Fix Bug #1378022, UTF-8 files with a leading BOM crashed the interpreter.
Needs backport.
diff --git a/Lib/test/bad_coding2.py b/Lib/test/bad_coding2.py
new file mode 100644
index 0000000..604b122
--- /dev/null
+++ b/Lib/test/bad_coding2.py
@@ -0,0 +1,2 @@
+#coding: utf8
+print '我'
\ No newline at end of file
diff --git a/Lib/test/test_coding.py b/Lib/test/test_coding.py
index aa7241d..e83015e 100644
--- a/Lib/test/test_coding.py
+++ b/Lib/test/test_coding.py
@@ -5,6 +5,13 @@
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__)
diff --git a/Misc/NEWS b/Misc/NEWS
index 1db35f4..7b27e49 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,6 +12,8 @@
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.
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 37e6c33..a79ea81 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -292,6 +292,12 @@
PyMem_DEL(cs);
}
}
+ if (!r) {
+ cs = tok->encoding;
+ if (!cs)
+ cs = "with BOM";
+ PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
+ }
return r;
}
diff --git a/Python/pythonrun.c b/Python/pythonrun.c
index a7f4fe7..30cb518 100644
--- a/Python/pythonrun.c
+++ b/Python/pythonrun.c
@@ -1439,8 +1439,8 @@
}
if (msg == NULL)
msg = "unknown decode error";
- Py_DECREF(type);
- Py_DECREF(value);
+ Py_XDECREF(type);
+ Py_XDECREF(value);
Py_XDECREF(tb);
break;
}