使用python来实现词法分析器

后面写的有些随便，过于冗杂

# 用来完成编译原理第一章节词法分析实验报告
# 新增正则表达式

import re
class Stack:#构建栈
    def __init__(self):
        self.st=[]
    def push(self,info):#入栈
        self.st.append(info)
    def pop(self):#出栈
        self.st.pop()
    def return_string(self):#返回字符串
        return ''.join(self.st)
    def clear(self):#清除栈
        self.st.clear()
k_array=['if','for','while','printf','then']#关键字表，单词种别码为1
s_array=[[';',',','(',')','[',']'],['+','-','*','/'],['<','<=','=','>','>=','<>']]#0 for 分界符；种类码为2
                                                                                      # 1 for 算数运算符；种类码为3
                                                                                      #2 for 关系运算符；单词种别码为4
id_array=['i','n','a']#存放标识符，单词种别码为6
ci_array=[]#存放常数，单词种类码为5
class word_analyse:
    def __init__(self):#初始化
        self.sentence=''
        f = open("context.txt", 'r')
        while True:
            line = f.readline()
            if line:
                self.sentence=self.sentence+line
            else:
                break
        f.close()
    def read(self):#读取输入语句，将分好的单词寄存在nametoken，类型分在typetoken，位置放在position中
        self.nametoken = []  # 输入单词
        self.typetoken = []  # 和nametoken对应的单词种别
        self.position=[] #存放单词的位置
        stack=Stack()
        while(len(self.sentence)!=0):
            if(self.sentence[0].isalpha()):
                med = 0
                while (self.sentence[med].isalnum()):#根据第一个字母来寻找关键字or标识符
                    stack.push(self.sentence[med])
                    med=med+1
                if stack.return_string() in k_array:
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append(1)
                elif stack.return_string() in id_array:
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append(6)
                else:
                    id_array.append(stack.return_string())
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append(6)
                stack.clear()
                self.sentence = self.sentence[med:]
                continue
            elif self.sentence[0].isdigit():#根据第一个字符为数字来使用栈来判断数字的合法性
                med=0
                while(not self.sentence[med].isspace()):
                    stack.push(self.sentence[med])
                    med=med+1
                reg = re.compile(r'^[-+]?[0-9]+\.[0-9]+$')
                res = reg.match(stack.return_string())
                if res is True:
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append(5)
                elif 'e+' in stack.return_string() or 'e-' in stack.return_string():
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append(5)
                else:
                    self.nametoken.append(stack.return_string())
                    self.typetoken.append('Error')
                stack.clear()
                self.sentence = self.sentence[med:]
                continue
            elif self.sentence[0:2]=='/*':   #消除注释
                while(self.sentence[0:2]!='*/'):
                    self.sentence=self.sentence[1:]
                self.sentence=self.sentence[2:]
                continue
            elif self.sentence[0].isspace():#清理空格
                self.sentence=self.sentence[1:]
                continue
            elif (not self.sentence[0].isalpha()) and (not self.sentence[0].isdigit()):
                if self.sentence[0] in s_array[0]:#关于分界符，即时多个分界符在一起无需栈来分辨是否多个栈在一起
                    self.nametoken.append(self.sentence[0])
                    self.typetoken.append(2)
                    self.sentence = self.sentence[1:]
                    continue
                elif self.sentence[0] in s_array[1]:#关于算数运算符，有多个算数运算符在一起的情况
                    med = 0
                    while (self.sentence[med] in s_array[1]):
                        stack.push(self.sentence[med])
                        med = med + 1
                    if stack.return_string() not in s_array[1]:
                        self.nametoken.append(stack.return_string())
                        self.typetoken.append('Error')

                    else:
                        self.nametoken.append(stack.return_string())
                        self.typetoken.append(3)

                    stack.clear()
                    self.sentence = self.sentence[med:]
                    continue
                elif self.sentence[0] in s_array[2]:#关于关系运算符，单一or多个
                    med = 0
                    while (self.sentence[med] in s_array[2]):
                        stack.push(self.sentence[med])
                        med = med + 1
                    if stack.return_string() not in s_array[2]:
                        self.nametoken.append(stack.return_string())
                        self.typetoken.append('Error')
                    else:
                        self.nametoken.append(stack.return_string())
                        self.typetoken.append(4)
                    stack.clear()
                    self.sentence = self.sentence[med:]
                    continue
                else:#剩下的基本上就是error了
                    self.nametoken.append(self.sentence[0])
                    self.typetoken.append('Error')
                    self.sentence = self.sentence[1:]
                    continue
    def get_position(self):#字符集合获取相关的位置
        x,y=1,0
        for i in range(len(self.nametoken)):
            if self.nametoken[i]==';':
                y=y+1
                self.position.append((x, y))
                x=x+1
                y=1
            else:y=y+1
            self.position.append((x,y))
def return_type_name(type):#反过来通过种类符号来推出其的单词汉语
    dy = {1: '关键字', 2: '分界符', 3: '算数运算符', 4: '关系运算符', 5: '常数', 6: '标识符', 'Error': 'Error'}
    return dy[type]
def show():#
    test = word_analyse()
    test.read()
    test.get_position()
    show_time = {}
    def return_binary(a, b):
        if a=='Error':
            return a
        else:
            return (a, b)
    for i in range(len(test.nametoken)):
        show_time.setdefault(i, []).append(test.nametoken[i])
        show_time.setdefault(i, []).append(return_binary(test.typetoken[i], test.nametoken[i]))
        show_time.setdefault(i, []).append(return_type_name(test.typetoken[i]))
        show_time.setdefault(i, []).append(test.position[i])
    print('单词，二元序列，类型，位置（行，列）')
    for i in range(len(test.nametoken)):
        print(show_time[i])
if __name__ =="__main__":
    show()