编译原理课程设计-词法分析器(附含源代码)

编译原理-词法分析器的设计

一．设计说明及设计要求

一般来说，编译程序的整个过程可以划分为五个阶段：词法分析、语法分析、中间代码生成、优化和目标代码生成。本课程设计即为词法分析阶段。词法分析阶段是编译过程的第一个阶段。这个阶段的任务是从左到右一个字符一个字符地读入源程序，对构成源程序的字符流进行扫描和分解，从而识别出一个个单词（也称单词符号或符号）。如保留字（关键字或基本字）、标志符、常数、算符和界符等等。

二．设计中相关关键字说明

1．基本字：也称关键字，如C语言中的 if , else ,

while , do ,for,case,break, return 等。

2．标志符：用来表示各种名字，如常量名、变量名和过程名等。

3．常数：各种类型的常数，如12，6.88，和“ABC”

等。

4．运算符：如 + ，- , * , / ,%, < , > ,<= , >= 等。5．界符，如逗点，冒号，分号，括号，# ，〈〈，〉〉等。

三、程序分析

词法分析是编译的第一个阶段，它的主要任务是从左到右逐个字符地对源

程序进行

扫描，产生一个个单词序列，用以语法分析。词法分析工作可以是独立的一遍，把字符流的源程序变为单词序列，输出在一个中间文件上，这个文件做为语法分析程序的输入而继续编译过程。然而，更一般的情况，常将

词法分析程序设计成一个子程序，每当语法分析程序需要一个单词时，则调用该子程序。词法分析程序每得到一次调用，便从源程序文件中读入一些字符，直到识别出一个单词，或说直到下一个单词的第一个字符为止。

四、模块设计

下面是程序的流程图

五、程序介绍

在程序当前目录里建立一个文本文档，取名为infile.txt,所有需要分析的程序都写在此文本文档里，程序的结尾必须以“@”标志符结束。程序结果输出在同一个目录下，文件名为outfile.txt，此文件为自动生成。本程序所输出的单词符号采用以下二元式表示：（单词种别，单词自身的值）如程序输出结果(57,"#")(33,"include")(52,"<")(33,"iostream") 等。

程序的功能：（1）能识别C语言中所有关键字（共32个）（单词种别分别为1 — 32 ，详情见程序代码相关部分，下同）

（2）能识别C语言中自定义的标示符（单词种别为 33）

（3）能识别C语言中的常数（单词种别为0）

（4）能识别C语言中几乎所有运算符（单词种别分别为41 — 54）

（5）能识别C语言中绝大多数界符（单词种别分别为 55 — 66）六、运行结果

输入文件infile.txt

运行结果（输出文件 outfile.txt）

七、设计体会

八、附录部分（程序代码）

提示：文件的打开和读写函数：

FILE *fp,*out; //定义文件指针

fp=fopen("infile.txt","r"))

如果打开文件"infile.txt"失败，则函数返回NULL，即fp=NULL，第二个参数“r”表示以只读方式打开，如果为”w”，则以可写方式打开

调用fgetc(fp)这个函数一次从fp所指向的文件读取一个字符

char ch=fgetc(fp);

想文件写字符的函数为fprintf(FILE * fp,写进的内容)

比如下面的调用fprintf(outfile,"abcd\n")是把字符串“abcd”写到文件outfile的末尾，并且在后面加上了一个换行标志

文件读写完成后要用函数fclose(fp)关闭。

源代码

#include "stdio.h"

#include "string.h"

#include "ctype.h"

void analzid(FILE *output,char *p)

{

int i=0;

int count=0;

if (isalpha(p[0]))

{if (strcmp(p,"if")==0) {fprintf(output,"(3,if)\n");}

else if(strcmp(p,"then")==0) {fprintf(output,"(4,then)\n");}

else if(strcmp(p,"else")==0) {fprintf(output,"(5,else)\n");}

else if(strcmp(p,"while")==0) {fprintf(output,"(6,while)\n");}

else if(strcmp(p,"do")==0) {fprintf(output,"(7,do)\n");}

else if(strcmp(p,"begin")==0) {fprintf(output,"(8,begin)\n");}

else if(strcmp(p,"end")==0) {fprintf(output,"(9,end)\n");}

else if(strcmp(p,"long")==0) {fprintf(output,"(10,long)\n");}

else if(strcmp(p,"switch")==0) {fprintf(output,"(11,switch)\n");} else if(strcmp(p,"case")==0) {fprintf(output,"(12,case)\n");}

else if(strcmp(p,"enum")==0) {fprintf(output,"(13,enum)\n");}

else if(strcmp(p,"register")==0) {fprintf(output,"(14,register)\n");} else if(strcmp(p,"typedef")==0) {fprintf(output,"(15,typedef)\n");} else if(strcmp(p,"char")==0) {fprintf(output,"(16,char)\n");}

else if(strcmp(p,"extern")==0) {fprintf(output,"(17,extern)\n");}

else if(strcmp(p,"return")==0) {fprintf(output,"(18,return)\n");}

else if(strcmp(p,"union")==0) {fprintf(output,"(19,union)\n");}

else if(strcmp(p,"const")==0) {fprintf(output,"(20,const)\n");}

else if(strcmp(p,"float")==0) {fprintf(output,"(21,float)\n");}

else if(strcmp(p,"short")==0) {fprintf(output,"(22,short)\n");}

else if(strcmp(p,"unsigned")==0) {fprintf(output,"(23,unsigned)\n");} else if(strcmp(p,"continue")==0) {fprintf(output,"(24,continue)\n");} else if(strcmp(p,"for")==0) {fprintf(output,"(25,for)\n");}

else if(strcmp(p,"signed")==0) {fprintf(output,"(26,signed)\n");} else if(strcmp(p,"void")==0) {fprintf(output,"(27,void)\n");}

else if(strcmp(p,"default")==0) {fprintf(output,"(28,default)\n");} else if(strcmp(p,"goto")==0) {fprintf(output,"(29,goto)\n");}

else if(strcmp(p,"sizeof")==0) {fprintf(output,"(30,sizeof)\n");} else if(strcmp(p,"volatile")==0) {fprintf(output,"(43,volatile)\n");} else if(strcmp(p,"auto")==0) {fprintf(output,"(44,auto)\n");}

else if(strcmp(p,"double")==0) {fprintf(output,"(45,double)\n");} else if(strcmp(p,"int")==0) {fprintf(output,"(46,int)\n");}

else if(strcmp(p,"struct")==0) {fprintf(output,"(47,struct)\n");} else if(strcmp(p,"break")==0) {fprintf(output,"(48,break)\n");}

else if(strcmp(p,"static")==0) {fprintf(output,"(49,static)\n");} else {fprintf(output,"(1,%s)\n",p);}

}

else

{for(;i<(int)strlen(p);i++) if(isdigit(p[i])) count++;

if (count==(int)strlen(p))

{fprintf(output,"(2,%s)\n",p);}

else

if (p[0]=='_'&&(isalpha(p[1])))

{fprintf(output,"(1,%s)\n",p);}

else {fprintf(output,"%s 未定义\n",p);}

}

}

void analzsy(FILE *outfile,char *p)

{

if (strcmp(p,"=")==0) {fprintf(outfile,"(37,=)\n");}

else if(strcmp(p,"+")==0) {fprintf(outfile,"(31,+)\n");}

else if(strcmp(p,"-")==0) {fprintf(outfile,"(32,-)\n");}

else if(strcmp(p,"*")==0) {fprintf(outfile,"(33,*)\n");}

else if(strcmp(p,"/")==0) {fprintf(outfile,"(34,/)\n");}

else if(strcmp(p,"(")==0) {fprintf(outfile,"(52,()\n");}

else if(strcmp(p,")")==0) {fprintf(outfile,"(53,))\n");}

else if(strcmp(p,"[")==0) {fprintf(outfile,"(55,[)\n");}

else if(strcmp(p,"]")==0) {fprintf(outfile,"(56,])\n");}

else if(strcmp(p,"{")==0) {fprintf(outfile,"(57,{)\n");}

else if(strcmp(p,"}")==0) {fprintf(outfile,"(58,})\n");}

else if(strcmp(p,"<<")==0) {fprintf(outfile,"(59,<<)\n");}

else if(strcmp(p,">>")==0) {fprintf(outfile,"(60,>>)\n");}

else if(strcmp(p,"'")==0) {fprintf(outfile,"(61,')\n");}

else if(strcmp(p,"#")==0) {fprintf(outfile,"(62,#)\n");}

else if(strcmp(p,".")==0) {fprintf(outfile,"(64,.)\n");}

else if(strcmp(p,"*")==0) {fprintf(outfile,"(33,*)\n");}

else if(strcmp(p,"/")==0) {fprintf(outfile,"(34,/)\n");}

else if(strcmp(p,"%")==0) {fprintf(outfile,"(40,%)\n");}

else if(strcmp(p,",")==0) {fprintf(outfile,"(64,,)\n");}

else if(strcmp(p,":")==0) {fprintf(outfile,"(65,:)\n");}

else if(strcmp(p,";")==0) {fprintf(outfile,"(54,;)\n");}

else if(strcmp(p,">")==0) {fprintf(outfile,"(36,>)\n");}

else if(strcmp(p,"<")==0) {fprintf(outfile,"(35,<)\n");}

else if(strcmp(p,">=")==0) {fprintf(outfile,"(39,>=)\n");}

else if(strcmp(p,"<=")==0) {fprintf(outfile,"(38,<=)\n");}

else if(strcmp(p,"==")==0) {fprintf(outfile,"(41,==)\n");}

else if(strcmp(p,"!=")==0) {fprintf(outfile,"(42,!=)\n");}

else if(strcmp(p," ")==0) ;

else if(strcmp(p,"\n")==0) ;

else {fprintf(outfile,"%s 未定义\n",p);}

}

void main()

{FILE *fp,*out;

int i=0,x=0,y=0;

int EA=0;

char ch,str[10000],idstr[10],systr[2];

if((fp=fopen("infile.txt","r"))==NULL)

{printf("Can not open infile!\n");

exit(0);}

if((out=fopen("outfile.txt","w"))==NULL)

{printf("Can not open outfile!\n");

exit(0);}

ch=fgetc(fp);

while(ch!=EOF)

{str[i]=ch;str[i+1]='\0';i++;ch=fgetc(fp);}

i=0;

while(1)

{

if(str[i]=='@') break;

else

if((str[i]>='a'&&str[i]<='z')||(str[i]>='A'&&str[i]<='Z')|| (str[i]>='0'&&str[i]<='9')||(str[i]=='_'))

{idstr[x]=str[i];idstr[x+1]='\0';x++;i++;EA=1;}

else

{

x=0;

if((strlen(idstr)!=0)&&(EA)) analzid(out,idstr);

idstr[x]='\0';

if(str[i]<'0'||(str[i]>'9'&&str[i]<'A')||

(str[i]>'Z'&&str[i]<'a')||str[i]>'z')

{

if(str[i]!='!'&&str[i]!='='&&str[i]!='<'&&str[i]!='>') {

systr[y]=str[i];systr[y+1]='\0';analzsy(out,systr);i++; }

else

if((str[i]=='!'&&str[i+1]=='=')||(str[i]=='='&&str[i+1]=='=')||

(str[i]=='>'&&str[i+1]=='=')||(str[i]=='<'&&str[i+1]=='=')||

(str[i]=='<'&&str[i+1]=='<')||(str[i]=='>'&&str[i+1]=='>'))

{

systr[y]=str[i];systr[y+1]=str[i+1];systr[y+2]='\0'; analzsy(out,systr);i++;i++;

}

else

{

systr[y]=str[i];systr[y+1]='\0';analzsy(out,systr);i++;

}}}}

printf("-----全部结果已经存入outfile.txt文档-----\n");

fprintf(out,"--------完成--------");

fclose(fp);

fclose(out);

}

（注：文档可能无法思考全面，请浏览后下载，供参考。可复制、编制，期待你的好评与关注！）