changeset 44286:bbecb6d80aa7

manifest: rewrite filesnotin to not make superfluous manifest copies This also skips using diff() when all we care about is the filenames. I'm expecting the built in set logic to be plenty fast. For really large manifests with a matcher in play this should copy substantially less data around. Differential Revision: https://phab.mercurial-scm.org/D8082
author Augie Fackler <augie@google.com>
date Wed, 05 Feb 2020 16:58:50 -0500
parents 63d84c18247a
children e76d98546bd2
files mercurial/manifest.py
diffstat 1 files changed, 6 insertions(+), 11 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/manifest.py	Sat Feb 08 03:13:45 2020 +0530
+++ b/mercurial/manifest.py	Wed Feb 05 16:58:50 2020 -0500
@@ -23,6 +23,7 @@
 from . import (
     encoding,
     error,
+    match as matchmod,
     mdiff,
     pathutil,
     policy,
@@ -482,17 +483,11 @@
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
-        if match:
-            m1 = self.matches(match)
-            m2 = m2.matches(match)
-            return m1.filesnotin(m2)
-        diff = self.diff(m2)
-        files = set(
-            filepath
-            for filepath, hashflags in pycompat.iteritems(diff)
-            if hashflags[1][0] is None
-        )
-        return files
+        if match is not None:
+            match = matchmod.badmatch(match, lambda path, msg: None)
+            sm2 = set(m2.walk(match))
+            return {f for f in self.walk(match) if f not in sm2}
+        return {f for f in self if f not in m2}
 
     @propertycache
     def _dirs(self):