# HG changeset patch
# User Yuya Nishihara <yuya@tcha.org>
# Date 1432446581 -32400
# Node ID 9d6cc87bd507a8804c77df6ec81c56e7fd4262c7
# Parent  28800ab40395fe1f7437a6da9aeed6f3781f2a0e
revset: make internal _list() expression remove duplicated revisions

This allows us to optimize chained 'or' operations to _list() expression.

Unlike _intlist() or _hexlist(), it's difficult to remove duplicates by the
caller of _list() because different symbols can point to the same revision.
If the caller knows all symbols are unique, that probably means revisions or
nodes are known, therefore, _intlist() or _hexlist() should be used instead.
So, it makes sense to check duplicates by _list() function.

'%ls' is no longer used in core, this won't cause performance regression.

diff -r 28800ab40395 -r 9d6cc87bd507 mercurial/revset.py
--- a/mercurial/revset.py	Sun May 24 14:34:12 2015 +0900
+++ b/mercurial/revset.py	Sun May 24 14:49:41 2015 +0900
@@ -1920,9 +1920,18 @@
     s = getstring(x, "internal error")
     if not s:
         return baseset()
-    ls = [repo[r].rev() for r in s.split('\0')]
-    s = subset
-    return baseset([r for r in ls if r in s])
+    # remove duplicates here. it's difficult for caller to deduplicate sets
+    # because different symbols can point to the same rev.
+    ls = []
+    seen = set()
+    for t in s.split('\0'):
+        r = repo[t].rev()
+        if r in seen:
+            continue
+        if r in subset:
+            ls.append(r)
+        seen.add(r)
+    return baseset(ls)
 
 # for internal use
 def _intlist(repo, subset, x):