def censor(ui, repo, path, rev='', tombstone='', **opts):
if not path:
raise util.Abort(_('must specify file path to censor'))
if not rev:
raise util.Abort(_('must specify revision to censor'))
wctx = repo[None]
m = scmutil.match(wctx, (path,))
if m.anypats() or len(m.files()) != 1:
raise util.Abort(_('can only specify an explicit filename'))
path = m.files()[0]
flog = repo.file(path)
if not len(flog):
raise util.Abort(_('cannot censor file with no history'))
rev = scmutil.revsingle(repo, rev, rev).rev()
try:
ctx = repo[rev]
except KeyError:
raise util.Abort(_('invalid revision identifier %s') % rev)
try:
fctx = ctx.filectx(path)
except error.LookupError:
raise util.Abort(_('file does not exist at revision %s') % rev)
fnode = fctx.filenode()
headctxs = [repo[c] for c in repo.heads()]
heads = [c for c in headctxs if path in c and c.filenode(path) == fnode]
if heads:
headlist = ', '.join([short(c.node()) for c in heads])
raise util.Abort(_('cannot censor file in heads (%s)') % headlist,
hint=_('clean/delete and commit first'))
wp = wctx.parents()
if ctx.node() in [p.node() for p in wp]:
raise util.Abort(_('cannot censor working directory'),
hint=_('clean/delete/update first'))
flogv = flog.version & 0xFFFF
if flogv != revlog.REVLOGNG:
raise util.Abort(
_('censor does not support revlog version %d') % (flogv,))
tombstone = filelog.packmeta({"censored": tombstone}, "")
crev = fctx.filerev()
if len(tombstone) > flog.rawsize(crev):
raise util.Abort(_(
'censor tombstone must be no longer than censored data'))
# Using two files instead of one makes it easy to rewrite entry-by-entry
idxread = repo.svfs(flog.indexfile, 'r')
idxwrite = repo.svfs(flog.indexfile, 'wb', atomictemp=True)
if flog.version & revlog.REVLOGNGINLINEDATA:
dataread, datawrite = idxread, idxwrite
else:
dataread = repo.svfs(flog.datafile, 'r')
datawrite = repo.svfs(flog.datafile, 'wb', atomictemp=True)
# Copy all revlog data up to the entry to be censored.
rio = revlog.revlogio()
offset = flog.start(crev)
for chunk in util.filechunkiter(idxread, limit=crev * rio.size):
idxwrite.write(chunk)
for chunk in util.filechunkiter(dataread, limit=offset):
datawrite.write(chunk)
def rewriteindex(r, newoffs, newdata=None):
"""Rewrite the index entry with a new data offset and optional new data.
The newdata argument, if given, is a tuple of three positive integers:
(new compressed, new uncompressed, added flag bits).
"""
offlags, comp, uncomp, base, link, p1, p2, nodeid = flog.index[r]
flags = revlog.gettype(offlags)
if newdata:
comp, uncomp, nflags = newdata
flags |= nflags
offlags = revlog.offset_type(newoffs, flags)
e = (offlags, comp, uncomp, r, link, p1, p2, nodeid)
idxwrite.write(rio.packentry(e, None, flog.version, r))
idxread.seek(rio.size, 1)
def rewrite(r, offs, data, nflags=revlog.REVIDX_DEFAULT_FLAGS):
"""Write the given full text to the filelog with the given data offset.
Returns:
The integer number of data bytes written, for tracking data offsets.
"""
flag, compdata = flog.compress(data)
newcomp = len(flag) + len(compdata)
rewriteindex(r, offs, (newcomp, len(data), nflags))
datawrite.write(flag)
datawrite.write(compdata)
dataread.seek(flog.length(r), 1)
return newcomp
# Rewrite censored revlog entry with (padded) tombstone data.
pad = ' ' * (flog.rawsize(crev) - len(tombstone))
offset += rewrite(crev, offset, tombstone + pad, revlog.REVIDX_ISCENSORED)
# Rewrite all following filelog revisions fixing up offsets and deltas.
for srev in xrange(crev + 1, len(flog)):
if crev in flog.parentrevs(srev):
# Immediate children of censored node must be re-added as fulltext.
try:
revdata = flog.revision(srev)
except error.CensoredNodeError as e:
revdata = e.tombstone
dlen = rewrite(srev, offset, revdata)
else:
# Copy any other revision data verbatim after fixing up the offset.
rewriteindex(srev, offset)
dlen = flog.length(srev)
for chunk in util.filechunkiter(dataread, limit=dlen):
datawrite.write(chunk)
offset += dlen
idxread.close()
idxwrite.close()
if dataread is not idxread:
dataread.close()
datawrite.close()
def _docensor(ui, repo, path, rev='', tombstone='', **opts):
if not path:
raise error.Abort(_('must specify file path to censor'))
if not rev:
raise error.Abort(_('must specify revision to censor'))
wctx = repo[None]
m = scmutil.match(wctx, (path,))
if m.anypats() or len(m.files()) != 1:
raise error.Abort(_('can only specify an explicit filename'))
path = m.files()[0]
flog = repo.file(path)
if not len(flog):
raise error.Abort(_('cannot censor file with no history'))
rev = scmutil.revsingle(repo, rev, rev).rev()
try:
ctx = repo[rev]
except KeyError:
raise error.Abort(_('invalid revision identifier %s') % rev)
try:
fctx = ctx.filectx(path)
except error.LookupError:
raise error.Abort(_('file does not exist at revision %s') % rev)
fnode = fctx.filenode()
headctxs = [repo[c] for c in repo.heads()]
heads = [c for c in headctxs if path in c and c.filenode(path) == fnode]
if heads:
headlist = ', '.join([short(c.node()) for c in heads])
raise error.Abort(_('cannot censor file in heads (%s)') % headlist,
hint=_('clean/delete and commit first'))
wp = wctx.parents()
if ctx.node() in [p.node() for p in wp]:
raise error.Abort(_('cannot censor working directory'),
hint=_('clean/delete/update first'))
flogv = flog.version & 0xFFFF
if flogv != revlog.REVLOGNG:
raise error.Abort(
_('censor does not support revlog version %d') % (flogv,))
tombstone = filelog.packmeta({"censored": tombstone}, "")
crev = fctx.filerev()
if len(tombstone) > flog.rawsize(crev):
raise error.Abort(_(
'censor tombstone must be no longer than censored data'))
# Using two files instead of one makes it easy to rewrite entry-by-entry
idxread = repo.svfs(flog.indexfile, 'r')
idxwrite = repo.svfs(flog.indexfile, 'wb', atomictemp=True)
if flog.version & revlog.REVLOGNGINLINEDATA:
dataread, datawrite = idxread, idxwrite
else:
dataread = repo.svfs(flog.datafile, 'r')
datawrite = repo.svfs(flog.datafile, 'wb', atomictemp=True)
# Copy all revlog data up to the entry to be censored.
rio = revlog.revlogio()
offset = flog.start(crev)
for chunk in util.filechunkiter(idxread, limit=crev * rio.size):
idxwrite.write(chunk)
for chunk in util.filechunkiter(dataread, limit=offset):
datawrite.write(chunk)
def rewriteindex(r, newoffs, newdata=None):
"""Rewrite the index entry with a new data offset and optional new data.
The newdata argument, if given, is a tuple of three positive integers:
(new compressed, new uncompressed, added flag bits).
"""
offlags, comp, uncomp, base, link, p1, p2, nodeid = flog.index[r]
flags = revlog.gettype(offlags)
if newdata:
comp, uncomp, nflags = newdata
flags |= nflags
offlags = revlog.offset_type(newoffs, flags)
e = (offlags, comp, uncomp, r, link, p1, p2, nodeid)
idxwrite.write(rio.packentry(e, None, flog.version, r))
idxread.seek(rio.size, 1)
def rewrite(r, offs, data, nflags=revlog.REVIDX_DEFAULT_FLAGS):
"""Write the given full text to the filelog with the given data offset.
Returns:
The integer number of data bytes written, for tracking data offsets.
"""
flag, compdata = flog.compress(data)
newcomp = len(flag) + len(compdata)
rewriteindex(r, offs, (newcomp, len(data), nflags))
datawrite.write(flag)
datawrite.write(compdata)
dataread.seek(flog.length(r), 1)
return newcomp
# Rewrite censored revlog entry with (padded) tombstone data.
pad = ' ' * (flog.rawsize(crev) - len(tombstone))
offset += rewrite(crev, offset, tombstone + pad, revlog.REVIDX_ISCENSORED)
# Rewrite all following filelog revisions fixing up offsets and deltas.
for srev in xrange(crev + 1, len(flog)):
if crev in flog.parentrevs(srev):
# Immediate children of censored node must be re-added as fulltext.
try:
revdata = flog.revision(srev)
except error.CensoredNodeError as e:
revdata = e.tombstone
dlen = rewrite(srev, offset, revdata)
else:
# Copy any other revision data verbatim after fixing up the offset.
rewriteindex(srev, offset)
dlen = flog.length(srev)
for chunk in util.filechunkiter(dataread, limit=dlen):
datawrite.write(chunk)
offset += dlen
idxread.close()
idxwrite.close()
if dataread is not idxread:
dataread.close()
datawrite.close()
def perfrevlogindex(ui, repo, file_=None, **opts):
"""Benchmark operations against a revlog index.
This tests constructing a revlog instance, reading index data,
parsing index data, and performing various operations related to
index data.
"""
rl = cmdutil.openrevlog(repo, 'perfrevlogindex', file_, opts)
opener = getattr(rl, 'opener') # trick linter
indexfile = rl.indexfile
data = opener.read(indexfile)
header = struct.unpack('>I', data[0:4])[0]
version = header & 0xFFFF
if version == 1:
revlogio = revlog.revlogio()
inline = header & (1 << 16)
else:
raise error.Abort(('unsupported revlog version: %d') % version)
rllen = len(rl)
node0 = rl.node(0)
node25 = rl.node(rllen // 4)
node50 = rl.node(rllen // 2)
node75 = rl.node(rllen // 4 * 3)
node100 = rl.node(rllen - 1)
allrevs = range(rllen)
allrevsrev = list(reversed(allrevs))
allnodes = [rl.node(rev) for rev in range(rllen)]
allnodesrev = list(reversed(allnodes))
def constructor():
revlog.revlog(opener, indexfile)
def read():
with opener(indexfile) as fh:
fh.read()
def parseindex():
revlogio.parseindex(data, inline)
def getentry(revornode):
index = revlogio.parseindex(data, inline)[0]
index[revornode]
def getentries(revs, count=1):
index = revlogio.parseindex(data, inline)[0]
for i in range(count):
for rev in revs:
index[rev]
def resolvenode(node):
nodemap = revlogio.parseindex(data, inline)[1]
# This only works for the C code.
if nodemap is None:
return
try:
nodemap[node]
except error.RevlogError:
pass
def resolvenodes(nodes, count=1):
nodemap = revlogio.parseindex(data, inline)[1]
if nodemap is None:
return
for i in range(count):
for node in nodes:
try:
nodemap[node]
except error.RevlogError:
pass
benches = [
(constructor, 'revlog constructor'),
(read, 'read'),
(parseindex, 'create index object'),
(lambda: getentry(0), 'retrieve index entry for rev 0'),
(lambda: resolvenode('a' * 20), 'look up missing node'),
(lambda: resolvenode(node0), 'look up node at rev 0'),
(lambda: resolvenode(node25), 'look up node at 1/4 len'),
(lambda: resolvenode(node50), 'look up node at 1/2 len'),
(lambda: resolvenode(node75), 'look up node at 3/4 len'),
(lambda: resolvenode(node100), 'look up node at tip'),
# 2x variation is to measure caching impact.
(lambda: resolvenodes(allnodes),
'look up all nodes (forward)'),
(lambda: resolvenodes(allnodes, 2),
'look up all nodes 2x (forward)'),
(lambda: resolvenodes(allnodesrev),
'look up all nodes (reverse)'),
(lambda: resolvenodes(allnodesrev, 2),
'look up all nodes 2x (reverse)'),
(lambda: getentries(allrevs),
'retrieve all index entries (forward)'),
(lambda: getentries(allrevs, 2),
'retrieve all index entries 2x (forward)'),
(lambda: getentries(allrevsrev),
'retrieve all index entries (reverse)'),
(lambda: getentries(allrevsrev, 2),
'retrieve all index entries 2x (reverse)'),
]
for fn, title in benches:
timer, fm = gettimer(ui, opts)
timer(fn, title=title)
fm.end()