view mercurial/archival.py @ 29304:5e32852fa4bd

revset: make filteredset.__nonzero__ respect the order of the filteredset

This fix allows __nonzero__ to respect the direction of iteration of the
whole filteredset. Here's the case when it matters. Imagine that we have a
very large repository and we want to execute a command like:

    $ hg log --rev '(tip:0) and user(ikostia)' --limit 1

(we want to get the latest commit by me).

Mercurial will evaluate a filteredset lazy data structure, an
instance of the filteredset class, which will know that it has to iterate
in a descending order (isdescending() will return True if called). This
means that when some code iterates over the instance of this filteredset,
the 'and user(ikostia)' condition will be first checked on the latest
revision, then on the second latest and so on, allowing Mercurial to
print matches as it founds them. However, cmdutil.getgraphlogrevs
contains the following code:

    revs = _logrevs(repo, opts)
    if not revs:
        return revset.baseset(), None, None

The "not revs" expression is evaluated by calling filteredset.__nonzero__,
which in its current implementation will try to iterate the filteredset
in ascending order until it finds a revision that matches the 'and user(..'
condition. If the condition is only true on late revisions, a lot of
useless iterations will be done. These iterations could be avoided if
__nonzero__ followed the order of the filteredset, which in my opinion
is a sensible thing to do here.

The problem gets even worse when instead of 'user(ikostia)' some more
expensive check is performed, like grepping the commit diff.


I tested this fix on a very large repo where tip is my commit and my very
first commit comes fairly late in the revision history. Results of timing
of the above command on that very large repo.

-with my fix:
real    0m1.795s
user    0m1.657s
sys     0m0.135s

-without my fix:
real    1m29.245s
user    1m28.223s
sys     0m0.929s

I understand that this is a very specific kind of problem that presents
itself very rarely, only on very big repositories and with expensive
checks and so on. But I don't see any disadvantages to this kind of fix
either.

# 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 __future__ import absolute_import

import gzip
import os
import struct
import tarfile
import time
import zipfile
import zlib

from .i18n import _

from . import (
    cmdutil,
    encoding,
    error,
    match as matchmod,
    scmutil,
    util,
)
stringio = util.stringio

# from unzip source code:
_UNX_IFREG = 0x8000
_UNX_IFLNK = 0xa000

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 += '/'
    # Drop the leading '.' path component if present, so Windows can read the
    # zip files (issue4634)
    if prefix.startswith('./'):
        prefix = prefix[2:]
    if prefix.startswith('../') or os.path.isabs(lpfx) or '/../' in prefix:
        raise error.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 any(dest.endswith(ext) for ext in extensions):
            return kind
    return None

def _rootctx(repo):
    # repo[0] may be hidden
    for rev in repo:
        return repo[rev]
    return repo['null']

def buildmetadata(ctx):
    '''build content of .hg_archival.txt'''
    repo = ctx.repo()
    hex = ctx.hex()
    if ctx.rev() is None:
        hex = ctx.p1().hex()
        if ctx.dirty():
            hex += '+'

    base = 'repo: %s\nnode: %s\nbranch: %s\n' % (
        _rootctx(repo).hex(), hex, 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}\n'
                            '{changessincelatesttag}',
                'style': '', 'patch': None, 'git': None}
        cmdutil.show_changeset(repo.ui, repo, opts).show(ctx)
        ltags, dist, changessince = repo.ui.popbuffer().split('\n')
        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

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
            fname = self.name
            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:
                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 = 0o777
            i.linkname = data
            data = None
            i.size = 0
        else:
            i.mode = mode
            data = 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.mtime = mtime
        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 = _UNX_IFREG
        if islink:
            mode = 0o777
            ftype = _UNX_IFLNK
        i.external_attr = (mode | ftype) << 16L
        # 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"
                               int(self.mtime)) # last modification (UTC)
        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.close()
        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='', 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 error.Abort(_('cannot give prefix when archiving to files'))
    else:
        prefix = tidyprefix(dest, kind, prefix)

    def write(name, mode, islink, getdata):
        data = getdata()
        if decode:
            data = repo.wwritedata(name, data)
        archiver.addfile(prefix + name, mode, islink, data)

    if kind not in archivers:
        raise error.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):
        name = '.hg_archival.txt'
        if not matchfn or matchfn(name):
            write(name, 0o644, False, lambda: buildmetadata(ctx))

    if matchfn:
        files = [f for f in ctx.manifest().keys() if matchfn(f)]
    else:
        files = ctx.manifest().keys()
    total = len(files)
    if total:
        files.sort()
        repo.ui.progress(_('archiving'), 0, unit=_('files'), total=total)
        for i, f in enumerate(files):
            ff = ctx.flags(f)
            write(f, 'x' in ff and 0o755 or 0o644, '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 sorted(ctx.substate):
            sub = ctx.workingsub(subpath)
            submatch = matchmod.subdirmatcher(subpath, matchfn)
            total += sub.archive(archiver, prefix, submatch)

    if total == 0:
        raise error.Abort(_('no files match the archive pattern'))

    archiver.done()
    return total