[SPARK-23903][SQL] Add support for date extract

sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4

@@ -592,6 +592,7 @@ primaryExpression
     | identifier                                                                               #columnReference
     | base=primaryExpression '.' fieldName=identifier                                          #dereference
     | '(' expression ')'                                                                       #parenthesizedExpression
+    | EXTRACT '(' field=identifier FROM source=valueExpression ')'                             #extract
     ;
 
 constant
@@ -739,6 +740,7 @@ nonReserved
     | VIEW | REPLACE
     | IF
     | POSITION
+    | EXTRACT | YEAR | QUARTER | MONTH | WEEK | DAY | DOW | HOUR | MINUTE | SECOND
     | NO | DATA
     | START | TRANSACTION | COMMIT | ROLLBACK | IGNORE
     | SORT | CLUSTER | DISTRIBUTE | UNSET | TBLPROPERTIES | SKEWED | STORED | DIRECTORIES | LOCATION
@@ -878,6 +880,16 @@ TRAILING: 'TRAILING';
 
 IF: 'IF';
 POSITION: 'POSITION';
+EXTRACT: 'EXTRACT';
+YEAR: 'YEAR';
+QUARTER: 'QUARTER';
+MONTH: 'MONTH';
+WEEK: 'WEEK';
+DAY: 'DAY';
+DOW: 'DOW';
+HOUR: 'HOUR';
+MINUTE: 'MINUTE';
+SECOND: 'SECOND';
 
 EQ  : '=' | '==';
 NSEQ: '<=>';

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala

@@ -1206,6 +1206,41 @@ class AstBuilder(conf: SQLConf) extends SqlBaseBaseVisitor[AnyRef] with Logging
     new StringLocate(expression(ctx.substr), expression(ctx.str))
   }
 
+  /**
+   * Create a Extract expression.
+   */
+  override def visitExtract(ctx: ExtractContext): Expression = withOrigin(ctx) {
+    val extractType = ctx.field.getText.toUpperCase(Locale.ROOT)
+    try {
+      extractType match {
+        case "YEAR" =>
+          Year(expression(ctx.source))
+        case "QUARTER" =>
+          Quarter(expression(ctx.source))
+        case "MONTH" =>
+          Month(expression(ctx.source))
+        case "WEEK" =>
+          WeekOfYear(expression(ctx.source))
+        case "DAY" =>
+          DayOfMonth(expression(ctx.source))
+        case "DOW" =>
+          DayOfWeek(expression(ctx.source))
+        case "HOUR" =>
+          Hour(expression(ctx.source))
+        case "MINUTE" =>
+          Minute(expression(ctx.source))
+        case "SECOND" =>
+          Second(expression(ctx.source))
+        case other =>
+          throw new ParseException(s"Literals of type '$other' are currently not supported.", ctx)
+      }
+    } catch {
+      case e: IllegalArgumentException =>
+        val message = Option(e.getMessage).getOrElse(s"Exception parsing $extractType")
+        throw new ParseException(message, ctx)
+    }
+  }
+
   /**
    * Create a (windowed) Function expression.
    */

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/TableIdentifierParserSuite.scala

@@ -51,7 +51,8 @@ class TableIdentifierParserSuite extends SparkFunSuite {
     "rollup", "row", "rows", "set", "smallint", "table", "timestamp", "to", "trigger",
     "true", "truncate", "update", "user", "values", "with", "regexp", "rlike",
     "bigint", "binary", "boolean", "current_date", "current_timestamp", "date", "double", "float",
-    "int", "smallint", "timestamp", "at", "position", "both", "leading", "trailing")
+    "int", "smallint", "timestamp", "at", "position", "both", "leading", "trailing",
+    "extract", "year", "quarter", "month", "week", "day", "dow", "hour", "minute", "second")
 
   val hiveStrictNonReservedKeyword = Seq("anti", "full", "inner", "left", "semi", "right",
     "natural", "union", "intersect", "except", "database", "on", "join", "cross", "select", "from",

sql/core/src/test/resources/sql-tests/inputs/extract.sql

@@ -0,0 +1,21 @@
+CREATE TEMPORARY VIEW t AS select '2011-05-06 07:08:09.1234567' as c;
+
+select extract(year from c) from t;
+
+select extract(quarter from c) from t;
+
+select extract(month from c) from t;
+
+select extract(week from c) from t;
+
+select extract(day from c) from t;
+
+select extract(dow from c) from t;
+
+select extract(hour from c) from t;
+
+select extract(minute from c) from t;
+
+select extract(second from c) from t;
+
+select extract(not_supported from c) from t;

sql/core/src/test/resources/sql-tests/results/extract.sql.out

@@ -0,0 +1,96 @@
+-- Automatically generated by SQLQueryTestSuite
+-- Number of queries: 11
+
+
+-- !query 0
+CREATE TEMPORARY VIEW t AS select '2011-05-06 07:08:09.1234567' as c
+-- !query 0 schema
+struct<>
+-- !query 0 output
+
+
+
+-- !query 1
+select extract(year from c) from t
+-- !query 1 schema
+struct<year(CAST(c AS DATE)):int>
+-- !query 1 output
+2011
+
+
+-- !query 2
+select extract(quarter from c) from t
+-- !query 2 schema
+struct<quarter(CAST(c AS DATE)):int>
+-- !query 2 output
+2
+
+
+-- !query 3
+select extract(month from c) from t
+-- !query 3 schema
+struct<month(CAST(c AS DATE)):int>
+-- !query 3 output
+5
+
+
+-- !query 4
+select extract(week from c) from t
+-- !query 4 schema
+struct<weekofyear(CAST(c AS DATE)):int>
+-- !query 4 output
+18
+
+
+-- !query 5
+select extract(day from c) from t
+-- !query 5 schema
+struct<dayofmonth(CAST(c AS DATE)):int>
+-- !query 5 output
+6
+
+
+-- !query 6
+select extract(dow from c) from t
+-- !query 6 schema
+struct<dayofweek(CAST(c AS DATE)):int>
+-- !query 6 output
+6
+
+
+-- !query 7
+select extract(hour from c) from t
+-- !query 7 schema
+struct<hour(CAST(c AS TIMESTAMP)):int>
+-- !query 7 output
+7
+
+
+-- !query 8
+select extract(minute from c) from t
+-- !query 8 schema
+struct<minute(CAST(c AS TIMESTAMP)):int>
+-- !query 8 output
+8
+
+
+-- !query 9
+select extract(second from c) from t
+-- !query 9 schema
+struct<second(CAST(c AS TIMESTAMP)):int>
+-- !query 9 output
+9
+
+
+-- !query 10
+select extract(not_supported from c) from t
+-- !query 10 schema
+struct<>
+-- !query 10 output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Literals of type 'NOT_SUPPORTED' are currently not supported.(line 1, pos 7)
+
+== SQL ==
+select extract(not_supported from c) from t
+-------^^^