spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From viirya <...@git.apache.org>
Subject [GitHub] spark pull request #15664: [SPARK-18123][SQL] Use db column names instead of...
Date Thu, 29 Dec 2016 03:25:10 GMT
Github user viirya commented on a diff in the pull request:

    https://github.com/apache/spark/pull/15664#discussion_r94098773
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala
---
    @@ -211,6 +211,55 @@ object JdbcUtils extends Logging {
       }
     
       /**
    +   * Returns the schema if the table already exists in the JDBC database.
    +   */
    +  def getSchema(conn: Connection, url: String, table: String): Option[StructType] = {
    +    val dialect = JdbcDialects.get(url)
    +
    +    try {
    +      val statement = conn.prepareStatement(dialect.getSchemaQuery(table))
    +      try {
    +        Some(getSchema(statement.executeQuery(), dialect))
    +      } catch {
    +        case _: SQLException => None
    +      } finally {
    +        statement.close()
    +      }
    +    } catch {
    +      case _: SQLException => None
    +    }
    +  }
    +
    +  /**
    +   * Returns a schema using rddSchema's column sequence and tableSchema's column names.
    +   *
    +   * When appending data into some case-sensitive DBMSs like PostgreSQL/Oracle, we need
to respect
    +   * the existing case-sensitive column names instead of RDD column names for user convenience.
    +   * See SPARK-18123 for more details.
    +   */
    +  def normalizeSchema(
    +      rddSchema: StructType,
    +      tableSchema: StructType,
    +      caseSensitive: Boolean): StructType = {
    +    val nameMap = tableSchema.fields.map(f => f.name -> f).toMap
    +    val lowercaseNameMap = tableSchema.fields.map(f => f.name.toLowerCase -> f).toMap
    +
    +    var schema = new StructType()
    +    rddSchema.fields.foreach { f =>
    +      if (nameMap.isDefinedAt(f.name)) {
    +        // identical names
    +        schema = schema.add(nameMap(f.name))
    +      } else if (!caseSensitive && lowercaseNameMap.isDefinedAt(f.name.toLowerCase))
{
    +        // identical names in a case-insensitive way
    +        schema = schema.add(lowercaseNameMap(f.name.toLowerCase))
    +      } else {
    +        throw new AnalysisException(s"""Column "${f.name}" not found""")
    --- End diff --
    
    The error message looks ambiguous. Maybe `Column "${f.name}" in RDD not found in table
schema`?


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message