sapling/eden/scm/edenscm/mercurial/bundlerepo.py

674 lines
23 KiB
Python
Raw Normal View History

# Portions Copyright (c) Facebook, Inc. and its affiliates.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2.
# bundlerepo.py - repository class for viewing uncompressed bundles
#
# Copyright 2006, 2007 Benoit Boissinot <bboissin@gmail.com>
#
# 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.
"""Repository class for viewing uncompressed bundles.
This provides a read-only repository interface to bundles as if they
were part of the actual repository.
"""
2015-08-08 10:36:35 +03:00
from __future__ import absolute_import
import os
import shutil
import tempfile
from typing import IO, Any, Optional, Union
2015-08-08 10:36:35 +03:00
from . import (
bundle2,
changegroup,
changelog,
cmdutil,
discovery,
error,
exchange,
filelog,
localrepo,
manifest,
mdiff,
mutation,
node as nodemod,
2015-08-08 10:36:35 +03:00
pathutil,
phases,
pycompat,
2015-08-08 10:36:35 +03:00
revlog,
util,
vfs as vfsmod,
visibility,
2015-08-08 10:36:35 +03:00
)
from .i18n import _
from .node import nullid, nullrev
class bundlerevlog(revlog.revlog):
def __init__(self, opener, indexfile, cgunpacker, linkmapper):
# How it works:
# To retrieve a revision, we need to know the offset of the revision in
# the bundle (an unbundle object). We store this offset in the index
# (start). The base of the delta is stored in the base field.
#
# To differentiate a rev in the bundle from a rev in the revlog, we
# check revision against repotiprev.
opener = vfsmod.readonlyvfs(opener)
# bundlechangelog might have called revlog.revlog.__init__ already.
# avoid re-init the revlog.
if not util.safehasattr(self, "opener"):
index2 = indexfile.startswith("00changelog")
revlog.revlog.__init__(self, opener, indexfile, index2=index2)
inner = getattr(self, "inner", None)
index2 = getattr(self, "index2", None)
self.bundle = cgunpacker
n = len(self)
self.repotiprev = n - 1
self.bundlerevs = set() # used by 'bundle()' revset expression
self.bundleheads = set() # used by visibility
for deltadata in cgunpacker.deltaiter():
node, p1, p2, cs, deltabase, delta, flags = deltadata
2011-04-30 12:41:06 +04:00
size = len(delta)
start = cgunpacker.tell() - size
2011-04-30 12:41:06 +04:00
link = linkmapper(cs)
if node in self.nodemap:
2011-04-30 12:41:06 +04:00
# this can happen if two branches make the same change
self.bundlerevs.add(self.nodemap[node])
continue
2011-04-30 12:41:06 +04:00
for p in (p1, p2):
2012-05-12 18:00:57 +04:00
if p not in self.nodemap:
raise error.LookupError(p, self.indexfile, _("unknown parent"))
if deltabase not in self.nodemap:
raise LookupError(deltabase, self.indexfile, _("unknown delta base"))
baserev = self.rev(deltabase)
p1rev = self.rev(p1)
p2rev = self.rev(p2)
# start, size, full unc. size, base (unused), link, p1, p2, node
e = (
revlog.offset_type(start, flags),
size,
-1,
baserev,
link,
p1rev,
p2rev,
node,
)
if self.index is not None:
self.index.insert(-1, e)
if index2 is not None:
index2.insert(node, [p for p in (p1rev, p2rev) if p >= 0])
if inner is not None:
parentnodes = [p for p in (p1, p2) if p != nullid]
basetext = self.revision(deltabase)
text = mdiff.patches(basetext, [delta])
inner.addcommits([(node, parentnodes, bytes(text))])
self.nodemap[node] = n
self.bundlerevs.add(n)
self.bundleheads.add(n)
self.bundleheads.discard(p1rev)
self.bundleheads.discard(p2rev)
n += 1
def _chunk(self, rev, df=None):
# Warning: in case of bundle, the diff is against what we stored as
# delta base, not against rev - 1
# XXX: could use some caching
if rev <= self.repotiprev:
return revlog.revlog._chunk(self, rev)
self.bundle.seek(self.start(rev))
return self.bundle.read(self.length(rev))
def revdiff(self, rev1, rev2):
"""return or calculate a delta between two revisions"""
if rev1 > self.repotiprev and rev2 > self.repotiprev:
# hot path for bundle
revb = self.index[rev2][3]
if revb == rev1:
return self._chunk(rev2)
elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
return revlog.revlog.revdiff(self, rev1, rev2)
return mdiff.textdiff(
self.revision(rev1, raw=True), self.revision(rev2, raw=True)
)
def revision(self, nodeorrev, _df=None, raw=False):
# type: (Union[int, bytes], Optional[IO], bool) -> bytes
"""return an uncompressed revision of a given node or revision
number.
"""
if isinstance(nodeorrev, int):
rev = nodeorrev
node = self.node(rev)
else:
node = nodeorrev
rev = self.rev(node)
2010-01-25 09:05:27 +03:00
if node == nullid:
return b""
rawtext = None
chain = []
iterrev = rev
cache = self._cache
# reconstruct the revision if it is from a changegroup
while iterrev > self.repotiprev:
if cache is not None:
if cache[1] == iterrev:
rawtext = cache[2]
break
chain.append(iterrev)
iterrev = self.index[iterrev][3]
if rawtext is None:
rawtext = self.baserevision(iterrev)
while chain:
delta = self._chunk(chain.pop())
rawtext = mdiff.patches(rawtext, [delta])
text, validatehash = self._processflags(
rawtext, self.flags(rev), "read", raw=raw
)
revlog: flag processor Add the ability for revlog objects to process revision flags and apply registered transforms on read/write operations. This patch introduces: - the 'revlog._processflags()' method that looks at revision flags and applies flag processors registered on them. Due to the need to handle non-commutative operations, flag transforms are applied in stable order but the order in which the transforms are applied is reversed between read and write operations. - the 'addflagprocessor()' method allowing to register processors on flags. Flag processors are defined as a 3-tuple of (read, write, raw) functions to be applied depending on the operation being performed. - an update on 'revlog.addrevision()' behavior. The current flagprocessor design relies on extensions to wrap around 'addrevision()' to set flags on revision data, and on the flagprocessor to perform the actual transformation of its contents. In the lfs case, this means we need to process flags before we meet the 2GB size check, leading to performing some operations before it happens: - if flags are set on the revision data, we assume some extensions might be modifying the contents using the flag processor next, and we compute the node for the original revision data (still allowing extension to override the node by wrapping around 'addrevision()'). - we then invoke the flag processor to apply registered transforms (in lfs's case, drastically reducing the size of large blobs). - finally, we proceed with the 2GB size check. Note: In the case a cachedelta is passed to 'addrevision()' and we detect the flag processor modified the revision data, we chose to trust the flag processor and drop the cachedelta.
2017-01-10 19:15:21 +03:00
if validatehash:
self.checkhash(text, node, rev=rev)
self._cache = (node, rev, rawtext)
return text
def baserevision(self, nodeorrev):
# Revlog subclasses may override 'revision' method to modify format of
# content retrieved from revlog. To use bundlerevlog with such class one
# needs to override 'baserevision' and make more specific call here.
return revlog.revlog.revision(self, nodeorrev, raw=True)
def addrevision(self, *args, **kwargs):
raise NotImplementedError
def addgroup(self, *args, **kwargs):
raise NotImplementedError
def strip(self, *args, **kwargs):
raise NotImplementedError
def checksize(self):
raise NotImplementedError
class bundlechangelog(bundlerevlog, changelog.changelog):
def __init__(self, opener, cgunpacker, uiconfig):
changelog.changelog.__init__(self, opener, uiconfig)
2011-04-30 12:41:06 +04:00
linkmapper = lambda x: x
bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker, linkmapper)
self._visibleheads.addbundleheads([self.node(r) for r in self.bundleheads])
def baserevision(self, nodeorrev):
# Although changelog doesn't override 'revision' method, some extensions
# may replace this class with another that does. Same story with
# manifest and filelog classes.
return changelog.changelog.revision(self, nodeorrev, raw=True)
def revision(self, nodeorrev, raw=False):
if self.userust("revision"):
if nodeorrev in {nullid, nullrev}:
return b""
if isinstance(nodeorrev, int):
node = self.node(nodeorrev)
else:
node = nodeorrev
text = self.inner.getcommitrawtext(node)
if text is None:
raise error.LookupError(node, self.indexfile, _("no node"))
return text
else:
return super(bundlechangelog, self).revision(nodeorrev, raw)
def _loadvisibleheads(self, opener):
return visibility.bundlevisibleheads(opener)
class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
def __init__(self, opener, cgunpacker, linkmapper, dirlogstarts=None, dir=""):
manifest.manifestrevlog.__init__(self, opener, dir=dir)
bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker, linkmapper)
if dirlogstarts is None:
dirlogstarts = {}
if self.bundle.version == "03":
dirlogstarts = _getfilestarts(self.bundle)
self._dirlogstarts = dirlogstarts
self._linkmapper = linkmapper
def baserevision(self, nodeorrev):
node = nodeorrev
if isinstance(node, int):
node = self.node(node)
if node in self.fulltextcache:
result = b"%s" % self.fulltextcache[node]
else:
result = manifest.manifestrevlog.revision(self, nodeorrev, raw=True)
return result
def dirlog(self, d):
if d in self._dirlogstarts:
self.bundle.seek(self._dirlogstarts[d])
return bundlemanifest(
self.opener, self.bundle, self._linkmapper, self._dirlogstarts, dir=d
)
return super(bundlemanifest, self).dirlog(d)
class bundlefilelog(bundlerevlog, filelog.filelog):
def __init__(self, opener, path, cgunpacker, linkmapper):
filelog.filelog.__init__(self, opener, path)
bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker, linkmapper)
def baserevision(self, nodeorrev):
return filelog.filelog.revision(self, nodeorrev, raw=True)
class bundlepeer(localrepo.localpeer):
def canpush(self):
# type: () -> bool
return False
class bundlephasecache(phases.phasecache):
def __init__(self, *args, **kwargs):
super(bundlephasecache, self).__init__(*args, **kwargs)
if util.safehasattr(self, "opener"):
self.opener = vfsmod.readonlyvfs(self.opener)
def write(self):
raise NotImplementedError
def _write(self, fp):
raise NotImplementedError
def _updateroots(self, phase, newroots, tr):
self.phaseroots[phase] = newroots
self.invalidate()
self.dirty = True
def _getfilestarts(cgunpacker):
filespos = {}
for chunkdata in iter(cgunpacker.filelogheader, {}):
fname = chunkdata["filename"]
filespos[fname] = cgunpacker.tell()
for chunk in iter(lambda: cgunpacker.deltachunk(None), {}):
pass
return filespos
class bundlerepository(localrepo.localrepository):
"""A repository instance that is a union of a local repo and a bundle.
Instances represent a read-only repository composed of a local repository
with the contents of a bundle file applied. The repository instance is
conceptually similar to the state of a repository after an
``hg unbundle`` operation. However, the contents of the bundle are never
applied to the actual base repository.
"""
def __init__(self, ui, repopath, bundlepath):
self._tempparent = None
try:
localrepo.localrepository.__init__(self, ui, repopath)
except error.RepoError:
self._tempparent = tempfile.mkdtemp()
localrepo.instance(ui, self._tempparent, 1)
localrepo.localrepository.__init__(self, ui, self._tempparent)
self.ui.setconfig("phases", "publish", False, "bundlerepo")
if repopath:
self._url = "bundle:" + util.expandpath(repopath) + "+" + bundlepath
else:
self._url = "bundle:" + bundlepath
self.tempfile = None
f = util.posixfile(bundlepath, "rb")
bundle = exchange.readbundle(ui, f, bundlepath)
if isinstance(bundle, bundle2.unbundle20):
self._bundlefile = bundle
self._cgunpacker = None
cgpart = None
bundle2: don't use seekable bundle2 parts by default (issue5691) The last commit removed the last use of the bundle2 part seek() API in the generic bundle2 part iteration code. This means we can now switch to using unseekable bundle2 parts by default and have the special consumers that actually need the behavior request it. This commit changes unbundle20.iterparts() to expose non-seekable unbundlepart instances by default. If seekable parts are needed, callers can pass "seekable=True." The bundlerepo class needs seekable parts, so it does this. The interrupt handler is also changed to use a regular unbundlepart. So, by default, all consumers except bundlerepo will see unseekable parts. Because the behavior of the iterparts() benchmark changed, we add a variation to test seekable parts vs unseekable parts. And because parts no longer have seek() unless "seekable=True," we update the "part seek" benchmark. Speaking of benchmarks, this change has the following impact to `hg perfbundleread` on an uncompressed bundle of the Firefox repo (6,070,036,163 bytes): ! read(8k) ! wall 0.722709 comb 0.720000 user 0.150000 sys 0.570000 (best of 14) ! read(16k) ! wall 0.602208 comb 0.590000 user 0.080000 sys 0.510000 (best of 17) ! read(32k) ! wall 0.554018 comb 0.560000 user 0.050000 sys 0.510000 (best of 18) ! read(128k) ! wall 0.520086 comb 0.530000 user 0.020000 sys 0.510000 (best of 20) ! bundle2 forwardchunks() ! wall 2.996329 comb 3.000000 user 2.300000 sys 0.700000 (best of 4) ! bundle2 iterparts() ! wall 8.070791 comb 8.060000 user 7.180000 sys 0.880000 (best of 3) ! wall 6.983756 comb 6.980000 user 6.220000 sys 0.760000 (best of 3) ! bundle2 iterparts() seekable ! wall 8.132131 comb 8.110000 user 7.160000 sys 0.950000 (best of 3) ! bundle2 part seek() ! wall 10.370142 comb 10.350000 user 7.430000 sys 2.920000 (best of 3) ! wall 10.860942 comb 10.840000 user 7.790000 sys 3.050000 (best of 3) ! bundle2 part read(8k) ! wall 8.599892 comb 8.580000 user 7.720000 sys 0.860000 (best of 3) ! wall 7.258035 comb 7.260000 user 6.470000 sys 0.790000 (best of 3) ! bundle2 part read(16k) ! wall 8.265361 comb 8.250000 user 7.360000 sys 0.890000 (best of 3) ! wall 7.099891 comb 7.080000 user 6.310000 sys 0.770000 (best of 3) ! bundle2 part read(32k) ! wall 8.290308 comb 8.280000 user 7.330000 sys 0.950000 (best of 3) ! wall 6.964685 comb 6.950000 user 6.130000 sys 0.820000 (best of 3) ! bundle2 part read(128k) ! wall 8.204900 comb 8.150000 user 7.210000 sys 0.940000 (best of 3) ! wall 6.852867 comb 6.850000 user 6.060000 sys 0.790000 (best of 3) The significant speedup is due to not incurring the overhead to track payload offset data. Of course, this overhead is proportional to bundle2 part size. So a multiple gigabyte changegroup part is on the extreme side of the spectrum for real-world impact. In addition to the CPU efficiency wins, not tracking offset data also means not using memory to hold that data. Using a bundle based on the example BSD repository in issue 5691, this change has a drastic impact to memory usage during `hg unbundle` (`hg clone` would behave similarly). Before, memory usage incrementally increased for the duration of bundle processing. In other words, as we advanced through the changegroup and bundle2 part, we kept allocating more memory to hold offset data. After this change, we still increase memory during changegroup application. But the rate of increase is significantly slower. (A bulk of the remaining gradual increase appears to be the storing of revlog sizes in the transaction object to facilitate rollback.) The RSS at the end of filelog application is as follows: Before: ~752 MB After: ~567 MB So, we were storing ~185 MB of offset data that we never even used. Talk about wasteful! .. api:: bundle2 parts are no longer seekable by default. .. perf:: bundle2 read I/O throughput significantly increased. .. perf:: Significant memory use reductions when reading from bundle2 bundles. On the BSD repository, peak RSS during changegroup application decreased by ~185 MB from ~752 MB to ~567 MB. Differential Revision: https://phab.mercurial-scm.org/D1390
2017-11-14 08:10:37 +03:00
for part in bundle.iterparts(seekable=True):
if part.type == "changegroup":
if cgpart:
raise NotImplementedError(
"can't process " "multiple changegroups"
)
cgpart = part
self._handlebundle2part(bundle, part)
if not cgpart:
raise error.Abort(_("No changegroups found"))
# This is required to placate a later consumer, which expects
# the payload offset to be at the beginning of the changegroup.
# We need to do this after the iterparts() generator advances
# because iterparts() will seek to end of payload after the
# generator returns control to iterparts().
cgpart.seek(0, os.SEEK_SET)
elif isinstance(bundle, changegroup.cg1unpacker):
if bundle.compressed():
f = self._writetempbundle(bundle.read, ".hg10un", header="HG10UN")
bundle = exchange.readbundle(ui, f, bundlepath, self.localvfs)
self._bundlefile = bundle
self._cgunpacker = bundle
else:
raise error.Abort(_("bundle type %s cannot be read") % type(bundle))
# dict with the mapping 'filename' -> position in the changegroup.
self._cgfilespos = {}
self.firstnewrev = self.changelog.repotiprev + 1
phases.retractboundary(
self, None, phases.draft, [ctx.node() for ctx in self[self.firstnewrev :]]
)
def _handlebundle2part(self, bundle, part):
if part.type != "changegroup":
return
cgstream = part
version = part.params.get("version", "01")
legalcgvers = changegroup.supportedincomingversions(self)
if version not in legalcgvers:
msg = _("Unsupported changegroup version: %s")
raise error.Abort(msg % version)
cgstream = self._writetempbundle(part.read, ".cg%sun" % version)
self._cgunpacker = changegroup.getunbundler(version, cgstream, "UN")
def _writetempbundle(self, readfn, suffix, header=""):
"""Write a temporary file to disk
"""
fdtemp, temp = self.localvfs.mkstemp(prefix="hg-bundle-", suffix=suffix)
self.tempfile = temp
with util.fdopen(fdtemp, "wb") as fptemp:
fptemp.write(pycompat.encodeutf8(header))
while True:
chunk = readfn(2 ** 18)
if not chunk:
break
fptemp.write(chunk)
return self.localvfs.open(self.tempfile, mode="rb")
@util.propertycache
def _phasecache(self):
return bundlephasecache(self, self._phasedefaults)
@util.propertycache
def _mutationstore(self):
return mutation.bundlemutationstore(self)
@util.propertycache
2009-04-30 05:47:15 +04:00
def changelog(self):
# consume the header if it exists
self._cgunpacker.changelogheader()
c = bundlechangelog(self.svfs, self._cgunpacker, self.ui.uiconfig())
self.manstart = self._cgunpacker.tell()
2009-04-30 05:47:15 +04:00
return c
@util.propertycache
def manifestlog(self):
return super(bundlerepository, self).manifestlog
def _constructmanifest(self):
self._cgunpacker.seek(self.manstart)
# consume the header if it exists
self._cgunpacker.manifestheader()
linkmapper = self.changelog.rev
m = bundlemanifest(self.svfs, self._cgunpacker, linkmapper)
self.filestart = self._cgunpacker.tell()
2009-04-30 05:47:15 +04:00
return m
def _consumemanifest(self):
"""Consumes the manifest portion of the bundle, setting filestart so the
file portion can be read."""
self._cgunpacker.seek(self.manstart)
self._cgunpacker.manifestheader()
for delta in self._cgunpacker.deltaiter():
pass
# Changegroup v3 supports additional manifest entries that we need to
# skip.
if self._cgunpacker.version == "03":
for chunkdata in iter(self._cgunpacker.filelogheader, {}):
# If we get here, there are directory manifests in the changegroup
for delta in self._cgunpacker.deltaiter():
pass
self.filestart = self._cgunpacker.tell()
@util.propertycache
2009-04-30 05:47:15 +04:00
def manstart(self):
self.changelog
return self.manstart
@util.propertycache
2009-04-30 05:47:15 +04:00
def filestart(self):
self.manifestlog
# If filestart was not set by self.manifestlog, that means the
# manifestlog implementation did not consume the manifests from the
# changegroup (ex: it might be consuming trees from a separate bundle2
# part instead). So we need to manually consume it.
if "filestart" not in self.__dict__:
self._consumemanifest()
2009-04-30 05:47:15 +04:00
return self.filestart
def url(self):
# type: () -> str
return self._url
def file(self, f):
# type: () -> filelog.filelog
if not self._cgfilespos:
self._cgunpacker.seek(self.filestart)
self._cgfilespos = _getfilestarts(self._cgunpacker)
if f in self._cgfilespos:
self._cgunpacker.seek(self._cgfilespos[f])
linkmapper = self.changelog.rev
return bundlefilelog(self.svfs, f, self._cgunpacker, linkmapper)
else:
return filelog.filelog(self.svfs, f)
2010-09-21 01:14:05 +04:00
def close(self):
# type: () -> None
2010-09-21 01:14:05 +04:00
"""Close assigned bundle file immediately."""
self._bundlefile.close()
if self.tempfile is not None:
self.localvfs.unlink(self.tempfile)
path = self._tempparent
if path is not None:
shutil.rmtree(path, True)
2008-03-20 19:12:35 +03:00
def cancopy(self):
# type: () -> bool
2008-03-20 19:12:35 +03:00
return False
def peer(self):
# type: () -> localrepo.localpeer
return bundlepeer(self)
def getcwd(self):
# type: () -> str
return pycompat.getcwd() # always outside the repo
# Check if parents exist in localrepo before setting
def setparents(self, p1, p2=nullid):
# type: (bytes, bytes) -> None
p1rev = self.changelog.rev(p1)
p2rev = self.changelog.rev(p2)
msg = _("setting parent to node %s that only exists in the bundle\n")
if self.changelog.repotiprev < p1rev:
self.ui.warn(msg % nodemod.hex(p1))
if self.changelog.repotiprev < p2rev:
self.ui.warn(msg % nodemod.hex(p2))
return super(bundlerepository, self).setparents(p1, p2)
def instance(ui, path, create):
if create:
raise error.Abort(_("cannot create new bundle repository"))
# internal config: bundle.mainreporoot
parentpath = ui.config("bundle", "mainreporoot")
if not parentpath:
# try to find the correct path to the working directory repo
parentpath = cmdutil.findrepo(pycompat.getcwd())
if parentpath is None:
parentpath = ""
if parentpath:
# Try to make the full path relative so we get a nice, short URL.
# In particular, we don't want temp dir names in test outputs.
cwd = pycompat.getcwd()
if parentpath == cwd:
parentpath = ""
else:
cwd = pathutil.normasprefix(cwd)
if parentpath.startswith(cwd):
parentpath = parentpath[len(cwd) :]
u = util.url(path)
url: refactor util.drop_scheme() and hg.localpath() into url.localpath() This replaces util.drop_scheme() with url.localpath(), using url.url for parsing instead of doing it on its own. The function is moved from util to url to avoid an import cycle. hg.localpath() is removed in favor of using url.localpath(). This provides more consistent behavior between "hg clone" and other commands. To preserve backwards compatibility, URLs like bundle://../foo still refer to ../foo, not /foo. If a URL contains a scheme, percent-encoded entities are decoded. When there's no scheme, all characters are left untouched. Comparison of old and new behaviors: URL drop_scheme() hg.localpath() url.localpath() === ============= ============== =============== file://foo/foo /foo foo/foo /foo file://localhost:80/foo /foo localhost:80/foo /foo file://localhost:/foo /foo localhost:/foo /foo file://localhost/foo /foo /foo /foo file:///foo /foo /foo /foo file://foo (empty string) foo / file:/foo /foo /foo /foo file:foo foo foo foo file:foo%23bar foo%23bar foo%23bar foo#bar foo%23bar foo%23bar foo%23bar foo%23bar /foo /foo /foo /foo Windows-related paths on Windows: URL drop_scheme() hg.localpath() url.localpath() === ============= ============== =============== file:///C:/foo C:/C:/foo /C:/foo C:/foo file:///D:/foo C:/D:/foo /D:/foo D:/foo file://C:/foo C:/foo C:/foo C:/foo file://D:/foo C:/foo D:/foo D:/foo file:////foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar \\foo\bar //foo/bar //foo/bar \\foo\bar Windows-related paths on other platforms: file:///C:/foo C:/C:/foo /C:/foo C:/foo file:///D:/foo C:/D:/foo /D:/foo D:/foo file://C:/foo C:/foo C:/foo C:/foo file://D:/foo C:/foo D:/foo D:/foo file:////foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar //foo/bar \\foo\bar //foo/bar //foo/bar \\foo\bar For more information about file:// URL handling, see: http://www-archive.mozilla.org/quality/networking/testing/filetests.html Related issues: - issue1153: File URIs aren't handled correctly in windows This patch should preserve the fix implemented in 5c92d05b064e. However, it goes a step further and "promotes" Windows-style drive letters from being interpreted as host names to being part of the path. - issue2154: Cannot escape '#' in Mercurial URLs (#1172 in THG) The fragment is still interpreted as a revision or a branch, even in paths to bundles. However, when file: is used, percent-encoded entities are decoded, so file:test%23bundle.hg can refer to test#bundle.hg ond isk.
2011-03-31 07:03:05 +04:00
path = u.localpath()
if u.scheme == "bundle":
s = path.split("+", 1)
if len(s) == 1:
repopath, bundlename = parentpath, s[0]
else:
repopath, bundlename = s
else:
repopath, bundlename = parentpath, path
return bundlerepository(ui, repopath, bundlename)
class bundletransactionmanager(object):
def transaction(self):
return None
def close(self):
raise NotImplementedError
def release(self):
raise NotImplementedError
def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None, force=False):
"""obtains a bundle of changes incoming from other
"onlyheads" restricts the returned changes to those reachable from the
specified heads.
"bundlename", if given, stores the bundle to this file path permanently;
otherwise it's stored to a temp file and gets deleted again when you call
the returned "cleanupfn".
"force" indicates whether to proceed on unrelated repos.
Returns a tuple (local, csets, cleanupfn):
2012-05-12 17:54:54 +04:00
"local" is a local repo from which to obtain the actual incoming
changesets; it is a bundlerepo for the obtained bundle when the
original "other" is remote.
"csets" lists the incoming changeset node ids.
2012-05-12 17:54:54 +04:00
"cleanupfn" must be called without arguments when you're done processing
the changes; it closes both the original "other" and the one returned
here.
"""
tmp = discovery.findcommonincoming(repo, other, heads=onlyheads, force=force)
common, incoming, rheads = tmp
if not incoming:
try:
if bundlename:
os.unlink(bundlename)
2011-04-23 01:51:25 +04:00
except OSError:
pass
return repo, [], other.close
commonset = set(common)
rheads = [x for x in rheads if x not in commonset]
bundle = None
bundlerepo = None
localrepo = other.local()
if bundlename or not localrepo:
# create a bundle (uncompressed if other repo is not local)
# developer config: devel.legacy.exchange
legexc = ui.configlist("devel", "legacy.exchange")
forcebundle1 = "bundle2" not in legexc and "bundle1" in legexc
canbundle2 = (
not forcebundle1 and other.capable("getbundle") and other.capable("bundle2")
)
if canbundle2:
kwargs = {}
kwargs[r"common"] = common
kwargs[r"heads"] = rheads
kwargs[r"bundlecaps"] = exchange.caps20to10(repo)
kwargs[r"cg"] = True
b2 = other.getbundle("incoming", **kwargs)
fname = bundle = changegroup.writechunks(
ui, b2._forwardchunks(), bundlename
)
else:
if other.capable("getbundle"):
cg = other.getbundle("incoming", common=common, heads=rheads)
elif onlyheads is None and not other.capable("changegroupsubset"):
# compat with older servers when pulling all remote heads
cg = other.changegroup(incoming, "incoming")
rheads = None
else:
cg = other.changegroupsubset(incoming, rheads, "incoming")
if localrepo:
bundletype = "HG10BZ"
else:
bundletype = "HG10UN"
fname = bundle = bundle2.writebundle(ui, cg, bundlename, bundletype)
# keep written bundle?
if bundlename:
bundle = None
if not localrepo:
# use the created uncompressed bundlerepo
localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root, fname)
# this repo contains local and other now, so filter out local again
common = repo.heads()
csets = localrepo.changelog.findmissing(common, rheads)
if bundlerepo:
reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev :]]
remotephases = other.listkeys("phases")
pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
pullop.trmanager = bundletransactionmanager()
exchange._pullapplyphases(pullop, remotephases)
def cleanup():
if bundlerepo:
bundlerepo.close()
if bundle:
os.unlink(bundle)
other.close()
return (localrepo, csets, cleanup)