gh-123884 Tee of tee was not producing n independent iterators

Doc/library/itertools.rst

@@ -691,25 +691,36 @@ loops that truncate the stream.
 
  def tee(iterable, n=2):
  if n < 0:
- raise ValueError('n must be >= 0')
- iterator = iter(iterable)
- shared_link = [None, None]
- return tuple(_tee(iterator, shared_link) for _ in range(n))
-
- def _tee(iterator, link):
- try:
- while True:
- if link[1] is None:
- link[0] = next(iterator)
- link[1] = [None, None]
- value, link = link
- yield value
- except StopIteration:
- return
-
- Once a :func:`tee` has been created, the original *iterable* should not be
- used anywhere else; otherwise, the *iterable* could get advanced without
- the tee objects being informed.
+ raise ValueError
+ if n == 0:
+ return ()
+ iterator = _tee(iterable)
+ result = [iterator]
+ for _ in range(n - 1):
+ result.append(_tee(iterator))
+ return tuple(result)
+
+ class _tee:
+
+ def __init__(self, iterable):
+ it = iter(iterable)
+ if isinstance(it, _tee):
+ self.iterator = it.iterator
+ self.link = it.link
+ else:
+ self.iterator = it
+ self.link = [None, None]
+
+ def __iter__(self):
+ return self
+
+ def __next__(self):
+ link = self.link
+ if link[1] is None:
+ link[0] = next(self.iterator)
+ link[1] = [None, None]
+ value, self.link = link
+ return value
 
  When the input *iterable* is already a tee iterator object, all
  members of the return tuple are constructed as if they had been

Include/internal/pycore_global_strings.h

@@ -93,7 +93,6 @@ struct _Py_global_strings{
  STRUCT_FOR_ID(__classdictcell__)
  STRUCT_FOR_ID(__complex__)
  STRUCT_FOR_ID(__contains__)
- STRUCT_FOR_ID(__copy__)
  STRUCT_FOR_ID(__ctypes_from_outparam__)
  STRUCT_FOR_ID(__del__)
  STRUCT_FOR_ID(__delattr__)

Lib/test/test_itertools.py

@@ -1249,10 +1249,11 @@ def test_tee(self):
  self.assertEqual(len(result), n)
  self.assertEqual([list(x) for x in result], [list('abc')]*n)
 
- # tee pass-through to copyable iterator
+ # tee objects are independent (see bug gh-123884)
  a, b = tee('abc')
  c, d = tee(a)
- self.assertTrue(a is c)
+ e, f = tee(c)
+ self.assertTrue(len({a, b, c, d, e, f}) == 6)
 
  # test tee_new
  t1, t2 = tee('abc')
@@ -1759,21 +1760,36 @@ def test_tee_recipe(self):
 
  def tee(iterable, n=2):
  if n < 0:
- raise ValueError('n must be >= 0')
- iterator = iter(iterable)
- shared_link = [None, None]
- return tuple(_tee(iterator, shared_link) for _ in range(n))
+ raise ValueError
+ if n == 0:
+ return ()
+ iterator = _tee(iterable)
+ result = [iterator]
+ for _ in range(n - 1):
+ result.append(_tee(iterator))
+ return tuple(result)
+
+ class _tee:
+
+ def __init__(self, iterable):
+ it = iter(iterable)
+ if isinstance(it, _tee):
+ self.iterator = it.iterator
+ self.link = it.link
+ else:
+ self.iterator = it
+ self.link = [None, None]
 
- def _tee(iterator, link):
-try:
- while True:
- if link[1] is None:
-link[0] = next(iterator)
-link[1] = [None, None]
-value, link = link
-yield value
-except StopIteration:
- return
+def __iter__(self):
+ return self
+
+def __next__(self):
+ link = self.link
+if link[1] is None:
+ link[0] = next(self.iterator)
+link[1] = [None, None]
+ value, self.link = link
+ return value
 
  # End tee() recipe #############################################
 
@@ -1819,12 +1835,10 @@ def _tee(iterator, link):
  self.assertRaises(TypeError, tee, [1,2], 'x')
  self.assertRaises(TypeError, tee, [1,2], 3, 'x')
 
- # Tests not applicable to the tee() recipe
- if False:
- # tee object should be instantiable
- a, b = tee('abc')
- c = type(a)('def')
- self.assertEqual(list(c), list('def'))
+ # tee object should be instantiable
+ a, b = tee('abc')
+ c = type(a)('def')
+ self.assertEqual(list(c), list('def'))
 
  # test long-lagged and multi-way split
  a, b, c = tee(range(2000), 3)
@@ -1845,21 +1859,19 @@ def _tee(iterator, link):
  self.assertEqual(len(result), n)
  self.assertEqual([list(x) for x in result], [list('abc')]*n)
 
+ # tee objects are independent (see bug gh-123884)
+ a, b = tee('abc')
+ c, d = tee(a)
+ e, f = tee(c)
+ self.assertTrue(len({a, b, c, d, e, f}) == 6)
 
- # Tests not applicable to the tee() recipe
- if False:
- # tee pass-through to copyable iterator
- a, b = tee('abc')
- c, d = tee(a)
- self.assertTrue(a is c)
-
- # test tee_new
- t1, t2 = tee('abc')
- tnew = type(t1)
- self.assertRaises(TypeError, tnew)
- self.assertRaises(TypeError, tnew, 10)
- t3 = tnew(t1)
- self.assertTrue(list(t1) == list(t2) == list(t3) == list('abc'))
+ # test tee_new
+ t1, t2 = tee('abc')
+ tnew = type(t1)
+ self.assertRaises(TypeError, tnew)
+ self.assertRaises(TypeError, tnew, 10)
+ t3 = tnew(t1)
+ self.assertTrue(list(t1) == list(t2) == list(t3) == list('abc'))
 
  # test that tee objects are weak referencable
  a, b = tee(range(10))

Misc/NEWS.d/next/Library/2024-09-24-22-38-51.gh-issue-123884.iEPTK4.rst

@@ -0,0 +1,4 @@
+Fixed bug in itertools.tee() handling of other tee inputs (a tee in a tee).
+The output now has the promised *n* independent new iterators. Formerly,
+the first iterator was identical (not independent) to the input iterator.
+This would sometimes give surprising results.

Modules/itertoolsmodule.c

@@ -1036,7 +1036,7 @@ itertools_tee_impl(PyObject *module, PyObject *iterable, Py_ssize_t n)
 /*[clinic end generated code: output=1c64519cd859c2f0 input=c99a1472c425d66d]*/
 {
  Py_ssize_t i;
- PyObject *it, *copyable, *copyfunc, *result;
+ PyObject *it, *to, *result;
 
  if (n < 0){
  PyErr_SetString(PyExc_ValueError, "n must be >= 0");
@@ -1053,41 +1053,23 @@ itertools_tee_impl(PyObject *module, PyObject *iterable, Py_ssize_t n)
  return NULL;
  }
 
- if (PyObject_GetOptionalAttr(it, &_Py_ID(__copy__), &copyfunc) < 0){
- Py_DECREF(it);
+ itertools_state *state = get_module_state(module);
+ to = tee_fromiterable(state, it);
+ Py_DECREF(it);
+ if (to == NULL){
  Py_DECREF(result);
  return NULL;
  }
- if (copyfunc != NULL){
- copyable = it;
- }
- else{
- itertools_state *state = get_module_state(module);
- copyable = tee_fromiterable(state, it);
- Py_DECREF(it);
- if (copyable == NULL){
- Py_DECREF(result);
- return NULL;
- }
- copyfunc = PyObject_GetAttr(copyable, &_Py_ID(__copy__));
- if (copyfunc == NULL){
- Py_DECREF(copyable);
- Py_DECREF(result);
- return NULL;
- }
- }
 
- PyTuple_SET_ITEM(result, 0, copyable);
+ PyTuple_SET_ITEM(result, 0, to);
  for (i = 1; i < n; i++){
- copyable = _PyObject_CallNoArgs(copyfunc);
- if (copyable == NULL){
- Py_DECREF(copyfunc);
+ to = tee_copy((teeobject *)to, NULL);
+ if (to == NULL){
  Py_DECREF(result);
  return NULL;
  }
- PyTuple_SET_ITEM(result, i, copyable);
+ PyTuple_SET_ITEM(result, i, to);
  }
- Py_DECREF(copyfunc);
  return result;
 }