#4877: Fix a segfault in xml.parsers.expat while attempting to parse a closed file.

Lib/test/test_pyexpat.py

@@ -6,6 +6,7 @@ import unittest
 
 from xml.parsers import expat
 
+from test import test_support
 from test.test_support import sortdict, run_unittest
 
 
@@ -217,6 +218,16 @@ class ParseTest(unittest.TestCase):
         self.assertEqual(op[15], "External entity ref: (None, u'entity.file', None)")
         self.assertEqual(op[16], "End element: u'root'")
 
+        # Issue 4877: expat.ParseFile causes segfault on a closed file.
+        fp = open(test_support.TESTFN, 'wb')
+        try:
+            fp.close()
+            parser = expat.ParserCreate()
+            with self.assertRaises(ValueError):
+                parser.ParseFile(fp)
+        finally:
+            test_support.unlink(test_support.TESTFN)
+
 
 class NamespaceSeparatorTest(unittest.TestCase):
     def test_legal(self):

Misc/NEWS

@@ -51,11 +51,14 @@ Core and Builtins
 Library
 -------
 
+- Issue #4877: Fix a segfault in xml.parsers.expat while attempting to parse
+  a closed file.
+
 - Issue #8428: Fix a race condition in multiprocessing.Pool when terminating
   worker processes: new processes would be spawned while the pool is being
   shut down.  Patch by Charles-François Natali.
 
-- Issue #7311: fix HTMLParser to accept non-ASCII attribute values.
+- Issue #7311: Fix HTMLParser to accept non-ASCII attribute values.
 
 - Issue #10963: Ensure that subprocess.communicate() never raises EPIPE.
 

Modules/pyexpat.c

@@ -962,21 +962,15 @@ static PyObject *
 xmlparse_ParseFile(xmlparseobject *self, PyObject *f)
 {
     int rv = 1;
-    FILE *fp;
     PyObject *readmethod = NULL;
 
-    if (PyFile_Check(f)) {
-        fp = PyFile_AsFile(f);
-    }
-    else {
-        fp = NULL;
-        readmethod = PyObject_GetAttrString(f, "read");
-        if (readmethod == NULL) {
-            PyErr_Clear();
-            PyErr_SetString(PyExc_TypeError,
-                            "argument must have 'read' attribute");
-            return NULL;
-        }
+    readmethod = PyObject_GetAttrString(f, "read");
+    if (readmethod == NULL) {
+        PyErr_Clear();
+        PyErr_SetString(PyExc_TypeError,
+                        "argument must have 'read' attribute");
+        return NULL;
+
     }
     for (;;) {
         int bytes_read;
@@ -986,20 +980,12 @@ xmlparse_ParseFile(xmlparseobject *self, PyObject *f)
             return PyErr_NoMemory();
         }
 
-        if (fp) {
-            bytes_read = fread(buf, sizeof(char), BUF_SIZE, fp);
-            if (bytes_read < 0) {
-                PyErr_SetFromErrno(PyExc_IOError);
-                return NULL;
-            }
-        }
-        else {
-            bytes_read = readinst(buf, BUF_SIZE, readmethod);
-            if (bytes_read < 0) {
-                Py_XDECREF(readmethod);
-                return NULL;
-            }
+        bytes_read = readinst(buf, BUF_SIZE, readmethod);
+        if (bytes_read < 0) {
+            Py_XDECREF(readmethod);
+            return NULL;
         }
+
         rv = XML_ParseBuffer(self->itself, bytes_read, bytes_read == 0);
         if (PyErr_Occurred()) {
             Py_XDECREF(readmethod);