summaryrefslogtreecommitdiffstats
path: root/Tools/cases_generator/parser.py
blob: f603bc6a9868e16fd0aa4b7958b752c229092cdf (plain)
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
"""Parser for bytecodes.inst."""

from dataclasses import dataclass, field
from typing import NamedTuple, Callable, TypeVar

import lexer as lx
from plexer import PLexer


P = TypeVar("P", bound="Parser")
N = TypeVar("N", bound="Node")
def contextual(func: Callable[[P], N|None]) -> Callable[[P], N|None]:
    # Decorator to wrap grammar methods.
    # Resets position if `func` returns None.
    def contextual_wrapper(self: P) -> N|None:
        begin = self.getpos()
        res = func(self)
        if res is None:
            self.setpos(begin)
            return
        end = self.getpos()
        res.context = Context(begin, end, self)
        return res
    return contextual_wrapper


class Context(NamedTuple):
    begin: int
    end: int
    owner: PLexer

    def __repr__(self):
        return f"<{self.begin}-{self.end}>"


@dataclass
class Node:
    context: Context|None = field(init=False, default=None)

    @property
    def text(self) -> str:
        return self.to_text()

    def to_text(self, dedent: int = 0) -> str:
        context = self.context
        if not context:
            return ""
        tokens = context.owner.tokens
        begin = context.begin
        end = context.end
        return lx.to_text(tokens[begin:end], dedent)


@dataclass
class Block(Node):
    tokens: list[lx.Token]


@dataclass
class InstDef(Node):
    name: str
    inputs: list[str] | None
    outputs: list[str] | None
    block: Block | None


@dataclass
class Super(Node):
    name: str
    ops: list[str]


@dataclass
class Family(Node):
    name: str
    members: list[str]


class Parser(PLexer):

    @contextual
    def inst_def(self) -> InstDef | None:
        if header := self.inst_header():
            if block := self.block():
                header.block = block
                return header
            raise self.make_syntax_error("Expected block")
        return None

    @contextual
    def inst_header(self):
        # inst(NAME) | inst(NAME, (inputs -- outputs))
        # TODO: Error out when there is something unexpected.
        # TODO: Make INST a keyword in the lexer.
        if (tkn := self.expect(lx.IDENTIFIER)) and tkn.text == "inst":
            if (self.expect(lx.LPAREN)
                    and (tkn := self.expect(lx.IDENTIFIER))):
                name = tkn.text
                if self.expect(lx.COMMA):
                    inp, outp = self.stack_effect()
                    if (self.expect(lx.RPAREN)
                            and self.peek().kind == lx.LBRACE):
                        return InstDef(name, inp, outp, [])
                elif self.expect(lx.RPAREN):
                    return InstDef(name, None, None, [])
        return None

    def stack_effect(self):
        # '(' [inputs] '--' [outputs] ')'
        if self.expect(lx.LPAREN):
            inp = self.inputs() or []
            if self.expect(lx.MINUSMINUS):
                outp = self.outputs() or []
                if self.expect(lx.RPAREN):
                    return inp, outp
        raise self.make_syntax_error("Expected stack effect")

    def inputs(self):
        # input (, input)*
        here = self.getpos()
        if inp := self.input():
            near = self.getpos()
            if self.expect(lx.COMMA):
                if rest := self.inputs():
                    return [inp] + rest
            self.setpos(near)
            return [inp]
        self.setpos(here)
        return None

    def input(self):
        # IDENTIFIER
        if (tkn := self.expect(lx.IDENTIFIER)):
            if self.expect(lx.LBRACKET):
                if arg := self.expect(lx.IDENTIFIER):
                    if self.expect(lx.RBRACKET):
                        return f"{tkn.text}[{arg.text}]"
                    if self.expect(lx.TIMES):
                        if num := self.expect(lx.NUMBER):
                            if self.expect(lx.RBRACKET):
                                return f"{tkn.text}[{arg.text}*{num.text}]"
                raise self.make_syntax_error("Expected argument in brackets", tkn)

            return tkn.text
        if self.expect(lx.CONDOP):
            while self.expect(lx.CONDOP):
                pass
            return "??"
        return None

    def outputs(self):
        # output (, output)*
        here = self.getpos()
        if outp := self.output():
            near = self.getpos()
            if self.expect(lx.COMMA):
                if rest := self.outputs():
                    return [outp] + rest
            self.setpos(near)
            return [outp]
        self.setpos(here)
        return None

    def output(self):
        return self.input()  # TODO: They're not quite the same.

    @contextual
    def super_def(self) -> Super | None:
        if (tkn := self.expect(lx.IDENTIFIER)) and tkn.text == "super":
            if self.expect(lx.LPAREN):
                if (tkn := self.expect(lx.IDENTIFIER)):
                    if self.expect(lx.RPAREN):
                        if self.expect(lx.EQUALS):
                            if ops := self.ops():
                                res = Super(tkn.text, ops)
                                return res

    def ops(self) -> list[str] | None:
        here = self.getpos()
        if tkn := self.expect(lx.IDENTIFIER):
            ops = [tkn.text]
            while self.expect(lx.PLUS):
                if tkn := self.require(lx.IDENTIFIER):
                    ops.append(tkn.text)
            self.require(lx.SEMI)
            return ops

    @contextual
    def family_def(self) -> Family | None:
        if (tkn := self.expect(lx.IDENTIFIER)) and tkn.text == "family":
            if self.expect(lx.LPAREN):
                if (tkn := self.expect(lx.IDENTIFIER)):
                    if self.expect(lx.RPAREN):
                        if self.expect(lx.EQUALS):
                            if members := self.members():
                                if self.expect(lx.SEMI):
                                    return Family(tkn.text, members)
        return None

    def members(self):
        here = self.getpos()
        if tkn := self.expect(lx.IDENTIFIER):
            near = self.getpos()
            if self.expect(lx.COMMA):
                if rest := self.members():
                    return [tkn.text] + rest
            self.setpos(near)
            return [tkn.text]
        self.setpos(here)
        return None

    @contextual
    def block(self) -> Block:
        tokens = self.c_blob()
        return Block(tokens)

    def c_blob(self):
        tokens = []
        level = 0
        while tkn := self.next(raw=True):
            if tkn.kind in (lx.LBRACE, lx.LPAREN, lx.LBRACKET):
                level += 1
            elif tkn.kind in (lx.RBRACE, lx.RPAREN, lx.RBRACKET):
                level -= 1
                if level <= 0:
                    break
            tokens.append(tkn)
        return tokens


if __name__ == "__main__":
    import sys
    if sys.argv[1:]:
        filename = sys.argv[1]
        if filename == "-c" and sys.argv[2:]:
            src = sys.argv[2]
            filename = None
        else:
            with open(filename) as f:
                src = f.read()
            srclines = src.splitlines()
            begin = srclines.index("// BEGIN BYTECODES //")
            end = srclines.index("// END BYTECODES //")
            src = "\n".join(srclines[begin+1 : end])
    else:
        filename = None
        src = "if (x) { x.foo; // comment\n}"
    parser = Parser(src, filename)
    x = parser.inst_def()
    print(x)