Merge pull request #10621 from ahaldane/fix_arrayprint_recursive_closure

eric-wieser · web-flow · commit 71555c48be7f · 2018-02-19T00:17:03.000-08:00
BUG: deallocate recursive closure in arrayprint.py
diff --git a/numpy/core/arrayprint.py b/numpy/core/arrayprint.py
@@ -772,7 +772,8 @@ def recurser(index, hanging_indent, curr_width):
                     s += hanging_indent + summary_insert + line_sep
 
             for i in range(trailing_items, 1, -1):
-                nested = recurser(index + (-i,), next_hanging_indent, next_width)
+                nested = recurser(index + (-i,), next_hanging_indent,
+                                  next_width)
                 s += hanging_indent + nested + line_sep
 
             nested = recurser(index + (-1,), next_hanging_indent, next_width)
@@ -782,12 +783,16 @@ def recurser(index, hanging_indent, curr_width):
         s = '[' + s[len(hanging_indent):] + ']'
         return s
 
-    # invoke the recursive part with an initial index and prefix
-    return recurser(
-        index=(),
-        hanging_indent=next_line_prefix,
-        curr_width=line_width)
-
+    try:
+        # invoke the recursive part with an initial index and prefix
+        return recurser(index=(),
+                        hanging_indent=next_line_prefix,
+                        curr_width=line_width)
+    finally:
+        # recursive closures have a cyclic reference to themselves, which
+        # requires gc to collect (gh-10620). To avoid this problem, for
+        # performance and PyPy friendliness, we break the cycle:
+        recurser = None
 
 def _none_or_positive_arg(x, name):
     if x is None:
diff --git a/numpy/core/shape_base.py b/numpy/core/shape_base.py
@@ -446,7 +446,13 @@ def block_recursion(arrays, depth=0):
             # type(arrays) is not list
             return atleast_nd(arrays, result_ndim)
 
-    return block_recursion(arrays)
+    try:
+        return block_recursion(arrays)
+    finally:
+        # recursive closures have a cyclic reference to themselves, which
+        # requires gc to collect (gh-10620). To avoid this problem, for
+        # performance and PyPy friendliness, we break the cycle:
+        block_recursion = None
 
 
 def block(arrays):
diff --git a/numpy/core/tests/test_arrayprint.py b/numpy/core/tests/test_arrayprint.py
@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import division, absolute_import, print_function
 
-import sys
+import sys, gc
 
 import numpy as np
 from numpy.testing import (
@@ -355,6 +355,18 @@ def test_wide_element(self):
             "[ 'xxxxx']"
         )
 
+    def test_refcount(self):
+        # make sure we do not hold references to the array due to a recursive
+        # closure (gh-10620)
+        gc.disable()
+        a = np.arange(2)
+        r1 = sys.getrefcount(a)
+        np.array2string(a)
+        np.array2string(a)
+        r2 = sys.getrefcount(a)
+        gc.collect()
+        gc.enable()
+        assert_(r1 == r2)
 
 class TestPrintOptions(object):
     """Test getting and setting global print options."""
diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py
@@ -1109,6 +1109,11 @@ def tobytes_first(x, conv):
     finally:
         if fown:
             fh.close()
+        # recursive closures have a cyclic reference to themselves, which
+        # requires gc to collect (gh-10620). To avoid this problem, for
+        # performance and PyPy friendliness, we break the cycle:
+        flatten_dtype_internal = None
+        pack_items = None
 
     if X is None:
         X = np.array([], dtype)
