wcfs: Move zuri filter to lib/zodb

The WCFS mountpoint of any ZODB storage must be a unique, persistent,
repeatable hash. This means any client which uses the same storage must
always calculate the same WCFS mountpoint (independent from
client-only parameters etc.). Therefore the WCFS mountpoint calculation
must be robust for all supported ZODB storage types (at least NEO, ZEO,
filestorage).

It was recently decided [1] that in order to provide this robustness, WCFS
mountpoint calculation should filter the parsed URI in order to drop
parts, which prevents the repeatability/persistence across different
clients (e.g. parts which can differ between clients although the same
storage is accessed). In order to make this filtering implementation a
bit easier to read and the wcfs/__init__.py less dense, the first step
is to move the zurl filtering ("normalization") into lib/zodb.py
This also makes sense since this normalization can be regarded as a
general zodb tool which may be useful for other solutions which use
zodburi.

[1] nexedi/neoppod!18 (comment 184671)

/reviewed-by @kirr
/reviewed-on nexedi/wendelin.core!17

lib/zodb.py

@@ -32,6 +32,7 @@ from weakref import WeakSet
 import gc
 from six.moves.urllib import parse as urlparse
 import socket
+from six.moves.urllib.parse import urlsplit, urlunsplit
 
 import pkg_resources
 
@@ -432,3 +433,34 @@ def _is_ipv6(host):
     except socket.error:
         return False
     return True
+
+
+# zurl_normalize_main returns main part of zurl in its canonical form.
+#
+# The main part of a zurl identifies particular ZODB database without
+# client-side options how to open and access it. The main part also does not
+# include secrets.
+#
+# The following invariant is true:
+#
+#   zurl_normalize_main(zurl₁) = zurl_normalize_main(zurl₂)
+#
+#                       ⇕
+#
+#                zurl₁ and zurl₂
+#           point to the same storage
+#
+#
+# Example:
+#
+#   neos://ca=zzz@def:2,abc:1/cluster   ->  neos://abc:1,def:2/cluster
+def zurl_normalize_main(zurl):
+    # remove credentials from zurl.
+    # The same database can be accessed from different clients with different
+    # credentials, but we want to map them all to the same single WCFS
+    # instance.
+    scheme, netloc, path, query, frag = urlsplit(zurl)
+    if '@' in netloc:
+        netloc = netloc[netloc.index('@')+1:]
+    zurl = urlunsplit((scheme, netloc, path, query, frag))
+    return zurl

wcfs/__init__.py

@@ -79,8 +79,8 @@ from golang.gcompat import qq
 
 from persistent import Persistent
 from zodbtools.util import ashex as h
-from six.moves.urllib.parse import urlsplit, urlunsplit
 
+from wendelin.lib.zodb import zurl_normalize_main
 from .client._wcfs import \
     PyWCFS          as _WCFS,       \
     PyWatchLink     as WatchLink    \
@@ -499,14 +499,10 @@ def _wcfs_exe():
 #
 # it also makes sure the mountpoint exists.
 def _mntpt_4zurl(zurl):
-    # remove credentials from zurl.
-    # The same database can be accessed from different clients with different
-    # credentials, but we want to map them all to the same single WCFS
-    # instance.
-    scheme, netloc, path, query, frag = urlsplit(zurl)
-    if '@' in netloc:
-        netloc = netloc[netloc.index('@')+1:]
-    zurl = urlunsplit((scheme, netloc, path, query, frag))
+    # normalize zurl so that even if we have e.g. two neos:// urls coming
+    # with different paths to ssl keys, or with different order in the list of
+    # masters, we still have them associated with the same wcfs mountpoint.
+    zurl = zurl_normalize_main(zurl)
 
     m = hashlib.sha1()
     m.update(zurl)