编译原理词法分析实验怎么做
❶ 有人知道编译原理实验之词法分析器用C++怎么做吗
#include "globals.h"
#include "util.h"
#include "scan.h"
#include "parse.h"
static TokenType token; /* holds current token */
/* function prototypes for recursive calls */
static TreeNode * stmt_sequence(void);
static TreeNode * statement(void);
static TreeNode * if_stmt(void);
static TreeNode * repeat_stmt(void);
static TreeNode * assign_stmt(void);
static TreeNode * read_stmt(void);
static TreeNode * write_stmt(void);
static TreeNode * exp(void);
static TreeNode * simple_exp(void);
static TreeNode * term(void);
static TreeNode * factor(void);
static void syntaxError(char * message)
{ fprintf(listing,"\n>>> ");
fprintf(listing,"Syntax error at line %d: %s",lineno,message);
Error = TRUE;
}
static void match(TokenType expected)
{ if (token == expected) token = getToken();
else {
syntaxError("unexpected token -> ");
printToken(token,tokenString);
fprintf(listing," ");
}
}
TreeNode * stmt_sequence(void)
{ TreeNode * t = statement();
TreeNode * p = t;
while ((token!=ENDFILE) && (token!=END) &&
(token!=ELSE) && (token!=UNTIL))
{ TreeNode * q;
match(SEMI);
q = statement();
if (q!=NULL) {
if (t==NULL) t = p = q;
else /* now p cannot be NULL either */
{ p->sibling = q;
p = q;
}
}
}
return t;
}
TreeNode * statement(void)
{ TreeNode * t = NULL;
switch (token) {
case IF : t = if_stmt(); break;
case REPEAT : t = repeat_stmt(); break;
case ID : t = assign_stmt(); break;
case READ : t = read_stmt(); break;
case WRITE : t = write_stmt(); break;
default : syntaxError("unexpected token -> ");
printToken(token,tokenString);
token = getToken();
break;
} /* end case */
return t;
}
TreeNode * if_stmt(void)
{ TreeNode * t = newStmtNode(IfK);
match(IF);
if (t!=NULL) t->child[0] = exp();
match(THEN);
if (t!=NULL) t->child[1] = stmt_sequence();
if (token==ELSE) {
match(ELSE);
if (t!=NULL) t->child[2] = stmt_sequence();
}
match(END);
return t;
}
TreeNode * repeat_stmt(void)
{ TreeNode * t = newStmtNode(RepeatK);
match(REPEAT);
if (t!=NULL) t->child[0] = stmt_sequence();
match(UNTIL);
if (t!=NULL) t->child[1] = exp();
return t;
}
TreeNode * assign_stmt(void)
{ TreeNode * t = newStmtNode(AssignK);
if ((t!=NULL) && (token==ID))
t->attr.name = String(tokenString);
match(ID);
match(ASSIGN);
if (t!=NULL) t->child[0] = exp();
return t;
}
TreeNode * read_stmt(void)
{ TreeNode * t = newStmtNode(ReadK);
match(READ);
if ((t!=NULL) && (token==ID))
t->attr.name = String(tokenString);
match(ID);
return t;
}
TreeNode * write_stmt(void)
{ TreeNode * t = newStmtNode(WriteK);
match(WRITE);
if (t!=NULL) t->child[0] = exp();
return t;
}
TreeNode * exp(void)
{ TreeNode * t = simple_exp();
if ((token==LT)||(token==EQ)) {
TreeNode * p = newExpNode(OpK);
if (p!=NULL) {
p->child[0] = t;
p->attr.op = token;
t = p;
}
match(token);
if (t!=NULL)
t->child[1] = simple_exp();
}
return t;
}
TreeNode * simple_exp(void)
{ TreeNode * t = term();
while ((token==PLUS)||(token==MINUS))
{ TreeNode * p = newExpNode(OpK);
if (p!=NULL) {
p->child[0] = t;
p->attr.op = token;
t = p;
match(token);
t->child[1] = term();
}
}
return t;
}
TreeNode * term(void)
{ TreeNode * t = factor();
while ((token==TIMES)||(token==OVER))
{ TreeNode * p = newExpNode(OpK);
if (p!=NULL) {
p->child[0] = t;
p->attr.op = token;
t = p;
match(token);
p->child[1] = factor();
}
}
return t;
}
TreeNode * factor(void)
{ TreeNode * t = NULL;
switch (token) {
case NUM :
t = newExpNode(ConstK);
if ((t!=NULL) && (token==NUM))
t->attr.val = atoi(tokenString);
match(NUM);
break;
case ID :
t = newExpNode(IdK);
if ((t!=NULL) && (token==ID))
t->attr.name = String(tokenString);
match(ID);
break;
case LPAREN :
match(LPAREN);
t = exp();
match(RPAREN);
break;
default:
syntaxError("unexpected token -> ");
printToken(token,tokenString);
token = getToken();
break;
}
return t;
}
/****************************************/
/* the primary function of the parser */
/****************************************/
/* Function parse returns the newly
* constructed syntax tree
*/
TreeNode * parse(void)
{ TreeNode * t;
token = getToken();
t = stmt_sequence();
if (token!=ENDFILE)
syntaxError("Code ends before file\n");
return t;
}
上面是一个语法分析器的主代码部分它可以识别类似下面的代码，但是由于篇幅有限，上面的代码不是完整代码，完整代码太长，还有好几个文件。
read x; { input an integer }
if 0 < x then { don't compute if x <= 0 }
fact := 1;
repeat
fact := fact * x;
x := x - 1
until x = 0;
write fact { output factorial of x }
end
❷ 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;
}
}
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 如何通俗易懂地解释编译原理中语法分析的过程
语法分析（Syntax analysis或Parsing）和语法分析程序（Parser）
语法分析是编译过程的一个逻辑阶段。语法分析的任务是在词法分析的基础上将单词序列组合成各类语法短语，如“程序”，“语句”，“表达式”等等.语法分析程序判断源程序在结构上是否正确.源程序的结构由上下文无关文法描述.
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 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
❼ 急求！！！用C语言编写一个编译原理实验的简单优先分析法程序
编译原理IF条件语句的翻译程序设计—简单优先法、输出四元式通过设计、编制、调试一个条件语句的语法及语义分析程序，加深对语法及语义分析原理的理解，并实现词法分析程序对单词序列的词法检查和分析。具体做到以下几点：①对输入语句进行词法分析。将输入的字符串进行扫描和分解，识别出一个个合法的单词。单词种类包括：关键字，标识符，运算符，常数和界限符②进行语法分析。编写条件语句的相应文法，按照语法分析方法中的简单优先分析法为文法设计简单优先表，对词法分析得到的单词序列进行语法分析，以判别输入的语句是否属于该文法的条件语句。③语法制导翻译。设计中间代码（四元式）序列的结构及属性文法，运用语法制导翻译，在进行语法分析的同时，执行相应的语义规则描述的动作，从而实现语义处理，生成中间代码以四元式的形式输出。④错误提示。对不同的错误给出简略描述，并终止程序的继续执行。下载地址如下，有你要的东西！pile.rar
❽ 编译原理词法分析器是干什么用的，怎么用
1、识别出源程序中的各个单词符号，并转换成内部编码形式 2、删除无用的空白字符回车字符以及其他非实质性字符 3、删除注释 4、进行词法检查，报告所发现的错误。
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！！！