bpo-44859: Improve error handling in sqlite3 and and raise more accurate exceptions. (GH-27654)

* MemoryError is now raised instead of sqlite3.Warning when
  memory is not enough for encoding a statement to UTF-8
  in Connection.__call__() and Cursor.execute().
* UnicodEncodeError is now raised instead of sqlite3.Warning when
  the statement contains surrogate characters
  in Connection.__call__() and Cursor.execute().
* TypeError is now raised instead of ValueError for non-string
  script argument in Cursor.executescript().
* ValueError is now raised for script containing the null
  character instead of truncating it in Cursor.executescript().
* Correctly handle exceptions raised when getting boolean value
  of the result of the progress handler.
* Add many tests covering different corner cases.

Co-authored-by: Erlend Egeberg Aasland <erlend.aasland@innova.no>

Modules/_sqlite/clinic/cursor.c.h

@@ -119,6 +119,35 @@ PyDoc_STRVAR(pysqlite_cursor_executescript__doc__,
 #define PYSQLITE_CURSOR_EXECUTESCRIPT_METHODDEF    \
     {"executescript", (PyCFunction)pysqlite_cursor_executescript, METH_O, pysqlite_cursor_executescript__doc__},
 
+static PyObject *
+pysqlite_cursor_executescript_impl(pysqlite_Cursor *self,
+                                   const char *sql_script);
+
+static PyObject *
+pysqlite_cursor_executescript(pysqlite_Cursor *self, PyObject *arg)
+{
+    PyObject *return_value = NULL;
+    const char *sql_script;
+
+    if (!PyUnicode_Check(arg)) {
+        _PyArg_BadArgument("executescript", "argument", "str", arg);
+        goto exit;
+    }
+    Py_ssize_t sql_script_length;
+    sql_script = PyUnicode_AsUTF8AndSize(arg, &sql_script_length);
+    if (sql_script == NULL) {
+        goto exit;
+    }
+    if (strlen(sql_script) != (size_t)sql_script_length) {
+        PyErr_SetString(PyExc_ValueError, "embedded null character");
+        goto exit;
+    }
+    return_value = pysqlite_cursor_executescript_impl(self, sql_script);
+
+exit:
+    return return_value;
+}
+
 PyDoc_STRVAR(pysqlite_cursor_fetchone__doc__,
 "fetchone($self, /)\n"
 "--\n"
@@ -270,4 +299,4 @@ pysqlite_cursor_close(pysqlite_Cursor *self, PyTypeObject *cls, PyObject *const
 exit:
     return return_value;
 }
-/*[clinic end generated code: output=7b216aba2439f5cf input=a9049054013a1b77]*/
+/*[clinic end generated code: output=ace31a7481aa3f41 input=a9049054013a1b77]*/

Modules/_sqlite/connection.c

@@ -997,6 +997,14 @@ static int _progress_handler(void* user_arg)
     ret = _PyObject_CallNoArg((PyObject*)user_arg);
 
     if (!ret) {
+        /* abort query if error occurred */
+        rc = -1;
+    }
+    else {
+        rc = PyObject_IsTrue(ret);
+        Py_DECREF(ret);
+    }
+    if (rc < 0) {
         pysqlite_state *state = pysqlite_get_state(NULL);
         if (state->enable_callback_tracebacks) {
             PyErr_Print();
@@ -1004,12 +1012,6 @@ static int _progress_handler(void* user_arg)
         else {
             PyErr_Clear();
         }
-
-        /* abort query if error occurred */
-        rc = 1;
-    } else {
-        rc = (int)PyObject_IsTrue(ret);
-        Py_DECREF(ret);
     }
 
     PyGILState_Release(gilstate);

Modules/_sqlite/cursor.c

@@ -728,21 +728,21 @@ pysqlite_cursor_executemany_impl(pysqlite_Cursor *self, PyObject *sql,
 /*[clinic input]
 _sqlite3.Cursor.executescript as pysqlite_cursor_executescript
 
-    sql_script as script_obj: object
+    sql_script: str
     /
 
 Executes multiple SQL statements at once. Non-standard.
 [clinic start generated code]*/
 
 static PyObject *
-pysqlite_cursor_executescript(pysqlite_Cursor *self, PyObject *script_obj)
-/*[clinic end generated code: output=115a8132b0f200fe input=ba3ec59df205e362]*/
+pysqlite_cursor_executescript_impl(pysqlite_Cursor *self,
+                                   const char *sql_script)
+/*[clinic end generated code: output=8fd726dde1c65164 input=1ac0693dc8db02a8]*/
 {
     _Py_IDENTIFIER(commit);
-    const char* script_cstr;
     sqlite3_stmt* statement;
     int rc;
-    Py_ssize_t sql_len;
+    size_t sql_len;
     PyObject* result;
 
     if (!check_cursor(self)) {
@@ -751,21 +751,12 @@ pysqlite_cursor_executescript(pysqlite_Cursor *self, PyObject *script_obj)
 
     self->reset = 0;
 
-    if (PyUnicode_Check(script_obj)) {
-        script_cstr = PyUnicode_AsUTF8AndSize(script_obj, &sql_len);
-        if (!script_cstr) {
-            return NULL;
-        }
-
-        int max_length = sqlite3_limit(self->connection->db,
-                                       SQLITE_LIMIT_LENGTH, -1);
-        if (sql_len >= max_length) {
-            PyErr_SetString(self->connection->DataError,
-                            "query string is too large");
-            return NULL;
-        }
-    } else {
-        PyErr_SetString(PyExc_ValueError, "script argument must be unicode.");
+    sql_len = strlen(sql_script);
+    int max_length = sqlite3_limit(self->connection->db,
+                                   SQLITE_LIMIT_LENGTH, -1);
+    if (sql_len >= (unsigned)max_length) {
+        PyErr_SetString(self->connection->DataError,
+                        "query string is too large");
         return NULL;
     }
 
@@ -782,7 +773,7 @@ pysqlite_cursor_executescript(pysqlite_Cursor *self, PyObject *script_obj)
 
         Py_BEGIN_ALLOW_THREADS
         rc = sqlite3_prepare_v2(self->connection->db,
-                                script_cstr,
+                                sql_script,
                                 (int)sql_len + 1,
                                 &statement,
                                 &tail);
@@ -816,8 +807,8 @@ pysqlite_cursor_executescript(pysqlite_Cursor *self, PyObject *script_obj)
         if (*tail == (char)0) {
             break;
         }
-        sql_len -= (tail - script_cstr);
-        script_cstr = tail;
+        sql_len -= (tail - sql_script);
+        sql_script = tail;
     }
 
 error:

Modules/_sqlite/statement.c

@@ -56,9 +56,6 @@ pysqlite_statement_create(pysqlite_Connection *connection, PyObject *sql)
     Py_ssize_t size;
     const char *sql_cstr = PyUnicode_AsUTF8AndSize(sql, &size);
     if (sql_cstr == NULL) {
-        PyErr_Format(connection->Warning,
-                     "SQL is of wrong type ('%s'). Must be string.",
-                     Py_TYPE(sql)->tp_name);
         return NULL;
     }