revlog: split the content verification of a node into a separate method
authorMatt Harbison <matt_harbison@yahoo.com>
Sun, 22 Dec 2019 16:36:09 -0500
changeset 43957 7c3118b9a9db
parent 43956 a447efd991b9
child 43958 26cf356ae772
revlog: split the content verification of a node into a separate method This will be used by LFS to tune what is skipped. In the future, this could also be used by LFS to indicate which nodes tagged with `skipread` are simply in need of a blob fetch, so that they can be done in a batch later. (Currently, `skipread` also indicates censored data and errors.) Additionally, it could be used to cache the sha1 hash value for each blob so that large blobs don't need to be re-read and re-hashed if they are used by multiple nodes. Differential Revision: https://phab.mercurial-scm.org/D7710
mercurial/revlog.py
--- a/mercurial/revlog.py	Sun Dec 22 00:47:33 2019 -0500
+++ b/mercurial/revlog.py	Sun Dec 22 16:36:09 2019 -0500
@@ -148,6 +148,16 @@
     return int(int(offset) << 16 | type)
 
 
+def _verify_revision(rl, skipflags, state, node):
+    """Verify the integrity of the given revlog ``node`` while providing a hook
+    point for extensions to influence the operation."""
+    if skipflags:
+        state[b'skipread'].add(node)
+    else:
+        # Side-effect: read content and verify hash.
+        rl.revision(node)
+
+
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
@@ -2914,11 +2924,7 @@
                 if skipflags:
                     skipflags &= self.flags(rev)
 
-                if skipflags:
-                    state[b'skipread'].add(node)
-                else:
-                    # Side-effect: read content and verify hash.
-                    self.revision(node)
+                _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))