BUG: to_json segfaults when exception occurs in UTF8 encoding of string

doc/source/whatsnew/v2.0.0.rst

@@ -875,7 +875,7 @@ I/O
 - Bug in :func:`DataFrame.to_string` with ``header=False`` that printed the index name on the same line as the first row of the data (:issue:`49230`)
 - Fixed memory leak which stemmed from the initialization of the internal JSON module (:issue:`49222`)
 - Fixed issue where :func:`json_normalize` would incorrectly remove leading characters from column names that matched the ``sep`` argument (:issue:`49861`)
--
+- Bug in :meth:`DataFrame.to_json` where it would segfault when failing to encode a string (:issue:`50307`)
 
 Period
 ^^^^^^

pandas/_libs/src/ujson/python/objToJSON.c

@@ -332,9 +332,18 @@ static char *PyBytesToUTF8(JSOBJ _obj, JSONTypeContext *Py_UNUSED(tc),
     return PyBytes_AS_STRING(obj);
 }
 
-static char *PyUnicodeToUTF8(JSOBJ _obj, JSONTypeContext *Py_UNUSED(tc),
+static char *PyUnicodeToUTF8(JSOBJ _obj, JSONTypeContext *tc,
                              size_t *_outLen) {
-    return (char *)PyUnicode_AsUTF8AndSize(_obj, (Py_ssize_t *)_outLen);
+    char *encoded = (char *)PyUnicode_AsUTF8AndSize(_obj,
+                                                    (Py_ssize_t *)_outLen);
+    if (encoded == NULL) {
+        /* Something went wrong.
+          Set errorMsg(to tell encoder to stop),
+          and let Python exception propagate. */
+        JSONObjectEncoder *enc = (JSONObjectEncoder *)tc->encoder;
+        enc->errorMsg = "Encoding failed.";
+    }
+    return encoded;
 }
 
 /* JSON callback. returns a char* and mutates the pointer to *len */

pandas/tests/io/json/test_ujson.py

@@ -291,6 +291,15 @@ def test_encode_unicode_4bytes_utf8highest(self):
         assert enc == json.dumps(four_bytes_input)
         assert dec == json.loads(enc)
 
+    def test_encode_unicode_error(self):
+        string = "'\udac0'"
+        msg = (
+            r"'utf-8' codec can't encode character '\\udac0' "
+            r"in position 1: surrogates not allowed"
+        )
+        with pytest.raises(UnicodeEncodeError, match=msg):
+            ujson.dumps([string])
+
     def test_encode_array_in_array(self):
         arr_in_arr_input = [[[[]]]]
         output = ujson.encode(arr_in_arr_input)