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:]))
This is one step towards removing a bunch of "if isinstance(gen,
unbundle20)" by treating bundle1 and bundle2 more similarly.
The name may sounds ironic for a method in the bundle2 module, but I
didn't think it was worth it yet to create a new 'bundle' module that
depends on the 'bundle2' module. Besides, we'll inline the method
again later.
The results only need to be combined if they come from a bundle2. More
importantly, we'll change its argument to a bundleoperation soon, and
then it definitely will no longer belong in changegroup.py.
When adding support for bundling and unbundling phases, it will be
useful to have the list of added changesets. To do that, we return the
list from changegroup.apply().
By calling applybundle() with 'clonebundles' and the url instead of
calling processbundle(), the hooks will get different arguments:
HG_SOURCE will be 'clonebundles' instead of 'bundle2' and HG_URL will
be the url instead of 'bundle2'. This is consistent with the bundle1
behavior and seems like a bug fix, but I'm marking it BC anyway.
changegroup.apply() currently creates a transation if there isn't
already one. Having the callers of that method pass in an existing
transaction seems a little cleaner. To do that, we need to make sure
all callers have a transaction. Since the transaction name is used as
a hook argument (HG_TXNNAME), we need to match the name from
changegroup.apply().
Client has a mechanism for the server to check that nothing changed server side
since the client prepared a push. That check is wide and any head changed on
the server will lead to an aborted push. We introduce a way for the client to
send a less strict checking. That logic will check that no heads impacted by
the push have been affected. If other unrelated heads (including named branches
heads) have been affected, the push will proceed.
This is very helpful for repositories with high developers traffic on different
heads, a common setup.
That behavior is currently controlled by an experimental option. The config
should live in the "server" section but bike-shedding of the name will happen
in the next changesets. Servers advertise this capability through a new bundle2
capability 'checkeads', using the value 'related'.
The 'test-push-race.t' is updated to check that new capabilities on the
documented cases.
This commit essentially reverts 62ad9c1dbce9.
urllib2.URLError receives a "reason" argument. It isn't always a
tuple. Mozilla has experienced at least IndexError failures due
to the reason[1] access.
https://bugzilla.mozilla.org/show_bug.cgi?id=1364687
Previously, `hg bundle zstd` on a non-generaldelta repo would
attempt to use a v1 bundle. This would fail because zstd is not
supported on v1 bundles.
This patch changes the behavior to automatically use a v2 bundle
when the user explicitly requests a bundlespec that is a compression
engine not supported on v1. If the bundlespec is <engine>-v1, it is
still explicitly rejected because that request cannot be fulfilled.
Version 1 bundles only support a fixed set of compression engines.
Before this change, we would accept any compression engine for v1
bundles, even those that may not work on v1. This could lead to
an error.
We define a fixed set of compression engines known to work with v1
bundles and we add checking to ensure a newer engine (like zstd)
won't work with v1 bundles.
I also took the liberty of adding test coverage for unknown compression
names because I noticed we didn't have coverage of it before.
bundle2 allow the server to report error explicitly. This was initially
implemented for push but there is not reason to not use it for pull too. This
changeset add logic similar to the one in 'unbundle' to the
client side of 'getbundle'. That logic make sure the error is properly reported
as "remote". This will allow the server side of getbundle to send clean "Abort"
message in the next changeset.
The remote hint message was ignored when reporting the remote error and
passed to the local generic abort error. I think I might initially have
tried to avoid reimplementing logic controlling the hint display depending of
the verbosity level. However, first, there does not seems to have such verbosity
related logic and second the resulting was wrong as the primary error and the
hint were split apart. We now properly print the hint as remote output.
Python 3 removed the "cmp" argument from sorted(). Custom sorting in
Python 3 must be implemented with the dunder comparison methods on
types and/or with a "key" function.
This patch converts our custom "cmp" function to a custom type.
The implementation is very similar to functools.cmp_to_key(). However,
cmp_to_key() doesn't exist in Python 2, so we can't use it.
This was the only use of the "cmp" argument to sorted() in the code
base.
Binary bookmark format should be used internally. It doesn't make sense to have
optional parameters `srchex` and `dsthex`. This patch removes them. It will
also be useful for `bookmarks` bundle2 part because unnecessary conversions
between hex and bin nodes will be avoided.
Next commit will remove optional parameters from `compare()` function.
Let's rename `compare()` to `comparebookmarks()` to avoid ambiguity from
callers from external extensions.
This function will be used to generate bookmarks bundle2 part.
It is a separate function in order to make it easy to overwrite it
in extensions. Passing `kwargs` to the function makes it easy to
add new parameters in extensions.
We move it next to similar part building functions. We will need it for the
"writenewbundle" logic. This will allow us to easily include obsmarkers in
on-disk bundle, a necessary step before having `hg strip` also operate on
markers.
(Yes, the bundle2 module was already too large, but there any many
interdependencies between its components so it is non-trivial to split, this is
a quest for another adventure.)
Commit 9233182ea547d0aa removed the unused bundlecaps argument from the
changegroup code. While it is unused in core Mercurial, it was an important
feature for the remotefilelog extension because it allowed the exchange layer to
communicate to the changegroup packer that this was a shallow repo and that
filelogs should not be included. Without bundlecaps, there is currently no other
way to pass that information along without a more extensive refactor of
exchange, bundle, and changegroup code.
This patch backs out the original removal, and merges it with some recent
changes to changegroup apis.
At the moment this isn't used and all stream clones use the legacy protocol.
In an upcoming diff, canperformstreamclone will print out a message if a stream
clone was requested but couldn't happen for some reason. Removing this call
ensures the message isn't printed twice.
I'm going to replace hgimporter with a simpler import function, so we can
access to pure/cext modules by name:
# util.py
base85 = policy.importmod('base85') # select pure.base85 or cext.base85
# cffi/base85.py
from ..pure.base85 import * # may re-export pure.base85 functions
This means we'll have to use policy.importmod() function in place of the
standard import statement, but we wouldn't want to write it every place where
C extension modules are used. So this patch makes util host base85 functions.
This is a small style update for clarity. The previous situation was:
if foo:
50 lines
else:
2 lines
In such case I tend to invert these to get the simpler branch out of the way
earlier:
if not foo:
2 lines
else:
50 lines
This makes the conditional and various alternatives fit on the same screen,
simpler to read overall.
Bundle2 has its own mechanisms to check for heads (and other) changes, so push
using bundle2 is relying on the "check:heads" bundle part of unbundle and the
'check_heads' call is not checking anything. We add a small comment to make
this clearer.
util.compengines has knowledge of all registered compression engines
and the metadata that associates them with various bundle types.
This patch removes the now redundant declaration of this metadata from
exchange.py and obtains it from the new source.
The effect of this patch is that once a new compression engine is
registered with util.compengines, `hg bundle -t <engine>` will just
work.
Currently, exchange.getbundle() returns either a cg1unpacker or a
util.chunkbuffer (in the case of bundle2). This is kinda OK, as
both expose a .read() to consumers. However, localpeer.getbundle()
has code inferring what the response type is based on arguments and
converts the util.chunkbuffer returned in the bundle2 case to a
bundle2.unbundle20 instance. This is a sign that the API for
exchange.getbundle() is not ideal because it doesn't consistently
return an "unbundler" instance.
In addition, unbundlers mask the fact that there is an underlying
generator of changegroup data. In both cg1 and bundle2, this generator
is being fed into a util.chunkbuffer so it can be re-exposed as a
file object.
util.chunkbuffer is a nice abstraction. However, it should only be
used "at the edges." This is because keeping data as a generator is
more efficient than converting it to a chunkbuffer, especially if we
convert that chunkbuffer back to a generator (as is the case in some
code paths currently).
This patch refactors exchange.getbundle() into
exchange.getbundlechunks(). The new API returns an iterator of chunks
instead of a file-like object.
Callers of exchange.getbundle() have been updated to use the new API.
There is a minor change of behavior in test-getbundle.t. This is
because `hg debuggetbundle` isn't defining bundlecaps. As a result,
a cg1 data stream and unpacker is being produced. This is getting fed
into a new bundle20 instance via bundle2.writebundle(), which uses
a backchannel mechanism between changegroup generation to add the
"nbchanges" part parameter. I never liked this backchannel mechanism
and I plan to remove it someday. `hg bundle` still produces the
"nbchanges" part parameter, so there should be no user-visible
change of behavior. I consider this "regression" a bug in
`hg debuggetbundle`. And that bug is captured by an existing
"TODO" in the code to use bundle2 capabilities.
because pull might move bookmarks and bookmark are protected by wlock, we have
to grab wlock for pull :-(
This required a small upgrade of the 'lockdelay' extension used by
'test-clone.t' because the delay must apply to a single lock only.
Now that all users are in exchange, we can safely move the code in the
'exchange' module. This function is really about processing the argument of a
'getbundle' call, so it even makes senses to do so.
There is various version of this function that differ mostly by the way they
define the bundled set. The flexibility is now available in the outgoing object
itself so we move the complexity into the caller themself. This will allow use
to remove a good share of the similar function to obtains a changegroup in the
'changegroup.py' module.
An important side effect is that we stop calling 'computeoutgoing' in
'getchangegroup'. This is fine as code that needs such argument processing
is actually going through the 'exchange' module which already all this function
itself.
This parameter is slightly confusingly named in wireproto, so it got
mis-specified from the start as 'push' instead of the URL to which we
are pushing. Sigh. I've got a patch for that which I'll mail
separately since it's not really appropriate for stable.
Fixes a regression in bundle2 from bundle1.
