【编译原理】 词法分析实验 基于Flex构造词法分析器

【编译原理】 词法分析实验 基于Flex构造词法分析器

【问题描述】
设计c语言常见单词的正规式,编制lex源文件,利用flex编译得到词法分析的.c文件,继而对该文件编译得到词法分析器。

【输入形式】
输入一段c语言程序

【输出形式】
各类单词的token字,或者给出程序中的单词错误。

【样例输入】

int main(){
    int a = 10;
    double b = 20.9;
    if(a <= b)
        a+=b;
    else a = 0;
    return a;
}

【样例输出】

line1:(type, int)
line1:(keyword, main)
line1:(bracket, ()
line1:(bracket, ))
line1:(bracket, {)
line2:(type, int)
line2:(identify, a)
line2:(OPT, =)
line2:(integer, 10)
line2:(bracket, ;)
line3:(type, double)
line3:(identify, b)
line3:(OPT, =)
line3:(decimal, 20.9)
line3:(bracket, ;)
line4:(keyword, if)
line4:(bracket, ()
line4:(identify, a)
line4:(OPT, <=)
line4:(identify, b)
line4:(bracket, ))
line5:(identify, a)
line5:(OPT, +=)
line5:(identify, b)
line5:(bracket, ;)
line6:(keyword, else)
line6:(identify, a)
line6:(OPT, =)
line6:(integer, 0)
line6:(bracket, ;)
line7:(keyword, return)
line7:(identify, a)
line7:(bracket, ;)
line8:(bracket, })

【样例说明】
需要识别的关键字包括main, return, if, else, do, while, for, scanf, printf, sqrt, abs;type类型包括void, int, double, float, char;运算符(算术、关系、逻辑、位);需要识别的其他单词有标识符, 整数(十进制形式、指数形式),实数(十进制形式、指数形式),字符串(输出类型名为string);过滤注释及空格。

【评分标准】
根据设计文档的质量、lex文件的正确性,代码的正确性、代码的时间空间复杂度、识别单词的种类等综合评分

【Flex源文件代码】

%{
	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>
	int line=1;
	int count=0;
	int atline[1005];
	int type[1005];
	char text[1005][30];
	int errorflag=0;
	int errorcount=0;
%}

DIGIT [0-9]
OINTEGER [0-9]{DIGIT}*
INTEGER ("+"|"-")?{OINTEGER}
DECIMAL	 {INTEGER}"."{OINTEGER}
LETTER [A-Za-z]
IDENTIFY ({LETTER}|_)({LETTER}|{DIGIT}|_)*
OPT "+"|"-"|"*"|"/"|"+="|"-="|"*="|"/="|">"|"<"|"="|">="|"<="|"=="|"++"|"--"
BRACKET "("|")"|"["|"]"|"{"|"}"|","|";"|"\""|"\'"
TYPE void|int|double|char|float
KEYWORD main|return|if|else|do|while|for|scanf|printf|sqrt|abs
TYPEIDENTIFY %{IDENTIFY}|&{IDENTIFY}
COMMENT \/\/(.)*|\/\*(.|\n)*\*\/
FLOAT ({INTEGER}|{DECIMAL})(e|E){INTEGER}
ERROR ({INTEGER}|{DECIMAL})(e|E)

%%

\n {line++;}
{COMMENT} {}
{BRACKET} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=0;}
{OPT} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=1;}
{KEYWORD} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=2;}
{TYPE} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=3;}
{TYPEIDENTIFY} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=4;}
{IDENTIFY} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=5;}
{INTEGER} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=6;}
{DECIMAL} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=7;}
{FLOAT} {count++;atline[count]=line;strcpy(text[count],yytext);type[count]=8;}
{ERROR} {count++;atline[count]=line;strcpy(text[count],yytext);errorcount=count;errorflag=1;}
. {}

%%

int main()
{
	yyin=fopen("test.txt","r");
	yylex();
	fclose(yyin);
	int n=1;
	if(errorflag==1)
	{
		printf("Error at Line %d: Illegal floating point number \"%s\".",atline[errorcount],text[errorcount]);
		return 0;
	}
	while(n<=count)
	{
		printf("line%d:(",atline[n]);
		if(type[n]==0) printf("bracket, ");
		else if(type[n]==1) printf("OPT, ");
		else if(type[n]==2) printf("keyword, ");
		else if(type[n]==3) printf("type, ");
		else if(type[n]==4) printf("typeidentify, ");
		else if(type[n]==5) printf("identify, ");
		else if(type[n]==6) printf("integer, ");
		else if(type[n]==7) printf("decimal, ");
		else if(type[n]==8) printf("float, ");
		printf("%s)\n",text[n]);
		n++;
	}
	return 0;
}
int yywrap()
{
	return 1;
}
  • 2
    点赞
  • 17
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 2
    评论
设计思想 (1)程序主体结构部分: 说明部分 %% 规则部分 %% 辅助程序部分 (2)主体结构的说明 在这里说明部分告诉我们使用的LETTER,DIGIT, IDENT(标识符,通常定义为字母开头的字母数字串)和STR(字符串常量,通常定义为双引号括起来的一串字符)是什么意思.这部分也可以包含一些初始化代码.例如用#include来使用标准的头文件和前向说明(forward ,references).这些代码应该再标记"%{"和"%}"之间;规则部分>可以包括任何你想用来分析的代码;我们这里包括了忽略所有注释中字符的功能,传送ID名称和字符串常量内容到主调函数和main函数的功能. (3)实现原理 程序中先判断这个句语句中每个单元为关键字、常数、运算符、界符,对与不同的单词符号给出不同编码形式的编码,用以区分之。 PL/0语言的EBNF表示 <常量定义>::=<标识符>=<无符号整数>; <标识符>::=<字母>={<字母>|<数字>}; <加法运算符>::=+|- <乘法运算符>::=*|/ <关系运算符>::==|#|<|<=|>|>= <字母>::=a|b|…|X|Y|Z <数字>::=0|1|2|…|8|9 三:设计过程 1. 关键字:void,main,if,then,break,int,Char,float,include,for,while,printfscanf 并为小写。 2."+”;”-”;”*”;”/”;”:=“;”:”;”<“;”<=“;”>“;”>=“;”<>“;”=“;”(“;”)”;”;”;”#”为运算符。 3. 其他标记 如字符串,表示以字母开头的标识符。 4. 空格符跳过。 5. 各符号对应种别码 关键字分别对应1-13 运算符分别对应401-418,501-513。 字符串对应100 常量对应200 结束符# 四:举例说明 目标:实现对常量的判别 代码: digit [0-9] letter [A-Za-z] other_char [!-@\[-~] id ({letter}|[_])({letter}|{digit}|[_])* string {({letter}|{digit}|{other_char})+} int_num {digit}+ %% [ |\t|\n]+ "auto"|"double"|"int"|"struct"|"break"|"else"|"long"|"switch"|"case"|"enum"|"register"|"typedef"|"char"|"extern"|"return"|"union"|"const"|"float"|"short"|"unsigned"|"continue"|"for"|"signed"|"void"|"default"|"goto"|"sizeof"|"do"|"if"|"static"|"while"|"main" {Upper(yytext,yyleng);printf("%s,NULL\n",yytext);} \"([!-~])*\" {printf("CONST_string,%s\n",yytext);} -?{int_num}[.]{int_num}?([E][+|-]?{int_num})? {printf("CONST_real,%s\n",yytext);} "0x"?{int_num} {printf("CONST_int,%s\n",yytext);} ","|";"|"("|")"|"{"|"}"|"["|"]"|"->"|"."|"!"|"~"|"++"|"--"|"*"|"&"|"sizeof"|"/"|"%"|"+"|"-"|">"|"<"|">="|"<="|"=="|"!="|"&"|"^"|"|"|"&"|"||"|"+="|"-="|"*="|"/="|"%="|">>="|"<<="|"&="|"^="|"|="|"=" {printf("%s,NULL\n",yytext);} {id} {printf("ID,%s\n",yytext);} {digit}({letter})+ {printf("error1:%s\n",yytext);} %% #include <ctype.h> Upper(char *s,int l) { int i; for(i=0;i<l;i++) { s[i]=toupper(s[i]); } } yywrap() { return 1; } 五:DFA 六:数据测试 七:心得体会 其实匹配并不困难,主要是C++知识要求相对较高,只要把握住指针就好了。 附源程序: #include<iostream.h> #include<stdio.h> #include<stdlib.h> #include<string.h> int i,j,k,flag,number,status; /*status which is use to judge the string is keywords or not!*/ char ch; char words[10] = {" "}; char program[500]; int Scan(char program[]) { char *keywords[13] = {"void","main","if","then","break","int", "char","float","include","for","while","printf", "scanf"}; number = 0; status = 0; j = 0; ch = program[i++]; /* To handle the lettle space ands tab*/ /*handle letters*/ if ((ch >= 'a') && (ch <= 'z' )) { while ((ch >= 'a') && (ch <= 'z' )) { words[j++]=ch; ch=program[i++]; } i--; words[j++] = '\0'; for (k = 0; k < 13; k++) if (strcmp (words,keywords[k]) == 0) switch(k) { case 0:{ flag = 1; status = 1; break; } case 1:{ flag = 2; status = 1; break; } case 2:{ flag = 3; status = 1; break; } case 3:{ flag = 4; status = 1; break; } case 4:{ flag = 5; status = 1; break; } case 5:{ flag = 6; status = 1; break; } case 6:{ flag = 7; status = 1; break; } case 7:{ flag = 8; status = 1; break; } case 8:{ flag = 9; status = 1; break; } case 9:{ flag = 10; status = 1; break; } case 10:{ flag = 11; status = 1; break; } case 11:{ flag = 12; status = 1; break; } case 12:{ flag = 13; status = 1; break; } } if (status == 0) { flag = 100; } } /*handle digits*/ else if ((ch >= '0') && (ch <= '9')) { number = 0; while ((ch >= '0' ) && (ch <= '9' )) { number = number*10+(ch-'0'); ch = program[i++]; } flag = 200; i--; } /*opereation and edge handle*/ else switch (ch) { case '=':{ if (ch == '=') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 401; } else { i--; flag = 402; } break; } case'>':{ if (ch == '>') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 403; } else { i--; flag = 404; } break; } case'<':{ if (ch == '<') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 405; } else { i--; flag = 406; } break; } case'!':{ if (ch == '!') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 407; } else { i--; flag = 408; } break; } case'+':{ if (ch == '+') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 409; } else if (ch == '+') { words[j++] = ch; words[j] = '\0'; flag = 410; } else { i--; flag = 411; } break; } case'-':{ if (ch == '-') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 412; } else if( ch == '-') { words[j++] = ch; words[j] = '\0'; flag = 413; } else { i--; flag = 414; } break; } case'*':{ if (ch == '*') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 415; } else { i--; flag = 416; } break; } case'/':{ if (ch == '/') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 417; } else { i--; flag = 418; } break; } case';':{ words[j] = ch; words[j+1] = '\0'; flag = 501; break; } case'(':{ words[j] = ch; words[j+1] = '\0'; flag = 502; break; } case')':{ words[j] = ch; words[j+1] = '\0'; flag = 503; break; } case'[':{ words[j] = ch; words[j+1] = '\0'; flag = 504; break; } case']':{ words[j] = ch; words[j+1] = '\0'; flag = 505; break; } case'{':{ words[j] = ch; words[j+1] = '\0'; flag = 506; break; } case'}':{ words[j] = ch; words[j+1] = '\0'; flag = 507; break; } case':':{ words[j] = ch; words[j+1] = '\0'; flag = 508; break; } case'"':{ words[j] = ch; words[j+1] = '\0'; flag = 509; break; } case'%':{ if (ch == '%') words[j++] = ch; words[j] = '\0'; ch = program[i++]; if (ch == '=') { words[j++] = ch; words[j] = '\0'; flag = 510; } else { i--; flag = 511; } break; } case',':{ words[j] = ch; words[j+1] = '\0'; flag = 512; break; } case'#':{ words[j] = ch; words[j+1] = '\0'; flag = 513; break; } case'@':{ words[j] = '#'; flag = 0; break; } default:{ flag = -1; break; } } return flag; } main() { i=0; printf("please input a program end with @"); do { ch = getchar(); program[i++] = ch; }while(ch != '@'); i = 0; do{ flag = Scan(program); if (flag == 200) { printf("(%2d,%4d)",flag,number); } else if (flag == -1) { printf("(%d,error)",flag); } else { printf("(%2d,%4s)",flag,words); } }while (flag != 0); system("pause"); }
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

球王武磊

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值