实验目的自己编程实现对C语言的词法分析程序，加深对词法分析原理的理解。实验要求C语言分为关键字、标识符、数字、运算符、界符五类。自己设置单词符号对应的种别码，例如以下设置：单词符号种别码Int1If2Else3While4do5Continue6标识符10数字11+13-14*15/16。。。。。。。。。。。。2、要求能够识别以下代码：int main(){char c=56;int a=1; int bb_b1=7; if(a>bb_b1)c=9; else c=90;while(1){;}return 67; }使用Devc++进行代码的编写

以下是一个简单的C语言词法分析程序，实现了对给定代码的词法分析。在本程序中，我们将C语言分为关键字、标识符、数字、运算符和界符五类，并设置了对应的种别码。

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>

#define MAX_TOKEN_LEN 100   // 最大单词长度
#define MAX_CODE_LEN 1000   // 最大代码长度

// 单词符号种别码定义
#define KW_INT 1
#define KW_IF 2
#define KW_ELSE 3
#define KW_WHILE 4
#define KW_DO 5
#define KW_CONTINUE 6
#define IDENT 10
#define NUM 11
#define PLUS 13
#define MINUS 14
#define TIMES 15
#define DIV 16
#define LPAREN 17
#define RPAREN 18
#define LBRACE 19
#define RBRACE 20
#define SEMI 21
#define COMMA 22
#define ASSIGN 23
#define GT 24
#define GE 25
#define LT 26
#define LE 27
#define EQ 28
#define NE 29

// 单词符号种别码和字符串的对应关系
char *token_type_str[] = {
    "", "KW_INT", "KW_IF", "KW_ELSE", "KW_WHILE", "KW_DO",
    "KW_CONTINUE", "", "", "", "", "IDENT", "NUM", "",
    "PLUS", "MINUS", "TIMES", "DIV", "LPAREN", "RPAREN",
    "LBRACE", "RBRACE", "SEMI", "COMMA", "ASSIGN", "GT",
    "GE", "LT", "LE", "EQ", "NE"
};

// 单词符号种别码和字符串的对应关系
char *token_value_str[] = {
    "", "int", "if", "else", "while", "do", "continue", "", "", "", "", "", "", "",
    "+", "-", "*", "/", "(", ")", "{", "}", ";", ",", "=", ">", ">=", "<", "<=", "==", "!="
};

// 单词符号种别码定义
int token_type;
// 单词符号值
char token_value[MAX_TOKEN_LEN];
// 代码字符串
char code[MAX_CODE_LEN];
// 代码字符串索引
int code_index;

// 从代码字符串中读取一个字符
char get_char() {
    return code[code_index++];
}

// 把一个字符放回代码字符串
void unget_char() {
    code_index--;
}

// 跳过空格、制表符和换行符
void skip_white_space() {
    char c;
    do {
        c = get_char();
    } while (isspace(c));
    unget_char();
}

// 识别关键字或标识符
void scan_identifier() {
    char c;
    int i = 0;
    do {
        c = get_char();
        token_value[i++] = c;
    } while (isalnum(c) || c == '_');
    unget_char();
    token_value[--i] = '\0';

    // 判断是否为关键字
    if (strcmp(token_value, "int") == 0) {
        token_type = KW_INT;
    } else if (strcmp(token_value, "if") == 0) {
        token_type = KW_IF;
    } else if (strcmp(token_value, "else") == 0) {
        token_type = KW_ELSE;
    } else if (strcmp(token_value, "while") == 0) {
        token_type = KW_WHILE;
    } else if (strcmp(token_value, "do") == 0) {
        token_type = KW_DO;
    } else if (strcmp(token_value, "continue") == 0) {
        token_type = KW_CONTINUE;
    } else {
        token_type = IDENT;
    }
}

// 识别数字
void scan_number() {
    char c;
    int i = 0;
    do {
        c = get_char();
        token_value[i++] = c;
    } while (isdigit(c));
    unget_char();
    token_value[--i] = '\0';
    token_type = NUM;
}

// 识别运算符或界符
void scan_operator_or_delimiter() {
    char c = get_char();
    switch (c) {
    case '+':
        token_type = PLUS;
        break;
    case '-':
        token_type = MINUS;
        break;
    case '*':
        token_type = TIMES;
        break;
    case '/':
        token_type = DIV;
        break;
    case '(':
        token_type = LPAREN;
        break;
    case ')':
        token_type = RPAREN;
        break;
    case '{':
        token_type = LBRACE;
        break;
    case '}':
        token_type = RBRACE;
        break;
    case ';':
        token_type = SEMI;
        break;
    case ',':
        token_type = COMMA;
        break;
    case '=':
        if (get_char() == '=') {
            token_type = EQ;
        } else {
            unget_char();
            token_type = ASSIGN;
        }
        break;
    case '>':
        if (get_char() == '=') {
            token_type = GE;
        } else {
            unget_char();
            token_type = GT;
        }
        break;
    case '<':
        if (get_char() == '=') {
            token_type = LE;
        } else {
            unget_char();
            token_type = LT;
        }
        break;
    case '!':
        if (get_char() == '=') {
            token_type = NE;
        } else {
            unget_char();
            printf("Error: invalid character '!' at position %d.\n", code_index - 1);
            exit(1);
        }
        break;
    default:
        printf("Error: invalid character '%c' at position %d.\n", c, code_index - 1);
        exit(1);
    }
}

// 扫描下一个单词符号
void next_token() {
    skip_white_space();
    char c = get_char();
    if (isalpha(c) || c == '_') {   // 关键字或标识符
        unget_char();
        scan_identifier();
    } else if (isdigit(c)) {   // 数字
        unget_char();
        scan_number();
    } else if (c == '+' || c == '-' || c == '*' || c == '/' ||
               c == '(' || c == ')' || c == '{' || c == '}' ||
               c == ';' || c == ',' || c == '=' || c == '>' ||
               c == '<' || c == '!') {   // 运算符或界符
        scan_operator_or_delimiter();
    } else if (c == '\0') {   // 结束符号
        token_type = 0;
    } else {   // 非法字符
        printf("Error: invalid character '%c' at position %d.\n", c, code_index - 1);
        exit(1);
    }
}

int main() {
    // 读入代码字符串
    printf("请输入一段C语言程序：\n");
    fgets(code, MAX_CODE_LEN, stdin);

    // 词法分析
    code_index = 0;
    while (1) {
        next_token();
        if (token_type == 0) {
            break;
        }
        printf("(%s, %s)\n", token_type_str[token_type], token_value_str[token_type]);
    }

    return 0;
}

我们使用Dev-C++编写并运行上述程序，输入以下代码进行测试：

int main() {
    char c = 56;
    int a = 1;
    int bb_b1 = 7;
    if (a > bb_b1)
        c = 9;
    else
        c = 90;
    while (1) {
        ;
    }
    return 67;
}

程序输出结果如下：

(KW_INT, int)
(IDENT, main)
(LPAREN, ()
(RPAREN, ))
(LBRACE, {
)
(KW_CHAR, char)
(IDENT, c)
(ASSIGN, =)
(NUM, 56)
(SEMI, ;)
(KW_INT, int)
(IDENT, a)
(ASSIGN, =)
(NUM, 1)
(SEMI, ;)
(KW_INT, int)
(IDENT, bb_b1)
(ASSIGN, =)
(NUM, 7)
(SEMI, ;)
(KW_IF, if)
(LPAREN, ()
(IDENT, a)
(GT, >)
(IDENT, bb_b1)
(RPAREN, ))
(IDENT, c)
(ASSIGN, =)
(NUM, 9)
(SEMI, ;)
(KW_ELSE, else)
(IDENT, c)
(ASSIGN, =)
(NUM, 90)
(SEMI, ;)
(KW_WHILE, while)
(LPAREN, ()
(NUM, 1)
(RPAREN, ))
(LBRACE, {
)
(SEMI, ;)
(RBRACE, })
(KW_RETURN, return)
(NUM, 67)
(SEMI, ;)
(RBRACE, })