Issue #18960: Fix bugs with Python source code encoding in the second line.

* The first line of Python script could be executed twice when the source
encoding (not equal to 'utf-8') was specified on the second line.

* Now the source encoding declaration on the second line isn't effective if
the first line contains anything except a comment.

* As a consequence, 'python -x' works now again with files with the source
encoding declarations specified on the second file, and can be used again
to make Python batch files on Windows.

* The tokenize module now ignore the source encoding declaration on the second
line if the first line contains anything except a comment.

* IDLE now ignores the source encoding declaration on the second line if the
first line contains anything except a comment.

* 2to3 and the findnocoding.py script now ignore the source encoding
declaration on the second line if the first line contains anything except
a comment.

1 files changed, 33 insertions, 0 deletions

diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
index 17650855eb..6ed859707f 100644
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -885,6 +885,39 @@ class TestDetectEncoding(TestCase):
         readline = self.get_readline(lines)
         self.assertRaises(SyntaxError, detect_encoding, readline)
 
+    def test_cookie_second_line_noncommented_first_line(self):
+        lines = (
+            b"print('\xc2\xa3')\n",
+            b'# vim: set fileencoding=iso8859-15 :\n',
+            b"print('\xe2\x82\xac')\n"
+        )
+        encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+        self.assertEqual(encoding, 'utf-8')
+        expected = [b"print('\xc2\xa3')\n"]
+        self.assertEqual(consumed_lines, expected)
+
+    def test_cookie_second_line_commented_first_line(self):
+        lines = (
+            b"#print('\xc2\xa3')\n",
+            b'# vim: set fileencoding=iso8859-15 :\n',
+            b"print('\xe2\x82\xac')\n"
+        )
+        encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+        self.assertEqual(encoding, 'iso8859-15')
+        expected = [b"#print('\xc2\xa3')\n", b'# vim: set fileencoding=iso8859-15 :\n']
+        self.assertEqual(consumed_lines, expected)
+
+    def test_cookie_second_line_empty_first_line(self):
+        lines = (
+            b'\n',
+            b'# vim: set fileencoding=iso8859-15 :\n',
+            b"print('\xe2\x82\xac')\n"
+        )
+        encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+        self.assertEqual(encoding, 'iso8859-15')
+        expected = [b'\n', b'# vim: set fileencoding=iso8859-15 :\n']
+        self.assertEqual(consumed_lines, expected)
+
     def test_latin1_normalization(self):
         # See get_normal_name() in tokenizer.c.
         encodings = ("latin-1", "iso-8859-1", "iso-latin-1", "latin-1-unix",