[GitHub] spark pull request #18375: [SPARK-21144][SQL] Print a warning if the data sc...
Github user maropu commented on a diff in the pull request:
https://github.com/apache/spark/pull/18375#discussion_r123869166
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala ---
@@ -0,0 +1,80 @@
+/*
+ * 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.util
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.analysis._
+import org.apache.spark.sql.types.StructType
+
+
+/**
+ * Utils for handling schemas.
+ *
+ * TODO: Merge this file with [[org.apache.spark.ml.util.SchemaUtils]].
+ */
+private[spark] object SchemaUtils {
+
+ // Returns true if a given resolver is case-sensitive
+ private def isCaseSensitiveAnalysis(resolver: Resolver): Boolean = {
+if (resolver == caseSensitiveResolution) {
+ true
+} else if (resolver == caseInsensitiveResolution) {
+ false
+} else {
+ sys.error("A resolver to check if two identifiers are equal must be
" +
+"`caseSensitiveResolution` or `caseInsensitiveResolution` in
o.a.s.sql.catalyst.")
+}
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param resolver resolver used to determine if two identifiers are
equal
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, resolver: Resolver): Unit
= {
+checkColumnNameDuplication(columnNames, colType,
isCaseSensitiveAnalysis(resolver))
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param caseSensitiveAnalysis whether duplication checks should be
case sensitive or not
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, caseSensitiveAnalysis:
Boolean): Unit = {
+val names = if (caseSensitiveAnalysis) {
--- End diff --
ok
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #18375: [SPARK-21144][SQL] Print a warning if the data sc...
Github user asfgit closed the pull request at: https://github.com/apache/spark/pull/18375 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #18375: [SPARK-21144][SQL] Print a warning if the data sc...
Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/18375#discussion_r123790777
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala ---
@@ -0,0 +1,80 @@
+/*
+ * 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.util
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.analysis._
+import org.apache.spark.sql.types.StructType
+
+
+/**
+ * Utils for handling schemas.
+ *
+ * TODO: Merge this file with [[org.apache.spark.ml.util.SchemaUtils]].
+ */
+private[spark] object SchemaUtils {
+
+ // Returns true if a given resolver is case-sensitive
+ private def isCaseSensitiveAnalysis(resolver: Resolver): Boolean = {
+if (resolver == caseSensitiveResolution) {
+ true
+} else if (resolver == caseInsensitiveResolution) {
+ false
+} else {
+ sys.error("A resolver to check if two identifiers are equal must be
" +
+"`caseSensitiveResolution` or `caseInsensitiveResolution` in
o.a.s.sql.catalyst.")
+}
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param resolver resolver used to determine if two identifiers are
equal
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, resolver: Resolver): Unit
= {
+checkColumnNameDuplication(columnNames, colType,
isCaseSensitiveAnalysis(resolver))
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param caseSensitiveAnalysis whether duplication checks should be
case sensitive or not
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, caseSensitiveAnalysis:
Boolean): Unit = {
+val names = if (caseSensitiveAnalysis) {
--- End diff --
Yeah. Let me first merge this.
@maropu , could you resolve this in your another related PR?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #18375: [SPARK-21144][SQL] Print a warning if the data sc...
Github user brad-kaiser commented on a diff in the pull request:
https://github.com/apache/spark/pull/18375#discussion_r123756832
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala ---
@@ -0,0 +1,80 @@
+/*
+ * 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.util
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.analysis._
+import org.apache.spark.sql.types.StructType
+
+
+/**
+ * Utils for handling schemas.
+ *
+ * TODO: Merge this file with [[org.apache.spark.ml.util.SchemaUtils]].
+ */
+private[spark] object SchemaUtils {
+
+ // Returns true if a given resolver is case-sensitive
+ private def isCaseSensitiveAnalysis(resolver: Resolver): Boolean = {
+if (resolver == caseSensitiveResolution) {
+ true
+} else if (resolver == caseInsensitiveResolution) {
+ false
+} else {
+ sys.error("A resolver to check if two identifiers are equal must be
" +
+"`caseSensitiveResolution` or `caseInsensitiveResolution` in
o.a.s.sql.catalyst.")
+}
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param resolver resolver used to determine if two identifiers are
equal
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, resolver: Resolver): Unit
= {
+checkColumnNameDuplication(columnNames, colType,
isCaseSensitiveAnalysis(resolver))
+ }
+
+ /**
+ * Checks if input column names have duplicate identifiers. This throws
an exception if
+ * the duplication exists.
+ *
+ * @param columnNames column names to check
+ * @param colType column type name, used in an exception message
+ * @param caseSensitiveAnalysis whether duplication checks should be
case sensitive or not
+ */
+ def checkColumnNameDuplication(
+ columnNames: Seq[String], colType: String, caseSensitiveAnalysis:
Boolean): Unit = {
+val names = if (caseSensitiveAnalysis) {
--- End diff --
This if might be easier to read on one line.
```scala
val names = if (caseSensitiveAnalysis) columnNames else
columnNames.map(_.toLowerCase)
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
