C语言的词法分析器代码

这是一个简单的C语言词法分析器代码，可以识别C语言中的关键字、标识符、常量和运算符。

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

#define MAX_TOKEN_LENGTH 100

typedef enum {
    KEYWORD,
    IDENTIFIER,
    NUMBER,
    OPERATOR
} TokenType;

typedef struct {
    TokenType type;
    char value[MAX_TOKEN_LENGTH];
} Token;

Token getNextToken(FILE *fp);
int isKeyword(char *token);
int isOperator(char ch);

int main() {
    FILE *fp;
    Token token;

    fp = fopen("input.c", "r");
    if(fp == NULL) {
        printf("Error opening file.\n");
        return 1;
    }

    while((token = getNextToken(fp)).type != EOF) {
        printf("%s\n", token.value);
    }

    fclose(fp);
    return 0;
}

Token getNextToken(FILE *fp) {
    Token token;
    char ch;
    int i = 0;

    token.type = EOF;
    memset(token.value, 0, MAX_TOKEN_LENGTH);

    while((ch = fgetc(fp)) != EOF) {
        if(isspace(ch)) {
            continue;
        }

        if(isalpha(ch)) {
            token.type = IDENTIFIER;
            token.value[i++] = ch;
            while(isalnum(ch = fgetc(fp))) {
                token.value[i++] = ch;
            }
            ungetc(ch, fp);
            if(isKeyword(token.value)) {
                token.type = KEYWORD;
            }
            break;
        }

        if(isdigit(ch)) {
            token.type = NUMBER;
            token.value[i++] = ch;
            while(isdigit(ch = fgetc(fp))) {
                token.value[i++] = ch;
            }
            ungetc(ch, fp);
            break;
        }

        if(isOperator(ch)) {
            token.type = OPERATOR;
            token.value[i++] = ch;
            if((ch == '>' || ch == '<') && (ch = fgetc(fp)) == '=') {
                token.value[i++] = ch;
            } else {
                ungetc(ch, fp);
            }
            break;
        }
    }

    return token;
}

int isKeyword(char *token) {
    char *keywords[] = {"auto", "break", "case", "char", "const", "continue", 
                        "default", "do", "double", "else", "enum", "extern", 
                        "float", "for", "goto", "if", "int", "long", "register", 
                        "return", "short", "signed", "sizeof", "static", 
                        "struct", "switch", "typedef", "union", "unsigned", 
                        "void", "volatile", "while"};
    int i, numKeywords = sizeof(keywords) / sizeof(keywords[0]);

    for(i = 0; i < numKeywords; i++) {
        if(strcmp(token, keywords[i]) == 0) {
            return 1;
        }
    }

    return 0;
}

int isOperator(char ch) {
    char operators[] = "+-*/%=&|<>^!~?";
    int i, numOperators = sizeof(operators) / sizeof(operators[0]);

    for(i = 0; i < numOperators; i++) {
        if(ch == operators[i]) {
            return 1;
        }
    }

    return 0;
}

该代码通过`getNextToken`函数逐个读取输入文件中的字符，并根据字符类型生成相应的Token。`isKeyword`和`isOperator`函数用于判断识别出的Token是否为关键字和运算符。程序将Token的类型和值保存在Token结构体中，并在主函数中输出Token的值。

该代码仅仅是一个简单的词法分析器，无法处理C语言中的复杂语法结构，例如函数调用、数组等。对于更复杂的语法分析，需要使用更复杂的算法和数据结构，例如递归下降分析器、自动机等。