##// END OF EJS Templates
mergetools: add new conflict marker format with diffs in...
mergetools: add new conflict marker format with diffs in I use 3-way conflict markers. Often when I resolve them, I manually compare one the base with one side and apply the differences to the other side. That can be hard when the conflict marker is large. This patch introduces a new type of conflict marker, which I'm hoping will make it easier to resolve conflicts. The new format uses `<<<<<<<` and `>>>>>>>` to open and close the markers, just like our existing 2-way and 3-way conflict markers. Instead of having 2 or 3 snapshots (left+right or left+base+right), it has a sequence of diffs. A diff looks like this: ``` ------- base +++++++ left a -b +c d ``` A diff that adds one side ("diff from nothing") has a `=======` header instead and does not have have `+` prefixed on its lines. A regular 3-way merge can be viewed as adding one side plus a diff between the base and the other side. It thus has two ways of being represented, depending on which side is being diffed: ``` <<<<<<< ======= left contents on left ------- base +++++++ right contents on -left +right >>>>>>> ``` or ``` <<<<<<< ------- base +++++++ left contents on -right +left ======= right contents on right >>>>>>> ``` I've made it so the new merge tool tries to pick a version that has the most common lines (no difference in the example above). I've called the new tool "mergediff" to stick to the convention of starting with "merge" if the tool tries a regular 3-way merge. The idea came from my pet VCS (placeholder name `jj`), which has support for octopus merges and other ways of ending up with merges of more than 3 versions. I wanted to be able to represent such conflicts in the working copy and therefore thought of this format (although I have not yet implemented it in my VCS). I then attended a meeting with Larry McVoy, who said BitKeeper has an option (`bk smerge -g`) for showing a similar format, which reminded me to actually attempt this in Mercurial. Differential Revision: https://phab.mercurial-scm.org/D9551

File last commit:

r46487:e641bb2a default
r46724:bdc2bf68 default
Show More
hbisect.py
329 lines | 10.9 KiB | text/x-python | PythonLexer
# changelog bisection for mercurial
#
# Copyright 2007 Matt Mackall
# Copyright 2005, 2006 Benoit Boissinot <benoit.boissinot@ens-lyon.org>
#
# Inspired by git bisect, extension skeleton taken from mq.py.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import collections
import contextlib
from .i18n import _
from .node import (
hex,
short,
)
from . import error
def bisect(repo, state):
"""find the next node (if any) for testing during a bisect search.
returns a (nodes, number, good) tuple.
'nodes' is the final result of the bisect if 'number' is 0.
Otherwise 'number' indicates the remaining possible candidates for
the search and 'nodes' contains the next bisect target.
'good' is True if bisect is searching for a first good changeset, False
if searching for a first bad one.
"""
repo = repo.unfiltered()
changelog = repo.changelog
clparents = changelog.parentrevs
skip = {changelog.rev(n) for n in state[b'skip']}
def buildancestors(bad, good):
badrev = min([changelog.rev(n) for n in bad])
ancestors = collections.defaultdict(lambda: None)
for rev in repo.revs(b"descendants(%ln) - ancestors(%ln)", good, good):
ancestors[rev] = []
if ancestors[badrev] is None:
return badrev, None
return badrev, ancestors
good = False
badrev, ancestors = buildancestors(state[b'bad'], state[b'good'])
if not ancestors: # looking for bad to good transition?
good = True
badrev, ancestors = buildancestors(state[b'good'], state[b'bad'])
bad = changelog.node(badrev)
if not ancestors: # now we're confused
if (
len(state[b'bad']) == 1
and len(state[b'good']) == 1
and state[b'bad'] != state[b'good']
):
raise error.Abort(_(b"starting revisions are not directly related"))
raise error.Abort(
_(b"inconsistent state, %d:%s is good and bad")
% (badrev, short(bad))
)
# build children dict
children = {}
visit = collections.deque([badrev])
candidates = []
while visit:
rev = visit.popleft()
if ancestors[rev] == []:
candidates.append(rev)
for prev in clparents(rev):
if prev != -1:
if prev in children:
children[prev].append(rev)
else:
children[prev] = [rev]
visit.append(prev)
candidates.sort()
# have we narrowed it down to one entry?
# or have all other possible candidates besides 'bad' have been skipped?
tot = len(candidates)
unskipped = [c for c in candidates if (c not in skip) and (c != badrev)]
if tot == 1 or not unskipped:
return ([changelog.node(c) for c in candidates], 0, good)
perfect = tot // 2
# find the best node to test
best_rev = None
best_len = -1
poison = set()
for rev in candidates:
if rev in poison:
# poison children
poison.update(children.get(rev, []))
continue
a = ancestors[rev] or [rev]
ancestors[rev] = None
x = len(a) # number of ancestors
y = tot - x # number of non-ancestors
value = min(x, y) # how good is this test?
if value > best_len and rev not in skip:
best_len = value
best_rev = rev
if value == perfect: # found a perfect candidate? quit early
break
if y < perfect and rev not in skip: # all downhill from here?
# poison children
poison.update(children.get(rev, []))
continue
for c in children.get(rev, []):
if ancestors[c]:
ancestors[c] = list(set(ancestors[c] + a))
else:
ancestors[c] = a + [c]
assert best_rev is not None
best_node = changelog.node(best_rev)
return ([best_node], tot, good)
def extendrange(repo, state, nodes, good):
# bisect is incomplete when it ends on a merge node and
# one of the parent was not checked.
parents = repo[nodes[0]].parents()
if len(parents) > 1:
if good:
side = state[b'bad']
else:
side = state[b'good']
num = len({i.node() for i in parents} & set(side))
if num == 1:
return parents[0].ancestor(parents[1])
return None
def load_state(repo):
state = {b'current': [], b'good': [], b'bad': [], b'skip': []}
for l in repo.vfs.tryreadlines(b"bisect.state"):
kind, node = l[:-1].split()
node = repo.unfiltered().lookup(node)
if kind not in state:
raise error.Abort(_(b"unknown bisect kind %s") % kind)
state[kind].append(node)
return state
def save_state(repo, state):
f = repo.vfs(b"bisect.state", b"w", atomictemp=True)
with repo.wlock():
for kind in sorted(state):
for node in state[kind]:
f.write(b"%s %s\n" % (kind, hex(node)))
f.close()
def resetstate(repo):
"""remove any bisect state from the repository"""
if repo.vfs.exists(b"bisect.state"):
repo.vfs.unlink(b"bisect.state")
def checkstate(state):
"""check we have both 'good' and 'bad' to define a range
Raise StateError exception otherwise."""
if state[b'good'] and state[b'bad']:
return True
if not state[b'good']:
raise error.StateError(_(b'cannot bisect (no known good revisions)'))
else:
raise error.StateError(_(b'cannot bisect (no known bad revisions)'))
@contextlib.contextmanager
def restore_state(repo, state, node):
try:
yield
finally:
state[b'current'] = [node]
save_state(repo, state)
def get(repo, status):
"""
Return a list of revision(s) that match the given status:
- ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
- ``goods``, ``bads`` : csets topologically good/bad
- ``range`` : csets taking part in the bisection
- ``pruned`` : csets that are goods, bads or skipped
- ``untested`` : csets whose fate is yet unknown
- ``ignored`` : csets ignored due to DAG topology
- ``current`` : the cset currently being bisected
"""
state = load_state(repo)
if status in (b'good', b'bad', b'skip', b'current'):
return map(repo.unfiltered().changelog.rev, state[status])
else:
# In the following sets, we do *not* call 'bisect()' with more
# than one level of recursion, because that can be very, very
# time consuming. Instead, we always develop the expression as
# much as possible.
# 'range' is all csets that make the bisection:
# - have a good ancestor and a bad descendant, or conversely
# that's because the bisection can go either way
range = b'( bisect(bad)::bisect(good) | bisect(good)::bisect(bad) )'
_t = repo.revs(b'bisect(good)::bisect(bad)')
# The sets of topologically good or bad csets
if len(_t) == 0:
# Goods are topologically after bads
goods = b'bisect(good)::' # Pruned good csets
bads = b'::bisect(bad)' # Pruned bad csets
else:
# Goods are topologically before bads
goods = b'::bisect(good)' # Pruned good csets
bads = b'bisect(bad)::' # Pruned bad csets
# 'pruned' is all csets whose fate is already known: good, bad, skip
skips = b'bisect(skip)' # Pruned skipped csets
pruned = b'( (%s) | (%s) | (%s) )' % (goods, bads, skips)
# 'untested' is all cset that are- in 'range', but not in 'pruned'
untested = b'( (%s) - (%s) )' % (range, pruned)
# 'ignored' is all csets that were not used during the bisection
# due to DAG topology, but may however have had an impact.
# E.g., a branch merged between bads and goods, but whose branch-
# point is out-side of the range.
iba = b'::bisect(bad) - ::bisect(good)' # Ignored bads' ancestors
iga = b'::bisect(good) - ::bisect(bad)' # Ignored goods' ancestors
ignored = b'( ( (%s) | (%s) ) - (%s) )' % (iba, iga, range)
if status == b'range':
return repo.revs(range)
elif status == b'pruned':
return repo.revs(pruned)
elif status == b'untested':
return repo.revs(untested)
elif status == b'ignored':
return repo.revs(ignored)
elif status == b"goods":
return repo.revs(goods)
elif status == b"bads":
return repo.revs(bads)
else:
raise error.ParseError(_(b'invalid bisect state'))
def label(repo, node):
rev = repo.changelog.rev(node)
# Try explicit sets
if rev in get(repo, b'good'):
# i18n: bisect changeset status
return _(b'good')
if rev in get(repo, b'bad'):
# i18n: bisect changeset status
return _(b'bad')
if rev in get(repo, b'skip'):
# i18n: bisect changeset status
return _(b'skipped')
if rev in get(repo, b'untested') or rev in get(repo, b'current'):
# i18n: bisect changeset status
return _(b'untested')
if rev in get(repo, b'ignored'):
# i18n: bisect changeset status
return _(b'ignored')
# Try implicit sets
if rev in get(repo, b'goods'):
# i18n: bisect changeset status
return _(b'good (implicit)')
if rev in get(repo, b'bads'):
# i18n: bisect changeset status
return _(b'bad (implicit)')
return None
def printresult(ui, repo, state, displayer, nodes, good):
repo = repo.unfiltered()
if len(nodes) == 1:
# narrowed it down to a single revision
if good:
ui.write(_(b"The first good revision is:\n"))
else:
ui.write(_(b"The first bad revision is:\n"))
displayer.show(repo[nodes[0]])
extendnode = extendrange(repo, state, nodes, good)
if extendnode is not None:
ui.write(
_(
b'Not all ancestors of this changeset have been'
b' checked.\nUse bisect --extend to continue the '
b'bisection from\nthe common ancestor, %s.\n'
)
% extendnode
)
else:
# multiple possible revisions
if good:
ui.write(
_(
b"Due to skipped revisions, the first "
b"good revision could be any of:\n"
)
)
else:
ui.write(
_(
b"Due to skipped revisions, the first "
b"bad revision could be any of:\n"
)
)
for n in nodes:
displayer.show(repo[n])
displayer.close()