From 2be5f8d7e0819de03971d0af6fa310793d2d0e65 Mon Sep 17 00:00:00 2001
From: Herman van Hovell <hvanhovell@databricks.com>
Date: Thu, 1 Sep 2016 12:01:22 -0700
Subject: [SPARK-17263][SQL] Add hexadecimal literal parsing

## What changes were proposed in this pull request?
This PR adds the ability to parse SQL (hexadecimal) binary literals (AKA bit strings). It follows the following syntax `X'[Hexadecimal Characters]+'`, for example: `X'01AB'` would create a binary the following binary array `0x01AB`.

If an uneven number of hexadecimal characters is passed, then the upper 4 bits of the initial byte are kept empty, and the lower 4 bits are filled using the first character. For example `X'1C7'` would create the following binary array `0x01C7`.

Binary data (Array[Byte]) does not have a proper `hashCode` and `equals` functions. This meant that comparing `Literal`s containing binary data was a pain. I have updated Literal.hashCode and Literal.equals to deal properly with binary data.

## How was this patch tested?
Added tests to the `ExpressionParserSuite`, `SQLQueryTestSuite` and `ExpressionSQLBuilderSuite`.

Author: Herman van Hovell <hvanhovell@databricks.com>

Closes #14832 from hvanhovell/SPARK-17263.
---
 .../test/resources/sql-tests/inputs/literals.sql   |  7 ++++
 .../resources/sql-tests/results/literals.sql.out   | 42 +++++++++++++++++++---
 2 files changed, 44 insertions(+), 5 deletions(-)

(limited to 'sql/core')

diff --git a/sql/core/src/test/resources/sql-tests/inputs/literals.sql b/sql/core/src/test/resources/sql-tests/inputs/literals.sql
index a532a598c6..40dceb19cf 100644
--- a/sql/core/src/test/resources/sql-tests/inputs/literals.sql
+++ b/sql/core/src/test/resources/sql-tests/inputs/literals.sql
@@ -96,3 +96,10 @@ select 90912830918230182310293801923652346786BD, 123.0E-28BD, 123.08BD;
 
 -- out of range big decimal
 select 1.20E-38BD;
+
+-- hexadecimal binary literal
+select x'2379ACFe';
+
+-- invalid hexadecimal binary literal
+select X'XuZ';
+
diff --git a/sql/core/src/test/resources/sql-tests/results/literals.sql.out b/sql/core/src/test/resources/sql-tests/results/literals.sql.out
index 85629f7ba8..e2d8daef98 100644
--- a/sql/core/src/test/resources/sql-tests/results/literals.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/literals.sql.out
@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 40
+-- Number of queries: 42
 
 
 -- !query 0
@@ -289,8 +289,13 @@ select date 'mar 11 2016'
 -- !query 31 schema
 struct<>
 -- !query 31 output
-java.lang.IllegalArgumentException
-null
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Exception parsing DATE(line 1, pos 7)
+
+== SQL ==
+select date 'mar 11 2016'
+-------^^^
 
 
 -- !query 32
@@ -306,8 +311,13 @@ select timestamp '2016-33-11 20:54:00.000'
 -- !query 33 schema
 struct<>
 -- !query 33 output
-java.lang.IllegalArgumentException
-Timestamp format must be yyyy-mm-dd hh:mm:ss[.fffffffff]
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Timestamp format must be yyyy-mm-dd hh:mm:ss[.fffffffff](line 1, pos 7)
+
+== SQL ==
+select timestamp '2016-33-11 20:54:00.000'
+-------^^^
 
 
 -- !query 34
@@ -376,3 +386,25 @@ DecimalType can only support precision up to 38(line 1, pos 7)
 == SQL ==
 select 1.20E-38BD
 -------^^^
+
+
+-- !query 40
+select x'2379ACFe'
+-- !query 40 schema
+struct<X'2379ACFE':binary>
+-- !query 40 output
+#y��
+
+
+-- !query 41
+select X'XuZ'
+-- !query 41 schema
+struct<>
+-- !query 41 output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+contains illegal character for hexBinary: 0XuZ(line 1, pos 7)
+
+== SQL ==
+select X'XuZ'
+-------^^^
-- 
cgit v1.2.3