absorb: clarify the reason for not finding changesets to modify

I'm used to pushing to non-publishing repos, so this was the last thing I
thought to check.

hgext/absorb.py

@@ -1,977 +1,977
 # absorb.py
 #
 # Copyright 2016 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.
 
 """apply working directory changes to changesets (EXPERIMENTAL)
 
 The absorb extension provides a command to use annotate information to
 amend modified chunks into the corresponding non-public changesets.
 
 ::
 
     [absorb]
     # only check 50 recent non-public changesets at most
     max-stack-size = 50
     # whether to add noise to new commits to avoid obsolescence cycle
     add-noise = 1
     # make `amend --correlated` a shortcut to the main command
     amend-flag = correlated
 
     [color]
     absorb.node = blue bold
     absorb.path = bold
 """
 
 # TODO:
 #  * Rename config items to [commands] namespace
 #  * Converge getdraftstack() with other code in core
 #  * move many attributes on fixupstate to be private
 
 from __future__ import absolute_import
 
 import collections
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     context,
     crecord,
     error,
     linelog,
     mdiff,
     node,
     obsolete,
     patch,
     phases,
     pycompat,
     registrar,
     repair,
     scmutil,
     util,
 )
 from mercurial.utils import (
     stringutil,
 )
 
 # 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'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('absorb', 'add-noise', default=True)
 configitem('absorb', 'amend-flag', default=None)
 configitem('absorb', 'max-stack-size', default=50)
 
 colortable = {
     'absorb.node': 'blue bold',
     'absorb.path': 'bold',
 }
 
 defaultdict = collections.defaultdict
 
 class nullui(object):
     """blank ui object doing nothing"""
     debugflag = False
     verbose = False
     quiet = True
 
     def __getitem__(name):
         def nullfunc(*args, **kwds):
             return
         return nullfunc
 
 class emptyfilecontext(object):
     """minimal filecontext representing an empty file"""
     def data(self):
         return ''
 
     def node(self):
         return node.nullid
 
 def uniq(lst):
     """list -> list. remove duplicated items without changing the order"""
     seen = set()
     result = []
     for x in lst:
         if x not in seen:
             seen.add(x)
             result.append(x)
     return result
 
 def getdraftstack(headctx, limit=None):
     """(ctx, int?) -> [ctx]. get a linear stack of non-public changesets.
 
     changesets are sorted in topo order, oldest first.
     return at most limit items, if limit is a positive number.
 
     merges are considered as non-draft as well. i.e. every commit
     returned has and only has 1 parent.
     """
     ctx = headctx
     result = []
     while ctx.phase() != phases.public:
         if limit and len(result) >= limit:
             break
         parents = ctx.parents()
         if len(parents) != 1:
             break
         result.append(ctx)
         ctx = parents[0]
     result.reverse()
     return result
 
 def getfilestack(stack, path, seenfctxs=None):
     """([ctx], str, set) -> [fctx], {ctx: fctx}
 
     stack is a list of contexts, from old to new. usually they are what
     "getdraftstack" returns.
 
     follows renames, but not copies.
 
     seenfctxs is a set of filecontexts that will be considered "immutable".
     they are usually what this function returned in earlier calls, useful
     to avoid issues that a file was "moved" to multiple places and was then
     modified differently, like: "a" was copied to "b", "a" was also copied to
     "c" and then "a" was deleted, then both "b" and "c" were "moved" from "a"
     and we enforce only one of them to be able to affect "a"'s content.
 
     return an empty list and an empty dict, if the specified path does not
     exist in stack[-1] (the top of the stack).
 
     otherwise, return a list of de-duplicated filecontexts, and the map to
     convert ctx in the stack to fctx, for possible mutable fctxs. the first item
     of the list would be outside the stack and should be considered immutable.
     the remaining items are within the stack.
 
     for example, given the following changelog and corresponding filelog
     revisions:
 
       changelog: 3----4----5----6----7
       filelog:   x    0----1----1----2 (x: no such file yet)
 
     - if stack = [5, 6, 7], returns ([0, 1, 2], {5: 1, 6: 1, 7: 2})
     - if stack = [3, 4, 5], returns ([e, 0, 1], {4: 0, 5: 1}), where "e" is a
       dummy empty filecontext.
     - if stack = [2], returns ([], {})
     - if stack = [7], returns ([1, 2], {7: 2})
     - if stack = [6, 7], returns ([1, 2], {6: 1, 7: 2}), although {6: 1} can be
       removed, since 1 is immutable.
     """
     if seenfctxs is None:
         seenfctxs = set()
     assert stack
 
     if path not in stack[-1]:
         return [], {}
 
     fctxs = []
     fctxmap = {}
 
     pctx = stack[0].p1() # the public (immutable) ctx we stop at
     for ctx in reversed(stack):
         if path not in ctx: # the file is added in the next commit
             pctx = ctx
             break
         fctx = ctx[path]
         fctxs.append(fctx)
         if fctx in seenfctxs: # treat fctx as the immutable one
             pctx = None # do not add another immutable fctx
             break
         fctxmap[ctx] = fctx # only for mutable fctxs
         renamed = fctx.renamed()
         if renamed:
             path = renamed[0] # follow rename
             if path in ctx: # but do not follow copy
                 pctx = ctx.p1()
                 break
 
     if pctx is not None: # need an extra immutable fctx
         if path in pctx:
             fctxs.append(pctx[path])
         else:
             fctxs.append(emptyfilecontext())
 
     fctxs.reverse()
     # note: we rely on a property of hg: filerev is not reused for linear
     # history. i.e. it's impossible to have:
     #   changelog:  4----5----6 (linear, no merges)
     #   filelog:    1----2----1
     #                         ^ reuse filerev (impossible)
     # because parents are part of the hash. if that's not true, we need to
     # remove uniq and find a different way to identify fctxs.
     return uniq(fctxs), fctxmap
 
 class overlaystore(patch.filestore):
     """read-only, hybrid store based on a dict and ctx.
     memworkingcopy: {path: content}, overrides file contents.
     """
     def __init__(self, basectx, memworkingcopy):
         self.basectx = basectx
         self.memworkingcopy = memworkingcopy
 
     def getfile(self, path):
         """comply with mercurial.patch.filestore.getfile"""
         if path not in self.basectx:
             return None, None, None
         fctx = self.basectx[path]
         if path in self.memworkingcopy:
             content = self.memworkingcopy[path]
         else:
             content = fctx.data()
         mode = (fctx.islink(), fctx.isexec())
         renamed = fctx.renamed() # False or (path, node)
         return content, mode, (renamed and renamed[0])
 
 def overlaycontext(memworkingcopy, ctx, parents=None, extra=None):
     """({path: content}, ctx, (p1node, p2node)?, {}?) -> memctx
     memworkingcopy overrides file contents.
     """
     # parents must contain 2 items: (node1, node2)
     if parents is None:
         parents = ctx.repo().changelog.parents(ctx.node())
     if extra is None:
         extra = ctx.extra()
     date = ctx.date()
     desc = ctx.description()
     user = ctx.user()
     files = set(ctx.files()).union(memworkingcopy)
     store = overlaystore(ctx, memworkingcopy)
     return context.memctx(
         repo=ctx.repo(), parents=parents, text=desc,
         files=files, filectxfn=store, user=user, date=date,
         branch=None, extra=extra)
 
 class filefixupstate(object):
     """state needed to apply fixups to a single file
 
     internally, it keeps file contents of several revisions and a linelog.
 
     the linelog uses odd revision numbers for original contents (fctxs passed
     to __init__), and even revision numbers for fixups, like:
 
         linelog rev 1: self.fctxs[0] (from an immutable "public" changeset)
         linelog rev 2: fixups made to self.fctxs[0]
         linelog rev 3: self.fctxs[1] (a child of fctxs[0])
         linelog rev 4: fixups made to self.fctxs[1]
         ...
 
     a typical use is like:
 
         1. call diffwith, to calculate self.fixups
         2. (optionally), present self.fixups to the user, or change it
         3. call apply, to apply changes
         4. read results from "finalcontents", or call getfinalcontent
     """
 
     def __init__(self, fctxs, ui=None, opts=None):
         """([fctx], ui or None) -> None
 
         fctxs should be linear, and sorted by topo order - oldest first.
         fctxs[0] will be considered as "immutable" and will not be changed.
         """
         self.fctxs = fctxs
         self.ui = ui or nullui()
         self.opts = opts or {}
 
         # following fields are built from fctxs. they exist for perf reason
         self.contents = [f.data() for f in fctxs]
         self.contentlines = pycompat.maplist(mdiff.splitnewlines, self.contents)
         self.linelog = self._buildlinelog()
         if self.ui.debugflag:
             assert self._checkoutlinelog() == self.contents
 
         # following fields will be filled later
         self.chunkstats = [0, 0] # [adopted, total : int]
         self.targetlines = [] # [str]
         self.fixups = [] # [(linelog rev, a1, a2, b1, b2)]
         self.finalcontents = [] # [str]
 
     def diffwith(self, targetfctx, showchanges=False):
         """calculate fixups needed by examining the differences between
         self.fctxs[-1] and targetfctx, chunk by chunk.
 
         targetfctx is the target state we move towards. we may or may not be
         able to get there because not all modified chunks can be amended into
         a non-public fctx unambiguously.
 
         call this only once, before apply().
 
         update self.fixups, self.chunkstats, and self.targetlines.
         """
         a = self.contents[-1]
         alines = self.contentlines[-1]
         b = targetfctx.data()
         blines = mdiff.splitnewlines(b)
         self.targetlines = blines
 
         self.linelog.annotate(self.linelog.maxrev)
         annotated = self.linelog.annotateresult # [(linelog rev, linenum)]
         assert len(annotated) == len(alines)
         # add a dummy end line to make insertion at the end easier
         if annotated:
             dummyendline = (annotated[-1][0], annotated[-1][1] + 1)
             annotated.append(dummyendline)
 
         # analyse diff blocks
         for chunk in self._alldiffchunks(a, b, alines, blines):
             newfixups = self._analysediffchunk(chunk, annotated)
             self.chunkstats[0] += bool(newfixups) # 1 or 0
             self.chunkstats[1] += 1
             self.fixups += newfixups
             if showchanges:
                 self._showchanges(alines, blines, chunk, newfixups)
 
     def apply(self):
         """apply self.fixups. update self.linelog, self.finalcontents.
 
         call this only once, before getfinalcontent(), after diffwith().
         """
         # the following is unnecessary, as it's done by "diffwith":
         #   self.linelog.annotate(self.linelog.maxrev)
         for rev, a1, a2, b1, b2 in reversed(self.fixups):
             blines = self.targetlines[b1:b2]
             if self.ui.debugflag:
                 idx = (max(rev - 1, 0)) // 2
                 self.ui.write(_('%s: chunk %d:%d -> %d lines\n')
                               % (node.short(self.fctxs[idx].node()),
                                  a1, a2, len(blines)))
             self.linelog.replacelines(rev, a1, a2, b1, b2)
         if self.opts.get('edit_lines', False):
             self.finalcontents = self._checkoutlinelogwithedits()
         else:
             self.finalcontents = self._checkoutlinelog()
 
     def getfinalcontent(self, fctx):
         """(fctx) -> str. get modified file content for a given filecontext"""
         idx = self.fctxs.index(fctx)
         return self.finalcontents[idx]
 
     def _analysediffchunk(self, chunk, annotated):
         """analyse a different chunk and return new fixups found
 
         return [] if no lines from the chunk can be safely applied.
 
         the chunk (or lines) cannot be safely applied, if, for example:
           - the modified (deleted) lines belong to a public changeset
             (self.fctxs[0])
           - the chunk is a pure insertion and the adjacent lines (at most 2
             lines) belong to different non-public changesets, or do not belong
             to any non-public changesets.
           - the chunk is modifying lines from different changesets.
             in this case, if the number of lines deleted equals to the number
             of lines added, assume it's a simple 1:1 map (could be wrong).
             otherwise, give up.
           - the chunk is modifying lines from a single non-public changeset,
             but other revisions touch the area as well. i.e. the lines are
             not continuous as seen from the linelog.
         """
         a1, a2, b1, b2 = chunk
         # find involved indexes from annotate result
         involved = annotated[a1:a2]
         if not involved and annotated: # a1 == a2 and a is not empty
             # pure insertion, check nearby lines. ignore lines belong
             # to the public (first) changeset (i.e. annotated[i][0] == 1)
             nearbylinenums = {a2, max(0, a1 - 1)}
             involved = [annotated[i]
                         for i in nearbylinenums if annotated[i][0] != 1]
         involvedrevs = list(set(r for r, l in involved))
         newfixups = []
         if len(involvedrevs) == 1 and self._iscontinuous(a1, a2 - 1, True):
             # chunk belongs to a single revision
             rev = involvedrevs[0]
             if rev > 1:
                 fixuprev = rev + 1
                 newfixups.append((fixuprev, a1, a2, b1, b2))
         elif a2 - a1 == b2 - b1 or b1 == b2:
             # 1:1 line mapping, or chunk was deleted
             for i in pycompat.xrange(a1, a2):
                 rev, linenum = annotated[i]
                 if rev > 1:
                     if b1 == b2: # deletion, simply remove that single line
                         nb1 = nb2 = 0
                     else: # 1:1 line mapping, change the corresponding rev
                         nb1 = b1 + i - a1
                         nb2 = nb1 + 1
                     fixuprev = rev + 1
                     newfixups.append((fixuprev, i, i + 1, nb1, nb2))
         return self._optimizefixups(newfixups)
 
     @staticmethod
     def _alldiffchunks(a, b, alines, blines):
         """like mdiff.allblocks, but only care about differences"""
         blocks = mdiff.allblocks(a, b, lines1=alines, lines2=blines)
         for chunk, btype in blocks:
             if btype != '!':
                 continue
             yield chunk
 
     def _buildlinelog(self):
         """calculate the initial linelog based on self.content{,line}s.
         this is similar to running a partial "annotate".
         """
         llog = linelog.linelog()
         a, alines = '', []
         for i in pycompat.xrange(len(self.contents)):
             b, blines = self.contents[i], self.contentlines[i]
             llrev = i * 2 + 1
             chunks = self._alldiffchunks(a, b, alines, blines)
             for a1, a2, b1, b2 in reversed(list(chunks)):
                 llog.replacelines(llrev, a1, a2, b1, b2)
             a, alines = b, blines
         return llog
 
     def _checkoutlinelog(self):
         """() -> [str]. check out file contents from linelog"""
         contents = []
         for i in pycompat.xrange(len(self.contents)):
             rev = (i + 1) * 2
             self.linelog.annotate(rev)
             content = ''.join(map(self._getline, self.linelog.annotateresult))
             contents.append(content)
         return contents
 
     def _checkoutlinelogwithedits(self):
         """() -> [str]. prompt all lines for edit"""
         alllines = self.linelog.getalllines()
         # header
         editortext = (_('HG: editing %s\nHG: "y" means the line to the right '
                         'exists in the changeset to the top\nHG:\n')
                       % self.fctxs[-1].path())
         # [(idx, fctx)]. hide the dummy emptyfilecontext
         visiblefctxs = [(i, f)
                         for i, f in enumerate(self.fctxs)
                         if not isinstance(f, emptyfilecontext)]
         for i, (j, f) in enumerate(visiblefctxs):
             editortext += (_('HG: %s/%s %s %s\n') %
                            ('|' * i, '-' * (len(visiblefctxs) - i + 1),
                             node.short(f.node()),
                             f.description().split('\n',1)[0]))
         editortext += _('HG: %s\n') % ('|' * len(visiblefctxs))
         # figure out the lifetime of a line, this is relatively inefficient,
         # but probably fine
         lineset = defaultdict(lambda: set()) # {(llrev, linenum): {llrev}}
         for i, f in visiblefctxs:
             self.linelog.annotate((i + 1) * 2)
             for l in self.linelog.annotateresult:
                 lineset[l].add(i)
         # append lines
         for l in alllines:
             editortext += ('    %s : %s' %
                            (''.join([('y' if i in lineset[l] else ' ')
                                      for i, _f in visiblefctxs]),
                             self._getline(l)))
         # run editor
         editedtext = self.ui.edit(editortext, '', action='absorb')
         if not editedtext:
             raise error.Abort(_('empty editor text'))
         # parse edited result
         contents = ['' for i in self.fctxs]
         leftpadpos = 4
         colonpos = leftpadpos + len(visiblefctxs) + 1
         for l in mdiff.splitnewlines(editedtext):
             if l.startswith('HG:'):
                 continue
             if l[colonpos - 1:colonpos + 2] != ' : ':
                 raise error.Abort(_('malformed line: %s') % l)
             linecontent = l[colonpos + 2:]
             for i, ch in enumerate(l[leftpadpos:colonpos - 1]):
                 if ch == 'y':
                     contents[visiblefctxs[i][0]] += linecontent
         # chunkstats is hard to calculate if anything changes, therefore
         # set them to just a simple value (1, 1).
         if editedtext != editortext:
             self.chunkstats = [1, 1]
         return contents
 
     def _getline(self, lineinfo):
         """((rev, linenum)) -> str. convert rev+line number to line content"""
         rev, linenum = lineinfo
         if rev & 1: # odd: original line taken from fctxs
             return self.contentlines[rev // 2][linenum]
         else: # even: fixup line from targetfctx
             return self.targetlines[linenum]
 
     def _iscontinuous(self, a1, a2, closedinterval=False):
         """(a1, a2 : int) -> bool
 
         check if these lines are continuous. i.e. no other insertions or
         deletions (from other revisions) among these lines.
 
         closedinterval decides whether a2 should be included or not. i.e. is
         it [a1, a2), or [a1, a2] ?
         """
         if a1 >= a2:
             return True
         llog = self.linelog
         offset1 = llog.getoffset(a1)
         offset2 = llog.getoffset(a2) + int(closedinterval)
         linesinbetween = llog.getalllines(offset1, offset2)
         return len(linesinbetween) == a2 - a1 + int(closedinterval)
 
     def _optimizefixups(self, fixups):
         """[(rev, a1, a2, b1, b2)] -> [(rev, a1, a2, b1, b2)].
         merge adjacent fixups to make them less fragmented.
         """
         result = []
         pcurrentchunk = [[-1, -1, -1, -1, -1]]
 
         def pushchunk():
             if pcurrentchunk[0][0] != -1:
                 result.append(tuple(pcurrentchunk[0]))
 
         for i, chunk in enumerate(fixups):
             rev, a1, a2, b1, b2 = chunk
             lastrev = pcurrentchunk[0][0]
             lasta2 = pcurrentchunk[0][2]
             lastb2 = pcurrentchunk[0][4]
             if (a1 == lasta2 and b1 == lastb2 and rev == lastrev and
                     self._iscontinuous(max(a1 - 1, 0), a1)):
                 # merge into currentchunk
                 pcurrentchunk[0][2] = a2
                 pcurrentchunk[0][4] = b2
             else:
                 pushchunk()
                 pcurrentchunk[0] = list(chunk)
         pushchunk()
         return result
 
     def _showchanges(self, alines, blines, chunk, fixups):
         ui = self.ui
 
         def label(line, label):
             if line.endswith('\n'):
                 line = line[:-1]
             return ui.label(line, label)
 
         # this is not optimized for perf but _showchanges only gets executed
         # with an extra command-line flag.
         a1, a2, b1, b2 = chunk
         aidxs, bidxs = [0] * (a2 - a1), [0] * (b2 - b1)
         for idx, fa1, fa2, fb1, fb2 in fixups:
             for i in pycompat.xrange(fa1, fa2):
                 aidxs[i - a1] = (max(idx, 1) - 1) // 2
             for i in pycompat.xrange(fb1, fb2):
                 bidxs[i - b1] = (max(idx, 1) - 1) // 2
 
         buf = [] # [(idx, content)]
         buf.append((0, label('@@ -%d,%d +%d,%d @@'
                              % (a1, a2 - a1, b1, b2 - b1), 'diff.hunk')))
         buf += [(aidxs[i - a1], label('-' + alines[i], 'diff.deleted'))
                 for i in pycompat.xrange(a1, a2)]
         buf += [(bidxs[i - b1], label('+' + blines[i], 'diff.inserted'))
                 for i in pycompat.xrange(b1, b2)]
         for idx, line in buf:
             shortnode = idx and node.short(self.fctxs[idx].node()) or ''
             ui.write(ui.label(shortnode[0:7].ljust(8), 'absorb.node') +
                      line + '\n')
 
 class fixupstate(object):
     """state needed to run absorb
 
     internally, it keeps paths and filefixupstates.
 
     a typical use is like filefixupstates:
 
         1. call diffwith, to calculate fixups
         2. (optionally), present fixups to the user, or edit fixups
         3. call apply, to apply changes to memory
         4. call commit, to commit changes to hg database
     """
 
     def __init__(self, stack, ui=None, opts=None):
         """([ctx], ui or None) -> None
 
         stack: should be linear, and sorted by topo order - oldest first.
         all commits in stack are considered mutable.
         """
         assert stack
         self.ui = ui or nullui()
         self.opts = opts or {}
         self.stack = stack
         self.repo = stack[-1].repo().unfiltered()
 
         # following fields will be filled later
         self.paths = [] # [str]
         self.status = None # ctx.status output
         self.fctxmap = {} # {path: {ctx: fctx}}
         self.fixupmap = {} # {path: filefixupstate}
         self.replacemap = {} # {oldnode: newnode or None}
         self.finalnode = None # head after all fixups
 
     def diffwith(self, targetctx, match=None, showchanges=False):
         """diff and prepare fixups. update self.fixupmap, self.paths"""
         # only care about modified files
         self.status = self.stack[-1].status(targetctx, match)
         self.paths = []
         # but if --edit-lines is used, the user may want to edit files
         # even if they are not modified
         editopt = self.opts.get('edit_lines')
         if not self.status.modified and editopt and match:
             interestingpaths = match.files()
         else:
             interestingpaths = self.status.modified
         # prepare the filefixupstate
         seenfctxs = set()
         # sorting is necessary to eliminate ambiguity for the "double move"
         # case: "hg cp A B; hg cp A C; hg rm A", then only "B" can affect "A".
         for path in sorted(interestingpaths):
             self.ui.debug('calculating fixups for %s\n' % path)
             targetfctx = targetctx[path]
             fctxs, ctx2fctx = getfilestack(self.stack, path, seenfctxs)
             # ignore symbolic links or binary, or unchanged files
             if any(f.islink() or stringutil.binary(f.data())
                    for f in [targetfctx] + fctxs
                    if not isinstance(f, emptyfilecontext)):
                 continue
             if targetfctx.data() == fctxs[-1].data() and not editopt:
                 continue
             seenfctxs.update(fctxs[1:])
             self.fctxmap[path] = ctx2fctx
             fstate = filefixupstate(fctxs, ui=self.ui, opts=self.opts)
             if showchanges:
                 colorpath = self.ui.label(path, 'absorb.path')
                 header = 'showing changes for ' + colorpath
                 self.ui.write(header + '\n')
             fstate.diffwith(targetfctx, showchanges=showchanges)
             self.fixupmap[path] = fstate
             self.paths.append(path)
 
     def apply(self):
         """apply fixups to individual filefixupstates"""
         for path, state in self.fixupmap.iteritems():
             if self.ui.debugflag:
                 self.ui.write(_('applying fixups to %s\n') % path)
             state.apply()
 
     @property
     def chunkstats(self):
         """-> {path: chunkstats}. collect chunkstats from filefixupstates"""
         return dict((path, state.chunkstats)
                     for path, state in self.fixupmap.iteritems())
 
     def commit(self):
         """commit changes. update self.finalnode, self.replacemap"""
         with self.repo.wlock(), self.repo.lock():
             with self.repo.transaction('absorb') as tr:
                 self._commitstack()
                 self._movebookmarks(tr)
                 if self.repo['.'].node() in self.replacemap:
                     self._moveworkingdirectoryparent()
                 if self._useobsolete:
                     self._obsoleteoldcommits()
             if not self._useobsolete: # strip must be outside transactions
                 self._stripoldcommits()
         return self.finalnode
 
     def printchunkstats(self):
         """print things like '1 of 2 chunk(s) applied'"""
         ui = self.ui
         chunkstats = self.chunkstats
         if ui.verbose:
             # chunkstats for each file
             for path, stat in chunkstats.iteritems():
                 if stat[0]:
                     ui.write(_('%s: %d of %d chunk(s) applied\n')
                              % (path, stat[0], stat[1]))
         elif not ui.quiet:
             # a summary for all files
             stats = chunkstats.values()
             applied, total = (sum(s[i] for s in stats) for i in (0, 1))
             ui.write(_('%d of %d chunk(s) applied\n') % (applied, total))
 
     def _commitstack(self):
         """make new commits. update self.finalnode, self.replacemap.
         it is splitted from "commit" to avoid too much indentation.
         """
         # last node (20-char) committed by us
         lastcommitted = None
         # p1 which overrides the parent of the next commit, "None" means use
         # the original parent unchanged
         nextp1 = None
         for ctx in self.stack:
             memworkingcopy = self._getnewfilecontents(ctx)
             if not memworkingcopy and not lastcommitted:
                 # nothing changed, nothing commited
                 nextp1 = ctx
                 continue
             msg = ''
             if self._willbecomenoop(memworkingcopy, ctx, nextp1):
                 # changeset is no longer necessary
                 self.replacemap[ctx.node()] = None
                 msg = _('became empty and was dropped')
             else:
                 # changeset needs re-commit
                 nodestr = self._commitsingle(memworkingcopy, ctx, p1=nextp1)
                 lastcommitted = self.repo[nodestr]
                 nextp1 = lastcommitted
                 self.replacemap[ctx.node()] = lastcommitted.node()
                 if memworkingcopy:
                     msg = _('%d file(s) changed, became %s') % (
                         len(memworkingcopy), self._ctx2str(lastcommitted))
                 else:
                     msg = _('became %s') % self._ctx2str(lastcommitted)
             if self.ui.verbose and msg:
                 self.ui.write(_('%s: %s\n') % (self._ctx2str(ctx), msg))
         self.finalnode = lastcommitted and lastcommitted.node()
 
     def _ctx2str(self, ctx):
         if self.ui.debugflag:
             return ctx.hex()
         else:
             return node.short(ctx.node())
 
     def _getnewfilecontents(self, ctx):
         """(ctx) -> {path: str}
 
         fetch file contents from filefixupstates.
         return the working copy overrides - files different from ctx.
         """
         result = {}
         for path in self.paths:
             ctx2fctx = self.fctxmap[path] # {ctx: fctx}
             if ctx not in ctx2fctx:
                 continue
             fctx = ctx2fctx[ctx]
             content = fctx.data()
             newcontent = self.fixupmap[path].getfinalcontent(fctx)
             if content != newcontent:
                 result[fctx.path()] = newcontent
         return result
 
     def _movebookmarks(self, tr):
         repo = self.repo
         needupdate = [(name, self.replacemap[hsh])
                       for name, hsh in repo._bookmarks.iteritems()
                       if hsh in self.replacemap]
         changes = []
         for name, hsh in needupdate:
             if hsh:
                 changes.append((name, hsh))
                 if self.ui.verbose:
                     self.ui.write(_('moving bookmark %s to %s\n')
                                   % (name, node.hex(hsh)))
             else:
                 changes.append((name, None))
                 if self.ui.verbose:
                     self.ui.write(_('deleting bookmark %s\n') % name)
         repo._bookmarks.applychanges(repo, tr, changes)
 
     def _moveworkingdirectoryparent(self):
         if not self.finalnode:
             # Find the latest not-{obsoleted,stripped} parent.
             revs = self.repo.revs('max(::. - %ln)', self.replacemap.keys())
             ctx = self.repo[revs.first()]
             self.finalnode = ctx.node()
         else:
             ctx = self.repo[self.finalnode]
 
         dirstate = self.repo.dirstate
         # dirstate.rebuild invalidates fsmonitorstate, causing "hg status" to
         # be slow. in absorb's case, no need to invalidate fsmonitorstate.
         noop = lambda: 0
         restore = noop
         if util.safehasattr(dirstate, '_fsmonitorstate'):
             bak = dirstate._fsmonitorstate.invalidate
             def restore():
                 dirstate._fsmonitorstate.invalidate = bak
             dirstate._fsmonitorstate.invalidate = noop
         try:
             with dirstate.parentchange():
                 dirstate.rebuild(ctx.node(), ctx.manifest(), self.paths)
         finally:
             restore()
 
     @staticmethod
     def _willbecomenoop(memworkingcopy, ctx, pctx=None):
         """({path: content}, ctx, ctx) -> bool. test if a commit will be noop
 
         if it will become an empty commit (does not change anything, after the
         memworkingcopy overrides), return True. otherwise return False.
         """
         if not pctx:
             parents = ctx.parents()
             if len(parents) != 1:
                 return False
             pctx = parents[0]
         # ctx changes more files (not a subset of memworkingcopy)
         if not set(ctx.files()).issubset(set(memworkingcopy)):
             return False
         for path, content in memworkingcopy.iteritems():
             if path not in pctx or path not in ctx:
                 return False
             fctx = ctx[path]
             pfctx = pctx[path]
             if pfctx.flags() != fctx.flags():
                 return False
             if pfctx.data() != content:
                 return False
         return True
 
     def _commitsingle(self, memworkingcopy, ctx, p1=None):
         """(ctx, {path: content}, node) -> node. make a single commit
 
         the commit is a clone from ctx, with a (optionally) different p1, and
         different file contents replaced by memworkingcopy.
         """
         parents = p1 and (p1, node.nullid)
         extra = ctx.extra()
         if self._useobsolete and self.ui.configbool('absorb', 'add-noise'):
             extra['absorb_source'] = ctx.hex()
         mctx = overlaycontext(memworkingcopy, ctx, parents, extra=extra)
         # preserve phase
         with mctx.repo().ui.configoverride({
             ('phases', 'new-commit'): ctx.phase()}):
             return mctx.commit()
 
     @util.propertycache
     def _useobsolete(self):
         """() -> bool"""
         return obsolete.isenabled(self.repo, obsolete.createmarkersopt)
 
     def _obsoleteoldcommits(self):
         relations = [(self.repo[k], v and (self.repo[v],) or ())
                      for k, v in self.replacemap.iteritems()]
         if relations:
             obsolete.createmarkers(self.repo, relations)
 
     def _stripoldcommits(self):
         nodelist = self.replacemap.keys()
         # make sure we don't strip innocent children
         revs = self.repo.revs('%ln - (::(heads(%ln::)-%ln))', nodelist,
                               nodelist, nodelist)
         tonode = self.repo.changelog.node
         nodelist = [tonode(r) for r in revs]
         if nodelist:
             repair.strip(self.repo.ui, self.repo, nodelist)
 
 def _parsechunk(hunk):
     """(crecord.uihunk or patch.recordhunk) -> (path, (a1, a2, [bline]))"""
     if type(hunk) not in (crecord.uihunk, patch.recordhunk):
         return None, None
     path = hunk.header.filename()
     a1 = hunk.fromline + len(hunk.before) - 1
     # remove before and after context
     hunk.before = hunk.after = []
     buf = util.stringio()
     hunk.write(buf)
     patchlines = mdiff.splitnewlines(buf.getvalue())
     # hunk.prettystr() will update hunk.removed
     a2 = a1 + hunk.removed
     blines = [l[1:] for l in patchlines[1:] if l[0] != '-']
     return path, (a1, a2, blines)
 
 def overlaydiffcontext(ctx, chunks):
     """(ctx, [crecord.uihunk]) -> memctx
 
     return a memctx with some [1] patches (chunks) applied to ctx.
     [1]: modifications are handled. renames, mode changes, etc. are ignored.
     """
     # sadly the applying-patch logic is hardly reusable, and messy:
     # 1. the core logic "_applydiff" is too heavy - it writes .rej files, it
     #    needs a file stream of a patch and will re-parse it, while we have
     #    structured hunk objects at hand.
     # 2. a lot of different implementations about "chunk" (patch.hunk,
     #    patch.recordhunk, crecord.uihunk)
     # as we only care about applying changes to modified files, no mode
     # change, no binary diff, and no renames, it's probably okay to
     # re-invent the logic using much simpler code here.
     memworkingcopy = {} # {path: content}
     patchmap = defaultdict(lambda: []) # {path: [(a1, a2, [bline])]}
     for path, info in map(_parsechunk, chunks):
         if not path or not info:
             continue
         patchmap[path].append(info)
     for path, patches in patchmap.iteritems():
         if path not in ctx or not patches:
             continue
         patches.sort(reverse=True)
         lines = mdiff.splitnewlines(ctx[path].data())
         for a1, a2, blines in patches:
             lines[a1:a2] = blines
         memworkingcopy[path] = ''.join(lines)
     return overlaycontext(memworkingcopy, ctx)
 
 def absorb(ui, repo, stack=None, targetctx=None, pats=None, opts=None):
     """pick fixup chunks from targetctx, apply them to stack.
 
     if targetctx is None, the working copy context will be used.
     if stack is None, the current draft stack will be used.
     return fixupstate.
     """
     if stack is None:
         limit = ui.configint('absorb', 'max-stack-size')
         stack = getdraftstack(repo['.'], limit)
         if limit and len(stack) >= limit:
             ui.warn(_('absorb: only the recent %d changesets will '
                       'be analysed\n')
                     % limit)
     if not stack:
-        raise error.Abort(_('no changeset to change'))
+        raise error.Abort(_('no mutable changeset to change'))
     if targetctx is None: # default to working copy
         targetctx = repo[None]
     if pats is None:
         pats = ()
     if opts is None:
         opts = {}
     state = fixupstate(stack, ui=ui, opts=opts)
     matcher = scmutil.match(targetctx, pats, opts)
     if opts.get('interactive'):
         diff = patch.diff(repo, stack[-1].node(), targetctx.node(), matcher)
         origchunks = patch.parsepatch(diff)
         chunks = cmdutil.recordfilter(ui, origchunks)[0]
         targetctx = overlaydiffcontext(stack[-1], chunks)
     state.diffwith(targetctx, matcher, showchanges=opts.get('print_changes'))
     if not opts.get('dry_run'):
         state.apply()
         if state.commit():
             state.printchunkstats()
         elif not ui.quiet:
             ui.write(_('nothing applied\n'))
     return state
 
 @command('^absorb',
          [('p', 'print-changes', None,
            _('print which changesets are modified by which changes')),
           ('i', 'interactive', None,
            _('interactively select which chunks to apply (EXPERIMENTAL)')),
           ('e', 'edit-lines', None,
            _('edit what lines belong to which changesets before commit '
              '(EXPERIMENTAL)')),
          ] + commands.dryrunopts + commands.walkopts,
          _('hg absorb [OPTION] [FILE]...'))
 def absorbcmd(ui, repo, *pats, **opts):
     """incorporate corrections into the stack of draft changesets
 
     absorb analyzes each change in your working directory and attempts to
     amend the changed lines into the changesets in your stack that first
     introduced those lines.
 
     If absorb cannot find an unambiguous changeset to amend for a change,
     that change will be left in the working directory, untouched. They can be
     observed by :hg:`status` or :hg:`diff` afterwards. In other words,
     absorb does not write to the working directory.
 
     Changesets outside the revset `::. and not public() and not merge()` will
     not be changed.
 
     Changesets that become empty after applying the changes will be deleted.
 
     If in doubt, run :hg:`absorb -pn` to preview what changesets will
     be amended by what changed lines, without actually changing anything.
 
     Returns 0 on success, 1 if all chunks were ignored and nothing amended.
     """
     state = absorb(ui, repo, pats=pats, opts=opts)
     if sum(s[0] for s in state.chunkstats.values()) == 0:
         return 1

tests/test-absorb.t

@@ -1,451 +1,451
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > absorb=
   > EOF
 
   $ sedi() { # workaround check-code
   > pattern="$1"
   > shift
   > for i in "$@"; do
   >     sed "$pattern" "$i" > "$i".tmp
   >     mv "$i".tmp "$i"
   > done
   > }
 
   $ hg init repo1
   $ cd repo1
 
 Do not crash with empty repo:
 
   $ hg absorb
-  abort: no changeset to change
+  abort: no mutable changeset to change
   [255]
 
 Make some commits:
 
   $ for i in 1 2 3 4 5; do
   >   echo $i >> a
   >   hg commit -A a -m "commit $i" -q
   > done
 
   $ hg annotate a
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 Change a few lines:
 
   $ cat > a <<EOF
   > 1a
   > 2b
   > 3
   > 4d
   > 5e
   > EOF
 
 Preview absorb changes:
 
   $ hg absorb --print-changes --dry-run
   showing changes for a
           @@ -0,2 +0,2 @@
   4ec16f8 -1
   5c5f952 -2
   4ec16f8 +1a
   5c5f952 +2b
           @@ -3,2 +3,2 @@
   ad8b8b7 -4
   4f55fa6 -5
   ad8b8b7 +4d
   4f55fa6 +5e
 
 Run absorb:
 
   $ hg absorb
   saved backup bundle to * (glob)
   2 of 2 chunk(s) applied
   $ hg annotate a
   0: 1a
   1: 2b
   2: 3
   3: 4d
   4: 5e
 
 Delete a few lines and related commits will be removed if they will be empty:
 
   $ cat > a <<EOF
   > 2b
   > 4d
   > EOF
   $ hg absorb
   saved backup bundle to * (glob)
   3 of 3 chunk(s) applied
   $ hg annotate a
   1: 2b
   2: 4d
   $ hg log -T '{rev} {desc}\n' -Gp
   @  2 commit 4
   |  diff -r 1cae118c7ed8 -r 58a62bade1c6 a
   |  --- a/a	Thu Jan 01 00:00:00 1970 +0000
   |  +++ b/a	Thu Jan 01 00:00:00 1970 +0000
   |  @@ -1,1 +1,2 @@
   |   2b
   |  +4d
   |
   o  1 commit 2
   |  diff -r 84add69aeac0 -r 1cae118c7ed8 a
   |  --- a/a	Thu Jan 01 00:00:00 1970 +0000
   |  +++ b/a	Thu Jan 01 00:00:00 1970 +0000
   |  @@ -0,0 +1,1 @@
   |  +2b
   |
   o  0 commit 1
   
 
 Non 1:1 map changes will be ignored:
 
   $ echo 1 > a
   $ hg absorb
   nothing applied
   [1]
 
 Insertaions:
 
   $ cat > a << EOF
   > insert before 2b
   > 2b
   > 4d
   > insert aftert 4d
   > EOF
   $ hg absorb -q
   $ hg status
   $ hg annotate a
   1: insert before 2b
   1: 2b
   2: 4d
   2: insert aftert 4d
 
 Bookmarks are moved:
 
   $ hg bookmark -r 1 b1
   $ hg bookmark -r 2 b2
   $ hg bookmark ba
   $ hg bookmarks
      b1                        1:b35060a57a50
      b2                        2:946e4bc87915
    * ba                        2:946e4bc87915
   $ sedi 's/insert/INSERT/' a
   $ hg absorb -q
   $ hg status
   $ hg bookmarks
      b1                        1:a4183e9b3d31
      b2                        2:c9b20c925790
    * ba                        2:c9b20c925790
 
 Non-mofified files are ignored:
 
   $ touch b
   $ hg commit -A b -m b
   $ touch c
   $ hg add c
   $ hg rm b
   $ hg absorb
   nothing applied
   [1]
   $ sedi 's/INSERT/Insert/' a
   $ hg absorb
   saved backup bundle to * (glob)
   2 of 2 chunk(s) applied
   $ hg status
   A c
   R b
 
 Public commits will not be changed:
 
   $ hg phase -p 1
   $ sedi 's/Insert/insert/' a
   $ hg absorb -pn
   showing changes for a
           @@ -0,1 +0,1 @@
           -Insert before 2b
           +insert before 2b
           @@ -3,1 +3,1 @@
   85b4e0e -Insert aftert 4d
   85b4e0e +insert aftert 4d
   $ hg absorb
   saved backup bundle to * (glob)
   1 of 2 chunk(s) applied
   $ hg diff -U 0
   diff -r 1c8eadede62a a
   --- a/a	Thu Jan 01 00:00:00 1970 +0000
   +++ b/a	* (glob)
   @@ -1,1 +1,1 @@
   -Insert before 2b
   +insert before 2b
   $ hg annotate a
   1: Insert before 2b
   1: 2b
   2: 4d
   2: insert aftert 4d
 
 Make working copy clean:
 
   $ hg revert -q -C a b
   $ hg forget c
   $ rm c
   $ hg status
 
 Merge commit will not be changed:
 
   $ echo 1 > m1
   $ hg commit -A m1 -m m1
   $ hg bookmark -q -i m1
   $ hg update -q '.^'
   $ echo 2 > m2
   $ hg commit -q -A m2 -m m2
   $ hg merge -q m1
   $ hg commit -m merge
   $ hg bookmark -d m1
   $ hg log -G -T '{rev} {desc} {phase}\n'
   @    6 merge draft
   |\
   | o  5 m2 draft
   | |
   o |  4 m1 draft
   |/
   o  3 b draft
   |
   o  2 commit 4 draft
   |
   o  1 commit 2 public
   |
   o  0 commit 1 public
   
   $ echo 2 >> m1
   $ echo 2 >> m2
   $ hg absorb
-  abort: no changeset to change
+  abort: no mutable changeset to change
   [255]
   $ hg revert -q -C m1 m2
 
 Use a new repo:
 
   $ cd ..
   $ hg init repo2
   $ cd repo2
 
 Make some commits to multiple files:
 
   $ for f in a b; do
   >   for i in 1 2; do
   >     echo $f line $i >> $f
   >     hg commit -A $f -m "commit $f $i" -q
   >   done
   > done
 
 Use pattern to select files to be fixed up:
 
   $ sedi 's/line/Line/' a b
   $ hg status
   M a
   M b
   $ hg absorb a
   saved backup bundle to * (glob)
   1 of 1 chunk(s) applied
   $ hg status
   M b
   $ hg absorb --exclude b
   nothing applied
   [1]
   $ hg absorb b
   saved backup bundle to * (glob)
   1 of 1 chunk(s) applied
   $ hg status
   $ cat a b
   a Line 1
   a Line 2
   b Line 1
   b Line 2
 
 Test config option absorb.max-stack-size:
 
   $ sedi 's/Line/line/' a b
   $ hg log -T '{rev}:{node} {desc}\n'
   3:712d16a8f445834e36145408eabc1d29df05ec09 commit b 2
   2:74cfa6294160149d60adbf7582b99ce37a4597ec commit b 1
   1:28f10dcf96158f84985358a2e5d5b3505ca69c22 commit a 2
   0:f9a81da8dc53380ed91902e5b82c1b36255a4bd0 commit a 1
   $ hg --config absorb.max-stack-size=1 absorb -pn
   absorb: only the recent 1 changesets will be analysed
   showing changes for a
           @@ -0,2 +0,2 @@
           -a Line 1
           -a Line 2
           +a line 1
           +a line 2
   showing changes for b
           @@ -0,2 +0,2 @@
           -b Line 1
   712d16a -b Line 2
           +b line 1
   712d16a +b line 2
 
 Test obsolete markers creation:
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > evolution=createmarkers
   > [absorb]
   > add-noise=1
   > EOF
 
   $ hg --config absorb.max-stack-size=3 absorb
   absorb: only the recent 3 changesets will be analysed
   2 of 2 chunk(s) applied
   $ hg log -T '{rev}:{node|short} {desc} {get(extras, "absorb_source")}\n'
   6:3dfde4199b46 commit b 2 712d16a8f445834e36145408eabc1d29df05ec09
   5:99cfab7da5ff commit b 1 74cfa6294160149d60adbf7582b99ce37a4597ec
   4:fec2b3bd9e08 commit a 2 28f10dcf96158f84985358a2e5d5b3505ca69c22
   0:f9a81da8dc53 commit a 1 
   $ hg absorb
   1 of 1 chunk(s) applied
   $ hg log -T '{rev}:{node|short} {desc} {get(extras, "absorb_source")}\n'
   10:e1c8c1e030a4 commit b 2 3dfde4199b4610ea6e3c6fa9f5bdad8939d69524
   9:816c30955758 commit b 1 99cfab7da5ffdaf3b9fc6643b14333e194d87f46
   8:5867d584106b commit a 2 fec2b3bd9e0834b7cb6a564348a0058171aed811
   7:8c76602baf10 commit a 1 f9a81da8dc53380ed91902e5b82c1b36255a4bd0
 
 Executable files:
 
   $ cat >> $HGRCPATH << EOF
   > [diff]
   > git=True
   > EOF
   $ cd ..
   $ hg init repo3
   $ cd repo3
 
 #if execbit
   $ echo > foo.py
   $ chmod +x foo.py
   $ hg add foo.py
   $ hg commit -mfoo
 #else
   $ hg import -q --bypass - <<EOF
   > # HG changeset patch
   > foo
   > 
   > diff --git a/foo.py b/foo.py
   > new file mode 100755
   > --- /dev/null
   > +++ b/foo.py
   > @@ -0,0 +1,1 @@
   > +
   > EOF
   $ hg up -q
 #endif
 
   $ echo bla > foo.py
   $ hg absorb --dry-run --print-changes
   showing changes for foo.py
           @@ -0,1 +0,1 @@
   99b4ae7 -
   99b4ae7 +bla
   $ hg absorb
   1 of 1 chunk(s) applied
   $ hg diff -c .
   diff --git a/foo.py b/foo.py
   new file mode 100755
   --- /dev/null
   +++ b/foo.py
   @@ -0,0 +1,1 @@
   +bla
   $ hg diff
 
 Remove lines may delete changesets:
 
   $ cd ..
   $ hg init repo4
   $ cd repo4
   $ cat > a <<EOF
   > 1
   > 2
   > EOF
   $ hg commit -m a12 -A a
   $ cat > b <<EOF
   > 1
   > 2
   > EOF
   $ hg commit -m b12 -A b
   $ echo 3 >> b
   $ hg commit -m b3
   $ echo 4 >> b
   $ hg commit -m b4
   $ echo 1 > b
   $ echo 3 >> a
   $ hg absorb -pn
   showing changes for a
           @@ -2,0 +2,1 @@
   bfafb49 +3
   showing changes for b
           @@ -1,3 +1,0 @@
   1154859 -2
   30970db -3
   a393a58 -4
   $ hg absorb -v | grep became
   bfafb49242db: 1 file(s) changed, became 1a2de97fc652
   115485984805: 2 file(s) changed, became 0c930dfab74c
   30970dbf7b40: became empty and was dropped
   a393a58b9a85: became empty and was dropped
   $ hg log -T '{rev} {desc}\n' -Gp
   @  5 b12
   |  diff --git a/b b/b
   |  new file mode 100644
   |  --- /dev/null
   |  +++ b/b
   |  @@ -0,0 +1,1 @@
   |  +1
   |
   o  4 a12
      diff --git a/a b/a
      new file mode 100644
      --- /dev/null
      +++ b/a
      @@ -0,0 +1,3 @@
      +1
      +2
      +3
   
 
 Use revert to make the current change and its parent disappear.
 This should move us to the non-obsolete ancestor.
 
   $ cd ..
   $ hg init repo5
   $ cd repo5
   $ cat > a <<EOF
   > 1
   > 2
   > EOF
   $ hg commit -m a12 -A a
   $ hg id
   bfafb49242db tip
   $ echo 3 >> a
   $ hg commit -m a123 a
   $ echo 4 >> a
   $ hg commit -m a1234 a
   $ hg id
   82dbe7fd19f0 tip
   $ hg revert -r 0 a
   $ hg absorb -pn
   showing changes for a
           @@ -2,2 +2,0 @@
   f1c23dd -3
   82dbe7f -4
   $ hg absorb --verbose
   f1c23dd5d08d: became empty and was dropped
   82dbe7fd19f0: became empty and was dropped
   a: 1 of 1 chunk(s) applied
   $ hg id
   bfafb49242db tip