annotate mercurial/verify.py @ 37080:1e30a26a65d0

filemerge: make the 'local' path match the format that 'base' and 'other' use

If we pass a separate '$output' arg to the merge tool, we produce four files:
local, base, other, and output.  In this situation, 'output' will be the
original filename, 'base' and 'other' are temporary files, and previously
'local' would be the backup file (so if 'output' was foo.txt, 'local' would be
foo.txt.orig).

This change makes it so that 'local' follows the same pattern as 'base' and
'other' - it will be a temporary file either in the
`experimental.mergetempdirprefix`-controlled directory with a name like
foo~local.txt, or in the normal system-wide temp dir with a name like
foo~local.RaNd0m.txt.

For the cases where the merge tool does not use an '$output' arg, 'local' is
still the destination filename, and 'base' and 'other' are unchanged.

The hope is that this is much easier for people to reason about; rather than
having a tool like Meld pop up with three panes, one of them with the filename
"foo.txt.orig", one with the filename "foo.txt", and one with
"foo~other.StuFf2.txt", we can (when the merge temp dir stuff is enabled) make
it show up as "foo~local.txt", "foo.txt" and "foo~other.txt", respectively.

This also opens the door to future customization, such as getting the
operation-provided labels and a hash prefix into the filenames (so we see
something like "foo~dest.abc123", "foo.txt", and "foo~src.d4e5f6").

Differential Revision: https://phab.mercurial-scm.org/D2889

# verify.py - repository integrity checking for Mercurial
#
# Copyright 2006, 2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os

from .i18n import _
from .node import (
    nullid,
    short,
)

from . import (
    error,
    pycompat,
    revlog,
    scmutil,
    util,
)

def verify(repo):
    with repo.lock():
        return verifier(repo).verify()

def _normpath(f):
    # under hg < 2.4, convert didn't sanitize paths properly, so a
    # converted repo may contain repeated slashes
    while '//' in f:
        f = f.replace('//', '/')
    return f

class verifier(object):
    # The match argument is always None in hg core, but e.g. the narrowhg
    # extension will pass in a matcher here.
    def __init__(self, repo, match=None):
        self.repo = repo.unfiltered()
        self.ui = repo.ui
        self.match = match or scmutil.matchall(repo)
        self.badrevs = set()
        self.errors = 0
        self.warnings = 0
        self.havecl = len(repo.changelog) > 0
        self.havemf = len(repo.manifestlog._revlog) > 0
        self.revlogv1 = repo.changelog.version != revlog.REVLOGV0
        self.lrugetctx = util.lrucachefunc(repo.changectx)
        self.refersmf = False
        self.fncachewarned = False
        # developer config: verify.skipflags
        self.skipflags = repo.ui.configint('verify', 'skipflags')

    def warn(self, msg):
        self.ui.warn(msg + "\n")
        self.warnings += 1

    def err(self, linkrev, msg, filename=None):
        if linkrev is not None:
            self.badrevs.add(linkrev)
            linkrev = "%d" % linkrev
        else:
            linkrev = '?'
        msg = "%s: %s" % (linkrev, msg)
        if filename:
            msg = "%s@%s" % (filename, msg)
        self.ui.warn(" " + msg + "\n")
        self.errors += 1

    def exc(self, linkrev, msg, inst, filename=None):
        fmsg = pycompat.bytestr(inst)
        if not fmsg:
            fmsg = pycompat.byterepr(inst)
        self.err(linkrev, "%s: %s" % (msg, fmsg), filename)

    def checklog(self, obj, name, linkrev):
        if not len(obj) and (self.havecl or self.havemf):
            self.err(linkrev, _("empty or missing %s") % name)
            return

        d = obj.checksize()
        if d[0]:
            self.err(None, _("data length off by %d bytes") % d[0], name)
        if d[1]:
            self.err(None, _("index contains %d extra bytes") % d[1], name)

        if obj.version != revlog.REVLOGV0:
            if not self.revlogv1:
                self.warn(_("warning: `%s' uses revlog format 1") % name)
        elif self.revlogv1:
            self.warn(_("warning: `%s' uses revlog format 0") % name)

    def checkentry(self, obj, i, node, seen, linkrevs, f):
        lr = obj.linkrev(obj.rev(node))
        if lr < 0 or (self.havecl and lr not in linkrevs):
            if lr < 0 or lr >= len(self.repo.changelog):
                msg = _("rev %d points to nonexistent changeset %d")
            else:
                msg = _("rev %d points to unexpected changeset %d")
            self.err(None, msg % (i, lr), f)
            if linkrevs:
                if f and len(linkrevs) > 1:
                    try:
                        # attempt to filter down to real linkrevs
                        linkrevs = [l for l in linkrevs
                                    if self.lrugetctx(l)[f].filenode() == node]
                    except Exception:
                        pass
                self.warn(_(" (expected %s)") % " ".join
                          (map(pycompat.bytestr, linkrevs)))
            lr = None # can't be trusted

        try:
            p1, p2 = obj.parents(node)
            if p1 not in seen and p1 != nullid:
                self.err(lr, _("unknown parent 1 %s of %s") %
                    (short(p1), short(node)), f)
            if p2 not in seen and p2 != nullid:
                self.err(lr, _("unknown parent 2 %s of %s") %
                    (short(p2), short(node)), f)
        except Exception as inst:
            self.exc(lr, _("checking parents of %s") % short(node), inst, f)

        if node in seen:
            self.err(lr, _("duplicate revision %d (%d)") % (i, seen[node]), f)
        seen[node] = i
        return lr

    def verify(self):
        repo = self.repo

        ui = repo.ui

        if not repo.url().startswith('file:'):
            raise error.Abort(_("cannot verify bundle or remote repos"))

        if os.path.exists(repo.sjoin("journal")):
            ui.warn(_("abandoned transaction found - run hg recover\n"))

        if ui.verbose or not self.revlogv1:
            ui.status(_("repository uses revlog format %d\n") %
                           (self.revlogv1 and 1 or 0))

        mflinkrevs, filelinkrevs = self._verifychangelog()

        filenodes = self._verifymanifest(mflinkrevs)
        del mflinkrevs

        self._crosscheckfiles(filelinkrevs, filenodes)

        totalfiles, filerevisions = self._verifyfiles(filenodes, filelinkrevs)

        ui.status(_("%d files, %d changesets, %d total revisions\n") %
                       (totalfiles, len(repo.changelog), filerevisions))
        if self.warnings:
            ui.warn(_("%d warnings encountered!\n") % self.warnings)
        if self.fncachewarned:
            ui.warn(_('hint: run "hg debugrebuildfncache" to recover from '
                      'corrupt fncache\n'))
        if self.errors:
            ui.warn(_("%d integrity errors encountered!\n") % self.errors)
            if self.badrevs:
                ui.warn(_("(first damaged changeset appears to be %d)\n")
                        % min(self.badrevs))
            return 1

    def _verifychangelog(self):
        ui = self.ui
        repo = self.repo
        match = self.match
        cl = repo.changelog

        ui.status(_("checking changesets\n"))
        mflinkrevs = {}
        filelinkrevs = {}
        seen = {}
        self.checklog(cl, "changelog", 0)
        total = len(repo)
        for i in repo:
            ui.progress(_('checking'), i, total=total, unit=_('changesets'))
            n = cl.node(i)
            self.checkentry(cl, i, n, seen, [i], "changelog")

            try:
                changes = cl.read(n)
                if changes[0] != nullid:
                    mflinkrevs.setdefault(changes[0], []).append(i)
                    self.refersmf = True
                for f in changes[3]:
                    if match(f):
                        filelinkrevs.setdefault(_normpath(f), []).append(i)
            except Exception as inst:
                self.refersmf = True
                self.exc(i, _("unpacking changeset %s") % short(n), inst)
        ui.progress(_('checking'), None)
        return mflinkrevs, filelinkrevs

    def _verifymanifest(self, mflinkrevs, dir="", storefiles=None,
                        progress=None):
        repo = self.repo
        ui = self.ui
        match = self.match
        mfl = self.repo.manifestlog
        mf = mfl._revlog.dirlog(dir)

        if not dir:
            self.ui.status(_("checking manifests\n"))

        filenodes = {}
        subdirnodes = {}
        seen = {}
        label = "manifest"
        if dir:
            label = dir
            revlogfiles = mf.files()
            storefiles.difference_update(revlogfiles)
            if progress: # should be true since we're in a subdirectory
                progress()
        if self.refersmf:
            # Do not check manifest if there are only changelog entries with
            # null manifests.
            self.checklog(mf, label, 0)
        total = len(mf)
        for i in mf:
            if not dir:
                ui.progress(_('checking'), i, total=total, unit=_('manifests'))
            n = mf.node(i)
            lr = self.checkentry(mf, i, n, seen, mflinkrevs.get(n, []), label)
            if n in mflinkrevs:
                del mflinkrevs[n]
            elif dir:
                self.err(lr, _("%s not in parent-directory manifest") %
                         short(n), label)
            else:
                self.err(lr, _("%s not in changesets") % short(n), label)

            try:
                mfdelta = mfl.get(dir, n).readdelta(shallow=True)
                for f, fn, fl in mfdelta.iterentries():
                    if not f:
                        self.err(lr, _("entry without name in manifest"))
                    elif f == "/dev/null":  # ignore this in very old repos
                        continue
                    fullpath = dir + _normpath(f)
                    if fl == 't':
                        if not match.visitdir(fullpath):
                            continue
                        subdirnodes.setdefault(fullpath + '/', {}).setdefault(
                            fn, []).append(lr)
                    else:
                        if not match(fullpath):
                            continue
                        filenodes.setdefault(fullpath, {}).setdefault(fn, lr)
            except Exception as inst:
                self.exc(lr, _("reading delta %s") % short(n), inst, label)
        if not dir:
            ui.progress(_('checking'), None)

        if self.havemf:
            for c, m in sorted([(c, m) for m in mflinkrevs
                        for c in mflinkrevs[m]]):
                if dir:
                    self.err(c, _("parent-directory manifest refers to unknown "
                                  "revision %s") % short(m), label)
                else:
                    self.err(c, _("changeset refers to unknown revision %s") %
                             short(m), label)

        if not dir and subdirnodes:
            self.ui.status(_("checking directory manifests\n"))
            storefiles = set()
            subdirs = set()
            revlogv1 = self.revlogv1
            for f, f2, size in repo.store.datafiles():
                if not f:
                    self.err(None, _("cannot decode filename '%s'") % f2)
                elif (size > 0 or not revlogv1) and f.startswith('meta/'):
                    storefiles.add(_normpath(f))
                    subdirs.add(os.path.dirname(f))
            subdircount = len(subdirs)
            currentsubdir = [0]
            def progress():
                currentsubdir[0] += 1
                ui.progress(_('checking'), currentsubdir[0], total=subdircount,
                            unit=_('manifests'))

        for subdir, linkrevs in subdirnodes.iteritems():
            subdirfilenodes = self._verifymanifest(linkrevs, subdir, storefiles,
                                                   progress)
            for f, onefilenodes in subdirfilenodes.iteritems():
                filenodes.setdefault(f, {}).update(onefilenodes)

        if not dir and subdirnodes:
            ui.progress(_('checking'), None)
            for f in sorted(storefiles):
                self.warn(_("warning: orphan revlog '%s'") % f)

        return filenodes

    def _crosscheckfiles(self, filelinkrevs, filenodes):
        repo = self.repo
        ui = self.ui
        ui.status(_("crosschecking files in changesets and manifests\n"))

        total = len(filelinkrevs) + len(filenodes)
        count = 0
        if self.havemf:
            for f in sorted(filelinkrevs):
                count += 1
                ui.progress(_('crosschecking'), count, total=total)
                if f not in filenodes:
                    lr = filelinkrevs[f][0]
                    self.err(lr, _("in changeset but not in manifest"), f)

        if self.havecl:
            for f in sorted(filenodes):
                count += 1
                ui.progress(_('crosschecking'), count, total=total)
                if f not in filelinkrevs:
                    try:
                        fl = repo.file(f)
                        lr = min([fl.linkrev(fl.rev(n)) for n in filenodes[f]])
                    except Exception:
                        lr = None
                    self.err(lr, _("in manifest but not in changeset"), f)

        ui.progress(_('crosschecking'), None)

    def _verifyfiles(self, filenodes, filelinkrevs):
        repo = self.repo
        ui = self.ui
        lrugetctx = self.lrugetctx
        revlogv1 = self.revlogv1
        havemf = self.havemf
        ui.status(_("checking files\n"))

        storefiles = set()
        for f, f2, size in repo.store.datafiles():
            if not f:
                self.err(None, _("cannot decode filename '%s'") % f2)
            elif (size > 0 or not revlogv1) and f.startswith('data/'):
                storefiles.add(_normpath(f))

        files = sorted(set(filenodes) | set(filelinkrevs))
        total = len(files)
        revisions = 0
        for i, f in enumerate(files):
            ui.progress(_('checking'), i, item=f, total=total, unit=_('files'))
            try:
                linkrevs = filelinkrevs[f]
            except KeyError:
                # in manifest but not in changelog
                linkrevs = []

            if linkrevs:
                lr = linkrevs[0]
            else:
                lr = None

            try:
                fl = repo.file(f)
            except error.RevlogError as e:
                self.err(lr, _("broken revlog! (%s)") % e, f)
                continue

            for ff in fl.files():
                try:
                    storefiles.remove(ff)
                except KeyError:
                    self.warn(_(" warning: revlog '%s' not in fncache!") % ff)
                    self.fncachewarned = True

            self.checklog(fl, f, lr)
            seen = {}
            rp = None
            for i in fl:
                revisions += 1
                n = fl.node(i)
                lr = self.checkentry(fl, i, n, seen, linkrevs, f)
                if f in filenodes:
                    if havemf and n not in filenodes[f]:
                        self.err(lr, _("%s not in manifests") % (short(n)), f)
                    else:
                        del filenodes[f][n]

                # Verify contents. 4 cases to care about:
                #
                #   common: the most common case
                #   rename: with a rename
                #   meta: file content starts with b'\1\n', the metadata
                #         header defined in filelog.py, but without a rename
                #   ext: content stored externally
                #
                # More formally, their differences are shown below:
                #
                #                       | common | rename | meta  | ext
                #  -------------------------------------------------------
                #   flags()             | 0      | 0      | 0     | not 0
                #   renamed()           | False  | True   | False | ?
                #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
                #
                # "rawtext" means the raw text stored in revlog data, which
                # could be retrieved by "revision(rev, raw=True)". "text"
                # mentioned below is "revision(rev, raw=False)".
                #
                # There are 3 different lengths stored physically:
                #  1. L1: rawsize, stored in revlog index
                #  2. L2: len(rawtext), stored in revlog data
                #  3. L3: len(text), stored in revlog data if flags==0, or
                #     possibly somewhere else if flags!=0
                #
                # L1 should be equal to L2. L3 could be different from them.
                # "text" may or may not affect commit hash depending on flag
                # processors (see revlog.addflagprocessor).
                #
                #              | common  | rename | meta  | ext
                # -------------------------------------------------
                #    rawsize() | L1      | L1     | L1    | L1
                #       size() | L1      | L2-LM  | L1(*) | L1 (?)
                # len(rawtext) | L2      | L2     | L2    | L2
                #    len(text) | L2      | L2     | L2    | L3
                #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
                #
                # LM:  length of metadata, depending on rawtext
                # (*): not ideal, see comment in filelog.size
                # (?): could be "- len(meta)" if the resolved content has
                #      rename metadata
                #
                # Checks needed to be done:
                #  1. length check: L1 == L2, in all cases.
                #  2. hash check: depending on flag processor, we may need to
                #     use either "text" (external), or "rawtext" (in revlog).
                try:
                    skipflags = self.skipflags
                    if skipflags:
                        skipflags &= fl.flags(i)
                    if not skipflags:
                        fl.read(n) # side effect: read content and do checkhash
                        rp = fl.renamed(n)
                    # the "L1 == L2" check
                    l1 = fl.rawsize(i)
                    l2 = len(fl.revision(n, raw=True))
                    if l1 != l2:
                        self.err(lr, _("unpacked size is %s, %s expected") %
                                 (l2, l1), f)
                except error.CensoredNodeError:
                    # experimental config: censor.policy
                    if ui.config("censor", "policy") == "abort":
                        self.err(lr, _("censored file data"), f)
                except Exception as inst:
                    self.exc(lr, _("unpacking %s") % short(n), inst, f)

                # check renames
                try:
                    if rp:
                        if lr is not None and ui.verbose:
                            ctx = lrugetctx(lr)
                            if not any(rp[0] in pctx for pctx in ctx.parents()):
                                self.warn(_("warning: copy source of '%s' not"
                                            " in parents of %s") % (f, ctx))
                        fl2 = repo.file(rp[0])
                        if not len(fl2):
                            self.err(lr, _("empty or missing copy source "
                                     "revlog %s:%s") % (rp[0], short(rp[1])), f)
                        elif rp[1] == nullid:
                            ui.note(_("warning: %s@%s: copy source"
                                      " revision is nullid %s:%s\n")
                                % (f, lr, rp[0], short(rp[1])))
                        else:
                            fl2.rev(rp[1])
                except Exception as inst:
                    self.exc(lr, _("checking rename of %s") % short(n), inst, f)

            # cross-check
            if f in filenodes:
                fns = [(v, k) for k, v in filenodes[f].iteritems()]
                for lr, node in sorted(fns):
                    self.err(lr, _("manifest refers to unknown revision %s") %
                             short(node), f)
        ui.progress(_('checking'), None)

        for f in sorted(storefiles):
            self.warn(_("warning: orphan revlog '%s'") % f)

        return len(files), revisions