Skip to content

gh-105549: Tokenize separately NUMBER and NAME tokens and allow 0-prefixed literals #105555

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pablogsal merged 2 commits into from
Jun 9, 2023
Merged

gh-105549: Tokenize separately NUMBER and NAME tokens and allow 0-prefixed literals #105555

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
93ee708
gh-105549: Tokenize separately NUMBER and NAME tokens
pablogsal Jun 9, 2023
558552a
Allow 0-prefixed underscore literals
pablogsal Jun 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Allow 0-prefixed underscore literals 
Signed-off-by: Pablo Galindo <pablogsal@gmail.com>
  • Loading branch information
@pablogsal
pablogsal committed Jun 9, 2023
commit 558552ae0e9b6610a25de87072c0dd416e9b3a1e
33 changes: 33 additions & 0 deletions Lib/test/test_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,7 +284,12 @@ def number_token(s):
# this won't work with compound complex inputs
continue
self.assertEqual(number_token(lit), lit)
# Valid cases with extra underscores in the tokenize module
# See gh-105549 for context
extra_valid_cases = {"0_7", "09_99"}
for lit in INVALID_UNDERSCORE_LITERALS:
if lit in extra_valid_cases:
continue
try:
number_token(lit)
except TokenError:
Expand Down Expand Up @@ -1873,6 +1878,34 @@ def test_indentation_semantics_retained(self):
self.check_roundtrip(code)


class InvalidPythonTests(TestCase):
def test_number_followed_by_name(self):
# See issue #gh-105549
source = "2sin(x)"
expected_tokens = [
TokenInfo(type=token.NUMBER, string='2', start=(1, 0), end=(1, 1), line='2sin(x)'),
TokenInfo(type=token.NAME, string='sin', start=(1, 1), end=(1, 4), line='2sin(x)'),
TokenInfo(type=token.OP, string='(', start=(1, 4), end=(1, 5), line='2sin(x)'),
TokenInfo(type=token.NAME, string='x', start=(1, 5), end=(1, 6), line='2sin(x)'),
TokenInfo(type=token.OP, string=')', start=(1, 6), end=(1, 7), line='2sin(x)'),
TokenInfo(type=token.NEWLINE, string='', start=(1, 7), end=(1, 8), line='2sin(x)'),
TokenInfo(type=token.ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
]

tokens = list(generate_tokens(StringIO(source).readline))
self.assertEqual(tokens, expected_tokens)

def test_number_starting_with_zero(self):
source = "01234"
expected_tokens = [
TokenInfo(type=token.NUMBER, string='01234', start=(1, 0), end=(1, 5), line='01234'),
TokenInfo(type=token.NEWLINE, string='', start=(1, 5), end=(1, 6), line='01234'),
TokenInfo(type=token.ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
]

tokens = list(generate_tokens(StringIO(source).readline))
self.assertEqual(tokens, expected_tokens)

class CTokenizeTest(TestCase):
def check_tokenize(self, s, expected):
# Format the tokens in s in a table format.
Expand Down
2 changes: 1 addition & 1 deletion Parser/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2325,7 +2325,7 @@ tok_get_normal_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct t
else if (c == 'j' || c == 'J') {
goto imaginary;
}
else if (nonzero) {
else if (nonzero && !tok->tok_extra_tokens) {
/* Old-style octal: now disallowed. */
tok_backup(tok, c);
return MAKE_TOKEN(syntaxerror_known_range(
Expand Down