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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
import json
import tempfile
import unittest
from pathlib import Path
import tatsu
from tatsu.parser import EBNFBuffer
from tatsu.util import asjson, eval_escapes, trim
class MockIncludeBuffer(EBNFBuffer):
def get_include(self, source, filename):
return f'\nINCLUDED "{filename}"\n', filename
class ParsingTests(unittest.TestCase):
def test_include(self):
text = """\
first
#include :: "something"
last\
"""
buf = MockIncludeBuffer(trim(text))
self.assertEqual('first\n\nINCLUDED "something"\nlast', buf.text)
def test_multiple_include(self):
text = """\
first
#include :: "something"
#include :: "anotherthing"
last\
"""
buf = MockIncludeBuffer(trim(text))
self.assertEqual(
'first\n\nINCLUDED "something"\n\nINCLUDED "anotherthing"\nlast',
buf.text,
)
def test_real_include(self):
_, include_a = tempfile.mkstemp(suffix='.ebnf', prefix='include_')
_, include_b = tempfile.mkstemp(suffix='.ebnf', prefix='include_')
grammar = """\
#include :: "{include_a}"
#include :: "{include_b}"
start = a b;"""
with Path(include_a).open('w') as fh:
fh.write("a = 'inclusion';")
with Path(include_b).open('w') as fh:
fh.write("b = 'works';")
model = tatsu.compile(
grammar=grammar.format(include_a=include_a, include_b=include_b),
)
self.assertIsNotNone(model)
def test_escape_sequences(self):
self.assertEqual('\n', eval_escapes(r'\n'))
self.assertEqual(
'this \xeds a test', eval_escapes(r'this \xeds a test'),
)
self.assertEqual('this ís a test', eval_escapes(r'this \xeds a test'))
self.assertEqual('\nañez', eval_escapes(r'\na\xf1ez'))
self.assertEqual('\nañez', eval_escapes(r'\nañez'))
def test_start(self):
grammar = """
@@grammar :: Test
true = "test" @:`True` $;
false = "test" @:`False` $;
"""
model = tatsu.compile(grammar=grammar)
self.assertEqual('Test', model.directives.get('grammar'))
self.assertEqual('Test', model.name)
# By default, parsing starts from the first rule in the grammar.
ast = model.parse('test')
self.assertEqual(ast, True)
# The start rule can be passed explicitly.
ast = model.parse('test', start='true')
self.assertEqual(ast, True)
# Backward compatibility argument name.
ast = model.parse('test', rule_name='true')
self.assertEqual(ast, True)
# The default rule can be overwritten.
ast = tatsu.parse(grammar, 'test', start='false')
self.assertEqual(ast, False)
# Backward compatibility argument name.
ast = tatsu.parse(grammar, 'test', rule_name='false')
self.assertEqual(ast, False)
def test_rule_capitalization(self):
grammar = """
start = ['test' {rulename}] ;
{rulename} = /[a-zA-Z0-9]+/ ;
"""
test_string = 'test 12'
lowercase_rule_names = ['nocaps', 'camelCase', 'tEST']
uppercase_rule_names = ['Capitalized', 'CamelCase', 'TEST']
ref_lowercase_result = tatsu.parse(
grammar.format(rulename='reflowercase'), test_string,
)
ref_uppercase_result = tatsu.parse(
grammar.format(rulename='Refuppercase'), test_string,
)
for rulename in lowercase_rule_names:
result = tatsu.parse(
grammar.format(rulename=rulename), test_string,
)
self.assertEqual(result, ref_lowercase_result)
for rulename in uppercase_rule_names:
result = tatsu.parse(
grammar.format(rulename=rulename), test_string,
)
self.assertEqual(result, ref_uppercase_result)
def test_startrule_issue62(self):
grammar = """
@@grammar::TEST
file_input = expr $ ;
expr = number '+' number ;
number = /[0-9]/ ;
"""
model = tatsu.compile(grammar=grammar)
model.parse('4 + 5')
def test_skip_whitespace(self):
grammar = """
statement = 'FOO' subject $ ;
subject = name:id ;
id = /[a-z]+/ ;
"""
model = tatsu.compile(grammar=grammar)
ast = model.parse('FOO' + ' ' * 3 + 'bar', parseinfo=True)
print(json.dumps(asjson(ast), indent=2))
subject = ast[1]
assert subject['name'] == 'bar'
parseinfo = subject['parseinfo']
assert parseinfo.pos == parseinfo.tokenizer.text.index('bar')
def test_cut_scope(self):
grammar = '''
start =
| one
| two
;
one =
| ~ !() # cut fail
| 'abc';
two = `something` ; # result is the quoted text
'''
ast = tatsu.parse(grammar, 'abc')
assert ast == 'something'
def suite():
return unittest.TestLoader().loadTestsFromTestCase(ParsingTests)
def main():
unittest.TextTestRunner(verbosity=2).run(suite())
if __name__ == '__main__':
main()
|
