c语言构造词法分析程序

下面是一个简单的C语言词法分析程序示例：

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

#define MAX_TOKEN_LENGTH 100

enum TokenType {
    KEYWORD,
    IDENTIFIER,
    INTEGER,
    FLOAT,
    OPERATOR,
    PUNCTUATOR,
};

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

int isKeyword(char* tokenValue) {
    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, count = sizeof(keywords) / sizeof(char*);
    for (i = 0; i < count; i++) {
        if (strcmp(keywords[i], tokenValue) == 0) {
            return 1;
        }
    }
    return 0;
}

int isOperator(char ch) {
    char* operators = "+-*/%=<>&|!";
    return strchr(operators, ch) != NULL;
}

int isPunctuator(char ch) {
    char* punctuators = "()[]{};,.:#?";
    return strchr(punctuators, ch) != NULL;
}

void lex(char* input) {
    int length = strlen(input);
    int i = 0;
    while (i < length) {
        if (isspace(input[i])) {
            i++;
            continue;
        }
        struct Token token;
        memset(&token, 0, sizeof(struct Token));
        if (isalpha(input[i]) || input[i] == '_') { // identifier or keyword
            int j = 0;
            while (isalnum(input[i]) || input[i] == '_') {
                token.value[j++] = input[i++];
            }
            token.value[j] = '\0';
            if (isKeyword(token.value)) {
                token.type = KEYWORD;
            } else {
                token.type = IDENTIFIER;
            }
        } else if (isdigit(input[i])) { // integer or float
            int j = 0;
            while (isdigit(input[i])) {
                token.value[j++] = input[i++];
            }
            if (input[i] == '.') {
                token.value[j++] = input[i++];
                while (isdigit(input[i])) {
                    token.value[j++] = input[i++];
                }
                token.type = FLOAT;
            } else {
                token.type = INTEGER;
            }
            token.value[j] = '\0';
        } else if (isOperator(input[i])) { // operator
            int j = 0;
            while (isOperator(input[i])) {
                token.value[j++] = input[i++];
            }
            token.value[j] = '\0';
            token.type = OPERATOR;
        } else if (isPunctuator(input[i])) { // punctuator
            token.value[0] = input[i++];
            token.value[1] = '\0';
            token.type = PUNCTUATOR;
        } else {
            printf("Invalid character: %c\n", input[i]);
            i++;
            continue;
        }
        printf("%s\t%d\n", token.value, token.type);
    }
}

int main() {
    char input[1000];
    printf("Enter C code:\n");
    fgets(input, 1000, stdin);
    printf("Token\tType\n");
    lex(input);
    return 0;
}

该程序使用了一个Token结构体来表示词法分析的结果，包含了token的类型和值。该程序将输入的C代码分割成了多个token，并且识别了关键字、标识符、整数、浮点数、运算符和标点符号等不同类型的token。程序也能够处理无效的字符并给出错误提示。