mercurial/changelog.py
author Valentin Gatien-Baron <valentin.gatienbaron@gmail.com>
Tue, 02 Jul 2019 12:59:58 -0400
changeset 42621 99ebde4fec99
parent 42553 e3df1e15bee9
child 42861 57ea0a81a65c
permissions -rw-r--r--
commit: improve the files field of changelog for merges Currently, the files list of merge commits repeats all the deletions (either actual deletions, or files that got renamed) that happened between base and p2 of the merge. If p2 is the main branch, the list can easily be much bigger than the change being merged. This results in various problems worth improving: - changelog is bigger than necessary - `hg log directory` lists many unrelated merge commits, and `hg log -v -r commit` frequently fills multiple screens worth of files - it possibly slows down adjustlinkrev, by forcing it to read more manifests, and that function can certainly be a bottleneck - the server side of pulls can waste a lot of time simply opening the filelogs for pointless files (the constant factors for opening even a tiny filelog is apparently pretty bad) So stop listing such files as described in the code. Impacted merge commits and their descendants get a different hash than they would have without this. This doesn't seem problematic, except for convert. The previous commit helped with that in the hg->hg case (but if you do svn->hg twice from scratch, hashes can still change). The rest of the description is numbers. I don't have much to report, because recreating the files list of existing repositories is not easy: - debugupgradeformat and bundle/unbundle don't recreate the list - export/import tends to choke quickly applying patches or on description that contain diffs, - merge commits from the convert extension don't have the right files list for reasons orthogonal to the current commit - replaying the merge with hg update/hg merge/hg revert --all/hg commit can end up failing in hg revert - I wasn't sure that using debugsetparents + debugrebuilddirstate would really build the right thing I measured commit time before and after this change, in a case with no files filtered out, several files filtered out (no difference) and 5k files filtered out (+1% time). Recreating the 100 more recent merges in a private repo, the concatenated uncompressed files lists goes from 1.12MB to 0.52MB. Excluding 3 merges that are not representative, then the size goes from 570k to 15k. I converted part of mozilla-central, and observed file list shrinking quite a bit too, starting at the very first merge, 733641d9feaf, going from 550 files to 10 files (although they have relatively few merges, so they probably wouldn't care). Differential Revision: https://phab.mercurial-scm.org/D6613

# changelog.py - changelog class for mercurial
#
# Copyright 2005-2007 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

from .i18n import _
from .node import (
    bin,
    hex,
    nullid,
)
from .thirdparty import (
    attr,
)

from . import (
    encoding,
    error,
    pycompat,
    revlog,
    util,
)
from .utils import (
    dateutil,
    stringutil,
)

_defaultextra = {'branch': 'default'}

def _string_escape(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
    >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)s12ab%(cr)scd%(bs)s%(nl)s" % d
    >>> s
    'ab\\ncd\\\\\\\\n\\x0012ab\\rcd\\\\\\n'
    >>> res = _string_escape(s)
    >>> s == _string_unescape(res)
    True
    """
    # subset of the string_escape codec
    text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
    return text.replace('\0', '\\0')

def _string_unescape(text):
    if '\\0' in text:
        # fix up \0 without getting into trouble with \\0
        text = text.replace('\\\\', '\\\\\n')
        text = text.replace('\\0', '\0')
        text = text.replace('\n', '')
    return stringutil.unescapestr(text)

def decodeextra(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})
    ...                    ).items())
    [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
    >>> sorted(decodeextra(encodeextra({b'foo': b'bar',
    ...                                 b'baz': chr(92) + chr(0) + b'2'})
    ...                    ).items())
    [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
    """
    extra = _defaultextra.copy()
    for l in text.split('\0'):
        if l:
            k, v = _string_unescape(l).split(':', 1)
            extra[k] = v
    return extra

def encodeextra(d):
    # keys must be sorted to produce a deterministic changelog entry
    items = [
        _string_escape('%s:%s' % (k, pycompat.bytestr(d[k])))
        for k in sorted(d)
    ]
    return "\0".join(items)

def encodecopies(files, copies):
    items = []
    for i, dst in enumerate(files):
        if dst in copies:
            items.append('%d\0%s' % (i, copies[dst]))
    if len(items) != len(copies):
        raise error.ProgrammingError('some copy targets missing from file list')
    return "\n".join(items)

def decodecopies(files, data):
    try:
        copies = {}
        if not data:
            return copies
        for l in data.split('\n'):
            strindex, src = l.split('\0')
            i = int(strindex)
            dst = files[i]
            copies[dst] = src
        return copies
    except (ValueError, IndexError):
        # Perhaps someone had chosen the same key name (e.g. "p1copies") and
        # used different syntax for the value.
        return None

def encodefileindices(files, subset):
    subset = set(subset)
    indices = []
    for i, f in enumerate(files):
        if f in subset:
            indices.append('%d' % i)
    return '\n'.join(indices)

def decodefileindices(files, data):
    try:
        subset = []
        if not data:
            return subset
        for strindex in data.split('\n'):
            i = int(strindex)
            if i < 0 or i >= len(files):
                return None
            subset.append(files[i])
        return subset
    except (ValueError, IndexError):
        # Perhaps someone had chosen the same key name (e.g. "added") and
        # used different syntax for the value.
        return None

def stripdesc(desc):
    """strip trailing whitespace and leading and trailing empty lines"""
    return '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')

class appender(object):
    '''the changelog index must be updated last on disk, so we use this class
    to delay writes to it'''
    def __init__(self, vfs, name, mode, buf):
        self.data = buf
        fp = vfs(name, mode)
        self.fp = fp
        self.offset = fp.tell()
        self.size = vfs.fstat(fp).st_size
        self._end = self.size

    def end(self):
        return self._end
    def tell(self):
        return self.offset
    def flush(self):
        pass

    @property
    def closed(self):
        return self.fp.closed

    def close(self):
        self.fp.close()

    def seek(self, offset, whence=0):
        '''virtual file offset spans real file and data'''
        if whence == 0:
            self.offset = offset
        elif whence == 1:
            self.offset += offset
        elif whence == 2:
            self.offset = self.end() + offset
        if self.offset < self.size:
            self.fp.seek(self.offset)

    def read(self, count=-1):
        '''only trick here is reads that span real file and data'''
        ret = ""
        if self.offset < self.size:
            s = self.fp.read(count)
            ret = s
            self.offset += len(s)
            if count > 0:
                count -= len(s)
        if count != 0:
            doff = self.offset - self.size
            self.data.insert(0, "".join(self.data))
            del self.data[1:]
            s = self.data[0][doff:doff + count]
            self.offset += len(s)
            ret += s
        return ret

    def write(self, s):
        self.data.append(bytes(s))
        self.offset += len(s)
        self._end += len(s)

    def __enter__(self):
        self.fp.__enter__()
        return self

    def __exit__(self, *args):
        return self.fp.__exit__(*args)

def _divertopener(opener, target):
    """build an opener that writes in 'target.a' instead of 'target'"""
    def _divert(name, mode='r', checkambig=False):
        if name != target:
            return opener(name, mode)
        return opener(name + ".a", mode)
    return _divert

def _delayopener(opener, target, buf):
    """build an opener that stores chunks in 'buf' instead of 'target'"""
    def _delay(name, mode='r', checkambig=False):
        if name != target:
            return opener(name, mode)
        return appender(opener, name, mode, buf)
    return _delay

@attr.s
class _changelogrevision(object):
    # Extensions might modify _defaultextra, so let the constructor below pass
    # it in
    extra = attr.ib()
    manifest = attr.ib(default=nullid)
    user = attr.ib(default='')
    date = attr.ib(default=(0, 0))
    files = attr.ib(default=attr.Factory(list))
    filesadded = attr.ib(default=None)
    filesremoved = attr.ib(default=None)
    p1copies = attr.ib(default=None)
    p2copies = attr.ib(default=None)
    description = attr.ib(default='')

class changelogrevision(object):
    """Holds results of a parsed changelog revision.

    Changelog revisions consist of multiple pieces of data, including
    the manifest node, user, and date. This object exposes a view into
    the parsed object.
    """

    __slots__ = (
        r'_offsets',
        r'_text',
    )

    def __new__(cls, text):
        if not text:
            return _changelogrevision(extra=_defaultextra)

        self = super(changelogrevision, cls).__new__(cls)
        # We could return here and implement the following as an __init__.
        # But doing it here is equivalent and saves an extra function call.

        # format used:
        # nodeid\n        : manifest node in ascii
        # user\n          : user, no \n or \r allowed
        # time tz extra\n : date (time is int or float, timezone is int)
        #                 : extra is metadata, encoded and separated by '\0'
        #                 : older versions ignore it
        # files\n\n       : files modified by the cset, no \n or \r allowed
        # (.*)            : comment (free text, ideally utf-8)
        #
        # changelog v0 doesn't use extra

        nl1 = text.index('\n')
        nl2 = text.index('\n', nl1 + 1)
        nl3 = text.index('\n', nl2 + 1)

        # The list of files may be empty. Which means nl3 is the first of the
        # double newline that precedes the description.
        if text[nl3 + 1:nl3 + 2] == '\n':
            doublenl = nl3
        else:
            doublenl = text.index('\n\n', nl3 + 1)

        self._offsets = (nl1, nl2, nl3, doublenl)
        self._text = text

        return self

    @property
    def manifest(self):
        return bin(self._text[0:self._offsets[0]])

    @property
    def user(self):
        off = self._offsets
        return encoding.tolocal(self._text[off[0] + 1:off[1]])

    @property
    def _rawdate(self):
        off = self._offsets
        dateextra = self._text[off[1] + 1:off[2]]
        return dateextra.split(' ', 2)[0:2]

    @property
    def _rawextra(self):
        off = self._offsets
        dateextra = self._text[off[1] + 1:off[2]]
        fields = dateextra.split(' ', 2)
        if len(fields) != 3:
            return None

        return fields[2]

    @property
    def date(self):
        raw = self._rawdate
        time = float(raw[0])
        # Various tools did silly things with the timezone.
        try:
            timezone = int(raw[1])
        except ValueError:
            timezone = 0

        return time, timezone

    @property
    def extra(self):
        raw = self._rawextra
        if raw is None:
            return _defaultextra

        return decodeextra(raw)

    @property
    def files(self):
        off = self._offsets
        if off[2] == off[3]:
            return []

        return self._text[off[2] + 1:off[3]].split('\n')

    @property
    def filesadded(self):
        rawindices = self.extra.get('filesadded')
        return rawindices and decodefileindices(self.files, rawindices)

    @property
    def filesremoved(self):
        rawindices = self.extra.get('filesremoved')
        return rawindices and decodefileindices(self.files, rawindices)

    @property
    def p1copies(self):
        rawcopies = self.extra.get('p1copies')
        return rawcopies and decodecopies(self.files, rawcopies)

    @property
    def p2copies(self):
        rawcopies = self.extra.get('p2copies')
        return rawcopies and decodecopies(self.files, rawcopies)

    @property
    def description(self):
        return encoding.tolocal(self._text[self._offsets[3] + 2:])

class changelog(revlog.revlog):
    def __init__(self, opener, trypending=False):
        """Load a changelog revlog using an opener.

        If ``trypending`` is true, we attempt to load the index from a
        ``00changelog.i.a`` file instead of the default ``00changelog.i``.
        The ``00changelog.i.a`` file contains index (and possibly inline
        revision) data for a transaction that hasn't been finalized yet.
        It exists in a separate file to facilitate readers (such as
        hooks processes) accessing data before a transaction is finalized.
        """
        if trypending and opener.exists('00changelog.i.a'):
            indexfile = '00changelog.i.a'
        else:
            indexfile = '00changelog.i'

        datafile = '00changelog.d'
        revlog.revlog.__init__(self, opener, indexfile, datafile=datafile,
                               checkambig=True, mmaplargeindex=True)

        if self._initempty and (self.version & 0xFFFF == revlog.REVLOGV1):
            # changelogs don't benefit from generaldelta.

            self.version &= ~revlog.FLAG_GENERALDELTA
            self._generaldelta = False

        # Delta chains for changelogs tend to be very small because entries
        # tend to be small and don't delta well with each. So disable delta
        # chains.
        self._storedeltachains = False

        self._realopener = opener
        self._delayed = False
        self._delaybuf = None
        self._divert = False
        self.filteredrevs = frozenset()

    def tiprev(self):
        for i in pycompat.xrange(len(self) -1, -2, -1):
            if i not in self.filteredrevs:
                return i

    def tip(self):
        """filtered version of revlog.tip"""
        return self.node(self.tiprev())

    def __contains__(self, rev):
        """filtered version of revlog.__contains__"""
        return (0 <= rev < len(self)
                and rev not in self.filteredrevs)

    def __iter__(self):
        """filtered version of revlog.__iter__"""
        if len(self.filteredrevs) == 0:
            return revlog.revlog.__iter__(self)

        def filterediter():
            for i in pycompat.xrange(len(self)):
                if i not in self.filteredrevs:
                    yield i

        return filterediter()

    def revs(self, start=0, stop=None):
        """filtered version of revlog.revs"""
        for i in super(changelog, self).revs(start, stop):
            if i not in self.filteredrevs:
                yield i

    def _checknofilteredinrevs(self, revs):
        """raise the appropriate error if 'revs' contains a filtered revision

        This returns a version of 'revs' to be used thereafter by the caller.
        In particular, if revs is an iterator, it is converted into a set.
        """
        safehasattr = util.safehasattr
        if safehasattr(revs, '__next__'):
            # Note that inspect.isgenerator() is not true for iterators,
            revs = set(revs)

        filteredrevs = self.filteredrevs
        if safehasattr(revs, 'first'):  # smartset
            offenders = revs & filteredrevs
        else:
            offenders = filteredrevs.intersection(revs)

        for rev in offenders:
            raise error.FilteredIndexError(rev)
        return revs

    def headrevs(self, revs=None):
        if revs is None and self.filteredrevs:
            try:
                return self.index.headrevsfiltered(self.filteredrevs)
            # AttributeError covers non-c-extension environments and
            # old c extensions without filter handling.
            except AttributeError:
                return self._headrevs()

        if self.filteredrevs:
            revs = self._checknofilteredinrevs(revs)
        return super(changelog, self).headrevs(revs)

    def strip(self, *args, **kwargs):
        # XXX make something better than assert
        # We can't expect proper strip behavior if we are filtered.
        assert not self.filteredrevs
        super(changelog, self).strip(*args, **kwargs)

    def rev(self, node):
        """filtered version of revlog.rev"""
        r = super(changelog, self).rev(node)
        if r in self.filteredrevs:
            raise error.FilteredLookupError(hex(node), self.indexfile,
                                            _('filtered node'))
        return r

    def node(self, rev):
        """filtered version of revlog.node"""
        if rev in self.filteredrevs:
            raise error.FilteredIndexError(rev)
        return super(changelog, self).node(rev)

    def linkrev(self, rev):
        """filtered version of revlog.linkrev"""
        if rev in self.filteredrevs:
            raise error.FilteredIndexError(rev)
        return super(changelog, self).linkrev(rev)

    def parentrevs(self, rev):
        """filtered version of revlog.parentrevs"""
        if rev in self.filteredrevs:
            raise error.FilteredIndexError(rev)
        return super(changelog, self).parentrevs(rev)

    def flags(self, rev):
        """filtered version of revlog.flags"""
        if rev in self.filteredrevs:
            raise error.FilteredIndexError(rev)
        return super(changelog, self).flags(rev)

    def delayupdate(self, tr):
        "delay visibility of index updates to other readers"

        if not self._delayed:
            if len(self) == 0:
                self._divert = True
                if self._realopener.exists(self.indexfile + '.a'):
                    self._realopener.unlink(self.indexfile + '.a')
                self.opener = _divertopener(self._realopener, self.indexfile)
            else:
                self._delaybuf = []
                self.opener = _delayopener(self._realopener, self.indexfile,
                                           self._delaybuf)
        self._delayed = True
        tr.addpending('cl-%i' % id(self), self._writepending)
        tr.addfinalize('cl-%i' % id(self), self._finalize)

    def _finalize(self, tr):
        "finalize index updates"
        self._delayed = False
        self.opener = self._realopener
        # move redirected index data back into place
        if self._divert:
            assert not self._delaybuf
            tmpname = self.indexfile + ".a"
            nfile = self.opener.open(tmpname)
            nfile.close()
            self.opener.rename(tmpname, self.indexfile, checkambig=True)
        elif self._delaybuf:
            fp = self.opener(self.indexfile, 'a', checkambig=True)
            fp.write("".join(self._delaybuf))
            fp.close()
            self._delaybuf = None
        self._divert = False
        # split when we're done
        self._enforceinlinesize(tr)

    def _writepending(self, tr):
        "create a file containing the unfinalized state for pretxnchangegroup"
        if self._delaybuf:
            # make a temporary copy of the index
            fp1 = self._realopener(self.indexfile)
            pendingfilename = self.indexfile + ".a"
            # register as a temp file to ensure cleanup on failure
            tr.registertmp(pendingfilename)
            # write existing data
            fp2 = self._realopener(pendingfilename, "w")
            fp2.write(fp1.read())
            # add pending data
            fp2.write("".join(self._delaybuf))
            fp2.close()
            # switch modes so finalize can simply rename
            self._delaybuf = None
            self._divert = True
            self.opener = _divertopener(self._realopener, self.indexfile)

        if self._divert:
            return True

        return False

    def _enforceinlinesize(self, tr, fp=None):
        if not self._delayed:
            revlog.revlog._enforceinlinesize(self, tr, fp)

    def read(self, node):
        """Obtain data from a parsed changelog revision.

        Returns a 6-tuple of:

           - manifest node in binary
           - author/user as a localstr
           - date as a 2-tuple of (time, timezone)
           - list of files
           - commit message as a localstr
           - dict of extra metadata

        Unless you need to access all fields, consider calling
        ``changelogrevision`` instead, as it is faster for partial object
        access.
        """
        c = changelogrevision(self.revision(node))
        return (
            c.manifest,
            c.user,
            c.date,
            c.files,
            c.description,
            c.extra
        )

    def changelogrevision(self, nodeorrev):
        """Obtain a ``changelogrevision`` for a node or revision."""
        return changelogrevision(self.revision(nodeorrev))

    def readfiles(self, node):
        """
        short version of read that only returns the files modified by the cset
        """
        text = self.revision(node)
        if not text:
            return []
        last = text.index("\n\n")
        l = text[:last].split('\n')
        return l[3:]

    def add(self, manifest, files, desc, transaction, p1, p2,
                  user, date=None, extra=None, p1copies=None, p2copies=None,
                  filesadded=None, filesremoved=None):
        # Convert to UTF-8 encoded bytestrings as the very first
        # thing: calling any method on a localstr object will turn it
        # into a str object and the cached UTF-8 string is thus lost.
        user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)

        user = user.strip()
        # An empty username or a username with a "\n" will make the
        # revision text contain two "\n\n" sequences -> corrupt
        # repository since read cannot unpack the revision.
        if not user:
            raise error.StorageError(_("empty username"))
        if "\n" in user:
            raise error.StorageError(_("username %r contains a newline")
                                     % pycompat.bytestr(user))

        desc = stripdesc(desc)

        if date:
            parseddate = "%d %d" % dateutil.parsedate(date)
        else:
            parseddate = "%d %d" % dateutil.makedate()
        if extra:
            branch = extra.get("branch")
            if branch in ("default", ""):
                del extra["branch"]
            elif branch in (".", "null", "tip"):
                raise error.StorageError(_('the name \'%s\' is reserved')
                                         % branch)
        extrasentries = p1copies, p2copies, filesadded, filesremoved
        if extra is None and any(x is not None for x in extrasentries):
            extra = {}
        sortedfiles = sorted(files)
        if p1copies is not None:
            extra['p1copies'] = encodecopies(sortedfiles, p1copies)
        if p2copies is not None:
            extra['p2copies'] = encodecopies(sortedfiles, p2copies)
        if filesadded is not None:
            extra['filesadded'] = encodefileindices(sortedfiles, filesadded)
        if filesremoved is not None:
            extra['filesremoved'] = encodefileindices(sortedfiles, filesremoved)

        if extra:
            extra = encodeextra(extra)
            parseddate = "%s %s" % (parseddate, extra)
        l = [hex(manifest), user, parseddate] + sortedfiles + ["", desc]
        text = "\n".join(l)
        return self.addrevision(text, transaction, len(self), p1, p2)

    def branchinfo(self, rev):
        """return the branch name and open/close state of a revision

        This function exists because creating a changectx object
        just to access this is costly."""
        extra = self.read(rev)[5]
        return encoding.tolocal(extra.get("branch")), 'close' in extra

    def _nodeduplicatecallback(self, transaction, node):
        # keep track of revisions that got "re-added", eg: unbunde of know rev.
        #
        # We track them in a list to preserve their order from the source bundle
        duplicates = transaction.changes.setdefault('revduplicates', [])
        duplicates.append(self.rev(node))