[PATCH 1 of 2] copies: add matcher parameter to copy logic

Martin von Zweigbergk martinvonz at google.com
Thu Apr 16 16:13:18 CDT 2015


On Thu, Apr 16, 2015 at 12:05 PM Durham Goode <durham at fb.com> wrote:

> # HG changeset patch
> # User Durham Goode <durham at fb.com>
> # Date 1429208970 25200
> #      Thu Apr 16 11:29:30 2015 -0700
> # Node ID 0270a44b46aabbaf794dbd62b08b622313fe1b85
> # Parent  c560d8c687916cb70a6d54c2c9ddcb5c9e457be2
> copies: add matcher parameter to copy logic
>
> This allows passing a matcher down the pathcopies() stack to
> _forwardcopies().
> This will let us add logic in a later patch to avoid tracing copies when
> not
> necessary (like when doing hg diff -r 1 -r 2 foo.txt).
>
> diff --git a/hgext/largefiles/overrides.py b/hgext/largefiles/overrides.py
> --- a/hgext/largefiles/overrides.py
> +++ b/hgext/largefiles/overrides.py
> @@ -547,8 +547,8 @@ def overridefilemerge(origfn, repo, myno
>          repo.wwrite(fcd.path(), fco.data(), fco.flags())
>      return 0
>
> -def copiespathcopies(orig, ctx1, ctx2):
> -    copies = orig(ctx1, ctx2)
> +def copiespathcopies(orig, ctx1, ctx2, match=None):
> +    copies = orig(ctx1, ctx2, match=match)
>      updated = {}
>
>      for k, v in copies.iteritems():
> diff --git a/mercurial/copies.py b/mercurial/copies.py
> --- a/mercurial/copies.py
> +++ b/mercurial/copies.py
> @@ -140,14 +140,16 @@ def _dirstatecopies(d):
>              del c[k]
>      return c
>
> -def _computeforwardmissing(a, b):
> +def _computeforwardmissing(a, b, match=None):
>      """Computes which files are in b but not a.
>      This is its own function so extensions can easily wrap this call to
> see what
>      files _forwardcopies is about to process.
>      """
> -    return b.manifest().filesnotin(a.manifest())
> +    for f in b.manifest().filesnotin(a.manifest()):
> +        if not match or match(f):
> +            yield f
>

I'd rather have this written as:
ma = a.manifest()
mb = b.manifest()
if match:
  ma = ma.matches(m)
  mb = mb.matches(m)
return mb.filesnotin(ma)

That avoids loading all modified subtrees when using tree manifests.
Hopefully it's not noticeably slower on flat manifests.

Also, you could do those steps in the caller. I don't remember if you need
the contexts for remotefilelog.

-def _forwardcopies(a, b):
+def _forwardcopies(a, b, match=None):
     '''find {dst at b: src at a} copy mapping where a is an ancestor of b'''

     # check for working copy
@@ -170,7 +172,7 @@ def _forwardcopies(a, b):
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
-    missing = _computeforwardmissing(a, b)
+    missing = _computeforwardmissing(a, b, match=match)
     ancestrycontext = a._repo.changelog.ancestors([b.rev()],
inclusive=True)
     for f in missing:
         fctx = b[f]
@@ -198,16 +200,17 @@ def _backwardrenames(a, b):
         r[v] = k
     return r

-def pathcopies(x, y):
+def pathcopies(x, y, match=None):
     '''find {dst at y: src at x} copy mapping for directed compare'''
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
-        return _forwardcopies(x, y)
+        return _forwardcopies(x, y, match=match)
     if a == y:
         return _backwardrenames(x, y)
-    return _chain(x, y, _backwardrenames(x, a), _forwardcopies(a, y))
+    return _chain(x, y, _backwardrenames(x, a),
+                  _forwardcopies(a, y, match=match))

 def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2):
     """Computes, based on addedinm1 and addedinm2, the files exclusive to
c1
_______________________________________________
Mercurial-devel mailing list
Mercurial-devel at selenic.com
http://selenic.com/mailman/listinfo/mercurial-devel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://selenic.com/pipermail/mercurial-devel/attachments/20150416/69a898bc/attachment.html>


More information about the Mercurial-devel mailing list