Without this patch on Windows 'hg ci -i' hangs waiting for user input
and "examine changes to 'file'? [Ynesfdaq?]" is never displayed (at least
if the diff is sufficiently small). When Ctrl+C is pressed, this prompt
becomes visible, which suggests that the buffer just wasn't flushed.
I've never seen this happening on Linux, but this looks harmless enough
to not platform-gate it.
Before this patch, explicit --pager=on is unintentionally ignored by
any disabling factor, even if priority of it is less than --pager=on
(e.g. "[ui] paginate = off").
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:]))
In some case, the default of one value is derived from other value. We add a
way to register them anyway and an associated devel-warning.
The registration is very naive for the moment. We might be able to have a
better way for registering each of these cases but it could be done later.
Aliases define optional alternatives to existing options. For example the old
option ui.user was deprecated and replaced by ui.username. With this mechanism,
it's even possible to create an alias to an option in a different section.
Add ui.user as alias to ui.username as an example of this concept.
The old alternates principle in ui.config is removed as it was used only for
this option.
Yuya pointed out that using mutable value as the default could be problematic.
To work around this we now support callable object as default value. This
allows for creating new mutable objects on demand when needed.
If the option is registered, there is already a default value available and
passing a new one is at best redundant. So we issue a deprecation warning in
this case.
(note: there will be case were the default value will not be as simple as what
is currently possible. We'll upgrade the configitems code to handle them in
time.)
We do not have any registered config yet, but we are now ready to use them.
For now we ignore this feature for config access with "alternates". On the long
run, we expect alternates to be handled as "aliases" by the config item
themself.
This should let 'configdate' delegate all special processing of the default
config value to the main 'config' method.
The default value for date (None) is still enforced in this method if no other
default were passed.
This should let 'configlist' delegate all special processing of the default
config value to the main 'config' method.
The default config value ([]) is still handled in this method.
This should let 'configwith' delegate all special processing of the default
config value to the main 'config' method.
This changeset introduce a small change in behavior since the default value is
run through the 'convert' function. This does not seems harmful and no actual
test break. This small change make the code simpler so I'm keeping it.
This should let 'configbool' delegate all special processing of the default
config value to the main 'config' method.
The default value for bool (False) is still enforced in this method if no other
default were passed.
We introduce a small object used to detect that no specific default value has
been passed to 'ui.config'. We need this explicit special value since "None" is
a valid and common default value.
The end goal here is to make progress on a centralised and explicit declaration
of the available config option. A first good usecase for this are "default"
value. Before starting looking further down this alley we needs to rework the
handling of default value in the 'ui' object to have all configxyz methods going
through the same logic. This is the first changeset on this trek.
We've been talking for years about a one-stop config knob to opt in to
better behavior. There have been a lot of ideas thrown around, but
they all seem to be too complicated to get anyone to actually do the
work.. As such, this patch is the stupidest thing that can possibly
work in the name of getting a good feature to users.
Right now it's just three config settings that I think are generally
uncontroversial, but I expect to add more soon. That will likely
include adding new config knobs for the express purpose of adding them
to tweakdefaults.
d46a7814be5f refactored util.parsedate in order to raise ValueError instead
of Abort for using with ui.configwith. It causes several problems, putting
arbitrary bytes in ValueError can cause issues with Python 3. Moreover, we
added a function to convert ValueError exceptions back to Abort.
A better approach would be to make parsedate raises ParseError, removing
the convert function and update configwith to also catch ParseError.
The side-effect is that error message when giving an invalid date in CLI
change from:
abort: invalid date: 'foo bar'
to:
hg: parse error: invalid date: 'foo bar'
I'm not sure if it's an acceptable change, I found personally the error
message more clear but more verbose too.
d46a7814be5f introduced util._parsedate with the aim to be used in
ui.configdate but ui.configdate was using util.parsedate instead. It have the
impact of raising an AbortError in case of an invalid date instead of a
ConfigError exception. Fix ui.configdate to use the right function and add a
test for invalid dates.
Thanks to Yuya for the catch!
This option was never released except for a release candidate. Dropping
compatibility with this option will free the 'pager.enable' config option for
other usage in the future.
This aligns with what we do for color (see cea7a760c58d). Pager is a central
enough notion that having the master config in the [ui] section makes senses. It
will helps with consistency, discoverability. It will also help having a simple
and clear example hgrc mentioning pager.
The previous form of the option had never been released in a non-rc version but
we keep it around for convenience. If both are set, 'ui.pager' take priority.
"Churn" is not the useful example we have, but this is the one used in
'hg help config.extensions'. As we need something to replace the deprecated
'pager' extension in the example config, we are adding 'churn'.
The prior code used to ignore all errors, which was intended to
deal with a decade-old problem with writing to broken pipes on
Windows.
However, that code inadvertantly went a lot further, making it
impossible to detect *all* I/O errors on stdio ... but only sometimes.
What actually happened was that if Mercurial wrote less than a stdio
buffer's worth of output (the overwhelmingly common case for most
commands), any error that occurred would get swallowed here. But
if the buffering strategy changed, an unhandled IOError could be
raised from any number of other locations.
Because we now have a top-level StdioError handler, and ui._write
and ui._write_err (and now flush!) will raise that exception, we
have one rational place to detect and handle these errors.
In spite of its longstanding use, Python's built-in atexit code is
not suitable for Mercurial's purposes, for several reasons:
* Handlers run after application code has finished.
* Because of this, the code that runs handlers swallows exceptions
(since there's no possible stacktrace to associate errors with).
If we're lucky, we'll get something spat out to stderr (if stderr
still works), which of course isn't any use in a big deployment
where it's important that exceptions get logged and aggregated.
* Mercurial's current atexit handlers make unfortunate assumptions
about process state (specifically stdio) that, coupled with the
above problems, make it impossible to deal with certain categories
of error (try "hg status > /dev/full" on a Linux box).
* In Python 3, the atexit implementation is completely hidden, so
we can't hijack the platform's atexit code to run handlers at a
time of our choosing.
As a result, here's a perfectly cromulent atexit-like implementation
over which we have control. This lets us decide exactly when the
handlers run (after each request has completed), and control what
the process state is when that occurs (and afterwards).
Text IO sucks on Python 3 as it must be a unicode stream. We could introduce
a wrapper that converts unicode back to bytes, but it wouldn't be simple to
handle offsets transparently from/to underlying IOBase API.
Fortunately, we don't need to process huge text files, so let's stick to
bytes IO and convert EOL in memory.
