Laz*_*der 7 c python python-3.x pycparser
我需要获取功能块（定义和所有内容，而不仅仅是声明），以便获取功能依赖关系图。从功能依赖关系图中，确定连接的组件并模块化我庞大的C代码库，一次仅一个文件。
问题：我需要一个C解析器来识别功能块，仅此而已。我们有自定义类型等，但签名去了
storage_class return_type function_name ( comma separated type value pairs )
{
//some content I view as generic stuff
}
我想出的解决方案：显然，像任何理智的人一样使用sly和pycparser。
pycparser的问题：需要从其他文件编译预处理器，只是为了识别代码块。就我而言，事情深入到6个层次。很抱歉，我无法显示实际代码。
尝试使用Sly进行代码：
from sly import Lexer, Parser
import re
def comment_remover(text):
def replacer(match):
s = match.group(0)
if s.startswith('/'):
return " " # note: a space and not an empty string
else:
return s
pattern = re.compile(
r'//.*?$|/\*.*?\*/|\'(?:\\.|[^\\\'])*\'|"(?:\\.|[^\\"])*"',
re.DOTALL | re.MULTILINE
)
return re.sub(pattern, replacer, text)
class CLexer(Lexer):
ignore = ' \t\n'
tokens = {LEXEME, PREPROP, FUNC_DECL,FUNC_DEF,LBRACE,RBRACE, SYMBOL}
literals = {'(', ')',',','\n','<','>','-',';','&','*','=','!'}
LBRACE = r'\{'
RBRACE = r'\}'
FUNC_DECL = r'[a-z]+[ \n\t]+[a-zA-Z_0-9]+[ \n\t]+[a-zA-Z_0-9]+[ \n\t]*\([a-zA-Z_\* \,\t\n]+\)[ ]*\;'
FUNC_DEF = r'[a-zA-Z_0-9]+[ \n\t]+[a-zA-Z_0-9]+[ \n\t]*\([a-zA-Z_\* \,\t\n]+\)'
PREPROP = r'#[a-zA-Z_][a-zA-Z0-9_\" .\<\>\/\(\)\-\+]*'
LEXEME = r'[a-zA-Z0-9]+'
SYMBOL = r'[-!$%^&*\(\)_+|~=`\[\]\:\"\;\'\<\>\?\,\.\/]'
def __init__(self):
self.nesting_level = 0
self.lineno = 0
@_(r'\n+')
def newline(self, t):
self.lineno += t.value.count('\n')
@_(r'[-!$%^&*\(\)_+|~=`\[\]\:\"\;\'\<\>\?\,\.\/]')
def symbol(self,t):
t.type = 'symbol'
return t
def error(self, t):
print("Illegal character '%s'" % t.value[0])
self.index += 1
class CParser(Parser):
# Get the token list from the lexer (required)
tokens = CLexer.tokens
@_('PREPROP')
def expr(self,p):
return p.PREPROP
@_('FUNC_DECL')
def expr(self,p):
return p.FUNC_DECL
@_('func')
def expr(self,p):
return p.func
# Grammar rules and actions
@_('FUNC_DEF LBRACE stmt RBRACE')
def func(self, p):
return p.func_def + p.lbrace + p.stmt + p.rbrace
@_('LEXEME stmt')
def stmt(self, p):
return p.LEXEME
@_('SYMBOL stmt')
def stmt(self, p):
return p.SYMBOL
@_('empty')
def stmt(self, p):
return p.empty
@_('')
def empty(self, p):
pass
with open('inputfile.c') as f:
data = "".join(f.readlines())
data = comment_remover(data)
lexer = CLexer()
parser = CParser()
while True:
try:
result = parser.parse(lexer.tokenize(data))
print(result)
except EOFError:
break
错误：
None
None
None
.
.
.
.
None
None
yacc: Syntax error at line 1, token=PREPROP
yacc: Syntax error at line 1, token=LBRACE
yacc: Syntax error at line 1, token=PREPROP
yacc: Syntax error at line 1, token=LBRACE
yacc: Syntax error at line 1, token=PREPROP
.
.
.
.
.
输入：
#include <mycustomheader1.h> //defines type T1
#include <somedir/mycustomheader2.h> //defines type T2
#include <someotherdir/somefile.c>
MACRO_THINGY_DEFINED_IN_SOMEFILE(M1,M2)
static T1 function_name_thats_way_too_long_than_usual(int *a, float* b, T2* c)
{
//some code I don't even care about at this point
}
extern T2 function_name_thats_way_too_long_than_usual(int *a, char* b, T1* c)
{
//some code I don't even care about at this point
}
期望的输出：
function1 :
static T1 function_name_thats_way_too_long_than_usual(int *a, float* b, T2* c)
{
//some code I don't even care about at this point
}
function2 :
extern T2 function_name_thats_way_too_long_than_usual(int *a, char* b, T1* c)
{
//some code I don't even care about at this point
}