1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
import unittest
from tatsu.exceptions import FailedParse
from tatsu.ngcodegen import codegen
from tatsu.tool import compile
from tatsu.util import trim
class PatternTests(unittest.TestCase):
def test_patterns_with_newlines(self):
grammar = """
@@whitespace :: /[ \t]/
start
=
blanklines $
;
blanklines
=
blankline [blanklines]
;
blankline
=
/(?m)^[^\\n]*\\n$/
;
"""
model = compile(grammar, 'test')
ast = model.parse('\n\n')
self.assertEqual(('\n', '\n'), ast)
def test_pattern_concatenation(self):
grammar = """
start
=
{letters_digits}+
;
letters_digits
=
?"[a-z]+"
+ ?'[0-9]+'
;
"""
pretty = """
start
=
{letters_digits}+
;
letters_digits
=
/[a-z]+/
+ /[0-9]+/
;
"""
model = compile(grammar=grammar)
ast = model.parse('abc123 def456')
self.assertEqual(['abc123', 'def456'], ast)
print(model.pretty())
self.assertEqual(trim(pretty), model.pretty())
def test_ignorecase_not_for_pattern(self):
grammar = """
@@ignorecase
start
=
{word} $
;
word
=
/[a-z]+/
;
"""
model = compile(grammar=grammar)
try:
model.parse('ABcD xYZ')
self.fail('@@ignorecase should not apply to patterns')
except FailedParse:
pass
def test_ignorecase_pattern(self):
grammar = """
start
=
{word} $
;
word
=
/(?i)[a-z]+/
;
"""
model = compile(grammar=grammar)
ast = model.parse('ABcD xYZ')
self.assertEqual(['ABcD', 'xYZ'], ast)
def test_multiline_pattern(self):
grammar = r"""
start =
/(?x)
foo
bar
/ $ ;
"""
model = compile(grammar=trim(grammar))
print(codegen(model.rules[0].exp.sequence[0]))
self.assertEqual(
codegen(model.rules[0].exp.sequence[0]).strip(),
repr("self._pattern('(?x)\nfoo\nbar\n')").strip('"\''),
)
grammar = r"""
start =
/(?x)foo\nbar
blort/ $ ;
"""
model = compile(grammar=trim(grammar))
print(codegen(model.rules[0].exp.sequence[0]))
self.assertEqual(
trim(codegen(model.rules[0].exp.sequence[0])),
repr("self._pattern('(?x)foo\\nbar\nblort')").strip(r'"\.'),
)
|
