# HG changeset patch
# User Matt Harbison <matt_harbison@yahoo.com>
# Date 2018-02-04 21:17:43
# Node ID 9b413478f2613c1b50de9de74237be7e37f22b24
# Parent  264b90a060b785533d22dd5a282f8587d42cb633

lfs: deduplicate oids in the transfer

Apparently, we can't rely on the server to deduplicate for us.

Sadly, the pointer object isn't hashable, so it can't be reduced by converting
it to a set.  In order to be hashable, it needs to be immutable.  I had a bunch
of code to change it to composition and forward the readonly dict methods to a
member dict.  But the pointer is updated via __setitem__() when creating the
pointer file.  So it didn't see worth adding all of that code to the class.

diff --git a/hgext/lfs/blobstore.py b/hgext/lfs/blobstore.py
--- a/hgext/lfs/blobstore.py
+++ b/hgext/lfs/blobstore.py
@@ -194,11 +194,11 @@ class _gitlfsremote(object):
 
     def writebatch(self, pointers, fromstore):
         """Batch upload from local to remote blobstore."""
-        self._batch(pointers, fromstore, 'upload')
+        self._batch(_deduplicate(pointers), fromstore, 'upload')
 
     def readbatch(self, pointers, tostore):
         """Batch download from remote to local blostore."""
-        self._batch(pointers, tostore, 'download')
+        self._batch(_deduplicate(pointers), tostore, 'download')
 
     def _batchrequest(self, pointers, action):
         """Get metadata about objects pointed by pointers for given action
@@ -399,13 +399,13 @@ class _dummyremote(object):
         self.vfs = lfsvfs(fullpath)
 
     def writebatch(self, pointers, fromstore):
-        for p in pointers:
+        for p in _deduplicate(pointers):
             content = fromstore.read(p.oid(), verify=True)
             with self.vfs(p.oid(), 'wb', atomictemp=True) as fp:
                 fp.write(content)
 
     def readbatch(self, pointers, tostore):
-        for p in pointers:
+        for p in _deduplicate(pointers):
             with self.vfs(p.oid(), 'rb') as fp:
                 tostore.download(p.oid(), fp)
 
@@ -444,6 +444,13 @@ class _promptremote(object):
     None: _promptremote,
 }
 
+def _deduplicate(pointers):
+    """Remove any duplicate oids that exist in the list"""
+    reduced = util.sortdict()
+    for p in pointers:
+        reduced[p.oid()] = p
+    return reduced.values()
+
 def _verify(oid, content):
     realoid = hashlib.sha256(content).hexdigest()
     if realoid != oid:
diff --git a/tests/test-lfs-test-server.t b/tests/test-lfs-test-server.t
--- a/tests/test-lfs-test-server.t
+++ b/tests/test-lfs-test-server.t
@@ -153,12 +153,10 @@ Archive will prefetch blobs in a group
 
   $ rm -rf .hg/store/lfs `hg config lfs.usercache`
   $ hg archive -vr 1 ../archive
-  lfs: need to transfer 4 objects (63 bytes)
+  lfs: need to transfer 3 objects (51 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: adding 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 to the usercache
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19
@@ -181,12 +179,10 @@ Cat will prefetch blobs in a group
 
   $ rm -rf .hg/store/lfs `hg config lfs.usercache`
   $ hg cat -vr 1 a b c
-  lfs: need to transfer 3 objects (43 bytes)
+  lfs: need to transfer 2 objects (31 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: adding d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 to the usercache
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
@@ -207,12 +203,10 @@ Revert will prefetch blobs in a group
   reverting b
   reverting c
   reverting d
-  lfs: need to transfer 4 objects (63 bytes)
+  lfs: need to transfer 3 objects (51 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: adding 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 to the usercache
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19