andy/parser_c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

添加一些cpu操作

Browse Source
This commit is contained in:
ranchuan
2024-12-04 11:39:53 +08:00
parent 7c97a9595e
commit 5e072f0380
3 changed files with 193 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

160
parser_c.py
View File

@@ -4,10 +4,6 @@ import dataclasses
from lex_c import lex_token
from lex_c import lex
import lex_c
from node_declear import dist_node_type_struct
from node_declear import dist_node_type_union
from node_declear import dist_node_type_enum
from node_declear import dist_node_type_typedef
_NodeTypeTable=[
"file","vdecl","fdef"
@@ -16,23 +12,19 @@ _NodeTypeTable=[
@dataclasses.dataclass
class node:
name:str
name:list[str]=dataclasses.field(default_factory=list)
type:str="base"
token_list:list[lex_token]=dataclasses.field(default_factory=list)
child:list=dataclasses.field(default_factory=list)
# 文件节点
@dataclasses.dataclass
class node_file(node):
type:str="file"
body:list=dataclasses.field(default_factory=list)
# 变量定义节点
@dataclasses.dataclass
class node_variable_def(node):
type:str="variable_def"
vvalue=None
vtype:str="unknown"
vattr:list[str]=dataclasses.field(default_factory=list)
# 结构体声明节点
@dataclasses.dataclass
@@ -43,7 +35,6 @@ class node_struct_decl(node):
@dataclasses.dataclass
class node_struct_def(node):
type:str="struct_def"
body:list[node_variable_def]=dataclasses.field(default_factory=list)
# 联合体声明节点
@dataclasses.dataclass
@@ -54,7 +45,6 @@ class node_union_decl(node):
@dataclasses.dataclass
class node_union_def(node):
type:str="union_def"
body:list[node_variable_def]=dataclasses.field(default_factory=list)
# 枚举声明节点
@dataclasses.dataclass
@@ -65,31 +55,21 @@ class node_enum_decl(node):
@dataclasses.dataclass
class node_enum_def(node):
type:str="enum_def"
body:list[dict]=dataclasses.field(default_factory=list)
# 函数声明节点
@dataclasses.dataclass
class node_func_decl(node):
type:str="func_decl"
rettype:str="unknown"
retattr:list[str]=dataclasses.field(default_factory=list)
para:list[node_variable_def]=dataclasses.field(default_factory=list)
#typedef 节点
@dataclasses.dataclass
class node_typedef(node):
type:str="typedef"
attr:list[str]=dataclasses.field(default_factory=list)
body:node=None
# 函数定义节点
@dataclasses.dataclass
class node_func_def(node):
type:str="func_def"
rettype:str="unknown"
retattr:list[str]=dataclasses.field(default_factory=list)
para:list[node_variable_def]=dataclasses.field(default_factory=list)
body:list[node]=dataclasses.field(default_factory=list)
# 找到闭合的括号
@@ -129,6 +109,138 @@ def find_sentence(token_list:list[lex_token]):
def dist_node_type_struct(token_list:list[lex_token]):
if(token_list[0].token==lex_c.TOKEN_STRUCT):
if(token_list[1].token==lex_c.TOKEN_SYMBOL):
if(len(token_list)==2):
return node_struct_decl(name=token_list[1].buff.decode("utf-8"),token_list=token_list)
elif(token_list[2].token==lex_c.TOKEN("{")):
if not token_list[-1].token==lex_c.TOKEN("}"):
raise Exception("没有出现预期的符号 '}'")
v_list:list[node_variable_def]=[]
token_list_local=token_list[3:-1]
while len(token_list_local)>0:
sentence=find_sentence(token_list_local)
v_list.append(dist_node_type(token_list=sentence))
token_list_local=token_list_local[len(sentence):]
return node_struct_def(name=token_list[1].buff.decode("utf-8"),token_list=token_list,body=v_list)
raise Exception(f"语法错误 {token_list[0]}")
def dist_node_type_union(token_list:list[lex_token]):
if(token_list[0].token==lex_c.TOKEN_UNION):
if(token_list[1].token==lex_c.TOKEN_SYMBOL):
if(len(token_list)==2):
return node_union_decl(name=token_list[1].buff.decode("utf-8"),token_list=token_list)
elif(token_list[2].token==lex_c.TOKEN("{")):
if not token_list[-1].token==lex_c.TOKEN("}"):
raise Exception("没有出现预期的符号 '}'")
v_list:list[node_variable_def]=[]
token_list_local=token_list[3:-1]
while len(token_list_local)>0:
sentence=find_sentence(token_list_local)
v_list.append(dist_node_type(token_list=sentence))
token_list_local=token_list_local[len(sentence):]
return node_union_def(name=token_list[1].buff.decode("utf-8"),token_list=token_list,body=v_list)
raise Exception(f"语法错误 {token_list[0]}")
def dist_node_type_enum(token_list:list[lex_token]):
if(token_list[0].token==lex_c.TOKEN_ENUM):
if(token_list[1].token==lex_c.TOKEN_SYMBOL):
if(len(token_list)==2):
return node_enum_decl(name=token_list[1].buff.decode("utf-8"),token_list=token_list)
elif(token_list[2].token==lex_c.TOKEN("{")):
if not token_list[-1].token==lex_c.TOKEN("}"):
raise Exception("没有出现预期的符号 '}'")
token_list_local=token_list[3:-1]
index=0
v_list:list[dict]=[]
while len(token_list_local)>0:
if(token_list_local[0].token==lex_c.TOKEN_SYMBOL):
key=token_list_local[0].buff.decode("utf-8")
if(token_list_local[1].token==lex_c.TOKEN("=") and token_list_local[2].token==lex_c.TOKEN_NUM):
index=int(token_list_local[2].buff.decode("utf-8"))
token_list_local=token_list_local[3:]
else:
index+=1
token_list_local=token_list_local[1:]
v_list.append({key:index})
if(len(token_list_local)>0):
if(token_list_local[0].token!=lex_c.TOKEN(",")):
raise Exception(f"枚举类型应该使用 ',' 分隔符")
token_list_local=token_list_local[1:]
return node_enum_def(name=token_list[1].buff.decode("utf-8"),token_list=token_list,body=v_list)
raise Exception(f"语法错误 {token_list[0]}")
def dist_node_type_typedef(token_list:list[lex_token]):
if(token_list[0].token==lex_c.TOKEN_TYPEDEF):
attr=[]
token_list_local=token_list
if(token_list[-1].token!=lex_c.TOKEN_SYMBOL):
raise Exception(f"没有定义新类型 {token_list[-1]}")
name=token_list[-1].buff.decode("utf-8")
token_list=token_list[1:]
while token_list[0].token in [lex_c.TOKEN_UNSIGNED,lex_c.TOKEN_CONST]:
attr.append(token_list[0].name)
token_list=token_list[1:]
if(token_list[0].token==lex_c.TOKEN_STRUCT or token_list[0].token==lex_c.TOKEN_UNION):
attr.append(token_list[0].name)
if(token_list[1].token==lex_c.TOKEN_SYMBOL):
node_r=None
attr.append(token_list[1].buff.decode("utf-8"))
if(token_list[2].token==lex_c.TOKEN("{")):
node_r=dist_node_type(token_list=token_list[1:-1])
elif(token_list[2].token==lex_c.TOKEN("*")):
attr.append(token_list[2].name)
return node_typedef(name=name,token_list=token_list_local,child=node_r)
if(token_list[0].token==lex_c.TOKEN_SYMBOL):
# 使用typedef 定义过的自定义类型
attr.append(token_list[0].buff.decode("utf-8"))
token_list=token_list[1:]
else:
# c语言预设类型
while(token_list[0].token in
[lex_c.TOKEN_INT,lex_c.TOKEN_CHAR,lex_c.TOKEN_SHORT,lex_c.TOKEN_LONG,lex_c.TOKEN_FLOAT,
lex_c.TOKEN_DOUBLE,lex_c.TOKEN_VOID,lex_c.TOKEN("*")]):
attr.append(token_list[0].name)
token_list=token_list[1:]
if(len(token_list)>1):
raise Exception(f"意外的token {token_list[0]}")
return node_typedef(name=name,token_list=token_list_local,attr=attr,body=None)
raise Exception(f"语法错误 {token_list[0]}")
# 判断一个语句的类型
def dist_node_type(token_list:list[lex_token]):
if(token_list[0].token==lex_c.TOKEN_EXTERN):
@@ -151,11 +263,11 @@ if __name__ == "__main__":
file_name="main.c"
with open(file_name,mode='rb') as f:
token_list=lex(f.read())
file=node_file(name=file_name,token_list=token_list,body=[])
file=node_file(name=file_name,token_list=token_list,child=[])
while len(token_list)>0:
sentence=find_sentence(token_list)
node_d=dist_node_type(sentence)
file.body.append(node_d)
file.child.append(node_d)
print('找到一个语句：')
for item in sentence:
print(f"\t{item}")