From 41f426febc8825c2b98a35851d5c3e9a93be2930 Mon Sep 17 00:00:00 2001 From: Lars Volker Date: Thu, 5 Jan 2017 19:53:26 +0100 Subject: [PATCH] PARQUET-826: Update comments on Statistics encoding --- src/main/thrift/parquet.thrift | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/main/thrift/parquet.thrift b/src/main/thrift/parquet.thrift index e89bc806c..6c369006a 100644 --- a/src/main/thrift/parquet.thrift +++ b/src/main/thrift/parquet.thrift @@ -202,7 +202,9 @@ enum FieldRepetitionType { * All fields are optional. */ struct Statistics { - /** min and max value of the column, encoded in PLAIN encoding */ + /** min and max value of the column, encoded in PLAIN encoding. However, BYTE_ARRAY + * columns store the values as strings directly, without prefixing them with their + * length. BOOLEAN columns store the values using a single byte. */ 1: optional binary max; 2: optional binary min; /** count of null value in the column */