scmutil: allowing different files to be prefetched per revision
authorRodrigo Damazio Bovendorp <rdamazio@google.com>
Thu, 09 Jul 2020 18:48:55 -0700
changeset 45072 a56ba57c837d
parent 45071 196ba4d4eb86
child 45073 54009f8c3e25
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
hgext/remotefilelog/__init__.py
mercurial/archival.py
mercurial/cmdutil.py
mercurial/context.py
mercurial/merge.py
mercurial/patch.py
mercurial/scmutil.py
mercurial/subrepo.py
--- a/hgext/lfs/wrapper.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/hgext/lfs/wrapper.py	Thu Jul 09 18:48:55 2020 -0700
@@ -337,7 +337,7 @@
             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 @@
     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)
--- a/hgext/remotefilelog/__init__.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/hgext/remotefilelog/__init__.py	Thu Jul 09 18:48:55 2020 -0700
@@ -148,7 +148,7 @@
     extensions,
     hg,
     localrepo,
-    match,
+    match as matchmod,
     merge,
     node as nodemod,
     patch,
@@ -824,12 +824,12 @@
 
     # 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 @@
     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]
--- a/mercurial/archival.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/archival.py	Thu Jul 09 18:48:55 2020 -0700
@@ -364,7 +364,7 @@
     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
--- a/mercurial/cmdutil.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/cmdutil.py	Thu Jul 09 18:48:55 2020 -0700
@@ -2138,7 +2138,9 @@
         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 @@
         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 @@
             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(
--- a/mercurial/context.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/context.py	Thu Jul 09 18:48:55 2020 -0700
@@ -2540,8 +2540,12 @@
         # 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():
--- a/mercurial/merge.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/merge.py	Thu Jul 09 18:48:55 2020 -0700
@@ -1121,8 +1121,14 @@
     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]
+                ),
+            )
+        ],
     )
 
 
--- a/mercurial/patch.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/patch.py	Thu Jul 09 18:48:55 2020 -0700
@@ -2666,7 +2666,11 @@
     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(
--- a/mercurial/scmutil.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/scmutil.py	Thu Jul 09 18:48:55 2020 -0700
@@ -1880,18 +1880,29 @@
 ]
 
 
-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
--- a/mercurial/subrepo.py	Sat Jul 11 00:31:21 2020 +0530
+++ b/mercurial/subrepo.py	Thu Jul 09 18:48:55 2020 -0700
@@ -639,7 +639,7 @@
         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: