北邮编译原理词法分析的实验报告

❶ 编译原理词法分析

编译的词法分析，一般是先画一个状态转换图，一般是有多少分支，就有多少if语句，分支里面再分（可能有循环语句）。注意记住词的类别和词的字符串，请以以下代码为例，理会一下词法分析的大致过程。
while(s[i]!='#')
{
while(s[i]==' '||s[i]=='\t'||s[i]=='\n')
{
if(s[i]=='\n')
line++;
i++;
}
if(s[i]=='#')
break;
j=i;
if(s[i]>='a'&&s[i]<='z'||s[i]>='A'&&s[i]<='Z')
{
i++;
while(s[i]>='a'&&s[i]<='z'||s[i]>='A'&&s[i]<='Z'||s[i]>='0'&&s[i]<='9')
i++;
if((i-j)==2&&s[j]=='i'&&s[j+1]=='f')
{
strcpy(dancishuzu[dancigeshu].name,"if");
dancishuzu[dancigeshu].bianhao=4;
dancigeshu++;
}
else if((i-j)==3&&s[j]=='i'&&s[j+1]=='n'&&s[j+2]=='t')
{
strcpy(dancishuzu[dancigeshu].name,"int");
dancishuzu[dancigeshu].bianhao=2;
dancigeshu++;
}
else if((i-j)==3&&s[j]=='f'&&s[j+1]=='o'&&s[j+2]=='r')
{
strcpy(dancishuzu[dancigeshu].name,"for");
dancishuzu[dancigeshu].bianhao=6;
dancigeshu++;
}
else if((i-j)==4&&s[j]=='m'&&s[j+1]=='a'&&s[j+2]=='i'&&s[j+3]=='n')
{
strcpy(dancishuzu[dancigeshu].name,"main");
dancishuzu[dancigeshu].bianhao=1;
dancigeshu++;
}
else if ((i-j)==4&&s[j]=='c'&&s[j+1]=='h'&&s[j+2]=='a'&&s[j+3]=='r')
{
strcpy(dancishuzu[dancigeshu].name,"char");
dancishuzu[dancigeshu].bianhao=3;
dancigeshu++;
}
else if ((i-j)==4&&s[j]=='e'&&s[j+1]=='l'&&s[j+2]=='s'&&s[j+3]=='e')
{
strcpy(dancishuzu[dancigeshu].name,"else");
dancishuzu[dancigeshu].bianhao=5;
dancigeshu++;
}
else if ((i-j)==5&&s[j]=='w'&&s[j+1]=='h'&&s[j+2]=='i'&&s[j+3]=='l'&&s[j+4]=='e')
{
strcpy(dancishuzu[dancigeshu].name,"while");
dancishuzu[dancigeshu].bianhao=7;
dancigeshu++;
}
else{
dancishuzu[dancigeshu].bianhao=10;
count=0;
while(j<i)
{
dancishuzu[dancigeshu].name[count++]=s[j];
j++;
}
dancishuzu[dancigeshu].name[count]='\0';
dancigeshu++;
}
}
else if(s[i]>='0'&&s[i]<='9')
{
while(s[i]>='0'&&s[i]<='9')
i++;
dancishuzu[dancigeshu].bianhao=11;
count=0;
while(j<i)
{
dancishuzu[dancigeshu].name[count++]=s[j];
j++;
}
dancishuzu[dancigeshu].name[count]='\0';
dancigeshu++;
}

else if(s[i]=='=')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=30;
strcpy(dancishuzu[dancigeshu].name,"==");
dancigeshu++;
i+=2;
}
else
{
dancishuzu[dancigeshu].bianhao=12;
strcpy(dancishuzu[dancigeshu].name,"=");
dancigeshu++;
i++;
}
}
else if(s[i]=='+')
{
dancishuzu[dancigeshu].bianhao=13;
strcpy(dancishuzu[dancigeshu].name,"+");
dancigeshu++;
i++;
}
else if(s[i]=='-')
{
dancishuzu[dancigeshu].bianhao=14;
strcpy(dancishuzu[dancigeshu].name,"-");
dancigeshu++;
i++;
}
else if(s[i]=='*')
{
dancishuzu[dancigeshu].bianhao=15;
strcpy(dancishuzu[dancigeshu].name,"*");
dancigeshu++;
i++;
}
else if(s[i]=='/')
{
dancishuzu[dancigeshu].bianhao=16;
strcpy(dancishuzu[dancigeshu].name,"/");
dancigeshu++;
i++;
}
else if(s[i]=='(')
{
i++;
dancishuzu[dancigeshu].bianhao=17;
strcpy(dancishuzu[dancigeshu].name,"(");
dancigeshu++;
}
else if(s[i]==')')
{
i++;
dancishuzu[dancigeshu].bianhao=18;
strcpy(dancishuzu[dancigeshu].name,")");
dancigeshu++;
}
else if(s[i]=='[')
{
i++;
dancishuzu[dancigeshu].bianhao=19;
strcpy(dancishuzu[dancigeshu].name,"[");
dancigeshu++;
}
else if(s[i]==']')
{
i++;
dancishuzu[dancigeshu].bianhao=20;
strcpy(dancishuzu[dancigeshu].name,"]");
dancigeshu++;
}
else if(s[i]=='{')
{
i++;
dancishuzu[dancigeshu].bianhao=21;
strcpy(dancishuzu[dancigeshu].name,"{");
dancigeshu++;
}
else if(s[i]=='}')
{
i++;
dancishuzu[dancigeshu].bianhao=22;
strcpy(dancishuzu[dancigeshu].name,"}");
dancigeshu++;
}
else if(s[i]==',')
{
i++;
dancishuzu[dancigeshu].bianhao=23;
strcpy(dancishuzu[dancigeshu].name,",");
dancigeshu++;
}
else if(s[i]==':')
{
i++;
dancishuzu[dancigeshu].bianhao=24;
strcpy(dancishuzu[dancigeshu].name,":");
dancigeshu++;
}
else if(s[i]==';')
{
i++;
dancishuzu[dancigeshu].bianhao=25;
strcpy(dancishuzu[dancigeshu].name,";");
dancigeshu++;
}
else if(s[i]=='>')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=28;
strcpy(dancishuzu[dancigeshu].name,">=");
dancigeshu++;
i+=2;
}
else
{
i++;
dancishuzu[dancigeshu].bianhao=26;
strcpy(dancishuzu[dancigeshu].name,">");
dancigeshu++;
}
}
else if(s[i]=='<')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=29;
strcpy(dancishuzu[dancigeshu].name,"<=");
dancigeshu++;
i+=2;
}
else
{
i++;
dancishuzu[dancigeshu].bianhao=27;
strcpy(dancishuzu[dancigeshu].name,"<");
dancigeshu++;
}
}
else if(s[i]=='!'&&s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=31;
strcpy(dancishuzu[dancigeshu].name,"!=");
dancigeshu++;
i+=2;
}
else
{
printf("\nline:%derror!",line);
i++;
return;
}
}

❷ 编译原理课程设计－词法分析器设计（C语言）

#include"stdio.h"/*定义I/O库所用的某些宏和变量*/

#include"string.h"/*定义字符串库函数*/

#include"conio.h"/*提供有关屏幕窗口操作函数*/

#include"ctype.h"/*分类函数*/

charprog[80]={''},

token[8];/*存放构成单词符号的字符串*/

charch;

intsyn,/*存放单词字符的种别码*/

n,

sum,/*存放整数型单词*/

m,p;/*p是缓冲区prog的指针，m是token的指针*/

char*rwtab[6]={"begin","if","then","while","do","end"};

voidscaner(){

m=0;

sum=0;

for(n=0;n<8;n++)

token[n]='';

ch=prog[p++];

while(ch=='')

ch=prog[p++];

if(isalpha(ch))/*ch为字母字符*/{

while(isalpha(ch)||isdigit(ch))/*ch为字母字符或者数字字符*/{

token[m++]=ch;

ch=prog[p++];}

token[m++]='';

ch=prog[p--];

syn=10;

for(n=0;n<6;n++)

if(strcmp(token,rwtab[n])==0)/*字符串的比较*/{

syn=n+1;

break;}}

else

if(isdigit(ch))/*ch是数字字符*/{

while(isdigit(ch))/*ch是数字字符*/{

sum=sum*10+ch-'0';

ch=prog[p++];}

ch=prog[p--];

syn=11;}

else

switch(ch){

case'<':m=0;token[m++]=ch;ch=prog[p++];

if(ch=='>'){

syn=21;

token[m++]=ch;}

elseif(ch=='='){

syn=22;

token[m++]=ch;}

else{

syn=20;

ch=prog[p--];}

break;

case'>':m=0;token[m++]=ch;ch=prog[p++];

if(ch=='='){

syn=24;

token[m++]=ch;}

else{

syn=23;

ch=prog[p--];}

break;

case':':m=0;token[m++]=ch;ch=prog[p++];

if(ch=='='){

syn=18;

token[m++]=ch;}

else{

syn=17;

ch=prog[p--];}

break;

case'+':syn=13;token[0]=ch;break;

case'-':syn=14;token[0]=ch;break;

case'*':syn=15;token[0]=ch;break;

case'/':syn=16;token[0]=ch;break;

case'=':syn=25;token[0]=ch;break;

case';':syn=26;token[0]=ch;break;

case'(':syn=27;token[0]=ch;break;

case')':syn=28;token[0]=ch;break;

case'#':syn=0;token[0]=ch;break;

default:syn=-1;}}

main()

{

printf(" Thesignificanceofthefigures: "

"1.figures1to6saidKeyword "

"2. "

"3.figures13to28saidOperators ");

p=0;

printf(" pleaseinputstring: ");

do{

ch=getchar();

prog[p++]=ch;

}while(ch!='#');

p=0;

do{

scaner();

switch(syn){

case11:printf("(%d,%d) ",syn,sum);break;

case-1:printf(" ERROR; ");break;

default:printf("(%d,%s) ",syn,token);

}

}while(syn!=0);

getch();

}

程序测试结果

对源程序beginx:=9:ifx>9thenx:=2*x+1/3;end#的源文件，经过词法分析后输出如下图5-1所示：

具体的你在修改修改吧

❸ 编译原理 词法分析程序的设计与实现实验题

说他像苍蝇，是骂苍蝇呢还是骂他呢？

❹ 编译原理 词法分析

你收到了吗，能给我发一份吗

❺ 编译原理实验求助

1)定义
所有token或者叫单词的有限自动机。
2)将有限自动机用代码实现。
3)写分析程序，利用你定义的有限自动机来识别所有的“单词”。并将识别出来的单词的相关信息，如名称，位置，类别等记录在相关的数据结构中。

❻ 递归下降语法分析实验和词法分析实验报告，是编译原理的，做好直接发我邮箱 [email protected]

同求啊 杭电的路过。。

❼ 学了编译原理这门课，要求编一个：词法分析的程序，要求对词法分析至少选择三种不同类型的句子进行单词识

给你一个toyl语言的
#include<stdio.h>
#include<conio.h>
#include<stdlib.h>
#include<windows.h>
#define is_end_of_input(ch) ((ch)=='#')
#define is_letter(ch) ('A'<=(ch)&&(ch)<='Z'||'a'<=(ch)&&(ch)<='z')
#define is_digit(ch) ('0'<=(ch)&&(ch)<='9')
#define is_digit_or_letter(ch) (is_letter(ch)||is_digit(ch))
#define is_operator(ch) ((ch)=='+'||(ch)='-'||(ch)='*')
#define is_layout(ch) (!is_end_of_input(ch)&&(ch)<=' ')
#define Step 10 //字符串每次增长的长度.

typedef struct
{
char * Class;
char seman[];
int len;
int value;
}mytoken;

typedef struct node
{
char words[20];
int length;
int time;
struct node *next;
}mynode;
//全局变量
char ch;
char *fp;
mytoken token;
int TYPE=-1;
int num=1;
int j=0;
int Length=0;
void error()//报错
{
printf("错误\n");
}

char * getstr() //从键盘获取任意长度的输入函数实现
{
char *temp, *str=(char *)malloc(10);
int c=0, len=0, times=1, number=0;
if(!str)
{
printf("内存不足!");
return (char *)NULL;
}
number+=times*Step;

do //遇到#则输入结束。
{
c=getchar();
if(len==number)
{
times++;
number=times*Step;
temp=str;
str=(char *)realloc(str,number);
if(str==NULL)
{
printf("内存不足!");
str=temp;
break;
}
}
*(str+len)=c;
len++;
}while(c!='#');
str=(char *)realloc(str,len+1); //字符串的最终长度调整.
*(str+len)='\0';
return str;
}

void next_char(void)//获取下一个字符
{
ch=*fp;
fp=fp+1;

}

void next_valchar(void)//获取第一个有效的字符，过滤空格等。
{
next_char();
if(ch=='#')exit(0);//当文件只有空格和#号时
while(is_layout(ch))
{
next_char();
//if(ch=='#')exit(0);
}
}

void back()//指针回走
{
fp=fp-1;
}

void recongnize_name(char chr)//识别字符串
{
char name[10];
int i=0;
name[i++]=ch;
next_char();
while(is_digit_or_letter(ch))
{
name[i++]=ch;
next_char();

}

if((ch!=' ')&&(ch!='\t')&&(ch!='\n')&&(ch!='#')&&(ch!=':')&&(ch!='(')&&(ch!=')')&&(ch!=';'))//转非法字符串处理
{

do
{
name[i++]=ch;
next_char();

}while((ch!=' ')&&(ch!='\t')&&(ch!='\n')&&(ch!='#'));
if((name[i-1]=='#')||(name[i-1]=='\n'))//去掉结束符#或回车
{
name[i-1]='\0';
}
back();//指针回走
name[i]='\0';
printf("非法字符串\t%s\n",name);

}
else{
name[i]='\0';
if (name== "begin")
{
token.Class="BEGIN";
}
else if (name== "end")
{
token.Class="END";
}
else if (name=="read")
{
token.Class=="READ";
}
else if (name=="write")
{
token.Class="WRITE";
}
else
{
token.Class="IDEN";
int n=0;
Length=0;
while(name[n]!='\0')
{

token.seman[n]=name[n];
n++;
}
Length=n;
token.seman[n]=name[n];

}
back();
}
}

void recongnize_number(char cha)//识别数字
{
int N=0;
int m;
char name[10];//存非法字符串
int i=0;
while((m=is_digit(ch)))
{
N=N*10+(ch-'0');

name[i++]=ch;
next_char();
}
if(ch==' '||ch=='\t'||ch=='\n'||ch=='#'||(ch==';'))
{
token.Class="NUMB";
token.value=N;
back();
}
else//转非法字符串处理
{

do
{
name[i++]=ch;
next_char();

}while((ch!=' ')&&(ch!='\t')&&(ch!='\n')&&(ch!='#'));
if((name[i-1]=='#')||(name[i-1]=='\n'))//去掉结束符#或回车
{
name[i-1]='\0';
}
back();//指针回走
name[i]='\0';
printf("非法字符串\t%s\n",name);
TYPE=-1;

}

}

int next_token(void)//读下一个单词
{
next_valchar();
char name[10];//存首字母非法的字符串
int fg=0;
int i=0;
if('0'<=(ch)&&(ch)<='9')
{
TYPE=0;
}
else if('A'<=(ch)&&(ch)<='Z'||'a'<=(ch)&&(ch)<='z')
{
TYPE=1;
}
else
{
TYPE=2;
}

switch(TYPE)
{
case 0:
recongnize_number(ch);break;
case 1:
recongnize_name(ch);break;
case 2:
switch(ch)
{
case '+' :
token.Class="ADD";
token.seman[0]='+';
token.seman[1]='\0';
TYPE=2;
break;
case '*' :
token.Class="MULT";
token.seman[0]='*';
token.seman[1]='\0';
TYPE=2;
break;
case ':' :
next_char();
if(ch!='=')
{
error();
TYPE=-1;
break;
}
token.Class="ASS";
token.seman[0]=':';
token.seman[1]='=';
token.seman[2]='\0';
TYPE=2;
break;
case ';' :
token.Class="SEMI";
token.seman[0]=';';
token.seman[1]='\0';
TYPE=2;
break;
case '(' :
token.Class="OPEN";
token.seman[0]='(';
token.seman[1]='\0';
TYPE=2;
break;
case ')' :
token.Class="CLOSE";
token.seman[0]=')';
token.seman[1]='\0';
TYPE=2;
break;
default :
fg=1;
break;

}
}
if(fg==1)//非法字符串处理
{
name[i++]=ch;
while((ch!=' ')&&(ch!='\t')&&(ch!='\n')&&(ch!='#'))
{
next_char();
name[i++]=ch;
}
if((name[i-1]=='#')||(name[i-1]=='\n'))//去掉结束符#或回车

{
name[i-1]='\0';
}
back();//指针回走
name[i]='\0';
printf("非法字符串\t%s\n",name);
TYPE=-1;//置TYPE为-1
}

}

int compare(node *head,char words[],int Length)//单词的比较
{
node *p;
p=head;
if(head==NULL)
{
return 0;
}
else
{

int fg=1;

do
{
int i,j,succ;
i=0;
succ=0;
while((i<=p->length-Length)&&(!succ))
{
j=0;
succ=1;
while((j<Length)&&succ)
{
if(words[j]==(p->words[i+j]))
{
j++;
}
else
{
succ=0;
}

}
i++;
}
if(succ&&(j>=p->length))
{
(p->time)++;
fg=0;

}
if(p->next!=NULL)
{
p=p->next;
}

}while((p->next!=NULL)&&fg);

if(fg==0)
{
return 1;
}
else
{
return 0;
}

}
}

node *insert(node *head) //将读到的新单词加入链表
{
node *p;
p=(mynode*)malloc(sizeof(mynode));/*分配空间*/
strcpy(p->words,token.seman);
int n=0;
p->length=0;
p->time=1;
while(p->words[n]!='\0')
{
p->length++;
n++;
}
p->next=NULL;
if(head==NULL)
{
head=p;
}
else
{
p->next=head->next;
head->next=p;
}

return head;
}

void display(node *head)//打印链表的内容
{
node *p;
p=head;
if(!p) printf("\n无标识符！");
else
{
printf("\n各标识符或保留字及其出现的次数为：\n");
printf("标识符\t出现次数\n");
while(p) { printf("%s\t%d\n",p->words,p->time);p=p->next;}

}
}

int main(int argc, char *argv[])
{
char *str1=NULL;
printf("请输入程序代码：\n");
str1=getstr();//获取用户程序段的输入
fp=str1;
mynode *head=NULL;
do{
next_token();

switch(TYPE)
{
case 0:
printf("[%d]\t(%s,\t\"%d\")\n",num++,token.Class,token.value);
break;
case 1:
case 2:
printf("[%d]\t(%s,\t\"%s\")\n",num++,token.Class,token.seman);
int f;
f=0;
f=compare(head,token.seman,Length);
if((TYPE==1)&&(f==0))
{

head=insert(head);
}
break;
default:
break;
}

}while(*fp!='#');

display(head);
return 0;
}

❽ 求编译原理的词法分析器源码

/* 我上编译原理课时的第一次作业就是这个，flex源码. */
%{
#include<math.h>
int num_lines=0;
%}
DIGIT [0-9]
ID [a-zA-Z_][a-zA-Z0-9]*
%%
"#include" {
printf("<包含头文件,请手动合并文件\\>\n");
fprintf(yyout,"<包含头文件,请手动合并文件\\>\n");
}
{DIGIT}+ {
printf("(3整数, \"%s\")\n", yytext);
fprintf(yyout,"(3整数, \"%s\")\n", yytext);
}
{DIGIT}+"."{DIGIT}* {
printf("(3浮点数, \" %s\")\n",yytext);
fprintf(yyout,"(3浮点数, \" %s\")\n",yytext);
}
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 {
fprintf(yyout,"(1, \"%s\")\n",yytext);
fprintf(yyout,"(1, \"%s\")\n",yytext);
}
{ID} {
printf("(2, \"%s\")\n",yytext);
fprintf(yyout,"(2, \"%s\")\n",yytext);
}
"+" |
"++" |
"+=" |
"-" |
"--" |
"-=" |
"->" |
"*" |
"**" |
"*=" |
"/" |
"/=" |
"=" |
"==" |
">" |
">>" |
">=" |
">>=" |
"<" |
"<<" |
"<=" |
"<<=" |
"!" |
"!=" |
"%" |
"%=" |
"&" |
"&&" |
"&=" |
"|" |
"||" |
"|=" |
"^" |
"^=" {
printf("(4, \"%s\")\n",yytext);
fprintf(yyout,"(4, \"%s\")\n",yytext);
}
"{" |
"}" |
"(" |
")" |
";" |
"," |
"'" |
"\"" |
"." |
"?" |
"[" |
"]" |
"\\" |
":" {
printf("(5, \"%s\")\n",yytext);
fprintf(yyout,"(5, \"%s\")\n",yytext);
}
\n {
++num_lines;
}
"/*"[^(*/)\n]*"*/"
(" ")+
[\t]+
. {
printf("(不能识别字符, \"%s\")\n",yytext);
fprintf(yyout,"(不能识别字符, \"%s\")\n",yytext);
}
%%
main(argc,argv)
int argc;
char **argv;
{
++argv,--argc;
if(argc>0)
yyin=fopen(argv[0],"r");
else
yyin=stdin;
yyout=fopen("output.txt","w");
yylex();
fclose(yyout);
}
int yywrap()
{
return 1;
}

/* 附：我们第一次作业的要求。
实验一：用高级语言编写词法分析器（用lex生成）一、实验目的：编制一个识别C语言子集的词法分析器。从输入的源程序中，识别出各个具有独立意义的记号，即基本保留字、标识符、常数、运算符、分隔符五大类。并依次输出各个记号的内部编码及记号符号自身值。（遇到错误时可显示“Error”，然后跳过错误部分继续显示）二、实验过程和指导：（一）准备：1.阅读课本有关章节，明确语言的词法，写出基本保留字、标识符、常数、运算符、分隔符和程序例。2.初步编制好程序。3.准备好多组测试数据。（二）程序要求：程序输入/输出示例：如源程序为C语言。输入如下一段：main(){ int a,b; a = 10; b = a + 20;}要求输出如下：（2，”main”）（5，”（“）（5，”）“）（5，”{“）（1，”int”）（2，”a”）（5，”,”）（2，”b”）（5，”;”）（2，”a”）（4，”=”）（3，”10”）（5，”;”）（2，”b”）（4，”=”）（2，”a”）（4，”+”）（3，”20”）（5，”;”）（5，”）“}
要求（满足以下要求可获得70%该题的得分）：识别保留字：if、int、for、while、do、return、break、continue其他的都识别为标识符；常数为无符号整形数；运算符包括：+、-、*、/、=、>、<、>=、<=、!=分隔符包括：,、;、{、}、(、)以上为参考，具体可自行增删。 三、实验检查：1.程序：输入：测试数据（以文件形式）；输出：二元组（以文件形式）。2.实验报告：（1）功能描述：该程序具有什么功能？（2）状态转换图。（2）程序结构描述：函数调用格式、参数含义、返回值描述、函数功能；函数之间的调用关系图、程序总体执行流程图。（4）源程序代码。（5）实验过程记录：出错次数、出错严重程度、解决办法摘要。（6）实验总结：你在编程过程中花时多少？多少时间在纸上设计？多少时间上机输入和调试？多少时间在思考问题？遇到了哪些难题？你是怎么克服的？你对你的程序的评价？你的收获有哪些？

另可附加：关键字 有符号数 符号表填写 行号记录，等
*/

❾ 编译原理 词法分析

C语言词法分析器
#include<iostream>
#include<stdio.h>
#include<string>

using namespace std;

FILE *f; //定义一个文件变量
static int line = 1; //表示光标所在的行数
struct ID{ char *name; int count;}id[100];//用于存放ID号码
static int I = 0; //用于记录ID存放的数量
int Number[100]; //用于存放数字
static int P = 0; //用于记录存放数字的个数
int error[100] = {0}; //用于记录错误所在的行数
static int K = 0; //记录错误次数
void Error(); //记录错误
void loginID(char *); //注册ID号
void loginNumber(int &); //记录数字
void noteLine(char &); //记录光标所在的行数
void print(); //输出分析结果
int same(char *chr); //判断单词是否已经存在

void Error()
{ error[K++] = line; }

void loginID(char *chr) //注册ID号
{
int k = 0;
int h = 0;
for(int i = 0; i < I; i++)
{
if(!strcmp(chr,id.name)) //如果单词已经存在
{
id.count++;
k = 1;
}
}
if(k == 0) //该单词不存在
{
h = I + 1;
//I = h;
id[h].count++;
id[h].name = chr;
//strcpy(id[h].name ,chr);
}

}

void loginNumber(int &nu)
{ Number[P++] = nu; }

void noteLine(char &ch)
{
if ( ch == ' ' )
++line;
}

void print()//输出部分
{
//cout << "关键字以及变量:" << endl;
//for(int i = 0; i < 100; i++)
//cout << i <<" " << id.name << " " << id.count << endl;
cout << "数字：" << endl;
for(int i = 1; i <= P; i++)
cout << i << ": " << Number[i-1] << endl;
if(error[0] != 0)
{
cout << "出现的错误！" << endl;
for(int i = 1; i <= K; i++)
cout << "第" << i << "个错误： " << "第" << error[i-1] << "行" << endl;
}
else cout << "没有错误！" << endl;
}

//文件处理部分
void noblank( char &ch) //跳过空格，回车
{
noteLine(ch);
while(ch == ' ' || ch == ' ')
ch = fgetc(f);
}

void identifier(char name[],char &ch)//字母变量
{

int i;
for(i = 0; i < 20; i++)
name = '';
i = 0;
while (('0'<= ch && ch <= '9')||('a'<= ch&&ch <= 'z')||('A'<= ch&&ch <='Z'))
{
name = ch;
i++;
ch = fgetc(f);
}
loginID(name);
//for(int j = 0; j < i; j++)
//{cout << name[j];}
// cout << ' ';

}

int number(char &ch)//数字
{
int num=0;
while('0'<= ch && ch <= '9')
{
num = num* 10 + (ch-'0');
ch = fgetc(f);
}
if( ('a'<= ch&&ch <= 'z')||('A'<= ch&&ch <='Z'))
{
Error();
}
else if( ch == '.')
{;}
loginNumber(num); //记录数字
return num;
}

void test(char &ch)//符号
{
char str[2]={'0/'};
if(ch == '*')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '.')
{ str[0] = ch; ch = fgetc(f);}
if(ch == ',')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '"')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '/')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '%')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '^')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '-')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '{')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '}')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '[')
{ str[0] = ch; ch = fgetc(f);}
if(ch == ']')
{ str[0] = ch; ch = fgetc(f);}
if(ch == ';')
{str[0] = ch; ch = fgetc(f);}
if(ch == ':')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '?')
{ str[0] = ch; ch = fgetc(f);}
if(ch == '(')
{ str[0] = ch; ch = fgetc(f);}
if(ch == ')')
{str[0] = ch; ch = fgetc(f);}
if(ch =='+')
{

str[0] = ch;
if((ch = fgetc(f)) == '+' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

//cout << str[0]<< endl;
}
if(ch == '-')
{

str[0] = ch;
if((ch = fgetc(f)) == '-' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

//cout << str[0]<< endl;
}
if(ch == '&')
{

str[0] = ch;
if((ch = fgetc(f)) == '&' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

//cout << str[0]<< endl;
}
if(ch == '|')
{

str[0] = ch;
if((ch = fgetc(f)) == '|' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

//cout << str[0]<< endl;
}
if(ch == '!')
{

str[0] = ch;
if((ch = fgetc(f)) == '=' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

//cout << str[0]<< endl;
}
if(ch == '=')
{

str[0] = ch;
if((ch = fgetc(f)) == '=' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

}
if(ch == '>')
{

str[0] = ch;
if((ch = fgetc(f)) == '=' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}
else
if(ch == '>' )
{
str[1] = ch;
ch = fgetc(f);
//cout << str[0] << str[1] << endl;
}

}
if(ch == '<')
{
str[0] = ch;
if((ch = fgetc(f)) == '=' )
{
str[1] = ch;
ch = fgetc(f);
}
else
if(ch == '<' )
{
str[1] = ch;
ch = fgetc(f);
}

}

}

int main()
{
char ch;
char name[30];
for(int i = 0; i < 30; i++)
name = '/0';
f = fopen("c.txt","r"); //打开指定输入文件
if (f == NULL)
cout<<"文件不存在！"<<endl;
ch = fgetc(f);
while(!feof(f))
{
noblank( ch ); //跳过回车，空格
if( ( ch >= 'a' && ch <= 'z' )||( ch >= 'A' && ch <= 'Z' ))
{ identifier(name,ch); } //处理字母
else if( ch >= '0'&& ch <= '9')
{ number(ch); } //处理数字
else
{ test(ch); } //处理符号
}
print(); //打印词法分析结果
fclose(f); //关闭文件
system("pause");
return 0;
}

❿ 编译原理 词法分析 要求输入一个源文件，或是text形式的，然后对该文件进行词法分析。要简单一点的。

#include <iostream>
#include <vector>
#include <string>
#include <fstream>

using namespace std;
/*用来存储目标文件名*/
string file_name;

/*提取文本文件中的信息。*/
string GetText();

/*获得一个单词符号,从位置i开始查找。
//并且有一个引用参数j，用来返回这个单词最后一个字符在str的位置。*/
string GetWord(string str,int i,int& j);

/*这个函数用来除去字符串中连续的空格和换行
//第一个参数为目标字符串，第二个参数为开始位置
//返回值为连续的空格和换行后的第一个有效字符在字符串的位置*/
int DeleteNull(string str,int i);

/*判断i当前所指的字符是否为一个分界符，是的话返回真，反之假*/
bool IsBoundary(string str,int i);

/*判断i当前所指的字符是否为一个运算符，是的话返回真，反之假*/
bool IsOperation(string str,int i);

/*此函数将一个pair数组输出到一个文件中*/
void OutFile(vector<pair<int,string> > v);

/*此函数接受一个字符串数组，对它进行词法分析，返回一个pair型数组*/
vector<pair<int,string> > analyst(vector<string> vec);

/*此函数判断传递的参数是否为关键字，是的话，返回真，反之返回假*/
bool IsKey(string str);

int main()
{
cout<<"*****************************\n";
cout<<"\n\nright: Archerzei\n\n\n";
cout<<"*****************************\n\n";
string com1=" ";
string com2="\n";
string fileline=GetText();
int begin=0,end=0;
vector<string> array;
do
{
begin=DeleteNull(fileline,begin);
string nowString;
nowString=GetWord(fileline,begin,end);
if(end==-1)
break;
if(nowString.compare(com1)&&nowString.compare(com2))
array.push_back(nowString);
begin=end+1;
}while(true);
vector<pair<int,string> > mid_result;
mid_result=analyst(array);
OutFile(mid_result);
cout<<"**********************************************************************\n";
cout<<"***程序已完成词法分析，分析结果已经存储在文件"<<file_name<<"中！！！***\n";
cout<<"**********************************************************************\n";
system("pause");
return 0;
}

/*提取文本文件中的信息*/
string GetText()
{
string file_name1;
cout<<"请输入源文件名（包括路径和后缀名）：";
cin>>file_name1;
ifstream infile(file_name1.c_str(),ios::in);
if (!infile)
{
cerr<<"无法打开文件! "<<file_name1.c_str()<<" !!!"<<endl;
exit(-1);
}
cout<<endl;
char f[1000];
infile.getline(f,1000,EOF);
infile.close();
return f;
}

/*获得一个单词符号,从位置i开始查找。
//并且有一个引用参数j，用来返回这个单词最后一个字符在原字符串的位置。*/
string GetWord(string str,int i,int& j)
{
string no_use("(){} , ; \n+=*/-<>\"");
j=str.find_first_of(no_use,i);
if(j==-1)
return "";
if(i!=j)
j--;
return str.substr(i,j-i+1);
}

/*这个函数用来除去字符串中连续的空格和换行
//第一个参数为目标字符串，第二个参数为开始位置
//返回值为连续的空格和换行后的第一个有效字符在字符串的位置*/
int DeleteNull(string str,int i)
{
for(;;i++)
if(str[i]!=' '&&str[i]!='\n')
return i;
}

/*判断i当前所指的字符是否为一个分界符，是的话返回真，反之假*/
bool IsBoundary(string str,int i)
{
int t;
char arr[7]={',',';','{','}','(',')','\"'};
for (t=0;t<7;t++)
if(str[i]==arr[t])
return true;
return false;
}

/*判断i当前所指的字符是否为一个运算符，是的话返回真，反之假*/
bool IsOperation(string str,int i)
{
int t;
char arr[7]={'+','-','*','/','=','<','>'};
for (t=0;t<7;t++)
if(str[i]==arr[t])
return true;
return false;
}

/*此函数将一个个字符串数组输出到一个文件中*/
void OutFile(vector<pair<int,string> > v)
{
cout<<"请输入目标文件名（包括路径和后缀名）：";
cin>>file_name;
ofstream outfile(file_name.c_str(),ios::out);
if (!outfile)
{
cerr<<"无法打开文件! "<<file_name.c_str()<<" !!!"<<endl;
exit(-1);
}
cout<<endl;
int i;
cout<<"*****************************\n";
cout<<"\n\nright: Archerzei\n\n\n";
cout<<"*****************************\n\n";
for(i=0;i<v.size();i++)
outfile<<"<"<<v[i].first<<" , \""<<v[i].second<<"\">"<<endl;
outfile<<"\n\n*********************************\n";
outfile.close();
return;
}

/*此函数接受一个字符串数组，对它进行词法分析，返回一个pair型数组*/
vector<pair<int,string> > analyst(vector<string> vec)
{
vector<pair<int,string> > temp;
int i;
for(i=0;i<vec.size();i++)
{
if(vec[i].size()==1)
{
if((vec[i]==">"||vec[i]=="<"||vec[i]=="!")&&vec[i+1]=="=")
{
string jk=vec[i];
jk.append(vec[++i],0,1);
pair<int,string> pp(4,jk);
temp.push_back(pp);
continue;
}
if((vec[i]=="+"&&vec[i+1]=="+")||(vec[i]=="-"&&vec[i+1]=="-"))
{
string jk=vec[i];
jk.append(vec[++i],0,1);
pair<int,string> pp(4,jk);
temp.push_back(pp);
continue;
}
if(IsBoundary(vec[i],0))
{
pair<int,string> pp(5,vec[i]);
temp.push_back(pp);
}
else if(IsOperation(vec[i],0))
{
pair<int,string> pp(4,vec[i]);
temp.push_back(pp);
}
else if(vec[i][0]<='9'&&vec[i][0]>='0')
{
pair<int,string> pp(3,vec[i]);
temp.push_back(pp);
}
else
{
pair<int,string> pp(2,vec[i]);
temp.push_back(pp);
}
}
else if(vec[i][0]<='9'&&vec[i][0]>='0')
{
pair<int,string> pp(3,vec[i]);
temp.push_back(pp);
}
else if(IsKey(vec[i]))
{
pair<int,string> pp(1,vec[i]);
temp.push_back(pp);
}
else
{
pair<int,string> pp(2,vec[i]);
temp.push_back(pp);
}
}
return temp;
}

/*此函数判断传递的参数是否为关键字，是的话，返回真，反之返回假*/
bool IsKey(string str)
{
string p[16]={"char","double","int","long","double","float","for","while","do","break","continue","switch","short","case","return","if"};
vector<string> ppp(p,p+16);
int u;
for(u=0;u<ppp.size();u++)
if(!str.compare(ppp[u]))
return true;
return false;
}
/*finished*/

已经验收过了，在VC6.0上运行没有问题。程序很容易看懂的，报告的话自己写写就可以了。要是有分就好了…………哈哈！！！