From 04e44b37cc04f62fbf9e08c7076349e0a4d12ea8 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Thu, 16 Apr 2015 16:20:57 -0700 Subject: [SPARK-4897] [PySpark] Python 3 support This PR update PySpark to support Python 3 (tested with 3.4). Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped. TODO: ec2/spark-ec2.py is not fully tested with python3. Author: Davies Liu Author: twneale Author: Josh Rosen Closes #5173 from davies/python3 and squashes the following commits: d7d6323 [Davies Liu] fix tests 6c52a98 [Davies Liu] fix mllib test 99e334f [Davies Liu] update timeout b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 cafd5ec [Davies Liu] adddress comments from @mengxr bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 179fc8d [Davies Liu] tuning flaky tests 8c8b957 [Davies Liu] fix ResourceWarning in Python 3 5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 4006829 [Davies Liu] fix test 2fc0066 [Davies Liu] add python3 path 71535e9 [Davies Liu] fix xrange and divide 5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ed498c8 [Davies Liu] fix compatibility with python 3 820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ad7c374 [Davies Liu] fix mllib test and warning ef1fc2f [Davies Liu] fix tests 4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 59bb492 [Davies Liu] fix tests 1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ca0fdd3 [Davies Liu] fix code style 9563a15 [Davies Liu] add imap back for python 2 0b1ec04 [Davies Liu] make python examples work with Python 3 d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 a716d34 [Davies Liu] test with python 3.4 f1700e8 [Davies Liu] fix test in python3 671b1db [Davies Liu] fix test in python3 692ff47 [Davies Liu] fix flaky test 7b9699f [Davies Liu] invalidate import cache for Python 3.3+ 9c58497 [Davies Liu] fix kill worker 309bfbf [Davies Liu] keep compatibility 5707476 [Davies Liu] cleanup, fix hash of string in 3.3+ 8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 f53e1f0 [Davies Liu] fix tests 70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3 a39167e [Davies Liu] support customize class in __main__ 814c77b [Davies Liu] run unittests with python 3 7f4476e [Davies Liu] mllib tests passed d737924 [Davies Liu] pass ml tests 375ea17 [Davies Liu] SQL tests pass 6cc42a9 [Davies Liu] rename 431a8de [Davies Liu] streaming tests pass 78901a7 [Davies Liu] fix hash of serializer in Python 3 24b2f2e [Davies Liu] pass all RDD tests 35f48fe [Davies Liu] run future again 1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py 6e3c21d [Davies Liu] make cloudpickle work with Python3 2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run 1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out 7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work. b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?). f40d925 [twneale] xrange --> range e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206 79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper 2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3 854be27 [Josh Rosen] Run `futurize` on Python code: 7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py. --- python/pyspark/worker.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'python/pyspark/worker.py') diff --git a/python/pyspark/worker.py b/python/pyspark/worker.py index 452d6fabdc..fbdaf3a581 100644 --- a/python/pyspark/worker.py +++ b/python/pyspark/worker.py @@ -18,6 +18,7 @@ """ Worker that receives input from Piped RDD. """ +from __future__ import print_function import os import sys import time @@ -37,9 +38,9 @@ utf8_deserializer = UTF8Deserializer() def report_times(outfile, boot, init, finish): write_int(SpecialLengths.TIMING_DATA, outfile) - write_long(1000 * boot, outfile) - write_long(1000 * init, outfile) - write_long(1000 * finish, outfile) + write_long(int(1000 * boot), outfile) + write_long(int(1000 * init), outfile) + write_long(int(1000 * finish), outfile) def add_path(path): @@ -72,6 +73,9 @@ def main(infile, outfile): for _ in range(num_python_includes): filename = utf8_deserializer.loads(infile) add_path(os.path.join(spark_files_dir, filename)) + if sys.version > '3': + import importlib + importlib.invalidate_caches() # fetch names and values of broadcast variables num_broadcast_variables = read_int(infile) @@ -106,14 +110,14 @@ def main(infile, outfile): except Exception: try: write_int(SpecialLengths.PYTHON_EXCEPTION_THROWN, outfile) - write_with_length(traceback.format_exc(), outfile) + write_with_length(traceback.format_exc().encode("utf-8"), outfile) except IOError: # JVM close the socket pass except Exception: # Write the error to stderr if it happened while serializing - print >> sys.stderr, "PySpark worker failed with exception:" - print >> sys.stderr, traceback.format_exc() + print("PySpark worker failed with exception:", file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) exit(-1) finish_time = time.time() report_times(outfile, boot_time, init_time, finish_time) -- cgit v1.2.3