shallowutil: introduce a helper function isenabled()

This patch introduces a inenabled() function which will check whether
remotefilelog is enabled or not. The function is then also used at all the
places where check whether remotefilelog is enabled or not. The new function
makes code easy to read without need to understand what is the constant involved
and why we are checking repo.requirements.

Differential Revision: https://phab.mercurial-scm.org/D5190

hgext/remotefilelog/__init__.py

@@ -1,1103 +1,1102 b''
 # __init__.py - remotefilelog extension
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """remotefilelog causes Mercurial to lazilly fetch file contents (EXPERIMENTAL)
 
 This extension is HIGHLY EXPERIMENTAL. There are NO BACKWARDS COMPATIBILITY
 GUARANTEES. This means that repositories created with this extension may
 only be usable with the exact version of this extension/Mercurial that was
 used. The extension attempts to enforce this in order to prevent repository
 corruption.
 
 remotefilelog works by fetching file contents lazily and storing them
 in a cache on the client rather than in revlogs. This allows enormous
 histories to be transferred only partially, making them easier to
 operate on.
 
 Configs:
 
     ``packs.maxchainlen`` specifies the maximum delta chain length in pack files
     ``packs.maxpacksize`` specifies the maximum pack file size
     ``packs.maxpackfilecount`` specifies the maximum number of packs in the
       shared cache (trees only for now)
     ``remotefilelog.backgroundprefetch`` runs prefetch in background when True
     ``remotefilelog.bgprefetchrevs`` specifies revisions to fetch on commit and
       update, and on other commands that use them. Different from pullprefetch.
     ``remotefilelog.gcrepack`` does garbage collection during repack when True
     ``remotefilelog.nodettl`` specifies maximum TTL of a node in seconds before
       it is garbage collected
     ``remotefilelog.repackonhggc`` runs repack on hg gc when True
     ``remotefilelog.prefetchdays`` specifies the maximum age of a commit in
       days after which it is no longer prefetched.
     ``remotefilelog.prefetchdelay`` specifies delay between background
       prefetches in seconds after operations that change the working copy parent
     ``remotefilelog.data.gencountlimit`` constraints the minimum number of data
       pack files required to be considered part of a generation. In particular,
       minimum number of packs files > gencountlimit.
     ``remotefilelog.data.generations`` list for specifying the lower bound of
       each generation of the data pack files. For example, list ['100MB','1MB']
       or ['1MB', '100MB'] will lead to three generations: [0, 1MB), [
       1MB, 100MB) and [100MB, infinity).
     ``remotefilelog.data.maxrepackpacks`` the maximum number of pack files to
       include in an incremental data repack.
     ``remotefilelog.data.repackmaxpacksize`` the maximum size of a pack file for
       it to be considered for an incremental data repack.
     ``remotefilelog.data.repacksizelimit`` the maximum total size of pack files
       to include in an incremental data repack.
     ``remotefilelog.history.gencountlimit`` constraints the minimum number of
       history pack files required to be considered part of a generation. In
       particular, minimum number of packs files > gencountlimit.
     ``remotefilelog.history.generations`` list for specifying the lower bound of
       each generation of the historhy pack files. For example, list [
       '100MB', '1MB'] or ['1MB', '100MB'] will lead to three generations: [
       0, 1MB), [1MB, 100MB) and [100MB, infinity).
     ``remotefilelog.history.maxrepackpacks`` the maximum number of pack files to
       include in an incremental history repack.
     ``remotefilelog.history.repackmaxpacksize`` the maximum size of a pack file
       for it to be considered for an incremental history repack.
     ``remotefilelog.history.repacksizelimit`` the maximum total size of pack
       files to include in an incremental history repack.
     ``remotefilelog.backgroundrepack`` automatically consolidate packs in the
       background
     ``remotefilelog.cachepath`` path to cache
     ``remotefilelog.cachegroup`` if set, make cache directory sgid to this
       group
     ``remotefilelog.cacheprocess`` binary to invoke for fetching file data
     ``remotefilelog.debug`` turn on remotefilelog-specific debug output
     ``remotefilelog.excludepattern`` pattern of files to exclude from pulls
     ``remotefilelog.includepattern``pattern of files to include in pulls
     ``remotefilelog.fetchwarning``: message to print when too many
       single-file fetches occur
     ``remotefilelog.getfilesstep`` number of files to request in a single RPC
     ``remotefilelog.getfilestype`` if set to 'threaded' use threads to fetch
       files, otherwise use optimistic fetching
     ``remotefilelog.pullprefetch`` revset for selecting files that should be
       eagerly downloaded rather than lazily
     ``remotefilelog.reponame`` name of the repo. If set, used to partition
       data from other repos in a shared store.
     ``remotefilelog.server`` if true, enable server-side functionality
     ``remotefilelog.servercachepath`` path for caching blobs on the server
     ``remotefilelog.serverexpiration`` number of days to keep cached server
       blobs
     ``remotefilelog.validatecache`` if set, check cache entries for corruption
       before returning blobs
     ``remotefilelog.validatecachelog`` if set, check cache entries for
       corruption before returning metadata
 
 """
 from __future__ import absolute_import
 
 import os
 import time
 import traceback
 
 from mercurial.node import hex
 from mercurial.i18n import _
 from mercurial import (
     changegroup,
     changelog,
     cmdutil,
     commands,
     configitems,
     context,
     copies,
     debugcommands as hgdebugcommands,
     dispatch,
     error,
     exchange,
     extensions,
     hg,
     localrepo,
     match,
     merge,
     node as nodemod,
     patch,
     registrar,
     repair,
     repoview,
     revset,
     scmutil,
     smartset,
     streamclone,
     templatekw,
     util,
 )
 from . import (
     constants,
     debugcommands,
     fileserverclient,
     remotefilectx,
     remotefilelog,
     remotefilelogserver,
     repack as repackmod,
     shallowbundle,
     shallowrepo,
     shallowstore,
     shallowutil,
     shallowverifier,
 )
 
 # ensures debug commands are registered
 hgdebugcommands.command
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('remotefilelog', 'debug', default=False)
 
 configitem('remotefilelog', 'reponame', default='')
 configitem('remotefilelog', 'cachepath', default=None)
 configitem('remotefilelog', 'cachegroup', default=None)
 configitem('remotefilelog', 'cacheprocess', default=None)
 configitem('remotefilelog', 'cacheprocess.includepath', default=None)
 configitem("remotefilelog", "cachelimit", default="1000 GB")
 
 configitem('remotefilelog', 'fallbackpath', default=configitems.dynamicdefault,
            alias=[('remotefilelog', 'fallbackrepo')])
 
 configitem('remotefilelog', 'validatecachelog', default=None)
 configitem('remotefilelog', 'validatecache', default='on')
 configitem('remotefilelog', 'server', default=None)
 configitem('remotefilelog', 'servercachepath', default=None)
 configitem("remotefilelog", "serverexpiration", default=30)
 configitem('remotefilelog', 'backgroundrepack', default=False)
 configitem('remotefilelog', 'bgprefetchrevs', default=None)
 configitem('remotefilelog', 'pullprefetch', default=None)
 configitem('remotefilelog', 'backgroundprefetch', default=False)
 configitem('remotefilelog', 'prefetchdelay', default=120)
 configitem('remotefilelog', 'prefetchdays', default=14)
 
 configitem('remotefilelog', 'getfilesstep', default=10000)
 configitem('remotefilelog', 'getfilestype', default='optimistic')
 configitem('remotefilelog', 'batchsize', configitems.dynamicdefault)
 configitem('remotefilelog', 'fetchwarning', default='')
 
 configitem('remotefilelog', 'includepattern', default=None)
 configitem('remotefilelog', 'excludepattern', default=None)
 
 configitem('remotefilelog', 'gcrepack', default=False)
 configitem('remotefilelog', 'repackonhggc', default=False)
 configitem('remotefilelog', 'datapackversion', default=0)
 configitem('repack', 'chainorphansbysize', default=True)
 
 configitem('packs', 'maxpacksize', default=0)
 configitem('packs', 'maxchainlen', default=1000)
 
 configitem('remotefilelog', 'historypackv1', default=False)
 #  default TTL limit is 30 days
 _defaultlimit = 60 * 60 * 24 * 30
 configitem('remotefilelog', 'nodettl', default=_defaultlimit)
 
 configitem('remotefilelog', 'data.gencountlimit', default=2),
 configitem('remotefilelog', 'data.generations',
            default=['1GB', '100MB', '1MB'])
 configitem('remotefilelog', 'data.maxrepackpacks', default=50)
 configitem('remotefilelog', 'data.repackmaxpacksize', default='4GB')
 configitem('remotefilelog', 'data.repacksizelimit', default='100MB')
 
 configitem('remotefilelog', 'history.gencountlimit', default=2),
 configitem('remotefilelog', 'history.generations', default=['100MB'])
 configitem('remotefilelog', 'history.maxrepackpacks', default=50)
 configitem('remotefilelog', 'history.repackmaxpacksize', default='400MB')
 configitem('remotefilelog', 'history.repacksizelimit', default='100MB')
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 repoclass = localrepo.localrepository
 repoclass._basesupported.add(constants.SHALLOWREPO_REQUIREMENT)
 
+isenabled = shallowutil.isenabled
+
 def uisetup(ui):
     """Wraps user facing Mercurial commands to swap them out with shallow
     versions.
     """
     hg.wirepeersetupfuncs.append(fileserverclient.peersetup)
 
     entry = extensions.wrapcommand(commands.table, 'clone', cloneshallow)
     entry[1].append(('', 'shallow', None,
                      _("create a shallow clone which uses remote file "
                        "history")))
 
     extensions.wrapcommand(commands.table, 'debugindex',
         debugcommands.debugindex)
     extensions.wrapcommand(commands.table, 'debugindexdot',
         debugcommands.debugindexdot)
     extensions.wrapcommand(commands.table, 'log', log)
     extensions.wrapcommand(commands.table, 'pull', pull)
 
     # Prevent 'hg manifest --all'
     def _manifest(orig, ui, repo, *args, **opts):
-        if (constants.SHALLOWREPO_REQUIREMENT in repo.requirements
-            and opts.get('all')):
+        if (isenabled(repo) and opts.get('all')):
             raise error.Abort(_("--all is not supported in a shallow repo"))
 
         return orig(ui, repo, *args, **opts)
     extensions.wrapcommand(commands.table, "manifest", _manifest)
 
     # Wrap remotefilelog with lfs code
     def _lfsloaded(loaded=False):
         lfsmod = None
         try:
             lfsmod = extensions.find('lfs')
         except KeyError:
             pass
         if lfsmod:
             lfsmod.wrapfilelog(remotefilelog.remotefilelog)
             fileserverclient._lfsmod = lfsmod
     extensions.afterloaded('lfs', _lfsloaded)
 
     # debugdata needs remotefilelog.len to work
     extensions.wrapcommand(commands.table, 'debugdata', debugdatashallow)
 
 def cloneshallow(orig, ui, repo, *args, **opts):
     if opts.get('shallow'):
         repos = []
         def pull_shallow(orig, self, *args, **kwargs):
-            if constants.SHALLOWREPO_REQUIREMENT not in self.requirements:
+            if not isenabled(self):
                 repos.append(self.unfiltered())
                 # set up the client hooks so the post-clone update works
                 setupclient(self.ui, self.unfiltered())
 
                 # setupclient fixed the class on the repo itself
                 # but we also need to fix it on the repoview
                 if isinstance(self, repoview.repoview):
                     self.__class__.__bases__ = (self.__class__.__bases__[0],
                                                 self.unfiltered().__class__)
                 self.requirements.add(constants.SHALLOWREPO_REQUIREMENT)
                 self._writerequirements()
 
                 # Since setupclient hadn't been called, exchange.pull was not
                 # wrapped. So we need to manually invoke our version of it.
                 return exchangepull(orig, self, *args, **kwargs)
             else:
                 return orig(self, *args, **kwargs)
         extensions.wrapfunction(exchange, 'pull', pull_shallow)
 
         # Wrap the stream logic to add requirements and to pass include/exclude
         # patterns around.
         def setup_streamout(repo, remote):
             # Replace remote.stream_out with a version that sends file
             # patterns.
             def stream_out_shallow(orig):
                 caps = remote.capabilities()
                 if constants.NETWORK_CAP_LEGACY_SSH_GETFILES in caps:
                     opts = {}
                     if repo.includepattern:
                         opts['includepattern'] = '\0'.join(repo.includepattern)
                     if repo.excludepattern:
                         opts['excludepattern'] = '\0'.join(repo.excludepattern)
                     return remote._callstream('stream_out_shallow', **opts)
                 else:
                     return orig()
             extensions.wrapfunction(remote, 'stream_out', stream_out_shallow)
         def stream_wrap(orig, op):
             setup_streamout(op.repo, op.remote)
             return orig(op)
         extensions.wrapfunction(
             streamclone, 'maybeperformlegacystreamclone', stream_wrap)
 
         def canperformstreamclone(orig, pullop, bundle2=False):
             # remotefilelog is currently incompatible with the
             # bundle2 flavor of streamclones, so force us to use
             # v1 instead.
             if 'v2' in pullop.remotebundle2caps.get('stream', []):
                 pullop.remotebundle2caps['stream'] = [
                     c for c in pullop.remotebundle2caps['stream']
                     if c != 'v2']
             if bundle2:
                 return False, None
             supported, requirements = orig(pullop, bundle2=bundle2)
             if requirements is not None:
                 requirements.add(constants.SHALLOWREPO_REQUIREMENT)
             return supported, requirements
         extensions.wrapfunction(
             streamclone, 'canperformstreamclone', canperformstreamclone)
 
     try:
         orig(ui, repo, *args, **opts)
     finally:
         if opts.get('shallow'):
             for r in repos:
                 if util.safehasattr(r, 'fileservice'):
                     r.fileservice.close()
 
 def debugdatashallow(orig, *args, **kwds):
     oldlen = remotefilelog.remotefilelog.__len__
     try:
         remotefilelog.remotefilelog.__len__ = lambda x: 1
         return orig(*args, **kwds)
     finally:
         remotefilelog.remotefilelog.__len__ = oldlen
 
 def reposetup(ui, repo):
     if not isinstance(repo, localrepo.localrepository):
         return
 
     # put here intentionally bc doesnt work in uisetup
     ui.setconfig('hooks', 'update.prefetch', wcpprefetch)
     ui.setconfig('hooks', 'commit.prefetch', wcpprefetch)
 
     isserverenabled = ui.configbool('remotefilelog', 'server')
-    isshallowclient = constants.SHALLOWREPO_REQUIREMENT in repo.requirements
+    isshallowclient = isenabled(repo)
 
     if isserverenabled and isshallowclient:
         raise RuntimeError("Cannot be both a server and shallow client.")
 
     if isshallowclient:
         setupclient(ui, repo)
 
     if isserverenabled:
         remotefilelogserver.setupserver(ui, repo)
 
 def setupclient(ui, repo):
     if not isinstance(repo, localrepo.localrepository):
         return
 
     # Even clients get the server setup since they need to have the
     # wireprotocol endpoints registered.
     remotefilelogserver.onetimesetup(ui)
     onetimeclientsetup(ui)
 
     shallowrepo.wraprepo(repo)
     repo.store = shallowstore.wrapstore(repo.store)
 
 clientonetime = False
 def onetimeclientsetup(ui):
     global clientonetime
     if clientonetime:
         return
     clientonetime = True
 
     changegroup.cgpacker = shallowbundle.shallowcg1packer
 
     extensions.wrapfunction(changegroup, '_addchangegroupfiles',
                             shallowbundle.addchangegroupfiles)
     extensions.wrapfunction(
         changegroup, 'makechangegroup', shallowbundle.makechangegroup)
 
     def storewrapper(orig, requirements, path, vfstype):
         s = orig(requirements, path, vfstype)
         if constants.SHALLOWREPO_REQUIREMENT in requirements:
             s = shallowstore.wrapstore(s)
 
         return s
     extensions.wrapfunction(localrepo, 'makestore', storewrapper)
 
     extensions.wrapfunction(exchange, 'pull', exchangepull)
 
     # prefetch files before update
     def applyupdates(orig, repo, actions, wctx, mctx, overwrite, labels=None):
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             manifest = mctx.manifest()
             files = []
             for f, args, msg in actions['g']:
                 files.append((f, hex(manifest[f])))
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(files)
         return orig(repo, actions, wctx, mctx, overwrite, labels=labels)
     extensions.wrapfunction(merge, 'applyupdates', applyupdates)
 
     # Prefetch merge checkunknownfiles
     def checkunknownfiles(orig, repo, wctx, mctx, force, actions,
                           *args, **kwargs):
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             files = []
             sparsematch = repo.maybesparsematch(mctx.rev())
             for f, (m, actionargs, msg) in actions.iteritems():
                 if sparsematch and not sparsematch(f):
                     continue
                 if m in ('c', 'dc', 'cm'):
                     files.append((f, hex(mctx.filenode(f))))
                 elif m == 'dg':
                     f2 = actionargs[0]
                     files.append((f2, hex(mctx.filenode(f2))))
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(files)
         return orig(repo, wctx, mctx, force, actions, *args, **kwargs)
     extensions.wrapfunction(merge, '_checkunknownfiles', checkunknownfiles)
 
     # Prefetch files before status attempts to look at their size and contents
     def checklookup(orig, self, files):
         repo = self._repo
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             prefetchfiles = []
             for parent in self._parents:
                 for f in files:
                     if f in parent:
                         prefetchfiles.append((f, hex(parent.filenode(f))))
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(prefetchfiles)
         return orig(self, files)
     extensions.wrapfunction(context.workingctx, '_checklookup', checklookup)
 
     # Prefetch the logic that compares added and removed files for renames
     def findrenames(orig, repo, matcher, added, removed, *args, **kwargs):
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             files = []
             parentctx = repo['.']
             for f in removed:
                 files.append((f, hex(parentctx.filenode(f))))
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(files)
         return orig(repo, matcher, added, removed, *args, **kwargs)
     extensions.wrapfunction(scmutil, '_findrenames', findrenames)
 
     # prefetch files before mergecopies check
     def computenonoverlap(orig, repo, c1, c2, *args, **kwargs):
         u1, u2 = orig(repo, c1, c2, *args, **kwargs)
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             m1 = c1.manifest()
             m2 = c2.manifest()
             files = []
 
             sparsematch1 = repo.maybesparsematch(c1.rev())
             if sparsematch1:
                 sparseu1 = []
                 for f in u1:
                     if sparsematch1(f):
                         files.append((f, hex(m1[f])))
                         sparseu1.append(f)
                 u1 = sparseu1
 
             sparsematch2 = repo.maybesparsematch(c2.rev())
             if sparsematch2:
                 sparseu2 = []
                 for f in u2:
                     if sparsematch2(f):
                         files.append((f, hex(m2[f])))
                         sparseu2.append(f)
                 u2 = sparseu2
 
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(files)
         return u1, u2
     extensions.wrapfunction(copies, '_computenonoverlap', computenonoverlap)
 
     # prefetch files before pathcopies check
     def computeforwardmissing(orig, a, b, match=None):
         missing = list(orig(a, b, match=match))
         repo = a._repo
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             mb = b.manifest()
 
             files = []
             sparsematch = repo.maybesparsematch(b.rev())
             if sparsematch:
                 sparsemissing = []
                 for f in missing:
                     if sparsematch(f):
                         files.append((f, hex(mb[f])))
                         sparsemissing.append(f)
                 missing = sparsemissing
 
             # batch fetch the needed files from the server
             repo.fileservice.prefetch(files)
         return missing
     extensions.wrapfunction(copies, '_computeforwardmissing',
                             computeforwardmissing)
 
     # close cache miss server connection after the command has finished
     def runcommand(orig, lui, repo, *args, **kwargs):
         try:
             return orig(lui, repo, *args, **kwargs)
         finally:
             # repo can be None when running in chg:
             # - at startup, reposetup was called because serve is not norepo
             # - a norepo command like "help" is called
-            if repo and constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+            if repo and isenabled(repo):
                 repo.fileservice.close()
     extensions.wrapfunction(dispatch, 'runcommand', runcommand)
 
     # disappointing hacks below
     templatekw.getrenamedfn = getrenamedfn
     extensions.wrapfunction(revset, 'filelog', filelogrevset)
     revset.symbols['filelog'] = revset.filelog
     extensions.wrapfunction(cmdutil, 'walkfilerevs', walkfilerevs)
 
     # prevent strip from stripping remotefilelogs
     def _collectbrokencsets(orig, repo, files, striprev):
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             files = list([f for f in files if not repo.shallowmatch(f)])
         return orig(repo, files, striprev)
     extensions.wrapfunction(repair, '_collectbrokencsets', _collectbrokencsets)
 
     # Don't commit filelogs until we know the commit hash, since the hash
     # is present in the filelog blob.
     # This violates Mercurial's filelog->manifest->changelog write order,
     # but is generally fine for client repos.
     pendingfilecommits = []
     def addrawrevision(orig, self, rawtext, transaction, link, p1, p2, node,
                        flags, cachedelta=None, _metatuple=None):
         if isinstance(link, int):
             pendingfilecommits.append(
                 (self, rawtext, transaction, link, p1, p2, node, flags,
                  cachedelta, _metatuple))
             return node
         else:
             return orig(self, rawtext, transaction, link, p1, p2, node, flags,
                         cachedelta, _metatuple=_metatuple)
     extensions.wrapfunction(
         remotefilelog.remotefilelog, 'addrawrevision', addrawrevision)
 
     def changelogadd(orig, self, *args):
         oldlen = len(self)
         node = orig(self, *args)
         newlen = len(self)
         if oldlen != newlen:
             for oldargs in pendingfilecommits:
                 log, rt, tr, link, p1, p2, n, fl, c, m = oldargs
                 linknode = self.node(link)
                 if linknode == node:
                     log.addrawrevision(rt, tr, linknode, p1, p2, n, fl, c, m)
                 else:
                     raise error.ProgrammingError(
                         'pending multiple integer revisions are not supported')
         else:
             # "link" is actually wrong here (it is set to len(changelog))
             # if changelog remains unchanged, skip writing file revisions
             # but still do a sanity check about pending multiple revisions
             if len(set(x[3] for x in pendingfilecommits)) > 1:
                 raise error.ProgrammingError(
                     'pending multiple integer revisions are not supported')
         del pendingfilecommits[:]
         return node
     extensions.wrapfunction(changelog.changelog, 'add', changelogadd)
 
     # changectx wrappers
     def filectx(orig, self, path, fileid=None, filelog=None):
         if fileid is None:
             fileid = self.filenode(path)
-        if (constants.SHALLOWREPO_REQUIREMENT in self._repo.requirements and
-            self._repo.shallowmatch(path)):
+        if (isenabled(self._repo) and self._repo.shallowmatch(path)):
             return remotefilectx.remotefilectx(self._repo, path,
                 fileid=fileid, changectx=self, filelog=filelog)
         return orig(self, path, fileid=fileid, filelog=filelog)
     extensions.wrapfunction(context.changectx, 'filectx', filectx)
 
     def workingfilectx(orig, self, path, filelog=None):
-        if (constants.SHALLOWREPO_REQUIREMENT in self._repo.requirements and
-            self._repo.shallowmatch(path)):
+        if (isenabled(self._repo) and self._repo.shallowmatch(path)):
             return remotefilectx.remoteworkingfilectx(self._repo,
                 path, workingctx=self, filelog=filelog)
         return orig(self, path, filelog=filelog)
     extensions.wrapfunction(context.workingctx, 'filectx', workingfilectx)
 
     # prefetch required revisions before a diff
     def trydiff(orig, repo, revs, ctx1, ctx2, modified, added, removed,
                 copy, getfilectx, *args, **kwargs):
-        if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if isenabled(repo):
             prefetch = []
             mf1 = ctx1.manifest()
             for fname in modified + added + removed:
                 if fname in mf1:
                     fnode = getfilectx(fname, ctx1).filenode()
                     # fnode can be None if it's a edited working ctx file
                     if fnode:
                         prefetch.append((fname, hex(fnode)))
                 if fname not in removed:
                     fnode = getfilectx(fname, ctx2).filenode()
                     if fnode:
                         prefetch.append((fname, hex(fnode)))
 
             repo.fileservice.prefetch(prefetch)
 
         return orig(repo, revs, ctx1, ctx2, modified, added, removed,
             copy, getfilectx, *args, **kwargs)
     extensions.wrapfunction(patch, 'trydiff', trydiff)
 
     # Prevent verify from processing files
     # a stub for mercurial.hg.verify()
     def _verify(orig, repo):
         lock = repo.lock()
         try:
             return shallowverifier.shallowverifier(repo).verify()
         finally:
             lock.release()
 
     extensions.wrapfunction(hg, 'verify', _verify)
 
     scmutil.fileprefetchhooks.add('remotefilelog', _fileprefetchhook)
 
 def getrenamedfn(repo, endrev=None):
     rcache = {}
 
     def getrenamed(fn, rev):
         '''looks up all renames for a file (up to endrev) the first
         time the file is given. It indexes on the changerev and only
         parses the manifest if linkrev != changerev.
         Returns rename info for fn at changerev rev.'''
         if rev in rcache.setdefault(fn, {}):
             return rcache[fn][rev]
 
         try:
             fctx = repo[rev].filectx(fn)
             for ancestor in fctx.ancestors():
                 if ancestor.path() == fn:
                     renamed = ancestor.renamed()
                     rcache[fn][ancestor.rev()] = renamed
 
             return fctx.renamed()
         except error.LookupError:
             return None
 
     return getrenamed
 
 def walkfilerevs(orig, repo, match, follow, revs, fncache):
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not isenabled(repo):
         return orig(repo, match, follow, revs, fncache)
 
     # remotefilelog's can't be walked in rev order, so throw.
     # The caller will see the exception and walk the commit tree instead.
     if not follow:
         raise cmdutil.FileWalkError("Cannot walk via filelog")
 
     wanted = set()
     minrev, maxrev = min(revs), max(revs)
 
     pctx = repo['.']
     for filename in match.files():
         if filename not in pctx:
             raise error.Abort(_('cannot follow file not in parent '
                                'revision: "%s"') % filename)
         fctx = pctx[filename]
 
         linkrev = fctx.linkrev()
         if linkrev >= minrev and linkrev <= maxrev:
             fncache.setdefault(linkrev, []).append(filename)
             wanted.add(linkrev)
 
         for ancestor in fctx.ancestors():
             linkrev = ancestor.linkrev()
             if linkrev >= minrev and linkrev <= maxrev:
                 fncache.setdefault(linkrev, []).append(ancestor.path())
                 wanted.add(linkrev)
 
     return wanted
 
 def filelogrevset(orig, repo, subset, x):
     """``filelog(pattern)``
     Changesets connected to the specified filelog.
 
     For performance reasons, ``filelog()`` does not show every changeset
     that affects the requested file(s). See :hg:`help log` for details. For
     a slower, more accurate result, use ``file()``.
     """
 
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not isenabled(repo):
         return orig(repo, subset, x)
 
     # i18n: "filelog" is a keyword
     pat = revset.getstring(x, _("filelog requires a pattern"))
     m = match.match(repo.root, repo.getcwd(), [pat], default='relpath',
                        ctx=repo[None])
     s = set()
 
     if not match.patkind(pat):
         # slow
         for r in subset:
             ctx = repo[r]
             cfiles = ctx.files()
             for f in m.files():
                 if f in cfiles:
                     s.add(ctx.rev())
                     break
     else:
         # partial
         files = (f for f in repo[None] if m(f))
         for f in files:
             fctx = repo[None].filectx(f)
             s.add(fctx.linkrev())
             for actx in fctx.ancestors():
                 s.add(actx.linkrev())
 
     return smartset.baseset([r for r in subset if r in s])
 
 @command('gc', [], _('hg gc [REPO...]'), norepo=True)
 def gc(ui, *args, **opts):
     '''garbage collect the client and server filelog caches
     '''
     cachepaths = set()
 
     # get the system client cache
     systemcache = shallowutil.getcachepath(ui, allowempty=True)
     if systemcache:
         cachepaths.add(systemcache)
 
     # get repo client and server cache
     repopaths = []
     pwd = ui.environ.get('PWD')
     if pwd:
         repopaths.append(pwd)
 
     repopaths.extend(args)
     repos = []
     for repopath in repopaths:
         try:
             repo = hg.peer(ui, {}, repopath)
             repos.append(repo)
 
             repocache = shallowutil.getcachepath(repo.ui, allowempty=True)
             if repocache:
                 cachepaths.add(repocache)
         except error.RepoError:
             pass
 
     # gc client cache
     for cachepath in cachepaths:
         gcclient(ui, cachepath)
 
     # gc server cache
     for repo in repos:
         remotefilelogserver.gcserver(ui, repo._repo)
 
 def gcclient(ui, cachepath):
     # get list of repos that use this cache
     repospath = os.path.join(cachepath, 'repos')
     if not os.path.exists(repospath):
         ui.warn(_("no known cache at %s\n") % cachepath)
         return
 
     reposfile = open(repospath, 'r')
     repos = set([r[:-1] for r in reposfile.readlines()])
     reposfile.close()
 
     # build list of useful files
     validrepos = []
     keepkeys = set()
 
     _analyzing = _("analyzing repositories")
 
     sharedcache = None
     filesrepacked = False
 
     count = 0
     for path in repos:
         ui.progress(_analyzing, count, unit="repos", total=len(repos))
         count += 1
         try:
             path = ui.expandpath(os.path.normpath(path))
         except TypeError as e:
             ui.warn(_("warning: malformed path: %r:%s\n") % (path, e))
             traceback.print_exc()
             continue
         try:
             peer = hg.peer(ui, {}, path)
             repo = peer._repo
         except error.RepoError:
             continue
 
         validrepos.append(path)
 
         # Protect against any repo or config changes that have happened since
         # this repo was added to the repos file. We'd rather this loop succeed
         # and too much be deleted, than the loop fail and nothing gets deleted.
-        if constants.SHALLOWREPO_REQUIREMENT not in repo.requirements:
+        if not isenabled(repo):
             continue
 
         if not util.safehasattr(repo, 'name'):
             ui.warn(_("repo %s is a misconfigured remotefilelog repo\n") % path)
             continue
 
         # If garbage collection on repack and repack on hg gc are enabled
         # then loose files are repacked and garbage collected.
         # Otherwise regular garbage collection is performed.
         repackonhggc = repo.ui.configbool('remotefilelog', 'repackonhggc')
         gcrepack = repo.ui.configbool('remotefilelog', 'gcrepack')
         if repackonhggc and gcrepack:
             try:
                 repackmod.incrementalrepack(repo)
                 filesrepacked = True
                 continue
             except (IOError, repackmod.RepackAlreadyRunning):
                 # If repack cannot be performed due to not enough disk space
                 # continue doing garbage collection of loose files w/o repack
                 pass
 
         reponame = repo.name
         if not sharedcache:
             sharedcache = repo.sharedstore
 
         # Compute a keepset which is not garbage collected
         def keyfn(fname, fnode):
             return fileserverclient.getcachekey(reponame, fname, hex(fnode))
         keepkeys = repackmod.keepset(repo, keyfn=keyfn, lastkeepkeys=keepkeys)
 
     ui.progress(_analyzing, None)
 
     # write list of valid repos back
     oldumask = os.umask(0o002)
     try:
         reposfile = open(repospath, 'w')
         reposfile.writelines([("%s\n" % r) for r in validrepos])
         reposfile.close()
     finally:
         os.umask(oldumask)
 
     # prune cache
     if sharedcache is not None:
         sharedcache.gc(keepkeys)
     elif not filesrepacked:
         ui.warn(_("warning: no valid repos in repofile\n"))
 
 def log(orig, ui, repo, *pats, **opts):
-    if constants.SHALLOWREPO_REQUIREMENT not in repo.requirements:
+    if not isenabled(repo):
         return orig(ui, repo, *pats, **opts)
 
     follow = opts.get('follow')
     revs = opts.get('rev')
     if pats:
         # Force slowpath for non-follow patterns and follows that start from
         # non-working-copy-parent revs.
         if not follow or revs:
             # This forces the slowpath
             opts['removed'] = True
 
         # If this is a non-follow log without any revs specified, recommend that
         # the user add -f to speed it up.
         if not follow and not revs:
             match, pats = scmutil.matchandpats(repo['.'], pats, opts)
             isfile = not match.anypats()
             if isfile:
                 for file in match.files():
                     if not os.path.isfile(repo.wjoin(file)):
                         isfile = False
                         break
 
             if isfile:
                 ui.warn(_("warning: file log can be slow on large repos - " +
                           "use -f to speed it up\n"))
 
     return orig(ui, repo, *pats, **opts)
 
 def revdatelimit(ui, revset):
     """Update revset so that only changesets no older than 'prefetchdays' days
     are included. The default value is set to 14 days. If 'prefetchdays' is set
     to zero or negative value then date restriction is not applied.
     """
     days = ui.configint('remotefilelog', 'prefetchdays')
     if days > 0:
         revset = '(%s) & date(-%s)' % (revset, days)
     return revset
 
 def readytofetch(repo):
     """Check that enough time has passed since the last background prefetch.
     This only relates to prefetches after operations that change the working
     copy parent. Default delay between background prefetches is 2 minutes.
     """
     timeout = repo.ui.configint('remotefilelog', 'prefetchdelay')
     fname = repo.vfs.join('lastprefetch')
 
     ready = False
     with open(fname, 'a'):
         # the with construct above is used to avoid race conditions
         modtime = os.path.getmtime(fname)
         if (time.time() - modtime) > timeout:
             os.utime(fname, None)
             ready = True
 
     return ready
 
 def wcpprefetch(ui, repo, **kwargs):
     """Prefetches in background revisions specified by bgprefetchrevs revset.
     Does background repack if backgroundrepack flag is set in config.
     """
-    shallow = constants.SHALLOWREPO_REQUIREMENT in repo.requirements
+    shallow = isenabled(repo)
     bgprefetchrevs = ui.config('remotefilelog', 'bgprefetchrevs')
     isready = readytofetch(repo)
 
     if not (shallow and bgprefetchrevs and isready):
         return
 
     bgrepack = repo.ui.configbool('remotefilelog', 'backgroundrepack')
     # update a revset with a date limit
     bgprefetchrevs = revdatelimit(ui, bgprefetchrevs)
 
     def anon():
         if util.safehasattr(repo, 'ranprefetch') and repo.ranprefetch:
             return
         repo.ranprefetch = True
         repo.backgroundprefetch(bgprefetchrevs, repack=bgrepack)
 
     repo._afterlock(anon)
 
 def pull(orig, ui, repo, *pats, **opts):
     result = orig(ui, repo, *pats, **opts)
 
-    if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if isenabled(repo):
         # prefetch if it's configured
         prefetchrevset = ui.config('remotefilelog', 'pullprefetch')
         bgrepack = repo.ui.configbool('remotefilelog', 'backgroundrepack')
         bgprefetch = repo.ui.configbool('remotefilelog', 'backgroundprefetch')
 
         if prefetchrevset:
             ui.status(_("prefetching file contents\n"))
             revs = scmutil.revrange(repo, [prefetchrevset])
             base = repo['.'].rev()
             if bgprefetch:
                 repo.backgroundprefetch(prefetchrevset, repack=bgrepack)
             else:
                 repo.prefetch(revs, base=base)
                 if bgrepack:
                     repackmod.backgroundrepack(repo, incremental=True)
         elif bgrepack:
             repackmod.backgroundrepack(repo, incremental=True)
 
     return result
 
 def exchangepull(orig, repo, remote, *args, **kwargs):
     # Hook into the callstream/getbundle to insert bundle capabilities
     # during a pull.
     def localgetbundle(orig, source, heads=None, common=None, bundlecaps=None,
                        **kwargs):
         if not bundlecaps:
             bundlecaps = set()
         bundlecaps.add(constants.BUNDLE2_CAPABLITY)
         return orig(source, heads=heads, common=common, bundlecaps=bundlecaps,
                     **kwargs)
 
     if util.safehasattr(remote, '_callstream'):
         remote._localrepo = repo
     elif util.safehasattr(remote, 'getbundle'):
         extensions.wrapfunction(remote, 'getbundle', localgetbundle)
 
     return orig(repo, remote, *args, **kwargs)
 
 def _fileprefetchhook(repo, revs, match):
-    if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if isenabled(repo):
         allfiles = []
         for rev in revs:
             if rev == nodemod.wdirrev or rev is None:
                 continue
             ctx = repo[rev]
             mf = ctx.manifest()
             sparsematch = repo.maybesparsematch(ctx.rev())
             for path in ctx.walk(match):
                 if path.endswith('/'):
                     # Tree manifest that's being excluded as part of narrow
                     continue
                 if (not sparsematch or sparsematch(path)) and path in mf:
                     allfiles.append((path, hex(mf[path])))
         repo.fileservice.prefetch(allfiles)
 
 @command('debugremotefilelog', [
     ('d', 'decompress', None, _('decompress the filelog first')),
     ], _('hg debugremotefilelog <path>'), norepo=True)
 def debugremotefilelog(ui, path, **opts):
     return debugcommands.debugremotefilelog(ui, path, **opts)
 
 @command('verifyremotefilelog', [
     ('d', 'decompress', None, _('decompress the filelogs first')),
     ], _('hg verifyremotefilelogs <directory>'), norepo=True)
 def verifyremotefilelog(ui, path, **opts):
     return debugcommands.verifyremotefilelog(ui, path, **opts)
 
 @command('debugdatapack', [
     ('', 'long', None, _('print the long hashes')),
     ('', 'node', '', _('dump the contents of node'), 'NODE'),
     ], _('hg debugdatapack <paths>'), norepo=True)
 def debugdatapack(ui, *paths, **opts):
     return debugcommands.debugdatapack(ui, *paths, **opts)
 
 @command('debughistorypack', [
     ], _('hg debughistorypack <path>'), norepo=True)
 def debughistorypack(ui, path, **opts):
     return debugcommands.debughistorypack(ui, path)
 
 @command('debugkeepset', [
     ], _('hg debugkeepset'))
 def debugkeepset(ui, repo, **opts):
     # The command is used to measure keepset computation time
     def keyfn(fname, fnode):
         return fileserverclient.getcachekey(repo.name, fname, hex(fnode))
     repackmod.keepset(repo, keyfn)
     return
 
 @command('debugwaitonrepack', [
     ], _('hg debugwaitonrepack'))
 def debugwaitonrepack(ui, repo, **opts):
     return debugcommands.debugwaitonrepack(repo)
 
 @command('debugwaitonprefetch', [
     ], _('hg debugwaitonprefetch'))
 def debugwaitonprefetch(ui, repo, **opts):
     return debugcommands.debugwaitonprefetch(repo)
 
 def resolveprefetchopts(ui, opts):
     if not opts.get('rev'):
         revset = ['.', 'draft()']
 
         prefetchrevset = ui.config('remotefilelog', 'pullprefetch', None)
         if prefetchrevset:
             revset.append('(%s)' % prefetchrevset)
         bgprefetchrevs = ui.config('remotefilelog', 'bgprefetchrevs', None)
         if bgprefetchrevs:
             revset.append('(%s)' % bgprefetchrevs)
         revset = '+'.join(revset)
 
         # update a revset with a date limit
         revset = revdatelimit(ui, revset)
 
         opts['rev'] = [revset]
 
     if not opts.get('base'):
         opts['base'] = None
 
     return opts
 
 @command('prefetch', [
     ('r', 'rev', [], _('prefetch the specified revisions'), _('REV')),
     ('', 'repack', False, _('run repack after prefetch')),
     ('b', 'base', '', _("rev that is assumed to already be local")),
     ] + commands.walkopts, _('hg prefetch [OPTIONS] [FILE...]'))
 def prefetch(ui, repo, *pats, **opts):
     """prefetch file revisions from the server
 
     Prefetchs file revisions for the specified revs and stores them in the
     local remotefilelog cache.  If no rev is specified, the default rev is
     used which is the union of dot, draft, pullprefetch and bgprefetchrev.
     File names or patterns can be used to limit which files are downloaded.
 
     Return 0 on success.
     """
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not isenabled(repo):
         raise error.Abort(_("repo is not shallow"))
 
     opts = resolveprefetchopts(ui, opts)
     revs = scmutil.revrange(repo, opts.get('rev'))
     repo.prefetch(revs, opts.get('base'), pats, opts)
 
     # Run repack in background
     if opts.get('repack'):
         repackmod.backgroundrepack(repo, incremental=True)
 
 @command('repack', [
      ('', 'background', None, _('run in a background process'), None),
      ('', 'incremental', None, _('do an incremental repack'), None),
      ('', 'packsonly', None, _('only repack packs (skip loose objects)'), None),
     ], _('hg repack [OPTIONS]'))
 def repack_(ui, repo, *pats, **opts):
     if opts.get('background'):
         repackmod.backgroundrepack(repo, incremental=opts.get('incremental'),
                                    packsonly=opts.get('packsonly', False))
         return
 
     options = {'packsonly': opts.get('packsonly')}
 
     try:
         if opts.get('incremental'):
             repackmod.incrementalrepack(repo, options=options)
         else:
             repackmod.fullrepack(repo, options=options)
     except repackmod.RepackAlreadyRunning as ex:
         # Don't propogate the exception if the repack is already in
         # progress, since we want the command to exit 0.
         repo.ui.warn('%s\n' % ex)

hgext/remotefilelog/debugcommands.py

@@ -1,377 +1,377 b''
 # debugcommands.py - debug logic for remotefilelog
 #
 # Copyright 2013 Facebook, Inc.
 #
 # 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 hashlib
 import os
 import zlib
 
 from mercurial.node import bin, hex, nullid, short
 from mercurial.i18n import _
 from mercurial import (
     error,
     filelog,
     revlog,
 )
 from . import (
     constants,
     datapack,
     extutil,
     fileserverclient,
     historypack,
     repack,
     shallowutil,
 )
 
 def debugremotefilelog(ui, path, **opts):
     decompress = opts.get('decompress')
 
     size, firstnode, mapping = parsefileblob(path, decompress)
 
     ui.status(_("size: %s bytes\n") % (size))
     ui.status(_("path: %s \n") % (path))
     ui.status(_("key: %s \n") % (short(firstnode)))
     ui.status(_("\n"))
     ui.status(_("%12s => %12s %13s %13s %12s\n") %
               ("node", "p1", "p2", "linknode", "copyfrom"))
 
     queue = [firstnode]
     while queue:
         node = queue.pop(0)
         p1, p2, linknode, copyfrom = mapping[node]
         ui.status(_("%s => %s  %s  %s  %s\n") %
             (short(node), short(p1), short(p2), short(linknode), copyfrom))
         if p1 != nullid:
             queue.append(p1)
         if p2 != nullid:
             queue.append(p2)
 
 def buildtemprevlog(repo, file):
     # get filename key
     filekey = hashlib.sha1(file).hexdigest()
     filedir = os.path.join(repo.path, 'store/data', filekey)
 
     # sort all entries based on linkrev
     fctxs = []
     for filenode in os.listdir(filedir):
         if '_old' not in filenode:
             fctxs.append(repo.filectx(file, fileid=bin(filenode)))
 
     fctxs = sorted(fctxs, key=lambda x: x.linkrev())
 
     # add to revlog
     temppath = repo.sjoin('data/temprevlog.i')
     if os.path.exists(temppath):
         os.remove(temppath)
     r = filelog.filelog(repo.svfs, 'temprevlog')
 
     class faket(object):
         def add(self, a, b, c):
             pass
     t = faket()
     for fctx in fctxs:
         if fctx.node() not in repo:
             continue
 
         p = fctx.filelog().parents(fctx.filenode())
         meta = {}
         if fctx.renamed():
             meta['copy'] = fctx.renamed()[0]
             meta['copyrev'] = hex(fctx.renamed()[1])
 
         r.add(fctx.data(), meta, t, fctx.linkrev(), p[0], p[1])
 
     return r
 
 def debugindex(orig, ui, repo, file_=None, **opts):
     """dump the contents of an index file"""
     if (opts.get('changelog') or
         opts.get('manifest') or
         opts.get('dir') or
-        not constants.SHALLOWREPO_REQUIREMENT in repo.requirements or
+        not shallowutil.isenabled(repo) or
         not repo.shallowmatch(file_)):
         return orig(ui, repo, file_, **opts)
 
     r = buildtemprevlog(repo, file_)
 
     # debugindex like normal
     format = opts.get('format', 0)
     if format not in (0, 1):
         raise error.Abort(_("unknown format %d") % format)
 
     generaldelta = r.version & revlog.FLAG_GENERALDELTA
     if generaldelta:
         basehdr = ' delta'
     else:
         basehdr = '  base'
 
     if format == 0:
         ui.write(("   rev    offset  length " + basehdr + " linkrev"
                   " nodeid       p1           p2\n"))
     elif format == 1:
         ui.write(("   rev flag   offset   length"
                   "     size " + basehdr + "   link     p1     p2"
                   "       nodeid\n"))
 
     for i in r:
         node = r.node(i)
         if generaldelta:
             base = r.deltaparent(i)
         else:
             base = r.chainbase(i)
         if format == 0:
             try:
                 pp = r.parents(node)
             except Exception:
                 pp = [nullid, nullid]
             ui.write("% 6d % 9d % 7d % 6d % 7d %s %s %s\n" % (
                     i, r.start(i), r.length(i), base, r.linkrev(i),
                     short(node), short(pp[0]), short(pp[1])))
         elif format == 1:
             pr = r.parentrevs(i)
             ui.write("% 6d %04x % 8d % 8d % 8d % 6d % 6d % 6d % 6d %s\n" % (
                     i, r.flags(i), r.start(i), r.length(i), r.rawsize(i),
                     base, r.linkrev(i), pr[0], pr[1], short(node)))
 
 def debugindexdot(orig, ui, repo, file_):
     """dump an index DAG as a graphviz dot file"""
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not shallowutil.isenabled(repo):
         return orig(ui, repo, file_)
 
     r = buildtemprevlog(repo, os.path.basename(file_)[:-2])
 
     ui.write(("digraph G {\n"))
     for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write("\t%d -> %d\n" % (r.rev(pp[0]), i))
         if pp[1] != nullid:
             ui.write("\t%d -> %d\n" % (r.rev(pp[1]), i))
     ui.write("}\n")
 
 def verifyremotefilelog(ui, path, **opts):
     decompress = opts.get('decompress')
 
     for root, dirs, files in os.walk(path):
         for file in files:
             if file == "repos":
                 continue
             filepath = os.path.join(root, file)
             size, firstnode, mapping = parsefileblob(filepath, decompress)
             for p1, p2, linknode, copyfrom in mapping.itervalues():
                 if linknode == nullid:
                     actualpath = os.path.relpath(root, path)
                     key = fileserverclient.getcachekey("reponame", actualpath,
                                                        file)
                     ui.status("%s %s\n" % (key, os.path.relpath(filepath,
                                                                 path)))
 
 def _decompressblob(raw):
     return zlib.decompress(raw)
 
 def parsefileblob(path, decompress):
     raw = None
     f = open(path, "r")
     try:
         raw = f.read()
     finally:
         f.close()
 
     if decompress:
         raw = _decompressblob(raw)
 
     offset, size, flags = shallowutil.parsesizeflags(raw)
     start = offset + size
 
     firstnode = None
 
     mapping = {}
     while start < len(raw):
         divider = raw.index('\0', start + 80)
 
         currentnode = raw[start:(start + 20)]
         if not firstnode:
             firstnode = currentnode
 
         p1 = raw[(start + 20):(start + 40)]
         p2 = raw[(start + 40):(start + 60)]
         linknode = raw[(start + 60):(start + 80)]
         copyfrom = raw[(start + 80):divider]
 
         mapping[currentnode] = (p1, p2, linknode, copyfrom)
         start = divider + 1
 
     return size, firstnode, mapping
 
 def debugdatapack(ui, *paths, **opts):
     for path in paths:
         if '.data' in path:
             path = path[:path.index('.data')]
         ui.write("%s:\n" % path)
         dpack = datapack.datapack(path)
         node = opts.get('node')
         if node:
             deltachain = dpack.getdeltachain('', bin(node))
             dumpdeltachain(ui, deltachain, **opts)
             return
 
         if opts.get('long'):
             hashformatter = hex
             hashlen = 42
         else:
             hashformatter = short
             hashlen = 14
 
         lastfilename = None
         totaldeltasize = 0
         totalblobsize = 0
         def printtotals():
             if lastfilename is not None:
                 ui.write("\n")
             if not totaldeltasize or not totalblobsize:
                 return
             difference = totalblobsize - totaldeltasize
             deltastr = "%0.1f%% %s" % (
                 (100.0 * abs(difference) / totalblobsize),
                 ("smaller" if difference > 0 else "bigger"))
 
             ui.write(("Total:%s%s  %s (%s)\n") % (
                 "".ljust(2 * hashlen - len("Total:")),
                 str(totaldeltasize).ljust(12),
                 str(totalblobsize).ljust(9),
                 deltastr
             ))
 
         bases = {}
         nodes = set()
         failures = 0
         for filename, node, deltabase, deltalen in dpack.iterentries():
             bases[node] = deltabase
             if node in nodes:
                 ui.write(("Bad entry: %s appears twice\n" % short(node)))
                 failures += 1
             nodes.add(node)
             if filename != lastfilename:
                 printtotals()
                 name = '(empty name)' if filename == '' else filename
                 ui.write("%s:\n" % name)
                 ui.write("%s%s%s%s\n" % (
                     "Node".ljust(hashlen),
                     "Delta Base".ljust(hashlen),
                     "Delta Length".ljust(14),
                     "Blob Size".ljust(9)))
                 lastfilename = filename
                 totalblobsize = 0
                 totaldeltasize = 0
 
             # Metadata could be missing, in which case it will be an empty dict.
             meta = dpack.getmeta(filename, node)
             if constants.METAKEYSIZE in meta:
                 blobsize = meta[constants.METAKEYSIZE]
                 totaldeltasize += deltalen
                 totalblobsize += blobsize
             else:
                 blobsize = "(missing)"
             ui.write("%s  %s  %s%s\n" % (
                 hashformatter(node),
                 hashformatter(deltabase),
                 str(deltalen).ljust(14),
                 blobsize))
 
         if filename is not None:
             printtotals()
 
         failures += _sanitycheck(ui, set(nodes), bases)
         if failures > 1:
             ui.warn(("%d failures\n" % failures))
             return 1
 
 def _sanitycheck(ui, nodes, bases):
     """
     Does some basic sanity checking on a packfiles with ``nodes`` ``bases`` (a
     mapping of node->base):
 
     - Each deltabase must itself be a node elsewhere in the pack
     - There must be no cycles
     """
     failures = 0
     for node in nodes:
         seen = set()
         current = node
         deltabase = bases[current]
 
         while deltabase != nullid:
             if deltabase not in nodes:
                 ui.warn(("Bad entry: %s has an unknown deltabase (%s)\n" %
                         (short(node), short(deltabase))))
                 failures += 1
                 break
 
             if deltabase in seen:
                 ui.warn(("Bad entry: %s has a cycle (at %s)\n" %
                         (short(node), short(deltabase))))
                 failures += 1
                 break
 
             current = deltabase
             seen.add(current)
             deltabase = bases[current]
         # Since ``node`` begins a valid chain, reset/memoize its base to nullid
         # so we don't traverse it again.
         bases[node] = nullid
     return failures
 
 def dumpdeltachain(ui, deltachain, **opts):
     hashformatter = hex
     hashlen = 40
 
     lastfilename = None
     for filename, node, filename, deltabasenode, delta in deltachain:
         if filename != lastfilename:
             ui.write("\n%s\n" % filename)
             lastfilename = filename
         ui.write("%s  %s  %s  %s\n" % (
             "Node".ljust(hashlen),
             "Delta Base".ljust(hashlen),
             "Delta SHA1".ljust(hashlen),
             "Delta Length".ljust(6),
         ))
 
         ui.write("%s  %s  %s  %s\n" % (
             hashformatter(node),
             hashformatter(deltabasenode),
             hashlib.sha1(delta).hexdigest(),
             len(delta)))
 
 def debughistorypack(ui, path):
     if '.hist' in path:
         path = path[:path.index('.hist')]
     hpack = historypack.historypack(path)
 
     lastfilename = None
     for entry in hpack.iterentries():
         filename, node, p1node, p2node, linknode, copyfrom = entry
         if filename != lastfilename:
             ui.write("\n%s\n" % filename)
             ui.write("%s%s%s%s%s\n" % (
                 "Node".ljust(14),
                 "P1 Node".ljust(14),
                 "P2 Node".ljust(14),
                 "Link Node".ljust(14),
                 "Copy From"))
             lastfilename = filename
         ui.write("%s  %s  %s  %s  %s\n" % (short(node), short(p1node),
             short(p2node), short(linknode), copyfrom))
 
 def debugwaitonrepack(repo):
     with extutil.flock(repack.repacklockvfs(repo).join('repacklock'), ''):
         return
 
 def debugwaitonprefetch(repo):
     with repo._lock(repo.svfs, "prefetchlock", True, None,
                          None, _('prefetching in %s') % repo.origroot):
         pass

hgext/remotefilelog/remotefilelogserver.py

@@ -1,418 +1,418 b''
 # remotefilelogserver.py - server logic for a remotefilelog server
 #
 # Copyright 2013 Facebook, Inc.
 #
 # 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 errno
 import os
 import stat
 import time
 import zlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import (
     changegroup,
     changelog,
     context,
     error,
     extensions,
     match,
     store,
     streamclone,
     util,
     wireprotoserver,
     wireprototypes,
     wireprotov1server,
 )
 from .  import (
     constants,
     shallowutil,
 )
 
 _sshv1server = wireprotoserver.sshv1protocolhandler
 
 def setupserver(ui, repo):
     """Sets up a normal Mercurial repo so it can serve files to shallow repos.
     """
     onetimesetup(ui)
 
     # don't send files to shallow clients during pulls
     def generatefiles(orig, self, changedfiles, linknodes, commonrevs, source,
                       *args, **kwargs):
         caps = self._bundlecaps or []
         if constants.BUNDLE2_CAPABLITY in caps:
             # only send files that don't match the specified patterns
             includepattern = None
             excludepattern = None
             for cap in (self._bundlecaps or []):
                 if cap.startswith("includepattern="):
                     includepattern = cap[len("includepattern="):].split('\0')
                 elif cap.startswith("excludepattern="):
                     excludepattern = cap[len("excludepattern="):].split('\0')
 
             m = match.always(repo.root, '')
             if includepattern or excludepattern:
                 m = match.match(repo.root, '', None,
                     includepattern, excludepattern)
 
             changedfiles = list([f for f in changedfiles if not m(f)])
         return orig(self, changedfiles, linknodes, commonrevs, source,
                     *args, **kwargs)
 
     extensions.wrapfunction(
         changegroup.cgpacker, 'generatefiles', generatefiles)
 
 onetime = False
 def onetimesetup(ui):
     """Configures the wireprotocol for both clients and servers.
     """
     global onetime
     if onetime:
         return
     onetime = True
 
     # support file content requests
     wireprotov1server.wireprotocommand(
         'x_rfl_getflogheads', 'path', permission='pull')(getflogheads)
     wireprotov1server.wireprotocommand(
         'x_rfl_getfiles', '', permission='pull')(getfiles)
     wireprotov1server.wireprotocommand(
         'x_rfl_getfile', 'file node', permission='pull')(getfile)
 
     class streamstate(object):
         match = None
         shallowremote = False
         noflatmf = False
     state = streamstate()
 
     def stream_out_shallow(repo, proto, other):
         includepattern = None
         excludepattern = None
         raw = other.get('includepattern')
         if raw:
             includepattern = raw.split('\0')
         raw = other.get('excludepattern')
         if raw:
             excludepattern = raw.split('\0')
 
         oldshallow = state.shallowremote
         oldmatch = state.match
         oldnoflatmf = state.noflatmf
         try:
             state.shallowremote = True
             state.match = match.always(repo.root, '')
             state.noflatmf = other.get('noflatmanifest') == 'True'
             if includepattern or excludepattern:
                 state.match = match.match(repo.root, '', None,
                     includepattern, excludepattern)
             streamres = wireprotov1server.stream(repo, proto)
 
             # Force the first value to execute, so the file list is computed
             # within the try/finally scope
             first = next(streamres.gen)
             second = next(streamres.gen)
             def gen():
                 yield first
                 yield second
                 for value in streamres.gen:
                     yield value
             return wireprototypes.streamres(gen())
         finally:
             state.shallowremote = oldshallow
             state.match = oldmatch
             state.noflatmf = oldnoflatmf
 
     wireprotov1server.commands['stream_out_shallow'] = (stream_out_shallow, '*')
 
     # don't clone filelogs to shallow clients
     def _walkstreamfiles(orig, repo):
         if state.shallowremote:
             # if we are shallow ourselves, stream our local commits
-            if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+            if shallowutil.isenabled(repo):
                 striplen = len(repo.store.path) + 1
                 readdir = repo.store.rawvfs.readdir
                 visit = [os.path.join(repo.store.path, 'data')]
                 while visit:
                     p = visit.pop()
                     for f, kind, st in readdir(p, stat=True):
                         fp = p + '/' + f
                         if kind == stat.S_IFREG:
                             if not fp.endswith('.i') and not fp.endswith('.d'):
                                 n = util.pconvert(fp[striplen:])
                                 yield (store.decodedir(n), n, st.st_size)
                         if kind == stat.S_IFDIR:
                             visit.append(fp)
 
             if 'treemanifest' in repo.requirements:
                 for (u, e, s) in repo.store.datafiles():
                     if (u.startswith('meta/') and
                         (u.endswith('.i') or u.endswith('.d'))):
                         yield (u, e, s)
 
             # Return .d and .i files that do not match the shallow pattern
             match = state.match
             if match and not match.always():
                 for (u, e, s) in repo.store.datafiles():
                     f = u[5:-2]  # trim data/...  and .i/.d
                     if not state.match(f):
                         yield (u, e, s)
 
             for x in repo.store.topfiles():
                 if state.noflatmf and x[0][:11] == '00manifest.':
                     continue
                 yield x
 
-        elif constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        elif shallowutil.isenabled(repo):
             # don't allow cloning from a shallow repo to a full repo
             # since it would require fetching every version of every
             # file in order to create the revlogs.
             raise error.Abort(_("Cannot clone from a shallow repo "
                                 "to a full repo."))
         else:
             for x in orig(repo):
                 yield x
 
     extensions.wrapfunction(streamclone, '_walkstreamfiles', _walkstreamfiles)
 
     # We no longer use getbundle_shallow commands, but we must still
     # support it for migration purposes
     def getbundleshallow(repo, proto, others):
         bundlecaps = others.get('bundlecaps', '')
         bundlecaps = set(bundlecaps.split(','))
         bundlecaps.add(constants.BUNDLE2_CAPABLITY)
         others['bundlecaps'] = ','.join(bundlecaps)
 
         return wireprotov1server.commands["getbundle"][0](repo, proto, others)
 
     wireprotov1server.commands["getbundle_shallow"] = (getbundleshallow, '*')
 
     # expose remotefilelog capabilities
     def _capabilities(orig, repo, proto):
         caps = orig(repo, proto)
-        if ((constants.SHALLOWREPO_REQUIREMENT in repo.requirements or
-            ui.configbool('remotefilelog', 'server'))):
+        if (shallowutil.isenabled(repo) or ui.configbool('remotefilelog',
+                                                         'server')):
             if isinstance(proto, _sshv1server):
                 # legacy getfiles method which only works over ssh
                 caps.append(constants.NETWORK_CAP_LEGACY_SSH_GETFILES)
             caps.append('x_rfl_getflogheads')
             caps.append('x_rfl_getfile')
         return caps
     extensions.wrapfunction(wireprotov1server, '_capabilities', _capabilities)
 
     def _adjustlinkrev(orig, self, *args, **kwargs):
         # When generating file blobs, taking the real path is too slow on large
         # repos, so force it to just return the linkrev directly.
         repo = self._repo
         if util.safehasattr(repo, 'forcelinkrev') and repo.forcelinkrev:
             return self._filelog.linkrev(self._filelog.rev(self._filenode))
         return orig(self, *args, **kwargs)
 
     extensions.wrapfunction(
         context.basefilectx, '_adjustlinkrev', _adjustlinkrev)
 
     def _iscmd(orig, cmd):
         if cmd == 'x_rfl_getfiles':
             return False
         return orig(cmd)
 
     extensions.wrapfunction(wireprotoserver, 'iscmd', _iscmd)
 
 def _loadfileblob(repo, cachepath, path, node):
     filecachepath = os.path.join(cachepath, path, hex(node))
     if not os.path.exists(filecachepath) or os.path.getsize(filecachepath) == 0:
         filectx = repo.filectx(path, fileid=node)
         if filectx.node() == nullid:
             repo.changelog = changelog.changelog(repo.svfs)
             filectx = repo.filectx(path, fileid=node)
 
         text = createfileblob(filectx)
         # TODO configurable compression engines
         text = zlib.compress(text)
 
         # everything should be user & group read/writable
         oldumask = os.umask(0o002)
         try:
             dirname = os.path.dirname(filecachepath)
             if not os.path.exists(dirname):
                 try:
                     os.makedirs(dirname)
                 except OSError as ex:
                     if ex.errno != errno.EEXIST:
                         raise
 
             f = None
             try:
                 f = util.atomictempfile(filecachepath, "w")
                 f.write(text)
             except (IOError, OSError):
                 # Don't abort if the user only has permission to read,
                 # and not write.
                 pass
             finally:
                 if f:
                     f.close()
         finally:
             os.umask(oldumask)
     else:
         with open(filecachepath, "r") as f:
             text = f.read()
     return text
 
 def getflogheads(repo, proto, path):
     """A server api for requesting a filelog's heads
     """
     flog = repo.file(path)
     heads = flog.heads()
     return '\n'.join((hex(head) for head in heads if head != nullid))
 
 def getfile(repo, proto, file, node):
     """A server api for requesting a particular version of a file. Can be used
     in batches to request many files at once. The return protocol is:
     <errorcode>\0<data/errormsg> where <errorcode> is 0 for success or
     non-zero for an error.
 
     data is a compressed blob with revlog flag and ancestors information. See
     createfileblob for its content.
     """
-    if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if shallowutil.isenabled(repo):
         return '1\0' + _('cannot fetch remote files from shallow repo')
     cachepath = repo.ui.config("remotefilelog", "servercachepath")
     if not cachepath:
         cachepath = os.path.join(repo.path, "remotefilelogcache")
     node = bin(node.strip())
     if node == nullid:
         return '0\0'
     return '0\0' + _loadfileblob(repo, cachepath, file, node)
 
 def getfiles(repo, proto):
     """A server api for requesting particular versions of particular files.
     """
-    if constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if shallowutil.isenabled(repo):
         raise error.Abort(_('cannot fetch remote files from shallow repo'))
     if not isinstance(proto, _sshv1server):
         raise error.Abort(_('cannot fetch remote files over non-ssh protocol'))
 
     def streamer():
         fin = proto._fin
 
         cachepath = repo.ui.config("remotefilelog", "servercachepath")
         if not cachepath:
             cachepath = os.path.join(repo.path, "remotefilelogcache")
 
         while True:
             request = fin.readline()[:-1]
             if not request:
                 break
 
             node = bin(request[:40])
             if node == nullid:
                 yield '0\n'
                 continue
 
             path = request[40:]
 
             text = _loadfileblob(repo, cachepath, path, node)
 
             yield '%d\n%s' % (len(text), text)
 
             # it would be better to only flush after processing a whole batch
             # but currently we don't know if there are more requests coming
             proto._fout.flush()
     return wireprototypes.streamres(streamer())
 
 def createfileblob(filectx):
     """
     format:
         v0:
             str(len(rawtext)) + '\0' + rawtext + ancestortext
         v1:
             'v1' + '\n' + metalist + '\0' + rawtext + ancestortext
             metalist := metalist + '\n' + meta | meta
             meta := sizemeta | flagmeta
             sizemeta := METAKEYSIZE + str(len(rawtext))
             flagmeta := METAKEYFLAG + str(flag)
 
             note: sizemeta must exist. METAKEYFLAG and METAKEYSIZE must have a
             length of 1.
     """
     flog = filectx.filelog()
     frev = filectx.filerev()
     revlogflags = flog._revlog.flags(frev)
     if revlogflags == 0:
         # normal files
         text = filectx.data()
     else:
         # lfs, read raw revision data
         text = flog.revision(frev, raw=True)
 
     repo = filectx._repo
 
     ancestors = [filectx]
 
     try:
         repo.forcelinkrev = True
         ancestors.extend([f for f in filectx.ancestors()])
 
         ancestortext = ""
         for ancestorctx in ancestors:
             parents = ancestorctx.parents()
             p1 = nullid
             p2 = nullid
             if len(parents) > 0:
                 p1 = parents[0].filenode()
             if len(parents) > 1:
                 p2 = parents[1].filenode()
 
             copyname = ""
             rename = ancestorctx.renamed()
             if rename:
                 copyname = rename[0]
             linknode = ancestorctx.node()
             ancestortext += "%s%s%s%s%s\0" % (
                 ancestorctx.filenode(), p1, p2, linknode,
                 copyname)
     finally:
         repo.forcelinkrev = False
 
     header = shallowutil.buildfileblobheader(len(text), revlogflags)
 
     return "%s\0%s%s" % (header, text, ancestortext)
 
 def gcserver(ui, repo):
     if not repo.ui.configbool("remotefilelog", "server"):
         return
 
     neededfiles = set()
     heads = repo.revs("heads(tip~25000:) - null")
 
     cachepath = repo.vfs.join("remotefilelogcache")
     for head in heads:
         mf = repo[head].manifest()
         for filename, filenode in mf.iteritems():
             filecachepath = os.path.join(cachepath, filename, hex(filenode))
             neededfiles.add(filecachepath)
 
     # delete unneeded older files
     days = repo.ui.configint("remotefilelog", "serverexpiration")
     expiration = time.time() - (days * 24 * 60 * 60)
 
     _removing = _("removing old server cache")
     count = 0
     ui.progress(_removing, count, unit="files")
     for root, dirs, files in os.walk(cachepath):
         for file in files:
             filepath = os.path.join(root, file)
             count += 1
             ui.progress(_removing, count, unit="files")
             if filepath in neededfiles:
                 continue
 
             stat = os.stat(filepath)
             if stat.st_mtime < expiration:
                 os.remove(filepath)
 
     ui.progress(_removing, None)

hgext/remotefilelog/shallowbundle.py

@@ -1,294 +1,294 b''
 # shallowbundle.py - bundle10 implementation for use with shallow repositories
 #
 # Copyright 2013 Facebook, Inc.
 #
 # 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
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import (
     bundlerepo,
     changegroup,
     error,
     match,
     mdiff,
     pycompat,
 )
 from . import (
     constants,
     remotefilelog,
     shallowutil,
 )
 
 NoFiles = 0
 LocalFiles = 1
 AllFiles = 2
 
 def shallowgroup(cls, self, nodelist, rlog, lookup, units=None, reorder=None):
     if not isinstance(rlog, remotefilelog.remotefilelog):
         for c in super(cls, self).group(nodelist, rlog, lookup,
                                         units=units):
             yield c
         return
 
     if len(nodelist) == 0:
         yield self.close()
         return
 
     nodelist = shallowutil.sortnodes(nodelist, rlog.parents)
 
     # add the parent of the first rev
     p = rlog.parents(nodelist[0])[0]
     nodelist.insert(0, p)
 
     # build deltas
     for i in pycompat.xrange(len(nodelist) - 1):
         prev, curr = nodelist[i], nodelist[i + 1]
         linknode = lookup(curr)
         for c in self.nodechunk(rlog, curr, prev, linknode):
             yield c
 
     yield self.close()
 
 class shallowcg1packer(changegroup.cgpacker):
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
-        if constants.SHALLOWREPO_REQUIREMENT in self._repo.requirements:
+        if shallowutil.isenabled(self._repo):
             fastpathlinkrev = False
 
         return super(shallowcg1packer, self).generate(commonrevs, clnodes,
             fastpathlinkrev, source)
 
     def group(self, nodelist, rlog, lookup, units=None, reorder=None):
         return shallowgroup(shallowcg1packer, self, nodelist, rlog, lookup,
                             units=units)
 
     def generatefiles(self, changedfiles, *args):
         try:
             linknodes, commonrevs, source = args
         except ValueError:
             commonrevs, source, mfdicts, fastpathlinkrev, fnodes, clrevs = args
-        if constants.SHALLOWREPO_REQUIREMENT in self._repo.requirements:
+        if shallowutil.isenabled(self._repo):
             repo = self._repo
             if isinstance(repo, bundlerepo.bundlerepository):
                 # If the bundle contains filelogs, we can't pull from it, since
                 # bundlerepo is heavily tied to revlogs. Instead require that
                 # the user use unbundle instead.
                 # Force load the filelog data.
                 bundlerepo.bundlerepository.file(repo, 'foo')
                 if repo._cgfilespos:
                     raise error.Abort("cannot pull from full bundles",
                                       hint="use `hg unbundle` instead")
                 return []
             filestosend = self.shouldaddfilegroups(source)
             if filestosend == NoFiles:
                 changedfiles = list([f for f in changedfiles
                                      if not repo.shallowmatch(f)])
 
         return super(shallowcg1packer, self).generatefiles(
             changedfiles, *args)
 
     def shouldaddfilegroups(self, source):
         repo = self._repo
-        if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+        if not shallowutil.isenabled(repo):
             return AllFiles
 
         if source == "push" or source == "bundle":
             return AllFiles
 
         caps = self._bundlecaps or []
         if source == "serve" or source == "pull":
             if constants.BUNDLE2_CAPABLITY in caps:
                 return LocalFiles
             else:
                 # Serving to a full repo requires us to serve everything
                 repo.ui.warn(_("pulling from a shallow repo\n"))
                 return AllFiles
 
         return NoFiles
 
     def prune(self, rlog, missing, commonrevs):
         if not isinstance(rlog, remotefilelog.remotefilelog):
             return super(shallowcg1packer, self).prune(rlog, missing,
                 commonrevs)
 
         repo = self._repo
         results = []
         for fnode in missing:
             fctx = repo.filectx(rlog.filename, fileid=fnode)
             if fctx.linkrev() not in commonrevs:
                 results.append(fnode)
         return results
 
     def nodechunk(self, revlog, node, prevnode, linknode):
         prefix = ''
         if prevnode == nullid:
             delta = revlog.revision(node, raw=True)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             # Actually uses remotefilelog.revdiff which works on nodes, not revs
             delta = revlog.revdiff(prevnode, node)
         p1, p2 = revlog.parents(node)
         flags = revlog.flags(node)
         meta = self.builddeltaheader(node, p1, p2, prevnode, linknode, flags)
         meta += prefix
         l = len(meta) + len(delta)
         yield changegroup.chunkheader(l)
         yield meta
         yield delta
 
 def makechangegroup(orig, repo, outgoing, version, source, *args, **kwargs):
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not shallowutil.isenabled(repo):
         return orig(repo, outgoing, version, source, *args, **kwargs)
 
     original = repo.shallowmatch
     try:
         # if serving, only send files the clients has patterns for
         if source == 'serve':
             bundlecaps = kwargs.get('bundlecaps')
             includepattern = None
             excludepattern = None
             for cap in (bundlecaps or []):
                 if cap.startswith("includepattern="):
                     raw = cap[len("includepattern="):]
                     if raw:
                         includepattern = raw.split('\0')
                 elif cap.startswith("excludepattern="):
                     raw = cap[len("excludepattern="):]
                     if raw:
                         excludepattern = raw.split('\0')
             if includepattern or excludepattern:
                 repo.shallowmatch = match.match(repo.root, '', None,
                     includepattern, excludepattern)
             else:
                 repo.shallowmatch = match.always(repo.root, '')
         return orig(repo, outgoing, version, source, *args, **kwargs)
     finally:
         repo.shallowmatch = original
 
 def addchangegroupfiles(orig, repo, source, revmap, trp, expectedfiles, *args):
-    if not constants.SHALLOWREPO_REQUIREMENT in repo.requirements:
+    if not shallowutil.isenabled(repo):
         return orig(repo, source, revmap, trp, expectedfiles, *args)
 
     files = 0
     newfiles = 0
     visited = set()
     revisiondatas = {}
     queue = []
 
     # Normal Mercurial processes each file one at a time, adding all
     # the new revisions for that file at once. In remotefilelog a file
     # revision may depend on a different file's revision (in the case
     # of a rename/copy), so we must lay all revisions down across all
     # files in topological order.
 
     # read all the file chunks but don't add them
     while True:
         chunkdata = source.filelogheader()
         if not chunkdata:
             break
         files += 1
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         repo.ui.progress(_('files'), files, total=expectedfiles)
 
         if not repo.shallowmatch(f):
             fl = repo.file(f)
             deltas = source.deltaiter()
             fl.addgroup(deltas, revmap, trp)
             continue
 
         chain = None
         while True:
             # returns: (node, p1, p2, cs, deltabase, delta, flags) or None
             revisiondata = source.deltachunk(chain)
             if not revisiondata:
                 break
 
             chain = revisiondata[0]
 
             revisiondatas[(f, chain)] = revisiondata
             queue.append((f, chain))
 
             if f not in visited:
                 newfiles += 1
                 visited.add(f)
 
         if chain is None:
             raise error.Abort(_("received file revlog group is empty"))
 
     processed = set()
     def available(f, node, depf, depnode):
         if depnode != nullid and (depf, depnode) not in processed:
             if not (depf, depnode) in revisiondatas:
                 # It's not in the changegroup, assume it's already
                 # in the repo
                 return True
             # re-add self to queue
             queue.insert(0, (f, node))
             # add dependency in front
             queue.insert(0, (depf, depnode))
             return False
         return True
 
     skipcount = 0
 
     # Prefetch the non-bundled revisions that we will need
     prefetchfiles = []
     for f, node in queue:
         revisiondata = revisiondatas[(f, node)]
         # revisiondata: (node, p1, p2, cs, deltabase, delta, flags)
         dependents = [revisiondata[1], revisiondata[2], revisiondata[4]]
 
         for dependent in dependents:
             if dependent == nullid or (f, dependent) in revisiondatas:
                 continue
             prefetchfiles.append((f, hex(dependent)))
 
     repo.fileservice.prefetch(prefetchfiles)
 
     # Apply the revisions in topological order such that a revision
     # is only written once it's deltabase and parents have been written.
     while queue:
         f, node = queue.pop(0)
         if (f, node) in processed:
             continue
 
         skipcount += 1
         if skipcount > len(queue) + 1:
             raise error.Abort(_("circular node dependency"))
 
         fl = repo.file(f)
 
         revisiondata = revisiondatas[(f, node)]
         # revisiondata: (node, p1, p2, cs, deltabase, delta, flags)
         node, p1, p2, linknode, deltabase, delta, flags = revisiondata
 
         if not available(f, node, f, deltabase):
             continue
 
         base = fl.revision(deltabase, raw=True)
         text = mdiff.patch(base, delta)
         if isinstance(text, buffer):
             text = str(text)
 
         meta, text = shallowutil.parsemeta(text)
         if 'copy' in meta:
             copyfrom = meta['copy']
             copynode = bin(meta['copyrev'])
             if not available(f, node, copyfrom, copynode):
                 continue
 
         for p in [p1, p2]:
             if p != nullid:
                 if not available(f, node, f, p):
                     continue
 
         fl.add(text, meta, trp, linknode, p1, p2)
         processed.add((f, node))
         skipcount = 0
 
     repo.ui.progress(_('files'), None)
 
     return len(revisiondatas), newfiles

hgext/remotefilelog/shallowutil.py

@@ -1,487 +1,491 b''
 # shallowutil.py -- remotefilelog utilities
 #
 # Copyright 2014 Facebook, Inc.
 #
 # 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 collections
 import errno
 import hashlib
 import os
 import stat
 import struct
 import tempfile
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     pycompat,
     revlog,
     util,
 )
 from mercurial.utils import (
     storageutil,
     stringutil,
 )
 from . import constants
 
 if not pycompat.iswindows:
     import grp
 
+def isenabled(repo):
+    """returns whether the repository is remotefilelog enabled or not"""
+    return constants.SHALLOWREPO_REQUIREMENT in repo.requirements
+
 def getcachekey(reponame, file, id):
     pathhash = hashlib.sha1(file).hexdigest()
     return os.path.join(reponame, pathhash[:2], pathhash[2:], id)
 
 def getlocalkey(file, id):
     pathhash = hashlib.sha1(file).hexdigest()
     return os.path.join(pathhash, id)
 
 def getcachepath(ui, allowempty=False):
     cachepath = ui.config("remotefilelog", "cachepath")
     if not cachepath:
         if allowempty:
             return None
         else:
             raise error.Abort(_("could not find config option "
                                 "remotefilelog.cachepath"))
     return util.expandpath(cachepath)
 
 def getcachepackpath(repo, category):
     cachepath = getcachepath(repo.ui)
     if category != constants.FILEPACK_CATEGORY:
         return os.path.join(cachepath, repo.name, 'packs', category)
     else:
         return os.path.join(cachepath, repo.name, 'packs')
 
 def getlocalpackpath(base, category):
     return os.path.join(base, 'packs', category)
 
 def createrevlogtext(text, copyfrom=None, copyrev=None):
     """returns a string that matches the revlog contents in a
     traditional revlog
     """
     meta = {}
     if copyfrom or text.startswith('\1\n'):
         if copyfrom:
             meta['copy'] = copyfrom
             meta['copyrev'] = copyrev
         text = storageutil.packmeta(meta, text)
 
     return text
 
 def parsemeta(text):
     """parse mercurial filelog metadata"""
     meta, size = storageutil.parsemeta(text)
     if text.startswith('\1\n'):
         s = text.index('\1\n', 2)
         text = text[s + 2:]
     return meta or {}, text
 
 def sumdicts(*dicts):
     """Adds all the values of *dicts together into one dictionary. This assumes
     the values in *dicts are all summable.
 
     e.g. [{'a': 4', 'b': 2}, {'b': 3, 'c': 1}] -> {'a': 4, 'b': 5, 'c': 1}
     """
     result = collections.defaultdict(lambda: 0)
     for dict in dicts:
         for k, v in dict.iteritems():
             result[k] += v
     return result
 
 def prefixkeys(dict, prefix):
     """Returns ``dict`` with ``prefix`` prepended to all its keys."""
     result = {}
     for k, v in dict.iteritems():
         result[prefix + k] = v
     return result
 
 def reportpackmetrics(ui, prefix, *stores):
     dicts = [s.getmetrics() for s in stores]
     dict = prefixkeys(sumdicts(*dicts), prefix + '_')
     ui.log(prefix + "_packsizes", "", **dict)
 
 def _parsepackmeta(metabuf):
     """parse datapack meta, bytes (<metadata-list>) -> dict
 
     The dict contains raw content - both keys and values are strings.
     Upper-level business may want to convert some of them to other types like
     integers, on their own.
 
     raise ValueError if the data is corrupted
     """
     metadict = {}
     offset = 0
     buflen = len(metabuf)
     while buflen - offset >= 3:
         key = metabuf[offset]
         offset += 1
         metalen = struct.unpack_from('!H', metabuf, offset)[0]
         offset += 2
         if offset + metalen > buflen:
             raise ValueError('corrupted metadata: incomplete buffer')
         value = metabuf[offset:offset + metalen]
         metadict[key] = value
         offset += metalen
     if offset != buflen:
         raise ValueError('corrupted metadata: redundant data')
     return metadict
 
 def _buildpackmeta(metadict):
     """reverse of _parsepackmeta, dict -> bytes (<metadata-list>)
 
     The dict contains raw content - both keys and values are strings.
     Upper-level business may want to serialize some of other types (like
     integers) to strings before calling this function.
 
     raise ProgrammingError when metadata key is illegal, or ValueError if
     length limit is exceeded
     """
     metabuf = ''
     for k, v in sorted((metadict or {}).iteritems()):
         if len(k) != 1:
             raise error.ProgrammingError('packmeta: illegal key: %s' % k)
         if len(v) > 0xfffe:
             raise ValueError('metadata value is too long: 0x%x > 0xfffe'
                              % len(v))
         metabuf += k
         metabuf += struct.pack('!H', len(v))
         metabuf += v
     # len(metabuf) is guaranteed representable in 4 bytes, because there are
     # only 256 keys, and for each value, len(value) <= 0xfffe.
     return metabuf
 
 _metaitemtypes = {
     constants.METAKEYFLAG: (int, long),
     constants.METAKEYSIZE: (int, long),
 }
 
 def buildpackmeta(metadict):
     """like _buildpackmeta, but typechecks metadict and normalize it.
 
     This means, METAKEYSIZE and METAKEYSIZE should have integers as values,
     and METAKEYFLAG will be dropped if its value is 0.
     """
     newmeta = {}
     for k, v in (metadict or {}).iteritems():
         expectedtype = _metaitemtypes.get(k, (bytes,))
         if not isinstance(v, expectedtype):
             raise error.ProgrammingError('packmeta: wrong type of key %s' % k)
         # normalize int to binary buffer
         if int in expectedtype:
             # optimization: remove flag if it's 0 to save space
             if k == constants.METAKEYFLAG and v == 0:
                 continue
             v = int2bin(v)
         newmeta[k] = v
     return _buildpackmeta(newmeta)
 
 def parsepackmeta(metabuf):
     """like _parsepackmeta, but convert fields to desired types automatically.
 
     This means, METAKEYFLAG and METAKEYSIZE fields will be converted to
     integers.
     """
     metadict = _parsepackmeta(metabuf)
     for k, v in metadict.iteritems():
         if k in _metaitemtypes and int in _metaitemtypes[k]:
             metadict[k] = bin2int(v)
     return metadict
 
 def int2bin(n):
     """convert a non-negative integer to raw binary buffer"""
     buf = bytearray()
     while n > 0:
         buf.insert(0, n & 0xff)
         n >>= 8
     return bytes(buf)
 
 def bin2int(buf):
     """the reverse of int2bin, convert a binary buffer to an integer"""
     x = 0
     for b in bytearray(buf):
         x <<= 8
         x |= b
     return x
 
 def parsesizeflags(raw):
     """given a remotefilelog blob, return (headersize, rawtextsize, flags)
 
     see remotefilelogserver.createfileblob for the format.
     raise RuntimeError if the content is illformed.
     """
     flags = revlog.REVIDX_DEFAULT_FLAGS
     size = None
     try:
         index = raw.index('\0')
         header = raw[:index]
         if header.startswith('v'):
             # v1 and above, header starts with 'v'
             if header.startswith('v1\n'):
                 for s in header.split('\n'):
                     if s.startswith(constants.METAKEYSIZE):
                         size = int(s[len(constants.METAKEYSIZE):])
                     elif s.startswith(constants.METAKEYFLAG):
                         flags = int(s[len(constants.METAKEYFLAG):])
             else:
                 raise RuntimeError('unsupported remotefilelog header: %s'
                                    % header)
         else:
             # v0, str(int(size)) is the header
             size = int(header)
     except ValueError:
         raise RuntimeError("unexpected remotefilelog header: illegal format")
     if size is None:
         raise RuntimeError("unexpected remotefilelog header: no size found")
     return index + 1, size, flags
 
 def buildfileblobheader(size, flags, version=None):
     """return the header of a remotefilelog blob.
 
     see remotefilelogserver.createfileblob for the format.
     approximately the reverse of parsesizeflags.
 
     version could be 0 or 1, or None (auto decide).
     """
     # choose v0 if flags is empty, otherwise v1
     if version is None:
         version = int(bool(flags))
     if version == 1:
         header = ('v1\n%s%d\n%s%d'
                   % (constants.METAKEYSIZE, size,
                      constants.METAKEYFLAG, flags))
     elif version == 0:
         if flags:
             raise error.ProgrammingError('fileblob v0 does not support flag')
         header = '%d' % size
     else:
         raise error.ProgrammingError('unknown fileblob version %d' % version)
     return header
 
 def ancestormap(raw):
     offset, size, flags = parsesizeflags(raw)
     start = offset + size
 
     mapping = {}
     while start < len(raw):
         divider = raw.index('\0', start + 80)
 
         currentnode = raw[start:(start + 20)]
         p1 = raw[(start + 20):(start + 40)]
         p2 = raw[(start + 40):(start + 60)]
         linknode = raw[(start + 60):(start + 80)]
         copyfrom = raw[(start + 80):divider]
 
         mapping[currentnode] = (p1, p2, linknode, copyfrom)
         start = divider + 1
 
     return mapping
 
 def readfile(path):
     f = open(path, 'rb')
     try:
         result = f.read()
 
         # we should never have empty files
         if not result:
             os.remove(path)
             raise IOError("empty file: %s" % path)
 
         return result
     finally:
         f.close()
 
 def unlinkfile(filepath):
     if pycompat.iswindows:
         # On Windows, os.unlink cannnot delete readonly files
         os.chmod(filepath, stat.S_IWUSR)
     os.unlink(filepath)
 
 def renamefile(source, destination):
     if pycompat.iswindows:
         # On Windows, os.rename cannot rename readonly files
         # and cannot overwrite destination if it exists
         os.chmod(source, stat.S_IWUSR)
         if os.path.isfile(destination):
             os.chmod(destination, stat.S_IWUSR)
             os.unlink(destination)
 
     os.rename(source, destination)
 
 def writefile(path, content, readonly=False):
     dirname, filename = os.path.split(path)
     if not os.path.exists(dirname):
         try:
             os.makedirs(dirname)
         except OSError as ex:
             if ex.errno != errno.EEXIST:
                 raise
 
     fd, temp = tempfile.mkstemp(prefix='.%s-' % filename, dir=dirname)
     os.close(fd)
 
     try:
         f = util.posixfile(temp, 'wb')
         f.write(content)
         f.close()
 
         if readonly:
             mode = 0o444
         else:
             # tempfiles are created with 0o600, so we need to manually set the
             # mode.
             oldumask = os.umask(0)
             # there's no way to get the umask without modifying it, so set it
             # back
             os.umask(oldumask)
             mode = ~oldumask
 
         renamefile(temp, path)
         os.chmod(path, mode)
     except Exception:
         try:
             unlinkfile(temp)
         except OSError:
             pass
         raise
 
 def sortnodes(nodes, parentfunc):
     """Topologically sorts the nodes, using the parentfunc to find
     the parents of nodes."""
     nodes = set(nodes)
     childmap = {}
     parentmap = {}
     roots = []
 
     # Build a child and parent map
     for n in nodes:
         parents = [p for p in parentfunc(n) if p in nodes]
         parentmap[n] = set(parents)
         for p in parents:
             childmap.setdefault(p, set()).add(n)
         if not parents:
             roots.append(n)
 
     roots.sort()
     # Process roots, adding children to the queue as they become roots
     results = []
     while roots:
         n = roots.pop(0)
         results.append(n)
         if n in childmap:
             children = childmap[n]
             for c in children:
                 childparents = parentmap[c]
                 childparents.remove(n)
                 if len(childparents) == 0:
                     # insert at the beginning, that way child nodes
                     # are likely to be output immediately after their
                     # parents.  This gives better compression results.
                     roots.insert(0, c)
 
     return results
 
 def readexactly(stream, n):
     '''read n bytes from stream.read and abort if less was available'''
     s = stream.read(n)
     if len(s) < n:
         raise error.Abort(_("stream ended unexpectedly"
                            " (got %d bytes, expected %d)")
                           % (len(s), n))
     return s
 
 def readunpack(stream, fmt):
     data = readexactly(stream, struct.calcsize(fmt))
     return struct.unpack(fmt, data)
 
 def readpath(stream):
     rawlen = readexactly(stream, constants.FILENAMESIZE)
     pathlen = struct.unpack(constants.FILENAMESTRUCT, rawlen)[0]
     return readexactly(stream, pathlen)
 
 def readnodelist(stream):
     rawlen = readexactly(stream, constants.NODECOUNTSIZE)
     nodecount = struct.unpack(constants.NODECOUNTSTRUCT, rawlen)[0]
     for i in pycompat.xrange(nodecount):
         yield readexactly(stream, constants.NODESIZE)
 
 def readpathlist(stream):
     rawlen = readexactly(stream, constants.PATHCOUNTSIZE)
     pathcount = struct.unpack(constants.PATHCOUNTSTRUCT, rawlen)[0]
     for i in pycompat.xrange(pathcount):
         yield readpath(stream)
 
 def getgid(groupname):
     try:
         gid = grp.getgrnam(groupname).gr_gid
         return gid
     except KeyError:
         return None
 
 def setstickygroupdir(path, gid, warn=None):
     if gid is None:
         return
     try:
         os.chown(path, -1, gid)
         os.chmod(path, 0o2775)
     except (IOError, OSError) as ex:
         if warn:
             warn(_('unable to chown/chmod on %s: %s\n') % (path, ex))
 
 def mkstickygroupdir(ui, path):
     """Creates the given directory (if it doesn't exist) and give it a
     particular group with setgid enabled."""
     gid = None
     groupname = ui.config("remotefilelog", "cachegroup")
     if groupname:
         gid = getgid(groupname)
         if gid is None:
             ui.warn(_('unable to resolve group name: %s\n') % groupname)
 
     # we use a single stat syscall to test the existence and mode / group bit
     st = None
     try:
         st = os.stat(path)
     except OSError:
         pass
 
     if st:
         # exists
         if (st.st_mode & 0o2775) != 0o2775 or st.st_gid != gid:
             # permission needs to be fixed
             setstickygroupdir(path, gid, ui.warn)
         return
 
     oldumask = os.umask(0o002)
     try:
         missingdirs = [path]
         path = os.path.dirname(path)
         while path and not os.path.exists(path):
             missingdirs.append(path)
             path = os.path.dirname(path)
 
         for path in reversed(missingdirs):
             try:
                 os.mkdir(path)
             except OSError as ex:
                 if ex.errno != errno.EEXIST:
                     raise
 
         for path in missingdirs:
             setstickygroupdir(path, gid, ui.warn)
     finally:
         os.umask(oldumask)
 
 def getusername(ui):
     try:
         return stringutil.shortuser(ui.username())
     except Exception:
         return 'unknown'
 
 def getreponame(ui):
     reponame = ui.config('paths', 'default')
     if reponame:
         return os.path.basename(reponame)
     return "unknown"