diff mercurial/revlog.py @ 45788:a5206e71c536

revlog: extend addgroup() with callback for duplicates

The addgroup() interface currently doesn't allow the caller to keep
track of duplicated nodes except by looking at the returned node list.
Add an optional second callback for this purpose and change the return
type to a boolean. This allows follow-up changes to use more efficient
storage for the node list in places that are memory-sensitive.

Differential Revision: https://phab.mercurial-scm.org/D9231

--- a/mercurial/revlog.py	Wed Oct 07 14:26:47 2020 +0530
+++ b/mercurial/revlog.py	Sun Oct 18 22:18:02 2020 +0200
@@ -2368,7 +2368,14 @@
             self._enforceinlinesize(transaction, ifh)
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
-    def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
+    def addgroup(
+        self,
+        deltas,
+        linkmapper,
+        transaction,
+        addrevisioncb=None,
+        duplicaterevisioncb=None,
+    ):
         """
         add a delta group
 
@@ -2383,8 +2390,6 @@
         if self._writinghandles:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
-        nodes = []
-
         r = len(self)
         end = 0
         if r:
@@ -2405,6 +2410,7 @@
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
+        empty = True
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
@@ -2414,11 +2420,12 @@
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
-                nodes.append(node)
-
                 if self.index.has_node(node):
+                    # this can happen if two branches make the same change
                     self._nodeduplicatecallback(transaction, node)
-                    # this can happen if two branches make the same change
+                    if duplicaterevisioncb:
+                        duplicaterevisioncb(self, node)
+                    empty = False
                     continue
 
                 for p in (p1, p2):
@@ -2472,6 +2479,7 @@
 
                 if addrevisioncb:
                     addrevisioncb(self, node)
+                empty = False
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
@@ -2486,8 +2494,7 @@
             if dfh:
                 dfh.close()
             ifh.close()
-
-        return nodes
+        return not empty
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""