2006-04-22 02:27:57 +04:00
|
|
|
# archival.py - revision archival for mercurial
|
|
|
|
#
|
|
|
|
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
|
|
|
|
#
|
2009-04-26 03:08:54 +04:00
|
|
|
# This software may be used and distributed according to the terms of the
|
2010-01-20 07:20:08 +03:00
|
|
|
# GNU General Public License version 2 or any later version.
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2015-08-08 05:47:49 +03:00
|
|
|
from __future__ import absolute_import
|
|
|
|
|
|
|
|
import cStringIO
|
|
|
|
import gzip
|
|
|
|
import os
|
2012-09-18 14:46:15 +04:00
|
|
|
import struct
|
2015-08-08 05:47:49 +03:00
|
|
|
import tarfile
|
|
|
|
import time
|
|
|
|
import zipfile
|
|
|
|
import zlib
|
|
|
|
|
|
|
|
from .i18n import _
|
|
|
|
|
|
|
|
from . import (
|
|
|
|
cmdutil,
|
|
|
|
encoding,
|
|
|
|
error,
|
|
|
|
match as matchmod,
|
|
|
|
scmutil,
|
|
|
|
util,
|
|
|
|
)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2012-08-28 01:16:22 +04:00
|
|
|
# from unzip source code:
|
|
|
|
_UNX_IFREG = 0x8000
|
|
|
|
_UNX_IFLNK = 0xa000
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
def tidyprefix(dest, kind, prefix):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''choose prefix to use for names in archive. make sure prefix is
|
|
|
|
safe for consumers.'''
|
|
|
|
|
|
|
|
if prefix:
|
2008-01-09 15:30:13 +03:00
|
|
|
prefix = util.normpath(prefix)
|
2006-04-22 02:27:57 +04:00
|
|
|
else:
|
|
|
|
if not isinstance(dest, str):
|
|
|
|
raise ValueError('dest must be string if no prefix')
|
|
|
|
prefix = os.path.basename(dest)
|
|
|
|
lower = prefix.lower()
|
2010-07-14 22:25:31 +04:00
|
|
|
for sfx in exts.get(kind, []):
|
2006-04-22 02:27:57 +04:00
|
|
|
if lower.endswith(sfx):
|
|
|
|
prefix = prefix[:-len(sfx)]
|
|
|
|
break
|
|
|
|
lpfx = os.path.normpath(util.localpath(prefix))
|
|
|
|
prefix = util.pconvert(lpfx)
|
|
|
|
if not prefix.endswith('/'):
|
|
|
|
prefix += '/'
|
2015-05-06 03:52:38 +03:00
|
|
|
# Drop the leading '.' path component if present, so Windows can read the
|
|
|
|
# zip files (issue4634)
|
|
|
|
if prefix.startswith('./'):
|
|
|
|
prefix = prefix[2:]
|
2006-04-22 02:27:57 +04:00
|
|
|
if prefix.startswith('../') or os.path.isabs(lpfx) or '/../' in prefix:
|
2015-10-08 22:55:45 +03:00
|
|
|
raise error.Abort(_('archive prefix contains illegal components'))
|
2006-04-22 02:27:57 +04:00
|
|
|
return prefix
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
exts = {
|
|
|
|
'tar': ['.tar'],
|
|
|
|
'tbz2': ['.tbz2', '.tar.bz2'],
|
|
|
|
'tgz': ['.tgz', '.tar.gz'],
|
|
|
|
'zip': ['.zip'],
|
|
|
|
}
|
|
|
|
|
|
|
|
def guesskind(dest):
|
|
|
|
for kind, extensions in exts.iteritems():
|
2015-05-16 21:30:07 +03:00
|
|
|
if any(dest.endswith(ext) for ext in extensions):
|
2010-07-14 22:25:31 +04:00
|
|
|
return kind
|
|
|
|
return None
|
|
|
|
|
2015-04-08 17:30:02 +03:00
|
|
|
def _rootctx(repo):
|
|
|
|
# repo[0] may be hidden
|
|
|
|
for rev in repo:
|
|
|
|
return repo[rev]
|
|
|
|
return repo['null']
|
|
|
|
|
2015-04-08 16:37:03 +03:00
|
|
|
def buildmetadata(ctx):
|
|
|
|
'''build content of .hg_archival.txt'''
|
|
|
|
repo = ctx.repo()
|
2015-06-17 06:14:45 +03:00
|
|
|
hex = ctx.hex()
|
|
|
|
if ctx.rev() is None:
|
|
|
|
hex = ctx.p1().hex()
|
|
|
|
if ctx.dirty():
|
|
|
|
hex += '+'
|
|
|
|
|
2015-04-08 16:37:03 +03:00
|
|
|
base = 'repo: %s\nnode: %s\nbranch: %s\n' % (
|
2015-06-17 06:14:45 +03:00
|
|
|
_rootctx(repo).hex(), hex, encoding.fromlocal(ctx.branch()))
|
2015-04-08 16:37:03 +03:00
|
|
|
|
|
|
|
tags = ''.join('tag: %s\n' % t for t in ctx.tags()
|
|
|
|
if repo.tagtype(t) == 'global')
|
|
|
|
if not tags:
|
|
|
|
repo.ui.pushbuffer()
|
2015-07-01 06:56:49 +03:00
|
|
|
opts = {'template': '{latesttag}\n{latesttagdistance}\n'
|
|
|
|
'{changessincelatesttag}',
|
2015-04-08 16:37:03 +03:00
|
|
|
'style': '', 'patch': None, 'git': None}
|
|
|
|
cmdutil.show_changeset(repo.ui, repo, opts).show(ctx)
|
2015-07-01 06:56:49 +03:00
|
|
|
ltags, dist, changessince = repo.ui.popbuffer().split('\n')
|
2015-04-08 16:37:03 +03:00
|
|
|
ltags = ltags.split(':')
|
|
|
|
tags = ''.join('latesttag: %s\n' % t for t in ltags)
|
|
|
|
tags += 'latesttagdistance: %s\n' % dist
|
|
|
|
tags += 'changessincelatesttag: %s\n' % changessince
|
|
|
|
|
|
|
|
return base + tags
|
2010-07-14 22:25:31 +04:00
|
|
|
|
2009-06-10 17:10:21 +04:00
|
|
|
class tarit(object):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''write archive to tar file or stream. can write uncompressed,
|
|
|
|
or compress with gzip or bzip2.'''
|
|
|
|
|
2007-06-11 21:09:01 +04:00
|
|
|
class GzipFileWithTime(gzip.GzipFile):
|
|
|
|
|
|
|
|
def __init__(self, *args, **kw):
|
|
|
|
timestamp = None
|
|
|
|
if 'timestamp' in kw:
|
|
|
|
timestamp = kw.pop('timestamp')
|
2009-05-20 02:52:46 +04:00
|
|
|
if timestamp is None:
|
2007-06-11 21:09:01 +04:00
|
|
|
self.timestamp = time.time()
|
|
|
|
else:
|
|
|
|
self.timestamp = timestamp
|
|
|
|
gzip.GzipFile.__init__(self, *args, **kw)
|
|
|
|
|
|
|
|
def _write_gzip_header(self):
|
|
|
|
self.fileobj.write('\037\213') # magic header
|
|
|
|
self.fileobj.write('\010') # compression method
|
2015-09-04 12:54:35 +03:00
|
|
|
fname = self.name
|
2010-12-07 11:47:53 +03:00
|
|
|
if fname and fname.endswith('.gz'):
|
|
|
|
fname = fname[:-3]
|
2007-06-11 21:09:01 +04:00
|
|
|
flags = 0
|
|
|
|
if fname:
|
|
|
|
flags = gzip.FNAME
|
|
|
|
self.fileobj.write(chr(flags))
|
|
|
|
gzip.write32u(self.fileobj, long(self.timestamp))
|
|
|
|
self.fileobj.write('\002')
|
|
|
|
self.fileobj.write('\377')
|
|
|
|
if fname:
|
|
|
|
self.fileobj.write(fname + '\000')
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
def __init__(self, dest, mtime, kind=''):
|
2006-06-22 02:31:23 +04:00
|
|
|
self.mtime = mtime
|
2010-12-24 17:23:01 +03:00
|
|
|
self.fileobj = None
|
2007-06-11 21:09:01 +04:00
|
|
|
|
|
|
|
def taropen(name, mode, fileobj=None):
|
|
|
|
if kind == 'gz':
|
|
|
|
mode = mode[0]
|
|
|
|
if not fileobj:
|
2007-06-27 19:35:26 +04:00
|
|
|
fileobj = open(name, mode + 'b')
|
2007-06-11 21:09:01 +04:00
|
|
|
gzfileobj = self.GzipFileWithTime(name, mode + 'b',
|
|
|
|
zlib.Z_BEST_COMPRESSION,
|
|
|
|
fileobj, timestamp=mtime)
|
2010-12-24 17:23:01 +03:00
|
|
|
self.fileobj = gzfileobj
|
2007-06-11 21:09:01 +04:00
|
|
|
return tarfile.TarFile.taropen(name, mode, gzfileobj)
|
|
|
|
else:
|
|
|
|
return tarfile.open(name, mode + kind, fileobj)
|
|
|
|
|
2006-04-22 02:27:57 +04:00
|
|
|
if isinstance(dest, str):
|
2007-06-11 21:09:01 +04:00
|
|
|
self.z = taropen(dest, mode='w:')
|
2006-04-22 02:27:57 +04:00
|
|
|
else:
|
2007-04-24 21:44:13 +04:00
|
|
|
# Python 2.5-2.5.1 have a regression that requires a name arg
|
2007-06-11 21:09:01 +04:00
|
|
|
self.z = taropen(name='', mode='w|', fileobj=dest)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2007-07-12 00:40:41 +04:00
|
|
|
def addfile(self, name, mode, islink, data):
|
2010-07-14 22:25:31 +04:00
|
|
|
i = tarfile.TarInfo(name)
|
2006-04-22 02:27:57 +04:00
|
|
|
i.mtime = self.mtime
|
|
|
|
i.size = len(data)
|
2007-07-12 00:40:41 +04:00
|
|
|
if islink:
|
|
|
|
i.type = tarfile.SYMTYPE
|
2015-06-24 08:30:33 +03:00
|
|
|
i.mode = 0o777
|
2007-07-12 00:40:41 +04:00
|
|
|
i.linkname = data
|
|
|
|
data = None
|
2009-02-15 20:14:20 +03:00
|
|
|
i.size = 0
|
2007-07-12 00:40:41 +04:00
|
|
|
else:
|
|
|
|
i.mode = mode
|
|
|
|
data = cStringIO.StringIO(data)
|
|
|
|
self.z.addfile(i, data)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
|
|
|
def done(self):
|
|
|
|
self.z.close()
|
2010-12-24 17:23:01 +03:00
|
|
|
if self.fileobj:
|
|
|
|
self.fileobj.close()
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2009-06-10 17:10:21 +04:00
|
|
|
class tellable(object):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''provide tell method for zipfile.ZipFile when writing to http
|
|
|
|
response file object.'''
|
|
|
|
|
|
|
|
def __init__(self, fp):
|
|
|
|
self.fp = fp
|
|
|
|
self.offset = 0
|
|
|
|
|
|
|
|
def __getattr__(self, key):
|
|
|
|
return getattr(self.fp, key)
|
|
|
|
|
|
|
|
def write(self, s):
|
|
|
|
self.fp.write(s)
|
|
|
|
self.offset += len(s)
|
|
|
|
|
|
|
|
def tell(self):
|
|
|
|
return self.offset
|
|
|
|
|
2009-06-10 17:10:21 +04:00
|
|
|
class zipit(object):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''write archive to zip file or stream. can write uncompressed,
|
|
|
|
or compressed with deflate.'''
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
def __init__(self, dest, mtime, compress=True):
|
2006-05-01 00:43:41 +04:00
|
|
|
if not isinstance(dest, str):
|
|
|
|
try:
|
|
|
|
dest.tell()
|
2006-05-01 00:46:54 +04:00
|
|
|
except (AttributeError, IOError):
|
2006-05-01 00:43:41 +04:00
|
|
|
dest = tellable(dest)
|
2006-04-22 02:27:57 +04:00
|
|
|
self.z = zipfile.ZipFile(dest, 'w',
|
|
|
|
compress and zipfile.ZIP_DEFLATED or
|
|
|
|
zipfile.ZIP_STORED)
|
2010-09-20 17:33:39 +04:00
|
|
|
|
|
|
|
# Python's zipfile module emits deprecation warnings if we try
|
|
|
|
# to store files with a date before 1980.
|
|
|
|
epoch = 315532800 # calendar.timegm((1980, 1, 1, 0, 0, 0, 1, 1, 0))
|
|
|
|
if mtime < epoch:
|
|
|
|
mtime = epoch
|
|
|
|
|
2012-09-18 14:46:15 +04:00
|
|
|
self.mtime = mtime
|
2006-06-22 02:31:23 +04:00
|
|
|
self.date_time = time.gmtime(mtime)[:6]
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2007-07-12 00:40:41 +04:00
|
|
|
def addfile(self, name, mode, islink, data):
|
2010-07-14 22:25:31 +04:00
|
|
|
i = zipfile.ZipInfo(name, self.date_time)
|
2006-04-22 02:27:57 +04:00
|
|
|
i.compress_type = self.z.compression
|
|
|
|
# unzip will not honor unix file modes unless file creator is
|
|
|
|
# set to unix (id 3).
|
|
|
|
i.create_system = 3
|
2012-08-28 01:16:22 +04:00
|
|
|
ftype = _UNX_IFREG
|
2007-07-12 00:40:41 +04:00
|
|
|
if islink:
|
2015-06-24 08:30:33 +03:00
|
|
|
mode = 0o777
|
2012-08-28 01:16:22 +04:00
|
|
|
ftype = _UNX_IFLNK
|
2007-07-12 00:40:41 +04:00
|
|
|
i.external_attr = (mode | ftype) << 16L
|
2012-09-18 14:46:15 +04:00
|
|
|
# add "extended-timestamp" extra block, because zip archives
|
|
|
|
# without this will be extracted with unexpected timestamp,
|
|
|
|
# if TZ is not configured as GMT
|
|
|
|
i.extra += struct.pack('<hhBl',
|
|
|
|
0x5455, # block type: "extended-timestamp"
|
|
|
|
1 + 4, # size of this block
|
|
|
|
1, # "modification time is present"
|
2013-01-04 00:07:04 +04:00
|
|
|
int(self.mtime)) # last modification (UTC)
|
2006-04-22 02:27:57 +04:00
|
|
|
self.z.writestr(i, data)
|
|
|
|
|
|
|
|
def done(self):
|
|
|
|
self.z.close()
|
|
|
|
|
2009-06-10 17:10:21 +04:00
|
|
|
class fileit(object):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''write archive as files in directory.'''
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
def __init__(self, name, mtime):
|
2006-04-22 02:27:57 +04:00
|
|
|
self.basedir = name
|
2011-04-20 21:54:57 +04:00
|
|
|
self.opener = scmutil.opener(self.basedir)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2007-07-12 00:40:41 +04:00
|
|
|
def addfile(self, name, mode, islink, data):
|
|
|
|
if islink:
|
|
|
|
self.opener.symlink(data, name)
|
|
|
|
return
|
2007-07-12 00:40:41 +04:00
|
|
|
f = self.opener(name, "w", atomictemp=True)
|
|
|
|
f.write(data)
|
2011-08-26 04:21:04 +04:00
|
|
|
f.close()
|
2006-04-22 02:27:57 +04:00
|
|
|
destfile = os.path.join(self.basedir, name)
|
2007-07-12 00:40:41 +04:00
|
|
|
os.chmod(destfile, mode)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
|
|
|
def done(self):
|
|
|
|
pass
|
|
|
|
|
|
|
|
archivers = {
|
|
|
|
'files': fileit,
|
|
|
|
'tar': tarit,
|
2010-07-14 22:25:31 +04:00
|
|
|
'tbz2': lambda name, mtime: tarit(name, mtime, 'bz2'),
|
|
|
|
'tgz': lambda name, mtime: tarit(name, mtime, 'gz'),
|
|
|
|
'uzip': lambda name, mtime: zipit(name, mtime, False),
|
2006-04-22 02:27:57 +04:00
|
|
|
'zip': zipit,
|
|
|
|
}
|
|
|
|
|
|
|
|
def archive(repo, dest, node, kind, decode=True, matchfn=None,
|
2015-02-16 01:21:48 +03:00
|
|
|
prefix='', mtime=None, subrepos=False):
|
2006-04-22 02:27:57 +04:00
|
|
|
'''create archive of repo as it was at node.
|
|
|
|
|
|
|
|
dest can be name of directory, name of archive file, or file
|
|
|
|
object to write archive to.
|
|
|
|
|
|
|
|
kind is type of archive to create.
|
|
|
|
|
|
|
|
decode tells whether to put files through decode filters from
|
|
|
|
hgrc.
|
|
|
|
|
|
|
|
matchfn is function to filter names of files to write to archive.
|
|
|
|
|
|
|
|
prefix is name of path to put before every archive member.'''
|
|
|
|
|
2010-07-14 22:25:31 +04:00
|
|
|
if kind == 'files':
|
|
|
|
if prefix:
|
2015-10-08 22:55:45 +03:00
|
|
|
raise error.Abort(_('cannot give prefix when archiving to files'))
|
2010-07-14 22:25:31 +04:00
|
|
|
else:
|
|
|
|
prefix = tidyprefix(dest, kind, prefix)
|
|
|
|
|
2007-07-20 02:43:25 +04:00
|
|
|
def write(name, mode, islink, getdata):
|
|
|
|
data = getdata()
|
2006-04-22 02:27:57 +04:00
|
|
|
if decode:
|
2006-12-30 05:04:31 +03:00
|
|
|
data = repo.wwritedata(name, data)
|
2010-07-14 22:25:31 +04:00
|
|
|
archiver.addfile(prefix + name, mode, islink, data)
|
2006-04-22 02:27:57 +04:00
|
|
|
|
2008-02-05 17:54:42 +03:00
|
|
|
if kind not in archivers:
|
2015-10-08 22:55:45 +03:00
|
|
|
raise error.Abort(_("unknown archive type '%s'") % kind)
|
2008-06-26 23:35:50 +04:00
|
|
|
|
|
|
|
ctx = repo[node]
|
2010-07-14 22:25:31 +04:00
|
|
|
archiver = archivers[kind](dest, mtime or ctx.date()[0])
|
2008-06-26 23:35:50 +04:00
|
|
|
|
2008-02-29 00:39:59 +03:00
|
|
|
if repo.ui.configbool("ui", "archivemeta", True):
|
2012-06-12 14:05:52 +04:00
|
|
|
name = '.hg_archival.txt'
|
|
|
|
if not matchfn or matchfn(name):
|
2015-06-24 08:30:33 +03:00
|
|
|
write(name, 0o644, False, lambda: buildmetadata(ctx))
|
2009-08-11 11:04:02 +04:00
|
|
|
|
2012-06-12 14:05:52 +04:00
|
|
|
if matchfn:
|
|
|
|
files = [f for f in ctx.manifest().keys() if matchfn(f)]
|
|
|
|
else:
|
|
|
|
files = ctx.manifest().keys()
|
|
|
|
total = len(files)
|
2013-03-22 01:09:15 +04:00
|
|
|
if total:
|
|
|
|
files.sort()
|
|
|
|
repo.ui.progress(_('archiving'), 0, unit=_('files'), total=total)
|
|
|
|
for i, f in enumerate(files):
|
|
|
|
ff = ctx.flags(f)
|
2015-06-24 08:30:33 +03:00
|
|
|
write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, ctx[f].data)
|
2013-03-22 01:09:15 +04:00
|
|
|
repo.ui.progress(_('archiving'), i + 1, item=f,
|
|
|
|
unit=_('files'), total=total)
|
|
|
|
repo.ui.progress(_('archiving'), None)
|
2010-09-20 17:46:17 +04:00
|
|
|
|
|
|
|
if subrepos:
|
2012-12-12 05:38:14 +04:00
|
|
|
for subpath in sorted(ctx.substate):
|
2015-06-17 06:06:57 +03:00
|
|
|
sub = ctx.workingsub(subpath)
|
2016-02-06 08:09:32 +03:00
|
|
|
submatch = matchmod.subdirmatcher(subpath, matchfn)
|
subrepo: drop the 'ui' parameter to archive()
The current state of subrepo methods is to pass a 'ui' object to some methods,
which has the effect of overriding the subrepo configuration since it is the
root repo's 'ui' that is passed along as deep as there are subrepos. Other
subrepo method are *not* passed the root 'ui', and instead delegate to their
repo object's 'ui'. Even in the former case where the root 'ui' is available,
some methods are inconsistent in their use of both the root 'ui' and the local
repo's 'ui'. (Consider hg._incoming() uses the root 'ui' for path expansion
and some status messages, but also calls bundlerepo.getremotechanges(), which
eventually calls discovery.findcommonincoming(), which calls
setdiscovery.findcommonheads(), which calls status() on the local repo 'ui'.)
This inconsistency with respect to the configured output level is probably
always hidden, because --verbose, --debug and --quiet, along with their 'ui.xxx'
equivalents in the global and user level hgrc files are propagated from the
parent repo to the subrepo via 'baseui'. The 'ui.xxx' settings in the parent
repo hgrc file are not propagated, but that seems like an unusual thing to set
on a per repo config file. Any 'ui.xxx' options changed by --config are also
not propagated, because they are set on repo.ui by dispatch.py, not repo.baseui.
The goal here is to cleanup the subrepo methods by dropping the 'ui' parameter,
which in turn prevents mixing subtly different 'ui' instances on a given subrepo
level. Some methods use more than just the output level settings in 'ui' (add
for example ends up calling scmutil.checkportabilityalert() with both the root
and local repo's 'ui' at different points). This series just goes for the low
hanging fruit and switches methods that only use the output level.
If we really care about not letting a subrepo config override the root repo's
output level, we can propagate the verbose, debug and quiet settings to the
subrepo in the same way 'ui.commitsubrepos' is in hgsubrepo.__init__.
Archive only uses the 'ui' object to call its progress() method, and gitsubrepo
calls status().
2014-12-13 22:53:46 +03:00
|
|
|
total += sub.archive(archiver, prefix, submatch)
|
2013-03-22 01:09:15 +04:00
|
|
|
|
|
|
|
if total == 0:
|
|
|
|
raise error.Abort(_('no files match the archive pattern'))
|
2010-09-20 17:46:17 +04:00
|
|
|
|
2006-04-22 02:27:57 +04:00
|
|
|
archiver.done()
|
2013-03-22 01:09:15 +04:00
|
|
|
return total
|