lark/examples/json_parser.py

#
# This example shows how to write a basic JSON parser
#
# The code is short and clear, and outperforms every other parser (that's written in Python).
# For an explanation, check out the JSON parser tutorial at /docs/json_tutorial.md
#

import sys

from lark import Lark, Transformer, v_args

json_grammar = r"""
    ?start: value

    ?value: object
          | array
          | string
          | SIGNED_NUMBER      -> number
          | "true"             -> true
          | "false"            -> false
          | "null"             -> null

    array  : "[" [value ("," value)*] "]"
    object : "{" [pair ("," pair)*] "}"
    pair   : string ":" value

    string : ESCAPED_STRING

    %import common.ESCAPED_STRING
    %import common.SIGNED_NUMBER
    %import common.WS

    %ignore WS
"""

class TreeToJson(Transformer):
    @v_args(inline=True)
    def string(self, s):
        return s[1:-1].replace('\\"', '"')

    array = list
    pair = tuple
    object = dict
    number = v_args(inline=True)(float)

    null = lambda self, _: None
    true = lambda self, _: True
    false = lambda self, _: False

# json_parser = Lark(json_grammar, parser='earley', lexer='standard')
# def parse(x):
#     return TreeToJson().transform(json_parser.parse(x))

json_parser = Lark(json_grammar, parser='lalr', lexer='standard', transformer=TreeToJson())
parse = json_parser.parse

def test():
    test_json = '''
        {
            "empty_object" : {},
            "empty_array"  : [],
            "booleans"     : { "YES" : true, "NO" : false },
            "numbers"      : [ 0, 1, -2, 3.3, 4.4e5, 6.6e-7 ],
            "strings"      : [ "This", [ "And" , "That", "And a \\"b" ] ],
            "nothing"      : null
        }
    '''

    j = parse(test_json)
    print(j)
    import json
    assert j == json.loads(test_json)

if __name__ == '__main__':
    # test()
    with open(sys.argv[1]) as f:
        print(parse(f.read()))