view mercurial/archival.py @ 14365:a8e3931e3fb5

revlog: linearize created changegroups in generaldelta revlogs

This greatly improves the speed of the bundling process, and often reduces the
bundle size considerably. (Although if the repository is already ordered, this
has little effect on both time and bundle size.)

For non-generaldelta clients, the reduced bundle size translates to a reduced
repository size, similar to shrinking the revlogs (which uses the exact same
algorithm). For generaldelta clients the difference is minor.

When the new bundle format comes, reordering will not be necessary since we
can then store the deltaparent relationsships directly. The eventual default
behavior for clients and servers is presented in the table below, where "new"
implies support for GD as well as the new bundle format:

                    old client                    new client
old server          old bundle, no reorder        old bundle, no reorder
new server, non-GD  old bundle, no reorder[1]     old bundle, no reorder[2]
new server, GD      old bundle, reorder[3]        new bundle, no reorder[4]

[1] reordering is expensive on the server in this case, skip it
[2] client can choose to do its own redelta here
[3] reordering is needed because otherwise the pull does a lot of extra
    work on the server
[4] reordering isn't needed because client can get deltabase in bundle
    format

Currently, the default is to reorder on GD-servers, and not otherwise. A new
setting, bundle.reorder, has been added to override the default reordering
behavior. It can be set to either 'auto' (the default), or any true or false
value as a standard boolean setting, to either force the reordering on or off
regardless of generaldelta.


Some timing data from a relatively branch test repository follows. All
bundling is done with --all --type none options.

Non-generaldelta, non-shrunk repo:
-----------------------------------
Size: 276M

Without reorder (default):
Bundle time: 14.4 seconds
Bundle size: 939M

With reorder:
Bundle time: 1 minute, 29.3 seconds
Bundle size: 381M

Generaldelta, non-shrunk repo:
-----------------------------------
Size: 87M

Without reorder:
Bundle time: 2 minutes, 1.4 seconds
Bundle size: 939M

With reorder (default):
Bundle time: 25.5 seconds
Bundle size: 381M

# archival.py - revision archival for mercurial
#
# Copyright 2006 Vadim Gelfer <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from i18n import _
from node import hex
import cmdutil
import scmutil, util, encoding
import cStringIO, os, tarfile, time, zipfile
import zlib, gzip

def tidyprefix(dest, kind, prefix):
    '''choose prefix to use for names in archive.  make sure prefix is
    safe for consumers.'''

    if prefix:
        prefix = util.normpath(prefix)
    else:
        if not isinstance(dest, str):
            raise ValueError('dest must be string if no prefix')
        prefix = os.path.basename(dest)
        lower = prefix.lower()
        for sfx in exts.get(kind, []):
            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 += '/'
    if prefix.startswith('../') or os.path.isabs(lpfx) or '/../' in prefix:
        raise util.Abort(_('archive prefix contains illegal components'))
    return prefix

exts = {
    'tar': ['.tar'],
    'tbz2': ['.tbz2', '.tar.bz2'],
    'tgz': ['.tgz', '.tar.gz'],
    'zip': ['.zip'],
    }

def guesskind(dest):
    for kind, extensions in exts.iteritems():
        if util.any(dest.endswith(ext) for ext in extensions):
            return kind
    return None


class tarit(object):
    '''write archive to tar file or stream.  can write uncompressed,
    or compress with gzip or bzip2.'''

    class GzipFileWithTime(gzip.GzipFile):

        def __init__(self, *args, **kw):
            timestamp = None
            if 'timestamp' in kw:
                timestamp = kw.pop('timestamp')
            if timestamp is None:
                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
            # Python 2.6 deprecates self.filename
            fname = getattr(self, 'name', None) or self.filename
            if fname and fname.endswith('.gz'):
                fname = fname[:-3]
            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')

    def __init__(self, dest, mtime, kind=''):
        self.mtime = mtime
        self.fileobj = None

        def taropen(name, mode, fileobj=None):
            if kind == 'gz':
                mode = mode[0]
                if not fileobj:
                    fileobj = open(name, mode + 'b')
                gzfileobj = self.GzipFileWithTime(name, mode + 'b',
                                                  zlib.Z_BEST_COMPRESSION,
                                                  fileobj, timestamp=mtime)
                self.fileobj = gzfileobj
                return tarfile.TarFile.taropen(name, mode, gzfileobj)
            else:
                self.fileobj = fileobj
                return tarfile.open(name, mode + kind, fileobj)

        if isinstance(dest, str):
            self.z = taropen(dest, mode='w:')
        else:
            # Python 2.5-2.5.1 have a regression that requires a name arg
            self.z = taropen(name='', mode='w|', fileobj=dest)

    def addfile(self, name, mode, islink, data):
        i = tarfile.TarInfo(name)
        i.mtime = self.mtime
        i.size = len(data)
        if islink:
            i.type = tarfile.SYMTYPE
            i.mode = 0777
            i.linkname = data
            data = None
            i.size = 0
        else:
            i.mode = mode
            data = cStringIO.StringIO(data)
        self.z.addfile(i, data)

    def done(self):
        self.z.close()
        if self.fileobj:
            self.fileobj.close()

class tellable(object):
    '''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

class zipit(object):
    '''write archive to zip file or stream.  can write uncompressed,
    or compressed with deflate.'''

    def __init__(self, dest, mtime, compress=True):
        if not isinstance(dest, str):
            try:
                dest.tell()
            except (AttributeError, IOError):
                dest = tellable(dest)
        self.z = zipfile.ZipFile(dest, 'w',
                                 compress and zipfile.ZIP_DEFLATED or
                                 zipfile.ZIP_STORED)

        # 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

        self.date_time = time.gmtime(mtime)[:6]

    def addfile(self, name, mode, islink, data):
        i = zipfile.ZipInfo(name, self.date_time)
        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
        ftype = 0x8000 # UNX_IFREG in unzip source code
        if islink:
            mode = 0777
            ftype = 0xa000 # UNX_IFLNK in unzip source code
        i.external_attr = (mode | ftype) << 16L
        self.z.writestr(i, data)

    def done(self):
        self.z.close()

class fileit(object):
    '''write archive as files in directory.'''

    def __init__(self, name, mtime):
        self.basedir = name
        self.opener = scmutil.opener(self.basedir)

    def addfile(self, name, mode, islink, data):
        if islink:
            self.opener.symlink(data, name)
            return
        f = self.opener(name, "w", atomictemp=True)
        f.write(data)
        f.rename()
        destfile = os.path.join(self.basedir, name)
        os.chmod(destfile, mode)

    def done(self):
        pass

archivers = {
    'files': fileit,
    'tar': tarit,
    'tbz2': lambda name, mtime: tarit(name, mtime, 'bz2'),
    'tgz': lambda name, mtime: tarit(name, mtime, 'gz'),
    'uzip': lambda name, mtime: zipit(name, mtime, False),
    'zip': zipit,
    }

def archive(repo, dest, node, kind, decode=True, matchfn=None,
            prefix=None, mtime=None, subrepos=False):
    '''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.'''

    if kind == 'files':
        if prefix:
            raise util.Abort(_('cannot give prefix when archiving to files'))
    else:
        prefix = tidyprefix(dest, kind, prefix)

    def write(name, mode, islink, getdata):
        if matchfn and not matchfn(name):
            return
        data = getdata()
        if decode:
            data = repo.wwritedata(name, data)
        archiver.addfile(prefix + name, mode, islink, data)

    if kind not in archivers:
        raise util.Abort(_("unknown archive type '%s'") % kind)

    ctx = repo[node]
    archiver = archivers[kind](dest, mtime or ctx.date()[0])

    if repo.ui.configbool("ui", "archivemeta", True):
        def metadata():
            base = 'repo: %s\nnode: %s\nbranch: %s\n' % (
                repo[0].hex(), hex(node), encoding.fromlocal(ctx.branch()))

            tags = ''.join('tag: %s\n' % t for t in ctx.tags()
                           if repo.tagtype(t) == 'global')
            if not tags:
                repo.ui.pushbuffer()
                opts = {'template': '{latesttag}\n{latesttagdistance}',
                        'style': '', 'patch': None, 'git': None}
                cmdutil.show_changeset(repo.ui, repo, opts).show(ctx)
                ltags, dist = repo.ui.popbuffer().split('\n')
                tags = ''.join('latesttag: %s\n' % t for t in ltags.split(':'))
                tags += 'latesttagdistance: %s\n' % dist

            return base + tags

        write('.hg_archival.txt', 0644, False, metadata)

    total = len(ctx.manifest())
    repo.ui.progress(_('archiving'), 0, unit=_('files'), total=total)
    for i, f in enumerate(ctx):
        ff = ctx.flags(f)
        write(f, 'x' in ff and 0755 or 0644, 'l' in ff, ctx[f].data)
        repo.ui.progress(_('archiving'), i + 1, item=f,
                         unit=_('files'), total=total)
    repo.ui.progress(_('archiving'), None)

    if subrepos:
        for subpath in ctx.substate:
            sub = ctx.sub(subpath)
            sub.archive(repo.ui, archiver, prefix)

    archiver.done()