# verify.py - repository integrity checking for Mercurial

#

# Copyright 2006, 2007 Matt Mackall <mpm@selenic.com>

#

# 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,

    revlog,

    util,

)

def verify(repo):

    lock = repo.lock()

    try:

        return verifier(repo).verify()

    finally:

        lock.release()

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

def _validpath(repo, path):

    """Returns False if a path should NOT be treated as part of a repo.

    For all in-core cases, this returns True, as we have no way for a

    path to be mentioned in the history but not actually be

    relevant. For narrow clones, this is important because many

    filelogs will be missing, and changelog entries may mention

    modified files that are outside the narrow scope.

    """

    return True

class verifier(object):

    def __init__(self, repo):

        self.repo = repo.unfiltered()

        self.ui = repo.ui

        self.badrevs = set()

        self.errors = 0

        self.warnings = 0

        self.havecl = len(repo.changelog) > 0

        self.havemf = len(repo.manifest) > 0

        self.revlogv1 = repo.changelog.version != revlog.REVLOGV0

        self.lrugetctx = util.lrucachefunc(repo.changectx)

        self.refersmf = False

        self.fncachewarned = False

    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)

        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):

        if not str(inst):

            inst = repr(inst)

        self.err(linkrev, "%s: %s" % (msg, inst), 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(str, 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

        mflinkrevs = {}

        filelinkrevs = {}

        filenodes = {}

        revisions = 0

        badrevs = self.badrevs

        ui = repo.ui

        cl = repo.changelog

        mf = repo.manifest

        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"))

        revlogv1 = self.revlogv1

        if ui.verbose or not revlogv1:

            ui.status(_("repository uses revlog format %d\n") %

                           (revlogv1 and 1 or 0))

        ui.status(_("checking changesets\n"))

        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 _validpath(repo, 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)

        ui.status(_("checking manifests\n"))

        seen = {}

        if self.refersmf:

            # Do not check manifest if there are only changelog entries with

            # null manifests.

            self.checklog(mf, "manifest", 0)

        total = len(mf)

        for i in mf:

            ui.progress(_('checking'), i, total=total, unit=_('manifests'))

            n = mf.node(i)

            lr = self.checkentry(mf, i, n, seen, mflinkrevs.get(n, []),

                                 "manifest")

            if n in mflinkrevs:

                del mflinkrevs[n]

            else:

                self.err(lr, _("%s not in changesets") % short(n), "manifest")

            try:

                for f, fn in mf.readdelta(n).iteritems():

                    if not f:

                        self.err(lr, _("file without name in manifest"))

                    elif f != "/dev/null": # ignore this in very old repos

                        if _validpath(repo, f):

                            filenodes.setdefault(

                                _normpath(f), {}).setdefault(fn, lr)

            except Exception as inst:

                self.exc(lr, _("reading manifest delta %s") % short(n), inst)

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

        ui.status(_("crosschecking files in changesets and manifests\n"))

        total = len(mflinkrevs) + len(filelinkrevs) + len(filenodes)

        count = 0

            for c, m in sorted([(c, m) for m in mflinkrevs

                                for c in mflinkrevs[m]]):

                count += 1

                if m == nullid:

                    continue

                ui.progress(_('crosschecking'), count, total=total)

                self.err(c, _("changeset refers to unknown manifest %s") %

                         short(m))

            mflinkrevs = None # del is bad here due to scope issues

            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)

            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:

                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)

            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

                try:

                    l = len(fl.read(n))

                    rp = fl.renamed(n)

                    if l != fl.size(i):

                        if len(fl.revision(n)) != fl.size(i):

                            self.err(lr, _("unpacked size is %s, %s expected") %

                                     (l, fl.size(i)), f)

                except error.CensoredNodeError:

                    # experimental config: censor.policy

                    if ui.config("censor", "policy", "abort") == "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)

                            found = False

                            for pctx in ctx.parents():

                                if rp[0] in pctx:

                                    found = True

                                    break

                            if not found: