From b6bde9fc42aecad5be0457198d17cfe7b481ad79 Mon Sep 17 00:00:00 2001 From: Pablo Galindo Salgado Date: Sat, 31 Jul 2021 02:17:09 +0100 Subject: bpo-44667: Treat correctly lines ending with comments and no newlines in the Python tokenizer (GH-27499) --- Lib/test/test_tokenize.py | 10 ++++++++++ Lib/tokenize.py | 2 +- .../next/Library/2021-07-30-23-27-30.bpo-44667.tu0Xrv.rst | 4 ++++ 3 files changed, 15 insertions(+), 1 deletion(-) create mode 100644 Misc/NEWS.d/next/Library/2021-07-30-23-27-30.bpo-44667.tu0Xrv.rst diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py index 681f2c7..4bce1ca 100644 --- a/Lib/test/test_tokenize.py +++ b/Lib/test/test_tokenize.py @@ -1458,6 +1458,16 @@ class TestTokenize(TestCase): # See http://bugs.python.org/issue16152 self.assertExactTypeEqual('@ ', token.AT) + def test_comment_at_the_end_of_the_source_without_newline(self): + # See http://bugs.python.org/issue44667 + source = 'b = 1\n\n#test' + expected_tokens = [token.NAME, token.EQUAL, token.NUMBER, token.NEWLINE, token.NL, token.COMMENT] + + tokens = list(tokenize(BytesIO(source.encode('utf-8')).readline)) + self.assertEqual(tok_name[tokens[0].exact_type], tok_name[ENCODING]) + for i in range(6): + self.assertEqual(tok_name[tokens[i + 1].exact_type], tok_name[expected_tokens[i]]) + self.assertEqual(tok_name[tokens[-1].exact_type], tok_name[token.ENDMARKER]) class UntokenizeTest(TestCase): diff --git a/Lib/tokenize.py b/Lib/tokenize.py index 42c1f10..7d7736f 100644 --- a/Lib/tokenize.py +++ b/Lib/tokenize.py @@ -604,7 +604,7 @@ def _tokenize(readline, encoding): pos += 1 # Add an implicit NEWLINE if the input doesn't end in one - if last_line and last_line[-1] not in '\r\n': + if last_line and last_line[-1] not in '\r\n' and not last_line.strip().startswith("#"): yield TokenInfo(NEWLINE, '', (lnum - 1, len(last_line)), (lnum - 1, len(last_line) + 1), '') for indent in indents[1:]: # pop remaining indent levels yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '') diff --git a/Misc/NEWS.d/next/Library/2021-07-30-23-27-30.bpo-44667.tu0Xrv.rst b/Misc/NEWS.d/next/Library/2021-07-30-23-27-30.bpo-44667.tu0Xrv.rst new file mode 100644 index 0000000..5b7e20e --- /dev/null +++ b/Misc/NEWS.d/next/Library/2021-07-30-23-27-30.bpo-44667.tu0Xrv.rst @@ -0,0 +1,4 @@ +The :func:`tokenize.tokenize` doesn't incorrectly generate a ``NEWLINE`` +token if the source doesn't end with a new line character but the last line +is a comment, as the function is already generating a ``NL`` token. Patch by +Pablo Galindo -- cgit v0.12