annotate: increase refcount of each revisions correctly (issue3841)
Before this patch, refcount (managed in "needed") of parents of each
revisions in "visit" is increased, only when parent is not annotated
yet (examined by "p not in hist").
But this causes less refcount of the revision like "A" in the tree
below ("A" is assumed as the second parent of "C"):
A --- B --- C
\ /
\-----/
Steps of annotation for "C" in this case are shown below:
1. for "C"
1.1 increase refcount of "B"
1.2 increase refcount of "A" (=> 1)
1.3 defer annotation for "C"
2. for "A"
2.1 annotate for "A" (=> put result into "hist[A]")
2.2 clear "pcache[A]" ("pcache[A] = []")
3. for "B"
3.1 not increase refcount of "A", because "A not in hist" is False
3.2 annotate for "B"
3.3 decrease refcount of "A" (=> 0)
3.4 delete "hist[A]", even though "A" is still needed by "C"
3.5 clear "pcache[B]"
4. for "C", again
4.1 not increase refcount of "B", because "B not in hist" is False
4.2 increase refcount of "A" (=> 1)
4.3 defer annotation for "C"
5. for "A", again
5.1 annotate for "A" (=> put result into "hist[A]", again)
5.2 clear "pcache[A]"
6. for "C", once again
6.1 not increase refcount of "B", because "B not in hist" is False
6.2 not increase refcount of "A", because "A not in hist" is False
6.3 annotate for "C"
6.4 decrease refcount of "A", and delete "hist[A]"
6.5 decrease refcount of "B", and delete "hist[B]"
6.6 clear "pcache[C]"
At step (5.1), annotation for "A" mis-recognizes that all lines are
created at "A", because "pcache[A]" already cleared at step (2.2)
prevents from scanning ancestors of "A".
So, annotation for "C" or its descendants loses information about "A"
or its ancestors.
The root cause of this problem is that refcount of "A" is decreased at
step (3.3), even though it isn't increased at step (3.1).
To increase refcount correctly, this patch increases refcount of each
parents of each revisions:
- regardless of "p not in hist" or not, and
- only once for each revisions in "visit" (by "not pcached")
In fact, this problem should occur only on legacy repositories in
which a filelog includes the merging between the revision and its
ancestor (as the second parent), because:
- tree is scanned in depth-first
without such merging, revisions in "visit" refer different
revisions as parent each other
- recent Mercurial doesn't allow such merging
changelog and manifest can include such merging someway, but
filelogs can't, because "localrepository._filecommit()" converts
such merging request to linear history.
This patch tests merging cases below: these cases are from filelog of
"mercurial/commands.py" in the repository of Mercurial itself.
- both parents are same
10 --- 11 --- 12
\_/
filelogrev: changesetid:
10 00ea3613f82c
11 fc4a6e5b5812
12 4f802588cdfb
- the second parent is also ancestor of the first one
37 --- 38 --- 39 --- 40
\________/
filelogrev: changesetid:
37 f8d56da6ac8f
38 38919e1c254d
39 d3400605d246
40 f06a4a3b86a7
# test-batching.py - tests for transparent command batching
#
# Copyright 2011 Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from mercurial.wireproto import localbatch, remotebatch, batchable, future
# equivalent of repo.repository
class thing(object):
def hello(self):
return "Ready."
# equivalent of localrepo.localrepository
class localthing(thing):
def foo(self, one, two=None):
if one:
return "%s and %s" % (one, two,)
return "Nope"
def bar(self, b, a):
return "%s und %s" % (b, a,)
def greet(self, name=None):
return "Hello, %s" % name
def batch(self):
'''Support for local batching.'''
return localbatch(self)
# usage of "thing" interface
def use(it):
# Direct call to base method shared between client and server.
print it.hello()
# Direct calls to proxied methods. They cause individual roundtrips.
print it.foo("Un", two="Deux")
print it.bar("Eins", "Zwei")
# Batched call to a couple of (possibly proxied) methods.
batch = it.batch()
# The calls return futures to eventually hold results.
foo = batch.foo(one="One", two="Two")
foo2 = batch.foo(None)
bar = batch.bar("Eins", "Zwei")
# We can call non-batchable proxy methods, but the break the current batch
# request and cause additional roundtrips.
greet = batch.greet(name="John Smith")
# We can also add local methods into the mix, but they break the batch too.
hello = batch.hello()
bar2 = batch.bar(b="Uno", a="Due")
# Only now are all the calls executed in sequence, with as few roundtrips
# as possible.
batch.submit()
# After the call to submit, the futures actually contain values.
print foo.value
print foo2.value
print bar.value
print greet.value
print hello.value
print bar2.value
# local usage
mylocal = localthing()
print
print "== Local"
use(mylocal)
# demo remoting; mimicks what wireproto and HTTP/SSH do
# shared
def escapearg(plain):
return (plain
.replace(':', '::')
.replace(',', ':,')
.replace(';', ':;')
.replace('=', ':='))
def unescapearg(escaped):
return (escaped
.replace(':=', '=')
.replace(':;', ';')
.replace(':,', ',')
.replace('::', ':'))
# server side
# equivalent of wireproto's global functions
class server(object):
def __init__(self, local):
self.local = local
def _call(self, name, args):
args = dict(arg.split('=', 1) for arg in args)
return getattr(self, name)(**args)
def perform(self, req):
print "REQ:", req
name, args = req.split('?', 1)
args = args.split('&')
vals = dict(arg.split('=', 1) for arg in args)
res = getattr(self, name)(**vals)
print " ->", res
return res
def batch(self, cmds):
res = []
for pair in cmds.split(';'):
name, args = pair.split(':', 1)
vals = {}
for a in args.split(','):
if a:
n, v = a.split('=')
vals[n] = unescapearg(v)
res.append(escapearg(getattr(self, name)(**vals)))
return ';'.join(res)
def foo(self, one, two):
return mangle(self.local.foo(unmangle(one), unmangle(two)))
def bar(self, b, a):
return mangle(self.local.bar(unmangle(b), unmangle(a)))
def greet(self, name):
return mangle(self.local.greet(unmangle(name)))
myserver = server(mylocal)
# local side
# equivalent of wireproto.encode/decodelist, that is, type-specific marshalling
# here we just transform the strings a bit to check we're properly en-/decoding
def mangle(s):
return ''.join(chr(ord(c) + 1) for c in s)
def unmangle(s):
return ''.join(chr(ord(c) - 1) for c in s)
# equivalent of wireproto.wirerepository and something like http's wire format
class remotething(thing):
def __init__(self, server):
self.server = server
def _submitone(self, name, args):
req = name + '?' + '&'.join(['%s=%s' % (n, v) for n, v in args])
return self.server.perform(req)
def _submitbatch(self, cmds):
req = []
for name, args in cmds:
args = ','.join(n + '=' + escapearg(v) for n, v in args)
req.append(name + ':' + args)
req = ';'.join(req)
res = self._submitone('batch', [('cmds', req,)])
return res.split(';')
def batch(self):
return remotebatch(self)
@batchable
def foo(self, one, two=None):
if not one:
yield "Nope", None
encargs = [('one', mangle(one),), ('two', mangle(two),)]
encresref = future()
yield encargs, encresref
yield unmangle(encresref.value)
@batchable
def bar(self, b, a):
encresref = future()
yield [('b', mangle(b),), ('a', mangle(a),)], encresref
yield unmangle(encresref.value)
# greet is coded directly. It therefore does not support batching. If it
# does appear in a batch, the batch is split around greet, and the call to
# greet is done in its own roundtrip.
def greet(self, name=None):
return unmangle(self._submitone('greet', [('name', mangle(name),)]))
# demo remote usage
myproxy = remotething(myserver)
print
print "== Remote"
use(myproxy)