词法分析器代码c语言

词法分析器是编译器的重要组成部分，用于将源代码转换为词法单元。以下是一个简单的词法分析器的C语言代码：

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

#define MAX_LENGTH 100

typedef enum {
    INT,
    FLOAT,
    IDENTIFIER,
    ADD_OP,
    SUB_OP,
    MUL_OP,
    DIV_OP,
    ASSIGN_OP,
    SEMICOLON,
    INVALID
} TokenType;

typedef struct {
    TokenType type;
    char lexeme[MAX_LENGTH];
} Token;

Token getNextToken(FILE* fp) {
    Token token;
    char ch;
    int lexemeIndex = 0;
    token.type = INVALID;

    // 忽略空格和换行符
    while ((ch = fgetc(fp)) != EOF && isspace(ch));

    if (ch == EOF) {
        token.lexeme[0] = '\0';
        return token;
    }

    // 处理整数和浮点数
    if (isdigit(ch)) {
        token.type = INT;

        while (isdigit(ch)) {
            if (lexemeIndex >= MAX_LENGTH - 1) {
                printf("Error: Token length exceeds the maximum limit.\n");
                exit(1);
            }
            token.lexeme[lexemeIndex++] = ch;
            ch = fgetc(fp);
        }

        if (ch == '.') {
            token.type = FLOAT;
            token.lexeme[lexemeIndex++] = ch;
            ch = fgetc(fp);
            
            while (isdigit(ch)) {
                if (lexemeIndex >= MAX_LENGTH - 1) {
                    printf("Error: Token length exceeds the maximum limit.\n");
                    exit(1);
                }
                token.lexeme[lexemeIndex++] = ch;
                ch = fgetc(fp);
            }
        }

        token.lexeme[lexemeIndex] = '\0';
        ungetc(ch, fp);
        return token;
    }

    // 处理标识符和关键字
    if (isalpha(ch)) {
        while (isalnum(ch)) {
            if (lexemeIndex >= MAX_LENGTH - 1) {
                printf("Error: Token length exceeds the maximum limit.\n");
                exit(1);
            }
            token.lexeme[lexemeIndex++] = ch;
            ch = fgetc(fp);
        }

        token.lexeme[lexemeIndex] = '\0';
        ungetc(ch, fp);

        // 检查是否是关键字
        if (strcmp(token.lexeme, "if") == 0 || strcmp(token.lexeme, "else") == 0 || strcmp(token.lexeme, "while") == 0) {
            token.type = KEYWORD;
        } else {
            token.type = IDENTIFIER;
        }

        return token;
    }

    // 处理操作符和分号
    switch (ch) {
        case '+':
            token.type = ADD_OP;
            break;
        case '-':
            token.type = SUB_OP;
            break;
        case '*':
            token.type = MUL_OP;
            break;
        case '/':
            token.type = DIV_OP;
            break;
        case '=':
            token.type = ASSIGN_OP;
            break;
        case ';':
            token.type = SEMICOLON;
            break;
    }

    token.lexeme[0] = ch;
    token.lexeme[1] = '\0';
    return token;
}

int main() {
    FILE* fp = fopen("input.txt", "r");
    Token token;

    if (fp == NULL) {
        printf("Error: Failed to open the input file.\n");
        return 1;
    }

    while ((token = getNextToken(fp)).type != INVALID) {
        printf("Type: %d, Lexeme: %s\n", token.type, token.lexeme);
    }

    fclose(fp);
    return 0;
}

以上的代码实现了一个简单的词法分析器，能够识别整数、浮点数、标识符、运算符和分号。