Skip to content

feat: add support for 'a' (ASCII) and 'L' (LOCALE) regex flags #1655

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

Closed
amansri-30 wants to merge 1 commit into from
Closed

feat: add support for 'a' (ASCII) and 'L' (LOCALE) regex flags #1655

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion lark/load_grammar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@

EXT = '.lark'

_RE_FLAGS = 'imslux'
_RE_FLAGS = 'imsluxaL'

_EMPTY = Symbol('__empty__')

Expand Down
7 changes: 7 additions & 0 deletions tests/test_lexer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,13 @@ def test_flag_order_is_deterministic(self):
self.assertEqual([t.pattern.to_regexp() for t in p.terminals],
['(?u:(?s:(?m:(?i:x))))'])

def test_flag_order_with_new_flags(self):
# Test that new flag (a) works and is sorted deterministically
p = Lark('start: A+\nA: /x/ai\n', parser='lalr')
# Flags should be sorted alphabetically: a before i
self.assertEqual([t.pattern.to_regexp() for t in p.terminals],
['(?i:(?a:x))'])

def test_subset_lex(self):
p = Lark("""
start: "a" "b" "c" "d"
Expand Down
8 changes: 8 additions & 0 deletions tests/test_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1808,6 +1808,14 @@ def test_token_flags_verbose_multiline(self):
x = g.parse('abcdef')
self.assertEqual(x.children, ['abcdef'])

def test_token_flags_ascii(self):
# Test the ASCII flag (a) - makes \w, \d, \s ASCII-only
l = _Lark(r"""!start: /\d/a+
""")
# Should match ASCII digits
tree = l.parse('123')
self.assertEqual(tree.children, ['1', '2', '3'])

@unittest.skipIf(PARSER == 'cyk', "No empty rules")
def test_twice_empty(self):
g = """!start: ("A"?)?
Expand Down