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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
|
from __future__ import annotations
import re
from itertools import chain
from tatsu import grammars as model
from tatsu.ast import AST
def camel2py(name):
return re.sub(
r'([a-z0-9])([A-Z])',
lambda m: m.group(1) + '_' + m.group(2).lower(),
name,
)
class ANTLRSemantics:
def __init__(self, name):
self.name = name
self.tokens = {}
self.token_rules = {}
self.synthetic_rules = []
def grammar(self, ast):
return model.Grammar(
self.name,
[
r
for r in chain(ast.rules, self.synthetic_rules)
if r is not None
],
)
def rule(self, ast):
name = camel2py(ast.name)
exp = ast.exp
if name[0].isupper():
name = name.upper()
if isinstance(exp, model.Token):
if name in self.token_rules:
self.token_rules[
name
].exp = exp # it is a model._Decorator
else:
self.token_rules[name] = exp
return None
elif not ast.fragment and not isinstance(exp, model.Sequence):
ref = model.RuleRef(name.lower())
if name in self.token_rules:
self.token_rules[name].exp = ref
else:
self.token_rules[name] = ref
name = name.lower()
return model.Rule(ast, name, exp, ast.params, ast.kwparams)
def alternatives(self, ast):
options = [o for o in ast.options if o is not None]
if len(options) == 1:
return options[0]
else:
options = [model.Option(o) for o in options]
return model.Choice(options)
def elements(self, ast):
elements = [e for e in ast if e is not None]
if not elements:
return model.Void()
elif len(elements) == 1:
return elements[0]
else:
return model.Sequence(AST(sequence=elements))
def predicate_or_action(self, ast):
return None
def named(self, ast):
if ast.force_list:
return model.NamedList(ast)
else:
return model.Named(ast)
def syntactic_predicate(self, ast):
return None
def optional(self, ast):
if isinstance(ast, model.Group | model.Optional | model.Closure):
ast = ast.exp
return model.Optional(ast)
def closure(self, ast):
if isinstance(ast, model.Group | model.Optional):
ast = ast.exp
return model.Closure(ast)
def positive_closure(self, ast):
if isinstance(ast, model.Group):
ast = ast.exp
return model.PositiveClosure(ast)
def negative(self, ast):
neg = model.NegativeLookahead(ast)
any = model.Pattern('.')
return model.Sequence(AST(sequence=[neg, any]))
def subexp(self, ast):
return model.Group(ast)
def regexp(self, ast):
pattern = ''.join(ast)
re.compile(pattern)
return model.Pattern(pattern)
def charset_optional(self, ast):
return f'{ast}?'
def charset_closure(self, ast):
return f'{ast}*'
def charset_positive_closure(self, ast):
return f'{ast}+'
def charset_or(self, ast):
return '[{}]'.format(''.join(ast))
def charset_negative_or(self, ast):
return '[^{}]'.format(''.join(ast))
@staticmethod
def escape(s):
return ''.join('\\' + c if c in '[]().*+{}^$' else c for c in s)
def charset_atom(self, ast):
return ast
def charset_char(self, ast):
return ast
def charset_range(self, ast):
return f'{ast.first}-{ast.last}'
def newranges(self, ast):
pattern = ''.join(ast)
re.compile(pattern)
return model.Pattern(pattern)
def newrange(self, ast):
pattern = '[{}]{}'.format(ast.range, ast.repeat or '')
re.compile(pattern)
return pattern
def negative_newrange(self, ast):
pattern = '[^{}]{}'.format(ast.range, ast.repeat or '')
re.compile(pattern)
return pattern
def rule_ref(self, ast):
assert ast[0].islower()
return model.RuleRef(camel2py(ast))
def any(self, ast):
return model.Pattern(r'\w+|\S+')
def string(self, ast):
text = ast
if isinstance(text, list):
text = ''.join(text)
return model.Token(text)
def eof(self, ast):
return model.EOF()
def token(self, ast):
name = ast.name
if ast.value:
exp = model.Token(ast.value)
self.tokens[name] = exp
else:
exp = model.Fail()
rule = model.Rule(ast, name, exp, [], {})
self.synthetic_rules.append(rule)
return exp
def token_ref(self, ast):
name = camel2py(ast).upper()
value = self.tokens.get(name)
if value and isinstance(value, model.Model):
return value
if name in self.token_rules:
exp = self.token_rules[name]
else:
exp = model.Decorator(model.RuleRef(name))
self.token_rules[name] = exp
return exp
|
