view mercurial/archival.py @ 5192:33015dac5df5

convert: fix mercurial_sink.putcommit Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a revision that touches no files, but this can break regular conversions from some repositories: - conceptually, since we're converting a repo, we should try to make the new hg repo as similar as possible to the original repo - we should create a new changeset, even if the original revision didn't touch any files (maybe the commit message had some important bit); - even if a "regular" revision that doesn't touch any file may seem weird (and maybe even broken), it's completely legitimate for a merge revision to not touch any file, and, if we just skip it, the converted repo will end up with wrong history and possibly an extra head. As an example, say the crew and main hg repos are sync'ed. Somebody sends an important patch to the mailing list. Matt quickly applies and pushes it. But at the same time somebody also applies it to crew and pushes it. Suppose the commit message ended up being a bit different (say, there was a typo and somebody didn't fix it) or that the date ended up being different (because of different patch-applying scripts): the changeset hashes will be different, but the manifests will be the same. Since both changesets were pushed to public repos, it's hard to recall them. If both are merged, the manifest from the resulting merge revision will have the exact same contents as its parents - i.e. the merge revision really doesn't touch any file at all. To keep the file filtering stuff "working", the generic code was changed to skip empty revisions if we're filtering the repo, fixing a bug in the process (we want parents[0] instead of tip).
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
date Fri, 17 Aug 2007 20:18:05 -0300
parents 667290b6c95e
children
line wrap: on
line source

# archival.py - revision archival for mercurial
#
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of
# the GNU General Public License, incorporated herein by reference.

from i18n import _
from node import *
import cStringIO, os, stat, tarfile, time, util, zipfile
import zlib, gzip

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

    if prefix:
        prefix = prefix.replace('\\', '/')
    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 suffixes:
            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

class tarit:
    '''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 == 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
            fname = self.filename[:-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, prefix, mtime, kind=''):
        self.prefix = tidyprefix(dest, prefix, ['.tar', '.tar.bz2', '.tar.gz',
                                                '.tgz', '.tbz2'])
        self.mtime = mtime

        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)
                return tarfile.TarFile.taropen(name, mode, gzfileobj)
            else:
                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(self.prefix + name)
        i.mtime = self.mtime
        i.size = len(data)
        if islink:
            i.type = tarfile.SYMTYPE
            i.mode = 0777
            i.linkname = data
            data = None
        else:
            i.mode = mode
            data = cStringIO.StringIO(data)
        self.z.addfile(i, data)

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

class tellable:
    '''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:
    '''write archive to zip file or stream.  can write uncompressed,
    or compressed with deflate.'''

    def __init__(self, dest, prefix, mtime, compress=True):
        self.prefix = tidyprefix(dest, prefix, ('.zip',))
        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)
        self.date_time = time.gmtime(mtime)[:6]

    def addfile(self, name, mode, islink, data):
        i = zipfile.ZipInfo(self.prefix + 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 = stat.S_IFREG
        if islink:
            mode = 0777
            ftype = stat.S_IFLNK
        i.external_attr = (mode | ftype) << 16L
        self.z.writestr(i, data)

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

class fileit:
    '''write archive as files in directory.'''

    def __init__(self, name, prefix, mtime):
        if prefix:
            raise util.Abort(_('cannot give prefix when archiving to files'))
        self.basedir = name
        self.opener = util.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, prefix, mtime: tarit(name, prefix, mtime, 'bz2'),
    'tgz': lambda name, prefix, mtime: tarit(name, prefix, mtime, 'gz'),
    'uzip': lambda name, prefix, mtime: zipit(name, prefix, mtime, False),
    'zip': zipit,
    }

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

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

    ctx = repo.changectx(node)
    archiver = archivers[kind](dest, prefix, mtime or ctx.date()[0])
    m = ctx.manifest()
    items = m.items()
    items.sort()
    write('.hg_archival.txt', 0644, False,
          lambda: 'repo: %s\nnode: %s\n' % (hex(repo.changelog.node(0)), hex(node)))
    for filename, filenode in items:
        write(filename, m.execf(filename) and 0755 or 0644, m.linkf(filename),
              lambda: repo.file(filename).read(filenode))
    archiver.done()