Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions build.sbt
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,11 @@ name := "spark-google-spreadsheets"

organization := "com.github.potix2"

scalaVersion := "2.11.12"
scalaVersion := "2.12.10"

crossScalaVersions := Seq("2.11.12")
crossScalaVersions := Seq("2.12.10")

version := "0.6.4-SNAPSHOT"
version := "0.6.4"

spName := "potix2/spark-google-spreadsheets"

Expand All @@ -16,7 +16,7 @@ spIncludeMaven := true

spIgnoreProvided := true

sparkVersion := "2.3.3"
sparkVersion := "2.4.4"

val testSparkVersion = settingKey[String]("The version of Spark to test against.")

Expand All @@ -26,7 +26,7 @@ sparkComponents := Seq("sql")

libraryDependencies ++= Seq(
"org.slf4j" % "slf4j-api" % "1.7.5" % "provided",
"org.scalatest" %% "scalatest" % "2.2.1" % "test",
"org.scalatest" %% "scalatest" % "3.0.8" % "test",
("com.google.api-client" % "google-api-client" % "1.22.0").
exclude("com.google.guava", "guava-jdk5"),
"com.google.oauth-client" % "google-oauth-client-jetty" % "1.22.0",
Expand Down Expand Up @@ -55,6 +55,9 @@ publishArtifact in Test := false

pomIncludeRepository := { _ => false }

//publishMavenStyle := true
//publishTo := Some(Resolver.file("file", new File(Path.userHome.absolutePath+"/.m2/repository")))

publishTo := {
val nexus = "https://oss.sonatype.org/"
if (version.value.endsWith("SNAPSHOT"))
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ case class SpreadsheetRelation protected[spark] (

import com.github.potix2.spark.google.spreadsheets.SparkSpreadsheetService._

private val fieldMap = scala.collection.mutable.Map[String, String]()
override def schema: StructType = userSchema.getOrElse(inferSchema())

private lazy val aWorksheet: SparkWorksheet =
Expand All @@ -47,6 +48,7 @@ case class SpreadsheetRelation protected[spark] (

override def buildScan(): RDD[Row] = {
val aSchema = schema
val schemaMap = fieldMap.toMap
sqlContext.sparkContext.makeRDD(rows).mapPartitions { iter =>
iter.map { m =>
var index = 0
Expand All @@ -55,6 +57,8 @@ case class SpreadsheetRelation protected[spark] (
val field = aSchema.fields(index)
rowArray(index) = if (m.contains(field.name)) {
TypeCast.castTo(m(field.name), field.dataType, field.nullable)
} else if (schemaMap.contains(field.name) && m.contains(schemaMap(field.name))) {
TypeCast.castTo(m(schemaMap(field.name)), field.dataType, field.nullable)
} else {
null
}
Expand All @@ -78,9 +82,19 @@ case class SpreadsheetRelation protected[spark] (
}
}

def sanitizeColumnName(name: String): String =
{
name
.replaceAll("[^a-zA-Z0-9]+", "_") // Replace sequences of non-alphanumeric characters with underscores
.replaceAll("_+$", "") // Strip trailing underscores
.replaceAll("^[0-9_]+", "") // Strip leading underscores and digits
}

private def inferSchema(): StructType =
StructType(aWorksheet.headers.toList.map { fieldName =>
StructField(fieldName, StringType, nullable = true)
})
StructType(aWorksheet.headers.toList.map { fieldName => {
val sanitizedName = sanitizeColumnName(fieldName)
fieldMap.put(sanitizedName, fieldName)
StructField(sanitizedName, StringType, true)
}})

}