1
2#------------------------------------------------------------------------------
3# $File: apache,v 1.1 2017/04/11 14:52:15 christos Exp $
4# apache: file(1) magic for Apache Big Data formats
5
6# Avro files
70         string              Obj                 Apache Avro
8>3        byte                x                   version %d
9
10# ORC files
11# Important information is in file footer, which we can't index to :(
120         string              ORC                 Apache ORC
13
14# Parquet files
150         string              PAR1                Apache Parquet
16
17# Hive RC files
180         string              RCF                 Apache Hive RC file
19>3        byte                x                   version %d
20
21# Sequence files (and the careless first version of RC file)
22
230         string              SEQ
24>3        byte                <6                  Apache Hadoop Sequence file version %d
25>3        byte                >6                  Apache Hadoop Sequence file version %d
26>3        byte                =6
27>>5       string              org.apache.hadoop.hive.ql.io.RCFile$KeyBuffer  Apache Hive RC file version 0
28>>3       default             x                   Apache Hadoop Sequence file version 6
29