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
|
from __future__ import annotations
from collections.abc import Sequence
from . import grammars
from .exceptions import FailedSemantics
from .semantics import ModelBuilderSemantics
from .util import eval_escapes, flatten, re, warning
class EBNFGrammarSemantics(ModelBuilderSemantics):
def __init__(self, grammar_name):
super().__init__(
base_type=grammars.Model, types=grammars.Model.classes(),
)
self.grammar_name = grammar_name
self.rules = {}
def token(self, ast, *args):
token = ast
if not token:
raise FailedSemantics('empty token')
return grammars.Token(token)
def pattern(self, ast, *args):
return grammars.Pattern(ast)
def regexes(self, ast, *args):
pattern = ''.join(ast)
try:
re.compile(pattern)
except (TypeError, re.error) as e:
raise FailedSemantics('regexp error: ' + str(e)) from e
return ast
def regex(self, ast, *args):
pattern = ast
try:
re.compile(pattern)
except (TypeError, re.error) as e:
raise FailedSemantics('regexp error: ' + str(e)) from e
return pattern
def string(self, ast):
return eval_escapes(ast)
def hex(self, ast):
return int(ast, 16)
def float(self, ast):
return float(ast)
def int(self, ast):
return int(ast)
def null(self, ast):
return None
def cut_deprecated(self, ast, *args):
warning(
'The use of >> for cut is deprecated. Use the ~ symbol instead.',
)
return grammars.Cut()
def override_single_deprecated(self, ast, *args):
warning('The use of @ for override is deprecated. Use @: instead')
return grammars.Override(ast)
def sequence(self, ast, *args):
seq = ast.sequence
assert isinstance(seq, Sequence), str(seq)
if len(seq) == 1:
return seq[0]
return grammars.Sequence(ast)
def choice(self, ast, *args):
if len(ast) == 1:
return ast[0]
return grammars.Choice(ast)
def new_name(self, name):
if name in self.rules:
raise FailedSemantics(f'rule "{name!s}" already defined')
return name
def known_name(self, name):
if name not in self.rules:
raise FailedSemantics(f'rule "{name!s}" not yet defined')
return name
def boolean(self, ast):
return str(ast).lower() in {'true', 'yes', 'ok', '1'}
def rule(self, ast, *args):
decorators = ast.decorators
name = ast.name
exp = ast.exp
base = ast.base
params = ast.params
kwparams = dict(ast.kwparams) if ast.kwparams else None
if 'override' not in decorators and name in self.rules:
self.new_name(name)
elif 'override' in decorators:
self.known_name(name)
if not base:
rule = grammars.Rule(
ast, name, exp, params, kwparams, decorators=decorators,
)
else:
self.known_name(base)
base_rule = self.rules[base]
rule = grammars.BasedRule(
ast,
name,
exp,
base_rule,
params,
kwparams,
decorators=decorators,
)
self.rules[name] = rule
return rule
def rule_include(self, ast, *args):
name = str(ast)
self.known_name(name)
rule = self.rules[name]
return grammars.RuleInclude(rule)
def grammar(self, ast, *args):
directives = {d.name: d.value for d in flatten(ast.directives)}
keywords = list(flatten(ast.keywords)) or []
if directives.get('whitespace') in {'None', 'False'}:
# NOTE: use '' because None will _not_ override defaults in configuration
directives['whitespace'] = ''
name = self.grammar_name or directives.get('grammar')
return grammars.Grammar(
name,
list(self.rules.values()),
directives=directives,
keywords=keywords,
)
|
