Issue #18038: SyntaxError raised during compilation sources with illegal

serhiy-storchaka · serhiy-storchaka · commit 3af14aaba5e5 · 2013-06-09T16:51:52.000+03:00
encoding now always contains an encoding name.
diff --git a/Lib/test/test_pep263.py b/Lib/test/test_pep263.py
@@ -55,6 +55,24 @@ def test_issue7820(self):
         # two bytes in common with the UTF-8 BOM
         self.assertRaises(SyntaxError, eval, b'\xef\xbb\x20')
 
+    def test_error_message(self):
+        compile(b'# -*- coding: iso-8859-15 -*-\n', 'dummy', 'exec')
+        compile(b'\xef\xbb\xbf\n', 'dummy', 'exec')
+        compile(b'\xef\xbb\xbf# -*- coding: utf-8 -*-\n', 'dummy', 'exec')
+        with self.assertRaisesRegexp(SyntaxError, 'fake'):
+            compile(b'# -*- coding: fake -*-\n', 'dummy', 'exec')
+        with self.assertRaisesRegexp(SyntaxError, 'iso-8859-15'):
+            compile(b'\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n',
+                    'dummy', 'exec')
+        with self.assertRaisesRegexp(SyntaxError, 'BOM'):
+            compile(b'\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n',
+                    'dummy', 'exec')
+        with self.assertRaisesRegexp(SyntaxError, 'fake'):
+            compile(b'\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec')
+        with self.assertRaisesRegexp(SyntaxError, 'BOM'):
+            compile(b'\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec')
+
+
 def test_main():
     support.run_unittest(PEP263Test)
 
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -12,6 +12,9 @@ What's New in Python 3.3.3 release candidate 1?
 Core and Builtins
 -----------------
 
+- Issue #18038: SyntaxError raised during compilation sources with illegal
+  encoding now always contains an encoding name.
+
 - Issue #17644: Fix a crash in str.format when curly braces are used in square
   brackets.
 
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
@@ -291,20 +291,20 @@ check_coding_spec(const char* line, Py_ssize_t size, struct tok_state *tok,
                     tok->encoding = cs;
                     tok->decoding_state = STATE_NORMAL;
                 }
-                else
+                else {
+                    PyErr_Format(PyExc_SyntaxError,
+                                 "encoding problem: %s", cs);
                     PyMem_FREE(cs);
+                }
             }
         } else {                /* then, compare cs with BOM */
             r = (strcmp(tok->encoding, cs) == 0);
+            if (!r)
+                PyErr_Format(PyExc_SyntaxError,
+                             "encoding problem: %s with BOM", cs);
             PyMem_FREE(cs);
         }
     }
-    if (!r) {
-        cs = tok->encoding;
-        if (!cs)
-            cs = "with BOM";
-        PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
-    }
     return r;
 }
 

Original file line number	Diff line number	Diff line change
`@@ -291,20 +291,20 @@ check_coding_spec(const char* line, Py_ssize_t size, struct tok_state *tok,`
`291`	`291`	`tok->encoding = cs;`
`292`	`292`	`tok->decoding_state = STATE_NORMAL;`
`293`	`293`	`}`
`294`		`- else`
	`294`	`+ else {`
	`295`	`+ PyErr_Format(PyExc_SyntaxError,`
	`296`	`+ "encoding problem: %s", cs);`
`295`	`297`	`PyMem_FREE(cs);`
	`298`	`+ }`
`296`	`299`	`}`
`297`	`300`	`} else { /* then, compare cs with BOM */`
`298`	`301`	`r = (strcmp(tok->encoding, cs) == 0);`
	`302`	`+ if (!r)`
	`303`	`+ PyErr_Format(PyExc_SyntaxError,`
	`304`	`+ "encoding problem: %s with BOM", cs);`
`299`	`305`	`PyMem_FREE(cs);`
`300`	`306`	`}`
`301`	`307`	`}`
`302`		`- if (!r) {`
`303`		`- cs = tok->encoding;`
`304`		`- if (!cs)`
`305`		`- cs = "with BOM";`
`306`		`- PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);`
`307`		`- }`
`308`	`308`	`return r;`
`309`	`309`	`}`
`310`	`310`