2020-04-22 19:29:27 -03:00
|
|
|
import ast
|
2021-11-26 06:50:34 -04:00
|
|
|
import os.path
|
2020-04-22 19:29:27 -03:00
|
|
|
import re
|
2021-09-05 10:58:52 -03:00
|
|
|
from dataclasses import dataclass, field
|
2020-04-29 06:42:21 -03:00
|
|
|
from enum import Enum
|
2021-09-05 10:58:52 -03:00
|
|
|
from typing import IO, Any, Dict, List, Optional, Set, Text, Tuple
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
from pegen import grammar
|
2020-04-22 19:29:27 -03:00
|
|
|
from pegen.grammar import (
|
2020-04-29 06:42:21 -03:00
|
|
|
Alt,
|
2020-04-22 19:29:27 -03:00
|
|
|
Cut,
|
2021-02-02 15:54:22 -04:00
|
|
|
Forced,
|
2020-04-29 06:42:21 -03:00
|
|
|
Gather,
|
2020-04-22 19:29:27 -03:00
|
|
|
GrammarVisitor,
|
2020-04-29 06:42:21 -03:00
|
|
|
Group,
|
2021-08-12 13:37:30 -03:00
|
|
|
Leaf,
|
2020-04-29 06:42:21 -03:00
|
|
|
Lookahead,
|
2020-04-22 19:29:27 -03:00
|
|
|
NamedItem,
|
|
|
|
NameLeaf,
|
|
|
|
NegativeLookahead,
|
|
|
|
Opt,
|
2020-04-29 06:42:21 -03:00
|
|
|
PositiveLookahead,
|
2020-04-22 19:29:27 -03:00
|
|
|
Repeat0,
|
|
|
|
Repeat1,
|
2020-04-29 06:42:21 -03:00
|
|
|
Rhs,
|
2020-04-22 19:29:27 -03:00
|
|
|
Rule,
|
2020-04-29 06:42:21 -03:00
|
|
|
StringLeaf,
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
2020-04-29 06:42:21 -03:00
|
|
|
from pegen.parser_generator import ParserGenerator
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
EXTENSION_PREFIX = """\
|
|
|
|
#include "pegen.h"
|
|
|
|
|
2020-05-25 16:17:12 -03:00
|
|
|
#if defined(Py_DEBUG) && defined(Py_BUILD_CORE)
|
2022-05-24 17:35:08 -03:00
|
|
|
# define D(x) if (p->debug) { x; }
|
2020-05-25 14:38:45 -03:00
|
|
|
#else
|
2021-03-18 05:54:13 -03:00
|
|
|
# define D(x)
|
2020-05-25 14:38:45 -03:00
|
|
|
#endif
|
|
|
|
|
2022-05-19 07:43:16 -03:00
|
|
|
#ifdef __wasi__
|
2023-11-20 09:27:33 -04:00
|
|
|
# ifdef Py_DEBUG
|
|
|
|
# define MAXSTACK 1000
|
|
|
|
# else
|
|
|
|
# define MAXSTACK 4000
|
|
|
|
# endif
|
2022-05-19 07:43:16 -03:00
|
|
|
#else
|
|
|
|
# define MAXSTACK 6000
|
|
|
|
#endif
|
2022-01-03 15:54:06 -04:00
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
"""
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
EXTENSION_SUFFIX = """
|
|
|
|
void *
|
|
|
|
_PyPegen_parse(Parser *p)
|
|
|
|
{
|
|
|
|
// Initialize keywords
|
|
|
|
p->keywords = reserved_keywords;
|
|
|
|
p->n_keyword_lists = n_keyword_lists;
|
2021-04-15 17:38:45 -03:00
|
|
|
p->soft_keywords = soft_keywords;
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
return start_rule(p);
|
|
|
|
}
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
class NodeTypes(Enum):
|
|
|
|
NAME_TOKEN = 0
|
|
|
|
NUMBER_TOKEN = 1
|
|
|
|
STRING_TOKEN = 2
|
|
|
|
GENERIC_TOKEN = 3
|
|
|
|
KEYWORD = 4
|
2020-05-26 20:15:52 -03:00
|
|
|
SOFT_KEYWORD = 5
|
|
|
|
CUT_OPERATOR = 6
|
2023-04-19 13:18:16 -03:00
|
|
|
F_STRING_CHUNK = 7
|
2020-04-29 06:42:21 -03:00
|
|
|
|
|
|
|
|
|
|
|
BASE_NODETYPES = {
|
|
|
|
"NAME": NodeTypes.NAME_TOKEN,
|
|
|
|
"NUMBER": NodeTypes.NUMBER_TOKEN,
|
|
|
|
"STRING": NodeTypes.STRING_TOKEN,
|
2021-04-15 17:38:45 -03:00
|
|
|
"SOFT_KEYWORD": NodeTypes.SOFT_KEYWORD,
|
2020-04-29 06:42:21 -03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
class FunctionCall:
|
|
|
|
function: str
|
2020-05-21 17:39:44 -03:00
|
|
|
arguments: List[Any] = field(default_factory=list)
|
2020-04-29 06:42:21 -03:00
|
|
|
assigned_variable: Optional[str] = None
|
2020-09-16 15:42:00 -03:00
|
|
|
assigned_variable_type: Optional[str] = None
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type: Optional[str] = None
|
2020-04-29 06:42:21 -03:00
|
|
|
nodetype: Optional[NodeTypes] = None
|
|
|
|
force_true: bool = False
|
2020-05-06 19:14:43 -03:00
|
|
|
comment: Optional[str] = None
|
2020-04-29 06:42:21 -03:00
|
|
|
|
|
|
|
def __str__(self) -> str:
|
|
|
|
parts = []
|
|
|
|
parts.append(self.function)
|
|
|
|
if self.arguments:
|
|
|
|
parts.append(f"({', '.join(map(str, self.arguments))})")
|
|
|
|
if self.force_true:
|
2021-10-19 16:24:12 -03:00
|
|
|
parts.append(", !p->error_indicator")
|
2020-04-29 06:42:21 -03:00
|
|
|
if self.assigned_variable:
|
2020-09-16 15:42:00 -03:00
|
|
|
if self.assigned_variable_type:
|
2021-08-12 13:37:30 -03:00
|
|
|
parts = [
|
|
|
|
"(",
|
|
|
|
self.assigned_variable,
|
|
|
|
" = ",
|
|
|
|
"(",
|
|
|
|
self.assigned_variable_type,
|
|
|
|
")",
|
|
|
|
*parts,
|
|
|
|
")",
|
|
|
|
]
|
2020-09-16 15:42:00 -03:00
|
|
|
else:
|
|
|
|
parts = ["(", self.assigned_variable, " = ", *parts, ")"]
|
2020-05-06 19:14:43 -03:00
|
|
|
if self.comment:
|
|
|
|
parts.append(f" // {self.comment}")
|
2020-04-29 06:42:21 -03:00
|
|
|
return "".join(parts)
|
|
|
|
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
class CCallMakerVisitor(GrammarVisitor):
|
2020-04-28 09:11:55 -03:00
|
|
|
def __init__(
|
|
|
|
self,
|
|
|
|
parser_generator: ParserGenerator,
|
|
|
|
exact_tokens: Dict[str, int],
|
|
|
|
non_exact_tokens: Set[str],
|
|
|
|
):
|
2020-04-22 19:29:27 -03:00
|
|
|
self.gen = parser_generator
|
2020-04-28 09:11:55 -03:00
|
|
|
self.exact_tokens = exact_tokens
|
|
|
|
self.non_exact_tokens = non_exact_tokens
|
2020-05-21 17:39:44 -03:00
|
|
|
self.cache: Dict[Any, FunctionCall] = {}
|
2022-02-10 09:12:14 -04:00
|
|
|
self.cleanup_statements: List[str] = []
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def keyword_helper(self, keyword: str) -> FunctionCall:
|
|
|
|
return FunctionCall(
|
2020-05-10 01:34:50 -03:00
|
|
|
assigned_variable="_keyword",
|
2020-04-29 06:42:21 -03:00
|
|
|
function="_PyPegen_expect_token",
|
2021-09-05 10:58:52 -03:00
|
|
|
arguments=["p", self.gen.keywords[keyword]],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="Token *",
|
2020-04-29 06:42:21 -03:00
|
|
|
nodetype=NodeTypes.KEYWORD,
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"token='{keyword}'",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-26 14:58:44 -03:00
|
|
|
def soft_keyword_helper(self, value: str) -> FunctionCall:
|
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable="_keyword",
|
|
|
|
function="_PyPegen_expect_soft_keyword",
|
|
|
|
arguments=["p", value],
|
|
|
|
return_type="expr_ty",
|
2020-05-26 20:15:52 -03:00
|
|
|
nodetype=NodeTypes.SOFT_KEYWORD,
|
2020-05-26 14:58:44 -03:00
|
|
|
comment=f"soft_keyword='{value}'",
|
|
|
|
)
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_NameLeaf(self, node: NameLeaf) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
name = node.value
|
2020-04-28 09:11:55 -03:00
|
|
|
if name in self.non_exact_tokens:
|
2020-04-29 06:42:21 -03:00
|
|
|
if name in BASE_NODETYPES:
|
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable=f"{name.lower()}_var",
|
|
|
|
function=f"_PyPegen_{name.lower()}_token",
|
|
|
|
arguments=["p"],
|
|
|
|
nodetype=BASE_NODETYPES[name],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="expr_ty",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=name,
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable=f"{name.lower()}_var",
|
|
|
|
function=f"_PyPegen_expect_token",
|
|
|
|
arguments=["p", name],
|
|
|
|
nodetype=NodeTypes.GENERIC_TOKEN,
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="Token *",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"token='{name}'",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
|
|
|
|
2020-05-01 08:32:26 -03:00
|
|
|
type = None
|
|
|
|
rule = self.gen.all_rules.get(name.lower())
|
|
|
|
if rule is not None:
|
|
|
|
type = "asdl_seq *" if rule.is_loop() or rule.is_gather() else rule.type
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable=f"{name}_var",
|
|
|
|
function=f"{name}_rule",
|
|
|
|
arguments=["p"],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type=type,
|
2020-05-10 01:34:50 -03:00
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_StringLeaf(self, node: StringLeaf) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
val = ast.literal_eval(node.value)
|
|
|
|
if re.match(r"[a-zA-Z_]\w*\Z", val): # This is a keyword
|
2020-05-26 14:58:44 -03:00
|
|
|
if node.value.endswith("'"):
|
|
|
|
return self.keyword_helper(val)
|
|
|
|
else:
|
|
|
|
return self.soft_keyword_helper(node.value)
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
2020-04-28 09:11:55 -03:00
|
|
|
assert val in self.exact_tokens, f"{node.value} is not a known literal"
|
|
|
|
type = self.exact_tokens[val]
|
2020-04-29 06:42:21 -03:00
|
|
|
return FunctionCall(
|
2020-05-10 01:34:50 -03:00
|
|
|
assigned_variable="_literal",
|
2020-04-29 06:42:21 -03:00
|
|
|
function=f"_PyPegen_expect_token",
|
|
|
|
arguments=["p", type],
|
|
|
|
nodetype=NodeTypes.GENERIC_TOKEN,
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="Token *",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"token='{val}'",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Rhs(self, node: Rhs) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
if node in self.cache:
|
|
|
|
return self.cache[node]
|
2021-09-05 10:58:52 -03:00
|
|
|
if node.can_be_inlined:
|
2020-05-21 17:39:44 -03:00
|
|
|
self.cache[node] = self.generate_call(node.alts[0].items[0])
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
2021-09-05 10:58:52 -03:00
|
|
|
name = self.gen.artifical_rule_from_rhs(node)
|
2020-04-29 06:42:21 -03:00
|
|
|
self.cache[node] = FunctionCall(
|
2020-05-10 01:34:50 -03:00
|
|
|
assigned_variable=f"{name}_var",
|
|
|
|
function=f"{name}_rule",
|
|
|
|
arguments=["p"],
|
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.cache[node]
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_NamedItem(self, node: NamedItem) -> FunctionCall:
|
2020-05-21 17:39:44 -03:00
|
|
|
call = self.generate_call(node.item)
|
2020-04-22 19:29:27 -03:00
|
|
|
if node.name:
|
2020-04-29 06:42:21 -03:00
|
|
|
call.assigned_variable = node.name
|
2020-09-16 15:42:00 -03:00
|
|
|
if node.type:
|
|
|
|
call.assigned_variable_type = node.type
|
2020-04-29 06:42:21 -03:00
|
|
|
return call
|
|
|
|
|
|
|
|
def lookahead_call_helper(self, node: Lookahead, positive: int) -> FunctionCall:
|
2020-05-21 17:39:44 -03:00
|
|
|
call = self.generate_call(node.node)
|
2020-04-29 06:42:21 -03:00
|
|
|
if call.nodetype == NodeTypes.NAME_TOKEN:
|
|
|
|
return FunctionCall(
|
|
|
|
function=f"_PyPegen_lookahead_with_name",
|
|
|
|
arguments=[positive, call.function, *call.arguments],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="int",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-05-26 20:15:52 -03:00
|
|
|
elif call.nodetype == NodeTypes.SOFT_KEYWORD:
|
|
|
|
return FunctionCall(
|
|
|
|
function=f"_PyPegen_lookahead_with_string",
|
|
|
|
arguments=[positive, call.function, *call.arguments],
|
|
|
|
return_type="int",
|
|
|
|
)
|
2020-04-29 06:42:21 -03:00
|
|
|
elif call.nodetype in {NodeTypes.GENERIC_TOKEN, NodeTypes.KEYWORD}:
|
|
|
|
return FunctionCall(
|
|
|
|
function=f"_PyPegen_lookahead_with_int",
|
|
|
|
arguments=[positive, call.function, *call.arguments],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="int",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"token={node.node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
2020-04-29 06:42:21 -03:00
|
|
|
return FunctionCall(
|
|
|
|
function=f"_PyPegen_lookahead",
|
|
|
|
arguments=[positive, call.function, *call.arguments],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="int",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_PositiveLookahead(self, node: PositiveLookahead) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.lookahead_call_helper(node, 1)
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_NegativeLookahead(self, node: NegativeLookahead) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.lookahead_call_helper(node, 0)
|
|
|
|
|
2021-02-02 15:54:22 -04:00
|
|
|
def visit_Forced(self, node: Forced) -> FunctionCall:
|
|
|
|
call = self.generate_call(node.node)
|
2021-08-12 13:37:30 -03:00
|
|
|
if isinstance(node.node, Leaf):
|
|
|
|
assert isinstance(node.node, Leaf)
|
2021-02-02 15:54:22 -04:00
|
|
|
val = ast.literal_eval(node.node.value)
|
2021-08-12 13:37:30 -03:00
|
|
|
assert val in self.exact_tokens, f"{node.node.value} is not a known literal"
|
2021-02-02 15:54:22 -04:00
|
|
|
type = self.exact_tokens[val]
|
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable="_literal",
|
|
|
|
function=f"_PyPegen_expect_forced_token",
|
|
|
|
arguments=["p", type, f'"{val}"'],
|
|
|
|
nodetype=NodeTypes.GENERIC_TOKEN,
|
|
|
|
return_type="Token *",
|
|
|
|
comment=f"forced_token='{val}'",
|
|
|
|
)
|
2021-08-12 13:37:30 -03:00
|
|
|
if isinstance(node.node, Group):
|
|
|
|
call = self.visit(node.node.rhs)
|
|
|
|
call.assigned_variable = None
|
|
|
|
call.comment = None
|
|
|
|
return FunctionCall(
|
|
|
|
assigned_variable="_literal",
|
|
|
|
function=f"_PyPegen_expect_forced_result",
|
|
|
|
arguments=["p", str(call), f'"{node.node.rhs!s}"'],
|
|
|
|
return_type="void *",
|
|
|
|
comment=f"forced_token=({node.node.rhs!s})",
|
|
|
|
)
|
2021-02-02 15:54:22 -04:00
|
|
|
else:
|
2021-08-12 13:37:30 -03:00
|
|
|
raise NotImplementedError(f"Forced tokens don't work with {node.node} nodes")
|
2021-02-02 15:54:22 -04:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Opt(self, node: Opt) -> FunctionCall:
|
2020-05-21 17:39:44 -03:00
|
|
|
call = self.generate_call(node.node)
|
2020-04-29 06:42:21 -03:00
|
|
|
return FunctionCall(
|
2020-05-10 01:34:50 -03:00
|
|
|
assigned_variable="_opt_var",
|
2020-04-29 06:42:21 -03:00
|
|
|
function=call.function,
|
|
|
|
arguments=call.arguments,
|
|
|
|
force_true=True,
|
2020-05-10 01:34:50 -03:00
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Repeat0(self, node: Repeat0) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
if node in self.cache:
|
|
|
|
return self.cache[node]
|
2021-09-05 10:58:52 -03:00
|
|
|
name = self.gen.artificial_rule_from_repeat(node.node, False)
|
2020-04-29 06:42:21 -03:00
|
|
|
self.cache[node] = FunctionCall(
|
|
|
|
assigned_variable=f"{name}_var",
|
|
|
|
function=f"{name}_rule",
|
|
|
|
arguments=["p"],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="asdl_seq *",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.cache[node]
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Repeat1(self, node: Repeat1) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
if node in self.cache:
|
|
|
|
return self.cache[node]
|
2021-09-05 10:58:52 -03:00
|
|
|
name = self.gen.artificial_rule_from_repeat(node.node, True)
|
2020-04-29 06:42:21 -03:00
|
|
|
self.cache[node] = FunctionCall(
|
|
|
|
assigned_variable=f"{name}_var",
|
|
|
|
function=f"{name}_rule",
|
|
|
|
arguments=["p"],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="asdl_seq *",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.cache[node]
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Gather(self, node: Gather) -> FunctionCall:
|
2020-04-22 19:29:27 -03:00
|
|
|
if node in self.cache:
|
|
|
|
return self.cache[node]
|
2021-09-05 10:58:52 -03:00
|
|
|
name = self.gen.artifical_rule_from_gather(node)
|
2020-04-29 06:42:21 -03:00
|
|
|
self.cache[node] = FunctionCall(
|
|
|
|
assigned_variable=f"{name}_var",
|
|
|
|
function=f"{name}_rule",
|
|
|
|
arguments=["p"],
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="asdl_seq *",
|
2020-05-06 19:14:43 -03:00
|
|
|
comment=f"{node}",
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
return self.cache[node]
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Group(self, node: Group) -> FunctionCall:
|
2020-05-21 17:39:44 -03:00
|
|
|
return self.generate_call(node.rhs)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_Cut(self, node: Cut) -> FunctionCall:
|
|
|
|
return FunctionCall(
|
2020-05-10 01:34:50 -03:00
|
|
|
assigned_variable="_cut_var",
|
2020-05-01 08:32:26 -03:00
|
|
|
return_type="int",
|
|
|
|
function="1",
|
|
|
|
nodetype=NodeTypes.CUT_OPERATOR,
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-21 17:39:44 -03:00
|
|
|
def generate_call(self, node: Any) -> FunctionCall:
|
|
|
|
return super().visit(node)
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
class CParserGenerator(ParserGenerator, GrammarVisitor):
|
|
|
|
def __init__(
|
|
|
|
self,
|
|
|
|
grammar: grammar.Grammar,
|
2020-05-01 19:14:12 -03:00
|
|
|
tokens: Dict[int, str],
|
2020-04-28 09:11:55 -03:00
|
|
|
exact_tokens: Dict[str, int],
|
|
|
|
non_exact_tokens: Set[str],
|
2020-04-22 19:29:27 -03:00
|
|
|
file: Optional[IO[Text]],
|
|
|
|
debug: bool = False,
|
|
|
|
skip_actions: bool = False,
|
|
|
|
):
|
2021-08-12 13:37:30 -03:00
|
|
|
super().__init__(grammar, set(tokens.values()), file)
|
2020-04-28 09:11:55 -03:00
|
|
|
self.callmakervisitor: CCallMakerVisitor = CCallMakerVisitor(
|
|
|
|
self, exact_tokens, non_exact_tokens
|
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
self._varname_counter = 0
|
|
|
|
self.debug = debug
|
|
|
|
self.skip_actions = skip_actions
|
2022-02-10 09:12:14 -04:00
|
|
|
self.cleanup_statements: List[str] = []
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-25 14:38:45 -03:00
|
|
|
def add_level(self) -> None:
|
2022-01-03 15:54:06 -04:00
|
|
|
self.print("if (p->level++ == MAXSTACK) {")
|
|
|
|
with self.indent():
|
2023-08-22 04:41:50 -03:00
|
|
|
self.print("_Pypegen_stack_overflow(p);")
|
2022-01-03 15:54:06 -04:00
|
|
|
self.print("}")
|
2020-05-25 14:38:45 -03:00
|
|
|
|
|
|
|
def remove_level(self) -> None:
|
2022-01-03 15:54:06 -04:00
|
|
|
self.print("p->level--;")
|
2020-05-25 14:38:45 -03:00
|
|
|
|
|
|
|
def add_return(self, ret_val: str) -> None:
|
2022-02-10 09:12:14 -04:00
|
|
|
for stmt in self.cleanup_statements:
|
|
|
|
self.print(stmt)
|
2020-05-25 14:38:45 -03:00
|
|
|
self.remove_level()
|
|
|
|
self.print(f"return {ret_val};")
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
def unique_varname(self, name: str = "tmpvar") -> str:
|
|
|
|
new_var = name + "_" + str(self._varname_counter)
|
|
|
|
self._varname_counter += 1
|
|
|
|
return new_var
|
|
|
|
|
|
|
|
def call_with_errorcheck_return(self, call_text: str, returnval: str) -> None:
|
|
|
|
error_var = self.unique_varname()
|
|
|
|
self.print(f"int {error_var} = {call_text};")
|
|
|
|
self.print(f"if ({error_var}) {{")
|
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return(returnval)
|
|
|
|
self.print("}")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def call_with_errorcheck_goto(self, call_text: str, goto_target: str) -> None:
|
|
|
|
error_var = self.unique_varname()
|
|
|
|
self.print(f"int {error_var} = {call_text};")
|
|
|
|
self.print(f"if ({error_var}) {{")
|
|
|
|
with self.indent():
|
|
|
|
self.print(f"goto {goto_target};")
|
|
|
|
self.print(f"}}")
|
|
|
|
|
2021-08-12 13:37:30 -03:00
|
|
|
def out_of_memory_return(
|
|
|
|
self,
|
|
|
|
expr: str,
|
|
|
|
cleanup_code: Optional[str] = None,
|
|
|
|
) -> None:
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(f"if ({expr}) {{")
|
|
|
|
with self.indent():
|
|
|
|
if cleanup_code is not None:
|
|
|
|
self.print(cleanup_code)
|
2020-05-17 00:19:23 -03:00
|
|
|
self.print("p->error_indicator = 1;")
|
2020-05-21 17:39:44 -03:00
|
|
|
self.print("PyErr_NoMemory();")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(f"}}")
|
|
|
|
|
2020-05-17 00:19:23 -03:00
|
|
|
def out_of_memory_goto(self, expr: str, goto_target: str) -> None:
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(f"if ({expr}) {{")
|
|
|
|
with self.indent():
|
2020-05-17 00:19:23 -03:00
|
|
|
self.print("PyErr_NoMemory();")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(f"goto {goto_target};")
|
|
|
|
self.print(f"}}")
|
|
|
|
|
|
|
|
def generate(self, filename: str) -> None:
|
2021-09-05 10:58:52 -03:00
|
|
|
self.collect_rules()
|
2021-11-26 06:50:34 -04:00
|
|
|
basename = os.path.basename(filename)
|
|
|
|
self.print(f"// @generated by pegen from {basename}")
|
2020-04-22 19:29:27 -03:00
|
|
|
header = self.grammar.metas.get("header", EXTENSION_PREFIX)
|
|
|
|
if header:
|
|
|
|
self.print(header.rstrip("\n"))
|
|
|
|
subheader = self.grammar.metas.get("subheader", "")
|
|
|
|
if subheader:
|
|
|
|
self.print(subheader)
|
|
|
|
self._setup_keywords()
|
2021-04-15 17:38:45 -03:00
|
|
|
self._setup_soft_keywords()
|
2021-09-05 10:58:52 -03:00
|
|
|
for i, (rulename, rule) in enumerate(self.all_rules.items(), 1000):
|
2020-04-22 19:29:27 -03:00
|
|
|
comment = " // Left-recursive" if rule.left_recursive else ""
|
|
|
|
self.print(f"#define {rulename}_type {i}{comment}")
|
|
|
|
self.print()
|
2021-09-05 10:58:52 -03:00
|
|
|
for rulename, rule in self.all_rules.items():
|
2020-04-22 19:29:27 -03:00
|
|
|
if rule.is_loop() or rule.is_gather():
|
|
|
|
type = "asdl_seq *"
|
|
|
|
elif rule.type:
|
|
|
|
type = rule.type + " "
|
|
|
|
else:
|
|
|
|
type = "void *"
|
|
|
|
self.print(f"static {type}{rulename}_rule(Parser *p);")
|
|
|
|
self.print()
|
2021-09-05 10:58:52 -03:00
|
|
|
for rulename, rule in list(self.all_rules.items()):
|
|
|
|
self.print()
|
|
|
|
if rule.left_recursive:
|
|
|
|
self.print("// Left-recursive")
|
|
|
|
self.visit(rule)
|
2020-04-22 19:29:27 -03:00
|
|
|
if self.skip_actions:
|
|
|
|
mode = 0
|
|
|
|
else:
|
|
|
|
mode = int(self.rules["start"].type == "mod_ty") if "start" in self.rules else 1
|
|
|
|
if mode == 1 and self.grammar.metas.get("bytecode"):
|
|
|
|
mode += 1
|
|
|
|
modulename = self.grammar.metas.get("modulename", "parse")
|
|
|
|
trailer = self.grammar.metas.get("trailer", EXTENSION_SUFFIX)
|
|
|
|
if trailer:
|
|
|
|
self.print(trailer.rstrip("\n") % dict(mode=mode, modulename=modulename))
|
|
|
|
|
|
|
|
def _group_keywords_by_length(self) -> Dict[int, List[Tuple[str, int]]]:
|
|
|
|
groups: Dict[int, List[Tuple[str, int]]] = {}
|
2021-09-05 10:58:52 -03:00
|
|
|
for keyword_str, keyword_type in self.keywords.items():
|
2020-04-22 19:29:27 -03:00
|
|
|
length = len(keyword_str)
|
|
|
|
if length in groups:
|
|
|
|
groups[length].append((keyword_str, keyword_type))
|
|
|
|
else:
|
|
|
|
groups[length] = [(keyword_str, keyword_type)]
|
|
|
|
return groups
|
|
|
|
|
|
|
|
def _setup_keywords(self) -> None:
|
|
|
|
n_keyword_lists = (
|
2021-09-05 10:58:52 -03:00
|
|
|
len(max(self.keywords.keys(), key=len)) + 1 if len(self.keywords) > 0 else 0
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
|
|
|
self.print(f"static const int n_keyword_lists = {n_keyword_lists};")
|
|
|
|
groups = self._group_keywords_by_length()
|
|
|
|
self.print("static KeywordToken *reserved_keywords[] = {")
|
|
|
|
with self.indent():
|
|
|
|
num_groups = max(groups) + 1 if groups else 1
|
|
|
|
for keywords_length in range(num_groups):
|
|
|
|
if keywords_length not in groups.keys():
|
2020-07-06 16:31:16 -03:00
|
|
|
self.print("(KeywordToken[]) {{NULL, -1}},")
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
|
|
|
self.print("(KeywordToken[]) {")
|
|
|
|
with self.indent():
|
|
|
|
for keyword_str, keyword_type in groups[keywords_length]:
|
|
|
|
self.print(f'{{"{keyword_str}", {keyword_type}}},')
|
|
|
|
self.print("{NULL, -1},")
|
|
|
|
self.print("},")
|
|
|
|
self.print("};")
|
|
|
|
|
2021-04-15 17:38:45 -03:00
|
|
|
def _setup_soft_keywords(self) -> None:
|
2021-09-05 10:58:52 -03:00
|
|
|
soft_keywords = sorted(self.soft_keywords)
|
2021-04-15 17:38:45 -03:00
|
|
|
self.print("static char *soft_keywords[] = {")
|
|
|
|
with self.indent():
|
|
|
|
for keyword in soft_keywords:
|
|
|
|
self.print(f'"{keyword}",')
|
|
|
|
self.print("NULL,")
|
|
|
|
self.print("};")
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
def _set_up_token_start_metadata_extraction(self) -> None:
|
|
|
|
self.print("if (p->mark == p->fill && _PyPegen_fill_token(p) < 0) {")
|
|
|
|
with self.indent():
|
|
|
|
self.print("p->error_indicator = 1;")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("int _start_lineno = p->tokens[_mark]->lineno;")
|
|
|
|
self.print("UNUSED(_start_lineno); // Only used by EXTRA macro")
|
|
|
|
self.print("int _start_col_offset = p->tokens[_mark]->col_offset;")
|
|
|
|
self.print("UNUSED(_start_col_offset); // Only used by EXTRA macro")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def _set_up_token_end_metadata_extraction(self) -> None:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("Token *_token = _PyPegen_get_last_nonnwhitespace_token(p);")
|
|
|
|
self.print("if (_token == NULL) {")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("int _end_lineno = _token->end_lineno;")
|
|
|
|
self.print("UNUSED(_end_lineno); // Only used by EXTRA macro")
|
|
|
|
self.print("int _end_col_offset = _token->end_col_offset;")
|
|
|
|
self.print("UNUSED(_end_col_offset); // Only used by EXTRA macro")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-18 14:32:03 -03:00
|
|
|
def _check_for_errors(self) -> None:
|
|
|
|
self.print("if (p->error_indicator) {")
|
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-05-18 14:32:03 -03:00
|
|
|
self.print("}")
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
def _set_up_rule_memoization(self, node: Rule, result_type: str) -> None:
|
|
|
|
self.print("{")
|
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_level()
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"{result_type} _res = NULL;")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(f"if (_PyPegen_is_memoized(p, {node.name}_type, &_res)) {{")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_res")
|
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("int _mark = p->mark;")
|
|
|
|
self.print("int _resmark = p->mark;")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("while (1) {")
|
|
|
|
with self.indent():
|
|
|
|
self.call_with_errorcheck_return(
|
2020-05-10 01:34:50 -03:00
|
|
|
f"_PyPegen_update_memo(p, _mark, {node.name}_type, _res)", "_res"
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("p->mark = _mark;")
|
|
|
|
self.print(f"void *_raw = {node.name}_raw(p);")
|
2022-01-03 15:54:06 -04:00
|
|
|
self.print("if (p->error_indicator) {")
|
2020-10-31 15:31:41 -03:00
|
|
|
with self.indent():
|
2022-01-03 15:54:06 -04:00
|
|
|
self.add_return("NULL")
|
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("if (_raw == NULL || p->mark <= _resmark)")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
|
|
|
self.print("break;")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"_resmark = p->mark;")
|
|
|
|
self.print("_res = _raw;")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"p->mark = _resmark;")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_res")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
|
|
|
self.print(f"static {result_type}")
|
|
|
|
self.print(f"{node.name}_raw(Parser *p)")
|
|
|
|
|
|
|
|
def _should_memoize(self, node: Rule) -> bool:
|
|
|
|
return node.memo and not node.left_recursive
|
|
|
|
|
|
|
|
def _handle_default_rule_body(self, node: Rule, rhs: Rhs, result_type: str) -> None:
|
|
|
|
memoize = self._should_memoize(node)
|
|
|
|
|
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_level()
|
2020-05-18 14:32:03 -03:00
|
|
|
self._check_for_errors()
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"{result_type} _res = NULL;")
|
2020-04-22 19:29:27 -03:00
|
|
|
if memoize:
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(f"if (_PyPegen_is_memoized(p, {node.name}_type, &_res)) {{")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_res")
|
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("int _mark = p->mark;")
|
2020-04-22 19:29:27 -03:00
|
|
|
if any(alt.action and "EXTRA" in alt.action for alt in rhs.alts):
|
|
|
|
self._set_up_token_start_metadata_extraction()
|
|
|
|
self.visit(
|
2021-08-12 13:37:30 -03:00
|
|
|
rhs,
|
|
|
|
is_loop=False,
|
|
|
|
is_gather=node.is_gather(),
|
|
|
|
rulename=node.name,
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
|
|
|
if self.debug:
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(f'D(fprintf(stderr, "Fail at %d: {node.name}\\n", p->mark));')
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("_res = NULL;")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(" done:")
|
|
|
|
with self.indent():
|
|
|
|
if memoize:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"_PyPegen_insert_memo(p, _mark, {node.name}_type, _res);")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_res")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def _handle_loop_rule_body(self, node: Rule, rhs: Rhs) -> None:
|
|
|
|
memoize = self._should_memoize(node)
|
|
|
|
is_repeat1 = node.name.startswith("_loop1")
|
|
|
|
|
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_level()
|
2020-05-18 14:32:03 -03:00
|
|
|
self._check_for_errors()
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("void *_res = NULL;")
|
2020-04-22 19:29:27 -03:00
|
|
|
if memoize:
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(f"if (_PyPegen_is_memoized(p, {node.name}_type, &_res)) {{")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_res")
|
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("int _mark = p->mark;")
|
2023-03-06 09:41:53 -04:00
|
|
|
if memoize:
|
|
|
|
self.print("int _start_mark = p->mark;")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("void **_children = PyMem_Malloc(sizeof(void *));")
|
2020-05-17 00:19:23 -03:00
|
|
|
self.out_of_memory_return(f"!_children")
|
2021-03-01 07:18:33 -04:00
|
|
|
self.print("Py_ssize_t _children_capacity = 1;")
|
|
|
|
self.print("Py_ssize_t _n = 0;")
|
2020-04-22 19:29:27 -03:00
|
|
|
if any(alt.action and "EXTRA" in alt.action for alt in rhs.alts):
|
|
|
|
self._set_up_token_start_metadata_extraction()
|
|
|
|
self.visit(
|
2021-08-12 13:37:30 -03:00
|
|
|
rhs,
|
|
|
|
is_loop=True,
|
|
|
|
is_gather=node.is_gather(),
|
|
|
|
rulename=node.name,
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
|
|
|
if is_repeat1:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("if (_n == 0 || p->error_indicator) {")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("PyMem_Free(_children);")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
2020-09-16 15:42:00 -03:00
|
|
|
self.print("asdl_seq *_seq = (asdl_seq*)_Py_asdl_generic_seq_new(_n, p->arena);")
|
2020-05-17 00:19:23 -03:00
|
|
|
self.out_of_memory_return(f"!_seq", cleanup_code="PyMem_Free(_children);")
|
2020-09-16 15:42:00 -03:00
|
|
|
self.print("for (int i = 0; i < _n; i++) asdl_seq_SET_UNTYPED(_seq, i, _children[i]);")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("PyMem_Free(_children);")
|
2023-03-06 09:41:53 -04:00
|
|
|
if memoize and node.name:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"_PyPegen_insert_memo(p, _start_mark, {node.name}_type, _seq);")
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("_seq")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def visit_Rule(self, node: Rule) -> None:
|
|
|
|
is_loop = node.is_loop()
|
|
|
|
is_gather = node.is_gather()
|
|
|
|
rhs = node.flatten()
|
|
|
|
if is_loop or is_gather:
|
|
|
|
result_type = "asdl_seq *"
|
|
|
|
elif node.type:
|
|
|
|
result_type = node.type
|
|
|
|
else:
|
|
|
|
result_type = "void *"
|
|
|
|
|
|
|
|
for line in str(node).splitlines():
|
|
|
|
self.print(f"// {line}")
|
|
|
|
if node.left_recursive and node.leader:
|
|
|
|
self.print(f"static {result_type} {node.name}_raw(Parser *);")
|
|
|
|
|
|
|
|
self.print(f"static {result_type}")
|
|
|
|
self.print(f"{node.name}_rule(Parser *p)")
|
|
|
|
|
|
|
|
if node.left_recursive and node.leader:
|
|
|
|
self._set_up_rule_memoization(node, result_type)
|
|
|
|
|
|
|
|
self.print("{")
|
2022-02-10 09:12:14 -04:00
|
|
|
|
|
|
|
if node.name.endswith("without_invalid"):
|
|
|
|
with self.indent():
|
|
|
|
self.print("int _prev_call_invalid = p->call_invalid_rules;")
|
|
|
|
self.print("p->call_invalid_rules = 0;")
|
|
|
|
self.cleanup_statements.append("p->call_invalid_rules = _prev_call_invalid;")
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
if is_loop:
|
|
|
|
self._handle_loop_rule_body(node, rhs)
|
|
|
|
else:
|
|
|
|
self._handle_default_rule_body(node, rhs, result_type)
|
2022-02-10 09:12:14 -04:00
|
|
|
|
|
|
|
if node.name.endswith("without_invalid"):
|
|
|
|
self.cleanup_statements.pop()
|
|
|
|
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def visit_NamedItem(self, node: NamedItem) -> None:
|
2020-05-21 17:39:44 -03:00
|
|
|
call = self.callmakervisitor.generate_call(node)
|
2020-04-29 06:42:21 -03:00
|
|
|
if call.assigned_variable:
|
|
|
|
call.assigned_variable = self.dedupe(call.assigned_variable)
|
|
|
|
self.print(call)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def visit_Rhs(
|
|
|
|
self, node: Rhs, is_loop: bool, is_gather: bool, rulename: Optional[str]
|
|
|
|
) -> None:
|
|
|
|
if is_loop:
|
|
|
|
assert len(node.alts) == 1
|
|
|
|
for alt in node.alts:
|
|
|
|
self.visit(alt, is_loop=is_loop, is_gather=is_gather, rulename=rulename)
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def join_conditions(self, keyword: str, node: Any) -> None:
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(f"{keyword} (")
|
|
|
|
with self.indent():
|
|
|
|
first = True
|
|
|
|
for item in node.items:
|
|
|
|
if first:
|
|
|
|
first = False
|
|
|
|
else:
|
|
|
|
self.print("&&")
|
2020-04-29 06:42:21 -03:00
|
|
|
self.visit(item)
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print(")")
|
|
|
|
|
2020-04-28 09:11:55 -03:00
|
|
|
def emit_action(self, node: Alt, cleanup_code: Optional[str] = None) -> None:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"_res = {node.action};")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("if (_res == NULL && PyErr_Occurred()) {")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
|
|
|
self.print("p->error_indicator = 1;")
|
|
|
|
if cleanup_code:
|
|
|
|
self.print(cleanup_code)
|
2020-05-25 14:38:45 -03:00
|
|
|
self.add_return("NULL")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
|
|
|
|
|
|
|
if self.debug:
|
|
|
|
self.print(
|
2020-05-25 14:38:45 -03:00
|
|
|
f'D(fprintf(stderr, "Hit with action [%d-%d]: %s\\n", _mark, p->mark, "{node}"));'
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def emit_default_action(self, is_gather: bool, node: Alt) -> None:
|
|
|
|
if len(self.local_variable_names) > 1:
|
2020-04-22 19:29:27 -03:00
|
|
|
if is_gather:
|
2020-04-29 06:42:21 -03:00
|
|
|
assert len(self.local_variable_names) == 2
|
|
|
|
self.print(
|
2020-05-10 01:34:50 -03:00
|
|
|
f"_res = _PyPegen_seq_insert_in_front(p, "
|
2020-04-29 06:42:21 -03:00
|
|
|
f"{self.local_variable_names[0]}, {self.local_variable_names[1]});"
|
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
|
|
|
if self.debug:
|
|
|
|
self.print(
|
2020-05-25 14:38:45 -03:00
|
|
|
f'D(fprintf(stderr, "Hit without action [%d:%d]: %s\\n", _mark, p->mark, "{node}"));'
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
2020-04-29 06:42:21 -03:00
|
|
|
self.print(
|
2020-05-10 01:34:50 -03:00
|
|
|
f"_res = _PyPegen_dummy_name(p, {', '.join(self.local_variable_names)});"
|
2020-04-29 06:42:21 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
|
|
|
if self.debug:
|
|
|
|
self.print(
|
2020-05-25 14:38:45 -03:00
|
|
|
f'D(fprintf(stderr, "Hit with default action [%d:%d]: %s\\n", _mark, p->mark, "{node}"));'
|
2020-04-22 19:29:27 -03:00
|
|
|
)
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print(f"_res = {self.local_variable_names[0]};")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
def emit_dummy_action(self) -> None:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("_res = _PyPegen_dummy_name(p);")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-25 14:38:45 -03:00
|
|
|
def handle_alt_normal(self, node: Alt, is_gather: bool, rulename: Optional[str]) -> None:
|
2020-04-29 06:42:21 -03:00
|
|
|
self.join_conditions(keyword="if", node=node)
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("{")
|
|
|
|
# We have parsed successfully all the conditions for the option.
|
|
|
|
with self.indent():
|
2020-05-26 14:58:44 -03:00
|
|
|
node_str = str(node).replace('"', '\\"')
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(
|
2020-05-26 14:58:44 -03:00
|
|
|
f'D(fprintf(stderr, "%*c+ {rulename}[%d-%d]: %s succeeded!\\n", p->level, \' \', _mark, p->mark, "{node_str}"));'
|
2020-05-25 14:38:45 -03:00
|
|
|
)
|
2021-10-06 14:55:16 -03:00
|
|
|
# Prepare to emit the rule action and do so
|
2020-04-22 19:29:27 -03:00
|
|
|
if node.action and "EXTRA" in node.action:
|
|
|
|
self._set_up_token_end_metadata_extraction()
|
|
|
|
if self.skip_actions:
|
|
|
|
self.emit_dummy_action()
|
|
|
|
elif node.action:
|
|
|
|
self.emit_action(node)
|
|
|
|
else:
|
2020-04-29 06:42:21 -03:00
|
|
|
self.emit_default_action(is_gather, node)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
# As the current option has parsed correctly, do not continue with the rest.
|
|
|
|
self.print(f"goto done;")
|
|
|
|
self.print("}")
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def handle_alt_loop(self, node: Alt, is_gather: bool, rulename: Optional[str]) -> None:
|
2020-04-22 19:29:27 -03:00
|
|
|
# Condition of the main body of the alternative
|
2020-04-29 06:42:21 -03:00
|
|
|
self.join_conditions(keyword="while", node=node)
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("{")
|
|
|
|
# We have parsed successfully one item!
|
|
|
|
with self.indent():
|
|
|
|
# Prepare to emit the rule action and do so
|
|
|
|
if node.action and "EXTRA" in node.action:
|
|
|
|
self._set_up_token_end_metadata_extraction()
|
|
|
|
if self.skip_actions:
|
|
|
|
self.emit_dummy_action()
|
|
|
|
elif node.action:
|
2020-05-10 01:34:50 -03:00
|
|
|
self.emit_action(node, cleanup_code="PyMem_Free(_children);")
|
2020-04-22 19:29:27 -03:00
|
|
|
else:
|
2020-04-29 06:42:21 -03:00
|
|
|
self.emit_default_action(is_gather, node)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
|
|
|
# Add the result of rule to the temporary buffer of children. This buffer
|
|
|
|
# will populate later an asdl_seq with all elements to return.
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("if (_n == _children_capacity) {")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("_children_capacity *= 2;")
|
2020-05-21 17:39:44 -03:00
|
|
|
self.print(
|
|
|
|
"void **_new_children = PyMem_Realloc(_children, _children_capacity*sizeof(void *));"
|
|
|
|
)
|
2023-01-16 14:45:37 -04:00
|
|
|
self.out_of_memory_return(f"!_new_children", cleanup_code="PyMem_Free(_children);")
|
2020-05-17 00:19:23 -03:00
|
|
|
self.print("_children = _new_children;")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("_children[_n++] = _res;")
|
|
|
|
self.print("_mark = p->mark;")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
|
|
|
|
|
|
|
def visit_Alt(
|
|
|
|
self, node: Alt, is_loop: bool, is_gather: bool, rulename: Optional[str]
|
|
|
|
) -> None:
|
2021-08-12 13:37:30 -03:00
|
|
|
if len(node.items) == 1 and str(node.items[0]).startswith("invalid_"):
|
2020-10-26 19:42:04 -03:00
|
|
|
self.print(f"if (p->call_invalid_rules) {{ // {node}")
|
|
|
|
else:
|
|
|
|
self.print(f"{{ // {node}")
|
2020-04-22 19:29:27 -03:00
|
|
|
with self.indent():
|
2020-05-18 14:32:03 -03:00
|
|
|
self._check_for_errors()
|
2020-05-26 14:58:44 -03:00
|
|
|
node_str = str(node).replace('"', '\\"')
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(
|
2020-05-26 14:58:44 -03:00
|
|
|
f'D(fprintf(stderr, "%*c> {rulename}[%d-%d]: %s\\n", p->level, \' \', _mark, p->mark, "{node_str}"));'
|
2020-05-25 14:38:45 -03:00
|
|
|
)
|
2020-04-22 19:29:27 -03:00
|
|
|
# Prepare variable declarations for the alternative
|
|
|
|
vars = self.collect_vars(node)
|
|
|
|
for v, var_type in sorted(item for item in vars.items() if item[0] is not None):
|
|
|
|
if not var_type:
|
|
|
|
var_type = "void *"
|
|
|
|
else:
|
|
|
|
var_type += " "
|
2020-05-10 01:34:50 -03:00
|
|
|
if v == "_cut_var":
|
2020-04-22 19:29:27 -03:00
|
|
|
v += " = 0" # cut_var must be initialized
|
|
|
|
self.print(f"{var_type}{v};")
|
2021-08-12 13:37:30 -03:00
|
|
|
if v and v.startswith("_opt_var"):
|
2020-05-24 19:20:18 -03:00
|
|
|
self.print(f"UNUSED({v}); // Silence compiler warnings")
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
with self.local_variable_context():
|
|
|
|
if is_loop:
|
|
|
|
self.handle_alt_loop(node, is_gather, rulename)
|
|
|
|
else:
|
2020-05-25 14:38:45 -03:00
|
|
|
self.handle_alt_normal(node, is_gather, rulename)
|
2020-04-22 19:29:27 -03:00
|
|
|
|
2020-05-10 01:34:50 -03:00
|
|
|
self.print("p->mark = _mark;")
|
2020-05-26 14:58:44 -03:00
|
|
|
node_str = str(node).replace('"', '\\"')
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print(
|
|
|
|
f"D(fprintf(stderr, \"%*c%s {rulename}[%d-%d]: %s failed!\\n\", p->level, ' ',\n"
|
2020-05-26 14:58:44 -03:00
|
|
|
f' p->error_indicator ? "ERROR!" : "-", _mark, p->mark, "{node_str}"));'
|
2020-05-25 14:38:45 -03:00
|
|
|
)
|
2020-05-10 01:34:50 -03:00
|
|
|
if "_cut_var" in vars:
|
2020-05-25 14:38:45 -03:00
|
|
|
self.print("if (_cut_var) {")
|
|
|
|
with self.indent():
|
|
|
|
self.add_return("NULL")
|
|
|
|
self.print("}")
|
2020-04-22 19:29:27 -03:00
|
|
|
self.print("}")
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def collect_vars(self, node: Alt) -> Dict[Optional[str], Optional[str]]:
|
2020-04-22 19:29:27 -03:00
|
|
|
types = {}
|
2020-04-29 06:42:21 -03:00
|
|
|
with self.local_variable_context():
|
|
|
|
for item in node.items:
|
|
|
|
name, type = self.add_var(item)
|
|
|
|
types[name] = type
|
2020-04-22 19:29:27 -03:00
|
|
|
return types
|
|
|
|
|
2020-04-29 06:42:21 -03:00
|
|
|
def add_var(self, node: NamedItem) -> Tuple[Optional[str], Optional[str]]:
|
2020-05-21 17:39:44 -03:00
|
|
|
call = self.callmakervisitor.generate_call(node.item)
|
2020-05-21 16:57:52 -03:00
|
|
|
name = node.name if node.name else call.assigned_variable
|
|
|
|
if name is not None:
|
|
|
|
name = self.dedupe(name)
|
2020-09-16 15:42:00 -03:00
|
|
|
return_type = call.return_type if node.type is None else node.type
|
|
|
|
return name, return_type
|