python 实现一个简单的C语言词法分析

python 实现一个简单的C语言词法分析

# 定义一个字典或者列表与其中的字符串进行输出来的进行匹配
import sys

map_key = {
    "begin", "if", "then", "while", "do", "end", "int", "main",
    "else", "float", "double", "return", "cout", "<=", ">=", "==",
    "!=", "<<", ">>", "/*", "include","*/"
}

map_sym = {
    "(", ")", "{", "}", "+", "-", "*", "=", "/", ">", "<", ";", ":", ",", "#"
}
# 写一个编码字典
map_data = {
    "begin": 1, "if": 2, "then": 3, "while": 4, "do": 5, "end": 6, "int": 7, "main": 8, "else": 50,
    "float": 51, "double": 52, "return": 12, "cout": 13, "<=": 38, ">=": 37, "==": 21, "!=": 40,
    "<<": 53, ">>": 54, "/*": 55, "(": 26, ")": 27, "{": 28, "}": 29, "+": 22, "-": 23, "*": 24,
    "=": 25, "/": 25, ">": 35, "<": 36, ";": 34, ":": 33, ",": 32, "#": 0, "include": 56,"*/":57
}


def data_map(a, b):  # a代表要比较的字符 b 代表map
    for i in range(len(a)):
        if a[i] in b:
            print(a[i], map_data[a[i]])


# 判断字母或数字，可以利用异常捕获，系统自带的String.isdigit()的方法，
# 该方法用于判定输入的字符串是否为纯数，但是一旦是浮点类型就会返回false
def data_is_number(a):
    try:
        float(a)
        return True
    except ValueError:
        pass
    else:
        return True


def data_start(a, b):
    if a.startswith('/*'):
        return a
    elif a.endswith('*/'):
        return '*/'
    else:
        for i in b:
            if a.startswith(i):
                print(i, map_data[i])
                a = a.replace(i, '')
        return a


# 打开需要检测的C程序txt文本文件
with open("cc.txt", "r", encoding='utf-8') as f:
    data = f.readlines()
    # print(data)  # 测试是否正常输出
    f.close()
# 删除字符串中的 \n
for i in range(len(data)):
    data_strip = data[i].replace('\n', '').strip().split()  # 删除\n 与 空白 并将其分割成字符块
    for i in range(len(data_strip)):
        data_strip[i] = data_start(data_strip[i], map_sym)  # 解决头文件形式

        if data_strip[i] in map_key:  # 判断字符在map中嘛
            print(data_strip[i], map_data[data_strip[i]])
        else:
            #  解决 main()的问题
            data_str = data_strip[i]
            for i in map_key:
                if data_str.startswith(i):
                    data_str = data_str.replace(i, '')
                    print(i, map_data[i])

            # 这里开始对字符串进行列表化处理
            data_data = list(data_str)
            for i in range(len(data_data)):
                if data_is_number(data_data[i]):
                    if data_data[i+1]:
                        if data_data[i+1].encode('utf-8').isalpha():
                            print(data_data[i], 10)
                            print('该程序存在词法错误')
                            sys.exit(0)
                        else:
                            print(data_data[i],10)
                elif data_data[i] in map_sym:
                    print(data_data[i],map_data[data_data[i]])
                elif data_data[i].encode('utf-8').isalpha():
                    print(data_data[i],20)