Note
Go to the end to download the full example code
Parsing Indentation
A demonstration of parsing indentation (“whitespace significant” language) and the usage of the Indenter class.
Since indentation is context-sensitive, a postlex stage is introduced to manufacture INDENT/DEDENT tokens.
It is crucial for the indenter that the NL_type matches the spaces (and tabs) after the newline.
from lark import Lark
from lark.indenter import Indenter
tree_grammar = r"""
?start: _NL* tree
tree: NAME _NL [_INDENT tree+ _DEDENT]
%import common.CNAME -> NAME
%import common.WS_INLINE
%declare _INDENT _DEDENT
%ignore WS_INLINE
_NL: /(\r?\n[\t ]*)+/
"""
class TreeIndenter(Indenter):
NL_type = '_NL'
OPEN_PAREN_types = []
CLOSE_PAREN_types = []
INDENT_type = '_INDENT'
DEDENT_type = '_DEDENT'
tab_len = 8
parser = Lark(tree_grammar, parser='lalr', postlex=TreeIndenter())
test_tree = """
a
b
c
d
e
f
g
"""
def test():
print(parser.parse(test_tree).pretty())
if __name__ == '__main__':
test()
Total running time of the script: (0 minutes 0.000 seconds)