[3.13] Tee of tee was not producing n independent iterators (gh-123884) (gh-125081)

diff --git a/Doc/library/itertools.rst b/Doc/library/itertools.rst
index ceaab2f3e724541a1737d312f54ed6df52191760..8eb8d07b3fb0642c602aadcb93984ec5bf05629b 100644 (file)
--- a/Doc/library/itertools.rst
+++ b/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

diff --git a/Lib/test/test_itertools.py b/Lib/test/test_itertools.py
index 2c8752d215dc696e4d443e7b5929bcd88b944d95..1e58354b43c14f6c5d9f9336b7a9bfd1ff211ff0 100644 (file)
--- a/Lib/test/test_itertools.py
+++ b/Lib/test/test_itertools.py
@@ -1642,10 +1642,11 @@ class TestBasicOps(unittest.TestCase):
             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')
@@ -2072,21 +2073,36 @@ class TestPurePythonRoughEquivalents(unittest.TestCase):
 
         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 #############################################
 
@@ -2132,12 +2148,10 @@ class TestPurePythonRoughEquivalents(unittest.TestCase):
         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)
@@ -2158,21 +2172,19 @@ class TestPurePythonRoughEquivalents(unittest.TestCase):
             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))

diff --git a/Misc/NEWS.d/next/Library/2024-09-24-22-38-51.gh-issue-123884.iEPTK4.rst b/Misc/NEWS.d/next/Library/2024-09-24-22-38-51.gh-issue-123884.iEPTK4.rst
new file mode 100644 (file)
index 0000000..55f1d4b
--- /dev/null
+++ b/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.

diff --git a/Modules/itertoolsmodule.c b/Modules/itertoolsmodule.c
index 0d6ff20489aa2c18905b3186ed3f762171174f9f..2d4587c1a91bc0e0cf47af1c8b1926261135cf9d 100644 (file)
--- a/Modules/itertoolsmodule.c
+++ b/Modules/itertoolsmodule.c
@@ -1173,7 +1173,7 @@ 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");
@@ -1190,41 +1190,24 @@ 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);
+    (void)&_Py_ID(__copy__); // Retain a reference to __copy__
+    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;
 }