[关闭]
@darkproject 2020-02-13T11:29:24.000000Z 字数 6532 阅读 860

网易新人作业

作业

不使用Re,其余库用Python解析cpp文件中的宏定义，含#ifdef #ifndef #else #undef #endif 注释空格制作符换行,#define identifier token-stringopt， 其中 token-stringopt 只有兼容如下几种C/C++指定基本类型常量表示内容：整型，浮点，布尔(true, false)，字符（忽略宽字符），字符串，及各上述基本类型组成的聚合。解析输出所有可用宏到字典，并存储到新的cpp文件。转换前后数据如下表:

image.png-37kB

image.png-805.4kB

  1. # -*- coding: UTF-8 -*-
  2. path = "D:/hw/a.cpp"
  3. save = "D:/hw/save.cpp"
  5. # 查表处理转义字符
  6. Escape = {'r': '\r', 't': '\t', 'v': '\v', "'": "\'", 'a': '\a', 'b': '\b', 'f': '\f',
  7.           'n': '\n', '"': '\"', '\\': '\\', '?': '\?', '0': '\0'}
  8. ReEscape = {'\a': '\\a', '\b': '\\b', '\f': '\\f', '\n': '\\n', '\r': '\\r', '\t': '\\t',
  9.             '\v': '\\v', "\'": "\\'", '\"': '\\"', '\\': '\\\\', '\?': '\\?'}
  11. def ParseAgg(value):
  12.     # 状态机解析聚合类型
  13.     # 栈匹配'{'与'}'
  14.     # 返回值:元组
  15.     temp = ''
  16.     Res = []
  17.     stack = []
  18.     state = 0
  19.     value = value[1:-1]
  20.     for i in value:
  21.         if state == 0 and i == ',':
  22.             Res.append(temp.strip())
  23.             print  Res
  24.             temp = ''
  25.         elif state == 0 and i == '\"':
  26.             state = 1
  27.             temp += i
  28.         elif state == 0 and i == '\'':
  29.             state = 2
  30.             temp += i
  31.         elif state == 0 and i == '{':
  32.             state = 3
  33.             temp += i
  34.             stack.append(True)
  35.         elif state == 0:
  36.             temp += i
  37.         elif state == 1 and i == '\"':
  38.             state = 0
  39.             temp += i
  40.         elif state == 1:
  41.             temp += i
  42.         elif state == 2 and i == '\'':
  43.             state = 0
  44.             temp += i
  45.         elif state == 2:
  46.             temp += i
  47.         elif state == 3 and i == '}':
  48.             temp += i
  49.             stack.pop()
  50.             if stack == []:
  51.                 state = 0
  52.         elif state == 3 and i == '{':
  53.             temp += i
  54.             stack.append(True)
  55.         elif state == 3:
  56.             temp += i
  57.     if len(temp) > 0:
  58.         Res.append(temp.strip())
  59.     tempRes = tuple(Res)
  60.     Res = []
  61.     for i in tempRes:
  62.         Res.append(ParseValue(i))  # 递归解析聚合类型嵌套情况
  63.     return tuple(Res)
  66. def ParseString(value):
  67.     lstr = False
  68.     Res = ''
  69.     state = 0
  70.     if value[0] == 'L':
  71.         lstr = True
  72.         value = value[1:]
  73.     for i in value:
  74.         if state == 0 and i == '\"':
  75.             state = 1
  76.         elif state == 1 and i == '\"':
  77.             state = 0
  78.         elif state == 1 and i == '\\':  # 处理字符串中转义可能出现'"'误判为终止态
  79.             state = 2
  80.         elif state == 1:
  81.             Res += i
  82.         elif state == 2 and i in Escape:
  83.             Res += Escape[i]
  84.             state = 1
  85.         elif state == 1:
  86.             Res += i
  87.     if lstr is True:
  88.         return unicode(Res)
  89.     else:
  90.         return Res
  93. def RePareseString(value):
  94.     Res = ''
  95.     for i in value:
  96.         if i in ReEscape:
  97.             Res += ReEscape[i]
  98.         else:
  99.             Res += i
  100.     return Res
  103. def ParseChar(value):
  104.     value = value[1:-1]
  105.     length = len(value)
  106.     if length == 1:
  107.         return ord(value)
  108.     elif value[0] == '\\' and length > 2:
  109.         if value[1] == 'x' or value[1] == 'X':
  110.             value = '0' + value[1:]
  111.             return int(value, 16)
  112.         else:
  113.             return int(value[1:], 8)
  114.     elif value[0] == '\\':
  115.         return ord(Escape[value[1]])
  118. def ParseValue(value):
  119.     # 将cpp源类型解析为python内置类型
  120.     sign = 1
  121.     if value is None:
  122.         return None
  123.     # 字符串
  124.     if value[0] == '\"' or value[0] == 'L':
  125.         return ParseString(value)
  126.     # 聚合类型
  127.     if value[0] == '{':
  128.         return ParseAgg(value)
  129.     # bool类型
  130.     if value == 'true':
  131.         return True
  132.     if value == 'false':
  133.         return False
  134.     # 前缀符号
  135.     if value[0] == '-':
  136.         sign = -1
  137.         value = value[1:]
  138.     elif value[0] == '+':
  139.         value = value[1:]
  140.     # 十六进制数
  141.     if value[0:2] == '0x' or value[0:2] == '0X':
  142.         value = value.replace('i64', '')
  143.         value = value.replace('I64', '')
  144.         value = value.rstrip("uUlL")
  145.         return sign * int(value, 16)
  146.     # 八进制数
  147.     elif value[0] == '0' and len(value) > 1 and '.' not in value:
  148.         return sign * int(value, 8)
  149.     # 浮点数
  150.     elif 'e' in value or 'E' in value or '.' in value: #
  152.         if 'f' in value or 'F' in value or 'l' in value or 'L' in value:
  153.             value = value.rstrip('fFlL')
  154.             return sign * float(value)
  155.         else:
  156.             return sign * float(value)
  157.     if value[0] == '\'':
  158.         # 字符类型
  159.         return ParseChar(value)
  160.     else:
  161.         # 十进制整数
  162.         value = value.replace('i64', '')
  163.         value = value.replace('I64', '')
  164.         value = value.rstrip("uUlL")
  165.         return sign * int(value)
  167. def ReParseValue(value):
  168.     if isinstance(value, unicode):
  169.         return 'L' + '"' + RePareseString(str(value)) + '"'
  170.     if isinstance(value, str):
  171.         return '"' + RePareseString(value) + '"'
  172.     if isinstance(value, bool):
  173.         if value is True:
  174.             return "true"
  175.         else:
  176.             return "false"
  177.     if isinstance(value, tuple):
  178.         res = ''
  179.         for i in value:
  180.             res += ReParseValue(i) + ','
  181.         res = '{' + res[:-1] + '}'
  182.         return res
  183.     return str(value)
  186. def RemoveComment(str):
  187.     # 有限状态机去除读取的字符串中的注释部分
  188.     # 注释可能存在的情况/**/多行注释、//单行注释、\\折行
  189.     # 返回值:字符串
  190.     state=0
  191.     Res=''
  192.     for i in str:
  193.         if state==0 and i=='/':
  194.             # 我们利用空格进行分词，出现#define/**/name注释紧贴情况，添加空格便于分词
  195.             Res+=' '
  196.             state=1
  197.         elif state==0 and i=='\`':
  198.             state=6
  199.         elif state==0 and i=='\"':
  200.             state=7
  201.         elif state==0:
  202.             Res+=i
  203.         elif state==1 and i=='*':
  204.             state=2
  205.         elif state==1 and i=='/':
  206.             state=4
  207.         elif state==1:
  208.             state=0
  209.             Res+='/'+i
  210.         elif state==2 and i=='*':
  211.             state=3
  212.         elif state==3 and i=='/':
  213.             state=0
  214.         elif state==3 and i=='*':
  215.             state=3
  216.         elif state==3:
  217.             state=2
  218.         elif state==4 and i=='\n':
  219.             state=0
  220.             Res+=i
  221.         elif state==4 and i=='\\':
  222.             state=5
  223.         elif state==5 and i=='\\':
  224.             state=5
  225.         elif state==5:
  226.             state=4
  227.         elif state==6 and i=='\\':
  228.             state=6
  229.         elif state==6 and i=='\`':
  230.             state=0
  231.             Res+=i
  232.         elif state==7 and i=='\\':
  233.             state=7
  234.         elif state==7 and i=='\"':
  235.             state=0
  236.             Res+=i
  237.         if state == 6 or state == 7:
  238.             Res+=i
  239.     return Res
  241. def RemoveTab(code):
  242.     # 处理不在“”和''内的制表符
  243.     Res = []
  244.     temp = ''
  245.     state = 0
  246.     for str in code:
  247.         for i in str:
  248.             if state == 0 and i == '\t':
  249.                 temp += ' '
  250.             elif state == 0 and i == '\"':
  251.                 temp += i
  252.                 state = 1
  253.             elif state == 0 and i == '\'':
  254.                 temp += i
  255.                 state = 2
  256.             elif state == 1 and i == '\"':
  257.                 temp += i
  258.                 state = 0
  259.             elif state == 2 and i == '\'':
  260.                 temp += i
  261.                 state = 0
  262.             else:
  263.                 temp += i
  264.         Res.append(temp)
  265.         temp = ''
  266.     return Res
  269. def To_List(str):
  270.     # 将处理掉注释的字符串按行分割,并清理多余符号
  271.     # 返回值:列表 ex:[#define a 1]
  272.     code = []
  273.     ans = []
  274.     start_index = 0
  275.     end_index = 0
  276.     while end_index < len(str):
  277.         if str[end_index] == '\n':
  278.             code.append(str[start_index:end_index])
  279.             start_index = end_index + 1
  280.         end_index += 1
  281.     if str[start_index:] != '':
  282.         code.append(str[start_index:])
  283.     print code
  284.     code = RemoveTab(code)
  285.     for t in code:
  286.         temp = t.strip().split(' ', 1)
  287.         ins = temp[0].strip()
  288.         if ins == '#':  # 处理'#'未紧贴宏指令的情况
  289.             temp = temp[1].strip().split(' ', 1)
  290.             ins += ''.join(temp[0])
  291.         if len(temp) > 1:
  292.             temp2 = temp[1].strip().split(' ', 1)
  293.             if len(temp2) > 1:
  294.                 temp2[1] = temp2[1].strip()
  295.                 ans.append(ins + ' ' + temp2[0] + ' ' + temp2[1].strip())
  296.             else:
  297.                 ans.append(ins + ' ' + temp2[0])
  298.         else:
  299.             if ins != '':
  300.                 ans.append(ins)
  301.     print ans
  302.     return ans
  305. def ParseMacro(code, dict):
  306.     # 进行分词,将宏的定义语法分为指令 宏名 值 三部分
  307.     # 2个栈匹配宏定义分支逻辑，一个栈匹配#ifdef #ifndef #else，
  308.     # 另一个栈记录分支的状态（防止前一个分支不满足时,内部遇到一个分支不满足，此时内部分支else时flag将会为true会执行内部#define）
  309.     index = 0
  310.     stack = []
  311.     state = [True]
  312.     flag = True
  313.     while index < len(code):
  314.         temp = code[index].split(' ', 2)
  315.         length = len(temp)
  316.         macro_ins = temp[0]
  317.         if macro_ins == '#define' and flag:
  318.             if length > 2:
  319.                 dict[temp[1]] = ParseValue(temp[2])
  320.             else:
  321.                 dict[temp[1]] = None
  322.         elif macro_ins == '#ifdef':
  323.             if temp[1] in dict:
  324.                 state.append(True and state[-1])
  325.                 stack.append(True)
  326.             else:
  327.                 state.append(False)
  328.                 stack.append(False)
  329.                 flag = False
  330.         elif macro_ins == '#ifndef':
  331.             if temp[1] not in dict:
  332.                 state.append(True and state[-1])
  333.                 stack.append(True)
  334.             else:
  335.                 state.append(False)
  336.                 stack.append(False)
  337.                 flag = False
  338.         elif macro_ins == '#else':
  339.             if not stack[-1] and state[-2]:
  340.                 state[-1] = True
  341.                 flag = True
  342.             else:
  343.                 state[-1] = False
  344.                 flag = False
  345.         elif macro_ins == '#undef' and flag:
  346.             if temp[1] in dict:
  347.                 del dict[temp[1]]
  348.         elif macro_ins == '#endif':
  349.             stack.pop()
  350.             state.pop()
  351.             flag = state[-1]
  352.         index += 1
  355. class PyMacroParser:
  356.     def __init__(self):
  357.         self.dict = {}
  358.         self.code = []
  359.         self.pDefine = []
  361.     def load(self, f):
  362.         try:
  363.             with open(f, 'r') as p:
  364.                 str = RemoveComment(p.read())
  365.                 self.code = To_List(str)
  366.         except IOError:
  367.             print "Not Find File!"
  369.     def preDefine(self, s):
  370.         self.dict = {}
  371.         self.pDefine = []
  372.         temp = s.split(";")
  373.         for i in temp:
  374.             if (i != ''):
  375.                 self.pDefine.append(i.strip())
  377.     def dumpDict(self):
  378.         self.dict = {}
  379.         for i in self.pDefine:
  380.             self.dict[i] = None
  381.         ParseMacro(self.code, self.dict)
  382.         print self.dict
  383.         return self.dict
  385.     def dump(self, f):
  386.         self.dict = {}
  387.         for i in self.pDefine:
  388.             self.dict[i] = None
  389.         ParseMacro(self.code, self.dict)
  390.         try:
  391.             with open(f, 'w') as p:
  392.                 for key in self.dict:
  393.                     if self.dict[key] is None:
  394.                         p.write('#define ' + key + '\n')
  395.                     else:
  396.                         p.write('#define ' + key + ' ')
  397.                         p.write(ReParseValue(self.dict[key]))
  398.                         p.write('\n')
  399.         except IOError:
  400.                 print "Not Write File!"
  402. if __name__ == '__main__':
  403.     t = PyMacroParser()
  404.     t.load(path)
  405.     t.preDefine("")
  406.     t.dumpDict()
  407.     t.dump(save)
添加新批注
在作者公开此批注前，只有你和作者可见。
回复批注