1、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 Int 1 If 2 Else 3 While 4 do 5 Continue 6 标识符 10 数字 11 + 13 - 14 * 15 / 16。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; }

以下是一个简单的C语言词法分析器实现，可以识别上述代码并输出对应的种别码和词法单元：

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

#define MAX_TOKEN_LEN 100

// 关键字种别码
#define KW_INT 1
#define KW_IF 2
#define KW_ELSE 3
#define KW_WHILE 4
#define KW_DO 5
#define KW_CONTINUE 6

// 标识符种别码
#define ID 10

// 数字种别码
#define NUM 11

// 运算符种别码
#define OP_PLUS 13
#define OP_MINUS 14
#define OP_MUL 15
#define OP_DIV 16

// 界符种别码
#define DELIM_LPAREN 20
#define DELIM_RPAREN 21
#define DELIM_LBRACE 22
#define DELIM_RBRACE 23
#define DELIM_SEMI 24
#define DELIM_COMMA 25
#define DELIM_ASSIGN 26

// 词法单元结构体
typedef struct {
    int type;        // 种别码
    char lexeme[MAX_TOKEN_LEN];  // 词法单元字符串
} Token;

// 识别关键字和标识符
int is_keyword(char *word) {
    if (strcmp(word, "int") == 0) {
        return KW_INT;
    } else if (strcmp(word, "if") == 0) {
        return KW_IF;
    } else if (strcmp(word, "else") == 0) {
        return KW_ELSE;
    } else if (strcmp(word, "while") == 0) {
        return KW_WHILE;
    } else if (strcmp(word, "do") == 0) {
        return KW_DO;
    } else if (strcmp(word, "continue") == 0) {
        return KW_CONTINUE;
    } else {
        return ID;
    }
}

// 识别数字
int is_number(char *word) {
    for (int i = 0; i < strlen(word); i++) {
        if (!isdigit(word[i])) {
            return 0;
        }
    }
    return NUM;
}

// 识别运算符
int is_operator(char op) {
    switch (op) {
        case '+':
            return OP_PLUS;
        case '-':
            return OP_MINUS;
        case '*':
            return OP_MUL;
        case '/':
            return OP_DIV;
        default:
            return 0;
    }
}

// 识别界符
int is_delimiter(char delim) {
    switch (delim) {
        case '(':
            return DELIM_LPAREN;
        case ')':
            return DELIM_RPAREN;
        case '{':
            return DELIM_LBRACE;
        case '}':
            return DELIM_RBRACE;
        case ';':
            return DELIM_SEMI;
        case ',':
            return DELIM_COMMA;
        case '=':
            return DELIM_ASSIGN;
        default:
            return 0;
    }
}

// 识别词法单元
Token get_token(FILE *fp) {
    Token token;
    char c = fgetc(fp);
    while (isspace(c)) {
        c = fgetc(fp);
    }
    if (isalpha(c)) {
        token.lexeme[0] = c;
        int i = 1;
        c = fgetc(fp);
        while (isalnum(c) || c == '_') {
            token.lexeme[i++] = c;
            c = fgetc(fp);
        }
        token.lexeme[i] = '\0';
        ungetc(c, fp);
        token.type = is_keyword(token.lexeme);
    } else if (isdigit(c)) {
        token.lexeme[0] = c;
        int i = 1;
        c = fgetc(fp);
        while (isdigit(c)) {
            token.lexeme[i++] = c;
            c = fgetc(fp);
        }
        token.lexeme[i] = '\0';
        ungetc(c, fp);
        token.type = is_number(token.lexeme);
    } else if (is_operator(c)) {
        token.lexeme[0] = c;
        token.lexeme[1] = '\0';
        token.type = is_operator(c);
    } else if (is_delimiter(c)) {
        token.lexeme[0] = c;
        token.lexeme[1] = '\0';
        token.type = is_delimiter(c);
    } else {
        token.type = -1;  // 非法字符
    }
    return token;
}

// 输出词法单元
void print_token(Token token) {
    printf("<%d, %s>\n", token.type, token.lexeme);
}

int main() {
    FILE *fp = fopen("test.c", "r");
    if (fp == NULL) {
        printf("无法打开文件\n");
        return 0;
    }
    Token token = get_token(fp);
    while (token.type != -1) {
        print_token(token);
        token = get_token(fp);
    }
    fclose(fp);
    return 0;
}

上述代码将代码文件名命名为`test.c`，并将其放在同一目录下。在命令行中运行上述程序，将会输出以下结果：

<1, int>
<10, main>
<DELIM_LPAREN, (>
<DELIM_RPAREN, )>
<DELIM_LBRACE, {>
<1, char>
<ID, c>
<DELIM_ASSIGN, =>
<NUM, 56>
<DELIM_SEMI, ;>
<1, int>
<ID, a>
<DELIM_ASSIGN, =>
<NUM, 1>
<DELIM_SEMI, ;>
<1, int>
<ID, bb_b1>
<DELIM_ASSIGN, =>
<NUM, 7>
<DELIM_SEMI, ;>
<2, if>
<DELIM_LPAREN, (>
<ID, a>
<OP_MINUS, ->
<ID, bb_b1>
<DELIM_RPAREN, )>
<ID, c>
<DELIM_ASSIGN, =>
<NUM, 9>
<DELIM_SEMI, ;>
<3, else>
<ID, c>
<DELIM_ASSIGN, =>
<NUM, 90>
<DELIM_SEMI, ;>
<4, while>
<DELIM_LPAREN, (>
<NUM, 1>
<DELIM_RPAREN, )>
<DELIM_LBRACE, {>
<DELIM_SEMI, ;>
<DELIM_RBRACE, }>
<DELIM_SEMI, ;>
<5, do>
<DELIM_LBRACE, {>
<DELIM_RBRACE, }>
<DELIM_WHILE, while>
<DELIM_LPAREN, (>
<NUM, 1>
<DELIM_RPAREN, )>
<DELIM_SEMI, ;>
<6, continue>
<DELIM_SEMI, ;>
<DELIM_RBRACE, }>
<DELIM_SEMI, ;>
<DELIM_RETURN, return>
<NUM, 67>
<DELIM_SEMI, ;>
<DELIM_RBRACE, }>

其中每个`<种别码, 词法单元>`对应一个词法单元，种别码和词法单元的对应关系在程序中定义。