Add an alias compression for codec for consistency with Spark's internal data sources

README.md

@@ -62,7 +62,7 @@ When writing files the API accepts several options:
 * `nullValue`: The value to write `null` value. Default is string `null`. When this is `null`, it does not write attributes and elements for fields.
 * `attributePrefix`: The prefix for attributes so that we can differentiating attributes and elements. This will be the prefix for field names. Default is `@`.
 * `valueTag`: The tag used for the value when there are attributes in the element having no child. Default is `#VALUE`.
-* `codec`: compression codec to use when saving to file. Should be the fully qualified name of a class implementing `org.apache.hadoop.io.compress.CompressionCodec` or one of case-insensitive shorten names (`bzip2`, `gzip`, `lz4`, and `snappy`). Defaults to no compression when a codec is not specified.
+* `compression`: compression codec to use when saving to file. Should be the fully qualified name of a class implementing `org.apache.hadoop.io.compress.CompressionCodec` or one of case-insensitive shorten names (`bzip2`, `gzip`, `lz4`, and `snappy`). Defaults to no compression when a codec is not specified.
 
 Currently it supports the shortened name usage. You can use just `xml` instead of `com.databricks.spark.xml` from Spark 1.5.0+
 

src/main/scala/com/databricks/spark/xml/XmlOptions.scala

@@ -23,7 +23,7 @@ private[xml] class XmlOptions(
   extends Serializable{
 
   val charset = parameters.getOrElse("charset", XmlOptions.DEFAULT_CHARSET)
-  val codec = parameters.get("codec").orNull
+  val codec = parameters.get("compression").orElse(parameters.get("codec")).orNull
   val rowTag = parameters.getOrElse("rowTag", XmlOptions.DEFAULT_ROW_TAG)
   val rootTag = parameters.getOrElse("rootTag", XmlOptions.DEFAULT_ROOT_TAG)
   val samplingRatio = parameters.get("samplingRatio").map(_.toDouble).getOrElse(1.0)

src/test/scala/com/databricks/spark/xml/XmlSuite.scala

@@ -353,7 +353,7 @@ class XmlSuite extends FunSuite with BeforeAndAfterAll {
 
     val cars = sqlContext.xmlFile(carsFile)
     cars.save("com.databricks.spark.xml", SaveMode.Overwrite,
-      Map("path" -> copyFilePath, "codec" -> "gZiP"))
+      Map("path" -> copyFilePath, "compression" -> "gZiP"))
     val carsCopyPartFile = new File(copyFilePath, "part-00000.gz")
     // Check that the part file has a .gz extension
     assert(carsCopyPartFile.exists())