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
198
199
200
201
202
203
204
205
206
207
208
|
# Copyright (c) 2017-2026 Juancarlo Añez (apalala@gmail.com)
# SPDX-License-Identifier: BSD-4-Clause
"""
Parse and translate a TatSu grammar into a Python parser for
the described language.
"""
from __future__ import annotations
from collections.abc import Callable
from typing import Any
from .. import grammars
from ..builder import BuilderConfig, Constructor, ModelBuilderSemantics, TypeContainer
from ..exceptions import ParseException
from ..infos import ParserConfig
from ..ngcodegen.walkgen_model import modelgen
from ..ngcodegen.walkgen_parser import pythongen
from ..objectmodel import Node
from ..parser import TatSuParserGenerator
from ..tokenizing import Tokenizer
from ..util.string import hashsha
__all__ = [
'compile',
'gencode',
'genmodel',
'grammars',
'modelgen',
'parse',
'pythongen',
'to_python_model',
'to_python_sourcecode',
]
__compiled_grammar_cache = {}
def compile(
grammar: str | Tokenizer,
name: str | None = None,
*,
config: ParserConfig | None = None,
filename: str | None = None,
basetype: type | None = None,
semantics: Any = None,
asmodel: bool = False,
builderconfig: BuilderConfig | None = None,
synthok: bool = True,
typedefs: list[TypeContainer] | None = None,
constructors: list[Constructor] | None = None,
**settings: Any,
) -> grammars.Grammar:
# check parameters
ParserConfig.new(
config=config,
semantics=semantics,
name=name,
filename=filename,
**settings,
)
if isinstance(semantics, type):
raise TypeError(
f'semantics must be an object instance or None, not class {semantics!r}',
)
cache = __compiled_grammar_cache
key = (name, hashsha(grammar), id(semantics))
if key in cache:
model = cache[key]
else:
gen = TatSuParserGenerator(name, **settings)
model = cache[key] = gen.parse(grammar, **settings)
asmodel = not semantics and (
asmodel
or isinstance(builderconfig, BuilderConfig)
or basetype is not None
or typedefs is not None
or constructors is not None
)
if semantics is not None:
model.semantics = semantics
elif asmodel:
# HACK: cheating, but necessary for bw-compatibility
builderconfig = BuilderConfig.new(
config=builderconfig,
synthok=synthok,
basetype=basetype,
typedefs=typedefs,
constructors=constructors,
)
model.semantics = ModelBuilderSemantics(config=builderconfig)
return model
def parse(
grammar: str,
text: str,
/,
*,
config: ParserConfig | None = None,
start: str | None = None,
name: str | None = None,
filename: str | None = None,
semantics: Any | None = None,
asmodel: bool = False,
builderconfig: BuilderConfig | None = None,
basetype: type | None = None,
synthok: bool = True,
typedefs: list[TypeContainer] | None = None,
constructors: list[Constructor] | None = None,
**settings: Any,
):
config = ParserConfig.new(
config=config,
start=start,
name=name,
filename=filename,
semantics=semantics,
**settings,
)
model = compile(grammar, config=config, asmodel=asmodel)
config.semantics = semantics or model.semantics
asmodel = not config.semantics and (
asmodel
or isinstance(builderconfig, BuilderConfig)
or basetype is not None
or typedefs is not None
or constructors is not None
)
if asmodel:
builderconfig = BuilderConfig.new(
config=builderconfig,
synthok=synthok,
basetype=basetype,
typedefs=typedefs,
constructors=constructors,
)
config.semantics = ModelBuilderSemantics(config=builderconfig)
return model.parse(text, start=start, semantics=semantics, config=config)
def to_python_sourcecode(
grammar: str,
/,
*,
name: str | None = None,
filename: str | None = None,
config: ParserConfig | None = None,
**settings: Any,
):
config = ParserConfig.new(config=config, name=name, filename=filename, **settings)
model = compile(grammar, name=name, filename=filename, config=config)
return pythongen(model)
def to_python_model(
grammar: str,
/,
*,
name: str | None = None,
filename: str | None = None,
basetype: type = Node,
config: ParserConfig | None = None,
**settings: Any,
):
config = ParserConfig.new(config=config, name=name, filename=filename, **settings)
model = compile(grammar, name=name, filename=filename, config=config)
return modelgen(model, basetype=basetype)
# for backwards compatibility. Use `compile()` instead
def genmodel(
*,
name: str | None = None,
grammar: str | None = None,
semantics: type | None = None,
config: ParserConfig | None = None,
**settings: Any,
):
if grammar is None:
raise ParseException('grammar is None')
return compile(grammar, name=name, semantics=semantics, config=config, **settings)
def gencode(
*,
name: str | None = None,
grammar: str,
trace: bool = False,
filename: str | None = None,
codegen: Callable = pythongen,
config: ParserConfig | None = None,
**settings: Any,
):
model = compile(
grammar,
name=name,
filename=filename,
trace=trace,
config=config,
**settings,
)
return codegen(model)
|
