Github user jkbradley commented on a diff in the pull request:

    https://github.com/apache/spark/pull/5431#discussion_r28282562
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala 
---
    @@ -0,0 +1,61 @@
    +/*
    + * 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.ml.util
    +
    +import org.apache.spark.annotation.DeveloperApi
    +import org.apache.spark.sql.types.{DataType, StructField, StructType}
    +
    +/**
    + * :: DeveloperApi ::
    + * Utils for handling schemas.
    + */
    +@DeveloperApi
    +object SchemaUtils {
    +
    +  // TODO: Move the utility methods to SQL.
    +
    +  /**
    +   * Check whether the given schema contains an column of the required 
data type.
    +   * @param colName  column name
    +   * @param dataType  required column data type
    +   */
    +  def checkColumnType(schema: StructType, colName: String, dataType: 
DataType): Unit = {
    +    val actualDataType = schema(colName).dataType
    +    require(actualDataType.equals(dataType),
    +      s"Column $colName must be of type $dataType but was actually 
$actualDataType.")
    +  }
    +
    +  /**
    +   * Appends a new column to the input schema. This fails if the given 
output column already exists.
    +   * @param schema input schema
    +   * @param colName new column name. If this column name is en empty 
string "", this method returns
    --- End diff --
    
    typo: "en" -> "an"


---
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

Reply via email to