AngersZhuuuu commented on a change in pull request #29966:
URL: https://github.com/apache/spark/pull/29966#discussion_r533495197
##########
File path: core/src/main/scala/org/apache/spark/SparkContext.scala
##########
@@ -1919,18 +1919,24 @@ class SparkContext(config: SparkConf) extends Logging {
// A JAR file which exists only on the driver node
case "file" => addLocalJarFile(new File(uri.getPath))
// A JAR file which exists locally on every worker node
- case "local" => "file:" + uri.getPath
+ case "local" => Seq("file:" + uri.getPath)
+ case "ivy" =>
+ // Since `new Path(path).toUri` will lose query information,
+ // so here we use `URI.create(path)`
+ DependencyUtils.resolveMavenDependencies(URI.create(path))
Review comment:
Done
##########
File path: core/src/main/scala/org/apache/spark/util/DependencyUtils.scala
##########
@@ -15,22 +15,115 @@
* limitations under the License.
*/
-package org.apache.spark.deploy
+package org.apache.spark.util
import java.io.File
-import java.net.URI
+import java.net.{URI, URISyntaxException}
import org.apache.commons.lang3.StringUtils
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.{SecurityManager, SparkConf, SparkException}
+import org.apache.spark.deploy.SparkSubmitUtils
import org.apache.spark.internal.Logging
-import org.apache.spark.util.{MutableURLClassLoader, Utils}
-private[deploy] object DependencyUtils extends Logging {
+private[spark] object DependencyUtils extends Logging {
+
+ def getIvyProperties(): Seq[String] = {
+ Seq(
+ "spark.jars.excludes",
+ "spark.jars.packages",
+ "spark.jars.repositories",
+ "spark.jars.ivy",
+ "spark.jars.ivySettings"
+ ).map(sys.props.get(_).orNull)
+ }
+
+ def parseQueryParams(uriQuery: String): (Boolean, String) = {
+ if (uriQuery == null) {
+ (false, "")
+ } else {
+ val mapTokens = uriQuery.split("&").map(_.split("="))
+ if (mapTokens.exists(_.length != 2)) {
+ throw new URISyntaxException(uriQuery, s"Invalid query string:
$uriQuery")
+ }
+ val groupedParams = mapTokens.map(kv => (kv(0), kv(1))).groupBy(_._1)
+ // Parse transitive parameters (e.g., transitive=true) in an ivy URL,
default value is false
+ var transitive = false
+ groupedParams.get("transitive").foreach { params =>
+ if (params.length > 1) {
+ logWarning("It's best to specify `transitive` parameter in ivy URL
query only once." +
+ " If there are multiple `transitive` parameter, we will select the
last one")
+ }
+ params.map(_._2).foreach(value => {
+ if (value == "true") {
+ transitive = true
+ } else if (value == "false") {
+ transitive = false
+ }
+ })
+ }
+ // Parse an excluded list (e.g.,
exclude=org.mortbay.jetty:jetty,org.eclipse.jetty:jetty-http)
+ // in an ivy URL. When download ivy URL jar, Spark won't download
transitive jar
+ // in a excluded list.
+ val exclusionList = groupedParams.get("exclude").map { params =>
+ params.flatMap { case (_, excludeString) =>
+ val excludes = excludeString.split(",")
+ if (excludes.exists(_.split(":").length != 2)) {
+ throw new URISyntaxException(excludeString, "Invalid exclude
string: " +
+ "expected 'org:module,org:module,..', found " + excludeString)
+ }
+ excludes
+ }.mkString(",")
+ }.getOrElse("")
+
+ (transitive, exclusionList)
Review comment:
Done
##########
File path: core/src/main/scala/org/apache/spark/util/DependencyUtils.scala
##########
@@ -15,22 +15,122 @@
* limitations under the License.
*/
-package org.apache.spark.deploy
+package org.apache.spark.util
import java.io.File
-import java.net.URI
+import java.net.{URI, URISyntaxException}
import org.apache.commons.lang3.StringUtils
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.{SecurityManager, SparkConf, SparkException}
+import org.apache.spark.deploy.SparkSubmitUtils
import org.apache.spark.internal.Logging
-import org.apache.spark.util.{MutableURLClassLoader, Utils}
-private[deploy] object DependencyUtils extends Logging {
+private[spark] object DependencyUtils extends Logging {
+
+ def getIvyProperties(): Seq[String] = {
+ Seq(
+ "spark.jars.excludes",
+ "spark.jars.packages",
+ "spark.jars.repositories",
+ "spark.jars.ivy",
+ "spark.jars.ivySettings"
+ ).map(sys.props.get(_).orNull)
+ }
+
+ /**
+ * Parse excluded list in ivy URL. When download ivy URL jar, Spark won't
download transitive jar
+ * in excluded list.
+ *
+ * @param queryString Ivy URI query part string.
+ * @return Exclude list which contains grape parameters of exclude.
+ * Example: Input:
exclude=org.mortbay.jetty:jetty,org.eclipse.jetty:jetty-http
+ * Output: [org.mortbay.jetty:jetty, org.eclipse.jetty:jetty-http]
+ */
+ private def parseExcludeList(excludes: Array[String]): String = {
+ excludes.flatMap { excludeString =>
+ val excludes: Array[String] = excludeString.split(",")
+ if (excludes.exists(_.split(":").length != 2)) {
+ throw new URISyntaxException(excludeString,
+ "Invalid exclude string: expected 'org:module,org:module,..', found
" + excludeString)
+ }
+ excludes
+ }.mkString(":")
+ }
+
+ /**
+ * Parse transitive parameter in ivy URL, default value is false.
+ *
+ * @param queryString Ivy URI query part string.
+ * @return Exclude list which contains grape parameters of transitive.
+ * Example: Input: exclude=org.mortbay.jetty:jetty&transitive=true
+ * Output: true
+ */
+ private def parseTransitive(transitives: Array[String]): Boolean = {
+ if (transitives.isEmpty) {
+ false
+ } else {
+ if (transitives.length > 1) {
+ logWarning("It's best to specify `transitive` parameter in ivy URL
query only once." +
+ " If there are multiple `transitive` parameter, we will select the
last one")
+ }
+ transitives.last.toBoolean
+ }
+ }
+
+ /**
+ * Download Ivy URIs dependency jars.
+ *
+ * @param uri Ivy uri need to be downloaded. The URI format should be:
+ * `ivy://group:module:version[?query]`
+ * Ivy URI query part format should be:
+ * `parameter=value¶meter=value...`
+ * Note that currently ivy URI query part support two parameters:
+ * 1. transitive: whether to download dependent jars related to
your ivy URL.
+ * transitive=false or `transitive=true`, if not set, the
default value is false.
+ * 2. exclude: exclusion list when download ivy URL jar and
dependency jars.
+ * The `exclude` parameter content is a ',' separated
`group:module` pair string :
+ * `exclude=group:module,group:module...`
+ * @return Comma separated string list of URIs of downloaded jars
+ */
+ def resolveMavenDependencies(uri: URI): String = {
+ val Seq(_, _, repositories, ivyRepoPath, ivySettingsPath) =
+ DependencyUtils.getIvyProperties()
+ val authority = uri.getAuthority
+ if (authority == null) {
+ throw new URISyntaxException(
+ authority, "Invalid url: Expected 'org:module:version', found null")
+ }
+ if (authority.split(":").length != 3) {
+ throw new URISyntaxException(
+ authority, "Invalid url: Expected 'org:module:version', found " +
authority)
+ }
+
+ val uriQuery = uri.getQuery
+ val queryParams: Array[(String, String)] = if (uriQuery == null) {
+ Array.empty[(String, String)]
+ } else {
+ val mapTokens = uriQuery.split("&").map(_.split("="))
+ if (mapTokens.exists(_.length != 2)) {
+ throw new URISyntaxException(uriQuery, s"Invalid query string:
$uriQuery")
+ }
+ mapTokens.map(kv => (kv(0), kv(1)))
+ }
+
+ resolveMavenDependencies(
+ parseTransitive(queryParams.filter(_._1.equals("transitive")).map(_._2)),
Review comment:
Done
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
