Allow json(..., sort_keys=True) to handle mixed keys. (https://bugs.python.org/issue25457)

Author: jheiv

Lib/json/encoder.py

@@ -331,6 +331,30 @@ def _iterencode_list(lst, _current_indent_level):
             del markers[markerid]
 
     def _iterencode_dict(dct, _current_indent_level):
+        def _coerce_key(key):
+            if isinstance(key, str):
+                return key
+            # JavaScript is weakly typed for these, so it makes sense to
+            # also allow them.  Many encoders seem to do something like this.
+            if isinstance(key, float):
+                # see comment for int/float in _make_iterencode
+                return _floatstr(key)
+            if key is True:
+                return 'true'
+            if key is False:
+                return 'false'
+            if key is None:
+                return 'null'
+            if isinstance(key, int):
+                # see comment for int/float in _make_iterencode
+                return _intstr(key)
+
+            if _skipkeys:
+                return None
+            else:
+                raise TypeError(f'keys must be str, int, float, bool or None, '
+                                f'not {key.__class__.__name__}')
+
         if not dct:
             yield '{}'
             return
@@ -349,32 +373,17 @@ def _iterencode_dict(dct, _current_indent_level):
             newline_indent = None
             item_separator = _item_separator
         first = True
+
+        # Coerce keys to strings (or None if _skipkeys)
+        items = ((_coerce_key(k), v) for (k,v) in dct.items())
+
         if _sort_keys:
-            items = sorted(dct.items(), key=lambda kv: kv[0])
-        else:
-            items = dct.items()
+            items = sorted((k,v) for (k,v) in items if k is not None)
+
         for key, value in items:
-            if isinstance(key, str):
-                pass
-            # JavaScript is weakly typed for these, so it makes sense to
-            # also allow them.  Many encoders seem to do something like this.
-            elif isinstance(key, float):
-                # see comment for int/float in _make_iterencode
-                key = _floatstr(key)
-            elif key is True:
-                key = 'true'
-            elif key is False:
-                key = 'false'
-            elif key is None:
-                key = 'null'
-            elif isinstance(key, int):
-                # see comment for int/float in _make_iterencode
-                key = _intstr(key)
-            elif _skipkeys:
+            if key is None:
+                # If specified, skip keys that we weren't able to coerce to strings
                 continue
-            else:
-                raise TypeError(f'keys must be str, int, float, bool or None, '
-                                f'not {key.__class__.__name__}')
             if first:
                 first = False
             else:

Modules/_json.c

@@ -1562,6 +1562,7 @@ encoder_listencode_dict(PyEncoderObject *s, _PyAccu *acc,
     PyObject *ident = NULL;
     PyObject *it = NULL;
     PyObject *items;
+	PyObject *coerced_items;
     PyObject *item = NULL;
     Py_ssize_t idx;
 
@@ -1607,55 +1608,81 @@ encoder_listencode_dict(PyEncoderObject *s, _PyAccu *acc,
     items = PyMapping_Items(dct);
     if (items == NULL)
         goto bail;
-    if (s->sort_keys && PyList_Sort(items) < 0) {
-        Py_DECREF(items);
+
+	coerced_items = PyList_New(0);
+	it = PyObject_GetIter(items);
+	Py_DECREF(items);
+	if (it == NULL)
+		goto bail;
+
+	while ((item = PyIter_Next(it)) != NULL) {
+		PyObject *key, *value, *coerced_item;
+		if (!PyTuple_Check(item) || PyTuple_GET_SIZE(item) != 2) {
+			PyErr_SetString(PyExc_ValueError, "items must return 2-tuples");
+			goto bail;
+		}
+		key = PyTuple_GET_ITEM(item, 0);
+		if (PyUnicode_Check(key)) {
+			Py_INCREF(key);
+			kstr = key;
+		}
+		else if (PyFloat_Check(key)) {
+			kstr = encoder_encode_float(s, key);
+			if (kstr == NULL)
+				goto bail;
+		}
+		else if (key == Py_True || key == Py_False || key == Py_None) {
+			/* This must come before the PyLong_Check because
+			True and False are also 1 and 0.*/
+			kstr = _encoded_const(key);
+			if (kstr == NULL)
+				goto bail;
+		}
+		else if (PyLong_Check(key)) {
+			kstr = PyLong_Type.tp_str(key);
+			if (kstr == NULL) {
+				goto bail;
+			}
+		}
+		else if (s->skipkeys) {
+			Py_DECREF(item);
+			continue;
+		}
+		else {
+			PyErr_Format(PyExc_TypeError,
+				"keys must be str, int, float, bool or None, "
+				"not %.100s", key->ob_type->tp_name);
+			goto bail;
+		}
+
+		value = PyTuple_GET_ITEM(item, 1);
+		coerced_item = PyTuple_Pack(2, kstr, value);
+		if (coerced_item == NULL) {
+			goto bail;
+		}
+		/* Append instead of set because skipkeys=True may 
+		   "shrink" the number of items */
+		if (-1 == PyList_Append(coerced_items, coerced_item))
+			goto bail;
+	}
+	
+    if (s->sort_keys && PyList_Sort(coerced_items) < 0) {
+        Py_DECREF(coerced_items);
         goto bail;
     }
-    it = PyObject_GetIter(items);
-    Py_DECREF(items);
+    it = PyObject_GetIter(coerced_items);
+    Py_DECREF(coerced_items);
     if (it == NULL)
         goto bail;
     idx = 0;
     while ((item = PyIter_Next(it)) != NULL) {
-        PyObject *encoded, *key, *value;
+        PyObject *encoded, *value;
         if (!PyTuple_Check(item) || PyTuple_GET_SIZE(item) != 2) {
             PyErr_SetString(PyExc_ValueError, "items must return 2-tuples");
             goto bail;
         }
-        key = PyTuple_GET_ITEM(item, 0);
-        if (PyUnicode_Check(key)) {
-            Py_INCREF(key);
-            kstr = key;
-        }
-        else if (PyFloat_Check(key)) {
-            kstr = encoder_encode_float(s, key);
-            if (kstr == NULL)
-                goto bail;
-        }
-        else if (key == Py_True || key == Py_False || key == Py_None) {
-                        /* This must come before the PyLong_Check because
-                           True and False are also 1 and 0.*/
-            kstr = _encoded_const(key);
-            if (kstr == NULL)
-                goto bail;
-        }
-        else if (PyLong_Check(key)) {
-            kstr = PyLong_Type.tp_str(key);
-            if (kstr == NULL) {
-                goto bail;
-            }
-        }
-        else if (s->skipkeys) {
-            Py_DECREF(item);
-            continue;
-        }
-        else {
-            PyErr_Format(PyExc_TypeError,
-                         "keys must be str, int, float, bool or None, "
-                         "not %.100s", key->ob_type->tp_name);
-            goto bail;
-        }
-
+        kstr = PyTuple_GET_ITEM(item, 0);
+        
         if (idx) {
             if (_PyAccu_Accumulate(acc, s->item_separator))
                 goto bail;
@@ -1703,6 +1730,7 @@ encoder_listencode_dict(PyEncoderObject *s, _PyAccu *acc,
     Py_XDECREF(item);
     Py_XDECREF(kstr);
     Py_XDECREF(ident);
+	Py_XDECREF(coerced_items);
     return -1;
 }