scmutil: allowing different files to be prefetched per revision

The old API takes a list of revision separate from the file matcher, and thus
provides no way to fetch different sets of files from each revision. In
preparation for adding one such usage, I'm changing the API to take a list of
(revision, file matcher) tuples instead.

Differential Revision: https://phab.mercurial-scm.org/D8721

hgext/lfs/wrapper.py

@@ -337,7 +337,7 b' def vfsinit(orig, self, othervfs):'
             setattr(self, name, getattr(othervfs, name))
 
 
-def _prefetchfiles(repo, revs, match):
+def _prefetchfiles(repo, revmatches):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     if not util.safehasattr(repo.svfs, b'lfslocalblobstore'):
@@ -347,7 +347,7 b' def _prefetchfiles(repo, revs, match):'
     oids = set()
     localstore = repo.svfs.lfslocalblobstore
 
-    for rev in revs:
+    for rev, match in revmatches:
         ctx = repo[rev]
         for f in ctx.walk(match):
             p = pointerfromctx(ctx, f)

hgext/remotefilelog/__init__.py

@@ -148,7 +148,7 b' from mercurial import ('
     extensions,
     hg,
     localrepo,
-    match,
+    match as matchmod,
     merge,
     node as nodemod,
     patch,
@@ -824,12 +824,12 b' def filelogrevset(orig, repo, subset, x)'
 
     # i18n: "filelog" is a keyword
     pat = revset.getstring(x, _(b"filelog requires a pattern"))
-    m = match.match(
+    m = matchmod.match(
         repo.root, repo.getcwd(), [pat], default=b'relpath', ctx=repo[None]
     )
     s = set()
 
-    if not match.patkind(pat):
+    if not matchmod.patkind(pat):
         # slow
         for r in subset:
             ctx = repo[r]
@@ -1118,10 +1118,10 b' def exchangepull(orig, repo, remote, *ar'
     return orig(repo, remote, *args, **kwargs)
 
 
-def _fileprefetchhook(repo, revs, match):
+def _fileprefetchhook(repo, revmatches):
     if isenabled(repo):
         allfiles = []
-        for rev in revs:
+        for rev, match in revmatches:
             if rev == nodemod.wdirrev or rev is None:
                 continue
             ctx = repo[rev]

mercurial/archival.py

@@ -364,7 +364,7 b' def archive('
     if total:
         files.sort()
         scmutil.prefetchfiles(
-            repo, [ctx.rev()], scmutil.matchfiles(repo, files)
+            repo, [(ctx.rev(), scmutil.matchfiles(repo, files))]
         )
         progress = repo.ui.makeprogress(
             _(b'archiving'), unit=_(b'files'), total=total

mercurial/cmdutil.py

@@ -2138,7 +2138,9 b' def _prefetchchangedfiles(repo, revs, ma'
         for file in repo[rev].files():
             if not match or match(file):
                 allfiles.add(file)
-    scmutil.prefetchfiles(repo, revs, scmutil.matchfiles(repo, allfiles))
+    match = scmutil.matchfiles(repo, allfiles)
+    revmatches = [(rev, match) for rev in revs]
+    scmutil.prefetchfiles(repo, revmatches)
 
 
 def export(
@@ -2997,14 +2999,14 b' def cat(ui, repo, ctx, matcher, basefm, '
         try:
             if mfnode and mfl[mfnode].find(file)[0]:
                 if _catfmtneedsdata(basefm):
-                    scmutil.prefetchfiles(repo, [ctx.rev()], matcher)
+                    scmutil.prefetchfiles(repo, [(ctx.rev(), matcher)])
                 write(file)
                 return 0
         except KeyError:
             pass
 
     if _catfmtneedsdata(basefm):
-        scmutil.prefetchfiles(repo, [ctx.rev()], matcher)
+        scmutil.prefetchfiles(repo, [(ctx.rev(), matcher)])
 
     for abs in ctx.walk(matcher):
         write(abs)
@@ -3769,11 +3771,11 b' def revert(ui, repo, ctx, parents, *pats'
             needdata = (b'revert', b'add', b'undelete')
             oplist = [actions[name][0] for name in needdata]
             prefetch = scmutil.prefetchfiles
-            matchfiles = scmutil.matchfiles
+            matchfiles = scmutil.matchfiles(
+                repo, [f for sublist in oplist for f in sublist]
+            )
             prefetch(
-                repo,
-                [ctx.rev()],
-                matchfiles(repo, [f for sublist in oplist for f in sublist]),
+                repo, [(ctx.rev(), matchfiles)],
             )
             match = scmutil.match(repo[None], pats)
             _performrevert(

mercurial/context.py

@@ -2540,8 +2540,12 b' class overlayworkingctx(committablectx):'
         # using things like remotefilelog.
         scmutil.prefetchfiles(
             self.repo(),
-            [self.p1().rev()],
-            scmutil.matchfiles(self.repo(), self._cache.keys()),
+            [
+                (
+                    self.p1().rev(),
+                    scmutil.matchfiles(self.repo(), self._cache.keys()),
+                )
+            ],
         )
 
         for path in self._cache.keys():

mercurial/merge.py

@@ -1121,8 +1121,14 b' def _prefetchfiles(repo, ctx, actions):'
     matchfiles = scmutil.matchfiles
     prefetch(
         repo,
-        [ctx.rev()],
-        matchfiles(repo, [f for sublist in oplist for f, args, msg in sublist]),
+        [
+            (
+                ctx.rev(),
+                matchfiles(
+                    repo, [f for sublist in oplist for f, args, msg in sublist]
+                ),
+            )
+        ],
     )
 
 

mercurial/patch.py

@@ -2666,7 +2666,11 b' def diffhunks('
     prefetchmatch = scmutil.matchfiles(
         repo, list(modifiedset | addedset | removedset)
     )
-    scmutil.prefetchfiles(repo, [ctx1.rev(), ctx2.rev()], prefetchmatch)
+    revmatches = [
+        (ctx1.rev(), prefetchmatch),
+        (ctx2.rev(), prefetchmatch),
+    ]
+    scmutil.prefetchfiles(repo, revmatches)
 
     def difffn(opts, losedata):
         return trydiff(

mercurial/scmutil.py

@@ -1880,18 +1880,29 b' class simplekeyvaluefile(object):'
 ]
 
 
-def prefetchfiles(repo, revs, match):
+def prefetchfiles(repo, revmatches):
     """Invokes the registered file prefetch functions, allowing extensions to
     ensure the corresponding files are available locally, before the command
-    uses them."""
-    if match:
-        # The command itself will complain about files that don't exist, so
-        # don't duplicate the message.
-        match = matchmod.badmatch(match, lambda fn, msg: None)
-    else:
-        match = matchall(repo)
+    uses them.
+
+    Args:
+      revmatches: a list of (revision, match) tuples to indicate the files to
+      fetch at each revision. If any of the match elements is None, it matches
+      all files.
+    """
 
-    fileprefetchhooks(repo, revs, match)
+    def _matcher(m):
+        if m:
+            assert isinstance(m, matchmod.basematcher)
+            # The command itself will complain about files that don't exist, so
+            # don't duplicate the message.
+            return matchmod.badmatch(m, lambda fn, msg: None)
+        else:
+            return matchall(repo)
+
+    revbadmatches = [(rev, _matcher(match)) for (rev, match) in revmatches]
+
+    fileprefetchhooks(repo, revbadmatches)
 
 
 # a list of (repo, revs, match) prefetch functions

mercurial/subrepo.py

@@ -639,7 +639,7 b' class hgsubrepo(abstractsubrepo):'
         rev = self._state[1]
         ctx = self._repo[rev]
         scmutil.prefetchfiles(
-            self._repo, [ctx.rev()], scmutil.matchfiles(self._repo, files)
+            self._repo, [(ctx.rev(), scmutil.matchfiles(self._repo, files))]
         )
         total = abstractsubrepo.archive(self, archiver, prefix, match)
         for subpath in ctx.substate: