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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480
|
"""Parser for bytecodes.inst."""
from dataclasses import dataclass, field
from typing import NamedTuple, Callable, TypeVar, Literal, cast
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 None
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) -> str:
return f"<{self.owner.filename}: {self.begin}-{self.end}>"
@dataclass
class Node:
context: Context | None = field(init=False, compare=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 ""
return lx.to_text(self.tokens, dedent)
@property
def tokens(self) -> list[lx.Token]:
context = self.context
if not context:
return []
tokens = context.owner.tokens
begin = context.begin
end = context.end
return tokens[begin:end]
@dataclass
class Block(Node):
# This just holds a context which has the list of tokens.
pass
@dataclass
class StackEffect(Node):
name: str = field(compare=False) # __eq__ only uses type, cond, size
type: str = "" # Optional `:type`
cond: str = "" # Optional `if (cond)`
size: str = "" # Optional `[size]`
# Note: size cannot be combined with type or cond
def __repr__(self) -> str:
items = [self.name, self.type, self.cond, self.size]
while items and items[-1] == "":
del items[-1]
return f"StackEffect({', '.join(repr(item) for item in items)})"
@dataclass
class Expression(Node):
size: str
@dataclass
class CacheEffect(Node):
name: str
size: int
@dataclass
class OpName(Node):
name: str
InputEffect = StackEffect | CacheEffect
OutputEffect = StackEffect
UOp = OpName | CacheEffect
@dataclass
class InstHeader(Node):
annotations: list[str]
kind: Literal["inst", "op"]
name: str
inputs: list[InputEffect]
outputs: list[OutputEffect]
@dataclass
class InstDef(Node):
annotations: list[str]
kind: Literal["inst", "op"]
name: str
inputs: list[InputEffect]
outputs: list[OutputEffect]
block: Block
@dataclass
class Macro(Node):
name: str
uops: list[UOp]
@dataclass
class Family(Node):
name: str
size: str # Variable giving the cache size in code units
members: list[str]
@dataclass
class Pseudo(Node):
name: str
flags: list[str] # instr flags to set on the pseudo instruction
targets: list[str] # opcodes this can be replaced by
AstNode = InstDef | Macro | Pseudo | Family
class Parser(PLexer):
@contextual
def definition(self) -> AstNode | None:
if macro := self.macro_def():
return macro
if family := self.family_def():
return family
if pseudo := self.pseudo_def():
return pseudo
if inst := self.inst_def():
return inst
return None
@contextual
def inst_def(self) -> InstDef | None:
if hdr := self.inst_header():
if block := self.block():
return InstDef(
hdr.annotations,
hdr.kind,
hdr.name,
hdr.inputs,
hdr.outputs,
block,
)
raise self.make_syntax_error("Expected block")
return None
@contextual
def inst_header(self) -> InstHeader | None:
# annotation* inst(NAME, (inputs -- outputs))
# | annotation* op(NAME, (inputs -- outputs))
annotations = []
while anno := self.expect(lx.ANNOTATION):
if anno.text == "replicate":
self.require(lx.LPAREN)
times = self.require(lx.NUMBER)
self.require(lx.RPAREN)
annotations.append(f"replicate({times.text})")
else:
annotations.append(anno.text)
tkn = self.expect(lx.INST)
if not tkn:
tkn = self.expect(lx.OP)
if tkn:
kind = cast(Literal["inst", "op"], tkn.text)
if self.expect(lx.LPAREN) and (tkn := self.expect(lx.IDENTIFIER)):
name = tkn.text
if self.expect(lx.COMMA):
inp, outp = self.io_effect()
if self.expect(lx.RPAREN):
if (tkn := self.peek()) and tkn.kind == lx.LBRACE:
return InstHeader(annotations, kind, name, inp, outp)
return None
def io_effect(self) -> tuple[list[InputEffect], list[OutputEffect]]:
# '(' [inputs] '--' [outputs] ')'
if self.expect(lx.LPAREN):
inputs = self.inputs() or []
if self.expect(lx.MINUSMINUS):
outputs = self.outputs() or []
if self.expect(lx.RPAREN):
return inputs, outputs
raise self.make_syntax_error("Expected stack effect")
def inputs(self) -> list[InputEffect] | None:
# input (',' input)*
here = self.getpos()
if inp := self.input():
inp = cast(InputEffect, inp)
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
@contextual
def input(self) -> InputEffect | None:
return self.cache_effect() or self.stack_effect()
def outputs(self) -> list[OutputEffect] | None:
# 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
@contextual
def output(self) -> OutputEffect | None:
return self.stack_effect()
@contextual
def cache_effect(self) -> CacheEffect | None:
# IDENTIFIER '/' NUMBER
if tkn := self.expect(lx.IDENTIFIER):
if self.expect(lx.DIVIDE):
num = self.require(lx.NUMBER).text
try:
size = int(num)
except ValueError:
raise self.make_syntax_error(f"Expected integer, got {num!r}")
else:
return CacheEffect(tkn.text, size)
return None
@contextual
def stack_effect(self) -> StackEffect | None:
# IDENTIFIER [':' IDENTIFIER [TIMES]] ['if' '(' expression ')']
# | IDENTIFIER '[' expression ']'
if tkn := self.expect(lx.IDENTIFIER):
type_text = ""
if self.expect(lx.COLON):
type_text = self.require(lx.IDENTIFIER).text.strip()
if self.expect(lx.TIMES):
type_text += " *"
cond_text = ""
if self.expect(lx.IF):
self.require(lx.LPAREN)
if not (cond := self.expression()):
raise self.make_syntax_error("Expected condition")
self.require(lx.RPAREN)
cond_text = cond.text.strip()
size_text = ""
if self.expect(lx.LBRACKET):
if type_text or cond_text:
raise self.make_syntax_error("Unexpected [")
if not (size := self.expression()):
raise self.make_syntax_error("Expected expression")
self.require(lx.RBRACKET)
type_text = "PyObject **"
size_text = size.text.strip()
return StackEffect(tkn.text, type_text, cond_text, size_text)
return None
@contextual
def expression(self) -> Expression | None:
tokens: list[lx.Token] = []
level = 1
while tkn := self.peek():
if tkn.kind in (lx.LBRACKET, lx.LPAREN):
level += 1
elif tkn.kind in (lx.RBRACKET, lx.RPAREN):
level -= 1
if level == 0:
break
tokens.append(tkn)
self.next()
if not tokens:
return None
return Expression(lx.to_text(tokens).strip())
# def ops(self) -> list[OpName] | None:
# if op := self.op():
# ops = [op]
# while self.expect(lx.PLUS):
# if op := self.op():
# ops.append(op)
# return ops
@contextual
def op(self) -> OpName | None:
if tkn := self.expect(lx.IDENTIFIER):
return OpName(tkn.text)
return None
@contextual
def macro_def(self) -> Macro | None:
if tkn := self.expect(lx.MACRO):
if self.expect(lx.LPAREN):
if tkn := self.expect(lx.IDENTIFIER):
if self.expect(lx.RPAREN):
if self.expect(lx.EQUALS):
if uops := self.uops():
self.require(lx.SEMI)
res = Macro(tkn.text, uops)
return res
return None
def uops(self) -> list[UOp] | None:
if uop := self.uop():
uop = cast(UOp, uop)
uops = [uop]
while self.expect(lx.PLUS):
if uop := self.uop():
uop = cast(UOp, uop)
uops.append(uop)
else:
raise self.make_syntax_error("Expected op name or cache effect")
return uops
return None
@contextual
def uop(self) -> UOp | None:
if tkn := self.expect(lx.IDENTIFIER):
if self.expect(lx.DIVIDE):
if num := self.expect(lx.NUMBER):
try:
size = int(num.text)
except ValueError:
raise self.make_syntax_error(
f"Expected integer, got {num.text!r}"
)
else:
return CacheEffect(tkn.text, size)
raise self.make_syntax_error("Expected integer")
else:
return OpName(tkn.text)
return None
@contextual
def family_def(self) -> Family | None:
if (tkn := self.expect(lx.IDENTIFIER)) and tkn.text == "family":
size = None
if self.expect(lx.LPAREN):
if tkn := self.expect(lx.IDENTIFIER):
if self.expect(lx.COMMA):
if not (size := self.expect(lx.IDENTIFIER)):
if not (size := self.expect(lx.NUMBER)):
raise self.make_syntax_error(
"Expected identifier or number"
)
if self.expect(lx.RPAREN):
if self.expect(lx.EQUALS):
if not self.expect(lx.LBRACE):
raise self.make_syntax_error("Expected {")
if members := self.members():
if self.expect(lx.RBRACE) and self.expect(lx.SEMI):
return Family(
tkn.text, size.text if size else "", members
)
return None
def flags(self) -> list[str]:
here = self.getpos()
if self.expect(lx.LPAREN):
if tkn := self.expect(lx.IDENTIFIER):
flags = [tkn.text]
while self.expect(lx.COMMA):
if tkn := self.expect(lx.IDENTIFIER):
flags.append(tkn.text)
else:
break
if not self.expect(lx.RPAREN):
raise self.make_syntax_error("Expected comma or right paren")
return flags
self.setpos(here)
return []
@contextual
def pseudo_def(self) -> Pseudo | None:
if (tkn := self.expect(lx.IDENTIFIER)) and tkn.text == "pseudo":
size = None
if self.expect(lx.LPAREN):
if tkn := self.expect(lx.IDENTIFIER):
if self.expect(lx.COMMA):
flags = self.flags()
else:
flags = []
if self.expect(lx.RPAREN):
if self.expect(lx.EQUALS):
if not self.expect(lx.LBRACE):
raise self.make_syntax_error("Expected {")
if members := self.members():
if self.expect(lx.RBRACE) and self.expect(lx.SEMI):
return Pseudo(tkn.text, flags, members)
return None
def members(self) -> list[str] | None:
here = self.getpos()
if tkn := self.expect(lx.IDENTIFIER):
members = [tkn.text]
while self.expect(lx.COMMA):
if tkn := self.expect(lx.IDENTIFIER):
members.append(tkn.text)
else:
break
peek = self.peek()
if not peek or peek.kind != lx.RBRACE:
raise self.make_syntax_error("Expected comma or right paren")
return members
self.setpos(here)
return None
@contextual
def block(self) -> Block | None:
if self.c_blob():
return Block()
return None
def c_blob(self) -> list[lx.Token]:
tokens: list[lx.Token] = []
level = 0
while tkn := self.next(raw=True):
tokens.append(tkn)
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
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 = "<string>"
else:
with open(filename, "r") 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 = "<default>"
src = "if (x) { x.foo; // comment\n}"
parser = Parser(src, filename)
x = parser.definition()
print(x)
|