largefiles: factor out procedures to update standins for pre-committing

This patch factors out procedures to update standins for
pre-committing. This is one of preparations to avoid execution of such
procedures according to invocation context.

For example, resuming automated committing (e.g. "hg rebase
--continue") should update standins at the 1st commit, because
largefiles in the working directory may be modified manually. But on
the other hand, it should avoid updating standins at subsequent
committings for efficiency reason.

For simplicity, this patch just moves procedures mechanically only
with replacing below.

  - "self"            => "repo"
  - "lfutil."         => (none)
  - "orig" invocation => returning "match"

Using "fstandin" instead "standin" as the name of local variable for
the loop below is the only special care, because the latter shadows
the same name function in "lfutil.py".

  [before]
                for standin in standins:
                    lfile = lfutil.splitstandin(standin)
                    if lfdirstate[lfile] != 'r':
                        lfutil.updatestandin(self, standin)

  [after]
    for fstandin in standins:
        lfile = splitstandin(fstandin)
        if lfdirstate[lfile] != 'r':
            updatestandin(repo, fstandin)

hgext/largefiles/lfutil.py

@@ -12,6 +12,7 b' import os'
 import platform
 import shutil
 import stat
+import copy
 
 from mercurial import dirstate, httpconnection, match as match_, util, scmutil
 from mercurial.i18n import _
@@ -427,3 +428,112 b' def getlfilestoupload(repo, missing, add'
         for fn in files:
             if isstandin(fn) and fn in ctx:
                 addfunc(fn, ctx[fn].data().strip())
+
+def updatestandinsbymatch(repo, match):
+    '''Update standins in the working directory according to specified match
+
+    This returns (possibly modified) ``match`` object to be used for
+    subsequent commit process.
+    '''
+
+    ui = repo.ui
+
+    # Case 0: Automated committing
+    #
+    # While automated committing (like rebase, transplant
+    # and so on), this code path is used to avoid:
+    # (1) updating standins, because standins should
+    #     be already updated at this point
+    # (2) aborting when standins are matched by "match",
+    #     because automated committing may specify them directly
+    #
+    if getattr(repo, "_isrebasing", False) or \
+            getattr(repo, "_istransplanting", False):
+        return match
+
+    # Case 1: user calls commit with no specific files or
+    # include/exclude patterns: refresh and commit all files that
+    # are "dirty".
+    if match is None or match.always():
+        # Spend a bit of time here to get a list of files we know
+        # are modified so we can compare only against those.
+        # It can cost a lot of time (several seconds)
+        # otherwise to update all standins if the largefiles are
+        # large.
+        lfdirstate = openlfdirstate(ui, repo)
+        dirtymatch = match_.always(repo.root, repo.getcwd())
+        unsure, s = lfdirstate.status(dirtymatch, [], False, False,
+                                      False)
+        modifiedfiles = unsure + s.modified + s.added + s.removed
+        lfiles = listlfiles(repo)
+        # this only loops through largefiles that exist (not
+        # removed/renamed)
+        for lfile in lfiles:
+            if lfile in modifiedfiles:
+                if os.path.exists(
+                        repo.wjoin(standin(lfile))):
+                    # this handles the case where a rebase is being
+                    # performed and the working copy is not updated
+                    # yet.
+                    if os.path.exists(repo.wjoin(lfile)):
+                        updatestandin(repo,
+                            standin(lfile))
+
+        return match
+
+    lfiles = listlfiles(repo)
+    match._files = repo._subdirlfs(match.files(), lfiles)
+
+    # Case 2: user calls commit with specified patterns: refresh
+    # any matching big files.
+    smatcher = composestandinmatcher(repo, match)
+    standins = repo.dirstate.walk(smatcher, [], False, False)
+
+    # No matching big files: get out of the way and pass control to
+    # the usual commit() method.
+    if not standins:
+        return match
+
+    # Refresh all matching big files.  It's possible that the
+    # commit will end up failing, in which case the big files will
+    # stay refreshed.  No harm done: the user modified them and
+    # asked to commit them, so sooner or later we're going to
+    # refresh the standins.  Might as well leave them refreshed.
+    lfdirstate = openlfdirstate(ui, repo)
+    for fstandin in standins:
+        lfile = splitstandin(fstandin)
+        if lfdirstate[lfile] != 'r':
+            updatestandin(repo, fstandin)
+
+    # Cook up a new matcher that only matches regular files or
+    # standins corresponding to the big files requested by the
+    # user.  Have to modify _files to prevent commit() from
+    # complaining "not tracked" for big files.
+    match = copy.copy(match)
+    origmatchfn = match.matchfn
+
+    # Check both the list of largefiles and the list of
+    # standins because if a largefile was removed, it
+    # won't be in the list of largefiles at this point
+    match._files += sorted(standins)
+
+    actualfiles = []
+    for f in match._files:
+        fstandin = standin(f)
+
+        # ignore known largefiles and standins
+        if f in lfiles or fstandin in standins:
+            continue
+
+        actualfiles.append(f)
+    match._files = actualfiles
+
+    def matchfn(f):
+        if origmatchfn(f):
+            return f not in lfiles
+        else:
+            return f in standins
+
+    match.matchfn = matchfn
+
+    return match

hgext/largefiles/reposetup.py

@@ -262,108 +262,7 b' def reposetup(ui, repo):'
 
             wlock = self.wlock()
             try:
-                # Case 0: Automated committing
-                #
-                # While automated committing (like rebase, transplant
-                # and so on), this code path is used to avoid:
-                # (1) updating standins, because standins should
-                #     be already updated at this point
-                # (2) aborting when standins are matched by "match",
-                #     because automated committing may specify them directly
-                #
-                if getattr(self, "_isrebasing", False) or \
-                        getattr(self, "_istransplanting", False):
-                    result = orig(text=text, user=user, date=date, match=match,
-                                    force=force, editor=editor, extra=extra)
-                    return result
-                # Case 1: user calls commit with no specific files or
-                # include/exclude patterns: refresh and commit all files that
-                # are "dirty".
-                if match is None or match.always():
-                    # Spend a bit of time here to get a list of files we know
-                    # are modified so we can compare only against those.
-                    # It can cost a lot of time (several seconds)
-                    # otherwise to update all standins if the largefiles are
-                    # large.
-                    lfdirstate = lfutil.openlfdirstate(ui, self)
-                    dirtymatch = match_.always(self.root, self.getcwd())
-                    unsure, s = lfdirstate.status(dirtymatch, [], False, False,
-                                                  False)
-                    modifiedfiles = unsure + s.modified + s.added + s.removed
-                    lfiles = lfutil.listlfiles(self)
-                    # this only loops through largefiles that exist (not
-                    # removed/renamed)
-                    for lfile in lfiles:
-                        if lfile in modifiedfiles:
-                            if os.path.exists(
-                                    self.wjoin(lfutil.standin(lfile))):
-                                # this handles the case where a rebase is being
-                                # performed and the working copy is not updated
-                                # yet.
-                                if os.path.exists(self.wjoin(lfile)):
-                                    lfutil.updatestandin(self,
-                                        lfutil.standin(lfile))
-
-                    result = orig(text=text, user=user, date=date, match=match,
-                                    force=force, editor=editor, extra=extra)
-
-                    return result
-
-                lfiles = lfutil.listlfiles(self)
-                match._files = self._subdirlfs(match.files(), lfiles)
-
-                # Case 2: user calls commit with specified patterns: refresh
-                # any matching big files.
-                smatcher = lfutil.composestandinmatcher(self, match)
-                standins = self.dirstate.walk(smatcher, [], False, False)
-
-                # No matching big files: get out of the way and pass control to
-                # the usual commit() method.
-                if not standins:
-                    return orig(text=text, user=user, date=date, match=match,
-                                    force=force, editor=editor, extra=extra)
-
-                # Refresh all matching big files.  It's possible that the
-                # commit will end up failing, in which case the big files will
-                # stay refreshed.  No harm done: the user modified them and
-                # asked to commit them, so sooner or later we're going to
-                # refresh the standins.  Might as well leave them refreshed.
-                lfdirstate = lfutil.openlfdirstate(ui, self)
-                for standin in standins:
-                    lfile = lfutil.splitstandin(standin)
-                    if lfdirstate[lfile] != 'r':
-                        lfutil.updatestandin(self, standin)
-
-                # Cook up a new matcher that only matches regular files or
-                # standins corresponding to the big files requested by the
-                # user.  Have to modify _files to prevent commit() from
-                # complaining "not tracked" for big files.
-                match = copy.copy(match)
-                origmatchfn = match.matchfn
-
-                # Check both the list of largefiles and the list of
-                # standins because if a largefile was removed, it
-                # won't be in the list of largefiles at this point
-                match._files += sorted(standins)
-
-                actualfiles = []
-                for f in match._files:
-                    fstandin = lfutil.standin(f)
-
-                    # ignore known largefiles and standins
-                    if f in lfiles or fstandin in standins:
-                        continue
-
-                    actualfiles.append(f)
-                match._files = actualfiles
-
-                def matchfn(f):
-                    if origmatchfn(f):
-                        return f not in lfiles
-                    else:
-                        return f in standins
-
-                match.matchfn = matchfn
+                match = lfutil.updatestandinsbymatch(self, match)
                 result = orig(text=text, user=user, date=date, match=match,
                                 force=force, editor=editor, extra=extra)
                 return result
@@ -381,6 +280,8 b' def reposetup(ui, repo):'
             return super(lfilesrepo, self).push(remote, force=force, revs=revs,
                 newbranch=newbranch)
 
+        # TODO: _subdirlfs should be moved into "lfutil.py", because
+        # it is referred only from "lfutil.updatestandinsbymatch"
         def _subdirlfs(self, files, lfiles):
             '''
             Adjust matched file list