文本解析将方程式块转换为Python语句

Question

我有一大组SAS方程式语句，并且想使用Python将这些方程式转换为Python语句。 他们看起来像下面这样：

从SAS：

select; 
    when(X_1 <= 6.7278  ) V_1 =-0.0594 ; 
    when(X_1 <= 19.5338  ) V_1 =0.0604  ; 
    when(X_1 <= 45.1458  ) V_1 =0.1755  ; 
    when(X_1 <= 83.5638  ) V_1 =0.2867  ; 
    when(X_1 <= 203.0878 ) V_1 =0.395  ; 
    when(X_1 > 203.0878 ) V_1 =0.5011  ; 
end; 
label V_1 ="X_1 "; 
select; 
    when(X_2 <= 0.0836    ) V_2 =0.0562  ; 
    when(X_2 <= 0.1826    ) V_2 =0.07  ; 
    when(X_2 <= 0.2486    ) V_2 =0.0836  ; 
    when(X_2 <= 0.3146    ) V_2 =0.0969  ; 
    when(X_2 <= 0.3806    ) V_2 =0.1095  ; 
    when(X_2 <= 0.4466    ) V_2 =0.1212  ; 
    when(X_2 <= 0.5126    ) V_2 =0.132  ; 
    when(X_2 <= 0.5786    ) V_2 =0.1419  ; 
    when(X_2 <= 0.6446    ) V_2 =0.1511  ; 
    when(X_2 <= 0.7106    ) V_2 =0.1596  ; 
    when(X_2 <= 0.8526    ) V_2 =0.1679  ; 
    when(X_2 > 0.8526    ) V_2 =0.176  ; 
end; 
label V_2 ="X_2 "; 
... 
... 
... 

到Python：

if X_1 <= 6.7278: 
    V_1 =-0.0594 
elif X_1 <= 19.5338: 
    V_1 =0.0604 
elif X_1 <= 45.1458: 
    V_1 =0.1755 
elif X_1 <= 83.5638: 
    V_1 =0.2867 
elif X_1 <= 203.0878: 
    V_1 =0.395 
else: 
    V_1 =0.5011 

if X_2 <= 0.0836: 
    .... 

我不知道从哪里开始，就像如果使用 '重新' 包或任何其他。任何帮助将非常感激！

Answer 1

如果输入非常一致（如图所示），那么您可能会得到re。

对于任何更复杂的事情，你可能想看看更强大的解析器，如pyparsing。

---

编辑：这里是使用正则表达式一个非常简单的有限状态机解析器;它处理空白行，未使用的select;和end;陈述，以及初始/连续when s。我不处理label因为我不确定他们在做什么 - 将V变量重命名为X？

import re 

class SasTranslator: 
    def __init__(self): 
     # modes: 
     # 0 not in START..END 
     # 1 in START..END, no CASE seen yet 
     # 2 in START..END, CASE already found 
     self.mode = 0 
     self.offset = -1 # input line # 

    def handle_blank(self, match): 
     return "" 

    def handle_start(self, match): 
     if self.mode == 0: 
      self.mode = 1 
      return None 
     else: 
      raise ValueError("Found 'select;' in select block, line {}".format(self.offset)) 

    def handle_end(self, match): 
     if self.mode == 0: 
      raise ValueError("Found 'end;' with no opening 'select;', line {}".format(self.offset)) 
     elif self.mode == 1: 
      raise ValueError("Found empty 'select;' .. 'end;', line {}".format(self.offset)) 
     elif self.mode == 2: 
      self.mode = 0 
      return None 

    def handle_case(self, match): 
     if self.mode == 0: 
      raise ValueError("Found 'when' clause outside 'select;' .. 'end;', line {}".format(self.offset)) 
     elif self.mode == 1: 
      test = "if" 
      self.mode = 2 
      # note: code continues after if..else block 
     elif self.mode == 2: 
      test = "elif" 
      # note: code continues after if..else block 

     test_var, op, test_val, assign_var, assign_val = match.groups() 
     return (
      "{test} {test_var} {op} {test_val}:\n" 
      " {assign_var} = {assign_val}".format(
       test  = test, 
       test_var = test_var, 
       op   = op, 
       test_val = test_val, 
       assign_var = assign_var, 
       assign_val = assign_val 
      ) 
     ) 

    # 
    # Build a dispatch table for the handlers 
    # 

    BLANK = re.compile("\s*$") 
    START = re.compile("select;\s*$") 
    END  = re.compile("end;\s*$") 
    CASE  = re.compile("\s*when\((\w+)\s*([<>=]+)\s*([\d.-]+)\s*\)\s*(\w+)\s*=\s*([\d.-]+)\s*;\s*$") 

    dispatch_table = [ 
     (BLANK, handle_blank), 
     (START, handle_start), 
     (END, handle_end), 
     (CASE, handle_case) 
    ] 

    def __call__(self, line): 
     """ 
     Translate a single line of input 
     """ 
     self.offset += 1 

     for test,handler in SasTranslator.dispatch_table: 
      match = test.match(line) 
      if match is not None: 
       return handler(self, match) 

     # nothing matched! 
     return None 

def main(): 
    with open("my_file.sas") as inf: 
     trans = SasTranslator() 
     for line in inf: 
      result = trans(line) 
      if result is not None: 
       print(result) 
      else: 
       print("***unknown*** {}".format(line.rstrip())) 

if __name__=="__main__": 
    main() 

，并运行对您的样品输入它产生

if X_1 <= 6.7278: 
    V_1 = -0.0594 
elif X_1 <= 19.5338: 
    V_1 = 0.0604 
elif X_1 <= 45.1458: 
    V_1 = 0.1755 
elif X_1 <= 83.5638: 
    V_1 = 0.2867 
elif X_1 <= 203.0878: 
    V_1 = 0.395 
elif X_1 > 203.0878: 
    V_1 = 0.5011 
***unknown*** label V_1 ="X_1 "; 
if X_2 <= 0.0836: 
    V_2 = 0.0562 
elif X_2 <= 0.1826: 
    V_2 = 0.07 
elif X_2 <= 0.2486: 
    V_2 = 0.0836 
elif X_2 <= 0.3146: 
    V_2 = 0.0969 
elif X_2 <= 0.3806: 
    V_2 = 0.1095 
elif X_2 <= 0.4466: 
    V_2 = 0.1212 
elif X_2 <= 0.5126: 
    V_2 = 0.132 
elif X_2 <= 0.5786: 
    V_2 = 0.1419 
elif X_2 <= 0.6446: 
    V_2 = 0.1511 
elif X_2 <= 0.7106: 
    V_2 = 0.1596 
elif X_2 <= 0.8526: 
    V_2 = 0.1679 
elif X_2 > 0.8526: 
    V_2 = 0.176 
***unknown*** label V_2 ="X_2 "; 

---

根据您使用这个频率，它可能是值得的使用bisect二项式查找功能和翻译select; ..而不是（end;），而不是将其嵌入到该表单中（尽管您希望非常小心比较运算符是您所期望的！） - 类似于

V_1 = index_into(
    X_1, 
    [ 6.7278, 19.5338, 45.1458, 83.5638, 203.0878  ], 
    [-0.0594, 0.0604, 0.1755, 0.2867, 0.395, 0.5011] 
) 

它可能会显着加快运行速度（特别是随着选件数量的增加），并且更容易理解和维护。