Mercurial > hg
view hgext/censor.py @ 27764:dd0c5f4d1b53
util: adjust 'datapath' to be correct in a frozen OS X package
Apparently unlike py2exe, py2app copies the Mercurial source tree as-is to a
Contents/Resources subdirectory of an app bundle, and places its binary stub in
Contents/MacOS. (The Windows install has the 'hgext' and 'mercurial' modules in
'lib/library.zip', while the help and templates subdirectories have been moved
out of the mercurial directory to the root of the installation. I assume that
the python code living in a zip file is why "py2exe doesn't support __file__".)
Therefore, prior to this change, Mercurial in a frozen app bundle on OS X would
go looking for help *.txt, templates and locale info in Contents/MacOS, where
they don't exist.
There are only a handful of places that test for frozen, and not all of them are
wrong for OS X, so it seems wiser to handle them on a case by case basis, rather
that try to change mainfrozen(). The remaining cases are:
1) util.hgexecutable() wrongly points to the bundled python executable, and
affects $HG in util.system() launched processes (e.g. external hooks)
2) util.hgcmd() wrongly points to the bundled python executable, but it seems
to only affect 'hg serve -d'
3) hook._pythonhook() may be OK, since I didn't see anything outrageous when
printing sys.path from an internal hook. I'm not sure if this special
case is needed on OS X though.
4) sslutil._plainapplepython() is OK, because sys.executable is not
/usr/bin/python, nor is it in /System/Library/Frameworks
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Sun, 10 Jan 2016 17:49:01 -0500 |
parents | 525d9b3f0a31 |
children | 5166b7a84b72 |
line wrap: on
line source
# Copyright (C) 2015 - Mike Edgar <adgar@google.com> # # This extension enables removal of file content at a given revision, # rewriting the data/metadata of successive revisions to preserve revision log # integrity. """erase file content at a given revision The censor command instructs Mercurial to erase all content of a file at a given revision *without updating the changeset hash.* This allows existing history to remain valid while preventing future clones/pulls from receiving the erased data. Typical uses for censor are due to security or legal requirements, including:: * Passwords, private keys, cryptographic material * Licensed data/code/libraries for which the license has expired * Personally Identifiable Information or other private data Censored nodes can interrupt mercurial's typical operation whenever the excised data needs to be materialized. Some commands, like ``hg cat``/``hg revert``, simply fail when asked to produce censored data. Others, like ``hg verify`` and ``hg update``, must be capable of tolerating censored data to continue to function in a meaningful way. Such commands only tolerate censored file revisions if they are allowed by the "censor.policy=ignore" config option. """ from mercurial.node import short from mercurial import cmdutil, error, filelog, revlog, scmutil, util from mercurial.i18n import _ from mercurial import lock as lockmod cmdtable = {} command = cmdutil.command(cmdtable) # Note for extension authors: ONLY specify testedwith = 'internal' 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 = 'internal' @command('censor', [('r', 'rev', '', _('censor file from specified revision'), _('REV')), ('t', 'tombstone', '', _('replacement tombstone data'), _('TEXT'))], _('-r REV [-t TEXT] [FILE]')) def censor(ui, repo, path, rev='', tombstone='', **opts): wlock = lock = None try: wlock = repo.wlock() lock = repo.lock() return _docensor(ui, repo, path, rev, tombstone, **opts) finally: lockmod.release(lock, wlock) 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()