mkaravel commented on code in PR #45064: URL: https://github.com/apache/spark/pull/45064#discussion_r1483412350
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala: ########## @@ -0,0 +1,81 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.expressions + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.codegen._ +import org.apache.spark.sql.catalyst.util.CollationFactory +import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.types.UTF8String + +/** + * A function that marks a given expression with specified collation. + * This function is pass-through, it will not modify the input data. + * Only type metadata will be updated. + */ +@ExpressionDescription( + usage = "expr _FUNC_ collationName", + examples = """ + Examples: + > SELECT 'Spark SQL' COLLATE 'UCS_BASIC_LCASE'; + Spark SQL + """, + since = "4.0.0", + group = "string_funcs") +case class Collate(child: Expression, collationName: String) + extends UnaryExpression with ExpectsInputTypes { + private val collationId = CollationFactory.collationNameToId(collationName) + override def dataType: DataType = StringType(collationId) + override def inputTypes: Seq[AbstractDataType] = Seq(StringType) + + override protected def withNewChildInternal( + newChild: Expression): Expression = copy(newChild) + + override def eval(row: InternalRow): Any = child.eval(row) + + override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = + defineCodeGen(ctx, ev, (in) => in) +} + +/** + * A function that returns the collation name of a given expression. + */ +@ExpressionDescription( + usage = "_FUNC_(expr)", + examples = """ + Examples: + > SELECT _FUNC_('Spark SQL'); + UCS_BASIC + """, + since = "4.0.0", + group = "string_funcs") +case class Collation(child: Expression) extends UnaryExpression { Review Comment: Would that work with user-defined collations? ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala: ########## @@ -0,0 +1,81 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.expressions + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.codegen._ +import org.apache.spark.sql.catalyst.util.CollationFactory +import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.types.UTF8String + +/** + * A function that marks a given expression with specified collation. + * This function is pass-through, it will not modify the input data. + * Only type metadata will be updated. + */ +@ExpressionDescription( + usage = "expr _FUNC_ collationName", + examples = """ + Examples: + > SELECT 'Spark SQL' COLLATE 'UCS_BASIC_LCASE'; + Spark SQL Review Comment: Wouldn't it be more interesting to have as example the query: ```sql SELECT collation('Spark SQL' COLLATE 'UCS_BASIC_LCASE'); ``` ########## sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnStats.scala: ########## @@ -270,8 +273,8 @@ private[columnar] final class StringColumnStats extends ColumnStats { } def gatherValueStats(value: UTF8String, size: Int): Unit = { Review Comment: +1 on this. I feel like we should disable column stats initially for non-UCS_BASIC string columns. This a separate task on its own. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
