[Request] [+- ] D8722: fix: obtain base paths before starting workers

[rdamazio (Rodrigo Damazio Bovendorp)]

rdamazio created this revision.
Herald added a reviewer: hg-reviewers.
Herald added a subscriber: mercurial-patches.

REVISION SUMMARY
  This moves calculation of base paths to before work is dispatched.
  While this does mean that copy tracing will be serialized instead of
  parallel, it is necessary to be able to prefetch the base contents
  in a batch, which will likely be more efficient.

REPOSITORY
  rHG Mercurial

BRANCH
  default

REVISION DETAIL
  https://phab.mercurial-scm.org/D8722

AFFECTED FILES
  hgext/fix.py

CHANGE DETAILS

diff --git a/hgext/fix.py b/hgext/fix.py
--- a/hgext/fix.py
+++ b/hgext/fix.py
@@ -268,6 +268,7 @@
         workqueue, numitems = getworkqueue(
             ui, repo, pats, opts, revstofix, basectxs
         )
+        basepaths = getbasepaths(repo, opts, workqueue, basectxs)
         fixers = getfixers(ui)
 
         # There are no data dependencies between the workers fixing each file
@@ -277,7 +278,7 @@
                 ctx = repo[rev]
                 olddata = ctx[path].data()
                 metadata, newdata = fixfile(
-                    ui, repo, opts, fixers, ctx, path, basectxs[rev]
+                    ui, repo, opts, fixers, ctx, path, basepaths, basectxs[rev]
                 )
                 # Don't waste memory/time passing unchanged content back, but
                 # produce one result per item either way.
@@ -473,7 +474,8 @@
     return files
 
 
-def lineranges(opts, path, basectxs, fixctx, content2):
+
+def lineranges(opts, path, basepaths, basectxs, fixctx, content2):
     """Returns the set of line ranges that should be fixed in a file
 
     Of the form [(10, 20), (30, 40)].
@@ -492,7 +494,8 @@
 
     rangeslist = []
     for basectx in basectxs:
-        basepath = copies.pathcopies(basectx, fixctx).get(path, path)
+        basepath = basepaths.get((basectx.rev(), fixctx.rev(), path), path)
+
         if basepath in basectx:
             content1 = basectx[basepath].data()
         else:
@@ -501,6 +504,21 @@
     return unionranges(rangeslist)
 
 
+def getbasepaths(repo, opts, workqueue, basectxs):
+    if opts.get(b'whole'):
+        # Base paths will never be fetched for line range determination.
+        return {}
+
+    basepaths = {}
+    for rev, path in workqueue:
+        fixctx = repo[rev]
+        for basectx in basectxs[rev]:
+            basepath = copies.pathcopies(basectx, fixctx).get(path, path)
+            if basepath in basectx:
+                basepaths[(basectx.rev(), fixctx.rev(), path)] = basepath
+    return basepaths
+
+
 def unionranges(rangeslist):
     """Return the union of some closed intervals
 
@@ -613,7 +631,7 @@
     return basectxs
 
 
-def fixfile(ui, repo, opts, fixers, fixctx, path, basectxs):
+def fixfile(ui, repo, opts, fixers, fixctx, path, basepaths, basectxs):
     """Run any configured fixers that should affect the file in this context
 
     Returns the file content that results from applying the fixers in some order
@@ -629,7 +647,8 @@
     newdata = fixctx[path].data()
     for fixername, fixer in pycompat.iteritems(fixers):
         if fixer.affects(opts, fixctx, path):
-            ranges = lineranges(opts, path, basectxs, fixctx, newdata)
+            ranges = lineranges(
+                opts, path, basepaths, basectxs, fixctx, newdata)
             command = fixer.command(ui, path, ranges)
             if command is None:
                 continue



To: rdamazio, #hg-reviewers
Cc: mercurial-patches, mercurial-devel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mercurial-scm.org/pipermail/mercurial-patches/attachments/20200710/e95441eb/attachment-0001.html>