[SPARK-13139][SQL] Create native DDL commands #11048
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,134 @@ | ||
| /* | ||
| * 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.parser | ||
|
|
||
| import org.apache.spark.sql.catalyst.TableIdentifier | ||
| import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan | ||
| import org.apache.spark.sql.catalyst.trees.CurrentOrigin | ||
| import org.apache.spark.sql.types._ | ||
|
|
||
| object ParserSupport { | ||
|
Contributor
There was a problem hiding this comment. this is more like |
||
| protected val escapedIdentifier = "`(.+)`".r | ||
| protected val doubleQuotedString = "\"([^\"]+)\"".r | ||
| protected val singleQuotedString = "'([^']+)'".r | ||
|
Contributor
There was a problem hiding this comment. these can all be private |
||
|
|
||
| private[sql] def unquoteString(str: String): String = str match { | ||
| case singleQuotedString(s) => s | ||
| case doubleQuotedString(s) => s | ||
| case other => other | ||
| } | ||
|
|
||
| /** Strips backticks from ident if present */ | ||
| private[sql] def cleanIdentifier(ident: String): String = ident match { | ||
| case escapedIdentifier(i) => i | ||
| case plainIdent => plainIdent | ||
| } | ||
|
|
||
| private[sql] def cleanAndUnquoteString(str: String): String = { | ||
| cleanIdentifier(unquoteString(str)) | ||
| } | ||
|
|
||
| object Token { | ||
|
Contributor
There was a problem hiding this comment. can you move this to the top so it's not hidden among other methods? |
||
| def unapply(node: ASTNode): Some[(String, List[ASTNode])] = { | ||
| CurrentOrigin.setPosition(node.line, node.positionInLine) | ||
| node.pattern | ||
| } | ||
| } | ||
|
|
||
| def getClauses( | ||
| clauseNames: Seq[String], | ||
| nodeList: Seq[ASTNode]): Seq[Option[ASTNode]] = { | ||
| var remainingNodes = nodeList | ||
| val clauses = clauseNames.map { clauseName => | ||
| val (matches, nonMatches) = remainingNodes.partition(_.text.toUpperCase == clauseName) | ||
| remainingNodes = nonMatches ++ (if (matches.nonEmpty) matches.tail else Nil) | ||
| matches.headOption | ||
| } | ||
|
|
||
| if (remainingNodes.nonEmpty) { | ||
| sys.error( | ||
| s"""Unhandled clauses: ${remainingNodes.map(_.treeString).mkString("\n")}. | ||
| |You are likely trying to use an unsupported Hive feature."""".stripMargin) | ||
| } | ||
| clauses | ||
| } | ||
|
|
||
| def getClause(clauseName: String, nodeList: Seq[ASTNode]): ASTNode = | ||
| getClauseOption(clauseName, nodeList).getOrElse(sys.error( | ||
| s"Expected clause $clauseName missing from ${nodeList.map(_.treeString).mkString("\n")}")) | ||
|
|
||
| def getClauseOption(clauseName: String, nodeList: Seq[ASTNode]): Option[ASTNode] = { | ||
| nodeList.filter { case ast: ASTNode => ast.text == clauseName } match { | ||
| case Seq(oneMatch) => Some(oneMatch) | ||
| case Seq() => None | ||
| case _ => sys.error(s"Found multiple instances of clause $clauseName") | ||
| } | ||
| } | ||
|
|
||
| def extractTableIdent(tableNameParts: ASTNode): TableIdentifier = { | ||
| tableNameParts.children.map { | ||
| case Token(part, Nil) => cleanIdentifier(part) | ||
| } match { | ||
| case Seq(tableOnly) => TableIdentifier(tableOnly) | ||
| case Seq(databaseName, table) => TableIdentifier(table, Some(databaseName)) | ||
| case other => sys.error("Hive only supports tables names like 'tableName' " + | ||
| s"or 'databaseName.tableName', found '$other'") | ||
| } | ||
| } | ||
|
|
||
| def nodeToDataType(node: ASTNode): DataType = node match { | ||
| case Token("TOK_DECIMAL", precision :: scale :: Nil) => | ||
| DecimalType(precision.text.toInt, scale.text.toInt) | ||
| case Token("TOK_DECIMAL", precision :: Nil) => | ||
| DecimalType(precision.text.toInt, 0) | ||
| case Token("TOK_DECIMAL", Nil) => DecimalType.USER_DEFAULT | ||
| case Token("TOK_BIGINT", Nil) => LongType | ||
| case Token("TOK_INT", Nil) => IntegerType | ||
| case Token("TOK_TINYINT", Nil) => ByteType | ||
| case Token("TOK_SMALLINT", Nil) => ShortType | ||
| case Token("TOK_BOOLEAN", Nil) => BooleanType | ||
| case Token("TOK_STRING", Nil) => StringType | ||
| case Token("TOK_VARCHAR", Token(_, Nil) :: Nil) => StringType | ||
| case Token("TOK_CHAR", Token(_, Nil) :: Nil) => StringType | ||
| case Token("TOK_FLOAT", Nil) => FloatType | ||
| case Token("TOK_DOUBLE", Nil) => DoubleType | ||
| case Token("TOK_DATE", Nil) => DateType | ||
| case Token("TOK_TIMESTAMP", Nil) => TimestampType | ||
| case Token("TOK_BINARY", Nil) => BinaryType | ||
| case Token("TOK_LIST", elementType :: Nil) => ArrayType(nodeToDataType(elementType)) | ||
| case Token("TOK_STRUCT", Token("TOK_TABCOLLIST", fields) :: Nil) => | ||
| StructType(fields.map(nodeToStructField)) | ||
| case Token("TOK_MAP", keyType :: valueType :: Nil) => | ||
| MapType(nodeToDataType(keyType), nodeToDataType(valueType)) | ||
| case _ => | ||
| noParseRule("DataType", node) | ||
| } | ||
|
|
||
| def nodeToStructField(node: ASTNode): StructField = node match { | ||
| case Token("TOK_TABCOL", Token(fieldName, Nil) :: dataType :: Nil) => | ||
| StructField(cleanIdentifier(fieldName), nodeToDataType(dataType), nullable = true) | ||
| case Token("TOK_TABCOL", Token(fieldName, Nil) :: dataType :: comment :: Nil) => | ||
| val meta = new MetadataBuilder().putString("comment", unquoteString(comment.text)).build() | ||
| StructField(cleanIdentifier(fieldName), nodeToDataType(dataType), nullable = true, meta) | ||
| case _ => | ||
| noParseRule("StructField", node) | ||
| } | ||
|
|
||
| def noParseRule(msg: String, node: ASTNode): Nothing = throw new NotImplementedError( | ||
| s"[$msg]: No parse rules for ASTNode type: ${node.tokenType}, tree:\n${node.treeString}") | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This class seems to belong to your new parser package. I would move it there instead of changing the import here. Also,
CatalystQlSuiteneeds to be moved sinceCatalystQlis now part of the parser package.