Issue #8195: Fix a crash in sqlite Connection.create_collation() if the

collation name contains a surrogate character.

3 files changed, 22 insertions, 5 deletions

diff --git a/Lib/sqlite3/test/regression.py b/Lib/sqlite3/test/regression.py
index 255bd3f..7d0553d 100644
--- a/Lib/sqlite3/test/regression.py
+++ b/Lib/sqlite3/test/regression.py
@@ -274,6 +274,13 @@ class RegressionTests(unittest.TestCase):
         """
         self.assertRaises(sqlite.Warning, self.con, 1)
 
+    def CheckCollation(self):
+        def collation_cb(a, b):
+            return 1
+        self.assertRaises(sqlite.ProgrammingError, self.con.create_collation,
+            # Lone surrogate cannot be encoded to the default encoding (utf8)
+            "\uDC80", collation_cb)
+
 def suite():
     regression_suite = unittest.makeSuite(RegressionTests, "Check")
     return unittest.TestSuite((regression_suite,))
diff --git a/Misc/NEWS b/Misc/NEWS
index fffe64f..ff93519 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -323,6 +323,9 @@ C-API
 Library
 -------
 
+- Issue #8195: Fix a crash in sqlite Connection.create_collation() if the
+  collation name contains a surrogate character.
+
 - Issue #8484: Load all ciphers and digest algorithms when initializing
   the _ssl extension, such that verification of some SSL certificates
   doesn't fail because of an "unknown algorithm".
diff --git a/Modules/_sqlite/connection.c b/Modules/_sqlite/connection.c
index d916c34..88d6b40 100644
--- a/Modules/_sqlite/connection.c
+++ b/Modules/_sqlite/connection.c
@@ -1374,7 +1374,9 @@ pysqlite_connection_create_collation(pysqlite_Connection* self, PyObject* args)
     PyObject* uppercase_name = 0;
     PyObject* name;
     PyObject* retval;
-    char* chk;
+    Py_UNICODE* chk;
+    Py_ssize_t i, len;
+    char *uppercase_name_str;
     int rc;
 
     if (!pysqlite_check_thread(self) || !pysqlite_check_connection(self)) {
@@ -1390,19 +1392,24 @@ pysqlite_connection_create_collation(pysqlite_Connection* self, PyObject* args)
         goto finally;
     }
 
-    chk = _PyUnicode_AsString(uppercase_name);
-    while (*chk) {
+    len = PyUnicode_GET_SIZE(uppercase_name);
+    chk = PyUnicode_AS_UNICODE(uppercase_name);
+    for (i=0; i<len; i++, chk++) {
         if ((*chk >= '0' && *chk <= '9')
          || (*chk >= 'A' && *chk <= 'Z')
          || (*chk == '_'))
         {
-            chk++;
+            continue;
         } else {
             PyErr_SetString(pysqlite_ProgrammingError, "invalid character in collation name");
             goto finally;
         }
     }
 
+    uppercase_name_str = _PyUnicode_AsString(uppercase_name);
+    if (!uppercase_name_str)
+        goto finally;
+
     if (callable != Py_None && !PyCallable_Check(callable)) {
         PyErr_SetString(PyExc_TypeError, "parameter must be callable");
         goto finally;
@@ -1417,7 +1424,7 @@ pysqlite_connection_create_collation(pysqlite_Connection* self, PyObject* args)
     }
 
     rc = sqlite3_create_collation(self->db,
-                                  _PyUnicode_AsString(uppercase_name),
+                                  uppercase_name_str,
                                   SQLITE_UTF8,
                                   (callable != Py_None) ? callable : NULL,
                                   (callable != Py_None) ? pysqlite_collation_callback : NULL);