编译原理词法分析实验语言

A. 编译原理的词法分析器（c++语言）实验总是出错（急）

strcmp只能对char类型的数组，而不能处理string类型，不能混淆着使用string类型用string.compare函数

B. 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;
}

C. 请问编译原理的词法分析用C语言编写的算法是怎样的

ε只能出现在NFA中，当然不是为了方便直观，而是连通NFA和DFA的桥梁。编译原理讲授的不是如何绘制NFA或者DFA，二是告诉读者怎样能够自动实现NFA或DFA的构造。在实际应用中ε可以帮助计算机转换NFA为DFA，而在属性文法和语法制导阶段，它也是沟通综合属性与继承属性、执行语义动作不可或缺的一部分。另外ε的使用可以大大简化文法产生式的构造难度。我记得最初使用ε是为了使得文法体系（字母表）更加完善，但是在实际应用中却变得应用广泛(此观点不一定正确)。 最后想说的是，在编译中，ε也带来了不小的麻烦，否则也就不会有诸如“去空产生式”这样的算法了:)
采纳哦

D. 编译原理词法分析程序

（一）Block子程序分析

procere enter(k: object1); //填写符号表
begin {enter object into table}
tx := tx + 1; //下标加1，tx的初始值为零，零下标不地址不填写标志符，用于查找失败使用
with table[tx] do //填入内容，保存标志符名和类型
begin name := id; kind := k;
case k of //根据类型判断是否正确
constant: begin if num > amax then //如果是常量，判断是否大于最大值，若是则报30号错
begin error(30); num :=0 end;
val := num //否则保存数值
end;
varible: begin level := lev; adr := dx; dx := dx + 1; //如果是变量，填写变量内部表示，LEVEl是变量的层次，adr为地址
end;
proc: level := lev //如果是过程，保存过程的层次
end
end
end {enter};

//查找符号表的位置
function position(id: alfa): integer;
var i: integer;
begin {find indentifier id in table} //从后向前查找
table[0].name := id; i := tx; //找到保存类型
while table[i].name <> id do i := i-1;
position := i //返回标志符在符号表中的位置
end {position};

procere block(lev,tx: integer; fsys: symset);
var dx: integer; {data allocation index} //数据分配索引
tx0: integer; {initial table index} //初始符号表索引
cx0: integer; {initial code index} //初始代码索引
procere enter(k: object1); //填写符号表，下次分析
begin {enter object into table}
tx := tx + 1;
with table[tx] do
begin name := id; kind := k;
case k of
constant: begin if num > amax then
begin error(30); num :=0 end;
val := num
end;
varible: begin level := lev; adr := dx; dx := dx + 1;
end;
proc: level := lev
end
end
end {enter};

function position(id: alfa): integer; //查找符号表，下次分析
var i: integer;
begin {find indentifier id in table}
table[0].name := id; i := tx;
while table[i].name <> id do i := i-1;
position := i
end {position};

procere constdeclaration; //常量声明
begin if sym = ident then //如果是标志符，读入一个TOKEN
begin getsym;
if sym in [eql, becomes] then //读入的是等号或符值号继续判断
begin if sym = becomes then error(1); //如果是“=”报1号错
getsym; //读入下一个TOKEN
if sym = number then //读入的是数字，填写符号表
begin enter(constant); getsym
end
else error(2) //如果不是数字，报2号错
end else error(3) //不是等号或符值号，报3号错
end else error(4) //如果不是标志符，报4号错
end {constdeclaration};

procere vardeclaration; //变量声明
begin if sym = ident then //读入的是标志符，填写符号表
begin enter(varible); getsym
end else error(4) //不是标志符，报4号错
end {vardeclaration};

procere listcode;
var i: integer;
begin {list code generated for this block}
for i := cx0 to cx-1 do
with code[i] do
writeln(i:5, mnemonic[f]:5, 1:3, a:5)
end {listcode};

procere statement(fsys: symset);
var i, cx1, cx2: integer;
procere expression(fsys: symset); //表达式分析
var addop: symbol;
procere term(fsys: symset); //项分析
var mulop: symbol;
procere factor(fsys: symset); //因子分析
var i: integer;
begin test(facbegsys, fsys, 24); //读入的是“（”，标志符或数字
while sym in facbegsys do
begin
if sym = ident then //是标志符，查表
begin i:= position(id);
if i = 0 then error(11) else //未找到，报11号错
with table[i] do //找到，读入标志符类型
case kind of
constant: gen(lit, 0, val); //写常量命令
varible: gen(lod, lev-level, adr);//写变量命令
proc: error(21) //过程名，报21号错
end;
getsym //读入下一个TOKEN
end else
if sym = number then //读入的是数字
begin if num > amax then //如果数字大于最大数，报30号错误
begin error(30); num := 0
end;
gen(lit, 0, num); getsym //调用数字命令，读入下一个TOKEN
end else
if sym = lparen then //读入的是“（”
begin getsym; expression([rparen]+fsys); //调用表达式分析函数
if sym = rparen then getsym else error(22) //如果“（”后无“）”，报22号错
end;
test(fsys, [lparen], 23)
end
end {factor};//因子分析结束

//项分析
begin {term} factor(fsys+[times, slash]); //调用因子分析程序
while sym in [times, slash] do //取得是乘、除号循环
begin mulop:=sym;getsym;factor(fsys+[times,slash]); //记录符号，调用因子分析
if mulop=times then gen(opr,0,4) else gen(opr,0,5) //写乘除指令
end
end {term};
begin {expression}
if sym in [plus, minus] then //如果是加减号
begin addop := sym; getsym; term(fsys+[plus,minus]); //记录符号，调用项分析程序
if addop = minus then gen(opr, 0,1) //写加减指令
end else term(fsys+[plus, minus]);
while sym in [plus, minus] do //如果是加减号循环
begin addop := sym; getsym; term(fsys+[plus,minus]);
if addop=plus then gen(opr,0,2) else gen(opr,0,3)
end
end {expression};

//条件过程
procere condition(fsys: symset);
var relop: symbol;
begin
if sym = oddsym then //如果是判奇符
begin getsym; expression(fsys); gen(opr, 0, 6) //取下一个TOKEN，调用expression，填指令
end else
begin expression([eql, neq, lss, gtr, leq, geq]+fsys);
if not(sym in [eql, neq, lss, leq, gtr, geq]) then //如果不是取到逻辑判断符号，出错.20
error(20) else
begin relop := sym; getsym; expression(fsys);
case relop of
eql: gen(opr, 0, 8); // =，相等
neq: gen(opr, 0, 9); // #，不相等
lss: gen(opr, 0, 10); // <，小于
geq: gen(opr, 0, 11); // ]，大于等于
gtr: gen(opr, 0, 12); // >，大于
leq: gen(opr, 0, 13); // [，小于等于
end
end
end
end {condition};

begin {statement}
if sym = ident then //如果是标识符
begin i := position(id); //查找符号表
if i = 0 then error(11) else //未找到，标识符未定义，报11号错
if table[i].kind <> varible then //如果标识符不是变量，报12号错
begin {assignment to non-varible} error(12); i := 0
end;
getsym; if sym = becomes then getsym else error(13); //如果是变量读入下一个TOKEN，不是赋值号，报13好错；是则读入一个TOKEN
expression(fsys); //调用表达是过程
if i <> 0 then //写指令
with table[i] do gen(sto, lev-level, adr)
end else
if sym = callsym then //如果是过程调用保留字，读入下一个TOKEN
begin getsym;
if sym <> ident then error(14) else //不是标识符报14号错
begin i := position(id);
if i = 0 then error(11) else //是标识符，未定义，报13号错
with table[i] do // 已定义的标识符读入类型
if kind=proc then gen(cal, lev-level, adr) //是过程名写指令
else error(15); //不是过程名，报15号错
getsym
end
end else
if sym = ifsym then //如果是IF
begin getsym; condition([thensym, dosym]+fsys); //读入一个TOKEN,调用条件判断过程
if sym = thensym then getsym else error(16); //如果是THEN,读入一个TOKEN，不是，报16号错
cx1 := cx; gen(jpc, 0, 0); //写指令
statement(fsys); code[cx1].a := cx
end else
if sym = beginsym then //如果是BEGIN
begin getsym; statement([semicolon, endsym]+fsys); //读入一个TOKEN
while sym in [semicolon]+statbegsys do
begin
if sym = semicolon then getsym else error(10); //如果读入的是分号
statement([semicolon, endsym]+fsys)
end;
if sym = endsym then getsym else error(17) //如果是END 读入一个TOKEN，不是，报17号错
end else
if sym = whilesym then //如果是WHILE
begin cx1 := cx; getsym; condition([dosym]+fsys); //调用条件过程
cx2 := cx; gen(jpc, 0, 0); //写指令
if sym = dosym then getsym else error(18); //如果是DO读入下一个TOKEN，不是报18号错
statement(fsys); gen(jmp, 0, cx1); code[cx2].a := cx
end;
test(fsys, [], 19)
end {statement};

begin {block}
dx:=3;
tx0:=tx;
table[tx].adr:=cx;
gen(jmp,0,0);
if lev > levmax then error(32);
repeat
if sym = constsym then //如果是CONST
begin getsym; //读入TOKEN
repeat constdeclaration; //常量声明
while sym = comma do
begin getsym; constdeclaration
end;
if sym = semicolon then getsym else error(5) //如果是分号读入下一个TOKEN，不是报5号错
until sym <> ident //不是标志符常量声明结束
end;
if sym = varsym then 如果是VAR
begin getsym; 读入下一个TOKEN
repeat vardeclaration; //变量声明
while sym = comma do
begin getsym; vardeclaration
end;
if sym = semicolon then getsym else error(5) //如果是分号读入下一个TOKEN，不是报5号错
until sym <> ident; //不是标志符常量声明结束
end;
while sym = procsym do //过程声明
begin getsym;
if sym = ident then
begin enter(proc); getsym
end
else error(4); //不是标志符报4号错
if sym = semicolon then getsym else error(5); //如果是分号读入下一个TOKEN，不是报5号错
block(lev+1, tx, [semicolon]+fsys);
if sym = semicolon then //如果是分号，取下一个TOKEN，不是报5号错
begin getsym;test(statbegsys+[ident,procsym],fsys,6)
end
else error(5)
end;
test(statbegsys+[ident], declbegsys, 7)
until not(sym in declbegsys); //取到的不是const var proc结束
code[table[tx0].adr].a := cx;
with table[tx0] do
begin adr := cx; {start adr of code}
end;
cx0 := 0{cx}; gen(int, 0, dx);
statement([semicolon, endsym]+fsys);
gen(opr, 0, 0); {return}
test(fsys, [], 8);
listcode;
end {block};

E. 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？

F. 请问编译原理的词法分析用C语言编写的算法是怎样的

#include <iostream>
using namespace std;
#define m 45
#define n 100
#define t 10
int main()
{
FILE *fp;
char filename[20],c[n];
printf("Type the file name which you want to open:");
scanf("%s",&filename);
fp=fopen(filename,"r+"); /*以r-只读方式打开指定文件*/
if((fp=fopen(filename,"r"))==NULL) /*文件不存在输出错误*/
{cout<<"文件不存在!"<<endl;exit(-1);}
cout<<"文件中内容如下:"<<endl;
for(int j=0;!feof(fp);j++){
c[j]=fgetc(fp);//从流中读取字符
}
char keyword[m][t]={"include","int","string","cout","cin","auto","break","case","char","class","const",
"continue","default","delete","do","double","else","enum","extern","float","for","friend","if","inline",
"int","long","new","operator","private","protected","public","register","return","short","sizeof","static",
"struct","switch","template","this","typedef","union","virtual","void","while"};//关键字数组
char a[t],*p=c,*q=a,*s=a;
bool w=0,r=0;
int i=0;
for(i=0;i<10;i++)a[i]=NULL;//初始化临时数组
while (*p !=NULL){
q=s=a;
if((*p>='a'&&*p<='z')||(*p>='A'&&*p<='Z')||*p=='_'){//识别标识符
*q=*p;p++;q++;
while ((*p>='a'&&*p<='z')||(*p>='A'&&*p<='Z')||(*p>='0'&&*p<='9')||*p=='_'){
*q=*p;p++;q++;
}
for(i=0;i<m;i++)if(strcmp(keyword[i],a)==0){r=1;break;}
if(r==1){cout<<"关键字为:";r=0;}
else cout<<"标识符为:";
while(s!=q){
cout<<*s;
s++;
}
cout<<endl;
for(i=0;i<t;i++)a[i]=NULL;
}
else if(*p=='\''){//识别字符常量
p++;
while(*p!='\''){

*q=*p;
p++;
q++;
}
cout<<"字符常量为:";
while(s!=q){
cout<<*s;
s++;
}
cout<<endl;
for(i=0;i<t;i++)a[i]=NULL;
p++;
}
else if(*p=='\"'){//识别字符串常量
p++;
while(*p!='\"'){
*q=*p;
p++;
q++;
}
cout<<"字符串常量为:";
while(s!=q){
cout<<*s;
s++;
}
cout<<endl;
for(i=0;i<t;i++)a[i]=NULL;
p++;
}
else if(*p=='+'||*p=='-'||*p=='*'||*p=='/'||*p=='='||*p=='%'||*p=='/'){//识别运算符
cout<<"运算符为:"<<*p;
cout<<endl;
p++;
}
else if(*p==';'||*p==','){//识别分解符
cout<<"分界符为:"<<*p;
cout<<endl;
p++;
}
else if(*p>='0'&&*p<='9'){
s=q=a;
*q=*p;p++;q++;
while(*p>='0'&&*p<='9'||*p=='.'){
*q=*p;p++;q++;
}
while(s!=q){
if(*s=='.'){w=1;break;}//识别实型常量
s++;
}
s=a;
if(w ==1){
cout<<"实型常量为:";
while(s!=q){
cout<<*s;
s++;
}
for(i=0;i<t;i++)a[i]=NULL;
}
else {
cout<<"整型常量为:";
while(s!=q){//识别整型常量
cout<<*s;
s++;
}
for(i=0;i<t;i++)a[i]=NULL;
}
cout<<endl;
}
else p++;
}
return 0;
}

G. 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;
}
}

H. 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

I. 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
*/