split: new extension to split changesets

This diff introduces an experimental split extension to split changesets.

The implementation is largely inspired by Laurent Charignon's implementation
for mutable-history (changeset 9603aa1ecdfd54b0d86e262318a72e0a2ffeb6cc [1])

This version contains various improvements:

  - Rebase by default.
    This is more friendly for new users. Split won't lead to merge conflicts
    so a rebase won't give the user more trouble.
    This has been on by default at Facebook for months now and seems to be a
    good UX improvement.
    The rebase skips obsoleted or orphaned changesets, which can avoid
    issues like allowdivergence, merge conflicts, etc. This is more flexible
    because the user can decide what to do next (see the last test case in
    test-split.t)

  - Remove "Done split? [y/n]" prompt.
    That could be detected by checking `repo.status()` instead.

  - Works with obsstore disabled.
    Without obsstore, split uses strip to clean up old nodes, and it can
    even handle split a non-head changeset with "allowunstable" disabled,
    since it runs a rebase to solve the "unstable" issue in a same
    transaction.

  - More friendly editor text.
    Put what has been already split into the editor text so users won't lost
    track about where they are.

[1]: https://bitbucket.org/marmoute/mutable-history/commits/9603aa1ecdfd54b

Differential Revision: https://phab.mercurial-scm.org/D1082

hgext/split.py

@@ -0,0 +1,177
+# split.py - split a changeset into smaller ones
+#
+# Copyright 2015 Laurent Charignon <[e-mail]>
+# Copyright 2017 Facebook, Inc.
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2 or any later version.
+"""command to split a changeset into smaller ones (EXPERIMENTAL)"""
+
+from __future__ import absolute_import
+
+from mercurial.i18n import _
+
+from mercurial.node import (
+    nullid,
+    short,
+)
+
+from mercurial import (
+    bookmarks,
+    cmdutil,
+    commands,
+    error,
+    hg,
+    obsolete,
+    phases,
+    registrar,
+    revsetlang,
+    scmutil,
+)
+
+# allow people to use split without explicitly enabling rebase extension
+from . import (
+    rebase,
+)
+
+cmdtable = {}
+command = registrar.command(cmdtable)
+
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
+# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
+# be specifying the version(s) of Mercurial they are tested with, or
+# leave the attribute unspecified.
+testedwith = 'ships-with-hg-core'
+
+@command('^split',
+    [('r', 'rev', '', _("revision to split"), _('REV')),
+     ('', 'rebase', True, _('rebase descendants after split')),
+    ] + cmdutil.commitopts2,
+    _('hg split [--no-rebase] [[-r] REV]'))
+def split(ui, repo, *revs, **opts):
+    """split a changeset into smaller ones
+
+    Repeatedly prompt changes and commit message for new changesets until there
+    is nothing left in the original changeset.
+
+    If --rev was not given, split the working directory parent.
+
+    By default, rebase connected non-obsoleted descendants onto the new
+    changeset. Use --no-rebase to avoid the rebase.
+    """
+    revlist = []
+    if opts.get('rev'):
+        revlist.append(opts.get('rev'))
+    revlist.extend(revs)
+    with repo.wlock(), repo.lock(), repo.transaction('split') as tr:
+        revs = scmutil.revrange(repo, revlist or ['.'])
+        if len(revs) > 1:
+            raise error.Abort(_('cannot split multiple revisions'))
+
+        rev = revs.first()
+        ctx = repo[rev]
+        if rev is None or ctx.node() == nullid:
+            ui.status(_('nothing to split\n'))
+            return 1
+        if ctx.node() is None:
+            raise error.Abort(_('cannot split working directory'))
+
+        # rewriteutil.precheck is not very useful here because:
+        # 1. null check is done above and it's more friendly to return 1
+        #    instead of abort
+        # 2. mergestate check is done below by cmdutil.bailifchanged
+        # 3. unstable check is more complex here because of --rebase
+        #
+        # So only "public" check is useful and it's checked directly here.
+        if ctx.phase() == phases.public:
+            raise error.Abort(_('cannot split public changeset'),
+                              hint=_("see 'hg help phases' for details"))
+
+        descendants = list(repo.revs('(%d::) - (%d)', rev, rev))
+        alloworphaned = obsolete.isenabled(repo, obsolete.allowunstableopt)
+        if opts.get('rebase'):
+            # Skip obsoleted descendants and their descendants so the rebase
+            # won't cause conflicts for sure.
+            torebase = list(repo.revs('%ld - (%ld & obsolete())::',
+                                      descendants, descendants))
+            if not alloworphaned and len(torebase) != len(descendants):
+                raise error.Abort(_('split would leave orphaned changesets '
+                                    'behind'))
+        else:
+            if not alloworphaned and descendants:
+                raise error.Abort(
+                    _('cannot split changeset with children without rebase'))
+            torebase = ()
+
+        if len(ctx.parents()) > 1:
+            raise error.Abort(_('cannot split a merge changeset'))
+
+        cmdutil.bailifchanged(repo)
+
+        # Deactivate bookmark temporarily so it won't get moved unintentionally
+        bname = repo._activebookmark
+        if bname and repo._bookmarks[bname] != ctx.node():
+            bookmarks.deactivate(repo)
+
+        wnode = repo['.'].node()
+        top = None
+        try:
+            top = dosplit(ui, repo, tr, ctx, opts)
+        finally:
+            # top is None: split failed, need update --clean recovery.
+            # wnode == ctx.node(): wnode split, no need to update.
+            if top is None or wnode != ctx.node():
+                hg.clean(repo, wnode, show_stats=False)
+            if bname:
+                bookmarks.activate(repo, bname)
+        if torebase and top:
+            dorebase(ui, repo, torebase, top)
+
+def dosplit(ui, repo, tr, ctx, opts):
+    committed = [] # [ctx]
+
+    # Set working parent to ctx.p1(), and keep working copy as ctx's content
+    # NOTE: if we can have "update without touching working copy" API, the
+    # revert step could be cheaper.
+    hg.clean(repo, ctx.p1().node(), show_stats=False)
+    parents = repo.changelog.parents(ctx.node())
+    ui.pushbuffer()
+    cmdutil.revert(ui, repo, ctx, parents)
+    ui.popbuffer() # discard "reverting ..." messages
+
+    # Any modified, added, removed, deleted result means split is incomplete
+    incomplete = lambda repo: any(repo.status()[:4])
+
+    # Main split loop
+    while incomplete(repo):
+        if committed:
+            header = (_('HG: Splitting %s. So far it has been split into:\n')
+                      % short(ctx.node()))
+            for c in committed:
+                firstline = c.description().split('\n', 1)[0]
+                header += _('HG: - %s: %s\n') % (short(c.node()), firstline)
+            header += _('HG: Write commit message for the next split '
+                        'changeset.\n')
+        else:
+            header = _('HG: Splitting %s. Write commit message for the '
+                       'first split changeset.\n') % short(ctx.node())
+        opts.update({
+            'edit': True,
+            'interactive': True,
+            'message': header + ctx.description(),
+        })
+        commands.commit(ui, repo, **opts)
+        newctx = repo['.']
+        committed.append(newctx)
+
+    if not committed:
+        raise error.Abort(_('cannot split an empty revision'))
+
+    scmutil.cleanupnodes(repo, {ctx.node(): [c.node() for c in committed]},
+                         operation='split')
+
+    return committed[-1]
+
+def dorebase(ui, repo, src, dest):
+    rebase.rebase(ui, repo, rev=[revsetlang.formatspec('%ld', src)],
+                  dest=revsetlang.formatspec('%d', dest))

tests/test-split.t

@@ -0,0 +1,525
+#testcases obsstore-on obsstore-off
+
+  $ cat > $TESTTMP/editor.py <<EOF
+  > #!$PYTHON
+  > import os, sys
+  > path = os.path.join(os.environ['TESTTMP'], 'messages')
+  > messages = open(path).read().split('--\n')
+  > prompt = open(sys.argv[1]).read()
+  > sys.stdout.write(''.join('EDITOR: %s' % l for l in prompt.splitlines(True)))
+  > sys.stdout.flush()
+  > with open(sys.argv[1], 'w') as f:
+  >    f.write(messages[0])
+  > with open(path, 'w') as f:
+  >    f.write('--\n'.join(messages[1:]))
+  > EOF
+
+  $ cat >> $HGRCPATH <<EOF
+  > [extensions]
+  > drawdag=$TESTDIR/drawdag.py
+  > split=
+  > [ui]
+  > interactive=1
+  > [diff]
+  > git=1
+  > unified=0
+  > [alias]
+  > glog=log -G -T '{rev}:{node|short} {desc} {bookmarks}\n'
+  > EOF
+
+#if obsstore-on
+  $ cat >> $HGRCPATH <<EOF
+  > [experimental]
+  > evolution=all
+  > EOF
+#endif
+
+  $ hg init a
+  $ cd a
+
+Nothing to split
+
+  $ hg split
+  nothing to split
+  [1]
+
+  $ hg commit -m empty --config ui.allowemptycommit=1
+  $ hg split
+  abort: cannot split an empty revision
+  [255]
+
+  $ rm -rf .hg
+  $ hg init
+
+Cannot split working directory
+
+  $ hg split -r 'wdir()'
+  abort: cannot split working directory
+  [255]
+
+Generate some content
+
+  $ $TESTDIR/seq.py 1 5 >> a
+  $ hg ci -m a1 -A a -q
+  $ hg bookmark -i r1
+  $ sed 's/1/11/;s/3/33/;s/5/55/' a > b
+  $ mv b a
+  $ hg ci -m a2 -q
+  $ hg bookmark -i r2
+
+Cannot split a public changeset
+
+  $ hg phase --public -r 'all()'
+  $ hg split .
+  abort: cannot split public changeset
+  (see 'hg help phases' for details)
+  [255]
+
+  $ hg phase --draft -f -r 'all()'
+
+Cannot split while working directory is dirty
+
+  $ touch dirty
+  $ hg add dirty
+  $ hg split .
+  abort: uncommitted changes
+  [255]
+  $ hg forget dirty
+  $ rm dirty
+
+Split a head
+
+  $ cp -R . ../b
+  $ cp -R . ../c
+
+  $ hg bookmark r3
+
+  $ hg split 'all()'
+  abort: cannot split multiple revisions
+  [255]
+
+  $ runsplit() {
+  > cat > $TESTTMP/messages <<EOF
+  > split 1
+  > --
+  > split 2
+  > --
+  > split 3
+  > EOF
+  > cat <<EOF | hg split "$@"
+  > y
+  > y
+  > y
+  > y
+  > y
+  > y
+  > EOF
+  > }
+
+  $ HGEDITOR=false runsplit
+  diff --git a/a b/a
+  1 hunks, 1 lines changed
+  examine changes to 'a'? [Ynesfdaq?] y
+  
+  @@ -5,1 +5,1 @@ 4
+  -5
+  +55
+  record this change to 'a'? [Ynesfdaq?] y
+  
+  transaction abort!
+  rollback completed
+  abort: edit failed: false exited with status 1
+  [255]
+  $ hg status
+
+  $ HGEDITOR="$PYTHON $TESTTMP/editor.py"
+  $ runsplit
+  diff --git a/a b/a
+  1 hunks, 1 lines changed
+  examine changes to 'a'? [Ynesfdaq?] y
+  
+  @@ -5,1 +5,1 @@ 4
+  -5
+  +55
+  record this change to 'a'? [Ynesfdaq?] y
+  
+  EDITOR: HG: Splitting 1df0d5c5a3ab. Write commit message for the first split changeset.
+  EDITOR: a2
+  EDITOR: 
+  EDITOR: 
+  EDITOR: HG: Enter commit message.  Lines beginning with 'HG:' are removed.
+  EDITOR: HG: Leave message empty to abort commit.
+  EDITOR: HG: --
+  EDITOR: HG: user: test
+  EDITOR: HG: branch 'default'
+  EDITOR: HG: changed a
+  created new head
+  diff --git a/a b/a
+  1 hunks, 1 lines changed
+  examine changes to 'a'? [Ynesfdaq?] y
+  
+  @@ -3,1 +3,1 @@ 2
+  -3
+  +33
+  record this change to 'a'? [Ynesfdaq?] y
+  
+  EDITOR: HG: Splitting 1df0d5c5a3ab. So far it has been split into:
+  EDITOR: HG: - e704349bd21b: split 1
+  EDITOR: HG: Write commit message for the next split changeset.
+  EDITOR: a2
+  EDITOR: 
+  EDITOR: 
+  EDITOR: HG: Enter commit message.  Lines beginning with 'HG:' are removed.
+  EDITOR: HG: Leave message empty to abort commit.
+  EDITOR: HG: --
+  EDITOR: HG: user: test
+  EDITOR: HG: branch 'default'
+  EDITOR: HG: changed a
+  diff --git a/a b/a
+  1 hunks, 1 lines changed
+  examine changes to 'a'? [Ynesfdaq?] y
+  
+  @@ -1,1 +1,1 @@
+  -1
+  +11
+  record this change to 'a'? [Ynesfdaq?] y
+  
+  EDITOR: HG: Splitting 1df0d5c5a3ab. So far it has been split into:
+  EDITOR: HG: - e704349bd21b: split 1
+  EDITOR: HG: - a09ad58faae3: split 2
+  EDITOR: HG: Write commit message for the next split changeset.
+  EDITOR: a2
+  EDITOR: 
+  EDITOR: 
+  EDITOR: HG: Enter commit message.  Lines beginning with 'HG:' are removed.
+  EDITOR: HG: Leave message empty to abort commit.
+  EDITOR: HG: --
+  EDITOR: HG: user: test
+  EDITOR: HG: branch 'default'
+  EDITOR: HG: changed a
+  saved backup bundle to $TESTTMP/a/.hg/strip-backup/1df0d5c5a3ab-8341b760-split.hg (glob) (obsstore-off !)
+
+#if obsstore-off
+  $ hg bookmark
+     r1                        0:a61bcde8c529
+     r2                        3:00eebaf8d2e2
+   * r3                        3:00eebaf8d2e2
+  $ hg glog -p
+  @  3:00eebaf8d2e2 split 3 r2 r3
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -1,1 +1,1 @@
+  |  -1
+  |  +11
+  |
+  o  2:a09ad58faae3 split 2
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -3,1 +3,1 @@
+  |  -3
+  |  +33
+  |
+  o  1:e704349bd21b split 1
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -5,1 +5,1 @@
+  |  -5
+  |  +55
+  |
+  o  0:a61bcde8c529 a1 r1
+     diff --git a/a b/a
+     new file mode 100644
+     --- /dev/null
+     +++ b/a
+     @@ -0,0 +1,5 @@
+     +1
+     +2
+     +3
+     +4
+     +5
+  
+#else
+  $ hg bookmark
+     r1                        0:a61bcde8c529
+     r2                        4:00eebaf8d2e2
+   * r3                        4:00eebaf8d2e2
+  $ hg glog
+  @  4:00eebaf8d2e2 split 3 r2 r3
+  |
+  o  3:a09ad58faae3 split 2
+  |
+  o  2:e704349bd21b split 1
+  |
+  o  0:a61bcde8c529 a1 r1
+  
+#endif
+
+Split a head while working parent is not that head
+
+  $ cd $TESTTMP/b
+
+  $ hg up 0 -q
+  $ hg bookmark r3
+
+  $ runsplit tip >/dev/null
+
+#if obsstore-off
+  $ hg bookmark
+     r1                        0:a61bcde8c529
+     r2                        3:00eebaf8d2e2
+   * r3                        0:a61bcde8c529
+  $ hg glog
+  o  3:00eebaf8d2e2 split 3 r2
+  |
+  o  2:a09ad58faae3 split 2
+  |
+  o  1:e704349bd21b split 1
+  |
+  @  0:a61bcde8c529 a1 r1 r3
+  
+#else
+  $ hg bookmark
+     r1                        0:a61bcde8c529
+     r2                        4:00eebaf8d2e2
+   * r3                        0:a61bcde8c529
+  $ hg glog
+  o  4:00eebaf8d2e2 split 3 r2
+  |
+  o  3:a09ad58faae3 split 2
+  |
+  o  2:e704349bd21b split 1
+  |
+  @  0:a61bcde8c529 a1 r1 r3
+  
+#endif
+
+Split a non-head
+
+  $ cd $TESTTMP/c
+  $ echo d > d
+  $ hg ci -m d1 -A d
+  $ hg bookmark -i d1
+  $ echo 2 >> d
+  $ hg ci -m d2
+  $ echo 3 >> d
+  $ hg ci -m d3
+  $ hg bookmark -i d3
+  $ hg up '.^' -q
+  $ hg bookmark d2
+  $ cp -R . ../d
+
+  $ runsplit -r 1 | grep rebasing
+  rebasing 2:b5c5ea414030 "d1" (d1)
+  rebasing 3:f4a0a8d004cc "d2" (d2)
+  rebasing 4:777940761eba "d3" (d3)
+#if obsstore-off
+  $ hg bookmark
+     d1                        4:c4b449ef030e
+   * d2                        5:c9dd00ab36a3
+     d3                        6:19f476bc865c
+     r1                        0:a61bcde8c529
+     r2                        3:00eebaf8d2e2
+  $ hg glog -p
+  o  6:19f476bc865c d3 d3
+  |  diff --git a/d b/d
+  |  --- a/d
+  |  +++ b/d
+  |  @@ -2,0 +3,1 @@
+  |  +3
+  |
+  @  5:c9dd00ab36a3 d2 d2
+  |  diff --git a/d b/d
+  |  --- a/d
+  |  +++ b/d
+  |  @@ -1,0 +2,1 @@
+  |  +2
+  |
+  o  4:c4b449ef030e d1 d1
+  |  diff --git a/d b/d
+  |  new file mode 100644
+  |  --- /dev/null
+  |  +++ b/d
+  |  @@ -0,0 +1,1 @@
+  |  +d
+  |
+  o  3:00eebaf8d2e2 split 3 r2
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -1,1 +1,1 @@
+  |  -1
+  |  +11
+  |
+  o  2:a09ad58faae3 split 2
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -3,1 +3,1 @@
+  |  -3
+  |  +33
+  |
+  o  1:e704349bd21b split 1
+  |  diff --git a/a b/a
+  |  --- a/a
+  |  +++ b/a
+  |  @@ -5,1 +5,1 @@
+  |  -5
+  |  +55
+  |
+  o  0:a61bcde8c529 a1 r1
+     diff --git a/a b/a
+     new file mode 100644
+     --- /dev/null
+     +++ b/a
+     @@ -0,0 +1,5 @@
+     +1
+     +2
+     +3
+     +4
+     +5
+  
+#else
+  $ hg bookmark
+     d1                        8:c4b449ef030e
+   * d2                        9:c9dd00ab36a3
+     d3                        10:19f476bc865c
+     r1                        0:a61bcde8c529
+     r2                        7:00eebaf8d2e2
+  $ hg glog
+  o  10:19f476bc865c d3 d3
+  |
+  @  9:c9dd00ab36a3 d2 d2
+  |
+  o  8:c4b449ef030e d1 d1
+  |
+  o  7:00eebaf8d2e2 split 3 r2
+  |
+  o  6:a09ad58faae3 split 2
+  |
+  o  5:e704349bd21b split 1
+  |
+  o  0:a61bcde8c529 a1 r1
+  
+#endif
+
+Split a non-head without rebase
+
+  $ cd $TESTTMP/d
+#if obsstore-off
+  $ runsplit -r 1 --no-rebase
+  abort: cannot split changeset with children without rebase
+  [255]
+#else
+  $ runsplit -r 1 --no-rebase >/dev/null
+  $ hg bookmark
+     d1                        2:b5c5ea414030
+   * d2                        3:f4a0a8d004cc
+     d3                        4:777940761eba
+     r1                        0:a61bcde8c529
+     r2                        7:00eebaf8d2e2
+
+  $ hg glog
+  o  7:00eebaf8d2e2 split 3 r2
+  |
+  o  6:a09ad58faae3 split 2
+  |
+  o  5:e704349bd21b split 1
+  |
+  | o  4:777940761eba d3 d3
+  | |
+  | @  3:f4a0a8d004cc d2 d2
+  | |
+  | o  2:b5c5ea414030 d1 d1
+  | |
+  | x  1:1df0d5c5a3ab a2
+  |/
+  o  0:a61bcde8c529 a1 r1
+  
+#endif
+
+Split a non-head with obsoleted descendants
+
+#if obsstore-on
+  $ hg init $TESTTMP/e
+  $ cd $TESTTMP/e
+  $ hg debugdrawdag <<'EOS'
+  >   H I   J
+  >   | |   |
+  >   F G1 G2  # amend: G1 -> G2
+  >   | |  /   # prune: F
+  >   C D E
+  >    \|/
+  >     B
+  >     |
+  >     A
+  > EOS
+  $ eval `hg tags -T '{tag}={node}\n'`
+  $ rm .hg/localtags
+  $ hg split $B --config experimental.evolution=createmarkers
+  abort: split would leave orphaned changesets behind
+  [255]
+  $ cat > $TESTTMP/messages <<EOF
+  > Split B
+  > EOF
+  $ cat <<EOF | hg split $B
+  > y
+  > y
+  > EOF
+  diff --git a/B b/B
+  new file mode 100644
+  examine changes to 'B'? [Ynesfdaq?] y
+  
+  @@ -0,0 +1,1 @@
+  +B
+  \ No newline at end of file
+  record this change to 'B'? [Ynesfdaq?] y
+  
+  EDITOR: HG: Splitting 112478962961. Write commit message for the first split changeset.
+  EDITOR: B
+  EDITOR: 
+  EDITOR: 
+  EDITOR: HG: Enter commit message.  Lines beginning with 'HG:' are removed.
+  EDITOR: HG: Leave message empty to abort commit.
+  EDITOR: HG: --
+  EDITOR: HG: user: test
+  EDITOR: HG: branch 'default'
+  EDITOR: HG: added B
+  created new head
+  rebasing 2:26805aba1e60 "C"
+  rebasing 3:be0ef73c17ad "D"
+  rebasing 4:49cb92066bfd "E"
+  rebasing 7:97a6268cc7ef "G2"
+  rebasing 10:e2f1e425c0db "J"
+  $ hg glog -r 'sort(all(), topo)'
+  o  16:556c085f8b52 J
+  |
+  o  15:8761f6c9123f G2
+  |
+  o  14:a7aeffe59b65 E
+  |
+  | o  13:e1e914ede9ab D
+  |/
+  | o  12:01947e9b98aa C
+  |/
+  o  11:0947baa74d47 Split B
+  |
+  | o  9:88ede1d5ee13 I
+  | |
+  | x  6:af8cbf225b7b G1
+  | |
+  | x  3:be0ef73c17ad D
+  | |
+  | | o  8:74863e5b5074 H
+  | | |
+  | | x  5:ee481a2a1e69 F
+  | | |
+  | | x  2:26805aba1e60 C
+  | |/
+  | x  1:112478962961 B
+  |/
+  o  0:426bada5c675 A
+  
+#endif