Fix Bug #1378022, UTF-8 files with a leading BOM crashed the interpreter.

Needs backport.

Lib/test/bad_coding2.py

@@ -0,0 +1,2 @@
+#coding: utf8
+print '我'

Lib/test/test_coding.py

@@ -5,6 +5,13 @@ import os
 class CodingTest(unittest.TestCase):
     def test_bad_coding(self):
         module_name = 'bad_coding'
+        self.verify_bad_module(module_name)
+
+    def test_bad_coding2(self):
+        module_name = 'bad_coding2'
+        self.verify_bad_module(module_name)
+
+    def verify_bad_module(self, module_name):
         self.assertRaises(SyntaxError, __import__, 'test.' + module_name)
 
         path = os.path.dirname(__file__)

Misc/NEWS

@@ -12,6 +12,8 @@ What's New in Python 2.5 alpha 1?
 Core and builtins
 -----------------
 
+- Bug #1378022, UTF-8 files with a leading BOM crashed the interpreter.
+
 - Support for converting hex strings to floats no longer works.
   This was not portable.  float('0x3') now raises a ValueError.
 

Parser/tokenizer.c

@@ -292,6 +292,12 @@ check_coding_spec(const char* line, int size, struct tok_state *tok,
 			PyMem_DEL(cs);
 		}
 	}
+	if (!r) {
+		cs = tok->encoding;
+		if (!cs)
+			cs = "with BOM";
+		PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
+	}
 	return r;
 }
 

Python/pythonrun.c

@@ -1439,8 +1439,8 @@ err_input(perrdetail *err)
 		}
 		if (msg == NULL)
 			msg = "unknown decode error";
-		Py_DECREF(type);
-		Py_DECREF(value);
+		Py_XDECREF(type);
+		Py_XDECREF(value);
 		Py_XDECREF(tb);
 		break;
 	}