[SPARK-18652][PYTHON] Include the example data and third-party licenses in pyspark package.

## What changes were proposed in this pull request?

Since we already include the python examples in the pyspark package, we should include the example data with it as well.

We should also include the third-party licences since we distribute their jars with the pyspark package.

## How was this patch tested?

Manually tested with python2.7 and python3.4
```sh
$ ./build/mvn -DskipTests -Phive -Phive-thriftserver -Pyarn -Pmesos clean package
$ cd python
$ python setup.py sdist
$ pip install  dist/pyspark-2.1.0.dev0.tar.gz

$ ls -1 /usr/local/lib/python2.7/dist-packages/pyspark/data/
graphx
mllib
streaming

$ du -sh /usr/local/lib/python2.7/dist-packages/pyspark/data/
600K    /usr/local/lib/python2.7/dist-packages/pyspark/data/

$ ls -1  /usr/local/lib/python2.7/dist-packages/pyspark/licenses/|head -5
LICENSE-AnchorJS.txt
LICENSE-DPark.txt
LICENSE-Mockito.txt
LICENSE-SnapTree.txt
LICENSE-antlr.txt
```

Author: Shuai Lin <linshuai2012@gmail.com>

Closes #16082 from lins05/include-data-in-pyspark-dist.

2 files changed, 21 insertions, 1 deletions

diff --git a/python/MANIFEST.in b/python/MANIFEST.in
index bbcce1baa4..40f1fb2f1e 100644
--- a/python/MANIFEST.in
+++ b/python/MANIFEST.in
@@ -17,6 +17,8 @@
 global-exclude *.py[cod] __pycache__ .DS_Store
 recursive-include deps/jars *.jar
 graft deps/bin
+recursive-include deps/data *.data *.txt
+recursive-include deps/licenses *.txt
 recursive-include deps/examples *.py
 recursive-include lib *.zip
 include README.md
diff --git a/python/setup.py b/python/setup.py
index 625aea0407..bc2eb4ce9d 100644
--- a/python/setup.py
+++ b/python/setup.py
@@ -69,10 +69,14 @@ elif len(JARS_PATH) == 0 and not os.path.exists(TEMP_PATH):
 
 EXAMPLES_PATH = os.path.join(SPARK_HOME, "examples/src/main/python")
 SCRIPTS_PATH = os.path.join(SPARK_HOME, "bin")
+DATA_PATH = os.path.join(SPARK_HOME, "data")
+LICENSES_PATH = os.path.join(SPARK_HOME, "licenses")
+
 SCRIPTS_TARGET = os.path.join(TEMP_PATH, "bin")
 JARS_TARGET = os.path.join(TEMP_PATH, "jars")
 EXAMPLES_TARGET = os.path.join(TEMP_PATH, "examples")
-
+DATA_TARGET = os.path.join(TEMP_PATH, "data")
+LICENSES_TARGET = os.path.join(TEMP_PATH, "licenses")
 
 # Check and see if we are under the spark path in which case we need to build the symlink farm.
 # This is important because we only want to build the symlink farm while under Spark otherwise we
@@ -114,11 +118,15 @@ try:
             os.symlink(JARS_PATH, JARS_TARGET)
             os.symlink(SCRIPTS_PATH, SCRIPTS_TARGET)
             os.symlink(EXAMPLES_PATH, EXAMPLES_TARGET)
+            os.symlink(DATA_PATH, DATA_TARGET)
+            os.symlink(LICENSES_PATH, LICENSES_TARGET)
         else:
             # For windows fall back to the slower copytree
             copytree(JARS_PATH, JARS_TARGET)
             copytree(SCRIPTS_PATH, SCRIPTS_TARGET)
             copytree(EXAMPLES_PATH, EXAMPLES_TARGET)
+            copytree(DATA_PATH, DATA_TARGET)
+            copytree(LICENSES_PATH, LICENSES_TARGET)
     else:
         # If we are not inside of SPARK_HOME verify we have the required symlink farm
         if not os.path.exists(JARS_TARGET):
@@ -161,18 +169,24 @@ try:
                   'pyspark.jars',
                   'pyspark.python.pyspark',
                   'pyspark.python.lib',
+                  'pyspark.data',
+                  'pyspark.licenses',
                   'pyspark.examples.src.main.python'],
         include_package_data=True,
         package_dir={
             'pyspark.jars': 'deps/jars',
             'pyspark.bin': 'deps/bin',
             'pyspark.python.lib': 'lib',
+            'pyspark.data': 'deps/data',
+            'pyspark.licenses': 'deps/licenses',
             'pyspark.examples.src.main.python': 'deps/examples',
         },
         package_data={
             'pyspark.jars': ['*.jar'],
             'pyspark.bin': ['*'],
             'pyspark.python.lib': ['*.zip'],
+            'pyspark.data': ['*.txt', '*.data'],
+            'pyspark.licenses': ['*.txt'],
             'pyspark.examples.src.main.python': ['*.py', '*/*.py']},
         scripts=scripts,
         license='http://www.apache.org/licenses/LICENSE-2.0',
@@ -202,8 +216,12 @@ finally:
             os.remove(os.path.join(TEMP_PATH, "jars"))
             os.remove(os.path.join(TEMP_PATH, "bin"))
             os.remove(os.path.join(TEMP_PATH, "examples"))
+            os.remove(os.path.join(TEMP_PATH, "data"))
+            os.remove(os.path.join(TEMP_PATH, "licenses"))
         else:
             rmtree(os.path.join(TEMP_PATH, "jars"))
             rmtree(os.path.join(TEMP_PATH, "bin"))
             rmtree(os.path.join(TEMP_PATH, "examples"))
+            rmtree(os.path.join(TEMP_PATH, "data"))
+            rmtree(os.path.join(TEMP_PATH, "licenses"))
         os.rmdir(TEMP_PATH)