comparison mercurial/changelog.py @ 43076:2372284d9457

formatting: blacken the codebase

This is using my patch to black
(https://github.com/psf/black/pull/826) so we don't un-wrap collection
literals.

Done with:

  hg files 'set:**.py - mercurial/thirdparty/** - "contrib/python-zstandard/**"' | xargs black -S

# skip-blame mass-reformatting only

# no-check-commit reformats foo_bar functions

Differential Revision: https://phab.mercurial-scm.org/D6971

43075:57875cf423c9

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

from . import (
    encoding,
    error,
    pycompat,

    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)}

    """
    # 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'})

        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:

    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:

    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):

                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):

        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

    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

        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)

        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]

    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)

        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.

            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._divert = False
        self.filteredrevs = frozenset()
        self._copiesstorage = opener.options.get('copies-storage')

    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 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:

                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):

        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))

            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)

        # 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)

        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)
        sortedfiles = sorted(files)
        if extra is not None:
            for name in ('p1copies', 'p2copies', 'filesadded', 'filesremoved'):
                extra.pop(name, None)
        if p1copies is not None:

43076:2372284d9457

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

from . import (
    encoding,
    error,
    pycompat,

    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)}

    """
    # 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'})

        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:

    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:

    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):

                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):

        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

    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

        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)

        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]

    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)

        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.

            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._divert = False
        self.filteredrevs = frozenset()
        self._copiesstorage = opener.options.get('copies-storage')

    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 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:

                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):

        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))

            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)

        # 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)

        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
                )
        sortedfiles = sorted(files)
        if extra is not None:
            for name in ('p1copies', 'p2copies', 'filesadded', 'filesremoved'):
                extra.pop(name, None)
        if p1copies is not None: