[SPARK-30125][SQL] Remove PostgreSQL dialect

docs/sql-keywords.md

@@ -19,7 +19,7 @@ license: |
   limitations under the License.
 ---
 
-When `spark.sql.dialect=PostgreSQL` or keep default `spark.sql.dialect=Spark` with setting `spark.sql.dialect.spark.ansi.enabled` to true, Spark SQL will use the ANSI mode parser.
+When `spark.sql.ansi.enabled` is true, Spark SQL will use the ANSI mode parser.
 In this mode, Spark SQL has two kinds of keywords:
 * Reserved keywords: Keywords that are reserved and can't be used as identifiers for table, view, column, function, alias, etc.
 * Non-reserved keywords: Keywords that have a special meaning only in particular contexts and can be used as identifiers in other contexts. For example, `SELECT 1 WEEK` is an interval literal, but WEEK can be used as identifiers in other places.
@@ -28,7 +28,7 @@ When the ANSI mode is disabled, Spark SQL has two kinds of keywords:
 * Non-reserved keywords: Same definition as the one when the ANSI mode enabled.
 * Strict-non-reserved keywords: A strict version of non-reserved keywords, which can not be used as table alias.
 
-By default `spark.sql.dialect.spark.ansi.enabled` is false.
+By default `spark.sql.ansi.enabled` is false.
 
 Below is a list of all the keywords in Spark SQL.
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala

@@ -232,7 +232,6 @@ class Analyzer(
       ResolveBinaryArithmetic(conf) ::
       TypeCoercion.typeCoercionRules(conf) ++
       extendedResolutionRules : _*),
-    Batch("PostgreSQL Dialect", Once, PostgreSQLDialect.postgreSQLDialectRules: _*),
     Batch("Post-Hoc Resolution", Once, postHocResolutionRules: _*),
     Batch("Remove Unresolved Hints", Once,
       new ResolveHints.RemoveAllHints(conf)),
@@ -287,11 +286,7 @@ class Analyzer(
           case (_, CalendarIntervalType) => Cast(TimeSub(l, r), l.dataType)
           case (TimestampType, _) => SubtractTimestamps(l, r)
           case (_, TimestampType) => SubtractTimestamps(l, r)
-          case (_, DateType) => if (conf.usePostgreSQLDialect) {
-            DateDiff(l, r)
-          } else {
-            SubtractDates(l, r)
-          }
+          case (_, DateType) => SubtractDates(l, r)
           case (DateType, _) => DateSub(l, r)
           case _ => s
         }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala

@@ -59,7 +59,7 @@ object TypeCoercion {
       CaseWhenCoercion ::
       IfCoercion ::
       StackCoercion ::
-      Division(conf) ::
+      Division ::
       ImplicitTypeCasts ::
       DateTimeOperations ::
       WindowFrameCoercion ::
@@ -662,7 +662,7 @@ object TypeCoercion {
    * Hive only performs integral division with the DIV operator. The arguments to / are always
    * converted to fractional types.
    */
-  case class Division(conf: SQLConf)  extends TypeCoercionRule {
+  object Division extends TypeCoercionRule {
     override protected def coerceTypes(
         plan: LogicalPlan): LogicalPlan = plan resolveExpressions {
       // Skip nodes who has not been resolved yet,
@@ -673,13 +673,7 @@ object TypeCoercion {
       case d: Divide if d.dataType == DoubleType => d
       case d: Divide if d.dataType.isInstanceOf[DecimalType] => d
       case Divide(left, right) if isNumericOrNull(left) && isNumericOrNull(right) =>
-        val preferIntegralDivision = conf.usePostgreSQLDialect
-        (left.dataType, right.dataType) match {
-          case (_: IntegralType, _: IntegralType) if preferIntegralDivision =>
-            IntegralDivide(left, right)
-          case _ =>
-            Divide(Cast(left, DoubleType), Cast(right, DoubleType))
-        }
+        Divide(Cast(left, DoubleType), Cast(right, DoubleType))
     }
 
     private def isNumericOrNull(ex: Expression): Boolean = {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala

@@ -276,7 +276,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
   private[this] def needsTimeZone: Boolean = Cast.needsTimeZone(child.dataType, dataType)
 
   // [[func]] assumes the input is no longer null because eval already does the null check.
-  @inline protected def buildCast[T](a: Any, func: T => Any): Any = func(a.asInstanceOf[T])
+  @inline private[this] def buildCast[T](a: Any, func: T => Any): Any = func(a.asInstanceOf[T])
 
   private lazy val dateFormatter = DateFormatter(zoneId)
   private lazy val timestampFormatter = TimestampFormatter.getFractionFormatter(zoneId)
@@ -387,7 +387,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
   }
 
   // UDFToBoolean
-  protected[this] def castToBoolean(from: DataType): Any => Any = from match {
+  private[this] def castToBoolean(from: DataType): Any => Any = from match {
     case StringType =>
       buildCast[UTF8String](_, s => {
         if (StringUtils.isTrueString(s)) {
@@ -602,7 +602,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
    * Change the precision / scale in a given decimal to those set in `decimalType` (if any),
    * modifying `value` in-place and returning it if successful. If an overflow occurs, it
    * either returns null or throws an exception according to the value set for
-   * `spark.sql.dialect.spark.ansi.enabled`.
+   * `spark.sql.ansi.enabled`.
    *
    * NOTE: this modifies `value` in-place, so don't call it on external data.
    */
@@ -621,7 +621,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
 
   /**
    * Create new `Decimal` with precision and scale given in `decimalType` (if any).
-   * If overflow occurs, if `spark.sql.dialect.spark.ansi.enabled` is false, null is returned;
+   * If overflow occurs, if `spark.sql.ansi.enabled` is false, null is returned;
    * otherwise, an `ArithmeticException` is thrown.
    */
   private[this] def toPrecision(value: Decimal, decimalType: DecimalType): Decimal =
@@ -794,7 +794,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
     }
   }
 
-  override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+  override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
     val eval = child.genCode(ctx)
     val nullSafeCast = nullSafeCastFunction(child.dataType, dataType, ctx)
 
@@ -804,7 +804,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
 
   // The function arguments are: `input`, `result` and `resultIsNull`. We don't need `inputIsNull`
   // in parameter list, because the returned code will be put in null safe evaluation region.
-  protected type CastFunction = (ExprValue, ExprValue, ExprValue) => Block
+  private[this] type CastFunction = (ExprValue, ExprValue, ExprValue) => Block
 
   private[this] def nullSafeCastFunction(
       from: DataType,
@@ -1254,7 +1254,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
   private[this] def timestampToDoubleCode(ts: ExprValue): Block =
     code"$ts / (double)$MICROS_PER_SECOND"
 
-  protected[this] def castToBooleanCode(from: DataType): CastFunction = from match {
+  private[this] def castToBooleanCode(from: DataType): CastFunction = from match {
     case StringType =>
       val stringUtils = inline"${StringUtils.getClass.getName.stripSuffix("$")}"
       (c, evPrim, evNull) =>

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala

@@ -150,7 +150,7 @@ abstract class BinaryArithmetic extends BinaryOperator with NullIntolerant {
     sys.error("BinaryArithmetics must override either calendarIntervalMethod or genCode")
 
   // Name of the function for the exact version of this expression in [[Math]].
-  // If the option "spark.sql.dialect.spark.ansi.enabled" is enabled and there is corresponding
+  // If the option "spark.sql.ansi.enabled" is enabled and there is corresponding
   // function in [[Math]], the exact function will be called instead of evaluation with [[symbol]].
   def exactMathMethod: Option[String] = None
 

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

@@ -28,7 +28,6 @@ import org.apache.spark.sql.catalyst.expressions.Expression
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.trees.Origin
 import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.internal.SQLConf.Dialect
 import org.apache.spark.sql.types.{DataType, StructType}
 
 /**
@@ -89,20 +88,13 @@ abstract class AbstractSqlParser(conf: SQLConf) extends ParserInterface with Log
   protected def parse[T](command: String)(toResult: SqlBaseParser => T): T = {
     logDebug(s"Parsing command: $command")
 
-    // When we use PostgreSQL dialect or use Spark dialect with setting
-    // `spark.sql.dialect.spark.ansi.enabled=true`, the parser will use ANSI SQL standard keywords.
-    val SQLStandardKeywordBehavior = conf.dialect match {
-      case Dialect.POSTGRESQL => true
-      case Dialect.SPARK => conf.dialectSparkAnsiEnabled
-    }
-
     val lexer = new SqlBaseLexer(new UpperCaseCharStream(CharStreams.fromString(command)))
     lexer.removeErrorListeners()
     lexer.addErrorListener(ParseErrorListener)
     lexer.legacy_setops_precedence_enbled = conf.setOpsPrecedenceEnforced
     lexer.legacy_exponent_literal_as_decimal_enabled = conf.exponentLiteralAsDecimalEnabled
     lexer.legacy_create_hive_table_by_default_enabled = conf.createHiveTableByDefaultEnabled
-    lexer.SQL_standard_keyword_behavior = SQLStandardKeywordBehavior
+    lexer.SQL_standard_keyword_behavior = conf.ansiEnabled
 
     val tokenStream = new CommonTokenStream(lexer)
     val parser = new SqlBaseParser(tokenStream)
@@ -112,7 +104,7 @@ abstract class AbstractSqlParser(conf: SQLConf) extends ParserInterface with Log
     parser.legacy_setops_precedence_enbled = conf.setOpsPrecedenceEnforced
     parser.legacy_exponent_literal_as_decimal_enabled = conf.exponentLiteralAsDecimalEnabled
     parser.legacy_create_hive_table_by_default_enabled = conf.createHiveTableByDefaultEnabled
-    parser.SQL_standard_keyword_behavior = SQLStandardKeywordBehavior
+    parser.SQL_standard_keyword_behavior = conf.ansiEnabled
 
     try {
       try {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/StringUtils.scala

@@ -38,7 +38,7 @@ object StringUtils extends Logging {
    * throw an [[AnalysisException]].
    *
    * @param pattern the SQL pattern to convert
-   * @param escapeStr the escape string contains one character.
+   * @param escapeChar the escape string contains one character.
    * @return the equivalent Java regular expression of the pattern
    */
   def escapeLikeRegex(pattern: String, escapeChar: Char): String = {