Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11509#discussion_r55117253
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/ResolvedDataSource.scala
---
@@ -92,19 +96,61 @@ object ResolvedDataSource extends Logging {
}
}
+ // TODO: Combine with apply?
def createSource(
sqlContext: SQLContext,
userSpecifiedSchema: Option[StructType],
providerName: String,
options: Map[String, String]): Source = {
val provider = lookupDataSource(providerName).newInstance() match {
- case s: StreamSourceProvider => s
+ case s: StreamSourceProvider =>
+ s.createSource(sqlContext, userSpecifiedSchema, providerName,
options)
+
+ case format: FileFormat =>
+ val caseInsensitiveOptions = new CaseInsensitiveMap(options)
+ val path = caseInsensitiveOptions.getOrElse("path", {
+ throw new IllegalArgumentException("'path' is not specified")
+ })
+ val metadataPath =
caseInsensitiveOptions.getOrElse("metadataPath", s"$path/_metadata")
+
+ val allPaths = caseInsensitiveOptions.get("path")
+ val globbedPaths = allPaths.toSeq.flatMap { path =>
+ val hdfsPath = new Path(path)
+ val fs =
hdfsPath.getFileSystem(sqlContext.sparkContext.hadoopConfiguration)
+ val qualified = hdfsPath.makeQualified(fs.getUri,
fs.getWorkingDirectory)
+ SparkHadoopUtil.get.globPathIfNecessary(qualified)
+ }.toArray
+
+ val fileCatalog: FileCatalog = new HDFSFileCatalog(sqlContext,
options, globbedPaths)
+ val dataSchema = userSpecifiedSchema.orElse {
+ format.inferSchema(
+ sqlContext,
+ caseInsensitiveOptions,
+ fileCatalog.allFiles())
+ }.getOrElse {
+ throw new AnalysisException("Unable to infer schema. It must be
specified manually.")
+ }
+
+ def dataFrameBuilder(files: Array[String]): DataFrame = {
+ new DataFrame(
+ sqlContext,
+ LogicalRelation(
+ apply(
+ sqlContext,
--- End diff --
indent?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
