96 lines
3.0 KiB
Python
96 lines
3.0 KiB
Python
import pytest
|
|
from core.sheerka.services.SheerkaExecute import ParserInput
|
|
from core.tokenizer import Tokenizer
|
|
|
|
|
|
@pytest.mark.parametrize("text, start, end, expected", [
|
|
("def concept a", None, None, "def concept a"),
|
|
("&é#(-è_çà)='string'", None, None, "&é#(-è_çà)='string'"),
|
|
("def concept a", 2, None, "concept a"),
|
|
("def concept a", 0, 2, "def concept"),
|
|
])
|
|
def test_i_can_use_parser_input(text, start, end, expected):
|
|
parser_input = ParserInput(text, start=start, end=end).reset()
|
|
assert parser_input.as_text() == expected
|
|
|
|
|
|
def test_i_can_get_the_next_token():
|
|
parser_input = ParserInput("def concept a from bnf 'xyz' as 'xyz'").reset()
|
|
res = []
|
|
while parser_input.next_token():
|
|
res.append(f"{parser_input.token.str_value}")
|
|
|
|
assert res == ['def', 'concept', 'a', 'from', 'bnf', "'xyz'", 'as', "'xyz'", '']
|
|
|
|
parser_input = ParserInput("def concept a concept name from bnf 'xyz' as 'xyz'", start=4, end=9).reset()
|
|
res = []
|
|
while parser_input.next_token(skip_whitespace=False):
|
|
res.append(f"{parser_input.token.str_value}")
|
|
|
|
assert res == ['a', ' ', 'concept', ' ', 'name', ' ']
|
|
|
|
|
|
def test_i_can_get_the_next_token_when_initialised_with_tokens():
|
|
tokens = list(Tokenizer(" def concept a as 'xyz' "))
|
|
parser_input = ParserInput(" def concept a as 'xyz' ", tokens).reset()
|
|
res = []
|
|
while parser_input.next_token():
|
|
res.append(f"{parser_input.token.str_value}")
|
|
|
|
assert res == ['def', 'concept', 'a', 'as', "'xyz'", '']
|
|
|
|
tokens = list(Tokenizer(" def concept a as 'xyz' ", yield_eof=False))
|
|
parser_input = ParserInput(" def concept a as 'xyz' ", tokens).reset()
|
|
res = []
|
|
while parser_input.next_token():
|
|
res.append(f"{parser_input.token.str_value}")
|
|
|
|
assert res == ['def', 'concept', 'a', 'as', "'xyz'"]
|
|
|
|
|
|
def test_i_can_parse_twice():
|
|
text = """
|
|
def concept a + b
|
|
where isinstance(a, int) and isinstance(b, int)
|
|
pre isinstance(a, int) and isinstance(b, int)
|
|
post isinstance(res, int)
|
|
as:
|
|
def func(x,y):
|
|
return x+y
|
|
func(a,b)
|
|
"""
|
|
|
|
p1 = ParserInput(text).reset()
|
|
while p1.next_token():
|
|
pass
|
|
|
|
p1.reset()
|
|
p2 = ParserInput(text).reset()
|
|
|
|
while p1.next_token():
|
|
p2.next_token()
|
|
assert p1.token == p2.token
|
|
|
|
p1.reset()
|
|
p2 = ParserInput(text).reset()
|
|
|
|
while p2.next_token():
|
|
p1.next_token()
|
|
assert p1.token == p2.token
|
|
|
|
|
|
@pytest.mark.parametrize("text, skip_whitespace, expected", [
|
|
("first second", True, "second"),
|
|
("first second", False, "<ws>"),
|
|
("first", True, "<EOF>"),
|
|
("first", False, "<EOF>"),
|
|
("first ", True, "<EOF>"),
|
|
("first ", False, "<ws>"),
|
|
("first:", True, ":"),
|
|
("first:", False, ":"),
|
|
])
|
|
def test_i_can_get_the_token_after(text, skip_whitespace, expected):
|
|
parser_input = ParserInput(text).reset()
|
|
parser_input.next_token()
|
|
assert parser_input.the_token_after(skip_whitespace).repr_value == expected
|