summaryrefslogtreecommitdiff
path: root/magic/Magdir/apache
diff options
context:
space:
mode:
Diffstat (limited to 'magic/Magdir/apache')
-rwxr-xr-xmagic/Magdir/apache20
1 files changed, 15 insertions, 5 deletions
diff --git a/magic/Magdir/apache b/magic/Magdir/apache
index d896b5055127..099efb77da57 100755
--- a/magic/Magdir/apache
+++ b/magic/Magdir/apache
@@ -1,18 +1,28 @@
#------------------------------------------------------------------------------
-# $File: apache,v 1.1 2017/04/11 14:52:15 christos Exp $
+# $File: apache,v 1.3 2025/05/30 13:25:13 christos Exp $
# apache: file(1) magic for Apache Big Data formats
# Avro files
-0 string Obj Apache Avro
->3 byte x version %d
+0 string Obj\001 Apache Avro, version 1
# ORC files
# Important information is in file footer, which we can't index to :(
0 string ORC Apache ORC
-# Parquet files
-0 string PAR1 Apache Parquet
+# Apache arrow file format
+# MIME: https://www.iana.org/assignments/media-types/application/vnd.apache.arrow.stream
+# Description: https://arrow.apache.org/docs/format/Columnar.html
+0 string ARROW1 Apache Arrow columnar file
+!:mime application/vnd.apache.arrow.file
+!:ext arrow/feather
+
+# Apache parquet file format
+# MIME: https://www.iana.org/assignments/media-types/application/vnd.apache.parquet
+# Description: https://parquet.apache.org/docs/file-format/
+0 string PAR1 Apache Parquet file
+!:mime application/vnd.apache.parquet
+!:ext parquet
# Hive RC files
0 string RCF Apache Hive RC file