# 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,

)

from .revlogutils import sidedata as sidedatamod

_defaultextra = {b'branch': b'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(b'\\', b'\\\\')

        .replace(b'\n', b'\\n')

        .replace(b'\r', b'\\r')

    )

    return text.replace(b'\0', b'\\0')

def _string_unescape(text):

    if b'\\0' in text:

        # fix up \0 without getting into trouble with \\0

        text = text.replace(b'\\\\', b'\\\\\n')

        text = text.replace(b'\\0', b'\0')

        text = text.replace(b'\n', b'')

    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(b'\0'):

        if l:

            k, v = _string_unescape(l).split(b':', 1)

            extra[k] = v

    return extra

def encodeextra(d):

    # keys must be sorted to produce a deterministic changelog entry

    items = [

        _string_escape(b'%s:%s' % (k, pycompat.bytestr(d[k])))

        for k in sorted(d)

    ]

    return b"\0".join(items)

def encodecopies(files, copies):

    items = []

    for i, dst in enumerate(files):

        if dst in copies:

            items.append(b'%d\0%s' % (i, copies[dst]))

    if len(items) != len(copies):

        raise error.ProgrammingError(

            b'some copy targets missing from file list'

        )

    return b"\n".join(items)

def decodecopies(files, data):

    try:

        copies = {}

        if not data:

            return copies

        for l in data.split(b'\n'):

            strindex, src = l.split(b'\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(b'%d' % i)

    return b'\n'.join(indices)

def decodefileindices(files, data):

    try:

        subset = []

        if not data:

            return subset

        for strindex in data.split(b'\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 b'\n'.join([l.rstrip() for l in desc.splitlines()]).strip(b'\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 = b""

        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, b"".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=b'r', checkambig=False):

        if name != target:

            return opener(name, mode)

        return opener(name + b".a", mode)

    return _divert

def _delayopener(opener, target, buf):

    """build an opener that stores chunks in 'buf' instead of 'target'"""

    def _delay(name, mode=b'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=b'')

    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=b'')

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',

    )

        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(b'\n')

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

        nl3 = text.index(b'\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] == b'\n':

            doublenl = nl3

        else:

            doublenl = text.index(b'\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(b' ', 2)[0:2]

    @property

    def _rawextra(self):

        off = self._offsets

        dateextra = self._text[off[1] + 1 : off[2]]

        fields = dateextra.split(b' ', 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(b'\n')

    @property

    def filesadded(self):

        rawindices = self.extra.get(b'filesadded')

        return rawindices and decodefileindices(self.files, rawindices)

    @property

    def filesremoved(self):

        rawindices = self.extra.get(b'filesremoved')

        return rawindices and decodefileindices(self.files, rawindices)

    @property

    def p1copies(self):

        rawcopies = self.extra.get(b'p1copies')

        return rawcopies and decodecopies(self.files, rawcopies)

    @property

    def p2copies(self):

        rawcopies = self.extra.get(b'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(b'00changelog.i.a'):

            indexfile = b'00changelog.i.a'

        else:

            indexfile = b'00changelog.i'

        datafile = b'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()

        self._copiesstorage = opener.options.get(b'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 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)