[pypy-commit] pypy default: A bit experimental - try to preallocate the size of unicode join and remove

[fijal]

Author: Maciej Fijalkowski <fijall at gmail.com>
Branch: 
Changeset: r51364:f6b8525d8a10
Date: 2012-01-16 22:14 +0200
http://bitbucket.org/pypy/pypy/changeset/f6b8525d8a10/

Log:	A bit experimental - try to preallocate the size of unicode join and
	remove a pointless performance hack (the general optimization should
	work already)

diff --git a/pypy/objspace/std/unicodeobject.py b/pypy/objspace/std/unicodeobject.py
--- a/pypy/objspace/std/unicodeobject.py
+++ b/pypy/objspace/std/unicodeobject.py
@@ -201,7 +201,7 @@
     return space.newbool(container.find(item) != -1)
 
 def unicode_join__Unicode_ANY(space, w_self, w_list):
-    list_w = space.unpackiterable(w_list)
+    list_w = space.listview(w_list)
     size = len(list_w)
 
     if size == 0:
@@ -216,22 +216,21 @@
 
 def _unicode_join_many_items(space, w_self, list_w, size):
     self = w_self._value
-    sb = UnicodeBuilder()
+    prealloc_size = 0
+    for i in range(size):
+        prealloc_size += len(space.unicode_w(list_w[i]))
+    sb = UnicodeBuilder(prealloc_size)
     for i in range(size):
         if self and i != 0:
             sb.append(self)
         w_s = list_w[i]
-        if isinstance(w_s, W_UnicodeObject):
-            # shortcut for performance
-            sb.append(w_s._value)
-        else:
-            try:
-                sb.append(space.unicode_w(w_s))
-            except OperationError, e:
-                if not e.match(space, space.w_TypeError):
-                    raise
-                raise operationerrfmt(space.w_TypeError,
-                    "sequence item %d: expected string or Unicode", i)
+        try:
+            sb.append(space.unicode_w(w_s))
+        except OperationError, e:
+            if not e.match(space, space.w_TypeError):
+                raise
+            raise operationerrfmt(space.w_TypeError,
+                        "sequence item %d: expected string or Unicode", i)
     return space.wrap(sb.build())
 
 def hash__Unicode(space, w_uni):