sidedata: add a `decode_files_sidedata` function

Right now the function mostly gather existing code to build a consistent object.
However having this function allow us prepare all user code independently from
the actual side data format change (and associated encoding/decoding changes)

Strictly speaking, we could not need to passe the sidedata explicitly since we
have access to it though the `changelogrevision` object. However, the short
term goal is to drop that first parameter to only pass the sidedata binaries.

mercurial/changelog.py

@@ -1,613 +1,616
 # changelog.py - changelog class for mercurial
 #
 # Copyright 2005-2007 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
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
 )
 from .thirdparty import attr
 
 from . import (
     encoding,
     error,
     metadata,
     pycompat,
     revlog,
 )
 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, d[k])) for k in sorted(d)]
     return b"\0".join(items)
 
 
 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)
 
 
 class _divertopener(object):
     def __init__(self, opener, target):
         self._opener = opener
         self._target = target
 
     def __call__(self, name, mode=b'r', checkambig=False, **kwargs):
         if name != self._target:
             return self._opener(name, mode, **kwargs)
         return self._opener(name + b".a", mode, **kwargs)
 
     def __getattr__(self, attr):
         return getattr(self._opener, attr)
 
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
 
     def _delay(name, mode=b'r', checkambig=False, **kwargs):
         if name != target:
             return opener(name, mode, **kwargs)
         assert not kwargs
         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__ = (
         '_offsets',
         '_text',
         '_sidedata',
         '_cpsd',
         '_changes',
     )
 
     def __new__(cls, text, sidedata, cpsd):
         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
         self._sidedata = sidedata
         self._cpsd = cpsd
         self._changes = None
 
         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 changes(self):
         if self._changes is not None:
             return self._changes
-        changes = metadata.ChangingFiles(
-            touched=self.files or (),
-            added=self.filesadded or (),
-            removed=self.filesremoved or (),
-            p1_copies=self.p1copies or {},
-            p2_copies=self.p2copies or {},
-        )
+        if self._cpsd:
+            changes = metadata.decode_files_sidedata(self, self._sidedata)
+        else:
+            changes = metadata.ChangingFiles(
+                touched=self.files or (),
+                added=self.filesadded or (),
+                removed=self.filesremoved or (),
+                p1_copies=self.p1copies or {},
+                p2_copies=self.p2copies or {},
+            )
         self._changes = changes
         return changes
 
     @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):
         if self._cpsd:
             rawindices = self._sidedata.get(sidedatamod.SD_FILESADDED)
             if not rawindices:
                 return []
         else:
             rawindices = self.extra.get(b'filesadded')
         if rawindices is None:
             return None
         return metadata.decodefileindices(self.files, rawindices)
 
     @property
     def filesremoved(self):
         if self._cpsd:
             rawindices = self._sidedata.get(sidedatamod.SD_FILESREMOVED)
             if not rawindices:
                 return []
         else:
             rawindices = self.extra.get(b'filesremoved')
         if rawindices is None:
             return None
         return metadata.decodefileindices(self.files, rawindices)
 
     @property
     def p1copies(self):
         if self._cpsd:
             rawcopies = self._sidedata.get(sidedatamod.SD_P1COPIES)
             if not rawcopies:
                 return {}
         else:
             rawcopies = self.extra.get(b'p1copies')
         if rawcopies is None:
             return None
         return metadata.decodecopies(self.files, rawcopies)
 
     @property
     def p2copies(self):
         if self._cpsd:
             rawcopies = self._sidedata.get(sidedatamod.SD_P2COPIES)
             if not rawcopies:
                 return {}
         else:
             rawcopies = self.extra.get(b'p2copies')
         if rawcopies is None:
             return None
         return metadata.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,
             persistentnodemap=opener.options.get(b'persistent-nodemap', False),
         )
 
         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._filteredrevs_hashcache = {}
         self._copiesstorage = opener.options.get(b'copies-storage')
 
     @property
     def filteredrevs(self):
         return self._filteredrevs
 
     @filteredrevs.setter
     def filteredrevs(self, val):
         # Ensure all updates go through this function
         assert isinstance(val, frozenset)
         self._filteredrevs = val
         self._filteredrevs_hashcache = {}
 
     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 + b'.a'):
                     self._realopener.unlink(self.indexfile + b'.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(b'cl-%i' % id(self), self._writepending)
         tr.addfinalize(b'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 + b".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile, checkambig=True)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, b'a', checkambig=True)
             fp.write(b"".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 + b".a"
             # register as a temp file to ensure cleanup on failure
             tr.registertmp(pendingfilename)
             # write existing data
             fp2 = self._realopener(pendingfilename, b"w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write(b"".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.
         """
         d, s = self._revisiondata(node)
         c = changelogrevision(
             d, s, self._copiesstorage == b'changeset-sidedata'
         )
         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."""
         text, sidedata = self._revisiondata(nodeorrev)
         return changelogrevision(
             text, sidedata, self._copiesstorage == b'changeset-sidedata'
         )
 
     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(b"\n\n")
         l = text[:last].split(b'\n')
         return l[3:]
 
     def add(
         self,
         manifest,
         files,
         desc,
         transaction,
         p1,
         p2,
         user,
         date=None,
         extra=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(_(b"empty username"))
         if b"\n" in user:
             raise error.StorageError(
                 _(b"username %r contains a newline") % pycompat.bytestr(user)
             )
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = b"%d %d" % dateutil.parsedate(date)
         else:
             parseddate = b"%d %d" % dateutil.makedate()
         if extra:
             branch = extra.get(b"branch")
             if branch in (b"default", b""):
                 del extra[b"branch"]
             elif branch in (b".", b"null", b"tip"):
                 raise error.StorageError(
                     _(b'the name \'%s\' is reserved') % branch
                 )
         sortedfiles = sorted(files.touched)
         sidedata = None
         if self._copiesstorage == b'changeset-sidedata':
             sidedata = metadata.encode_files_sidedata(files)
 
         if extra:
             extra = encodeextra(extra)
             parseddate = b"%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sortedfiles + [b"", desc]
         text = b"\n".join(l)
         return self.addrevision(
             text, transaction, len(self), p1, p2, sidedata=sidedata
         )
 
     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(b"branch")), b'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(b'revduplicates', [])
         duplicates.append(self.rev(node))

mercurial/metadata.py

@@ -1,488 +1,514
 # metadata.py -- code related to various metadata computation and access.
 #
 # Copyright 2019 Google, Inc <[e-mail]>
 # Copyright 2020 Pierre-Yves David <[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, print_function
 
 import multiprocessing
 
 from . import (
     error,
     node,
     pycompat,
     util,
 )
 
 from .revlogutils import (
     flagutil as sidedataflag,
     sidedata as sidedatamod,
 )
 
 
 class ChangingFiles(object):
     """A class recording the changes made to a file by a changeset
 
     Actions performed on files are gathered into 3 sets:
 
     - added:   files actively added in the changeset.
     - removed: files removed in the revision
     - touched: files affected by the merge
 
     and copies information is held by 2 mappings
 
     - copied_from_p1: {"<new-name>": "<source-name-in-p1>"} mapping for copies
     - copied_from_p2: {"<new-name>": "<source-name-in-p2>"} mapping for copies
 
     See their inline help for details.
     """
 
     def __init__(
         self, touched=(), added=(), removed=(), p1_copies=(), p2_copies=(),
     ):
         self._added = set(added)
         self._removed = set(removed)
         self._touched = set(touched)
         self._touched.update(self._added)
         self._touched.update(self._removed)
         self._p1_copies = dict(p1_copies)
         self._p2_copies = dict(p2_copies)
 
     def __eq__(self, other):
         return (
             self.added == other.added
             and self.removed == other.removed
             and self.touched == other.touched
             and self.copied_from_p1 == other.copied_from_p1
             and self.copied_from_p2 == other.copied_from_p2
         )
 
     @property
     def added(self):
         """files actively added in the changeset
 
         Any file present in that revision that was absent in all the changeset's
         parents.
 
         In case of merge, this means a file absent in one of the parents but
         existing in the other will *not* be contained in this set. (They were
         added by an ancestor)
         """
         return frozenset(self._added)
 
     def mark_added(self, filename):
         self._added.add(filename)
         self._touched.add(filename)
 
     def update_added(self, filenames):
         for f in filenames:
             self.mark_added(f)
 
     @property
     def removed(self):
         """files actively removed by the changeset
 
         In case of merge this will only contain the set of files removing "new"
         content. For any file absent in the current changeset:
 
         a) If the file exists in both parents, it is clearly "actively" removed
         by this changeset.
 
         b) If a file exists in only one parent and in none of the common
         ancestors, then the file was newly added in one of the merged branches
         and then got "actively" removed.
 
         c) If a file exists in only one parent and at least one of the common
         ancestors using the same filenode, then the file was unchanged on one
         side and deleted on the other side. The merge "passively" propagated
         that deletion, but didn't "actively" remove the file. In this case the
         file is *not* included in the `removed` set.
 
         d) If a file exists in only one parent and at least one of the common
         ancestors using a different filenode, then the file was changed on one
         side and removed on the other side. The merge process "actively"
         decided to drop the new change and delete the file. Unlike in the
         previous case, (c), the file included in the `removed` set.
 
         Summary table for merge:
 
         case | exists in parents | exists in gca || removed
          (a) |       both        |     *         ||   yes
          (b) |       one         |     none      ||   yes
          (c) |       one         | same filenode ||   no
          (d) |       one         |  new filenode ||   yes
         """
         return frozenset(self._removed)
 
     def mark_removed(self, filename):
         self._removed.add(filename)
         self._touched.add(filename)
 
     def update_removed(self, filenames):
         for f in filenames:
             self.mark_removed(f)
 
     @property
     def touched(self):
         """files either actively modified, added or removed"""
         return frozenset(self._touched)
 
     def mark_touched(self, filename):
         self._touched.add(filename)
 
     def update_touched(self, filenames):
         for f in filenames:
             self.mark_touched(f)
 
     @property
     def copied_from_p1(self):
         return self._p1_copies.copy()
 
     def mark_copied_from_p1(self, source, dest):
         self._p1_copies[dest] = source
 
     def update_copies_from_p1(self, copies):
         for dest, source in copies.items():
             self.mark_copied_from_p1(source, dest)
 
     @property
     def copied_from_p2(self):
         return self._p2_copies.copy()
 
     def mark_copied_from_p2(self, source, dest):
         self._p2_copies[dest] = source
 
     def update_copies_from_p2(self, copies):
         for dest, source in copies.items():
             self.mark_copied_from_p2(source, dest)
 
 
 def computechangesetfilesadded(ctx):
     """return the list of files added in a changeset
     """
     added = []
     for f in ctx.files():
         if not any(f in p for p in ctx.parents()):
             added.append(f)
     return added
 
 
 def get_removal_filter(ctx, x=None):
     """return a function to detect files "wrongly" detected as `removed`
 
     When a file is removed relative to p1 in a merge, this
     function determines whether the absence is due to a
     deletion from a parent, or whether the merge commit
     itself deletes the file. We decide this by doing a
     simplified three way merge of the manifest entry for
     the file. There are two ways we decide the merge
     itself didn't delete a file:
     - neither parent (nor the merge) contain the file
     - exactly one parent contains the file, and that
       parent has the same filelog entry as the merge
       ancestor (or all of them if there two). In other
       words, that parent left the file unchanged while the
       other one deleted it.
     One way to think about this is that deleting a file is
     similar to emptying it, so the list of changed files
     should be similar either way. The computation
     described above is not done directly in _filecommit
     when creating the list of changed files, however
     it does something very similar by comparing filelog
     nodes.
     """
 
     if x is not None:
         p1, p2, m1, m2 = x
     else:
         p1 = ctx.p1()
         p2 = ctx.p2()
         m1 = p1.manifest()
         m2 = p2.manifest()
 
     @util.cachefunc
     def mas():
         p1n = p1.node()
         p2n = p2.node()
         cahs = ctx.repo().changelog.commonancestorsheads(p1n, p2n)
         if not cahs:
             cahs = [node.nullrev]
         return [ctx.repo()[r].manifest() for r in cahs]
 
     def deletionfromparent(f):
         if f in m1:
             return f not in m2 and all(
                 f in ma and ma.find(f) == m1.find(f) for ma in mas()
             )
         elif f in m2:
             return all(f in ma and ma.find(f) == m2.find(f) for ma in mas())
         else:
             return True
 
     return deletionfromparent
 
 
 def computechangesetfilesremoved(ctx):
     """return the list of files removed in a changeset
     """
     removed = []
     for f in ctx.files():
         if f not in ctx:
             removed.append(f)
     if removed:
         rf = get_removal_filter(ctx)
         removed = [r for r in removed if not rf(r)]
     return removed
 
 
 def computechangesetcopies(ctx):
     """return the copies data for a changeset
 
     The copies data are returned as a pair of dictionnary (p1copies, p2copies).
 
     Each dictionnary are in the form: `{newname: oldname}`
     """
     p1copies = {}
     p2copies = {}
     p1 = ctx.p1()
     p2 = ctx.p2()
     narrowmatch = ctx._repo.narrowmatch()
     for dst in ctx.files():
         if not narrowmatch(dst) or dst not in ctx:
             continue
         copied = ctx[dst].renamed()
         if not copied:
             continue
         src, srcnode = copied
         if src in p1 and p1[src].filenode() == srcnode:
             p1copies[dst] = src
         elif src in p2 and p2[src].filenode() == srcnode:
             p2copies[dst] = src
     return p1copies, p2copies
 
 
 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 encode_files_sidedata(files):
     sortedfiles = sorted(files.touched)
     sidedata = {}
     p1copies = files.copied_from_p1
     if p1copies:
         p1copies = encodecopies(sortedfiles, p1copies)
         sidedata[sidedatamod.SD_P1COPIES] = p1copies
     p2copies = files.copied_from_p2
     if p2copies:
         p2copies = encodecopies(sortedfiles, p2copies)
         sidedata[sidedatamod.SD_P2COPIES] = p2copies
     filesadded = files.added
     if filesadded:
         filesadded = encodefileindices(sortedfiles, filesadded)
         sidedata[sidedatamod.SD_FILESADDED] = filesadded
     filesremoved = files.removed
     if filesremoved:
         filesremoved = encodefileindices(sortedfiles, filesremoved)
         sidedata[sidedatamod.SD_FILESREMOVED] = filesremoved
     if not sidedata:
         sidedata = None
     return sidedata
 
 
+def decode_files_sidedata(changelogrevision, sidedata):
+    """Return a ChangingFiles instance from a changelogrevision using sidata
+    """
+    touched = changelogrevision.files
+
+    rawindices = sidedata.get(sidedatamod.SD_FILESADDED)
+    added = decodefileindices(touched, rawindices)
+
+    rawindices = sidedata.get(sidedatamod.SD_FILESREMOVED)
+    removed = decodefileindices(touched, rawindices)
+
+    rawcopies = sidedata.get(sidedatamod.SD_P1COPIES)
+    p1_copies = decodecopies(touched, rawcopies)
+
+    rawcopies = sidedata.get(sidedatamod.SD_P2COPIES)
+    p2_copies = decodecopies(touched, rawcopies)
+
+    return ChangingFiles(
+        touched=touched,
+        added=added,
+        removed=removed,
+        p1_copies=p1_copies,
+        p2_copies=p2_copies,
+    )
+
+
 def _getsidedata(srcrepo, rev):
     ctx = srcrepo[rev]
     filescopies = computechangesetcopies(ctx)
     filesadded = computechangesetfilesadded(ctx)
     filesremoved = computechangesetfilesremoved(ctx)
     sidedata = {}
     if any([filescopies, filesadded, filesremoved]):
         sortedfiles = sorted(ctx.files())
         p1copies, p2copies = filescopies
         p1copies = encodecopies(sortedfiles, p1copies)
         p2copies = encodecopies(sortedfiles, p2copies)
         filesadded = encodefileindices(sortedfiles, filesadded)
         filesremoved = encodefileindices(sortedfiles, filesremoved)
         if p1copies:
             sidedata[sidedatamod.SD_P1COPIES] = p1copies
         if p2copies:
             sidedata[sidedatamod.SD_P2COPIES] = p2copies
         if filesadded:
             sidedata[sidedatamod.SD_FILESADDED] = filesadded
         if filesremoved:
             sidedata[sidedatamod.SD_FILESREMOVED] = filesremoved
     return sidedata
 
 
 def getsidedataadder(srcrepo, destrepo):
     use_w = srcrepo.ui.configbool(b'experimental', b'worker.repository-upgrade')
     if pycompat.iswindows or not use_w:
         return _get_simple_sidedata_adder(srcrepo, destrepo)
     else:
         return _get_worker_sidedata_adder(srcrepo, destrepo)
 
 
 def _sidedata_worker(srcrepo, revs_queue, sidedata_queue, tokens):
     """The function used by worker precomputing sidedata
 
     It read an input queue containing revision numbers
     It write in an output queue containing (rev, <sidedata-map>)
 
     The `None` input value is used as a stop signal.
 
     The `tokens` semaphore is user to avoid having too many unprocessed
     entries. The workers needs to acquire one token before fetching a task.
     They will be released by the consumer of the produced data.
     """
     tokens.acquire()
     rev = revs_queue.get()
     while rev is not None:
         data = _getsidedata(srcrepo, rev)
         sidedata_queue.put((rev, data))
         tokens.acquire()
         rev = revs_queue.get()
     # processing of `None` is completed, release the token.
     tokens.release()
 
 
 BUFF_PER_WORKER = 50
 
 
 def _get_worker_sidedata_adder(srcrepo, destrepo):
     """The parallel version of the sidedata computation
 
     This code spawn a pool of worker that precompute a buffer of sidedata
     before we actually need them"""
     # avoid circular import copies -> scmutil -> worker -> copies
     from . import worker
 
     nbworkers = worker._numworkers(srcrepo.ui)
 
     tokens = multiprocessing.BoundedSemaphore(nbworkers * BUFF_PER_WORKER)
     revsq = multiprocessing.Queue()
     sidedataq = multiprocessing.Queue()
 
     assert srcrepo.filtername is None
     # queue all tasks beforehand, revision numbers are small and it make
     # synchronisation simpler
     #
     # Since the computation for each node can be quite expensive, the overhead
     # of using a single queue is not revelant. In practice, most computation
     # are fast but some are very expensive and dominate all the other smaller
     # cost.
     for r in srcrepo.changelog.revs():
         revsq.put(r)
     # queue the "no more tasks" markers
     for i in range(nbworkers):
         revsq.put(None)
 
     allworkers = []
     for i in range(nbworkers):
         args = (srcrepo, revsq, sidedataq, tokens)
         w = multiprocessing.Process(target=_sidedata_worker, args=args)
         allworkers.append(w)
         w.start()
 
     # dictionnary to store results for revision higher than we one we are
     # looking for. For example, if we need the sidedatamap for 42, and 43 is
     # received, when shelve 43 for later use.
     staging = {}
 
     def sidedata_companion(revlog, rev):
         sidedata = {}
         if util.safehasattr(revlog, b'filteredrevs'):  # this is a changelog
             # Is the data previously shelved ?
             sidedata = staging.pop(rev, None)
             if sidedata is None:
                 # look at the queued result until we find the one we are lookig
                 # for (shelve the other ones)
                 r, sidedata = sidedataq.get()
                 while r != rev:
                     staging[r] = sidedata
                     r, sidedata = sidedataq.get()
             tokens.release()
         return False, (), sidedata
 
     return sidedata_companion
 
 
 def _get_simple_sidedata_adder(srcrepo, destrepo):
     """The simple version of the sidedata computation
 
     It just compute it in the same thread on request"""
 
     def sidedatacompanion(revlog, rev):
         sidedata = {}
         if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
             sidedata = _getsidedata(srcrepo, rev)
         return False, (), sidedata
 
     return sidedatacompanion
 
 
 def getsidedataremover(srcrepo, destrepo):
     def sidedatacompanion(revlog, rev):
         f = ()
         if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
             if revlog.flags(rev) & sidedataflag.REVIDX_SIDEDATA:
                 f = (
                     sidedatamod.SD_P1COPIES,
                     sidedatamod.SD_P2COPIES,
                     sidedatamod.SD_FILESADDED,
                     sidedatamod.SD_FILESREMOVED,
                 )
         return False, f, {}
 
     return sidedatacompanion