Skip to content

gh-149277: Fix error position for invalid numeric literals #155534

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

Open
skirpichev wants to merge 3 commits into
base: main
Choose a base branch
from
Open

gh-149277: Fix error position for invalid numeric literals #155534

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7fb8fb6
gh-149277: Fix error position for invalid numeric literals
skirpichev Aug 11, 2026
8f4bb35
Merge branch 'master' into better-lit-errors/149277
skirpichev Aug 11, 2026
105d36c
+1
skirpichev Aug 11, 2026
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
10 changes: 5 additions & 5 deletions Lib/test/test_exceptions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -279,14 +279,14 @@ def testSyntaxErrorOffset(self):
check('try:\n pass\nexcept*:\n pass\nexcept* ValueError:\n pass', 3, 8)

# Errors thrown by the tokenizer
check('(0x+1)', 1, 3)
check('x = 0xI', 1, 6)
check('(0x+1)', 1, 4)
check('x = 0xI', 1, 7)
check('0010 + 2', 1, 1)
check('x = 32e-+4', 1, 8)
check('x = 0o9', 1, 7)
check('\u03b1 = 0xI', 1, 6)
check(b'\xce\xb1 = 0xI', 1, 6)
check(b'# -*- coding: iso8859-7 -*-\n\xe1 = 0xI', 2, 6,
check('\u03b1 = 0xI', 1, 7)
check(b'\xce\xb1 = 0xI', 1, 7)
check(b'# -*- coding: iso8859-7 -*-\n\xe1 = 0xI', 2, 7,
encoding='iso8859-7')
check(b"""if 1:
def foo():
Expand Down
22 changes: 22 additions & 0 deletions Lib/test/test_grammar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
import_helper,
skip_emscripten_stack_overflow,
skip_wasi_stack_overflow,
subTests,
)
from test.support.numbers import (
VALID_UNDERSCORE_LITERALS,
Expand Down Expand Up @@ -180,6 +181,27 @@ def check(test, error=False):
check("[0x1for x in ()]")
check("[0xfor x in ()]")

@subTests('source,offset,msg',
[("0xfg", 4, "hexadecimal"),
("0x9g", 4, "hexadecimal"),
("0b1z", 4, "binary"),
("0o7q", 4, "octal"),
("9spam", 2, " decimal"),
("0xfspam", 4, "hexadecimal"),
("1.0x", 4, " decimal"),
("1e3w", 4, " decimal"),
("1jz", 3, "imaginary"),
("0xI", 3, "hexadecimal"),
("0bz", 3, "binary"),
])
def test_end_of_numerical_literals_offset(self, source, offset, msg):
# gh-149277: verify the error caret points at the first invalid
# character, not the last valid digit.
with self.assertRaises(SyntaxError) as cm:
compile(source, "<test>", "eval")
self.assertEqual(cm.exception.offset, offset)
self.assertIn(msg, cm.exception.msg)

def test_string_literals(self):
x = ''; y = ""; self.assertTrue(len(x) == 0 and x == y)
x = '\''; y = "'"; self.assertTrue(len(x) == 1 and x == y and ord(x) == 39)
Expand Down
2 changes: 1 addition & 1 deletion Lib/test/test_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2277,7 +2277,7 @@ def test_extra_tokens_relaxes_lexer_errors(self):
cases = [
(
"2sin(x)",
("invalid decimal literal", (1, 1)),
("invalid decimal literal", (1, 2)),
[
(token.NUMBER, "2", (1, 0), (1, 1)),
(token.NAME, "sin", (1, 1), (1, 4)),
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Core_and_Builtins/2026-08-11-08-16-20.gh-issue-149277.dYRtaF.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fix the :exc:`SyntaxError` caret position for invalid numeric literals to
point at the first invalid character.
4 changes: 0 additions & 4 deletions Parser/lexer/number.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,6 @@ verify_end_of_number(struct tok_state *tok, int c, const char *kind) {
}
else /* In future releases, only error will remain. */
if (c < 128 && is_potential_identifier_char(c)) {
tok_backup(tok, c);
_PyTokenizer_syntaxerror(tok, "invalid %s literal", kind);
return 0;
}
Expand Down Expand Up @@ -130,7 +129,6 @@ _PyLexer_scan_number(struct tok_state *tok, struct token *token, int c,
c = tok_nextc(tok);
}
if (!Py_ISXDIGIT(c)) {
tok_backup(tok, c);
return MAKE_TOKEN(_PyTokenizer_syntaxerror(tok, "invalid hexadecimal literal"));
}
do {
Expand All @@ -154,7 +152,6 @@ _PyLexer_scan_number(struct tok_state *tok, struct token *token, int c,
"invalid digit '%c' in octal literal", c));
}
else {
tok_backup(tok, c);
return MAKE_TOKEN(_PyTokenizer_syntaxerror(tok, "invalid octal literal"));
}
}
Expand Down Expand Up @@ -182,7 +179,6 @@ _PyLexer_scan_number(struct tok_state *tok, struct token *token, int c,
return MAKE_TOKEN(_PyTokenizer_syntaxerror(tok, "invalid digit '%c' in binary literal", c));
}
else {
tok_backup(tok, c);
return MAKE_TOKEN(_PyTokenizer_syntaxerror(tok, "invalid binary literal"));
}
}
Expand Down
Loading