C语言词法分析器 源代码 风君版
c语言编写的词法分析程序
#include <stdio.h>#include <stdlib.h>#include <string.h>#include <ctype.h>#define SPACE 0x20 //空格键#define CHANGE 'c' //转义字符#define STRING 'S' //引号里的字符串#define BOUNDARY 'B' //界符#define OPERATION 'O' //运算符#define WORD 'I' //标识符#define KEY_WORD 'K' //关键字#define DIGIT 'n' //数字，包括小数#define DOTH 'd' //头文件，“.h”文件#define INT 't'#define VOID 'v'#define IF 'f'#define ELSE 'e'#define WHILE 'w'#define FOR 'r'#define MAIN 'm'#define PRINTF 'p'#define INCLUDE 'u'#define FLOAT 'l'#define KEYNUM 10#define BOUNDNUM 8#define OPERNUM 7#define V ALUENUM 100/************************************************************************/ /* data type */ /************************************************************************/ struct bianliang{int id;char name[20];int value;};struct changliang{int data;};KeyWord[KEYNUM][8]={"int","void","if","else","while","for","main","printf","include","float"} ;char Boundary[BOUNDNUM]={'"',';',',','(',')','#','{','}'};char Operation[OPERNUM]={'+','-','*','/','=','<','>'};charLogogram[KEYNUM]={INT,VOID,IF,ELSE,WHILE,FOR,MAIN,PRINTF,INCLUDE,FLOAT};char Value[V ALUENUM][8];int Value_n=0;int ErrorLine=0;int QuotationCount=0; //计算引号的数量int QuotationFlag=0; //引号数量为奇数时为1，偶数时为0char LastOpera=0; //用于判断"=="号存前一个"="号/************************************************************************//* function describe *//************************************************************************/int isKeyWord(char* s) //是关键字返回1，否则返回0{int i;for (i=0;i<KEYNUM;i++){if (strcmp(KeyWord[i],s)==0){return i+1;}}return 0;}int isBoundary(char ch) //是界符{int i;for (i=0;i<BOUNDNUM;i++){if (Boundary[i]==ch){return i+1;}}return 0;}int isOperation(char ch) //是运算符int i;for (i=0;i<OPERNUM;i++) {if (Operation[i]==ch){return i+1;}}return 0;}int isDigit(char *s) //是数字{int i,l=strlen(s);for (i=0;i<l;i++){if (!isdigit(s[i])){break;}}if (i>=l){return 1;}else{if ('.'==s[i]){i++;for (;i<l;i++){if (!isdigit(s[i])){break;}}}else{return 0;}if (i>=l)return 1;elsereturn 0;}}int isDotH(char *s) //是头文件{int i,l=strlen(s);for (i=0;i<l;i++){if (!isalpha(s[i])){break;}}if (i>=l){return 0;}else{if ('.'==s[i]){i++;if(s[i]=='h')return 1;elsereturn 0;}elsereturn 0;}}int isWord(char *s) //是标识符{int i=0,l=strlen(s);if (isalpha(s[i])){i++;for (;i<l;i++){if (!isalnum(s[i])){break;}}}if (i>=l){return 1;}elsereturn 0;}void isWhat(int *i,char *str,FILE *fileOutput,FILE *fileOutput2) //判断字符串，并把相应类型存入文件{int n;struct bianliang temp;struct changliang t;FILE *file=fopen("num.txt","ab");if(1!=*i){str[--(*i)]='\0';if(n=isKeyWord(str)){fputs(str,fileOutput);fputc('\t',fileOutput);fputc(KEY_WORD,fileOutput);fputc('\t',fileOutput);if(isKeyWord(str)>9)fputc(isKeyWord(str)+'a'-10,fileOutput);elsefputc(isKeyWord(str)+'0',fileOutput);fputc('\t',fileOutput);fputc(Logogram[n-1],fileOutput);fputc('\n',fileOutput);}else if(isWord(str)){fputs(str,fileOutput);fputc('\t',fileOutput);fputc(WORD,fileOutput);fputc('\t',fileOutput);for(n=0;n<Value_n;n++){if(0==strcmp(Value[n],str))break;}if(n==Value_n){n=++Value_n;strcpy(Value[n-1],str);temp.id=n-1;strcpy(,str);temp.value=0;fwrite(&temp,sizeof(struct bianliang),1,fileOutput2); fputc('0'+n,fileOutput);}else{fputc('0'+n+1,fileOutput);}fputc('\t',fileOutput);fputc('i',fileOutput);fputc('\n',fileOutput);}else if (isDotH(str)){fputs(str,fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc(DOTH,fileOutput);fputc('\n',fileOutput);}else if (isDigit(str)){fputs(str,fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc(DIGIT,fileOutput);fputc('\n',fileOutput);t.data=atoi(str);fwrite(&t,sizeof(struct changliang),1,file);}(*i)=0;}fclose(file);}void writeMessage(FILE *f){fputs("字符\t类型\t附加值\t缩写\n",f);}void error(){printf("%d line error!\n",ErrorLine);exit(1);}/************************************************************************/ /* main */ /************************************************************************/ void main(){FILE*fileInput;FILE*fileOutput;FILE*fileOutput2;char ch,qtemp;char str[20];int i;int flag=0;fileInput=fopen("1.cpp","r");fileOutput=fopen("object.txt","w");fileOutput2=fopen("variable.txt","w");writeMessage(fileOutput);if (NULL!=fileInput){i=0;do{ch=fgetc(fileInput);str[i++]=ch;if(isBoundary(ch)){if(1==isBoundary(ch)){QuotationCount++;if (0==QuotationCount%2){QuotationFlag=0;}elseQuotationFlag=1;}isWhat(&i,str,fileOutput,fileOutput2);fputc(ch,fileOutput);fputc('\t',fileOutput);fputc('B',fileOutput);fputc('\t',fileOutput);if(isBoundary(ch)>9)fputc(isBoundary(ch)+'a'-10,fileOutput); elsefputc(isBoundary(ch)+'0',fileOutput);fputc('\t',fileOutput);fputc(Boundary[isBoundary(ch)-1],fileOutput); fputc('\n',fileOutput);i=0;}else if(isOperation(ch)){if(0==QuotationCount%2){isWhat(&i,str,fileOutput,fileOutput2);if ('='==ch){qtemp=fgetc(fileInput);if ('='==qtemp){fputc('=',fileOutput);fputc('=',fileOutput);flag=1;}else{fputc('=',fileOutput);fseek(fileInput,-1,SEEK_CUR);flag=0;}}elsefputc(ch,fileOutput);fputc('\t',fileOutput);fputc(OPERA TION,fileOutput);fputc('\t',fileOutput);if(isOperation(ch)>9)fputc(isOperation(ch)+'a'-10,fileOutput);elsefputc(isOperation(ch)+'0',fileOutput);fputc('\t',fileOutput);if (flag){fputc('q',fileOutput);}elsefputc(Operation[isOperation(ch)-1],fileOutput); fputc('\n',fileOutput);i=0;}else{fputc(ch,fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('c',fileOutput);fputc('\n',fileOutput);i=0;}}else if('\n'==ch){isWhat(&i,str,fileOutput,fileOutput2); ErrorLine++;i=0;}else if(SPACE==ch||'\t'==ch){if(1<i)isWhat(&i,str,fileOutput,fileOutput2); elsei=0;}else if ('\\'==ch){if (1==QuotationFlag){if (1!=i){str[--i]='\0';fputs(str,fileOutput);fputc('\t',fileOutput);fputc(STRING,fileOutput);fputc('\n',fileOutput);i=0;}ch=fgetc(fileInput);if ('t'==ch){fputc('\\',fileOutput);fputc('t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc(CHANGE,fileOutput);fputc('\n',fileOutput);i=0;}else if('b'==ch){fputc('\\',fileOutput);fputc('b',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc(CHANGE,fileOutput);fputc('\n',fileOutput);}else if ('n'==ch){fputc('\\',fileOutput);fputc('b',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc('\t',fileOutput);fputc(CHANGE,fileOutput);fputc('\n',fileOutput);i=0;}}else error();}else if (1==QuotationFlag){continue;}else if (isalnum(ch)||ch=='.'){}else if (EOF!=ch){error();}}while(EOF!=ch);printf("词法分析完毕\n");fclose(fileInput);}fclose(fileOutput);fclose(fileOutput2);}/****************************************************/ /* 1.cpp 例子文件*/#include <stdio.h>{int i;int j;int m;m=1;for(i=0;i<5;i=i+1) {printf("\t",i);for(j=0;j<i;j=j+1) {printf("\b",i);}for(j=0;j<m;j=j+1) {printf("*",i);}printf("\n",i);m=m+2;}}。
编译原理----词法分析程序----C语言版
编译原理----词法分析程序----C语⾔版#include<stdio.h>#include<string.h>#include<stdlib.h>char KeyWord[20][100]={"begin","end","if","while","var","procedure","else","for","do","int","read","write"};char yunsuanfu[]="+-*/<>%=";char fenjiefu[]=",;(){}:";int main(){char test[]="var a=10;\nvar b,c;\nprocedure p; \n\tbegin\n\t\tc=a+b\n\tend\n";int len_yunsuanfu=strlen(yunsuanfu);int len_fenjiefu=strlen(fenjiefu);puts(test);int length=strlen(test),i,j,k;for(i=0;i<length;i++){if(test[i]==' '||test[i]=='\n'||test[i]=='\t')continue;int tag=0;for(j=0;j<len_fenjiefu;j++){if(fenjiefu [j]==test[i]){printf("分界符\t%c\n",test[i]);tag=1;break;}}if(tag==1)continue;tag=0;for(j=0;j<len_yunsuanfu;j++){if(yunsuanfu[j]==test[i]){printf("运算符\t%c\n",test[i]);tag=1;break;}}if(tag==1)continue;if(test[i]>='0'&&test[i]<='9'){printf("数字\t");while(test[i]>='0'&&test[i]<='9'){printf("%c",test[i]);i++;}printf("\n");continue;}char temp[100];j=0;while(test[i]>='0'&&test[i]<='9'||test[i]>='a'&&test[i]<='z'||test[i]>='A'&&test[i]<='Z'||test[i]=='_') {temp[j++]=test[i];i++;}i--;temp[j++]='\0';tag=0;for(j=0;j<20;j++){if(strcmp(temp,KeyWord[j])==0){tag=1;printf("关键字\t%s\n",temp);break;}}if(tag==0)printf("标识符\t%s\n",temp);}}。
编译原理词法分析和语法分析报告 代码(C语言版)
admit=0;
for(in=0;in<cal-1;in++){str[in]=str[in+1];}
str[in]='\0';
cal--;
r_find=r_find->next;
}//:入栈~
if(r_find->line_States==s_find->num&&r_find->rank_Letter==str[0]&&r_find->name=='r'){//:规约
词法分析
三、词法分析程序的算法思想：
算法的基本任务是从字符串表示的源程序中识别出具有独立意义的单词符号，其基本思想是根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。
3.1主程序示意图：
否
是
扫描子程序主要部分流程图
是是
否
字母
数字其他
运算符、符号
界符等符号
否
是
词法分析程序的C语言程序源代码：
//词法分析函数: void scan()
//数据传递:形参fp接收指向文本文件头的文件指针；
//全局变量buffer与line对应保存源文件字符及其行号，char_num保存字符总数。
void scan()
{
char ch;
int flag,j=0,i=-1;
while(!feof(fp1))
{
ch=fgetc(fp1);
flag=judge(ch);
struct Sign *next;
编译原理词法分析和语法分析报告+代码(C语言版)_2
词法分析一、实验目的设计、编制并调试一个词法分析程序，加深对词法分析原理的理解。
二、实验要求2.1 待分析的简单的词法（1）关键字：begin if then while do end所有的关键字都是小写。
（2）运算符和界符：= + - * / < <= <> > >= = ; ( ) #（3）其他单词是标识符（ID）和整型常数（SUM），通过以下正规式定义：ID = letter (letter | digit)*NUM = digit digit*（4）空格有空白、制表符和换行符组成。
空格一般用来分隔ID、SUM、运算符、界符和关键字，词法分析阶段通常被忽略。
2.2 各种单词符号对应的种别码：输入：所给文法的源程序字符串。
输出：二元组（syn,token或sum）构成的序列。
其中：syn为单词种别码；token为存放的单词自身字符串；sum为整型常数。
例如：对源程序begin x:=9: if x>9 then x:=2*x+1/3; end #的源文件，经过词法分析后输出如下序列：(1,begin)(10,x)(18,:=)(11,9)(26,;)(2,if)……三、词法分析程序的算法思想：算法的基本任务是从字符串表示的源程序中识别出具有独立意义的单词符号，其基本思想是根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。
3.1 主程序示意图：主程序示意图如图3-1所示。
其中初始包括以下两个方面：⑴关键字表的初值。
关键字作为特殊标识符处理，把它们预先安排在一张表格中（称为关键字表），当扫描程序识别出标识符时，查关键字表。
如能查到匹配的单词，则该单词为关键字，否则为一般标识符。
关键字表为一个字符串数组，其描述如下：Char *rwtab[6] = {“begin”, “if”, “then”, “while”, “do”, “end”,};图3-1（2）程序中需要用到的主要变量为syn,token和sum3.2 扫描子程序的算法思想：首先设置3个变量：①token用来存放构成单词符号的字符串；②sum用来整型单词；③syn用来存放单词符号的种别码。
编译原理词法分析和语法分析报告 代码(C语言版)[1]
![编译原理词法分析和语法分析报告 代码(C语言版)[1]](https://img.taocdn.com/s3/m/a1924436453610661ed9f4cc.png)
char ch='\0';
/*从字符缓冲区读取当前字符*/
int count=0;
/*词法分析结果缓冲区计数器*/
static char spelling[10]={""}; /*存放识别的字*/
static char line[81]={""}; /*一行字符缓冲区，最多 80 个字符*/
char *pline;
scaner(); main() {p=0;
printf("\n please input a string(end with '#'):/n"); do{
scanf("%c",&ch); prog[p++]=ch; }while(ch!='#'); p=0; do{ scaner(); switch(syn)
EO
19
B or(即布尔表达式中的 B∨ )
Plus
34
“+”
Times
36
Becomes
38
Op_and
39
Op_or
40
Op_not
41
Rop
42
Lparent
48
Rparent
49
Ident
56
Intconst
57
#define sy_if
0
#define sy_then 1
#define sy_else 2
case '*': syn=15; token[m++]=ch; break;
case '/': syn=16; token[m++]=ch; break;
词法分析器(C语言版)
#include <stdlib.h>
#include <assert.h>
#define LENGTH1 10//type reserved word size
FILE * fp=NULL;//outstream Pointer
FILE * fw=NULL;//instream pointer
if(character=='=')
returntofile(9,0,id,con);
else
{
retract(fp);
returntofile(8,0,id,con);
}
break;
case '>':
getNextChar(fp);
if(character=='=')
returntofile(11,0,id,con);
{
char s[3];
int i=num/10;
while(i>0)
{
char c=i+'0';
strcat(s,&c);
}
return s;
}
//将结果写入到文件并且输出到屏幕。
void returntofile(int num,int val,identifier *id,constnumber *con)
//存入常数表中，并返回它在常数表中的位置编号。
int constant(constnumber * con)
{
con->cont[con->len]=strtonumber();
con->len++;
词法分析器源代码
词法分析器源代码#include <iostream> #include <vector> #include <string> #include<fstream>/*单词种别码*/#define _CHAR 1 #define _INT 2#define _SHORT 3 #define _LONG 4 #define _SIGNED 5 #define _UNSIGNED 6 #define _FLOAT 7 #define _DOUBLE 8 #define _CONST 9 #define _VOID 10 #define _VOLATILE 11 #define _ENUM 12 #define _STRUCT 13 #define _UNION 14 #define _TYPEDEF 15 #define _AUTO 16 #define _EXTERN 17 #define_STATIC 18 #define _REGISTER 19 #define _IF 20#define _ELSE 21 #define _SWITCH 22 #define _CASE 23 #define_DEFAULT 24 #define _WHILE 25 #define _DO 26#define _FOR 27 #define _BREAK 28 #define _CONTINUE 29 #define _GOTO 30 #define _RETURN 31 #define _SIZEOF 32 #define _INCLUDE 33 #define_DEFINE 34 /*以上为关键字的种别码*/#define _ID 40 //标识符#define _NUM 50 //数#define _AS 51 //= #define _PLUS 52 //+ #define _SUB 53 //- #define _TIMES 54 // * #define _DIV 55 // / #define _LP 56 // ( #define _RP 57 // ) #define _LB1 58 // [ #define _RB1 59 // ] #define _LB2 60 //{ #define _RB2 61 // } #define _COM 62 // , #define _COL 63 // : #define_SEM 64 // #define _POINT 65 // . #define _LG 66 // > #define _LT 67 // < #define _ME 68 // >= #define _LE 69 // <= #define _EQ 70 // == #define _NE 71 // != #define _A 72 // >> #define _B 73 // >>= #define _C 74 // << #define _D 75 // <<= #define _E 76 // & #define _F 76 // && #define _G 77 // &= #define _H 78 // | #define _I 79 // || #define _J 80 // |= #define _K 81 // ~ #define _L 82 // ++ #define _M 83 // -- #define _N 84 // -> #define _O 85 // += #define _P 86 // -= #define _Q 87 // *=#define _R 88 // /= #define _S 89 // %=#define _T 90 // ^=#define _U 91 // %#define _V 92 // "#define _W 93 // '#define _X 94 // ?#define _EROOR -1 // 错误using namespace std;int ERROR_NUM=0; //记载词法编译错误个数bool isnum(string str) //判断是不是合法的数字{int y;int i;int j=0;int k=0;for(i=0;i<str.size();i++){if(!(str[i]<='9'&&str[i]>='0')){k++;if((k-j)>1){cout<<"数字串"<<str<<"出现词法错误～"<<endl;return false;} if(str[i]=='.') {j++;if(j>1) {cout<<"数字串"<<str<<"出现词法错误～"<<endl;return false;} }else if((str[i]=='E'||str[i]=='e')&&(str[i-1]<='9'&&str[i-1]>='0')&&((str[i+1]<='9'&&str[i+1]>='0')||(y=i+1)==str.size())) continue;else{cout<<"数字串"<<str<<"出现词法错误～"<<endl;return false;} }}return true;}/*该函数用来略过空格和换行符，找到有效字符的位置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 valuable(string str,int i) {while(true){if(str[i]!=' '&&str[i]!='\n')return i;i++;}}int isexp(string str,int i) {if(str[i]=='/'&&str[i+1]=='/'){while(str[i]!='\n'){i++;}}return i;}int iskey(string str) //判断是不是关键字{stringp[34]={"char","int","short","long","signed","unsigned","float","double", "const","void","volatile","enum","struct","union","typedef","auto"," extern","static","register","if","else","switch","case","default","while","do", "for","break","continue","goto","return","size of","#include","#define"};vector<string> ppp(p,p+34); int u;for(u=0;u<ppp.size();u++)if(!pare(ppp[u]))return u+1;return 0;}vector<pair<int,string> > scan(vector<string> vec)//本次程序的主要分析程序 {vector<pair<int,string> > temp;int i;for(i=0;i<vec.size();i++){if(vec[i].size()==1){if(vec[i]==">"){if(vec[i+1]=="="){string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_ME,jk);temp.push_back(pp);continue;}else if(vec[i+1]==">"&&vec[i+2]!="=") { string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_A,jk);temp.push_back(pp);continue; }else if(vec[i+1]==">"&&vec[i+2]=="="){ string jk=vec[i];jk.append(vec[++i],0,1);jk.append(vec[++i],0,1);pair<int,string> pp(_B,jk);temp.push_back(pp);continue;}else {pair<int,string> pp(_LG,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i]=="<") {if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_LE,jk);temp.push_back(pp);continue; }else if(vec[i+1]=="<"&&vec[i+2]!="=") { string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_C,jk);temp.push_back(pp);continue;}else if(vec[i+1]=="<"&&vec[i+2]=="=") { string jk=vec[i];jk.append(vec[++i],0,1);jk.append(vec[++i],0,1);pair<int,string> pp(_D,jk);temp.push_back(pp);continue; }else {pair<int,string> pp(_LT,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i]=="!") {if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_LE,jk);temp.push_back(pp);continue;}else {pair<int,string> pp(_NE,vec[i]);//标识符temp.push_back(pp);}else if(vec[i]=="=") {if(vec[i+1]=="="){string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_EQ,jk);temp.push_back(pp);continue; }else {pair<int,string> pp(_AS,vec[i]);//标识符temp.push_back(pp); }}else if(vec[i]=="&") {if(vec[i+1]=="&") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_F,jk);temp.push_back(pp);continue;}else if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_G,jk);temp.push_back(pp);continue;}else {pair<int,string> pp(_E,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i]=="|"){if(vec[i+1]=="|") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_I,jk);temp.push_back(pp);continue;}else if(vec[i+1]=="="){string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_J,jk);temp.push_back(pp);continue;}else {pair<int,string> pp(_H,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i]=="(") {{pair<int,string> pp(_LP,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i]==")"){{pair<int,string> pp(_RP,vec[i]);//标识符temp.push_back(pp); }}else if(vec[i]=="["){{pair<int,string> pp(_LB1,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="]") {{pair<int,string> pp(_RB1,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="~") {{pair<int,string> pp(_K,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]==",") {{pair<int,string> pp(_COM,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="{") {{pair<int,string> pp(_LB2,vec[i]);//标识符temp.push_back(pp);} }else if(vec[i]==":") {{pair<int,string> pp(_COL,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]==";") {{pair<int,string> pp(_SEM,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="}") {{pair<int,string> pp(_RB2,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="*") {if(vec[i+1]=="="){string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_Q,jk);temp.push_back(pp);continue; }else {pair<int,string> pp(_TIMES,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="/") {if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_R,jk);temp.push_back(pp);continue; }else if(vec[i+1]=="*") {i=i+4;while(i<vec.size()&&(vec[i-1]!="*"||vec[i]!="/"))i++; cont inue; }else {pair<int,string> pp(_DIV,vec[i]);//标识符temp.push_back(pp); }}else if(vec[i]=="%") {if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_S,jk);temp.push_back(pp);continue; }else {pair<int,string> pp(_U,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i][0]=='"') {pair<int,string> pp(_V,vec[i]);//标识符temp.push_back(pp);}else if(vec[i][0]=='\'') {pair<int,string> pp(_W,vec[i]);//标识符temp.push_back(pp);}else if(vec[i][0]=='?'){pair<int,string> pp(_X,vec[i]);//标识符temp.push_back(pp); }else if(vec[i]=="+") {if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_O,jk);temp.push_back(pp);continue; }else if(vec[i+1]=="+") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_L,jk);temp.push_back(pp);continue; }else if((vec[i-1]=="="||vec[i-1]=="(")&&isnum(vec[i+1])) {string jk=vec[i]; jk.append(vec[++i]);pair<int,string> pp(_NUM,jk);temp.push_back(pp);continue; }else{pair<int,string> pp(_PLUS,vec[i]);//标识符temp.push_back(pp); } }else if(vec[i]=="-"){if(vec[i+1]=="=") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_P,jk);temp.push_back(pp);continue;}else if(vec[i+1]=="-") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_M,jk);temp.push_back(pp);continue; }else if(vec[i+1]==">") {string jk=vec[i];jk.append(vec[++i],0,1);pair<int,string> pp(_N,jk);temp.push_back(pp);continue;} else if((vec[i-1]=="="||vec[i-1]=="(")&&isnum(vec[i+1])) { string jk=vec[i]; jk.append(vec[++i]);pair<int,string> pp(_NUM,jk);temp.push_back(pp);continue; }else {pair<int,string> pp(_SUB,vec[i]);//标识符temp.push_back(pp);}}else if(vec[i][0]<='9'&&vec[i][0]>='0'){pair<int,string> pp(_NUM,vec[i]);temp.push_back(pp);}else{pair<int,string> pp(_ID,vec[i]);//标识符temp.push_back(pp);}}else if((vec[i][0]<='9'&&vec[i][0]>='0')||vec[i][0]=='.'){if(!isnum(vec[i]))ERROR_NUM++;else if((vec[i+1][0]=='+'||vec[i+1][0]=='-')&&isnum(vec[i+2])) { string jk=vec[i];jk.append(vec[++i]);jk.append(vec[++i]);pair<int,string> pp(_NUM,jk);temp.push_back(pp);continue;}else{pair<int,string> pp(_NUM,vec[i]);temp.push_back(pp);}}else if(iskey(vec[i])){pair<int,string> pp(iskey(vec[i]),vec[i]);temp.push_back(pp);}else{pair<int,string> pp(_ID,vec[i]);temp.push_back(pp);}}return temp;}void OutFile(vector<pair<int,string> > v) {int i;for(i=0;i<v.size();i++)outfile<<"<"<<v[i].first<<" , \""<<v[i].second<<"\">"<<endl; return;}。
词法分析器源代码
1.实验目的及要求设计、编制并调试一个词法分析程序，加深对词法分析原理的理解。
2.实验要求一、词法分析程序的功能：二、输入：所给文法的源程序字符串。
三、输出：二元组（syn,token或sum）构成的序列。
四、其中：syn为单词种别码；五、token为存放的单词自身字符串；六、sum为整型常数。
各种单词符号对应的种别码单词符号种别码单词符号种别码begin 1 : 17if 2 := 18then 3 > 20while 4 <> 21do 5 <= 22end 6 < 23 letter(letter| digit)* 10 >= 24 digit digit * 11 = 25 * 13 ; 26/ 14 ( 27+ 15 ) 28- 16 # 03源代码#include<stdio.h>#include<string.h>#include<iostream.h>char prog[80],token[8];char ch;int syn,p,m=0,n,row,sum=0;char *rwtab[6]={"begin","if","then","while","do","end"};void scaner(){for(n=0;n<8;n++) token[n]=NULL;ch=prog[p++];while(ch==' '){ch=prog[p];p++;}if((ch>='a'&&ch<='z')||(ch>='A'&&ch<='Z')){m=0;while((ch>='0'&&ch<='9')||(ch>='a'&&ch<='z')||(ch>='A'&&ch<='Z')){token[m++]=ch;ch=prog[p++];}token[m++]='\0';p--;syn=10;for(n=0;n<6;n++)if(strcmp(token,rwtab[n])==0){syn=n+1;break;}}else if((ch>='0'&&ch<='9')){{sum=0;while((ch>='0'&&ch<='9')){sum=sum*10+ch-'0';ch=prog[p++];}}p--;syn=11;if(sum>32767)syn=-1;}else switch(ch){case'<':m=0;token[m++]=ch;ch=prog[p++];if(ch=='>'){syn=21;token[m++]=ch;}else if(ch=='='){syn=22;token[m++]=ch;}else{syn=23;p--;}break;case'>':m=0;token[m++]=ch;ch=prog[p++];if(ch=='='){syn=24;token[m++]=ch;}else{syn=20;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=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;case'\n':syn=-2;break;default: syn=-1;break;}}void main(){p=0;row=1;cout<<"请输入字符串:"<<endl;do{cin.get(ch);prog[p++]=ch;}while(ch!='#');p=0;do{scaner();switch(syn){case 11: cout<<"("<<syn<<","<<sum<<")"<<endl; break;case -1: cout<<"Error in row "<<row<<"!"<<endl; break;case -2: row=row++;break;default: cout<<"("<<syn<<","<<token<<")"<<endl;break;}}while (syn!=0);}4 结果验证给定源程序begin x:=12; if x>0 then x:=3-4*2+3/2; end#源程序（包括上式未有的while、do以及判断错误语句）：begin x<=$; while a<0 do b<..>9-x; end#5 心得体会通过此次实验，我更加深入的了解了词法构造，词法分析编制程序并调试，熟悉了构造词法分析程序的手工方式的相关原理，还有特别要注意种别码不能写错，必须一一对应，否则会很难检查出来。
《C语言词法分析器》开发文档及源代码
《C语言词法分析器》开发文档Powered By 萌萌的玉雪一、实验题目编制并调试C词法分析程序。
二、实验目的全面深入理解高级语言程序设计知识，掌握应用技巧，提高应用与分析能力。
三、主要函数四、设计1.主函数void main ( )2. 初始化函数void load ( )3. 保留字及标识符判断函数void char_search(char *word)4. 整数类型判断函数void inta_search(char *word)5. 浮点类型判断函数void intb_search(char *word)6. 字符串常量判断函数void cc_search(char *word)7. 字符常量判断函数void c_search(char *word)同4、5函数图8.主扫描函数void scan ( )五、关键代码#include <stdio.h>#include <string.h>#include <stdlib.h>char *key0[]={" ","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","_Complex","_Imaginary"," union","unsigned","void","volatile","while"};/*保留字表*/char *key1[]={" ","(",")","[","]","{","}",",",";","'"};/*分隔符表*/char *key2[]={" ","+","-","*","/","%","<",">","==",">=","<=","!=","!","&&","||","<<",">>","~","|","^","&","=","?:","->","++","--",".","+ =","-=","*=","/="};/*运算符表*/int xx0[35],xx1[10],xx2[31];int temp_key3=0,temp_c40=0,temp_c41=0,temp_c42=0,temp_c43=0; /******* 初始化函数*******/void load(){int mm;for (mm=0;mm<=34;mm++){xx0[mm]=0;}for (mm=0;mm<=9;mm++){xx1[mm]=0;}for (mm=0;mm<=30;mm++){xx2[mm]=0;}FILE *floading;if ((floading=fopen("key0.txt","w"))==NULL){printf("Error! Can't create file : key0.txt");return;}fclose (floading);/*建立保留字表文件：key0.txt*/if ((floading=fopen("key1.txt","w"))==NULL){printf("Error! Can't create file : key1.txt");return;}/*建立分隔符表文件：key1.txt*/if ((floading=fopen("key2.txt","w"))==NULL){printf("Error! Can't create file : key2.txt");return;}fclose(floading);/*建立运算符表文件：key2.txt*/if ((floading=fopen("key3.txt","w"))==NULL){printf("Error! Can't create file : key3.txt");return;}fclose (floading);/*建立标识符表文件：key3.txt*/if ((floading=fopen("c40.txt","w"))==NULL){printf("Error! Can't create file : c40.txt");return;}fclose (floading);/*建立整数类型常量表文件：c40.txt*/if ((floading=fopen("c41.txt","w"))==NULL){printf("Error! Can't create file : c41.txt");return;}fclose (floading);/*建立浮点类型常量表文件：c41.txt*/if ((floading=fopen("c42.txt","w"))==NULL){printf("Error! Can't create file : c42.txt");return;}fclose (floading);/*建立字符类型常量表文件：c42.txt*/if ((floading=fopen("c43.txt","w"))==NULL){printf("Error! Can't create file : c43.txt");return;}fclose (floading);/*建立字符串类型常量表文件：c43.txt*/if ((floading=fopen("defination.txt","w"))==NULL) {printf("Error! Can't create file : defination.txt");return;}fclose (floading);/*建立注释文件：defination.txt*/if ((floading=fopen("output.txt","w"))==NULL) {printf("Error! Can't create file : output.txt");return;}fclose (floading);/*建立内部码文件：output.txt*/if ((floading=fopen("temp_key1","w"))==NULL) {printf("Error! Can't create file : temp_key1");return;}fclose (floading);/*建立保留字临时表文件：temp_key1*/if ((floading=fopen("temp_key3","w"))==NULL) {printf("Error! Can't create file : temp_key3");return;}fclose (floading);/*建立标识符临时文件：temp_key3*/if ((floading=fopen("temp_c40","w"))==NULL){printf("Error! Can't create file : temp_c40");return;}fclose (floading);/*建立整数类型常量临时文件：temp_c40*/if ((floading=fopen("temp_c41","w"))==NULL){printf("Error! Can't create file : temp_c41");return;}fclose (floading);/*建立浮点类型常量临时文件：temp_c41*/if ((floading=fopen("temp_c42","w"))==NULL){printf("Error! Can't create file : temp_c42");return;}fclose (floading);/*建立字符类型常量临时文件：temp_c42*/if ((floading=fopen("temp_c43","w"))==NULL){printf("Error! Can't create file : temp_c43");return;}fclose (floading);/*建立字符串类型常量临时文件：temp_c43*/ }/******* 保留字及标识符判断函数*******/void char_search(char *word){int m,line=0,csi=0;int value=0;int value2=0;char c,cs[100];FILE *foutput,*finput;for (m=1;m<=34;m++){if (strcmp(word,key0[m])==0){value=1;break;}}if (value==1){if (xx0[m]==0){foutput=fopen("key0.txt","a");fprintf(foutput,"0\t%d\t\t%s\n",m,word);fclose(foutput);xx0[m]=1;}foutput=fopen("output.txt","a");fprintf(foutput,"0\t%d\t\t%s\n",m,word);fclose(foutput);}else{if (temp_key3==0){foutput=fopen("temp_key3","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_key3++;foutput=fopen("key3.txt","a");fprintf(foutput,"3\t1\t\t%s\n",word);fclose(foutput);}finput=fopen("temp_key3","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if ((strcmp(cs,word))==0){value2=1;break;}else{value2=0;c=fgetc(finput);}}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_key3","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_key3++;foutput=fopen("output.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",temp_key3,word);fclose(foutput);foutput=fopen("key3.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",temp_key3,word);fclose(foutput);}}}/******* 整数类型判断函数*******/void inta_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c40==0)foutput=fopen("temp_c40","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c40++;foutput=fopen("c40.txt","a");fprintf(foutput,"4\t0\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c40","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c40","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c40++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",temp_c40,word);fclose(foutput);foutput=fopen("c40.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",temp_c40,word);fclose(foutput);}/******* 浮点类型判断函数*******/void intb_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c41==0){foutput=fopen("temp_c41","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c41++;foutput=fopen("c41.txt","a");fprintf(foutput,"4\t1\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c41","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c41","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c41++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",temp_c41,word);fclose(foutput);foutput=fopen("c40.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",temp_c41,word);fclose(foutput);}}/******* 字符串常量判断函数*******/void cc_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c43==0){foutput=fopen("temp_c43","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c43++;foutput=fopen("c43.txt","a");fprintf(foutput,"4\t3\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c43","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c43","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c43++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",temp_c43,word);fclose(foutput);foutput=fopen("c43.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",temp_c43,word);fclose(foutput);}}/******* 字符常量判断函数*******/void c_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c42==0){foutput=fopen("temp_c42","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c42++;foutput=fopen("c42.txt","a");fprintf(foutput,"4\t2\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c42","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c42","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c42++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",temp_c42,word);fclose(foutput);foutput=fopen("c42.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",temp_c42,word);fclose(foutput);}}/******* 主扫描函数*******/void scan(){int count;char chin;FILE *fin;FILE *fout;char filename[50];char temp[100];char target[3]="'";printf("请输入文件名：");scanf("%s",filename);if ((fin=fopen(filename,"r"))==NULL){printf("Error! Can't open file : %s\n",filename);return;}chin=fgetc(fin);while (chin!=EOF){/*对文件包含、宏定义进行处理*/if (chin=='#'){while (chin!='>')chin=fgetc(fin);/*chin=fgetc(fin);*/}/*对空格符、水平制表符进行处理*/else if ((chin==' ')||(chin=='\t')){;}/*对回车符进行处理*/else if (chin=='\n'){;}/*对单引号内的字符常量进行处理*/else if (chin==target[0]){if (xx1[9]==0){fout=fopen("key1.txt","a");fprintf(fout,"1\t9\t\t%c\n",target[0]);fclose(fout);xx1[9]=1;}temp[0]=chin;chin=fgetc(fin);temp[1]=chin;chin=fgetc(fin);if (chin!=target[0]){temp[2]=chin;chin=fgetc(fin);temp[3]=chin;temp[4]='\0';}else{temp[2]=chin;temp[3]='\0';}c_search(temp);}/*对双引号内的字符串常量进行处理*/else if (chin=='"'){int i=0;temp[i++]='"';chin=fgetc(fin);while (chin!='"'){temp[i++]=chin;chin=fgetc(fin);}temp[i]='"';temp[i+1]='\0';cc_search(temp);}/*对保留字、标识符进行处理*/else if (((chin>='A')&&(chin<='Z'))||((chin>='a')&&(chin<='z'))||(chin=='_')){int i=0;while(((chin>='A')&&(chin<='Z'))||((chin>='a')&&(chin<='z'))||(chin=='_')||((chin>='0')&&(chin<='9'))) {temp[i++]=chin;chin=fgetc(fin);}temp[i]='\0';char_search(temp);if (chin!=EOF)fseek (fin,-1L,SEEK_CUR);}/*对整型、浮点型数据进行处理*/else if ((chin>='0')&&(chin<='9')){int dotcount=0;int i=0;while (((chin>='0')&&(chin<='9'))||(chin=='.')) {if (chin=='.')dotcount++;if (dotcount==2)break;temp[i++]=chin;chin=fgetc(fin);}temp[i]='\0';if (dotcount==1)intb_search(temp);elseinta_search(temp);if (chin!=EOF)fseek (fin,-1L,SEEK_CUR);}/*对注释进行处理*/else if (chin=='/'){chin=fgetc(fin);if (chin=='='){fout=fopen("output.txt","a");fprintf(fout,"2\t30\t\t/=\n");fclose(fout);}else if (chin!='*'){fout=fopen("output.txt","a");fprintf(fout,"2\t4\t\t/\n");fclose(fout);fseek(fin,-1L,SEEK_CUR);}else if (chin=='*'){count=0;chin=fgetc(fin);fout=fopen("defination.txt","a");fprintf(fout,"/*");while (count!=2){count=0;while (chin!='*'){fprintf(fout,"%c",chin);chin=fgetc(fin);}count++;fprintf(fout,"%c",chin);chin=fgetc(fin);if (chin=='/'){count++;fprintf(fout,"%c\n",chin);}else{fprintf(fout,"%c",chin);chin=fgetc(fin);}}}}/*对运算符、分隔符进行处理*/else{int time=0;int firstblood=0;temp[0]=chin;chin=fgetc(fin);if (chin!=EOF){temp[1]=chin;temp[2]='\0';for (time=1;time<=30;time++){if (strcmp(temp,key2[time])==0){firstblood=1;if (xx2[time]==0){fout=fopen("key2.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);xx2[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);break;}}if (firstblood!=1){fseek(fin,-1L,SEEK_CUR);temp[1]='\0';for (time=1;time<=9;time++){if (strcmp(temp,key1[time])==0){if (xx1[time]==0){fout=fopen("key1.txt","a");fprintf(fout,"1\t%d\t\t%s\n",time,temp);fclose(fout);xx1[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"1\t%d\t\t%s\n",time,temp);fclose(fout);break;}}for (time=1;time<=30;time++){if (strcmp(temp,key2[time])==0){if (xx2[time]==0){fout=fopen("key2.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);xx2[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);break;}}}}}chin=fgetc(fin);}fout=fopen("output.txt","a");fprintf(fout,"1\t6\t\t}\n");fclose(fout);}/******* Main函数*******/void main(){FILE *fread;char charin;char command='Q';printf("\n");printf("******************** C语言词法分析工具********************\n");printf("* *\n");printf("* *\n");printf("* 命令如下：*\n");printf("* 0 --> 查看保留字表文件*\n");printf("* 1 --> 查看分隔符表文件*\n");printf("* 2 --> 查看运算符表文件*\n");printf("* 3 --> 查看标识符表文件*\n");printf("* 4 --> 查看整数类型常量表*\n");printf("* 5 --> 查看浮点类型常量表*\n");printf("* 6 --> 查看字符类型常量表*\n");printf("* 7 --> 查看字符串类型常量表*\n");printf("* 8 --> 查看注释文件*\n");printf("* 9 --> 查看内部码文件*\n");printf("* -------------------------- *\n");printf("* Q --> 退出*\n");printf("***************************************************************\n");printf("\n");load();scan();printf("\n");printf("分析完成！\n");getchar();printf("\n");printf("请输入命令：");command=getchar();while ((command!='Q')&&(command!='q')){switch (command){case '0':{printf("*************************\n");printf("\n");fread=fopen("key0.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '1':{printf("*************************\n");printf("\n");fread=fopen("key1.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '2':{printf("*************************\n");printf("\n");fread=fopen("key2.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '3':{printf("*************************\n");printf("\n");fread=fopen("key3.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '4':{printf("*************************\n");printf("\n");fread=fopen("c40.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '5':{printf("*************************\n");printf("\n");fread=fopen("c41.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");21printf("请输入命令：");break;}case '6':{printf("*************************\n");printf("\n");fread=fopen("c42.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '7':{printf("*************************\n");printf("\n");fread=fopen("c43.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '8':{printf("*************************\n");printf("\n");fread=fopen("defination.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);22}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '9':{printf("*************************\n");printf("\n");fread=fopen("output.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}}command=getchar();}}23。
编译原理词法分析和语法分析报告+代码(C语言版)
词法分析一、实验目的设计、编制并调试一个词法分析程序，加深对词法分析原理的理解。
二、实验要求2.1 待分析的简单的词法（1）关键字：begin if then while do end所有的关键字都是小写。
（2）运算符和界符：= + - * / < <= <> > >= = ; ( ) #（3）其他单词是标识符（ID）和整型常数（SUM），通过以下正规式定义：ID = letter (letter | digit)*NUM = digit digit*（4）空格有空白、制表符和换行符组成。
空格一般用来分隔ID、SUM、运算符、界符和关键字，词法分析阶段通常被忽略。
2.2 各种单词符号对应的种别码：表2.1 各种单词符号对应的种别码单词符号种别码单词符号种别码bgin 1 ：17If 2 ：= 18Then 3 < 20wile 4 <> 21do 5 <= 22end 6 > 23lettet（letter|digit）* 10 >= 24 dight dight* 11 = 25 + 13 ；26—14 ( 27* 15 ) 28/ 16 # 02.3 词法分析程序的功能：输入：所给文法的源程序字符串。
输出：二元组（syn,token或sum）构成的序列。
其中：syn为单词种别码；token为存放的单词自身字符串；sum为整型常数。
例如：对源程序begin x:=9: if x>9 then x:=2*x+1/3; end #的源文件，经过词法分析后输出如下序列：(1,begin)(10,x)(18,:=)(11,9)(26,;)(2,if)……三、词法分析程序的算法思想：算法的基本任务是从字符串表示的源程序中识别出具有独立意义的单词符号，其基本思想是根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。
3.1 主程序示意图：主程序示意图如图3-1所示。
c语言的词法分析程序
myword->typenum =20; myword->word ="<"; return myword; break; case'!': m_getch(); if(ch=='=') { myword->typenum =40; myword->word ="!="; return myword; } retract(); myword->typenum =-1; myword->word ="ERROR"; return myword; break; case'\0': myword->typenum=100; myword->word="OVER"; return myword; break; default: myword->typenum=-1; myword->word="ERROR"; return myword; } }
break; case',':myword->typenum =34; myword->word =","; return myword; break; case':': if(input[p_input]=='=') { myword->typenum =18; myword->word =":="; return myword; } else myword->typenum =17; myword->word =":"; return myword; break; case';':myword->typenum =26; myword->word =";"; return myword; break; case'>': m_getch(); if(ch=='=') { myword->typenum =24; myword->word =">="; return myword; } retract(); myword->typenum =23; myword->word =">"; return myword; break; case'<': m_getch(); if(ch=='=') { myword->typenum =22; myword->word ="<="; return myword; } retract();
词法分析程序(c语言版)
源代码：1、词法分析/*cifa fenxi chengxu*/#include <stdio.h>#include <ctype.h>#include <alloc.h>#include <stdlib.h>#include <string.h>#define NULL 0FILE *fp;char cbuffer;char*key[8]={"if","else","for","while","do","return","break","continue"}; char *border[6]={",",";","{","}","(",")"};char *arithmetic[4]={"+","-","*","/"};char *relation[6]={"<","<=","=",">",">=","<>"};char *consts[20];char *label[20];int constnum=0,labelnum=0;int search(char searchchar[],int wordtype){int i=0;switch (wordtype) {case 1:for (i=0;i<=7;i++){if (strcmp(key[i],searchchar)==0)return(i+1);}case 2:{for (i=0;i<=5;i++){if (strcmp(border[i],searchchar)==0)return(i+1);} return(0);}case 3:{for (i=0;i<=3;i++){if (strcmp(arithmetic[i],searchchar)==0){return(i+1);}}return(0);}case 4:{for (i=0;i<=5;i++){if (strcmp(relation[i],searchchar)==0){return(i+1);}}return(0);}case 5:{for (i=0;i<=constnum;i++){if (strcmp(consts[i],searchchar)==0){return(i+1);}}consts[i-1]=(char *)malloc(sizeof(searchchar));strcpy(consts[i-1],searchchar);constnum++;return(i);}case 6:{for (i=0;i<=labelnum;i++){if (strcmp(label[i],searchchar)==0){return(i+1);}}label[i-1]=(char *)malloc(sizeof(searchchar));strcpy(label[i-1],searchchar);labelnum++;return(i);}}}char alphaprocess(char buffer){int atype;int i=-1;char alphatp[20];while ((isalpha(buffer))||(isdigit(buffer))) {alphatp[++i]=buffer;buffer=fgetc(fp);}alphatp[i+1]='\0';if (atype=search(alphatp,1))printf("%s (1,%d)\n",alphatp,atype-1);else{atype=search(alphatp,6);printf("%s (6,%d)\n",alphatp,atype-1);}return(buffer);}char digitprocess(char buffer){int i=-1;char digittp[20];int dtype;while ((isdigit(buffer))){digittp[++i]=buffer;buffer=fgetc(fp);}digittp[i+1]='\0';dtype=search(digittp,5);printf("%s (5,%d)\n",digittp,dtype-1);return(buffer);}char otherprocess(char buffer){int i=-1;char othertp[20];int otype,otypetp;othertp[0]=buffer;othertp[1]='\0';if (otype=search(othertp,3)){printf("%s (3,%d)\n",othertp,otype-1);buffer=fgetc(fp);goto out;}if (otype=search(othertp,4)){buffer=fgetc(fp);othertp[1]=buffer;othertp[2]='\0';if (otypetp=search(othertp,4)){printf("%s (4,%d)\n",othertp,otypetp-1);goto out;}elseothertp[1]='\0';printf("%s (4,%d)\n",othertp,otype-1);goto out;}if (buffer==':'){buffer=fgetc(fp);if (buffer=='=')printf(":= (2,2)\n");buffer=fgetc(fp);goto out;}else{if (otype=search(othertp,2)){printf("%s (2,%d)\n",othertp,otype-1);buffer=fgetc(fp);goto out;}}if ((buffer!='\n')&&(buffer!=' '))printf("%c error,not a word\n",buffer);buffer=fgetc(fp);out: return(buffer);}void main(){int i;for (i=0;i<=20;i++){label[i]=NULL;consts[i]=NULL;};if ((fp=fopen("c:\\example.c","r"))==NULL)printf("error");else{cbuffer = fgetc(fp);while (cbuffer!=EOF){if (isalpha(cbuffer))cbuffer=alphaprocess(cbuffer);else if (isdigit(cbuffer))cbuffer=digitprocess(cbuffer);else cbuffer=otherprocess(cbuffer);}printf("over\n");getchar();}}2、递归向下分析#include <stdio.h>#include<dos.h>#include<stdlib.h>#include<string.h>char a[50] ,b[50],d[200],e[10];char ch;int n1,i1=0,flag=1,n=5;int E();int E1();int T();int G();int S();int F();void input();void input1();void output();void main() /*递归分析*/{int f,p,j=0;char x;d[0]='E';d[1]='=';d[2]='>';d[3]='T';d[4]='G';d[5]='#';printf("请输入字符串(长度<50,以#号结束）\n");do{scanf("%c",&ch);a[j]=ch;j++;}while(ch!='#');n1=j;ch=b[0]=a[0];printf("文法\t分析串\t\t分析字符\t剩余串\n");f=E1();if (f==0) return;if (ch=='#'){ printf("accept\n");p=0;x=d[p];while(x!='#') {printf("%c",x);p=p+1;x=d[p]; /*输出推导式*/}}else {printf("error\n");printf("回车返回\n");getchar();getchar();return;}printf("\n");printf("回车返回\n");getchar();getchar();}int E1(){ int f,t;printf("E TG\t");flag=1;input();input1();f=T();if (f==0) return(0);t=G();if (t==0) return(0);else return(1);}int E(){ int f,t;printf("E→TG\t");e[0]='E';e[1]='=';e[2]='>';e[3]='T';e[4]='G';e[5]='#';output();flag=1;input();input1();f=T();if (f==0) return(0);t=G();if (t==0) return(0);else return(1);}int T(){ int f,t;printf("T→FS\t");e[0]='T';e[1]='=';e[2]='>';e[3]='F';e[4]='S';e[5]='#';output();flag=1;input();input1();f=F();if (f==0) return(0);t=S();if (t==0) return(0);else return(1);}int G(){ int f;if(ch=='+') {b[i1]=ch;printf("G→+TG\t");e[0]='G';e[1]='=';e[2]='>';e[3]='+';e[4]='T';e[5]='G';e[6]='#';output();flag=0;input();input1();ch=a[++i1];f=T();if (f==0) return(0);G();return(1);}printf("G→^\t");e[0]='G';e[1]='=';e[2]='>';e[3]='^';e[4]='#';output();flag=1;input();input1();return(1);}int S(){int f,t;if(ch=='*') {b[i1]=ch;printf("S→*FS\t");e[0]='S';e[1]='=';e[2]='>';e[3]='*';e[4]='F';e[5]='S';e[6]='#';output();flag=0;input();input1();ch=a[++i1];f=F();if (f==0) return(0);t=S();if (t==0) return(0);else return(1);}printf("S→^\t");e[0]='S';e[1]='=';e[2]='>';e[3]='^';e[4]='#';output();flag=1;a[i1]=ch;input();input1();return(1);}int F(){ int f;if(ch=='(') {b[i1]=ch;printf("F→(E)\t");e[0]='F';e[1]='=';e[2]='>';e[3]='(';e[4]='E';e[5]=')';e[6]='#';output();flag=0;input();input1();ch=a[++i1];f=E();if (f==0) return(0);if(ch==')') {b[i1]=ch;printf("F→(E)\t");flag=0;input();input1();ch=a[++i1];}else {printf("error\n");return(0);}}else if(ch=='i') {b[i1]=ch;printf("F→i\t");e[0]='F';e[1]='=';e[2]='>';e[3]='i';e[4]='#';output();flag=0;input();input1();ch=a[++i1];}else {printf("error\n");return(0);}return(1);}void input(){int j=0;for (;j<=i1-flag;j++)printf("%c",b[j]); /*输出分析串*/printf("\t\t");printf("%c\t\t",ch); /*输出分析字符*/ }void input1(){int j;for (j=i1+1-flag;j<n1;j++)printf("%c",a[j]); /*输出剩余字符*/ printf("\n");void output(){ /*推导式计算*/ int m,k,j,q;int i=0;m=0;k=0;q=0;i=n;d[n]='=';d[n+1]='>';d[n+2]='#';n=n+2;i=n;i=i-2;while(d[i]!='>'&&i!=0) i=i-1;i=i+1;while(d[i]!=e[0]) i=i+1;q=i;m=q;k=q;while(d[m]!='>') m=m-1;m=m+1;while(m!=q) {d[n]=d[m];m=m+1;n=n+1;}d[n]='#';for(j=3;e[j]!='#';j++){d[n]=e[j];n=n+1;}k=k+1;while(d[k]!='=') {d[n]=d[k];n=n+1;k=k+1;}d[n]='#';}3、LL（1）/*LL(1)分析法源程序，只能在VC++中运行 */#include<stdio.h>#include<stdlib.h>#include<string.h>#include<dos.h>char A[20];/*分析栈*/char B[20];/*剩余串*/char v1[20]={'i','+','*','(',')','#'};/*终结符 */char v2[20]={'E','G','T','S','F'};/*非终结符 */int j=0,b=0,top=0,l;/*L为输入串长度 */typedef struct type/*产生式类型定义 */ {char origin;/*大写字符 */char array[5];/*产生式右边字符 */int length;/*字符个数 */}type;type e,t,g,g1,s,s1,f,f1;/*结构体变量 */ type C[10][10];/*预测分析表 */void print()/*输出分析栈 */{int a;/*指针*/for(a=0;a<=top+1;a++)printf("%c",A[a]);printf("\t\t");}/*print*/void print1()/*输出剩余串*/{int j;for(j=0;j<b;j++)/*输出对齐符*/printf(" ");for(j=b;j<=l;j++)printf("%c",B[j]);printf("\t\t\t");}/*print1*/void main(){int m,n,k=0,flag=0,finish=0;char ch,x;type cha;/*用来接受C[m][n]*//*把文法产生式赋值结构体*/e.origin='E';strcpy(e.array,"TG");e.length=2;t.origin='T';strcpy(t.array,"FS");t.length=2;g.origin='G';strcpy(g.array,"+TG");g.length=3;g1.origin='G';g1.array[0]='^';g1.length=1;s.origin='S';strcpy(s.array,"*FS");s.length=3;s1.origin='S';s1.array[0]='^';s1.length=1;f.origin='F';strcpy(f.array,"(E)");f.length=3;f1.origin='F';f1.array[0]='i';f1.length=1;for(m=0;m<=4;m++)/*初始化分析表*/for(n=0;n<=5;n++)C[m][n].origin='N';/*全部赋为空*//*填充分析表*/C[0][0]=e;C[0][3]=e;C[1][1]=g;C[1][4]=g1;C[1][5]=g1;C[2][0]=t;C[2][3]=t;C[3][1]=s1;C[3][2]=s;C[3][4]=C[3][5]=s1;C[4][0]=f1;C[4][3]=f;printf("提示:本程序只能对由'i','+','*','(',')'构成的以'#'结束的字符串进行分析,\n");printf("请输入要分析的字符串:");do/*读入分析串*/{scanf("%c",&ch);if ((ch!='i') &&(ch!='+')&&(ch!='*')&&(ch!='(')&&(ch!=')')&&(ch!='#')){printf("输入串中有非法字符\n");exit(1);}B[j]=ch;j++;}while(ch!='#');l=j;/*分析串长度*/ch=B[0];/*当前分析字符*/A[top]='#'; A[++top]='E';/*'#','E'进栈*/printf("步骤\t\t分析栈 \t\t剩余字符 \t\t所用产生式 \n"); do{x=A[top--];/*x为当前栈顶字符*/printf("%d",k++);printf("\t\t");for(j=0;j<=5;j++)/*判断是否为终结符*/if(x==v1[j]){flag=1;break;}if(flag==1)/*如果是终结符*/{if(x=='#'){finish=1;/*结束标记*/printf("acc!\n");/*接受 */getchar();getchar();exit(1);}/*if*/if(x==ch){print();print1();printf("%c匹配\n",ch);ch=B[++b];/*下一个输入字符*/flag=0;/*恢复标记*/}/*if*/else/*出错处理*/{print();print1();printf("%c出错\n",ch);/*输出出错终结符*/exit(1);}/*else*/}/*if*/else/*非终结符处理*/{for(j=0;j<=4;j++)if(x==v2[j]){m=j;/*行号*/break;}for(j=0;j<=5;j++)if(ch==v1[j]){n=j;/*列号*/break;}cha=C[m][n];if(cha.origin!='N')/*判断是否为空*/{print();print1();printf("%c->",cha.origin);/*输出产生式*/for(j=0;j<cha.length;j++)printf("%c",cha.array[j]);printf("\n");for(j=(cha.length-1);j=0;j--)/*产生式逆序入栈*/A[++top]=cha.array[j];if(A[top]=='^')/*为空则不进栈*/top--;}/*if*/else/*出错处理*/{print();print1();printf("%c出错\n",x);/*输出出错非终结符*/exit(1);}/*else*/}/*else*/}while(finish==0);}/*main*/4、LL（2）/*LL(1)分析法源程序，只能在VC++中运行 */#include<stdio.h>#include<stdlib.h>#include<string.h>#include<dos.h>char A[20];/*分析栈*/char B[20];/*剩余串*/char v1[20]={'i','+','*','(',')','#'};/*终结符 */ char v2[20]={'E','G','T','S','F'};/*非终结符 */int j=0,b=0,top=0,l;/*L为输入串长度 */typedef struct type/*产生式类型定义 */{char origin;/*大写字符 */char array[5];/*产生式右边字符 */int length;/*字符个数 */}type;type e,t,g,g1,s,s1,f,f1;/*结构体变量 */type C[10][10];/*预测分析表 */void print()/*输出分析栈 */{int a;/*指针*/for(a=0;a<=top;a++)printf("%c",A[a]);printf("\t\t");}/*print*/void print1()/*输出剩余串*/{int j;for(j=0;j<b;j++)/*输出对齐符*/printf(" ");for(j=b;j<=l;j++)printf("%c",B[j]);printf("\t\t\t");}/*print1*/void main(){int m,n,k=0,flag=0;char ch,x;type cha;/*用来接受C[m][n]*//*把文法产生式赋值结构体*/e.origin='E';strcpy(e.array,"TG");e.length=2;t.origin='T';strcpy(t.array,"FS");t.length=2;g.origin='G';strcpy(g.array,"+TG");g.length=3;g1.origin='G';g1.array[0]='^';g1.length=1;s.origin='S';strcpy(s.array,"*FS");s.length=3;s1.origin='S';s1.array[0]='^';s1.length=1;f.origin='F';strcpy(f.array,"(E)");f.length=3;f1.origin='F';f1.array[0]='i';f1.length=1;for(m=0;m<=4;m++)/*初始化分析表*/for(n=0;n<=5;n++)C[m][n].origin='N';/*全部赋为空*/ /*填充分析表*/C[0][0]=e;C[0][3]=e;C[1][1]=g;C[1][4]=g1;C[1][5]=g1;C[2][0]=t;C[2][3]=t;C[3][1]=s1;C[3][2]=s;C[3][4]=C[3][5]=s1;C[4][0]=f1;C[4][3]=f;printf("提示:本程序只能对由'i','+','*','(',')'构成的以'#'结束的字符串进行分析,\n");printf("请输入要分析的字符串:");do/*读入分析串*/{scanf("%c",&ch);if ((ch!='i') &&(ch!='+')&&(ch!='*')&&(ch!='(')&&(ch!=')')&&(ch!='#')){printf("输入串中有非法字符\n");exit(1);}B[j]=ch;j++;}while(ch!='#');l=j;/*分析串长度*/ch=B[0];/*当前分析字符*/A[top]='#';A[++top]='E';/*'#','E'进栈*/x=A[top];/*x为当前栈顶字符*/printf("步骤\t\t分析栈 \t\t剩余字符 \t\t所用产生式 \n");loop: printf("%d",k++);printf("\t\t");for(j=0;j<=5;j++)/*判断是否为终结符*/if(x==v1[j]) flag=1;if(flag==1)/*如果是终结符*/{if(x=='#'){printf("acc!\n");/*接受 */getchar();getchar();exit(1);}/*if*/if(x==ch){print();print1();printf("%c匹配\n",ch);top--;/*栈顶出栈*/ch=B[++b];/*下一个输入字符*/x=A[top];flag=0;/*恢复标记*/goto loop;}/*if*/else/*出错处理*/{print();print1();printf("%c出错\n",ch);/*输出出错终结符*/exit(0);}/*else*/}/*if*/else/*非终结符处理*/{for(j=0;j<=4;j++)if(x==v2[j])m=j;/*行号*/for(j=0;j<=5;j++)if(ch==v1[j])n=j;/*列号*/cha=C[m][n];if(cha.origin!='N')/*判断是否为空*/{print();print1();printf("%c-",cha.origin);/*输出产生式*/for(j=0;j<cha.length;j++)printf("%c",cha.array[j]);printf("\n");top--;for(j=(cha.length-1);j=0;j--)/*产生式逆序入栈*/A[++top]=cha.array[j];if(A[top]=='^')/*为空则不进栈*/top--;x=A[top];goto loop;}/*if*/else/*出错处理*/{print();print1();printf("%c出错\n",x);/*输出出错非终结符*/exit(0);}/*else*/}/*else*/}/*main*/5、逆波兰式include<stdio.h>#include<math.h>#define max 100char ex[max]; /*存储后缀表达式*/void trans(){ /*将算术表达式转化为后缀表达式*/char str[max]; /*存储原算术表达式*/char stack[max]; /*作为栈使用*/char ch;int sum,i,j,t,top=0;printf("*****************************************\n");printf("*输入一个求值的表达式，以#结束。
简单的C语言编译器--词法分析器
简单的C语⾔编译器--词法分析器1. 定义词法单元Tag ⾸先要将可能出现的词进⾏分类，可以有不同的分类⽅式。
如多符⼀类：将所有逗号、分号、括号等都归为⼀类，或者⼀符⼀类，将⼀个符号归为⼀类。
我这⾥采⽤的是⼀符⼀类的⽅式。
C代码如下：#ifndef TAG_H#define TAG_Hnamespace Tag {//保留字const intINT = 1, BOOL = 2, MAIN = 3, IF = 4,ELSE = 5, FOR = 6, WHILE = 7, FALSE = 8,BREAK = 9, RETURN = 10, TRUE = 11 ;//运算符const intNOT = 20, NE = 21, AUTOMINUS =22, MINUS = 23,AUTOADD = 24, ADD = 25, OR = 26,AND = 27, MUTIPLY = 28, DIVIDE = 29, MOD = 30,EQ = 31, ASSIN = 32, GE = 33, GT = 34,LE = 35, LS = 36;//分界符const intCOMMA = 40, SEMICOLON = 41, LLBRACKET = 42,RLBRACKET = 43, LMBRACKET = 44, RMBRACKET = 45,LGBRACKET = 46, RGBRACKET = 47;//整数常数const int NUM = 50;//标识符const int ID = 60;//错误const int ERROR = 404;//空const int EMPTY = 70;}#endif2. 具体步骤⼀个⼀个字符地扫描测试代码，忽略空⽩字符，遇到回车时，记录⾏数加1要进⾏区分标识符(即普通变量名字)和保留字因为将标识符和常数都guiwe各⾃归为⼀类，所以要有算法能够识别出⼀整个常数和完整的标识符加⼊适当的⾮法词检测3. 设计词法分析类 设计⼀个词法分析器，当然要包括如何存储⼀个词法单元，如何扫描(scan)测试代码等，直接上代码：myLexer.h#ifndef MYLEXER_H#define MYLEXER_H#include <fstream>#include <string>#include <unordered_map>#include "tag.h"/** 主要是定义基本的词法单元类，* 声明了词法分析类*///存储词法单元class Word {public:Word() = default;Word(std::string s, int t) : lexeme(s), tag(t) {};std::string getLexeme() { return lexeme; };int getTag() { return tag; }void setTag(int t) { tag = t; }void setLexeme(std::string s) { lexeme = s; }private:std::string lexeme;int tag;};//词法分析器类class Lexer {public:Lexer();void reserve(Word w);bool readnext(char c, std::ifstream &in);Word scan(std::ifstream &in);int getLine() { return line; }private:char peek;std::unordered_map<std::string, Word> words;int line;};#endifmyLexer.cpp#include <iostream>#include <cctype>#include <sstream>#include "myLexer.h"void Lexer::reserve(Word w) {words.insert({w.getLexeme(), w});}Lexer::Lexer() {//存⼊保留字，为了区分标识符reserve( Word("int", Tag::INT) );reserve( Word("bool", Tag::BOOL) );reserve( Word("main", Tag::MAIN) );reserve( Word("if", Tag::IF) );reserve( Word("else", Tag::ELSE) );reserve( Word("for", Tag::FOR) );reserve( Word("while", Tag::WHILE) );reserve( Word("break", Tag::BREAK) );reserve( Word("return", Tag::RETURN) );reserve( Word("true", Tag::TRUE) );reserve( Word("false", Tag::FALSE) );peek = ' ';line = 1;}//⽅便处理像>=,++等这些两个字符连在⼀起的运算符 bool Lexer::readnext(char c, std::ifstream &in) {in >> peek;if( peek != c)return false;peek = ' ';return true;}Word Lexer::scan(std::ifstream &in) {//跳过空⽩符while(!in.eof()) {if(peek == ' ' || peek == '\t') {in >> peek;continue;}else if(peek == '\n')++line;elsebreak;in >> peek;}//处理分界符、运算符等switch(peek) {case '!':if(readnext('=', in))return Word("!=", Tag::NE);elsereturn Word("!", Tag::NOT);case '-':if(readnext('-', in))return Word("--", Tag::AUTOMINUS);elsereturn Word("-", Tag::MINUS);case '+':if(readnext('+', in))return Word("++", Tag::AUTOADD);elsereturn Word("+", Tag::ADD);case '|':if(readnext('|', in))return Word("||", Tag::OR);elsereturn Word("error", Tag::ERROR);case '&':if(readnext('&', in))return Word("&&", Tag::AND);elsereturn Word("error", Tag::ERROR);case '*':in >> peek;return Word("*", Tag::MUTIPLY);case '/':in >> peek;return Word("/", Tag::DIVIDE);case '%':in >> peek;return Word("%", Tag::MOD);case '=':if(readnext('=', in))return Word("==", Tag::EQ);elsereturn Word("=", Tag::ASSIN);case '>':if(readnext('=', in))return Word(">=", Tag::GE);elsereturn Word(">", Tag::GT);case '<':if(readnext('=', in))return Word("<=", Tag::LE);elsereturn Word("<", Tag::LS);case ',':in >> peek;return Word(",", Tag::COMMA);case ';':in >> peek;return Word(";", Tag::SEMICOLON);case '(':in >> peek;return Word("(", Tag::LLBRACKET);case ')':in >> peek;return Word(")", Tag::RLBRACKET);case '[':in >> peek;return Word("[", Tag::LMBRACKET);case ']':in >> peek;return Word("]", Tag::RMBRACKET);case '{':in >> peek;return Word("{", Tag::LGBRACKET);case '}':in >> peek;return Word("}", Tag::RGBRACKET);}//处理常数if(isdigit(peek)) {int v = 0;do {v = 10*v + peek - 48;in >> peek;} while(isdigit(peek));if(peek != '.')return Word(std::to_string(v), Tag::NUM);}//处理标识符if(isalpha(peek)) {std::ostringstream b;do {b << peek;in >> peek;} while(isalnum(peek) || peek == '_');std::string tmp = b.str();//判断是否为保留字if(words.find(tmp) != words.end())return words[tmp];elsereturn Word(tmp, Tag::ID);}if(peek != ' ' && peek != '\t' && peek != '\n')return Word("error", Tag::ERROR);return Word("empty", Tag::EMPTY);} 设计完成后，⾃⼰写⼀个Main函数，在while循环中调⽤scan函数，每次打印出Word内容，就能够得到。
编译原理词法分析和语法分析报告+代码(C语言版)
编译原理词法分析和语法分析报告+代码(C语言版)-CAL-FENGHAI.-(YICAI)-Company One1信息工程学院实验报告（2010 ~2011 学年度第一学期）姓名：柳冠天学号：2081908318班级：083词法分析一、实验目的设计、编制并调试一个词法分析程序，加深对词法分析原理的理解。
二、实验要求2.1 待分析的简单的词法（1）关键字：begin if then while do end所有的关键字都是小写。
（2）运算符和界符： = + - * / < <= <> > >= = ; ( ) #（3）其他单词是标识符（ID）和整型常数（SUM），通过以下正规式定义：ID = letter (letter | digit)*NUM = digit digit*（4）空格有空白、制表符和换行符组成。
空格一般用来分隔ID、SUM、运算符、界符和关键字，词法分析阶段通常被忽略。
2.2 各种单词符号对应的种别码：表2.1 各种单词符号对应的种别码2.3 词法分析程序的功能：输入：所给文法的源程序字符串。
输出：二元组（syn,token或sum）构成的序列。
其中：syn为单词种别码；token为存放的单词自身字符串；sum为整型常数。
例如：对源程序begin x:=9: if x>9 then x:=2*x+1/3; end #的源文件，经过词法分析后输出如下序列：(1,begin)(10,x)(18,:=)(11,9)(26,;)(2,if)……三、词法分析程序的算法思想：算法的基本任务是从字符串表示的源程序中识别出具有独立意义的单词符号，其基本思想是根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。
3.1 主程序示意图：主程序示意图如图3-1所示。
其中初始包括以下两个方面：⑴关键字表的初值。
关键字作为特殊标识符处理，把它们预先安排在一张表格中（称为关键字表），当扫描程序识别出标识符时，查关键字表。
词法分析程序源代码
词法分析程序源代码#include<stdio.h>#include<string.h>#include<stdlib.h>char TOken[10];//分开进⾏⽐较char ch;char r1[]={"auto"};char r2[]={"break"};char r3[]={"case"};char r4[]={"char"};char r5[]={"const"};char r6[]={"continue"};char r7[]={"default"};char r8[]={"do"};char r9[]={"double"};char r10[]={"else"};char r11[]={"enum"};char r12[]={"extern"};char r13[]={"float"};char r14[]={"for"};char r15[]={"goto"};char r16[]={"if"};char r17[]={"int"};char r18[]={"long"};char r19[]={"register"};char r20[]={"return"};char r21[]={"short"};char r22[]={"signed"};char r23[]={"sizeof"};char r24[]={"static"};char r25[]={"struct"};char r26[]={"switch"};char r27[]={"typedef"};char r28[]={"union"};char r29[]={"unsigned"};char r30[]={"void"};char r31[]={"volatile"};char r32[]={"while"};char r33[]={"end"};char r34[]={"include"};char r35[]={"stdio"};char r36[]={"string"};char r37[]={"main"};char r38[]={"stdlib"};//这是我定义的char A[10000];//输⼊的所有值int syn,row;int n,m,p,sum,j;static int i = 0;void scaner();int main(){row = 0 ;p = 0 ;printf("Please input string:(end of '@')\n");do{scanf("%c",&ch);A[p]=ch;p++;}//输⼊值到数组A【】中，以@结束while(ch!='@');do{scaner();//进⼊函数进⾏判定switch(syn){case40: printf("(%d,%d)\n",syn,sum); break;//如果是40，那么就是数字case0: printf("(%d,%c)\n",syn,TOken[0]);break;//如果是0，那么是@ 结束case -2: row=row++;break;default: printf("(%d,%s)\n",syn,TOken);break;//否则，就是变量名、关键词}}while (syn!=0);}void scaner(){/*共分为三⼤块，分别是标⽰符、数字、符号，对应下⾯的 if else if 和 else */for(n=0;n<7;n++)TOken[n]=0;//每次循环完就清零ch=A[i];while(ch==''||ch=='\n')//如果字符是空格或者回车，跳过ch=A[i];}if((ch>='a'&&ch<='z')||(ch>='A'&&ch<='Z')) //可能是标⽰符或者变量名{m=0;while((ch>='0'&&ch<='9')||(ch>='a'&&ch<='z')||(ch>='A'&&ch<='Z'))//找到⼀个变量名或者关键字，直到遇到空格为⽌ {TOken[m]=ch;m++;i++;ch=A[i];}TOken[m]='\0';//将识别出来的字符和已定义的标⽰符作⽐较， //因为定义的begin为1，if为2......if(strcmp(TOken,r1)==0){syn=1;}else if(strcmp(TOken,r2)==0){syn=2; }else if(strcmp(TOken,r3)==0){syn=3;}else if(strcmp(TOken,r4)==0){syn=4;}else if(strcmp(TOken,r5)==0){syn=5;}else if(strcmp(TOken,r6)==0){syn=6;}else if(strcmp(TOken,r7)==0){syn=7;}else if(strcmp(r8,TOken)==0){syn=8;}else if(strcmp(r9,TOken)==0){syn=9;}else if(strcmp(r10,TOken)==0){syn=10;}else if(strcmp(r11,TOken)==0){syn=11;}else if(strcmp(r12,TOken)==0){syn=12;}else if(strcmp(r13,TOken)==0){syn=13;}else if(strcmp(r14,TOken)==0){syn=14;}else if(strcmp(r15,TOken)==0){syn=15;}else if(strcmp(r16,TOken)==0){syn=16;}else if(strcmp(r17,TOken)==0){syn=17;}else if(strcmp(r18,TOken)==0){syn=18;}else if(strcmp(r19,TOken)==0){syn=19;}else if(strcmp(r20,TOken)==0){syn=20;}else if(strcmp(r21,TOken)==0){syn=21;}else if(strcmp(r22,TOken)==0){syn=22;}else if(strcmp(r23,TOken)==0){syn=23;}else if(strcmp(r24,TOken)==0){syn=24;}else if(strcmp(r25,TOken)==0){syn=25;}else if(strcmp(r26,TOken)==0){syn=26;}else if(strcmp(r27,TOken)==0){syn=27;}else if(strcmp(r28,TOken)==0){syn=28;}else if(strcmp(r29,TOken)==0){syn=29;}else if(strcmp(r30,TOken)==0){syn=30;}else if(strcmp(r31,TOken)==0){syn=31;}else if(strcmp(r32,TOken)==0){syn=32;}else if(strcmp(r33,TOken)==0){syn=33;}else if(strcmp(r34,TOken)==0){syn=34;}else if(strcmp(r35,TOken)==0){syn=35;}else if(strcmp(r36,TOken)==0){syn=36;}else if(strcmp(r37,TOken)==0){syn=37;}else if(strcmp(r38,TOken)==0){syn=38;}else{syn=100;} //变量名}else if((ch>='0'&&ch<='9')) //数字{sum=0;while((ch>='0'&&ch<='9')){sum=sum*10+ch-'0';//显⽰其数字sumi++;ch=A[i];}syn=40;}else switch(ch) //其他字符{case'<':m=0;TOken[m]=ch;m++;i++;ch=A[i];if(ch=='=')//<>为22{syn=41;TOken[m]=ch;m++;i++;}else{syn=46;}break;case'>':m=0;TOken[m]=ch;m++;i++;ch=A[i];if(ch=='='){syn=42;TOken[m]=ch;m++;i++;{syn=47;}break;case':':m=0;TOken[m]=ch;m++; i++;ch=A[i];if(ch=='='){syn=44;TOken[m]=ch;m++;i++; }else{syn=49;}break;case'@':syn=0;TOken[0]=ch;i++;break;case'=':syn=48;TOken[0]=ch;i++;break;case'#':syn=50;TOken[0]=ch;i++;break;case'+':syn=50;TOken[0]=ch;i++;break;case'-':syn=51;TOken[0]=ch;i++;break;case'*':syn=52;TOken[0]=ch;i++;break;case'/':syn=53;TOken[0]=ch;i++;break;case'(':syn=54;TOken[0]=ch;i++;break;case')':syn=55;TOken[0]=ch;i++;break;case'{':syn=56;TOken[0]=ch;i++;break;case'}':syn=57;TOken[0]=ch;i++;break;case';':syn=58;TOken[0]=ch;i++;break;case'.':syn=59;TOken[0]=ch;i++;break;case'\'':syn=60;TOken[0]=ch;i++;break;case'\n':syn=-2;break;default: syn=-1;break;}}。
词法分析器原代码
// 456.cpp : 定义控制台应用程序的入口点。
//#include "stdafx.h"#include<iostream>#include<fstream>#include<string.h>using namespace std;bool Isnoshow(char ch){ //判断是不是空格、回车、换行符if(ch=='\n'||ch=='\t'||ch==' ')return true;return false;}bool Isletter(char ch){ //判断是不是字母if((ch>='a'&&ch<='z')||(ch>='A '&&ch<='Z'))return true;return false;}bool Isdigital(char ch){ //判断是不是数字if(ch>='0'&&ch<='9')return true;return false;}bool Isunline(char ch){ //判断是不是下划线if(ch=='_')return true;return false;}bool Iscacus(char ch){ //判断是不是运算符if(ch=='+'||ch=='-'||ch=='*'|| ch=='/'||ch=='%'||ch=='<'||ch=='>'||ch=='&'||ch= ='|'||ch=='!'||ch=='=')return true;return false;}bool Issplits(char ch){ //判断是不是分界符if(ch=='{'||ch=='}'||ch=='['|| ch==']'||ch=='('||ch==')'||ch==';'||ch==','||ch= ='.'||ch==':'||ch=='"')return true;return false;}int _tmain(int argc, _TCHAR* argv[]){char b[1000];ifstream ifile;ifile.open("d:\\1.txt");int i=0;while(ifile.get(b[i])){{int a=i+1;if(ifile.eof()==1) break;if(Isletter(b[i])||Isunline(b[i ]))cout<<b[i];else if(Isnoshow(b[i])){if(Isletter(b[i-1])||Isunline(b [i-1]))cout<<"是标识符"<<endl;elseif( Isdigital(b[i-1]))cout<<"是数字"<<endl;elseif(Issplits(b[i-1]))cout<<"是分界符"<<endl;else if(Iscacus(b[i-1]))cout<<"是运算符"<<endl;}else if(Isdigital(b[i])){if(Isletter(b[i-1])||Isunline( b[i-1]))cout<<"是标识符"<<endl; elseif(Issplits(b[i-1]))cout<<b[i-1]<<"是分界符"<<endl;else if(Iscacus(b[i-1]))cout<<"是运算符"<<endl; cout<<b[i];}else if(Iscacus(b[i]))//运算符{if(Isletter(b[i-1])||Isunline(b [i-1]))cout<<"是标识符"<<endl;elseif( Isdigital(b[i-1]))cout<<"是数字"<<endl;else if(Issplits(b[i-1]))cout<<"是分界符"<<endl;cout<<b[i];}else if(Issplits(b[i]))//分界符{if(Isletter(b[i-1])||Isunline( b[i-1]))cout<<"是标识符"<<endl;elseif( Isdigital(b[i-1]))cout<<"是数字"<<endl;else if(Iscacus(b[i-1]))cout<<"是运算符"<<endl;cout<<b[i];}i++;}}if(b[i]='/0'){if(Isletter(b[i-1])||Isunline( b[i-1]))cout<<"是标识符"<<endl;else if( Isdigital(b[i-1]))cout<<"是数字"<<endl;else if(Issplits(b[i-1]))cout<<"是分界符"<<endl;else if(Iscacus(b[i-1]))cout<<"是运算符"<<endl;}ifile.close(); return 0;}。
词法分析源代码
#include <stdio.h>#include <stdlib.h>#include <string.h>#define _KEY_WORD_END "waiting for your expanding"typedef struct{int typenum;char * word;} WORD;char input[255];char token[255]="";int p_input;int p_token;char ch;char* KEY_WORDS[]={"main","int","char","if","else","for","while",_KEY_WORD_END}; WORD* scaner();void main(){FILE *fin;char buffer[100];int size;int over=1;WORD* oneword=new WORD;if((fin=fopen("test.txt","r"))==NULL){printf("Cannot open the file!\n");exit(-1);}fin=fopen("test.txt","r");while(fgets(buffer,100,fin)!=NULL){strcat(input,buffer);}while(over<1000&&over!=-1){oneword=scaner();if(oneword->typenum<1000)printf("(%d,%s)",oneword->typenum,oneword->word);over=oneword->typenum;}printf("\npress # to exit:\n");scanf("%[^#]",input);fclose(fin);}char m_getch(){ch=input[p_input];p_input=p_input+1;return (ch);}void getbc(){while(ch==' '||ch==10){ch=input[p_input];p_input=p_input+1;}}void concat(){token[p_token]=ch;p_token=p_token+1;token[p_token]='\0';}int letter(){if(ch>='a'&&ch<='z'||ch>='A'&&ch<='Z')return 1;else return 0;}int digit(){if(ch>='0'&&ch<='9')return 1;else return 0;}int reserve(){int i=0;while(strcmp(KEY_WORDS[i],_KEY_WORD_END)){ if(!strcmp(KEY_WORDS[i],token)){return i+1;}i=i+1;}return 10;}void retract(){p_input=p_input-1;}char* dtb(){return NULL;}WORD* scaner(){WORD* myword=new WORD;myword->typenum=10;myword->word="";p_token=0;m_getch();getbc();if(letter()){while(letter()||digit()){concat();m_getch();}retract();myword->typenum=reserve();myword->word=token;return(myword);}else if(digit()){while(digit()){concat();m_getch();}retract();myword->typenum=20;myword->word=token;return(myword);}else switch(ch){case '=': m_getch();if (ch=='='){myword->typenum=39;myword->word="==";return(myword);}retract();myword->typenum=21;myword->word="=";return(myword);break;case '+': myword->typenum=22;myword->word="+";return(myword);break;case '-': myword->typenum=23;myword->word="-";return(myword);break;case '*': myword->typenum=24;myword->word="*";return(myword);break;case '/': myword->typenum=25;myword->word="/";return(myword);break;case '(': myword->typenum=26;myword->word="(";return(myword);break;case ')': myword->typenum=27;myword->word=")";return(myword);break;case '[': myword->typenum=28;myword->word="[";return(myword);break;case ']': myword->typenum=29;myword->word="]";return(myword);break;case '{': myword->typenum=30;myword->word="{";return(myword);break;case '}': myword->typenum=31;myword->word="}";return(myword);break;case ',': myword->typenum=32;myword->word=",";return(myword);break;case ':': myword->typenum=33;myword->word=":";return(myword);break;case ';': myword->typenum=34;myword->word=";";return(myword);break;case '>': m_getch();if (ch=='='){myword->typenum=37;myword->word=">=";return(myword);}retract();myword->typenum=35;myword->word=">";return(myword);break;case '<': m_getch();if (ch=='='){myword->typenum=38;myword->word="<=";return(myword);}retract();myword->typenum=36;myword->word="<";return(myword);break;case '!': m_getch();if (ch=='='){myword->typenum=40;myword->word="!=";return(myword);}retract();myword->typenum=-1;myword->word="ERROR";return(myword);break;case '\0': myword->typenum=1000;myword->word="OVER";return(myword);break;default: myword->typenum=-1;myword->word="ERROR";return(myword);}}。
编译原理词法分析和语法分析报告+代码(C语言版)[1]
![编译原理词法分析和语法分析报告+代码(C语言版)[1]](https://img.taocdn.com/s3/m/4183ca9b7cd184254a35352c.png)
词法分析一、实验目的设计、编制并调试一个词法分析程序，加深对词法分析原理的理解。
二、实验要求2.1 待分析的简单的词法（1）关键字：begin if then while do end所有的关键字都是小写。
（2）运算符和界符：= + - * / < <= <> > >= = ; ( ) #（3）其他单词是标识符（ID）和整型常数（SUM），通过以下正规式定义：ID = letter (letter | digit)*NUM = digit digit*（4）空格有空白、制表符和换行符组成。
空格一般用来分隔ID、SUM、运算符、界符和关键字，词法分析阶段通常被忽略。
2.2 各种单词符号对应的种别码：输入：所给文法的源程序字符串。
输出：二元组（syn,token或sum）构成的序列。
其中：syn为单词种别码；token为存放的单词自身字符串；sum为整型常数。
例如：对源程序begin x:=9: if x>9 then x:=2*x+1/3; end #的源文件，经过词法分析后输出如下序列：(1,begin)(10,x)(18,:=)(11,9)(26,;)(2,if)……三、词法分析程序的算法思想：算法的基本任务是从字符串表示的源程序中识别出具有独立意义的单词符号，其基本思想是根据扫描到单词符号的第一个字符的种类，拼出相应的单词符号。
3.1 主程序示意图：主程序示意图如图3-1所示。
其中初始包括以下两个方面：⑴关键字表的初值。
关键字作为特殊标识符处理，把它们预先安排在一张表格中（称为关键字表），当扫描程序识别出标识符时，查关键字表。
如能查到匹配的单词，则该单词为关键字，否则为一般标识符。
关键字表为一个字符串数组，其描述如下：Char *rwtab[6] = {“begin”, “if”, “then”, “while”, “do”, “end”,};图3-1（2）程序中需要用到的主要变量为syn,token和sum3.2 扫描子程序的算法思想：首先设置3个变量：①token用来存放构成单词符号的字符串；②sum用来整型单词；③syn用来存放单词符号的种别码。
- 1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。
#include <stdio.h>#include <string.h>#include <stdlib.h>char *key0[]={" ","auto","break","case","char","const","continue","default","do","double","else" ,"enum","extern","float","for","goto","if","int","long","register","return","sho rt","signed","sizeof","static","struct","switch","typedef","_Complex","_Imaginar y","union","unsigned","void","volatile","while"};/*保留字表*/char *key1[]={" ","(",")","[","]","{","}",",",";","'"};/*分隔符表*/char *key2[]={" ","+","-","*","/","%","<",">","==",">=","<=","!=","!","&&","||","<<",">>","~","| ","^","&","=","?:","->","++","--",".","+=","-=","*=","/="};/*运算符表*/int xx0[35],xx1[10],xx2[31];int temp_key3=0,temp_c40=0,temp_c41=0,temp_c42=0,temp_c43=0;/******* 初始化函数 *******/void load(){int mm;for (mm=0;mm<=34;mm++){xx0[mm]=0;}for (mm=0;mm<=9;mm++){xx1[mm]=0;}for (mm=0;mm<=30;mm++){xx2[mm]=0;}FILE *floading;if ((floading=fopen("key0.txt","w"))==NULL){printf("Error! Can't create file : key0.txt");return;}fclose (floading);/*建立保留字表文件：key0.txt*/if ((floading=fopen("key1.txt","w"))==NULL){printf("Error! Can't create file : key1.txt");return;}/*建立分隔符表文件：key1.txt*/if ((floading=fopen("key2.txt","w"))==NULL){printf("Error! Can't create file : key2.txt");return;}fclose(floading);/*建立运算符表文件：key2.txt*/if ((floading=fopen("key3.txt","w"))==NULL){printf("Error! Can't create file : key3.txt");return;}fclose (floading);/*建立标识符表文件：key3.txt*/if ((floading=fopen("c40.txt","w"))==NULL){printf("Error! Can't create file : c40.txt");return;}fclose (floading);/*建立整数类型常量表文件：c40.txt*/if ((floading=fopen("c41.txt","w"))==NULL){printf("Error! Can't create file : c41.txt");return;}fclose (floading);/*建立浮点类型常量表文件：c41.txt*/if ((floading=fopen("c42.txt","w"))==NULL){printf("Error! Can't create file : c42.txt");return;}fclose (floading);/*建立字符类型常量表文件：c42.txt*/if ((floading=fopen("c43.txt","w"))==NULL){printf("Error! Can't create file : c43.txt");return;}fclose (floading);/*建立字符串类型常量表文件：c43.txt*/if ((floading=fopen("defination.txt","w"))==NULL) {printf("Error! Can't create file : defination.txt");return;}fclose (floading);/*建立注释文件：defination.txt*/if ((floading=fopen("output.txt","w"))==NULL){printf("Error! Can't create file : output.txt");return;}fclose (floading);/*建立内部码文件：output.txt*/if ((floading=fopen("temp_key1","w"))==NULL){printf("Error! Can't create file : temp_key1");return;}fclose (floading);/*建立保留字临时表文件：temp_key1*/if ((floading=fopen("temp_key3","w"))==NULL){printf("Error! Can't create file : temp_key3");return;}fclose (floading);/*建立标识符临时文件：temp_key3*/if ((floading=fopen("temp_c40","w"))==NULL){printf("Error! Can't create file : temp_c40");return;}fclose (floading);/*建立整数类型常量临时文件：temp_c40*/if ((floading=fopen("temp_c41","w"))==NULL){printf("Error! Can't create file : temp_c41");return;}fclose (floading);/*建立浮点类型常量临时文件：temp_c41*/if ((floading=fopen("temp_c42","w"))==NULL){printf("Error! Can't create file : temp_c42");return;}fclose (floading);/*建立字符类型常量临时文件：temp_c42*/if ((floading=fopen("temp_c43","w"))==NULL){printf("Error! Can't create file : temp_c43");return;}fclose (floading);/*建立字符串类型常量临时文件：temp_c43*/}/******* 保留字及标识符判断函数 *******/void char_search(char *word){int m,line=0,csi=0;int value=0;int value2=0;char c,cs[100];FILE *foutput,*finput;for (m=1;m<=34;m++){if (strcmp(word,key0[m])==0){value=1;break;}}if (value==1){if (xx0[m]==0){foutput=fopen("key0.txt","a");fprintf(foutput,"0\t%d\t\t%s\n",m,word);fclose(foutput);xx0[m]=1;}foutput=fopen("output.txt","a");fprintf(foutput,"0\t%d\t\t%s\n",m,word);fclose(foutput);}else{if (temp_key3==0){foutput=fopen("temp_key3","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_key3++;foutput=fopen("key3.txt","a");fprintf(foutput,"3\t1\t\t%s\n",word);fclose(foutput);}finput=fopen("temp_key3","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if ((strcmp(cs,word))==0){value2=1;break;}else{value2=0;c=fgetc(finput);}}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_key3","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_key3++;foutput=fopen("output.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",temp_key3,word);fclose(foutput);foutput=fopen("key3.txt","a");fprintf(foutput,"3\t%d\t\t%s\n",temp_key3,word);fclose(foutput);}}}/******* 整数类型判断函数 *******/void inta_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c40==0){foutput=fopen("temp_c40","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c40++;foutput=fopen("c40.txt","a");fprintf(foutput,"4\t0\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c40","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c40","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c40++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",temp_c40,word);fclose(foutput);foutput=fopen("c40.txt","a");fprintf(foutput,"4\t0\t%d\t%s\n",temp_c40,word);fclose(foutput);}}/******* 浮点类型判断函数 *******/void intb_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c41==0){foutput=fopen("temp_c41","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c41++;foutput=fopen("c41.txt","a");fprintf(foutput,"4\t1\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c41","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c41","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c41++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",temp_c41,word);fclose(foutput);foutput=fopen("c40.txt","a");fprintf(foutput,"4\t1\t%d\t%s\n",temp_c41,word);fclose(foutput);}}/******* 字符串常量判断函数 *******/void cc_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c43==0){foutput=fopen("temp_c43","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c43++;foutput=fopen("c43.txt","a");fprintf(foutput,"4\t3\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c43","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c43","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c43++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",temp_c43,word);fclose(foutput);foutput=fopen("c43.txt","a");fprintf(foutput,"4\t3\t%d\t%s\n",temp_c43,word);fclose(foutput);}}/******* 字符常量判断函数 *******/void c_search(char *word){FILE *foutput,*finput;char c;char cs[100];int csi=0;int line=0;int value2=0;if (temp_c42==0){foutput=fopen("temp_c42","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c42++;foutput=fopen("c42.txt","a");fprintf(foutput,"4\t2\t1\t%s\n",word);fclose(foutput);}finput=fopen("temp_c42","r");c=fgetc(finput);while (c!=EOF){while (c!='\n'){cs[csi++]=c;c=fgetc(finput);}cs[csi]='\0';csi=0;line++;if (strcmp(cs,word)==0){value2=1;break;}c=fgetc(finput);}fclose(finput);if (value2==1){foutput=fopen("output.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",line,word);fclose(foutput);}else{foutput=fopen("temp_c42","a");fprintf(foutput,"%s\n",word);fclose(foutput);temp_c42++;foutput=fopen("output.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",temp_c42,word);fclose(foutput);foutput=fopen("c42.txt","a");fprintf(foutput,"4\t2\t%d\t%s\n",temp_c42,word);fclose(foutput);}}/******* 主扫描函数 *******/void scan(){int count;char chin;FILE *fin;FILE *fout;char filename[50];char temp[100];char target[3]="'";printf("请输入文件名：");scanf("%s",filename);if ((fin=fopen(filename,"r"))==NULL){printf("Error! Can't open file : %s\n",filename);return;}chin=fgetc(fin);while (chin!=EOF){/*对文件包含、宏定义进行处理*/if (chin=='#'){while (chin!='>')chin=fgetc(fin);/*chin=fgetc(fin);*/}/*对空格符、水平制表符进行处理*/else if ((chin==' ')||(chin=='\t')){;}/*对回车符进行处理*/else if (chin=='\n'){;}/*对单引号内的字符常量进行处理*/else if (chin==target[0]){if (xx1[9]==0){fout=fopen("key1.txt","a");fprintf(fout,"1\t9\t\t%c\n",target[0]);fclose(fout);xx1[9]=1;}temp[0]=chin;chin=fgetc(fin);temp[1]=chin;chin=fgetc(fin);if (chin!=target[0]){temp[2]=chin;chin=fgetc(fin);temp[3]=chin;temp[4]='\0';}else{temp[2]=chin;temp[3]='\0';}c_search(temp);}/*对双引号内的字符串常量进行处理*/else if (chin=='"'){int i=0;temp[i++]='"';chin=fgetc(fin);while (chin!='"'){temp[i++]=chin;chin=fgetc(fin);}temp[i]='"';temp[i+1]='\0';cc_search(temp);}/*对保留字、标识符进行处理*/else if (((chin>='A')&&(chin<='Z'))||((chin>='a')&&(chin<='z'))||(chin=='_')) {int i=0;while(((chin>='A')&&(chin<='Z'))||((chin>='a')&&(chin<='z'))||(chin=='_')||((chin>='0 ')&&(chin<='9'))){temp[i++]=chin;chin=fgetc(fin);}temp[i]='\0';char_search(temp);if (chin!=EOF)fseek (fin,-1L,SEEK_CUR);}/*对整型、浮点型数据进行处理*/else if ((chin>='0')&&(chin<='9')){int dotcount=0;int i=0;while (((chin>='0')&&(chin<='9'))||(chin=='.')) {if (chin=='.')dotcount++;if (dotcount==2)break;temp[i++]=chin;chin=fgetc(fin);}temp[i]='\0';if (dotcount==1)intb_search(temp);elseinta_search(temp);if (chin!=EOF)fseek (fin,-1L,SEEK_CUR);}/*对注释进行处理*/else if (chin=='/'){chin=fgetc(fin);if (chin=='='){fout=fopen("output.txt","a");fprintf(fout,"2\t30\t\t/=\n");fclose(fout);}else if (chin!='*'){fout=fopen("output.txt","a");fprintf(fout,"2\t4\t\t/\n");fclose(fout);fseek(fin,-1L,SEEK_CUR);}else if (chin=='*'){count=0;chin=fgetc(fin);fout=fopen("defination.txt","a");fprintf(fout,"/*");while (count!=2){count=0;while (chin!='*'){fprintf(fout,"%c",chin);chin=fgetc(fin);}count++;fprintf(fout,"%c",chin);chin=fgetc(fin);if (chin=='/'){count++;fprintf(fout,"%c\n",chin);}else{fprintf(fout,"%c",chin);chin=fgetc(fin);}}}}/*对运算符、分隔符进行处理*/else{int time=0;int firstblood=0;temp[0]=chin;chin=fgetc(fin);if (chin!=EOF){temp[1]=chin;temp[2]='\0';for (time=1;time<=30;time++){if (strcmp(temp,key2[time])==0){firstblood=1;if (xx2[time]==0){fout=fopen("key2.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);xx2[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);break;}}if (firstblood!=1){fseek(fin,-1L,SEEK_CUR);temp[1]='\0';for (time=1;time<=9;time++){if (strcmp(temp,key1[time])==0){if (xx1[time]==0){fout=fopen("key1.txt","a");fprintf(fout,"1\t%d\t\t%s\n",time,temp);fclose(fout);xx1[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"1\t%d\t\t%s\n",time,temp);fclose(fout);break;}}for (time=1;time<=30;time++){if (strcmp(temp,key2[time])==0){if (xx2[time]==0){fout=fopen("key2.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);xx2[time]=1;}fout=fopen("output.txt","a");fprintf(fout,"2\t%d\t\t%s\n",time,temp);fclose(fout);break;}}}}}chin=fgetc(fin);}fout=fopen("output.txt","a");fprintf(fout,"1\t6\t\t}\n");fclose(fout);}/******* Main函数 *******/void main(){FILE *fread;char charin;char command='Q';printf("\n");printf("******************** C语言词法分析工具********************\n");printf("* *\n");printf("* *\n");printf("* 命令如下： *\n");printf("* 0 --> 查看保留字表文件 *\n");printf("* 1 --> 查看分隔符表文件 *\n");printf("* 2 --> 查看运算符表文件 *\n");printf("* 3 --> 查看标识符表文件 *\n");printf("* 4 --> 查看整数类型常量表 *\n");printf("* 5 --> 查看浮点类型常量表 *\n");printf("* 6 --> 查看字符类型常量表 *\n");printf("* 7 --> 查看字符串类型常量表 *\n");printf("* 8 --> 查看注释文件 *\n");printf("* 9 --> 查看内部码文件 *\n"); printf("* -------------------------- *\n"); printf("* Q --> 退出 *\n"); printf("***************************************************************\n"); printf("\n");load();scan();printf("\n");printf("分析完成！\n");getchar();printf("\n");printf("请输入命令：");command=getchar();while ((command!='Q')&&(command!='q')){switch (command){case '0':{printf("*************************\n");printf("\n");fread=fopen("key0.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '1':{printf("*************************\n");printf("\n");fread=fopen("key1.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '2':{printf("*************************\n");printf("\n");fread=fopen("key2.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '3':{printf("*************************\n");printf("\n");fread=fopen("key3.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '4':{printf("*************************\n");printf("\n");fread=fopen("c40.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '5':{printf("*************************\n");printf("\n");fread=fopen("c41.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '6':{printf("*************************\n");printf("\n");fread=fopen("c42.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '7':{printf("*************************\n");printf("\n");fread=fopen("c43.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '8':{printf("*************************\n");printf("\n");fread=fopen("defination.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}case '9':{printf("*************************\n");printf("\n");fread=fopen("output.txt","r");charin=fgetc(fread);while (charin!=EOF){putchar(charin);charin=fgetc(fread);}printf("\n");printf("*************************\n");printf("\n");printf("请输入命令：");break;}}command=getchar();}}。