From 67ebe16f7249a4f84bb8a53ab406d21e4bf4963a Mon Sep 17 00:00:00 2001
From: mprahl <mprahl@redhat.com>
Date: Jan 11 2019 21:24:18 +0000
Subject: Read the files to be hashed as binary to ensure end of lines are not converted


When encoutering a Windows end of line (^M), io.open and open in Python 3
will convert those to UNIX end of lines by default. When reading logs
to compute the checksum, it's important those new lines aren't converted,
to ensure the checksum is correct. This caused issues in Fedora staging
because when cloning down a repo, the repoSpanner output had Windows end
of lines, and this would end up in build.log. The solution is to just read
it as binary so that Python doesn't perform these conversions.

---

diff --git a/module_build_service/builder/KojiContentGenerator.py b/module_build_service/builder/KojiContentGenerator.py
index 138e11c..fe63863 100644
--- a/module_build_service/builder/KojiContentGenerator.py
+++ b/module_build_service/builder/KojiContentGenerator.py
@@ -404,8 +404,8 @@ class KojiContentGenerator(object):
         # parse it to get the Modulemd instance.
         mmd_path = os.path.join(output_path, mmd_filename)
         try:
-            with open(mmd_path) as mmd_f:
-                data = mmd_f.read()
+            with open(mmd_path, 'rb') as mmd_f:
+                data = mmd_f.read().decode('utf-8')
                 mmd = Modulemd.Module().new_from_string(data)
                 ret['filename'] = mmd_filename
                 ret['filesize'] = len(data)
@@ -452,8 +452,8 @@ class KojiContentGenerator(object):
 
         try:
             log_path = os.path.join(output_path, "build.log")
-            with open(log_path) as build_log:
-                checksum = hashlib.md5(build_log.read().encode('utf-8')).hexdigest()
+            with open(log_path, 'rb') as build_log:
+                checksum = hashlib.md5(build_log.read()).hexdigest()
             stat = os.stat(log_path)
             ret.append(
                 {