##// END OF EJS Templates
rebase: skip resolved but emptied revisions...
rebase: skip resolved but emptied revisions When rebasing, if a conflict occurs and is resolved in a way the rebased revision becomes empty, it is not skipped, unlike revisions being emptied without conflicts. The reason is: - File 'x' is merged and resolved, merge.update() marks it as 'm' in the dirstate. - rebase.concludenode() calls localrepo.commit(), which calls localrepo.status() which calls dirstate.status(). 'x' shows up as 'm' and is unconditionnally added to the modified files list, instead of being checked again. - localrepo.commit() detects 'x' as changed an create a new revision where only the manifest parents and linkrev differ. Marking 'x' as modified without checking it makes sense for regular merges. But in rebase case, the merge looks normal but the second parent is usually discarded. When this happens, 'm' files in dirstate are a bit irrelevant and should be considered 'n' possibly dirty instead. That is what the current patch does. Another approach, maybe more efficient, would be to pass another flag to merge.update() saying the 'branchmerge' is a bit of a lie and recordupdate() should call dirstate.normallookup() instead of merge(). It is also tempting to add this logic to dirstate.setparents(), moving from two to one parent is what invalidates the 'm' markers. But this is a far bigger change to make. v2: succumb to the temptation and move the logic in dirstate.setparents(). mpm suggested trying _filecommit() first but it is called by commitctx() which knows nothing about the dirstate and comes too late into the game. A second approach was to rewrite the 'm' state into 'n' on the fly in dirstate.status() which failed for graft in the following case: $ hg init repo $ cd repo $ echo a > a $ hg ci -qAm0 $ echo a >> a $ hg ci -m1 $ hg up 0 1 files updated, 0 files merged, 0 files removed, 0 files unresolved $ hg mv a b $ echo c > b $ hg ci -m2 created new head $ hg graft 1 --tool internal:local grafting revision 1 $ hg --config extensions.graphlog= glog --template '{rev} {desc|firstline}\n' @ 3 1 | o 2 2 | | o 1 1 |/ o 0 0 $ hg log -r 3 --debug --patch --git --copies changeset: 3:19cd7d1417952af13161b94c32e901769104560c tag: tip phase: draft parent: 2:b5c505595c9e9a12d5dd457919c143e05fc16fb8 parent: -1:0000000000000000000000000000000000000000 manifest: 3:3d27ce8d02241aa59b60804805edf103c5c0cda4 user: test date: Thu Jan 01 00:00:00 1970 +0000 extra: branch=default extra: source=a03df74c41413a75c0a42997fc36c2de97b26658 description: 1 Here, revision 3 is created because there is a copy record for 'b' in the dirstate and thus 'b' is considered modified. But this information is discarded at commit time since 'b' content is unchanged. I do not know if discarding this information is correct or not, but at this time we cannot represent it anyway. This patch therefore implements the last solution of moving the logic into dirstate.setparents(). It does not sound crazy as 'm' files makes no sense with only one parent. It also makes dirstate.merge() calls .lookupnormal() if there is one parent, to preserve the invariant. I am a bit concerned about introducing this kind of stateful behaviour to existing code which historically treated setparents() as a basic setter without side-effects. And doing that during the code freeze.

File last commit:

r15052:06c3667c stable
r16509:eab9119c stable
Show More
dagutil.py
277 lines | 8.1 KiB | text/x-python | PythonLexer
# dagutil.py - dag utilities for mercurial
#
# Copyright 2010 Benoit Boissinot <bboissin@gmail.com>
# and 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 node import nullrev
from i18n import _
class basedag(object):
'''generic interface for DAGs
terms:
"ix" (short for index) identifies a nodes internally,
"id" identifies one externally.
All params are ixs unless explicitly suffixed otherwise.
Pluralized params are lists or sets.
'''
def __init__(self):
self._inverse = None
def nodeset(self):
'''set of all node idxs'''
raise NotImplementedError()
def heads(self):
'''list of head ixs'''
raise NotImplementedError()
def parents(self, ix):
'''list of parents ixs of ix'''
raise NotImplementedError()
def inverse(self):
'''inverse DAG, where parents becomes children, etc.'''
raise NotImplementedError()
def ancestorset(self, starts, stops=None):
'''
set of all ancestors of starts (incl), but stop walk at stops (excl)
'''
raise NotImplementedError()
def descendantset(self, starts, stops=None):
'''
set of all descendants of starts (incl), but stop walk at stops (excl)
'''
return self.inverse().ancestorset(starts, stops)
def headsetofconnecteds(self, ixs):
'''
subset of connected list of ixs so that no node has a descendant in it
By "connected list" we mean that if an ancestor and a descendant are in
the list, then so is at least one path connecting them.
'''
raise NotImplementedError()
def externalize(self, ix):
'''return a list of (or set if given a set) of node ids'''
return self._externalize(ix)
def externalizeall(self, ixs):
'''return a list of (or set if given a set) of node ids'''
ids = self._externalizeall(ixs)
if isinstance(ixs, set):
return set(ids)
return list(ids)
def internalize(self, id):
'''return a list of (or set if given a set) of node ixs'''
return self._internalize(id)
def internalizeall(self, ids, filterunknown=False):
'''return a list of (or set if given a set) of node ids'''
ixs = self._internalizeall(ids, filterunknown)
if isinstance(ids, set):
return set(ixs)
return list(ixs)
class genericdag(basedag):
'''generic implementations for DAGs'''
def ancestorset(self, starts, stops=None):
stops = stops and set(stops) or set()
seen = set()
pending = list(starts)
while pending:
n = pending.pop()
if n not in seen and n not in stops:
seen.add(n)
pending.extend(self.parents(n))
return seen
def headsetofconnecteds(self, ixs):
hds = set(ixs)
if not hds:
return hds
for n in ixs:
for p in self.parents(n):
hds.discard(p)
assert hds
return hds
class revlogbaseddag(basedag):
'''generic dag interface to a revlog'''
def __init__(self, revlog, nodeset):
basedag.__init__(self)
self._revlog = revlog
self._heads = None
self._nodeset = nodeset
def nodeset(self):
return self._nodeset
def heads(self):
if self._heads is None:
self._heads = self._getheads()
return self._heads
def _externalize(self, ix):
return self._revlog.index[ix][7]
def _externalizeall(self, ixs):
idx = self._revlog.index
return [idx[i][7] for i in ixs]
def _internalize(self, id):
ix = self._revlog.rev(id)
if ix == nullrev:
raise LookupError(id, self._revlog.indexfile, _('nullid'))
return ix
def _internalizeall(self, ids, filterunknown):
rl = self._revlog
if filterunknown:
return [r for r in map(rl.nodemap.get, ids)
if r is not None and r != nullrev]
return map(self._internalize, ids)
class revlogdag(revlogbaseddag):
'''dag interface to a revlog'''
def __init__(self, revlog):
revlogbaseddag.__init__(self, revlog, set(xrange(len(revlog))))
def _getheads(self):
return [r for r in self._revlog.headrevs() if r != nullrev]
def parents(self, ix):
rlog = self._revlog
idx = rlog.index
revdata = idx[ix]
prev = revdata[5]
if prev != nullrev:
prev2 = revdata[6]
if prev2 == nullrev:
return [prev]
return [prev, prev2]
prev2 = revdata[6]
if prev2 != nullrev:
return [prev2]
return []
def inverse(self):
if self._inverse is None:
self._inverse = inverserevlogdag(self)
return self._inverse
def ancestorset(self, starts, stops=None):
rlog = self._revlog
idx = rlog.index
stops = stops and set(stops) or set()
seen = set()
pending = list(starts)
while pending:
rev = pending.pop()
if rev not in seen and rev not in stops:
seen.add(rev)
revdata = idx[rev]
for i in [5, 6]:
prev = revdata[i]
if prev != nullrev:
pending.append(prev)
return seen
def headsetofconnecteds(self, ixs):
if not ixs:
return set()
rlog = self._revlog
idx = rlog.index
headrevs = set(ixs)
for rev in ixs:
revdata = idx[rev]
for i in [5, 6]:
prev = revdata[i]
if prev != nullrev:
headrevs.discard(prev)
assert headrevs
return headrevs
def linearize(self, ixs):
'''linearize and topologically sort a list of revisions
The linearization process tries to create long runs of revs where
a child rev comes immediately after its first parent. This is done by
visiting the heads of the given revs in inverse topological order,
and for each visited rev, visiting its second parent, then its first
parent, then adding the rev itself to the output list.
'''
sorted = []
visit = list(self.headsetofconnecteds(ixs))
visit.sort(reverse=True)
finished = set()
while visit:
cur = visit.pop()
if cur < 0:
cur = -cur - 1
if cur not in finished:
sorted.append(cur)
finished.add(cur)
else:
visit.append(-cur - 1)
visit += [p for p in self.parents(cur)
if p in ixs and p not in finished]
assert len(sorted) == len(ixs)
return sorted
class inverserevlogdag(revlogbaseddag, genericdag):
'''inverse of an existing revlog dag; see revlogdag.inverse()'''
def __init__(self, orig):
revlogbaseddag.__init__(self, orig._revlog, orig._nodeset)
self._orig = orig
self._children = {}
self._roots = []
self._walkfrom = len(self._revlog) - 1
def _walkto(self, walkto):
rev = self._walkfrom
cs = self._children
roots = self._roots
idx = self._revlog.index
while rev >= walkto:
data = idx[rev]
isroot = True
for prev in [data[5], data[6]]: # parent revs
if prev != nullrev:
cs.setdefault(prev, []).append(rev)
isroot = False
if isroot:
roots.append(rev)
rev -= 1
self._walkfrom = rev
def _getheads(self):
self._walkto(nullrev)
return self._roots
def parents(self, ix):
if ix is None:
return []
if ix <= self._walkfrom:
self._walkto(ix)
return self._children.get(ix, [])
def inverse(self):
return self._orig