A. c语言编译原理是什么
编译共分为四个阶段：预处理阶段、编译阶段、汇编阶段、链接阶段。
1、预处理阶段：
主要工作是将头文件插入到所写的代码中，生成扩展名为“.i”的文件替换原来的扩展名为“.c”的文件，但是原来的文件仍然保留，只是执行过程中的实际文件发生了改变。（这里所说的替换并不是指原来的文件被删除）
2、汇编阶段：
插入汇编语言程序，将代码翻译成汇编语言。编译器首先要检查代码的规范性、是否有语法错误等，以确定代码的实际要做的工作，在检查无误后，编译器把代码翻译成汇编语言，同时将扩展名为“.i”的文件翻译成扩展名为“.s”的文件。
3、编译阶段：
将汇编语言翻译成机器语言指令，并将指令打包封存成可重定位目标程序的格式,将扩展名为“.s”的文件翻译成扩展名为“.o”的二进制文件。
4、链接阶段：
在示例代码中，改代码文件调用了标准库中printf函数。而printf函数的实际存储位置是一个单独编译的目标文件（编译的结果也是扩展名为“.o”的文件），所以此时主函数调用的时候，需要将该文件（即printf函数所在的编译文件）与hello world文件整合到一起，此时链接器就可以大显神通了，将两个文件合并后生成一个可执行目标文件。
B. 编译原理语法分析器程序设计，用C语言或C++，哪里有这个程序
1.文法简略，没有实现的部分，可以在此文法的基础上进行扩充，本程序的采用自顶向下的LL(1)文法。
2.可以自动实现求First
集和
Follow
集。
3.处终结符外（有些硬编码的成分），终结符的文法可以自定义，也就是说读者可以自定义文法。
4.为方便理解，C语言的文法描述写成中文。
5.程序将词法分析和语法分析结合起来，词法分析的结果作为语法分析的输入。
6.最终结果在控制台显示的有：词法分析、First集、Follow集、Select集，在preciateResult.txt
中写入了语法分析结果，在preciateTable.txt
中写入了预测分析表。
7.文法的词素之间必须有空格分开。
C. 编译原理语法分析器程序设计，用C语言或C++，哪里有这个程序
我写团孙好旦困的.
scan.h
/*
* scan.h
* ccompiler
*
* Created by on 09-10-12.
* Copyright 2009 __MyCompanyName__. All rights reserved.
*
*/
#ifndef _SCAN_H_
#define _SCAN_H_
#include <string>
#include <fstream>
using namespace std;
typedef enum
{
ENDFILE,ERROR,
ELSE,IF,INT,RETURN,VOID,WHILE,
ID,NUM,
ASSIGN,EQ,LT,GT,LE,GE,NE,ADD,SUB,MUL,DIV,SEMI,LPAREN,RPAREN,LZK,RZK,LDK,RDK,COMMA
}
TokenType;
class Scan
{
private:
string tokenStr;
string linebuffer;
ifstream * in;
int linepos;
int lineno;
bool EOF_Flag;
bool traceScan;
void printToken(TokenType tt,const string &tok);
public:
Scan(ifstream * in)
{
this->in=in;
linepos=0;
linebuffer="";
lineno=0;
EOF_Flag=false
traceScan=true;
}
char getNextChar();
void ungetNextChar();
TokenType reservedLookup(string &s);
void setTraceScan(bool f);
bool getTraceScan();
TokenType getToken();
string getTokenStr();
};
#endif
scan.cpp
/*
* scan.cpp
* ccompiler
*
* Created by on 09-10-12.
* Copyright 2009 __MyCompanyName__. All rights reserved.
*
*/
#include <string>塌迟链
#include <fstream>
#include <iostream>
using namespace std;
#include "scan.h"
typedef enum
{START,INNUM,INID,INNOTEQ,TEMPE,TEMPG,TEMPL,SLASH,INCOMMENT1,INCOMMENT2,DONE}
StateType;
static struct
{
string str;
TokenType tok;
} reservedWords[6]
={{"else",ELSE},{"if",IF},{"int",INT},{"return",RETURN},{"void",VOID},{"while",WHILE}};
char Scan::getNextChar()
{
if(linepos>=linebuffer.size())
{
if(getline(*in,linebuffer))
{
linebuffer+="\n";
lineno++;
linepos=0;
return linebuffer[linepos++];
}
else
{
EOF_Flag=true;
return EOF;
}
}
else
return linebuffer[linepos++];
}
void Scan::ungetNextChar()
{
if(!EOF_Flag) linepos--;
}
TokenType Scan::reservedLookup(string &s)
{
for(int i=0;i<6;i++)
if(s==reservedWords[i].str)
return reservedWords[i].tok;
return ID;
}
void Scan::setTraceScan(bool f)
{
traceScan=f;
}
bool Scan::getTraceScan()
{
return traceScan;
}
TokenType Scan::getToken()
{
tokenStr="";
TokenType currentToken;
StateType state=START;
while(state!=DONE)
{
bool save=false;
char c=getNextChar();
switch (state) {
case START:
if(c>='0'&&c<='9'){
state=INNUM;
save=true;
}
else if((c>='a'&&c<='z')||(c>='A'&&c<='Z')){
state=INID;
save=true;
}
else if(c==' '||c=='\t'||c=='\n')
{
state=START;
}
else if(c=='/'){
state=SLASH;
}
else if(c=='='){
state=TEMPE;
}
else if(c=='>')
state=TEMPG;
else if(c=='<')
state=TEMPL;
else if(c=='!')
state=INNOTEQ;
else
{
state=DONE;
switch (c) {
case EOF:
currentToken=ENDFILE;
break;
case '+':
currentToken=ADD;
break;
case '-':
currentToken=SUB;
break;
case '*':
currentToken=MUL;
break;
case '(':
currentToken=LPAREN;
break;
case ')':
currentToken=RPAREN;
break;
case '[':
currentToken=LZK;
break;
case ']':
currentToken=RZK;
break;
case '{':
currentToken=LDK;
break;
case '}':
currentToken=RDK;
break;
case ';':
currentToken=SEMI;
break;
case ',':
currentToken=COMMA;
break;
default:
currentToken=ERROR;
break;
}
}
break;
case INNUM:
if(c<'0'||c>'9')
{
ungetNextChar();
state=DONE;
currentToken=NUM;
}
else
save=true;
break;
case INID:
if(!((c>='a'&&c<='z')||(c>='A'&&c<='Z')))
{
ungetNextChar();
state=DONE;
currentToken=ID;
}
else
save=true;
break;
case SLASH:
if (c!='*')
{
state=DONE;
currentToken=DIV;
}
else
state=INCOMMENT1;
break;
case INCOMMENT1:
if (c!='*')
state=INCOMMENT1;
else if(c==EOF){
state=DONE;
currentToken=ENDFILE;
}
else
state=INCOMMENT2;
break;
case INCOMMENT2:
if (c=='*') {
state=INCOMMENT2;
}else if(c=='/'){
state=START;
}else if(c==EOF){
state=DONE;
currentToken=ENDFILE;
}else {
state=INCOMMENT1;
}
break;
case TEMPE:
if (c=='=') {
state=DONE;
currentToken=EQ;
}else{
state=DONE;
ungetNextChar();
currentToken=ASSIGN;
}
break;
case TEMPG:
if (c=='=') {
state=DONE;
currentToken=GE;
}else{
state=DONE;
ungetNextChar();
currentToken=GT;
}
break;
case TEMPL:
if (c=='=') {
state=DONE;
currentToken=LE;
}else{
state=DONE;
ungetNextChar();
currentToken=LT;
}
break;
case INNOTEQ:
if (c=='=') {
state=DONE;
currentToken=NE;
}else {
state=DONE;
ungetNextChar();
currentToken=ERROR;
}
break;
default:
cerr<<"Scanner Bug: state= "<<state<<endl;
state=DONE;
currentToken=ERROR;
break;
}
if(save){
string newChar(1,c);
tokenStr+=newChar;
}
if (state==DONE&¤tToken==ID)
currentToken=reservedLookup(tokenStr);
}
if (traceScan) {
cout<<"Scan at line "<<lineno<<" token: ";
printToken(currentToken, tokenStr);
cout<<endl;
}
return currentToken;
}
string Scan::getTokenStr()
{
return tokenStr;
}
void Scan::printToken(TokenType tt,const string &tok)
{
string type;
switch (tt) {
case ENDFILE:
type="EOF";
break;
case ERROR:
type="ERROR";
break;
case ELSE:
case IF:
case INT:
case RETURN:
case VOID:
case WHILE:
type="reserved word";
break;
case ID:
type="ID";
break;
case NUM:
type="NUM";
break;
case ASSIGN:
type="=";
break;
case EQ:
type="==";
break;
case LT:
type="<";
break;
case GT:
type=">";
break;
case LE:
type="<=";
break;
case GE:
type=">=";
break;
case NE:
type="!=";
break;
case ADD:
type="+";
break;
case SUB:
type="-";
break;
case MUL:
type="*";
break;
case DIV:
type="/";
break;
case SEMI:
type=";";
break;
case LPAREN:
type="(";
break;
case RPAREN:
type=")";
break;
case LZK:
type="[";
break;
case RZK:
type="]";
break;
case LDK:
type="{";
case RDK:
type="}";
break;
case COMMA:
type=",";
break;
default:
break;
}
cout << type<<": "<<tok;
}
main.cpp
#include <iostream>
#include <fstream>
#include <string>
using namespace std;
#include "scan.h"
int main (int argc, char * const argv[]) {
string fileName="/Users/huanglongyin/scan_in.txt";
//cout<< "File name: ";
//cin>>fileName;
ifstream in(fileName.c_str());
if(!in){
cerr<<"Error occurs when openning file "<<fileName<<endl;
return -1;
}
Scan scan(&in);
while(scan.getToken()!=ENDFILE);
return 0;
}
D. 急（高悬赏 帮个忙） 求编译原理课程设计---c语言实现c-的语法分析，在线等
新建一个文本文档在你工程目录下，名字起为"输入.txt",里面的内容可以为
begin a:=1+7*(6+3);b:=1end#
输出是在"输出.txt"中查看，以下为输出情况：
词法分析结果如下:
(1, begin)
(10, a)
(18, :=)
(11, 1)
(13, +)
(11, 7)
(15, *)
(27, ()
(11, 6)
(13, +)
(11, 3)
(28, ))
(26, ;)
(10, b)
(18, :=)
(11, 1)
(6, end)
(0, #)
语法分析结果如下:（以四元式形式输出）
( +, 6, 3, t1)
( *, 7, t1, t2)
( +, 1, t2, t3)
( =, t3, __, a)
( =, 1, __, b)
//提供一个编译原理的语义分析程序 你可以直接拆猜森复制 用TC进行调试
#include "stdio.h"
#include "string.h"
#include <malloc.h>
#include <conio.h>
#include "stdlib.h"
char prog[100],token[8],ch;
char *rwtab[6]={"begin","if","then","while","do","end"};
int syn,p,m,n,sum,q;
int kk;
//四元式表的结构如下：
struct
{
char result1[8];
char ag11[8];
char op1[8];
char ag21[8];
}quad[20];
char *factor();
char *expression();
int yucu();
char *term();
int statement();
int lrparser();
char *newtemp();
void scaner();
void emit(char *result,char *ag1,char *op,char *ag2);
void main()
{
FILE *fp1,*fp2;
if((fp1=fopen("输入.txt","rt"))==NULL)
{
printf("Cannot open 输入.txt\n");
getch();
exit(1);
}
if((fp2=fopen("输出.txt","wt+"))==NULL)
{
printf("Cannot create 输出.txt FILE.strike any key exit");
getch();
exit(1);
}
int j;
q=p=kk=0;
p=0;
//printf("Please Input a String(end with '#'旅亩):\n");
while(ch!='#')
{
ch = fgetc(fp1);
if(ch == EOF)
{
printf("文件为空，请检查后再尝试!");
return ;
}
prog[p++]=ch;
}
if(prog[p]=='#')
{
printf("输入的待分析的串不是以'#'结尾,请修改之后再尝试!\n");
return;
}
p=0;
char buffer1[200] = {0};
sprintf(buffer1,"词法分析结果如下:\n");
fputs(buffer1,fp2);
//printf("词法分析结果如下:\n");
do
{
scaner();
switch(syn)
{
case 11:
//printf("(%d,%d)\n"兆旦,syn,sum);
sprintf(buffer1,"(%d, %d) \n",syn,sum);
fputs(buffer1,fp2);
break;
default:
//printf("(%d,%s)\n",syn,token);
sprintf(buffer1,"(%d, %s)\n",syn,token);
fputs(buffer1,fp2);
break;
}
}while(syn!=0);
printf("\n");
p=0;
char buffer[200]={0};
sprintf(buffer,"语法分析结果如下:（以四元式形式输出）\n");
fputs(buffer,fp2);
//printf("语法分析结果如下:（以四元式形式输出）\n");
scaner();//扫描函数
lrparser();
if(q>19)
printf(" to long sentense!\n");
else
{
for (j=0;j<q;j++)
{
//printf("( %s, %s, %s, %s) \n\n",quad[j].op1,quad[j].ag11,quad[j].ag21,quad[j].result1);
sprintf(buffer,"( %s, %s, %s, %s) \n\n",quad[j].op1,quad[j].ag11,quad[j].ag21,quad[j].result1);
fputs(buffer,fp2);
}
}
printf("已把相应的词法和语法的结果保存到相应的文件中，请查阅!\n");
fclose(fp1);
fclose(fp2);
}
int lrparser()
{
int schain=0;
kk=0;
if (syn==1) //得到begin
{
scaner();//扫描下个字符
schain=yucu();
if(syn==6)//得到end
{
scaner();//扫描下个字符
if((syn==0)&&(kk==0)) //得到#
printf("Success!\n");
}
else
{
if(kk!=1)
printf("short of 'end' !\n");
kk=1;
getch();
exit(0);
}
}
else
{
printf("short of 'begin' !\n");
kk=1;
getch();
exit(0);
}
return (schain);
}
int yucu()
{
int schain=0;
schain=statement();
while(syn==26)
{
scaner();
schain=statement();
}
return (schain);
}
int statement()
{
char tt[8],eplace[8];
int schain=0;
if (syn==10)
{
strcpy(tt,token); //tt中保存的是第一个字符
scaner();
if(syn==18) //检测到=号
{
scaner();
strcpy(eplace,expression());
emit(tt,eplace,"=","__");
schain=0;
}
else
{
printf("short of sign ':=' !\n");
kk=1;
getch();
exit(0);
}
return (schain);
}
}
char *expression()
{
char *tp,*ep2,*eplace,*tt;
tp=(char *)malloc(12);
ep2=(char *)malloc(12);
eplace=(char *)malloc(12);
tt=(char *)malloc(12);
strcpy(eplace,term());
while((syn==13)||(syn==14))
{
if (syn==13)
strcpy(tt,"+");
else
strcpy(tt,"-");
scaner();
strcpy(ep2,term());
strcpy(tp,newtemp());
emit(tp,eplace,tt,ep2);
strcpy(eplace,tp);
}
return (eplace);
}
char *term()
{
char *tp,*ep2,*eplace,*tt;
tp=(char *)malloc(12);
ep2=(char *)malloc(12);
eplace=(char *)malloc(12);
tt=(char *)malloc(12);
strcpy(eplace,factor());
while((syn==15)||(syn==16))
{
if (syn==15)
strcpy(tt,"*");
else
strcpy(tt,"/");
scaner();
strcpy(ep2,factor());
strcpy(tp,newtemp());
emit(tp,eplace,tt,ep2);
strcpy(eplace,tp);
}
return (eplace);
}
char *factor()
{
char *fplace;
fplace=(char *)malloc(12);
strcpy(fplace,"");
if(syn==10) //得到字符
{
strcpy(fplace,token);
scaner();
}
else if(syn==11) //得到数字
{
itoa(sum,fplace,10);
scaner();
}
else if(syn==27) //得到)
{
scaner();
fplace=expression();
if(syn==28) //得到(
scaner();
else
{
printf("error on ')' !\n");
kk=1;
getch();
exit(0);
}
}
else
{
printf("error on '(' !\n");
kk=1;
getch();
exit(0);
}
return (fplace);
}
//该函数回送一个新的临时变量名，临时变量名产生的顺序为T1,T2...
char *newtemp()
{
char *p;
char m[8];
p=(char *)malloc(8);
kk++;
itoa(kk,m,10);
strcpy(p+1,m);
p[0]='t';
return(p); //设置中间变量名放在一个字符数组中，字符数组的第一个字符为t第二个字符为m表示的数值
}
void scaner()
{
sum=0;
///for(m=0;m<8;m++)
//token[m++]=NULL;
memset(token,0,8);
m=0;
ch=prog[p++];
while(ch==' ')
ch=prog[p++];
if(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A')))
{
while(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A'))||((ch>='0')&&(ch<='9')))
{
token[m++]=ch;
ch=prog[p++];
}
p--;
syn=10;
token[m++]='\0';
for(n=0;n<6;n++)
if(strcmp(token,rwtab[n])==0)
{
syn=n+1;
break;
}
}
else if((ch>='0')&&(ch<='9'))
{
while((ch>='0')&&(ch<='9'))
{
sum=sum*10+ch-'0';
ch=prog[p++];
}
p--;
syn=11;
}
else switch(ch)
{
case '<':m=0;
ch=prog[p++];
if(ch=='>')
{
syn=21;
}
else if(ch=='=')
{
syn=22;
}
else
{
syn=20;
p--;
}
break;
case '>':m=0;
ch=prog[p++];
if(ch=='=')
{
syn=24;
}
else
{
syn=23;
p--;
}
break;
case ':':m=0;
token[m++] = ch;
ch=prog[p++];
if(ch=='=')
{
syn=18;
token[m++] = ch;
}
else
{
syn=17;
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=27;token[0] = ch;break;
case ')': syn=28;token[0] = ch;break;
case '=': syn=25;token[0] = ch;break;
case ';': syn=26;token[0] = ch;break;
case '#': syn=0;token[0] = ch;break;
default: syn=-1;break;
}
}
//该函数是生成一个三地址语句送到四元式表中
void emit(char *result,char *ag1,char *op,char *ag2)
{
strcpy(quad[q].result1,result);
strcpy(quad[q].ag11,ag1);
strcpy(quad[q].op1,op);
strcpy(quad[q].ag21,ag2);
q++; //统计有多少个四元式
}
E. 编译原理课程设计
%{
/* FILENAME: C.Y */
%}
#define YYDEBUG_LEXER_TEXT (yylval) /* our lexer loads this up each time */
#define YYDEBUG 1 /* get the pretty debugging code to compile*/
#define YYSTYPE char * /* interface with flex: should be in header file */
/* Define terminal tokens */
/* keywords */
%token AUTO DOUBLE INT STRUCT
%token BREAK ELSE LONG SWITCH
%token CASE ENUM REGISTER TYPEDEF
%token CHAR EXTERN RETURN UNION
%token CONST FLOAT SHORT UNSIGNED
%token CONTINUE FOR SIGNED VOID
%token DEFAULT GOTO SIZEOF VOLATILE
%token DO IF STATIC WHILE
/* ANSI Grammar suggestions */
%token IDENTIFIER STRINGliteral
%token FLOATINGconstant INTEGERconstant CHARACTERconstant
%token OCTALconstant HEXconstant
/* New Lexical element, whereas ANSI suggested non-terminal */
%token TYPEDEFname /* Lexer will tell the difference between this and
an identifier! An identifier that is CURRENTLY in scope as a
typedef name is provided to the parser as a TYPEDEFname.*/
/* Multi-Character operators */
%token ARROW /* ->轮宴 */
%token ICR DECR /* ++ -- */
%token LS RS /* << >> */
%token LE GE EQ NE /* <= >= == != */
%token ANDAND OROR /* && || */
%token ELLIPSIS /* ... */腊隐银
/* modifying assignment operators */
%token MULTassign DIVassign MODassign /* *= /= %= */
%token PLUSassign MINUSassign /携虚* += -= */
%token LSassign RSassign /* <<= >>= */
%token ANDassign ERassign ORassign /* &= ^= |= */
%start translation_unit
%%
/* CONSTANTS */
constant:
INTEGERconstant
| FLOATINGconstant
/* We are not including ENUMERATIONconstant here because we
are treating it like a variable with a type of "enumeration
constant". */
| OCTALconstant
| HEXconstant
| CHARACTERconstant
;
string_literal_list:
STRINGliteral
| string_literal_list STRINGliteral
;
/************************* EXPRESSIONS ********************************/
primary_expression:
IDENTIFIER /* We cannot use a typedef name as a variable */
| constant
| string_literal_list
| '(' comma_expression ')'
;
postfix_expression:
primary_expression
| postfix_expression '[' comma_expression ']'
| postfix_expression '(' ')'
| postfix_expression '(' argument_expression_list ')'
| postfix_expression {} '.' member_name
| postfix_expression {} ARROW member_name
| postfix_expression ICR
| postfix_expression DECR
;
member_name:
IDENTIFIER
| TYPEDEFname
;
argument_expression_list:
assignment_expression
| argument_expression_list ',' assignment_expression
;
unary_expression:
postfix_expression
| ICR unary_expression
| DECR unary_expression
| unary_operator cast_expression
| SIZEOF unary_expression
| SIZEOF '(' type_name ')'
;
unary_operator:
'&'
| '*'
| '+'
| '-'
| '~'
| '!'
;
cast_expression:
unary_expression
| '(' type_name ')' cast_expression
;
multiplicative_expression:
cast_expression
| multiplicative_expression '*' cast_expression
| multiplicative_expression '/' cast_expression
| multiplicative_expression '%' cast_expression
;
additive_expression:
multiplicative_expression
| additive_expression '+' multiplicative_expression
| additive_expression '-' multiplicative_expression
;
shift_expression:
additive_expression
| shift_expression LS additive_expression
| shift_expression RS additive_expression
;
relational_expression:
shift_expression
| relational_expression '<' shift_expression
| relational_expression '>' shift_expression
| relational_expression LE shift_expression
| relational_expression GE shift_expression
;
equality_expression:
relational_expression
| equality_expression EQ relational_expression
| equality_expression NE relational_expression
;
AND_expression:
equality_expression
| AND_expression '&' equality_expression
;
exclusive_OR_expression:
AND_expression
| exclusive_OR_expression '^' AND_expression
;
inclusive_OR_expression:
exclusive_OR_expression
| inclusive_OR_expression '|' exclusive_OR_expression
;
logical_AND_expression:
inclusive_OR_expression
| logical_AND_expression ANDAND inclusive_OR_expression
;
logical_OR_expression:
logical_AND_expression
| logical_OR_expression OROR logical_AND_expression
;
conditional_expression:
logical_OR_expression
| logical_OR_expression '?' comma_expression ':'
conditional_expression
;
assignment_expression:
conditional_expression
| unary_expression assignment_operator assignment_expression
;
assignment_operator:
'='
| MULTassign
| DIVassign
| MODassign
| PLUSassign
| MINUSassign
| LSassign
| RSassign
| ANDassign
| ERassign
| ORassign
;
comma_expression:
assignment_expression
| comma_expression ',' assignment_expression
;
constant_expression:
conditional_expression
;
/* The following was used for clarity */
comma_expression_opt:
/* Nothing */
| comma_expression
;
/******************************* DECLARATIONS *********************************/
/* The following is different from the ANSI C specified grammar.
The changes were made to disambiguate typedef's presence in
declaration_specifiers (vs. in the declarator for redefinition);
to allow struct/union/enum tag declarations without declarators,
and to better reflect the parsing of declarations (declarators
must be combined with declaration_specifiers ASAP so that they
are visible in scope).
Example of typedef use as either a declaration_specifier or a
declarator:
typedef int T;
struct S { T T;}; /* redefinition of T as member name * /
Example of legal and illegal statements detected by this grammar:
int; /* syntax error: vacuous declaration * /
struct S; /* no error: tag is defined or elaborated * /
Example of result of proper declaration binding:
int a=sizeof(a); /* note that "a" is declared with a type in
the name space BEFORE parsing the initializer * /
int b, c[sizeof(b)]; /* Note that the first declarator "b" is
declared with a type BEFORE the second declarator is
parsed * /
*/
declaration:
sue_declaration_specifier ';'
| sue_type_specifier ';'
| declaring_list ';'
| default_declaring_list ';'
;
/* Note that if a typedef were redeclared, then a declaration
specifier must be supplied */
default_declaring_list: /* Can't redeclare typedef names */
declaration_qualifier_list identifier_declarator {} initializer_opt
| type_qualifier_list identifier_declarator {} initializer_opt
| default_declaring_list ',' identifier_declarator {} initializer_opt
;
declaring_list:
declaration_specifier declarator {} initializer_opt
| type_specifier declarator {} initializer_opt
| declaring_list ',' declarator {} initializer_opt
;
declaration_specifier:
basic_declaration_specifier /* Arithmetic or void */
| sue_declaration_specifier /* struct/union/enum */
| typedef_declaration_specifier /* typedef*/
;
type_specifier:
basic_type_specifier /* Arithmetic or void */
| sue_type_specifier /* Struct/Union/Enum */
| typedef_type_specifier /* Typedef */
;
declaration_qualifier_list: /* const/volatile, AND storage class */
storage_class
| type_qualifier_list storage_class
| declaration_qualifier_list declaration_qualifier
;
type_qualifier_list:
type_qualifier
| type_qualifier_list type_qualifier
;
declaration_qualifier:
storage_class
| type_qualifier /* const or volatile */
;
type_qualifier:
CONST
| VOLATILE
;
basic_declaration_specifier: /*Storage Class+Arithmetic or void*/
declaration_qualifier_list basic_type_name
| basic_type_specifier storage_class
| basic_declaration_specifier declaration_qualifier
| basic_declaration_specifier basic_type_name
;
basic_type_specifier:
basic_type_name /* Arithmetic or void */
| type_qualifier_list basic_type_name
| basic_type_specifier type_qualifier
| basic_type_specifier basic_type_name
;
sue_declaration_specifier: /* Storage Class + struct/union/enum */
declaration_qualifier_list elaborated_type_name
| sue_type_specifier storage_class
| sue_declaration_specifier declaration_qualifier
;
sue_type_specifier:
elaborated_type_name /* struct/union/enum */
| type_qualifier_list elaborated_type_name
| sue_type_specifier type_qualifier
;
typedef_declaration_specifier: /*Storage Class + typedef types */
typedef_type_specifier storage_class
| declaration_qualifier_list TYPEDEFname
| typedef_declaration_specifier declaration_qualifier
;
typedef_type_specifier: /* typedef types */
TYPEDEFname
| type_qualifier_list TYPEDEFname
| typedef_type_specifier type_qualifier
;
storage_class:
TYPEDEF
| EXTERN
| STATIC
| AUTO
| REGISTER
;
basic_type_name:
INT
| CHAR
| SHORT
| LONG
| FLOAT
| DOUBLE
| SIGNED
| UNSIGNED
| VOID
;
elaborated_type_name:
aggregate_name
| enum_name
;
aggregate_name:
aggregate_key '{' member_declaration_list '}'
| aggregate_key identifier_or_typedef_name
'{' member_declaration_list '}'
| aggregate_key identifier_or_typedef_name
;
F. 求C语言文法及产生式！要做C编译器——语法分析部分
转自http://blog.csdn.net/rill_zhen/article/details/7701259http://blog.csdn.net/rill_zhen/article/details/7701259
希望能帮到你
编译原理-1-C语言的文法
编译原理-1-C语言的文法
c语言的文法产生式：
program ->
银此指external_declaration
| program external_declaration
external_declaration ->
function_definition
| declaration
function_definition -> type_specifier declarator compound_statement
type_specifier ->
锋配VOID
| CHAR
| INT
| FLOAT
declarator
pointer direct_declarator
| direct_declarator
Pointer->
'*'
| '*' pointer
direct_declarator
IDENTIFIER
|direct_declarator’[‘ ‘]’
|direct_declarator ’[’ constant_expression ’]’
| IDENTIFIER '(' parameter_list ')'
| IDENTIFIER '(' ')'
|direct_declarator‘,’identifier_list
identifier_list
: IDENTIFIER
| identifier_list ',' IDENTIFIER
constant_expression->
conditional_expression
parameter_list ->
parameter_declaration
| parameter_list ',' parameter_declaration
parameter_declaration ->
declaration_specifiers IDENTIFIER
compound_statement ->
'{' '}'
| '{' statement_list '}'
| '{' declaration_list statement_list '}'
declaration_list ->
declaration
| declaration_list declaration
Declaration->
init_declarator
| init_declarator_list ',' init_declarator
init_declarator ->
declarator
| declarator '=' initializer
Initializer ->
assignment_expression
| '{' initializer_list '}'
| '{' initializer_list ',' '}'
initializer_list ->
initializer
| initializer_list ',' initializer
statement_list->
statement
| statement_list statement
Statement ->
| compound_statement
| expression_statement
| selection_statement
| iteration_statement
| jump_statement
expression_statement ->
';'
| expression ';'
selection_statement
: IF '(' expression ')' statement
扒腊| IF '(' expression ')' statement ELSE statement
iteration_statement->
WHILE '(' expression ')' statement
| FOR '(' expression_statement expression_statement ')' statement
| FOR '(' expression_statement expression_statement expression ')' statement
jump_statement
| CONTINUE ';'
| BREAK ';'
| RETURN ';'
| RETURN expression ';'
expression
: assignment_expression
| expression ',' assignment_expression
assignment_expression ->
conditional_expression
| unary_expression assignment_operator assignment_expression
conditional_expression ->
logical_or_expression
| logical_or_expression ' ' expression ':' conditional_expression
logical_or_expression ->
logical_and_expression
| logical_or_expression OR_OP logical_and_expression
logical_and_expression
: inclusive_or_expression
| logical_and_expression AND_OP inclusive_or_expression
inclusive_or_expression->
exclusive_or_expression
| inclusive_or_expression '|' exclusive_or_expression
exclusive_or_expression
: and_expression
| exclusive_or_expression '^' and_expression
and_expression
: equality_expression
| and_expression '&' equality_expression
equality_expression
: relational_expression
| equality_expression EQ_OP relational_expression
| equality_expression NE_OP relational_expression
relational_expression
: shift_expression
| relational_expression '$amp;
| relational_expression '$amp;>apos;$ shift_expression
| relational_expression LE_OP shift_expression
| relational_expression GE_OP shift_expression
shift_expression
: additive_expression
| shift_expression LEFT_OP additive_expression
| shift_expression RIGHT_OP additive_expression
additive_expression
: multiplicative_expression
| additive_expression '+' multiplicative_expression
| additive_expression '-' multiplicative_expression
multiplicative_expression
: cast_expression
| multiplicative_expression '*' cast_expression
| multiplicative_expression '/' cast_expression
| multiplicative_expression '%' cast_expression
cast_expression
: unary_expression
| '(' type_name ')' cast_expression
unary_expression
: postfix_expression
| INC_OP unary_expression
| DEC_OP unary_expression
| unary_operator cast_expression
| SIZEOF unary_expression
| SIZEOF '(' type_name ')'
postfix_expression ->
: primary_expression
| postfix_expression '[' expression ']'
| postfix_expression '(' ')'
| postfix_expression '(' argument_expression_list ')'
| postfix_expression '.' IDENTIFIER
| postfix_expression PTR_OP IDENTIFIER
| postfix_expression INC_OP
| postfix_expression DEC_OP
primary_expression ->
IDENTIFIER
| CONSTANT
| STRING_LITERAL
| '(' expression ')'
argument_expression_list
: assignment_expression
| argument_expression_list ',' assignment_expression
unary_operator
: '&'
| '*'
| '+'
| '-'
| '~'
| '!'
assignment_operator ->
'='
| MUL_ASSIGN
| DIV_ASSIGN
| MOD_ASSIGN
| ADD_ASSIGN
| SUB_ASSIGN
| LEFT_ASSIGN
| RIGHT_ASSIGN
| AND_ASSIGN
| XOR_ASSIGN
| OR_ASSIGN
storage_class_specifier ->
TYPEDEF
| EXTERN
| STATIC
| AUTO
| REGISTER
struct_or_union_specifier
: struct_or_union IDENTIFIER '{' struct_declaration_list '}'
| struct_or_union '{' struct_declaration_list '}'
| struct_or_union IDENTIFIER
struct_or_union
: STRUCT
| UNION
struct_declaration_list
: struct_declaration
| struct_declaration_list struct_declaration
struct_declaration
: specifier_qualifier_list struct_declarator_list ';'
specifier_qualifier_list ->
type_specifier specifier_qualifier_list
| type_specifier
| type_qualifier specifier_qualifier_list
| type_qualifier
struct_declarator_list ->
struct_declarator
| struct_declarator_list ',' struct_declarator
struct_declarator ->
: declarator
| ':' constant_expression
| declarator ':' constant_expression
enum_specifier ->
ENUM '{' enumerator_list '}'
| ENUM IDENTIFIER '{' enumerator_list '}'
| ENUM IDENTIFIER
enumerator_list ->
enumerator
| enumerator_list ',' enumerator
Enumerator ->
IDENTIFIER
| IDENTIFIER '=' constant_expression
type_qualifier ->
CONST
| VOLATILE
type_qualifier_list ->
type_qualifier
| type_qualifier_list type_qualifier
parameter_type_list ->
parameter_list
| parameter_list ',' ELLIPSIS
parameter_list ->
: parameter_declaration
| parameter_list ',' parameter_declaration
type_name ->
specifier_qualifier_list
| specifier_qualifier_list abstract_declarator
abstract_declarator ->
pointer
| direct_abstract_declarator
| pointer direct_abstract_declarator
direct_abstract_declarator ->
'(' abstract_declarator ')'
| '[' ']'
| '[' constant_expression ']'
| direct_abstract_declarator '[' ']'
| direct_abstract_declarator '[' constant_expression ']'
| '(' ')'
| '(' parameter_type_list ')'
| direct_abstract_declarator '(' ')'
| direct_abstract_declarator '(' parameter_type_list ')'
labeled_statement ->
IDENTIFIER ':' statement
| CASE constant_expression ':' statement
| DEFAULT ':' statement
G. 本科独立用C语言完成没有优化的C语言编译器属于什么水平
我觉得水平还是很高的，但意义恐怕不大。编译器技术是非常成熟的领域，而且由于应用场景的限
制实时，复杂的算法已经自动出局了，你可选的东西是有限的。编译器可能有很多实现的形
式，虚拟机/解释器/静态编译器 等，也有成熟的开源实现。作为本科生，而非专门研究该分支的学生，应该合理分配自己学习的时间，如果做这个编译器就干
掉了大半年，那计网和OS这些课程该咋办？
我知道很多人会认为没有做编译器优化特指中段优化，不考虑机器码上的优化比较划水。但编
译器优化是一个很复杂的东衡拿西：首先它和你用的IR表示有关而且是强烈耦合，SSA IR基本还
好，有开源代码和文献记载，你想要的都能在网上挖到但这怎么体现你的水平是吧。你
要考虑编译器的性能，尽管编译器的后端优化基本上可以纳入到某种PEabstract interpretation的
范畴中。
要不然你可以通过编写插件的方式白嫖例如visual studio code这类软
件的强大编辑功能,如果你写的不是c compiler,你也可以尽量把语法设计得很像c,这样你又能进一步
白嫖其强大的intellisense code,当然仍然有不少人或者应该说团队达到了这一步,到这里,应该卷死
了99.99%的同行应该毫无问题。
H. 自己写编译器怎么写，我想为中国程序员做个编译C语言的编译器。
用C语言比较好，效率比较高。
用JAVA也可以，好调试。
我用过以上两种做过编译器，别的语言不好说。
做个编译器不难，一个人做也用不了太多时间。但相关的东西要做的话就花时间了。比如编辑环境，比如调试跟踪器。
祝成功！
I. 编译原理
编译原理是计算机专业的一门重要专业课，旨在介绍编译程序构造的一般原理和基本方法。内容包括语言和文法、词法分析、语法分析、语法制导翻译、中间代码生成、存储管理、代码优化和目标代码生成。 编译原理是计算机专业设置的一门重要的专业课程。编译原理课程是计算机相关专业学生的必修课程和高等学校培养计算机专业人才的基础及核心课程，同时也是计算机专业课程中最难及最挑战学习能力的课程之一。编译原理课程内容主要是原理性质，高度抽象[1]。
中文名
编译原理[1]
外文名
Compilers: Principles, Techniques, and Tools[1]
领域
计算机专业的一门重要专业课[1]
快速
导航
编译器
编译原理课程
编译技术的发展
编译的基本流程
编译过程概述
基本概念
编译原理即是对高级程序语言进行翻译的一门科学技术, 我们都知道计算机程序由程序语言编写而成, 在早期计算机程序语言发展较为缓慢, 因为计算机存储的数据和执行的程序都是由0、1代码组合而成的, 那么在早期程序员编写计算机程序时必须十分了解计算机的底层指令代码通过将这些微程序指令组合排列从而完成一个特定功能的程序, 这就对程序员的要求非常高了。人们一直在研究如何如何高效的开发计算机程序, 使编程的门槛降低。[2]
编译器
C语言编译器是一种现代化的设备, 其需要借助计算机编译程序, C语言编译器的设计是一项专业性比较强的工作, 设计人员需要考虑计算机程序繁琐的设计流程, 还要考虑计算机用户的需求。计算机的种类在不断增加, 所以, 在对C语言编译器进行设计时, 一定要增加其适用性。C语言具有较强的处理能力, 其属于结构化语言, 而且在计算机系统维护中应用比较多, C语言具有高效率的优点, 在其不同类型的计算机中应用比较多。[3]
C语言编译器前端设计
编译过程一般是在计算机系统中实现的, 是将源代码转化为计算机通用语言的过程。编译器中包含入口点的地址、名称以及机器代码。编译器是计算机程序中应用比较多的工具, 在对编译器进行前端设计时, 一定要充分考虑影响因素, 还要对词法、语法、语义进行分析。[3]
1 词法分析[3]
词法分析是编译器前端设计的基础阶段, 在这一阶段, 编译器会根据设定的语法规则, 对源程序进行标记, 在标记的过程中, 每一处记号都代表着一类单词, 在做记号的过程中, 主要有标识符、关键字、特殊符号等类型, 编译器中包含词法分析器、输入源程序、输出识别记号符, 利用这些功能可以将字号转化为熟悉的单词。[3]
2 语法分析[3]
语法分析是指利用设定的语法规则, 对记号中的结构进行标识, 这包括句子、短语等方式, 在标识的过程中, 可以形成特殊的结构语法树。语法分析对编译器功能的发挥有着重要影响, 在设计的过程中, 一定要保证标识的准确性。[3]
3 语义分析[3]
语义分析也需要借助语法规则, 在对语法单元的静态语义进行检查时, 要保证语法规则设定的准确性。在对词法或者语法进行转化时, 一定要保证语法结构设置的合法性。在对语法、词法进行检查时, 语法结构设定不合理, 则会出现编译错误的问题。前端设计对精确性要求比较好, 设计人员能够要做好校对工作, 这会影响到编译的准确性, 如果前端设计存在失误, 则会影响C语言编译的效果。[3]
J. 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