[Python-checkins] cpython (3.2): Issue #14629: Raise SyntaxError in tokenizer.detect_encoding

[martin.v.loewis]

http://hg.python.org/cpython/rev/b07488490001
changeset:   76425:b07488490001
branch:      3.2
parent:      76421:41c64c700e1e
user:        Martin v. Löwis <martin at v.loewis.de>
date:        Fri Apr 20 14:36:47 2012 +0200
summary:
  Issue #14629: Raise SyntaxError in tokenizer.detect_encoding
if the first two lines have non-UTF-8 characters without an encoding declaration.

files:
  Lib/test/test_tokenize.py |  10 ++++++++++
  Lib/tokenize.py           |   7 +++++--
  Misc/NEWS                 |   3 +++
  3 files changed, 18 insertions(+), 2 deletions(-)


diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -825,6 +825,16 @@
                 found, consumed_lines = detect_encoding(rl)
                 self.assertEqual(found, "iso-8859-1")
 
+    def test_syntaxerror_latin1(self):
+        # Issue 14629: need to raise SyntaxError if the first
+        # line(s) have non-UTF-8 characters
+        lines = (
+            b'print("\xdf")', # Latin-1: LATIN SMALL LETTER SHARP S
+            )
+        readline = self.get_readline(lines)
+        self.assertRaises(SyntaxError, detect_encoding, readline)
+
+
     def test_utf8_normalization(self):
         # See get_normal_name() in tokenizer.c.
         encodings = ("utf-8", "utf-8-mac", "utf-8-unix")
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -292,9 +292,12 @@
 
     def find_cookie(line):
         try:
-            line_string = line.decode('ascii')
+            # Decode as UTF-8. Either the line is an encoding declaration,
+            # in which case it should be pure ASCII, or it must be UTF-8
+            # per default encoding.
+            line_string = line.decode('utf-8')
         except UnicodeDecodeError:
-            return None
+            raise SyntaxError("invalid or missing encoding declaration")
 
         matches = cookie_re.findall(line_string)
         if not matches:
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -47,6 +47,9 @@
 Library
 -------
 
+- Issue #14629: Raise SyntaxError in tokenizer.detect_encoding if the
+  first two lines have non-UTF-8 characters without an encoding declaration.
+
 - Issue #14308: Fix an exception when a "dummy" thread is in the threading
   module's active list after a fork().
 

-- 
Repository URL: http://hg.python.org/cpython