[SPARK-10359] Enumerate dependencies in a file and diff against it for new pull requests

This patch adds a new build check which enumerates Spark's resolved runtime classpath and saves it to a file, then diffs against that file to detect whether pull requests have introduced dependency changes. The aim of this check is to make it simpler to reason about whether pull request which modify the build have introduced new dependencies or changed transitive dependencies in a way that affects the final classpath.

This supplants the checks added in SPARK-4123 / #5093, which are currently disabled due to bugs.

This patch is based on pwendell's work in #8531.

Closes #8531.

Author: Josh Rosen <joshrosen@databricks.com>
Author: Patrick Wendell <patrick@databricks.com>

Closes #10461 from JoshRosen/SPARK-10359.

2 files changed, 369 insertions, 0 deletions

diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3
new file mode 100644
index 0000000000..6014d50c6b
--- /dev/null
+++ b/dev/deps/spark-deps-hadoop-2.3
@@ -0,0 +1,184 @@
+JavaEWAH-0.3.2.jar
+RoaringBitmap-0.5.11.jar
+ST4-4.0.4.jar
+activation-1.1.1.jar
+akka-actor_2.10-2.3.11.jar
+akka-remote_2.10-2.3.11.jar
+akka-slf4j_2.10-2.3.11.jar
+antlr-2.7.7.jar
+antlr-runtime-3.4.jar
+aopalliance-1.0.jar
+apache-log4j-extras-1.2.17.jar
+arpack_combined_all-0.1.jar
+asm-3.1.jar
+asm-commons-3.1.jar
+asm-tree-3.1.jar
+avro-1.7.7.jar
+avro-ipc-1.7.7-tests.jar
+avro-ipc-1.7.7.jar
+avro-mapred-1.7.7-hadoop2.jar
+base64-2.3.8.jar
+bcprov-jdk15on-1.51.jar
+bonecp-0.8.0.RELEASE.jar
+breeze-macros_2.10-0.11.2.jar
+breeze_2.10-0.11.2.jar
+calcite-avatica-1.2.0-incubating.jar
+calcite-core-1.2.0-incubating.jar
+calcite-linq4j-1.2.0-incubating.jar
+chill-java-0.5.0.jar
+chill_2.10-0.5.0.jar
+commons-beanutils-1.7.0.jar
+commons-beanutils-core-1.8.0.jar
+commons-cli-1.2.jar
+commons-codec-1.10.jar
+commons-collections-3.2.2.jar
+commons-compiler-2.7.6.jar
+commons-compress-1.4.1.jar
+commons-configuration-1.6.jar
+commons-dbcp-1.4.jar
+commons-digester-1.8.jar
+commons-httpclient-3.1.jar
+commons-io-2.4.jar
+commons-lang-2.6.jar
+commons-lang3-3.3.2.jar
+commons-logging-1.1.3.jar
+commons-math3-3.4.1.jar
+commons-net-2.2.jar
+commons-pool-1.5.4.jar
+compress-lzf-1.0.3.jar
+config-1.2.1.jar
+core-1.1.2.jar
+curator-client-2.4.0.jar
+curator-framework-2.4.0.jar
+curator-recipes-2.4.0.jar
+datanucleus-api-jdo-3.2.6.jar
+datanucleus-core-3.2.10.jar
+datanucleus-rdbms-3.2.9.jar
+derby-10.10.1.1.jar
+eigenbase-properties-1.1.5.jar
+geronimo-annotation_1.0_spec-1.1.1.jar
+geronimo-jaspic_1.0_spec-1.0.jar
+geronimo-jta_1.1_spec-1.1.1.jar
+groovy-all-2.1.6.jar
+guice-3.0.jar
+guice-servlet-3.0.jar
+hadoop-annotations-2.3.0.jar
+hadoop-auth-2.3.0.jar
+hadoop-client-2.3.0.jar
+hadoop-common-2.3.0.jar
+hadoop-hdfs-2.3.0.jar
+hadoop-mapreduce-client-app-2.3.0.jar
+hadoop-mapreduce-client-common-2.3.0.jar
+hadoop-mapreduce-client-core-2.3.0.jar
+hadoop-mapreduce-client-jobclient-2.3.0.jar
+hadoop-mapreduce-client-shuffle-2.3.0.jar
+hadoop-yarn-api-2.3.0.jar
+hadoop-yarn-client-2.3.0.jar
+hadoop-yarn-common-2.3.0.jar
+hadoop-yarn-server-common-2.3.0.jar
+hadoop-yarn-server-web-proxy-2.3.0.jar
+httpclient-4.3.2.jar
+httpcore-4.3.2.jar
+ivy-2.4.0.jar
+jackson-annotations-2.4.4.jar
+jackson-core-2.4.4.jar
+jackson-core-asl-1.9.13.jar
+jackson-databind-2.4.4.jar
+jackson-jaxrs-1.9.13.jar
+jackson-mapper-asl-1.9.13.jar
+jackson-module-scala_2.10-2.4.4.jar
+jackson-xc-1.9.13.jar
+janino-2.7.8.jar
+jansi-1.4.jar
+java-xmlbuilder-1.0.jar
+javax.inject-1.jar
+javax.servlet-3.0.0.v201112011016.jar
+javolution-5.5.1.jar
+jaxb-api-2.2.2.jar
+jaxb-impl-2.2.3-1.jar
+jcl-over-slf4j-1.7.10.jar
+jdo-api-3.0.1.jar
+jersey-core-1.9.jar
+jersey-guice-1.9.jar
+jersey-json-1.9.jar
+jersey-server-1.9.jar
+jets3t-0.9.3.jar
+jettison-1.1.jar
+jetty-6.1.26.jar
+jetty-all-7.6.0.v20120127.jar
+jetty-util-6.1.26.jar
+jline-2.10.5.jar
+jline-2.12.jar
+joda-time-2.9.jar
+jodd-core-3.5.2.jar
+jpam-1.1.jar
+json-20090211.jar
+json4s-ast_2.10-3.2.10.jar
+json4s-core_2.10-3.2.10.jar
+json4s-jackson_2.10-3.2.10.jar
+jsr305-1.3.9.jar
+jta-1.1.jar
+jtransforms-2.4.0.jar
+jul-to-slf4j-1.7.10.jar
+kryo-2.21.jar
+leveldbjni-all-1.8.jar
+libfb303-0.9.2.jar
+libthrift-0.9.2.jar
+log4j-1.2.17.jar
+lz4-1.3.0.jar
+mail-1.4.7.jar
+mesos-0.21.1-shaded-protobuf.jar
+metrics-core-3.1.2.jar
+metrics-graphite-3.1.2.jar
+metrics-json-3.1.2.jar
+metrics-jvm-3.1.2.jar
+minlog-1.2.jar
+mx4j-3.0.2.jar
+netty-3.8.0.Final.jar
+netty-all-4.0.29.Final.jar
+objenesis-1.2.jar
+opencsv-2.3.jar
+oro-2.0.8.jar
+paranamer-2.6.jar
+parquet-column-1.7.0.jar
+parquet-common-1.7.0.jar
+parquet-encoding-1.7.0.jar
+parquet-format-2.3.0-incubating.jar
+parquet-generator-1.7.0.jar
+parquet-hadoop-1.7.0.jar
+parquet-hadoop-bundle-1.6.0.jar
+parquet-jackson-1.7.0.jar
+pmml-agent-1.2.7.jar
+pmml-model-1.2.7.jar
+pmml-schema-1.2.7.jar
+protobuf-java-2.5.0.jar
+py4j-0.9.jar
+pyrolite-4.9.jar
+quasiquotes_2.10-2.0.0-M8.jar
+reflectasm-1.07-shaded.jar
+scala-compiler-2.10.5.jar
+scala-library-2.10.5.jar
+scala-reflect-2.10.5.jar
+scalap-2.10.5.jar
+servlet-api-2.5.jar
+slf4j-api-1.7.10.jar
+slf4j-log4j12-1.7.10.jar
+snappy-0.2.jar
+snappy-java-1.1.2.jar
+spire-macros_2.10-0.7.4.jar
+spire_2.10-0.7.4.jar
+stax-api-1.0-2.jar
+stax-api-1.0.1.jar
+stream-2.7.0.jar
+stringtemplate-3.2.1.jar
+super-csv-2.2.0.jar
+tachyon-client-0.8.2.jar
+tachyon-underfs-hdfs-0.8.2.jar
+tachyon-underfs-local-0.8.2.jar
+tachyon-underfs-s3-0.8.2.jar
+uncommons-maths-1.2.2a.jar
+unused-1.0.0.jar
+xbean-asm5-shaded-4.4.jar
+xmlenc-0.52.jar
+xz-1.0.jar
+zookeeper-3.4.5.jar
diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4
new file mode 100644
index 0000000000..f56e6f4393
--- /dev/null
+++ b/dev/deps/spark-deps-hadoop-2.4
@@ -0,0 +1,185 @@
+JavaEWAH-0.3.2.jar
+RoaringBitmap-0.5.11.jar
+ST4-4.0.4.jar
+activation-1.1.1.jar
+akka-actor_2.10-2.3.11.jar
+akka-remote_2.10-2.3.11.jar
+akka-slf4j_2.10-2.3.11.jar
+antlr-2.7.7.jar
+antlr-runtime-3.4.jar
+aopalliance-1.0.jar
+apache-log4j-extras-1.2.17.jar
+arpack_combined_all-0.1.jar
+asm-3.1.jar
+asm-commons-3.1.jar
+asm-tree-3.1.jar
+avro-1.7.7.jar
+avro-ipc-1.7.7-tests.jar
+avro-ipc-1.7.7.jar
+avro-mapred-1.7.7-hadoop2.jar
+base64-2.3.8.jar
+bcprov-jdk15on-1.51.jar
+bonecp-0.8.0.RELEASE.jar
+breeze-macros_2.10-0.11.2.jar
+breeze_2.10-0.11.2.jar
+calcite-avatica-1.2.0-incubating.jar
+calcite-core-1.2.0-incubating.jar
+calcite-linq4j-1.2.0-incubating.jar
+chill-java-0.5.0.jar
+chill_2.10-0.5.0.jar
+commons-beanutils-1.7.0.jar
+commons-beanutils-core-1.8.0.jar
+commons-cli-1.2.jar
+commons-codec-1.10.jar
+commons-collections-3.2.2.jar
+commons-compiler-2.7.6.jar
+commons-compress-1.4.1.jar
+commons-configuration-1.6.jar
+commons-dbcp-1.4.jar
+commons-digester-1.8.jar
+commons-httpclient-3.1.jar
+commons-io-2.4.jar
+commons-lang-2.6.jar
+commons-lang3-3.3.2.jar
+commons-logging-1.1.3.jar
+commons-math3-3.4.1.jar
+commons-net-2.2.jar
+commons-pool-1.5.4.jar
+compress-lzf-1.0.3.jar
+config-1.2.1.jar
+core-1.1.2.jar
+curator-client-2.4.0.jar
+curator-framework-2.4.0.jar
+curator-recipes-2.4.0.jar
+datanucleus-api-jdo-3.2.6.jar
+datanucleus-core-3.2.10.jar
+datanucleus-rdbms-3.2.9.jar
+derby-10.10.1.1.jar
+eigenbase-properties-1.1.5.jar
+geronimo-annotation_1.0_spec-1.1.1.jar
+geronimo-jaspic_1.0_spec-1.0.jar
+geronimo-jta_1.1_spec-1.1.1.jar
+groovy-all-2.1.6.jar
+guice-3.0.jar
+guice-servlet-3.0.jar
+hadoop-annotations-2.4.0.jar
+hadoop-auth-2.4.0.jar
+hadoop-client-2.4.0.jar
+hadoop-common-2.4.0.jar
+hadoop-hdfs-2.4.0.jar
+hadoop-mapreduce-client-app-2.4.0.jar
+hadoop-mapreduce-client-common-2.4.0.jar
+hadoop-mapreduce-client-core-2.4.0.jar
+hadoop-mapreduce-client-jobclient-2.4.0.jar
+hadoop-mapreduce-client-shuffle-2.4.0.jar
+hadoop-yarn-api-2.4.0.jar
+hadoop-yarn-client-2.4.0.jar
+hadoop-yarn-common-2.4.0.jar
+hadoop-yarn-server-common-2.4.0.jar
+hadoop-yarn-server-web-proxy-2.4.0.jar
+httpclient-4.3.2.jar
+httpcore-4.3.2.jar
+ivy-2.4.0.jar
+jackson-annotations-2.4.4.jar
+jackson-core-2.4.4.jar
+jackson-core-asl-1.9.13.jar
+jackson-databind-2.4.4.jar
+jackson-jaxrs-1.9.13.jar
+jackson-mapper-asl-1.9.13.jar
+jackson-module-scala_2.10-2.4.4.jar
+jackson-xc-1.9.13.jar
+janino-2.7.8.jar
+jansi-1.4.jar
+java-xmlbuilder-1.0.jar
+javax.inject-1.jar
+javax.servlet-3.0.0.v201112011016.jar
+javolution-5.5.1.jar
+jaxb-api-2.2.2.jar
+jaxb-impl-2.2.3-1.jar
+jcl-over-slf4j-1.7.10.jar
+jdo-api-3.0.1.jar
+jersey-client-1.9.jar
+jersey-core-1.9.jar
+jersey-guice-1.9.jar
+jersey-json-1.9.jar
+jersey-server-1.9.jar
+jets3t-0.9.3.jar
+jettison-1.1.jar
+jetty-6.1.26.jar
+jetty-all-7.6.0.v20120127.jar
+jetty-util-6.1.26.jar
+jline-2.10.5.jar
+jline-2.12.jar
+joda-time-2.9.jar
+jodd-core-3.5.2.jar
+jpam-1.1.jar
+json-20090211.jar
+json4s-ast_2.10-3.2.10.jar
+json4s-core_2.10-3.2.10.jar
+json4s-jackson_2.10-3.2.10.jar
+jsr305-1.3.9.jar
+jta-1.1.jar
+jtransforms-2.4.0.jar
+jul-to-slf4j-1.7.10.jar
+kryo-2.21.jar
+leveldbjni-all-1.8.jar
+libfb303-0.9.2.jar
+libthrift-0.9.2.jar
+log4j-1.2.17.jar
+lz4-1.3.0.jar
+mail-1.4.7.jar
+mesos-0.21.1-shaded-protobuf.jar
+metrics-core-3.1.2.jar
+metrics-graphite-3.1.2.jar
+metrics-json-3.1.2.jar
+metrics-jvm-3.1.2.jar
+minlog-1.2.jar
+mx4j-3.0.2.jar
+netty-3.8.0.Final.jar
+netty-all-4.0.29.Final.jar
+objenesis-1.2.jar
+opencsv-2.3.jar
+oro-2.0.8.jar
+paranamer-2.6.jar
+parquet-column-1.7.0.jar
+parquet-common-1.7.0.jar
+parquet-encoding-1.7.0.jar
+parquet-format-2.3.0-incubating.jar
+parquet-generator-1.7.0.jar
+parquet-hadoop-1.7.0.jar
+parquet-hadoop-bundle-1.6.0.jar
+parquet-jackson-1.7.0.jar
+pmml-agent-1.2.7.jar
+pmml-model-1.2.7.jar
+pmml-schema-1.2.7.jar
+protobuf-java-2.5.0.jar
+py4j-0.9.jar
+pyrolite-4.9.jar
+quasiquotes_2.10-2.0.0-M8.jar
+reflectasm-1.07-shaded.jar
+scala-compiler-2.10.5.jar
+scala-library-2.10.5.jar
+scala-reflect-2.10.5.jar
+scalap-2.10.5.jar
+servlet-api-2.5.jar
+slf4j-api-1.7.10.jar
+slf4j-log4j12-1.7.10.jar
+snappy-0.2.jar
+snappy-java-1.1.2.jar
+spire-macros_2.10-0.7.4.jar
+spire_2.10-0.7.4.jar
+stax-api-1.0-2.jar
+stax-api-1.0.1.jar
+stream-2.7.0.jar
+stringtemplate-3.2.1.jar
+super-csv-2.2.0.jar
+tachyon-client-0.8.2.jar
+tachyon-underfs-hdfs-0.8.2.jar
+tachyon-underfs-local-0.8.2.jar
+tachyon-underfs-s3-0.8.2.jar
+uncommons-maths-1.2.2a.jar
+unused-1.0.0.jar
+xbean-asm5-shaded-4.4.jar
+xmlenc-0.52.jar
+xz-1.0.jar
+zookeeper-3.4.5.jar