codemod: register core configitems using a script
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:]))
# mail.py - mail sending bits for mercurial
#
# Copyright 2006 Matt Mackall <mpm@selenic.com>
#
# 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 email
import email.charset
import email.header
import os
import quopri
import smtplib
import socket
import time
from .i18n import _
from . import (
encoding,
error,
sslutil,
util,
)
class STARTTLS(smtplib.SMTP):
'''Derived class to verify the peer certificate for STARTTLS.
This class allows to pass any keyword arguments to SSL socket creation.
'''
def __init__(self, ui, host=None, **kwargs):
smtplib.SMTP.__init__(self, **kwargs)
self._ui = ui
self._host = host
def starttls(self, keyfile=None, certfile=None):
if not self.has_extn("starttls"):
msg = "STARTTLS extension not supported by server"
raise smtplib.SMTPException(msg)
(resp, reply) = self.docmd("STARTTLS")
if resp == 220:
self.sock = sslutil.wrapsocket(self.sock, keyfile, certfile,
ui=self._ui,
serverhostname=self._host)
self.file = smtplib.SSLFakeFile(self.sock)
self.helo_resp = None
self.ehlo_resp = None
self.esmtp_features = {}
self.does_esmtp = 0
return (resp, reply)
class SMTPS(smtplib.SMTP):
'''Derived class to verify the peer certificate for SMTPS.
This class allows to pass any keyword arguments to SSL socket creation.
'''
def __init__(self, ui, keyfile=None, certfile=None, host=None,
**kwargs):
self.keyfile = keyfile
self.certfile = certfile
smtplib.SMTP.__init__(self, **kwargs)
self._host = host
self.default_port = smtplib.SMTP_SSL_PORT
self._ui = ui
def _get_socket(self, host, port, timeout):
if self.debuglevel > 0:
self._ui.debug('connect: %r\n' % (host, port))
new_socket = socket.create_connection((host, port), timeout)
new_socket = sslutil.wrapsocket(new_socket,
self.keyfile, self.certfile,
ui=self._ui,
serverhostname=self._host)
self.file = smtplib.SSLFakeFile(new_socket)
return new_socket
def _smtp(ui):
'''build an smtp connection and return a function to send mail'''
local_hostname = ui.config('smtp', 'local_hostname')
tls = ui.config('smtp', 'tls')
# backward compatible: when tls = true, we use starttls.
starttls = tls == 'starttls' or util.parsebool(tls)
smtps = tls == 'smtps'
if (starttls or smtps) and not util.safehasattr(socket, 'ssl'):
raise error.Abort(_("can't use TLS: Python SSL support not installed"))
mailhost = ui.config('smtp', 'host')
if not mailhost:
raise error.Abort(_('smtp.host not configured - cannot send mail'))
if smtps:
ui.note(_('(using smtps)\n'))
s = SMTPS(ui, local_hostname=local_hostname, host=mailhost)
elif starttls:
s = STARTTLS(ui, local_hostname=local_hostname, host=mailhost)
else:
s = smtplib.SMTP(local_hostname=local_hostname)
if smtps:
defaultport = 465
else:
defaultport = 25
mailport = util.getport(ui.config('smtp', 'port', defaultport))
ui.note(_('sending mail: smtp host %s, port %d\n') %
(mailhost, mailport))
s.connect(host=mailhost, port=mailport)
if starttls:
ui.note(_('(using starttls)\n'))
s.ehlo()
s.starttls()
s.ehlo()
if starttls or smtps:
ui.note(_('(verifying remote certificate)\n'))
sslutil.validatesocket(s.sock)
username = ui.config('smtp', 'username')
password = ui.config('smtp', 'password')
if username and not password:
password = ui.getpass()
if username and password:
ui.note(_('(authenticating to mail server as %s)\n') %
(username))
try:
s.login(username, password)
except smtplib.SMTPException as inst:
raise error.Abort(inst)
def send(sender, recipients, msg):
try:
return s.sendmail(sender, recipients, msg)
except smtplib.SMTPRecipientsRefused as inst:
recipients = [r[1] for r in inst.recipients.values()]
raise error.Abort('\n' + '\n'.join(recipients))
except smtplib.SMTPException as inst:
raise error.Abort(inst)
return send
def _sendmail(ui, sender, recipients, msg):
'''send mail using sendmail.'''
program = ui.config('email', 'method')
cmdline = '%s -f %s %s' % (program, util.email(sender),
' '.join(map(util.email, recipients)))
ui.note(_('sending mail: %s\n') % cmdline)
fp = util.popen(cmdline, 'w')
fp.write(msg)
ret = fp.close()
if ret:
raise error.Abort('%s %s' % (
os.path.basename(program.split(None, 1)[0]),
util.explainexit(ret)[0]))
def _mbox(mbox, sender, recipients, msg):
'''write mails to mbox'''
fp = open(mbox, 'ab+')
# Should be time.asctime(), but Windows prints 2-characters day
# of month instead of one. Make them print the same thing.
date = time.strftime('%a %b %d %H:%M:%S %Y', time.localtime())
fp.write('From %s %s\n' % (sender, date))
fp.write(msg)
fp.write('\n\n')
fp.close()
def connect(ui, mbox=None):
'''make a mail connection. return a function to send mail.
call as sendmail(sender, list-of-recipients, msg).'''
if mbox:
open(mbox, 'wb').close()
return lambda s, r, m: _mbox(mbox, s, r, m)
if ui.config('email', 'method') == 'smtp':
return _smtp(ui)
return lambda s, r, m: _sendmail(ui, s, r, m)
def sendmail(ui, sender, recipients, msg, mbox=None):
send = connect(ui, mbox=mbox)
return send(sender, recipients, msg)
def validateconfig(ui):
'''determine if we have enough config data to try sending email.'''
method = ui.config('email', 'method')
if method == 'smtp':
if not ui.config('smtp', 'host'):
raise error.Abort(_('smtp specified as email transport, '
'but no smtp host configured'))
else:
if not util.findexe(method):
raise error.Abort(_('%r specified as email transport, '
'but not in PATH') % method)
def codec2iana(cs):
''''''
cs = email.charset.Charset(cs).input_charset.lower()
# "latin1" normalizes to "iso8859-1", standard calls for "iso-8859-1"
if cs.startswith("iso") and not cs.startswith("iso-"):
return "iso-" + cs[3:]
return cs
def mimetextpatch(s, subtype='plain', display=False):
'''Return MIME message suitable for a patch.
Charset will be detected by first trying to decode as us-ascii, then utf-8,
and finally the global encodings. If all those fail, fall back to
ISO-8859-1, an encoding with that allows all byte sequences.
Transfer encodings will be used if necessary.'''
cs = ['us-ascii', 'utf-8', encoding.encoding, encoding.fallbackencoding]
if display:
return mimetextqp(s, subtype, 'us-ascii')
for charset in cs:
try:
s.decode(charset)
return mimetextqp(s, subtype, codec2iana(charset))
except UnicodeDecodeError:
pass
return mimetextqp(s, subtype, "iso-8859-1")
def mimetextqp(body, subtype, charset):
'''Return MIME message.
Quoted-printable transfer encoding will be used if necessary.
'''
enc = None
for line in body.splitlines():
if len(line) > 950:
body = quopri.encodestring(body)
enc = "quoted-printable"
break
msg = email.MIMEText.MIMEText(body, subtype, charset)
if enc:
del msg['Content-Transfer-Encoding']
msg['Content-Transfer-Encoding'] = enc
return msg
def _charsets(ui):
'''Obtains charsets to send mail parts not containing patches.'''
charsets = [cs.lower() for cs in ui.configlist('email', 'charsets')]
fallbacks = [encoding.fallbackencoding.lower(),
encoding.encoding.lower(), 'utf-8']
for cs in fallbacks: # find unique charsets while keeping order
if cs not in charsets:
charsets.append(cs)
return [cs for cs in charsets if not cs.endswith('ascii')]
def _encode(ui, s, charsets):
'''Returns (converted) string, charset tuple.
Finds out best charset by cycling through sendcharsets in descending
order. Tries both encoding and fallbackencoding for input. Only as
last resort send as is in fake ascii.
Caveat: Do not use for mail parts containing patches!'''
try:
s.decode('ascii')
except UnicodeDecodeError:
sendcharsets = charsets or _charsets(ui)
for ics in (encoding.encoding, encoding.fallbackencoding):
try:
u = s.decode(ics)
except UnicodeDecodeError:
continue
for ocs in sendcharsets:
try:
return u.encode(ocs), ocs
except UnicodeEncodeError:
pass
except LookupError:
ui.warn(_('ignoring invalid sendcharset: %s\n') % ocs)
# if ascii, or all conversion attempts fail, send (broken) ascii
return s, 'us-ascii'
def headencode(ui, s, charsets=None, display=False):
'''Returns RFC-2047 compliant header from given string.'''
if not display:
# split into words?
s, cs = _encode(ui, s, charsets)
return str(email.header.Header(s, cs))
return s
def _addressencode(ui, name, addr, charsets=None):
name = headencode(ui, name, charsets)
try:
acc, dom = addr.split('@')
acc = acc.encode('ascii')
dom = dom.decode(encoding.encoding).encode('idna')
addr = '%s@%s' % (acc, dom)
except UnicodeDecodeError:
raise error.Abort(_('invalid email address: %s') % addr)
except ValueError:
try:
# too strict?
addr = addr.encode('ascii')
except UnicodeDecodeError:
raise error.Abort(_('invalid local address: %s') % addr)
return email.Utils.formataddr((name, addr))
def addressencode(ui, address, charsets=None, display=False):
'''Turns address into RFC-2047 compliant header.'''
if display or not address:
return address or ''
name, addr = email.Utils.parseaddr(address)
return _addressencode(ui, name, addr, charsets)
def addrlistencode(ui, addrs, charsets=None, display=False):
'''Turns a list of addresses into a list of RFC-2047 compliant headers.
A single element of input list may contain multiple addresses, but output
always has one address per item'''
if display:
return [a.strip() for a in addrs if a.strip()]
result = []
for name, addr in email.Utils.getaddresses(addrs):
if name or addr:
result.append(_addressencode(ui, name, addr, charsets))
return result
def mimeencode(ui, s, charsets=None, display=False):
'''creates mime text object, encodes it if needed, and sets
charset and transfer-encoding accordingly.'''
cs = 'us-ascii'
if not display:
s, cs = _encode(ui, s, charsets)
return mimetextqp(s, 'plain', cs)
def headdecode(s):
'''Decodes RFC-2047 header'''
uparts = []
for part, charset in email.header.decode_header(s):
if charset is not None:
try:
uparts.append(part.decode(charset))
continue
except UnicodeDecodeError:
pass
try:
uparts.append(part.decode('UTF-8'))
continue
except UnicodeDecodeError:
pass
uparts.append(part.decode('ISO-8859-1'))
return encoding.unitolocal(u' '.join(uparts))