s3 module: fix urlparse invocation and netloc mixup on Python 3 (#20836)

lib/ansible/modules/cloud/amazon/s3.py

@@ -415,7 +415,7 @@ def get_download_url(module, s3, bucket, obj, expiry, changed=True):
 def is_fakes3(s3_url):
     """ Return True if s3_url has scheme fakes3:// """
     if s3_url is not None:
-        return urlparse.urlparse(s3_url).scheme in ('fakes3', 'fakes3s')
+        return urlparse(s3_url).scheme in ('fakes3', 'fakes3s')
     else:
         return False
 
@@ -424,8 +424,8 @@ def is_walrus(s3_url):
 
     We assume anything other than *.amazonaws.com is Walrus"""
     if s3_url is not None:
-        o = urlparse.urlparse(s3_url)
-        return not o.hostname.endswith('amazonaws.com')
+        o = urlparse(s3_url)
+        return not o.netloc.endswith('amazonaws.com')
     else:
         return False
 
@@ -517,34 +517,7 @@ def main():
     # Look at s3_url and tweak connection settings
     # if connecting to RGW, Walrus or fakes3
     try:
-        if s3_url and rgw:
-            rgw = urlparse.urlparse(s3_url)
-            s3 = boto.connect_s3(
-                is_secure=rgw.scheme == 'https',
-                host=rgw.hostname,
-                port=rgw.port,
-                calling_format=OrdinaryCallingFormat(),
-                **aws_connect_kwargs
-            )
-        elif is_fakes3(s3_url):
-            fakes3 = urlparse.urlparse(s3_url)
-            s3 = S3Connection(
-                is_secure=fakes3.scheme == 'fakes3s',
-                host=fakes3.hostname,
-                port=fakes3.port,
-                calling_format=OrdinaryCallingFormat(),
-                **aws_connect_kwargs
-            )
-        elif is_walrus(s3_url):
-            walrus = urlparse.urlparse(s3_url).hostname
-            s3 = boto.connect_walrus(walrus, **aws_connect_kwargs)
-        else:
-            aws_connect_kwargs['is_secure'] = True
-            try:
-                s3 = connect_to_aws(boto.s3, location, **aws_connect_kwargs)
-            except AnsibleAWSError:
-                # use this as fallback because connect_to_region seems to fail in boto + non 'classic' aws accounts in some cases
-                s3 = boto.connect_s3(**aws_connect_kwargs)
+        s3 = get_s3_connection(aws_connect_kwargs, location, rgw, s3_url)
 
     except boto.exception.NoAuthHandlerFound as e:
         module.fail_json(msg='No Authentication Handler found: %s ' % str(e))
@@ -736,6 +709,39 @@ def main():
 
     module.exit_json(failed=False)
 
+
+def get_s3_connection(aws_connect_kwargs, location, rgw, s3_url):
+    if s3_url and rgw:
+        rgw = urlparse(s3_url)
+        s3 = boto.connect_s3(
+            is_secure=rgw.scheme == 'https',
+            host=rgw.hostname,
+            port=rgw.port,
+            calling_format=OrdinaryCallingFormat(),
+            **aws_connect_kwargs
+        )
+    elif is_fakes3(s3_url):
+        fakes3 = urlparse(s3_url)
+        s3 = S3Connection(
+            is_secure=fakes3.scheme == 'fakes3s',
+            host=fakes3.hostname,
+            port=fakes3.port,
+            calling_format=OrdinaryCallingFormat(),
+            **aws_connect_kwargs
+        )
+    elif is_walrus(s3_url):
+        walrus = urlparse(s3_url).hostname
+        s3 = boto.connect_walrus(walrus, **aws_connect_kwargs)
+    else:
+        aws_connect_kwargs['is_secure'] = True
+        try:
+            s3 = connect_to_aws(boto.s3, location, **aws_connect_kwargs)
+        except AnsibleAWSError:
+            # use this as fallback because connect_to_region seems to fail in boto + non 'classic' aws accounts in some cases
+            s3 = boto.connect_s3(**aws_connect_kwargs)
+    return s3
+
+
 # import module snippets
 from ansible.module_utils.basic import *
 from ansible.module_utils.ec2 import *

test/units/modules/cloud/amazon/test_s3.py

@@ -0,0 +1,46 @@
+from nose.plugins.skip import SkipTest
+
+try:
+    import boto
+    HAS_BOTO = True
+except ImportError:
+    HAS_BOTO = False
+
+if not HAS_BOTO:
+    raise SkipTest("test_s3.py requires the python module 'boto3' and 'botocore'")
+
+import unittest
+import ansible.modules.cloud.amazon.s3 as s3
+from ansible.module_utils.six.moves.urllib.parse import urlparse
+
+class TestUrlparse(unittest.TestCase):
+
+    def test_urlparse(self):
+        actual = urlparse("http://test.com/here")
+        self.assertEqual("http", actual.scheme)
+        self.assertEqual("test.com", actual.netloc)
+        self.assertEqual("/here", actual.path)
+
+    def test_is_fakes3(self):
+        actual = s3.is_fakes3("fakes3://bla.blubb")
+        self.assertEqual(True, actual)
+
+    def test_is_walrus(self):
+        actual = s3.is_walrus("trulywalrus_but_invalid_url")
+        #I don't know if this makes sense, but this is the current behaviour...
+        self.assertEqual(True, actual)
+        actual = s3.is_walrus("http://notwalrus.amazonaws.com")
+        self.assertEqual(False, actual)
+
+    def test_get_s3_connection(self):
+        aws_connect_kwargs = dict(aws_access_key_id="access_key",
+                                    aws_secret_access_key="secret_key")
+        location=None
+        rgw=True
+        s3_url="http://bla.blubb"
+        actual = s3.get_s3_connection(aws_connect_kwargs, location, rgw, s3_url)
+        self.assertEqual("bla.blubb", actual.host)
+
+
+if __name__ == '__main__':
+    unittest.main()