 | |||
| 51 | |||
| 52 | =head2 BlockSizeBytes => Int | ||
| 53 | |||
| 54 | The Hadoop Distributed File System (HDFS) block size. This is useful if | ||
| 55 | you intend to copy the data from Amazon S3 to HDFS before querying. The | ||
| 56 | default is 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose | ||
| 57 | uses this value for padding calculations. | ||
| 58 | |||
| 59 | |||
| 60 | =head2 BloomFilterColumns => ArrayRef[Str|Undef] | ||
| 61 | |||
| 62 | The column names for which you want Kinesis Data Firehose to create | ||
| 63 | bloom filters. The default is C<null>. | ||
| 64 | |||
| 65 | |||
| 66 | =head2 BloomFilterFalsePositiveProbability => Num | ||
| 67 | |||
| 68 | The Bloom filter false positive probability (FPP). The lower the FPP, | ||
| 69 | the bigger the Bloom filter. The default value is 0.05, the minimum is | ||
| 70 | 0, and the maximum is 1. | ||
| 71 | |||
| 72 | |||
| 73 | =head2 Compression => Str | ||
| 74 | |||
| 75 | The compression code to use over data blocks. The default is C<SNAPPY>. | ||
| 76 | |||
| 77 | |||
| 78 | =head2 DictionaryKeyThreshold => Num | ||
| 79 | |||
| 80 | Represents the fraction of the total number of non-null rows. To turn | ||
| 81 | off dictionary encoding, set this fraction to a number that is less | ||
| 82 | than the number of distinct keys in a dictionary. To always use | ||
| 83 | dictionary encoding, set this threshold to 1. | ||
| 84 | |||
| 85 | |||
| 86 | =head2 EnablePadding => Bool | ||
| 87 | |||
| 88 | Set this to C<true> to indicate that you want stripes to be padded to | ||
| 89 | the HDFS block boundaries. This is useful if you intend to copy the | ||
| 90 | data from Amazon S3 to HDFS before querying. The default is C<false>. | ||
| 91 | |||
| 92 | |||
| 93 | =head2 FormatVersion => Str | ||
| 94 | |||
| 95 | The version of the file to write. The possible values are C<V0_11> and | ||
| 96 | C<V0_12>. The default is C<V0_12>. | ||
| 97 | |||
| 98 | |||
| 99 | =head2 PaddingTolerance => Num | ||
| 100 | |||
| 101 | A number between 0 and 1 that defines the tolerance for block padding | ||
| 102 | as a decimal fraction of stripe size. The default value is 0.05, which | ||
| 103 | means 5 percent of stripe size. | ||
| 104 | |||
| 105 | For the default values of 64 MiB ORC stripes and 256 MiB HDFS blocks, | ||
| 106 | the default block padding tolerance of 5 percent reserves a maximum of | ||
| 107 | 3.2 MiB for padding within the 256 MiB block. In such a case, if the | ||
| 108 | available size within the block is more than 3.2 MiB, a new, smaller | ||
| 109 | stripe is inserted to fit within that space. This ensures that no | ||
| 110 | stripe crosses block boundaries and causes remote reads within a | ||
| 111 | node-local task. | ||
| 112 | |||
| 113 | Kinesis Data Firehose ignores this parameter when | ||
| 114 | OrcSerDe$EnablePadding is C<false>. | ||
| 115 | |||
| 116 | |||
| 117 | =head2 RowIndexStride => Int | ||
| 118 | |||
| 119 | The number of rows between index entries. The default is 10,000 and the | ||
| 120 | minimum is 1,000. | ||
| 121 | |||
| 122 | |||
| 123 | =head2 StripeSizeBytes => Int | ||
| 124 | |||
| 125 | The number of bytes in each stripe. The default is 64 MiB and the | ||
| 126 | minimum is 8 MiB. | ||
| 127 | |||
| 128 | |||
| 129 | |||
| 130 | =head1 SEE ALSO | ||
| 131 | |||
| 132 | This class forms part of L<Paws>, describing an object used in L<Paws::Firehose> | ||
| 133 | |||
| 134 | =head1 BUGS and CONTRIBUTIONS | ||
| 135 | |||
| 136 | The source code is located here: L<https://github.com/pplu/aws-sdk-perl> | ||
| 137 | |||
| 138 | Please report bugs to: L<https://github.com/pplu/aws-sdk-perl/issues> | ||
| 139 | |||
| 140 | =cut | ||
| 141 |