[SPARK-10300] [BUILD] [TESTS] Add support for test tags in run-tests.py.

This change does two things:

- tag a few tests and adds the mechanism in the build to be able to disable those tags,
  both in maven and sbt, for both junit and scalatest suites.
- add some logic to run-tests.py to disable some tags depending on what files have
  changed; that's used to disable expensive tests when a module hasn't explicitly
  been changed, to speed up testing for changes that don't directly affect those
  modules.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #8437 from vanzin/test-tags.

1 files changed, 23 insertions, 1 deletions

diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index 346452f317..65397f1f3e 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -31,7 +31,7 @@ class Module(object):
 
     def __init__(self, name, dependencies, source_file_regexes, build_profile_flags=(), environ={},
                  sbt_test_goals=(), python_test_goals=(), blacklisted_python_implementations=(),
-                 should_run_r_tests=False):
+                 test_tags=(), should_run_r_tests=False):
         """
         Define a new module.
 
@@ -50,6 +50,8 @@ class Module(object):
         :param blacklisted_python_implementations: A set of Python implementations that are not
             supported by this module's Python components. The values in this set should match
             strings returned by Python's `platform.python_implementation()`.
+        :param test_tags A set of tags that will be excluded when running unit tests if the module
+            is not explicitly changed.
         :param should_run_r_tests: If true, changes in this module will trigger all R tests.
         """
         self.name = name
@@ -60,6 +62,7 @@ class Module(object):
         self.environ = environ
         self.python_test_goals = python_test_goals
         self.blacklisted_python_implementations = blacklisted_python_implementations
+        self.test_tags = test_tags
         self.should_run_r_tests = should_run_r_tests
 
         self.dependent_modules = set()
@@ -85,6 +88,9 @@ sql = Module(
         "catalyst/test",
         "sql/test",
         "hive/test",
+    ],
+    test_tags=[
+        "org.apache.spark.sql.hive.ExtendedHiveTest"
     ]
 )
 
@@ -398,6 +404,22 @@ ec2 = Module(
 )
 
 
+yarn = Module(
+    name="yarn",
+    dependencies=[],
+    source_file_regexes=[
+        "yarn/",
+        "network/yarn/",
+    ],
+    sbt_test_goals=[
+        "yarn/test",
+        "network-yarn/test",
+    ],
+    test_tags=[
+        "org.apache.spark.deploy.yarn.ExtendedYarnTest"
+    ]
+)
+
 # The root module is a dummy module which is used to run all of the tests.
 # No other modules should directly depend on this module.
 root = Module(