編譯原理詞法分析實驗語言

A. 編譯原理的詞法分析器（c++語言）實驗總是出錯（急）

strcmp只能對char類型的數組，而不能處理string類型，不能混淆著使用string類型用string.compare函數

B. 編譯原理 詞法分析

C語言詞法分析器
#include<iostream>
#include<stdio.h>
#include<string>

using namespace std;

FILE *f; //定義一個文件變數
static int line = 1; //表示游標所在的行數
struct ID{ char *name; int count;}id[100];//用於存放ID號碼
static int I = 0; //用於記錄ID存放的數量
int Number[100]; //用於存放數字
static int P = 0; //用於記錄存放數字的個數
int error[100] = {0}; //用於記錄錯誤所在的行數
static int K = 0; //記錄錯誤次數
void Error(); //記錄錯誤
void loginID(char *); //注冊ID號
void loginNumber(int &); //記錄數字
void noteLine(char &); //記錄游標所在的行數
void print(); //輸出分析結果
int same(char *chr); //判斷單詞是否已經存在

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

void loginID(char *chr) //注冊ID號
{
int k = 0;
int h = 0;
for(int i = 0; i < I; i++)
{
if(!strcmp(chr,id.name)) //如果單詞已經存在
{
id.count++;
k = 1;
}
}
if(k == 0) //該單詞不存在
{
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()//輸出部分
{
//cout << "關鍵字以及變數:" << endl;
//for(int i = 0; i < 100; i++)
//cout << i <<" " << id.name << " " << id.count << endl;
cout << "數字：" << endl;
for(int i = 1; i <= P; i++)
cout << i << ": " << Number[i-1] << endl;
if(error[0] != 0)
{
cout << "出現的錯誤！" << endl;
for(int i = 1; i <= K; i++)
cout << "第" << i << "個錯誤： " << "第" << error[i-1] << "行" << endl;
}
else cout << "沒有錯誤！" << endl;
}

//文件處理部分
void noblank( char &ch) //跳過空格，回車
{
noteLine(ch);
while(ch == ' ' || ch == ' ')
ch = fgetc(f);
}

void identifier(char name[],char &ch)//字母變數
{

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)//數字
{
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); //記錄數字
return num;
}

void test(char &ch)//符號
{
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"); //打開指定輸入文件
if (f == NULL)
cout<<"文件不存在！"<<endl;
ch = fgetc(f);
while(!feof(f))
{
noblank( ch ); //跳過回車，空格
if( ( ch >= 'a' && ch <= 'z' )||( ch >= 'A' && ch <= 'Z' ))
{ identifier(name,ch); } //處理字母
else if( ch >= '0'&& ch <= '9')
{ number(ch); } //處理數字
else
{ test(ch); } //處理符號
}
print(); //列印詞法分析結果
fclose(f); //關閉文件
system("pause");
return 0;
}

C. 請問編譯原理的詞法分析用C語言編寫的演算法是怎樣的

ε只能出現在NFA中，當然不是為了方便直觀，而是連通NFA和DFA的橋梁。編譯原理講授的不是如何繪制NFA或者DFA，二是告訴讀者怎樣能夠自動實現NFA或DFA的構造。在實際應用中ε可以幫助計算機轉換NFA為DFA，而在屬性文法和語法制導階段，它也是溝通綜合屬性與繼承屬性、執行語義動作不可或缺的一部分。另外ε的使用可以大大簡化文法產生式的構造難度。我記得最初使用ε是為了使得文法體系（字母表）更加完善，但是在實際應用中卻變得應用廣泛(此觀點不一定正確)。 最後想說的是，在編譯中，ε也帶來了不小的麻煩，否則也就不會有諸如「去空產生式」這樣的演算法了:)
採納哦

D. 編譯原理詞法分析程序

（一）Block子程序分析

procere enter(k: object1); //填寫符號表
begin {enter object into table}
tx := tx + 1; //下標加1，tx的初始值為零，零下標不地址不填寫標志符，用於查找失敗使用
with table[tx] do //填入內容，保存標志符名和類型
begin name := id; kind := k;
case k of //根據類型判斷是否正確
constant: begin if num > amax then //如果是常量，判斷是否大於最大值，若是則報30號錯
begin error(30); num :=0 end;
val := num //否則保存數值
end;
varible: begin level := lev; adr := dx; dx := dx + 1; //如果是變數，填寫變數內部表示，LEVEl是變數的層次，adr為地址
end;
proc: level := lev //如果是過程，保存過程的層次
end
end
end {enter};

//查找符號表的位置
function position(id: alfa): integer;
var i: integer;
begin {find indentifier id in table} //從後向前查找
table[0].name := id; i := tx; //找到保存類型
while table[i].name <> id do i := i-1;
position := i //返回標志符在符號表中的位置
end {position};

procere block(lev,tx: integer; fsys: symset);
var dx: integer; {data allocation index} //數據分配索引
tx0: integer; {initial table index} //初始符號表索引
cx0: integer; {initial code index} //初始代碼索引
procere enter(k: object1); //填寫符號表，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; //查找符號表，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; //常量聲明
begin if sym = ident then //如果是標志符，讀入一個TOKEN
begin getsym;
if sym in [eql, becomes] then //讀入的是等號或符值號繼續判斷
begin if sym = becomes then error(1); //如果是「=」報1號錯
getsym; //讀入下一個TOKEN
if sym = number then //讀入的是數字，填寫符號表
begin enter(constant); getsym
end
else error(2) //如果不是數字，報2號錯
end else error(3) //不是等號或符值號，報3號錯
end else error(4) //如果不是標志符，報4號錯
end {constdeclaration};

procere vardeclaration; //變數聲明
begin if sym = ident then //讀入的是標志符，填寫符號表
begin enter(varible); getsym
end else error(4) //不是標志符，報4號錯
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); //表達式分析
var addop: symbol;
procere term(fsys: symset); //項分析
var mulop: symbol;
procere factor(fsys: symset); //因子分析
var i: integer;
begin test(facbegsys, fsys, 24); //讀入的是「（」，標志符或數字
while sym in facbegsys do
begin
if sym = ident then //是標志符，查表
begin i:= position(id);
if i = 0 then error(11) else //未找到，報11號錯
with table[i] do //找到，讀入標志符類型
case kind of
constant: gen(lit, 0, val); //寫常量命令
varible: gen(lod, lev-level, adr);//寫變數命令
proc: error(21) //過程名，報21號錯
end;
getsym //讀入下一個TOKEN
end else
if sym = number then //讀入的是數字
begin if num > amax then //如果數字大於最大數，報30號錯誤
begin error(30); num := 0
end;
gen(lit, 0, num); getsym //調用數字命令，讀入下一個TOKEN
end else
if sym = lparen then //讀入的是「（」
begin getsym; expression([rparen]+fsys); //調用表達式分析函數
if sym = rparen then getsym else error(22) //如果「（」後無「）」，報22號錯
end;
test(fsys, [lparen], 23)
end
end {factor};//因子分析結束

//項分析
begin {term} factor(fsys+[times, slash]); //調用因子分析程序
while sym in [times, slash] do //取得是乘、除號循環
begin mulop:=sym;getsym;factor(fsys+[times,slash]); //記錄符號，調用因子分析
if mulop=times then gen(opr,0,4) else gen(opr,0,5) //寫乘除指令
end
end {term};
begin {expression}
if sym in [plus, minus] then //如果是加減號
begin addop := sym; getsym; term(fsys+[plus,minus]); //記錄符號，調用項分析程序
if addop = minus then gen(opr, 0,1) //寫加減指令
end else term(fsys+[plus, minus]);
while sym in [plus, minus] do //如果是加減號循環
begin addop := sym; getsym; term(fsys+[plus,minus]);
if addop=plus then gen(opr,0,2) else gen(opr,0,3)
end
end {expression};

//條件過程
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) //取下一個TOKEN，調用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 //如果不是取到邏輯判斷符號，出錯.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); // <，小於
geq: gen(opr, 0, 11); // ]，大於等於
gtr: gen(opr, 0, 12); // >，大於
leq: gen(opr, 0, 13); // [，小於等於
end
end
end
end {condition};

begin {statement}
if sym = ident then //如果是標識符
begin i := position(id); //查找符號表
if i = 0 then error(11) else //未找到，標識符未定義，報11號錯
if table[i].kind <> varible then //如果標識符不是變數，報12號錯
begin {assignment to non-varible} error(12); i := 0
end;
getsym; if sym = becomes then getsym else error(13); //如果是變數讀入下一個TOKEN，不是賦值號，報13好錯；是則讀入一個TOKEN
expression(fsys); //調用表達是過程
if i <> 0 then //寫指令
with table[i] do gen(sto, lev-level, adr)
end else
if sym = callsym then //如果是過程調用保留字，讀入下一個TOKEN
begin getsym;
if sym <> ident then error(14) else //不是標識符報14號錯
begin i := position(id);
if i = 0 then error(11) else //是標識符，未定義，報13號錯
with table[i] do // 已定義的標識符讀入類型
if kind=proc then gen(cal, lev-level, adr) //是過程名寫指令
else error(15); //不是過程名，報15號錯
getsym
end
end else
if sym = ifsym then //如果是IF
begin getsym; condition([thensym, dosym]+fsys); //讀入一個TOKEN,調用條件判斷過程
if sym = thensym then getsym else error(16); //如果是THEN,讀入一個TOKEN，不是，報16號錯
cx1 := cx; gen(jpc, 0, 0); //寫指令
statement(fsys); code[cx1].a := cx
end else
if sym = beginsym then //如果是BEGIN
begin getsym; statement([semicolon, endsym]+fsys); //讀入一個TOKEN
while sym in [semicolon]+statbegsys do
begin
if sym = semicolon then getsym else error(10); //如果讀入的是分號
statement([semicolon, endsym]+fsys)
end;
if sym = endsym then getsym else error(17) //如果是END 讀入一個TOKEN，不是，報17號錯
end else
if sym = whilesym then //如果是WHILE
begin cx1 := cx; getsym; condition([dosym]+fsys); //調用條件過程
cx2 := cx; gen(jpc, 0, 0); //寫指令
if sym = dosym then getsym else error(18); //如果是DO讀入下一個TOKEN，不是報18號錯
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; //讀入TOKEN
repeat constdeclaration; //常量聲明
while sym = comma do
begin getsym; constdeclaration
end;
if sym = semicolon then getsym else error(5) //如果是分號讀入下一個TOKEN，不是報5號錯
until sym <> ident //不是標志符常量聲明結束
end;
if sym = varsym then 如果是VAR
begin getsym; 讀入下一個TOKEN
repeat vardeclaration; //變數聲明
while sym = comma do
begin getsym; vardeclaration
end;
if sym = semicolon then getsym else error(5) //如果是分號讀入下一個TOKEN，不是報5號錯
until sym <> ident; //不是標志符常量聲明結束
end;
while sym = procsym do //過程聲明
begin getsym;
if sym = ident then
begin enter(proc); getsym
end
else error(4); //不是標志符報4號錯
if sym = semicolon then getsym else error(5); //如果是分號讀入下一個TOKEN，不是報5號錯
block(lev+1, tx, [semicolon]+fsys);
if sym = semicolon then //如果是分號，取下一個TOKEN，不是報5號錯
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結束
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. 編譯原理 詞法分析程序的設計與實現實驗題

說他像蒼蠅，是罵蒼蠅呢還是罵他呢？

F. 請問編譯原理的詞法分析用C語言編寫的演算法是怎樣的

#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-只讀方式打開指定文件*/
if((fp=fopen(filename,"r"))==NULL) /*文件不存在輸出錯誤*/
{cout<<"文件不存在!"<<endl;exit(-1);}
cout<<"文件中內容如下:"<<endl;
for(int j=0;!feof(fp);j++){
c[j]=fgetc(fp);//從流中讀取字元
}
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"};//關鍵字數組
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;//初始化臨時數組
while (*p !=NULL){
q=s=a;
if((*p>='a'&&*p<='z')||(*p>='A'&&*p<='Z')||*p=='_'){//識別標識符
*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<<"關鍵字為:";r=0;}
else cout<<"標識符為:";
while(s!=q){
cout<<*s;
s++;
}
cout<<endl;
for(i=0;i<t;i++)a[i]=NULL;
}
else if(*p=='\''){//識別字元常量
p++;
while(*p!='\''){

*q=*p;
p++;
q++;
}
cout<<"字元常量為:";
while(s!=q){
cout<<*s;
s++;
}
cout<<endl;
for(i=0;i<t;i++)a[i]=NULL;
p++;
}
else if(*p=='\"'){//識別字元串常量
p++;
while(*p!='\"'){
*q=*p;
p++;
q++;
}
cout<<"字元串常量為:";
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=='/'){//識別運算符
cout<<"運算符為:"<<*p;
cout<<endl;
p++;
}
else if(*p==';'||*p==','){//識別分解符
cout<<"分界符為:"<<*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;}//識別實型常量
s++;
}
s=a;
if(w ==1){
cout<<"實型常量為:";
while(s!=q){
cout<<*s;
s++;
}
for(i=0;i<t;i++)a[i]=NULL;
}
else {
cout<<"整型常量為:";
while(s!=q){//識別整型常量
cout<<*s;
s++;
}
for(i=0;i<t;i++)a[i]=NULL;
}
cout<<endl;
}
else p++;
}
return 0;
}

G. 編譯原理詞法分析

編譯的詞法分析，一般是先畫一個狀態轉換圖，一般是有多少分支，就有多少if語句，分支裡面再分（可能有循環語句）。注意記住詞的類別和詞的字元串，請以以下代碼為例，理會一下詞法分析的大致過程。
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. 編譯原理課程設計－詞法分析器設計（C語言）

#include"stdio.h"/*定義I/O庫所用的某些宏和變數*/

#include"string.h"/*定義字元串庫函數*/

#include"conio.h"/*提供有關屏幕窗口操作函數*/

#include"ctype.h"/*分類函數*/

charprog[80]={''},

token[8];/*存放構成單詞符號的字元串*/

charch;

intsyn,/*存放單詞字元的種別碼*/

n,

sum,/*存放整數型單詞*/

m,p;/*p是緩沖區prog的指針，m是token的指針*/

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為字母字元*/{

while(isalpha(ch)||isdigit(ch))/*ch為字母字元或者數字字元*/{

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)/*字元串的比較*/{

syn=n+1;

break;}}

else

if(isdigit(ch))/*ch是數字字元*/{

while(isdigit(ch))/*ch是數字字元*/{

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();

}

程序測試結果

對源程序beginx:=9:ifx>9thenx:=2*x+1/3;end#的源文件，經過詞法分析後輸出如下圖5-1所示：

具體的你在修改修改吧

I. 求編譯原理的詞法分析器源碼

/* 我上編譯原理課時的第一次作業就是這個，flex源碼. */
%{
#include<math.h>
int num_lines=0;
%}
DIGIT [0-9]
ID [a-zA-Z_][a-zA-Z0-9]*
%%
"#include" {
printf("<包含頭文件,請手動合並文件\\>\n");
fprintf(yyout,"<包含頭文件,請手動合並文件\\>\n");
}
{DIGIT}+ {
printf("(3整數, \"%s\")\n", yytext);
fprintf(yyout,"(3整數, \"%s\")\n", yytext);
}
{DIGIT}+"."{DIGIT}* {
printf("(3浮點數, \" %s\")\n",yytext);
fprintf(yyout,"(3浮點數, \" %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("(不能識別字元, \"%s\")\n",yytext);
fprintf(yyout,"(不能識別字元, \"%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：我們第一次作業的要求。
實驗一：用高級語言編寫詞法分析器（用lex生成）一、實驗目的：編制一個識別C語言子集的詞法分析器。從輸入的源程序中，識別出各個具有獨立意義的記號，即基本保留字、標識符、常數、運算符、分隔符五大類。並依次輸出各個記號的內部編碼及記號符號自身值。（遇到錯誤時可顯示「Error」，然後跳過錯誤部分繼續顯示）二、實驗過程和指導：（一）准備：1.閱讀課本有關章節，明確語言的詞法，寫出基本保留字、標識符、常數、運算符、分隔符和程序例。2.初步編制好程序。3.准備好多組測試數據。（二）程序要求：程序輸入/輸出示例：如源程序為C語言。輸入如下一段：main(){ int a,b; a = 10; b = a + 20;}要求輸出如下：（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（滿足以下要求可獲得70%該題的得分）：識別保留字：if、int、for、while、do、return、break、continue其他的都識別為標識符；常數為無符號整形數；運算符包括：+、-、*、/、=、>、<、>=、<=、!=分隔符包括：,、;、{、}、(、)以上為參考，具體可自行增刪。 三、實驗檢查：1.程序：輸入：測試數據（以文件形式）；輸出：二元組（以文件形式）。2.實驗報告：（1）功能描述：該程序具有什麼功能？（2）狀態轉換圖。（2）程序結構描述：函數調用格式、參數含義、返回值描述、函數功能；函數之間的調用關系圖、程序總體執行流程圖。（4）源程序代碼。（5）實驗過程記錄：出錯次數、出錯嚴重程度、解決辦法摘要。（6）實驗總結：你在編程過程中花時多少？多少時間在紙上設計？多少時間上機輸入和調試？多少時間在思考問題？遇到了哪些難題？你是怎麼克服的？你對你的程序的評價？你的收獲有哪些？

另可附加：關鍵字 有符號數 符號表填寫 行號記錄，等
*/