词法分析练习一:简单提取token

词法分析练习一:简单提取token
思路:

1. 第一次碰到字母,下划线: 开启新token, 设置type=identify; 直到遇见非(字母,数字,下划线 截止), 则以上为一个标识符
2. 第一次碰到数字: 开启新token, 设置type=number; 直到遇见非(数字,字母U,L,u,l)截止, 则以上为一个数字

typedef char bool;
#define true 1
#define false 0

#define CASE_ALPHA_LOWER    case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n': \
                            case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u': case 'v': case 'w': case 'x': case 'y': case 'z':

#define CASE_ALPHA_UPPER    case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G': case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': \
                            case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z':

#define CASE_NUM            case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9':

#define CASE_UNDERLINE      case '_':

#define CASE_LINEEND        case '\0':

enum token_type
{
    TOKEN_IDENTIFY,
    TOKEN_NUMBER,
    TOKEN_LINEFEED,
};

typedef struct token
{
    enum token_type type;
    char str[256];
    unsigned char len;
} token_t;

void parse_token(char* str)
{
    bool in_token = false;
    token_t cur_token;
    cur_token.len = 0;

    while(1)
    {
        char c = *str++;
        switch(c)
        {
            CASE_ALPHA_LOWER
            CASE_ALPHA_UPPER
            CASE_UNDERLINE
            {
                if (in_token == false) {
                    //first token set type
                    cur_token.type = TOKEN_IDENTIFY;
                    in_token = true;
                }

                //save char
                cur_token.str[cur_token.len++] = c;
                break;
            }
            CASE_NUM
            {
                if (in_token == false) {
                    //first token set type
                    cur_token.type = TOKEN_NUMBER;
                    in_token = true;
                }
                //save char
                cur_token.str[cur_token.len++] = c;
                break;
            }
            default:
            {
                if (in_token == true) {
                    //token end
                    cur_token.str[cur_token.len] = '\0';
                    if (cur_token.len) {
                        printf("token type %d: str [%s] \n", cur_token.type, cur_token.str);
                        //get back for next time parse from current char
                        str--;
                    }
                    else {
                        printf("warning unexpect here");
                    }
                    cur_token.len = 0;
                    in_token = false;
                }
                else {
                    //do nothing
                    printf("[%c]\n", c);
                }
                break;
            }
        }

        if (c == '\0') {
            printf("line end\n");
            return;
        }
    }

}

int main(int argc, char* argv[])
{
    printf("please input string to parse\n");
    char string[1024];
    while(1)
    {
        gets(string);
        parse_token(string);
    }
}

运行结果