BUG: Fix pandas-dev#15344 by backporting ujson usage of PEP 393 APIs for compact ascii

Author: tobgu

doc/source/whatsnew/v0.20.0.txt

@@ -517,3 +517,5 @@ Bug Fixes
 
 - Bug in ``DataFrame.boxplot`` where ``fontsize`` was not applied to the tick labels on both axes (:issue:`15108`)
 - Bug in ``Series.replace`` and ``DataFrame.replace`` which failed on empty replacement dicts (:issue:`15289`)
+
+- Bug in ``to_json`` causing single byte ascii characters to be expanded to four byte unicode (:issue:`15344`)

pandas/io/tests/json/test_pandas.py

@@ -1044,3 +1044,13 @@ def roundtrip(s, encoding='latin-1'):
 
         for s in examples:
             roundtrip(s)
+
+    def test_data_frame_size_after_to_json(self):
+        # GH15344
+        df = DataFrame({'a': [str(1)]})
+
+        size_before = df.memory_usage(index=True, deep=True).sum()
+        df.to_json()
+        size_after = df.memory_usage(index=True, deep=True).sum()
+
+        self.assertEqual(size_before, size_after)

pandas/src/ujson/python/objToJSON.c

@@ -402,6 +402,16 @@ static void *PyStringToUTF8(JSOBJ _obj, JSONTypeContext *tc, void *outValue,
 static void *PyUnicodeToUTF8(JSOBJ _obj, JSONTypeContext *tc, void *outValue,
                              size_t *_outLen) {
     PyObject *obj = (PyObject *)_obj;
+
+#if (PY_VERSION_HEX >= 0x03030000)
+    if(PyUnicode_IS_COMPACT_ASCII(obj)) {
+        Py_ssize_t len;
+        char *data = PyUnicode_AsUTF8AndSize(obj, &len);
+        *_outLen = len;
+        return data;
+    }
+#endif
+
     PyObject *newObj = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(obj),
                                             PyUnicode_GET_SIZE(obj), NULL);