Issue #6676: Ensure a meaningful exception is raised when attempting to parse more than one XML document per pyexpat xmlparser instance. (Original patches by Hirokazu Yamamoto and Amaury Forgeot d'Arc, with suggested wording by David Gutteridge) diff --git a/Doc/library/pyexpat.rst b/Doc/library/pyexpat.rst --- a/Doc/library/pyexpat.rst +++ b/Doc/library/pyexpat.rst @@ -103,6 +103,10 @@ http://www.python.org/ns/ elem1 elem2 + Due to limitations in the ``Expat`` library used by :mod:`pyexpat`, + the :class:`xmlparser` instance returned can only be used to parse a single + XML document. Call ``ParserCreate`` for each document to provide unique + parser instances. .. seealso:: @@ -122,7 +126,9 @@ Parses the contents of the string *data*, calling the appropriate handler functions to process the parsed data. *isfinal* must be true on the final call - to this method. *data* can be the empty string at any time. + to this method; it allows the parsing of a single file in fragments, + not the submission of multiple files. + *data* can be the empty string at any time. .. method:: xmlparser.ParseFile(file) diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py --- a/Lib/test/test_pyexpat.py +++ b/Lib/test/test_pyexpat.py @@ -228,6 +228,17 @@ finally: test_support.unlink(test_support.TESTFN) + def test_parse_again(self): + parser = expat.ParserCreate() + file = StringIO.StringIO(data) + parser.ParseFile(file) + # Issue 6676: ensure a meaningful exception is raised when attempting + # to parse more than one XML document per xmlparser instance, + # a limitation of the Expat library. + with self.assertRaises(expat.error) as cm: + parser.ParseFile(file) + self.assertEqual(expat.ErrorString(cm.exception.code), + expat.errors.XML_ERROR_FINISHED) class NamespaceSeparatorTest(unittest.TestCase): def test_legal(self): diff --git a/Modules/pyexpat.c b/Modules/pyexpat.c --- a/Modules/pyexpat.c +++ b/Modules/pyexpat.c @@ -976,7 +976,7 @@ void *buf = XML_GetBuffer(self->itself, BUF_SIZE); if (buf == NULL) { Py_XDECREF(readmethod); - return PyErr_NoMemory(); + return get_parse_result(self, 0); } bytes_read = readinst(buf, BUF_SIZE, readmethod);