Issue #12911: Fix memory consumption when calculating the repr() of huge tuples or lists.

This introduces a small private API for this common pattern.
The issue has been discovered thanks to Martin's huge-mem buildbot.

3 files changed, 185 insertions, 85 deletions

diff --git a/Objects/accu.c b/Objects/accu.c
new file mode 100644
index 0000000..88e8f08
--- /dev/null
+++ b/Objects/accu.c
@@ -0,0 +1,114 @@
+/* Accumulator struct implementation */
+
+#include "Python.h"
+
+static PyObject *
+join_list_unicode(PyObject *lst)
+{
+    /* return ''.join(lst) */
+    PyObject *sep, *ret;
+    sep = PyUnicode_FromStringAndSize("", 0);
+    ret = PyUnicode_Join(sep, lst);
+    Py_DECREF(sep);
+    return ret;
+}
+
+int
+_PyAccu_Init(_PyAccu *acc)
+{
+    /* Lazily allocated */
+    acc->large = NULL;
+    acc->small = PyList_New(0);
+    if (acc->small == NULL)
+        return -1;
+    return 0;
+}
+
+static int
+flush_accumulator(_PyAccu *acc)
+{
+    Py_ssize_t nsmall = PyList_GET_SIZE(acc->small);
+    if (nsmall) {
+        int ret;
+        PyObject *joined;
+        if (acc->large == NULL) {
+            acc->large = PyList_New(0);
+            if (acc->large == NULL)
+                return -1;
+        }
+        joined = join_list_unicode(acc->small);
+        if (joined == NULL)
+            return -1;
+        if (PyList_SetSlice(acc->small, 0, nsmall, NULL)) {
+            Py_DECREF(joined);
+            return -1;
+        }
+        ret = PyList_Append(acc->large, joined);
+        Py_DECREF(joined);
+        return ret;
+    }
+    return 0;
+}
+
+int
+_PyAccu_Accumulate(_PyAccu *acc, PyObject *unicode)
+{
+    Py_ssize_t nsmall;
+    assert(PyUnicode_Check(unicode));
+
+    if (PyList_Append(acc->small, unicode))
+        return -1;
+    nsmall = PyList_GET_SIZE(acc->small);
+    /* Each item in a list of unicode objects has an overhead (in 64-bit
+     * builds) of:
+     *   - 8 bytes for the list slot
+     *   - 56 bytes for the header of the unicode object
+     * that is, 64 bytes.  100000 such objects waste more than 6MB
+     * compared to a single concatenated string.
+     */
+    if (nsmall < 100000)
+        return 0;
+    return flush_accumulator(acc);
+}
+
+PyObject *
+_PyAccu_FinishAsList(_PyAccu *acc)
+{
+    int ret;
+    PyObject *res;
+
+    ret = flush_accumulator(acc);
+    Py_CLEAR(acc->small);
+    if (ret) {
+        Py_CLEAR(acc->large);
+        return NULL;
+    }
+    res = acc->large;
+    acc->large = NULL;
+    return res;
+}
+
+PyObject *
+_PyAccu_Finish(_PyAccu *acc)
+{
+    PyObject *list, *res;
+    if (acc->large == NULL) {
+        list = acc->small;
+        acc->small = NULL;
+    }
+    else {
+        list = _PyAccu_FinishAsList(acc);
+        if (!list)
+            return NULL;
+    }
+    res = join_list_unicode(list);
+    Py_DECREF(list);
+    return res;
+}
+
+void
+_PyAccu_Destroy(_PyAccu *acc)
+{
+    Py_CLEAR(acc->small);
+    Py_CLEAR(acc->large);
+}
diff --git a/Objects/listobject.c b/Objects/listobject.c
index 1c516e9..28d94e7 100644
--- a/Objects/listobject.c
+++ b/Objects/listobject.c
@@ -321,70 +321,59 @@ static PyObject *
 list_repr(PyListObject *v)
 {
     Py_ssize_t i;
-    PyObject *s, *temp;
-    PyObject *pieces = NULL, *result = NULL;
+    PyObject *s = NULL;
+    _PyAccu acc;
+    static PyObject *sep = NULL;
+
+    if (Py_SIZE(v) == 0) {
+        return PyUnicode_FromString("[]");
+    }
+
+    if (sep == NULL) {
+        sep = PyUnicode_FromString(", ");
+        if (sep == NULL)
+            return NULL;
+    }
 
     i = Py_ReprEnter((PyObject*)v);
     if (i != 0) {
         return i > 0 ? PyUnicode_FromString("[...]") : NULL;
     }
 
-    if (Py_SIZE(v) == 0) {
-        result = PyUnicode_FromString("[]");
-        goto Done;
-    }
+    if (_PyAccu_Init(&acc))
+        goto error;
 
-    pieces = PyList_New(0);
-    if (pieces == NULL)
-        goto Done;
+    s = PyUnicode_FromString("[");
+    if (s == NULL || _PyAccu_Accumulate(&acc, s))
+        goto error;
+    Py_CLEAR(s);
 
     /* Do repr() on each element.  Note that this may mutate the list,
        so must refetch the list size on each iteration. */
     for (i = 0; i < Py_SIZE(v); ++i) {
-        int status;
         if (Py_EnterRecursiveCall(" while getting the repr of a list"))
-            goto Done;
+            goto error;
         s = PyObject_Repr(v->ob_item[i]);
         Py_LeaveRecursiveCall();
-        if (s == NULL)
-            goto Done;
-        status = PyList_Append(pieces, s);
-        Py_DECREF(s);  /* append created a new ref */
-        if (status < 0)
-            goto Done;
+        if (i > 0 && _PyAccu_Accumulate(&acc, sep))
+            goto error;
+        if (s == NULL || _PyAccu_Accumulate(&acc, s))
+            goto error;
+        Py_CLEAR(s);
     }
+    s = PyUnicode_FromString("]");
+    if (s == NULL || _PyAccu_Accumulate(&acc, s))
+        goto error;
+    Py_CLEAR(s);
 
-    /* Add "[]" decorations to the first and last items. */
-    assert(PyList_GET_SIZE(pieces) > 0);
-    s = PyUnicode_FromString("[");
-    if (s == NULL)
-        goto Done;
-    temp = PyList_GET_ITEM(pieces, 0);
-    PyUnicode_AppendAndDel(&s, temp);
-    PyList_SET_ITEM(pieces, 0, s);
-    if (s == NULL)
-        goto Done;
+    Py_ReprLeave((PyObject *)v);
+    return _PyAccu_Finish(&acc);
 
-    s = PyUnicode_FromString("]");
-    if (s == NULL)
-        goto Done;
-    temp = PyList_GET_ITEM(pieces, PyList_GET_SIZE(pieces) - 1);
-    PyUnicode_AppendAndDel(&temp, s);
-    PyList_SET_ITEM(pieces, PyList_GET_SIZE(pieces) - 1, temp);
-    if (temp == NULL)
-        goto Done;
-
-    /* Paste them all together with ", " between. */
-    s = PyUnicode_FromString(", ");
-    if (s == NULL)
-        goto Done;
-    result = PyUnicode_Join(s, pieces);
-    Py_DECREF(s);
-
-Done:
-    Py_XDECREF(pieces);
+error:
+    _PyAccu_Destroy(&acc);
+    Py_XDECREF(s);
     Py_ReprLeave((PyObject *)v);
-    return result;
+    return NULL;
 }
 
 static Py_ssize_t
diff --git a/Objects/tupleobject.c b/Objects/tupleobject.c
index ddb69e4..54a580d 100644
--- a/Objects/tupleobject.c
+++ b/Objects/tupleobject.c
@@ -240,13 +240,20 @@ static PyObject *
 tuplerepr(PyTupleObject *v)
 {
     Py_ssize_t i, n;
-    PyObject *s, *temp;
-    PyObject *pieces, *result = NULL;
+    PyObject *s = NULL;
+    _PyAccu acc;
+    static PyObject *sep = NULL;
 
     n = Py_SIZE(v);
     if (n == 0)
         return PyUnicode_FromString("()");
 
+    if (sep == NULL) {
+        sep = PyUnicode_FromString(", ");
+        if (sep == NULL)
+            return NULL;
+    }
+
     /* While not mutable, it is still possible to end up with a cycle in a
        tuple through an object that stores itself within a tuple (and thus
        infinitely asks for the repr of itself). This should only be
@@ -256,52 +263,42 @@ tuplerepr(PyTupleObject *v)
         return i > 0 ? PyUnicode_FromString("(...)") : NULL;
     }
 
-    pieces = PyTuple_New(n);
-    if (pieces == NULL)
-        return NULL;
+    if (_PyAccu_Init(&acc))
+        goto error;
+
+    s = PyUnicode_FromString("(");
+    if (s == NULL || _PyAccu_Accumulate(&acc, s))
+        goto error;
+    Py_CLEAR(s);
 
     /* Do repr() on each element. */
     for (i = 0; i < n; ++i) {
         if (Py_EnterRecursiveCall(" while getting the repr of a tuple"))
-            goto Done;
+            goto error;
         s = PyObject_Repr(v->ob_item[i]);
         Py_LeaveRecursiveCall();
-        if (s == NULL)
-            goto Done;
-        PyTuple_SET_ITEM(pieces, i, s);
+        if (i > 0 && _PyAccu_Accumulate(&acc, sep))
+            goto error;
+        if (s == NULL || _PyAccu_Accumulate(&acc, s))
+            goto error;
+        Py_CLEAR(s);
     }
+    if (n > 1)
+        s = PyUnicode_FromString(")");
+    else
+        s = PyUnicode_FromString(",)");
+    if (s == NULL || _PyAccu_Accumulate(&acc, s))
+        goto error;
+    Py_CLEAR(s);
 
-    /* Add "()" decorations to the first and last items. */
-    assert(n > 0);
-    s = PyUnicode_FromString("(");
-    if (s == NULL)
-        goto Done;
-    temp = PyTuple_GET_ITEM(pieces, 0);
-    PyUnicode_AppendAndDel(&s, temp);
-    PyTuple_SET_ITEM(pieces, 0, s);
-    if (s == NULL)
-        goto Done;
-
-    s = PyUnicode_FromString(n == 1 ? ",)" : ")");
-    if (s == NULL)
-        goto Done;
-    temp = PyTuple_GET_ITEM(pieces, n-1);
-    PyUnicode_AppendAndDel(&temp, s);
-    PyTuple_SET_ITEM(pieces, n-1, temp);
-    if (temp == NULL)
-        goto Done;
-
-    /* Paste them all together with ", " between. */
-    s = PyUnicode_FromString(", ");
-    if (s == NULL)
-        goto Done;
-    result = PyUnicode_Join(s, pieces);
-    Py_DECREF(s);
-
-Done:
-    Py_DECREF(pieces);
     Py_ReprLeave((PyObject *)v);
-    return result;
+    return _PyAccu_Finish(&acc);
+
+error:
+    _PyAccu_Destroy(&acc);
+    Py_XDECREF(s);
+    Py_ReprLeave((PyObject *)v);
+    return NULL;
 }
 
 /* The addend 82520, was selected from the range(0, 1000000) for