This is done by a script [2] using RedBaron [1], a tool designed for doing
code refactoring. All "default" values are decided by the script and are
strongly consistent with the existing code.
There are 2 changes done manually to fix tests:
[warn] mercurial/exchange.py: experimental.bundle2-output-capture: default needs manual removal
[warn] mercurial/localrepo.py: experimental.hook-track-tags: default needs manual removal
Since RedBaron is not confident about how to indent things [2].
[1]: https://github.com/PyCQA/redbaron
[2]: https://github.com/PyCQA/redbaron/issues/100
[3]:
#!/usr/bin/env python
# codemod_configitems.py - codemod tool to fill configitems
#
# Copyright 2017 Facebook, Inc.
#
# 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, print_function
import os
import sys
import redbaron
def readpath(path):
with open(path) as f:
return f.read()
def writepath(path, content):
with open(path, 'w') as f:
f.write(content)
_configmethods = {'config', 'configbool', 'configint', 'configbytes',
'configlist', 'configdate'}
def extractstring(rnode):
"""get the string from a RedBaron string or call_argument node"""
while rnode.type != 'string':
rnode = rnode.value
return rnode.value[1:-1] # unquote, "'str'" -> "str"
def uiconfigitems(red):
"""match *.ui.config* pattern, yield (node, method, args, section, name)"""
for node in red.find_all('atomtrailers'):
entry = None
try:
obj = node[-3].value
method = node[-2].value
args = node[-1]
section = args[0].value
name = args[1].value
if (obj in ('ui', 'self') and method in _configmethods
and section.type == 'string' and name.type == 'string'):
entry = (node, method, args, extractstring(section),
extractstring(name))
except Exception:
pass
else:
if entry:
yield entry
def coreconfigitems(red):
"""match coreconfigitem(...) pattern, yield (node, args, section, name)"""
for node in red.find_all('atomtrailers'):
entry = None
try:
args = node[1]
section = args[0].value
name = args[1].value
if (node[0].value == 'coreconfigitem' and section.type == 'string'
and name.type == 'string'):
entry = (node, args, extractstring(section),
extractstring(name))
except Exception:
pass
else:
if entry:
yield entry
def registercoreconfig(cfgred, section, name, defaultrepr):
"""insert coreconfigitem to cfgred AST
section and name are plain string, defaultrepr is a string
"""
# find a place to insert the "coreconfigitem" item
entries = list(coreconfigitems(cfgred))
for node, args, nodesection, nodename in reversed(entries):
if (nodesection, nodename) < (section, name):
# insert after this entry
node.insert_after(
'coreconfigitem(%r, %r,\n'
' default=%s,\n'
')' % (section, name, defaultrepr))
return
def main(argv):
if not argv:
print('Usage: codemod_configitems.py FILES\n'
'For example, FILES could be "{hgext,mercurial}/*/**.py"')
dirname = os.path.dirname
reporoot = dirname(dirname(dirname(os.path.abspath(__file__))))
# register configitems to this destination
cfgpath = os.path.join(reporoot, 'mercurial', 'configitems.py')
cfgred = redbaron.RedBaron(readpath(cfgpath))
# state about what to do
registered = set((s, n) for n, a, s, n in coreconfigitems(cfgred))
toregister = {} # {(section, name): defaultrepr}
coreconfigs = set() # {(section, name)}, whether it's used in core
# first loop: scan all files before taking any action
for i, path in enumerate(argv):
print('(%d/%d) scanning %s' % (i + 1, len(argv), path))
iscore = ('mercurial' in path) and ('hgext' not in path)
red = redbaron.RedBaron(readpath(path))
# find all repo.ui.config* and ui.config* calls, and collect their
# section, name and default value information.
for node, method, args, section, name in uiconfigitems(red):
if section == 'web':
# [web] section has some weirdness, ignore them for now
continue
defaultrepr = None
key = (section, name)
if len(args) == 2:
if key in registered:
continue
if method == 'configlist':
defaultrepr = 'list'
elif method == 'configbool':
defaultrepr = 'False'
else:
defaultrepr = 'None'
elif len(args) >= 3 and (args[2].target is None or
args[2].target.value == 'default'):
# try to understand the "default" value
dnode = args[2].value
if dnode.type == 'name':
if dnode.value in {'None', 'True', 'False'}:
defaultrepr = dnode.value
elif dnode.type == 'string':
defaultrepr = repr(dnode.value[1:-1])
elif dnode.type in ('int', 'float'):
defaultrepr = dnode.value
# inconsistent default
if key in toregister and toregister[key] != defaultrepr:
defaultrepr = None
# interesting to rewrite
if key not in registered:
if defaultrepr is None:
print('[note] %s: %s.%s: unsupported default'
% (path, section, name))
registered.add(key) # skip checking it again
else:
toregister[key] = defaultrepr
if iscore:
coreconfigs.add(key)
# second loop: rewrite files given "toregister" result
for path in argv:
# reconstruct redbaron - trade CPU for memory
red = redbaron.RedBaron(readpath(path))
changed = False
for node, method, args, section, name in uiconfigitems(red):
key = (section, name)
defaultrepr = toregister.get(key)
if defaultrepr is None or key not in coreconfigs:
continue
if len(args) >= 3 and (args[2].target is None or
args[2].target.value == 'default'):
try:
del args[2]
changed = True
except Exception:
# redbaron fails to do the rewrite due to indentation
# see https://github.com/PyCQA/redbaron/issues/100
print('[warn] %s: %s.%s: default needs manual removal'
% (path, section, name))
if key not in registered:
print('registering %s.%s' % (section, name))
registercoreconfig(cfgred, section, name, defaultrepr)
registered.add(key)
if changed:
print('updating %s' % path)
writepath(path, red.dumps())
if toregister:
print('updating configitems.py')
writepath(cfgpath, cfgred.dumps())
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
One hitch is that sometimes fcd is actually an absentfilectx which does not
expose any mutator functions. In order to still use the context functions,
we look up the underlying workingfilectx to perform the write there.
One alternate way would be to put the write functions on the absentfilectx and
have them pass-through. While this makes the callsites cleaner, we would need
to decide what its getter functions would return after this point, since
returning None for `data` (and True for `isabsent()`) might no longer be
correct after a write. I discussed with Sidd about just having the getters
raise RuntimeErrors after a mutator has been called, but we actually call
isabsent() in merge.py after running the internal merge tools.
This provides a simpler API for callers which don't need full templating
stack. Instead of storing the given template as the name specified by topic,
use '' as the default template to be rendered.
Copytracing may be disabled because it's too slow (see
experimental.disablecopytrace config option). In that case user may get errors
like 'local changed FILE which other deleted'. It would be nice to give user a
hint to rerun command with `--config experimental.disablecopytrace=False`. To
make it possible let's extract error message to variables so that extension may
overwrite them.
Internal merge tool :dump implies premerge. Therefore, files aren't
dumped, if premerge runs successfully.
This undocumented behavior might confuse users, if they want to always
dump files. But just making :dump omit premerge might cause backward
compatibility issue for existing automation.
This patch adds new internal merge tool :forcedump, which works as
same as :dump, but omits premerge always.
Internal tools annotated with "nomerge" should merge "change and
delete" correctly, but _forcedump() can't. Therefore, it is annotated
with "mergeonly" to always omit premerge, even though it doesn't merge
files actually.
This patch also adds explanation about premerge to :dump, to clarify
how :dump actually works.
BTW, this patch specifies internal tools with "internal:" prefix in
newly added test scenario in test-merge-tools.t, even though this
prefix is already deprecated. This is only for similarity to other
tests in test-merge-tools.t.
Before this patch, internal merge tool :prompt shows "no tool found to
merge FILE" line, even if :prompt is explicitly specified as a tool to
be used.
This patch shows warning message about choice of :prompt only at an
actual fallback, in which case any tool is rejected by capability for
binary or symlink.
It is for backward compatibility to omit warning message in
"changedelete" case.
For consistency with the other template options. Quotes are necessary if
you want to preserve leading/trailing whitespace, which would be stripped
by config parser.
Changeset 3495cae22a41 removed the mutable default value, but did not explicitly
tested for None. Such implicit testing can introduce semantic and performance
issue. We move to an explicit testing for None as recommended by PEP8:
https://www.python.org/dev/peps/pep-0008/#programming-recommendations
os.fdopen() does not accepts bytes as its second argument which represent the
mode in which the file is to be opened. This patch makes sure unicodes are
passed in py3 by using pycompat.sysstr().
It seems somewhat common that people run into a merge conflict and
don't notice the launched merge tool, and instead they think hg just
hung. Let's print a message for each file that we launch a GUI merge
tool for.
Some merge tools (like Araxis?) can pick merge mode based on the file
extension. That didn't work well when temporary files were given random
suffixes. It seems to work better when the random part is before the extension.
As usual, when using $output, $local will have the .orig extension. That could
perhaps be the subject of another change another day.
The way default marker template was defined before this patch,
the spacing before dash in conflict markes was dependent on
whether changeset is a tip one or not. This is a relevant part
of template:
'{ifeq(tags, "tip", "", "{tags} "}'
If revision is a tip revision with no other tags, this would
resolve to an empty string, but for revisions which are not tip
and don't have any other tags, this would resolve to a single
space string. In the end this causes weirdnesses like the ones
you can see in the affected tests.
This is a not a big deal, but double spacing may be visually
less pleasant.
Please note that test changes where commit hashes change are
the result of marking files as resolved without removing markers.
Now that we store and display merge labels in user prompts (not just
conflict markets), we should rely on labels to clarify the two sides of a
merge operation (hg merge, hg update, hg rebase etc).
"remote" is not a great name here, as it conflates "remote" as in "remote
server" with "remote" as in "the side of the merge that's further away". In
cases where you're merging the "wrong way" around, remote can even be the
"local" commit that you're merging with something pulled from the remote
server.
Now that we persist the labels, we can consistently use the labels in
prompts for the user without risk of confusion. This changes a huge amount
of command output:
This means that merge prompts like:
no tool found to merge a
keep (l)ocal, take (o)ther, or leave (u)nresolved? u
and
remote changed a which local deleted
use (c)hanged version, leave (d)eleted, or leave (u)nresolved? c
become:
no tool found to merge a
keep (l)ocal [working copy], take (o)ther [destination], or leave (u)nresolved? u
and
remote [source] changed a which local [dest] deleted
use (c)hanged version, leave (d)eleted, or leave (u)nresolved? c
where "working copy" and "destination" were supplied by the command that
requested the merge as labels for conflict markers, and thus should be
human-friendly.
This function will host loading of template aliases. It is not defined at
templater, but at formatter, since formatter is the module handling ui stuff
in front of templater.
New frommapfile() function will make it clear when template aliases will be
loaded. They should be applied to command arguments and templates in hgrc,
but not to map files. Otherwise, our stock styles and web templates
(i.e map-file templates) could be modified unintentionally.
Future patches will add "aliases" argument to __init__(), but not to
frommapfile().
It makes far more sense to leave these conflicts unresolved and kick back to
the user than to just assume that the local version be chosen. There are almost
certainly buggy scripts and applications using Mercurial in the wild that do
merges or rebases non-interactively, and then assume that if the operation
succeeded there's nothing the user needs to pay attention to.
(This wasn't possible earlier because there was no way to re-resolve
change/delete conflicts -- but now it is.)
It makes far more sense to leave these conflicts unresolved and kick back to
the user than to just assume that the local version be chosen. There are almost
certainly buggy scripts and applications using Mercurial in the wild that do
merges or rebases non-interactively, and then assume that if the operation
succeeded there's nothing the user needs to pay attention to.
The ':fail' tool now knows to write out the changed side for change/delete
conflicts.
This has no impact right now but will make things better when we move
change/delete conflicts in here.
We do this because we don't want to modify the dirstate for failures, and don't
just want to leave the file missing from disk. Plus it's more useful for the
user if the changed side is written out -- it is easier to delete a file than
to get it back via hg revert.
For --tool or HGMERGE, we could have either:
(a) proceeded with the particular tool, then failed the merge.
(b) chosen to prompt regardless.
We're explicitly choosing (b) here, because it's effectively what we've been
doing so far and helps maintain an easier-to-use interface.
However, in future patches we're going to change the default selection from
'pick changed version' to 'leave unresolved'. That fixes most of the brokenness
involved with choice (b).
We're going to support the filemerge code resolving change/delete conflicts in
upcoming patches. Some of these resolutions require that the dirstate be
modified. Modifying the dirstate directly from in here would be (a) a pretty
bad layering violation and (b) wrong because all dirstate removals should
happen before adds. So in this and upcoming patches we're instead going to pass
whether the file is deleted up to merge.mergestate, then in there figure out
what dirstate action needs to be taken.
Most code is going to barf at the return values here (particularly from data
and size), so we restrict it to the filemerge code.
This is already somewhat supported via:
ctx.filectx(f, fileid=nullid)
Indeed, for add/add conflicts (ancestor doesn't have the file) we use precisely
that. However, that is broken in subtle ways:
- The cmp() function in filectx returns False (identical) for such a filectx
when compared to a zero-length file.
- size() returns 0 rather than some sort of value indicating that the file isn't
present.
- data() returns '' rather than some sort of value indicating that the file isn't
present.
Given the relatively niche use of such filectxes, this seems to be the simplest
way to fix all these issues.
Having .orig files litter your working copy is a common complaint. This patch
uses cmdutil.orig to let the user determine where those files should reside.
