From 70beb808e13f6371968ac87f7cf625ed110375e6 Mon Sep 17 00:00:00 2001 From: Simon Hafner Date: Tue, 7 Jul 2015 09:42:59 -0700 Subject: [SPARK-8821] [EC2] Switched to binary mode for file reading Otherwise the script will crash with - Downloading boto... Traceback (most recent call last): File "ec2/spark_ec2.py", line 148, in setup_external_libs(external_libs) File "ec2/spark_ec2.py", line 128, in setup_external_libs if hashlib.md5(tar.read()).hexdigest() != lib["md5"]: File "/usr/lib/python3.4/codecs.py", line 319, in decode (result, consumed) = self._buffer_decode(data, self.errors, final) UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte In case of an utf8 env setting. Author: Simon Hafner Closes #7215 from reactormonk/branch-1.4 and squashes the following commits: e86957a [Simon Hafner] [SPARK-8821] [EC2] Switched to binary mode (cherry picked from commit 83a621a5a8f8a2991c4cfa687279589e5c623d46) Signed-off-by: Shivaram Venkataraman --- ec2/spark_ec2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'ec2') diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index 18ccbc0a3e..8582d434a8 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -125,7 +125,7 @@ def setup_external_libs(libs): ) with open(tgz_file_path, "wb") as tgz_file: tgz_file.write(download_stream.read()) - with open(tgz_file_path) as tar: + with open(tgz_file_path, "rb") as tar: if hashlib.md5(tar.read()).hexdigest() != lib["md5"]: print("ERROR: Got wrong md5sum for {lib}.".format(lib=lib["name"]), file=stderr) sys.exit(1) -- cgit v1.2.3