编译器练习：找出C程序中声明的变量，关键字和自然数

1.源代码

//glovar.h

#ifndef _GLOVAR_H_

#define _GLOBAR_H_

#include <stdio.h>

#include <stdlib.h>

#include <ctype.h>

#define MAXTOKEN 40

extern FILE *fps;

extern FILE *fpt;

char tokenStr[MAXTOKEN+1];

typedef enum {

INIT,

INNUM,

INID,

IN_MARK,

IN_MARK_SEG,IN_MARK_SEG1,

IN_MARK_LINE,

DONE

}TokenState;

typedef enum {

ID,NUM,/*JUDGE SYMBOL*/

IF,ELSE,DO,WHILE,SWITCH,CASE,INT,LONG,DOUBLE,FLOAT,CHAR,BREAK,

EQ,LS,LE,GT,GE,NE, //EQ =,LS <,LE <= ,GT >, GE >=, NE !=

ASSIGN, //'='

ADD,SUB,MUL,DIV,//OP + , - , * , / ,

INC,DEC,

LC,RC, // '(' ')'

LR,RR, // '[' ']'

LS,RS, // '{' '}'

OR,AND,NOT, // '|' '&' '!'

SEMI,// ';'

SHARP,//'#'

ENDFILE

}TokenType;

#endif

//scan.h

#ifndef _SCAN_H_

#define _SCAN_H_

TokenType GetToken(void);

#endif

//scan.c
#include "glovar.h"
#include "scan.h"
int line=1;
static struct {
char *str;
TokenType tok;
}kw[12]={{"if",IF},{"else",ELSE},{"do",DO},{"while",WHILE},{"break",BREAK}, {"switch",SWITCH},{"case",CASE},
{"int",INT},{"char",CHAR},{"float",FLOAT},{"double",DOUBLE},{"long",LONG}};
int reservelookup(char *s){
int i;
for(i=0;i<12;i++){
if(strcmp(s,kw[i].str)==0)
return 1;
}
return 0;
}
TokenType GetToken(void){
int tokenBufferIndex=0;
char ch;
TokenType tt;
TokenState state=INIT;
while(state!=DONE){
ch=getc(fps);
switch(state){
case INIT: if(isdigit(ch))
{
state=INNUM;
tokenStr[tokenBufferIndex++]=ch;
}
else if (isalpha(ch)){
state=INID;
tokenStr[tokenBufferIndex++]=ch;}
else if((ch==' ')||ch=='/t') state=INIT;
else {
switch(ch){
case '=' : ch=getc(fps);
if(ch=='=') tt=EQ;
else {
ungetc(ch,fps);
tt= ASSIGN;
}
break;
case '<' : ch=getc(fps);
if(ch=='=') tt=LE;
else if(ch=='>') tt=NE;
else {
ungetc(ch,fps);
tt= LS;
}
break;
case '>' : ch=getc(fps);
if(ch=='=') tt= GE;
else {
ungetc(ch,fps);
tt= GT;
}
break;
case '|': tt=OR;
state=DONE;
break;
case '&': tt=AND;
state=DONE;
break;
case '!': tt=NOT;
state=DONE;
break;
case '+': ch=getc(fps);
if(ch=='+') tt= INC;
else{
ungetc(ch,fps);
tt= ADD;
break;
}
case '-': ch=getc(fps);
if(ch=='-') tt= DEC;
else{
ungetc(ch,fps);
tt=SUB;
break;
}
case '*':
tt= MUL;
state=DONE;
break;
case '/': state=IN_MARK;
break;
case '/n': line++;
break;
case '#': tt=SHARP;
break;
case ';' : tt= SEMI;
state=DONE;
break;
case '(' : tt= LC;
state=DONE;
break;
case ')' : tt= RC;
state=DONE;
break;
case '[' : tt= LR;
state=DONE;
break;
case ']' : tt= RR;
state=DONE;
break;
case '{' : tt= LS;
state=DONE;
break;
case '}' : tt= RS;
state=DONE;
break;
case EOF:
tt=ENDFILE;
state=DONE;
break;
default : break;
}
}
break;
case IN_MARK:
if(ch=='*') state= IN_MARK_SEG;
else if(ch=='/') state= IN_MARK_LINE;
else {
ungetc(ch,fps);
tt=DIV;
state=DONE;
}
break;
case IN_MARK_SEG:
if(ch=='*') state=IN_MARK_SEG1;
break;
case IN_MARK_SEG1:
if(ch=='/') state=INIT;
break;
case IN_MARK_LINE:
if(ch=='/n') state=INIT;
break;
case INNUM: if(isdigit(ch))
tokenStr[tokenBufferIndex++]=ch;
else
{ tokenStr[tokenBufferIndex]='/0';
state=DONE;
ungetc(ch,fps);
tt=NUM;
}
break;
case INID: if(isalpha(ch))
tokenStr[tokenBufferIndex++]=ch;
else{
tokenStr[tokenBufferIndex]='/0';
state=DONE;
ungetc(ch,fps);
tt=ID;
}
break;
case DONE: break;
}
}
if(tt==ID){
if(reservelookup(tokenStr))
fprintf(fpt,"Get Keywords -->%s/n/n",tokenStr);
else
fprintf(fpt,"Get ID -->%s/n/n",tokenStr);
}
else if(tt==NUM)
fprintf(fpt,"Get NUM -->%s/n",tokenStr);
return tt;
}

//main.c
#include "glovar.h"
#include "scan.h"
/*
programed by:alex shoal
edit date:2009-4-22, Sunday
revision:2
****************
*Question:gettoken practice
****************
*/
FILE *fps; //* file point of source
FILE *fpt; //* file point of target
int main(int argc, char *argv[]){
TokenType tp;
int i=0;
fpt=stdout;
if (argc != 2){
printf("Usage: %s filename/n", argv[0]);
exit(1);
}
if ((fps = fopen(argv[1], "r")) == NULL){
printf("Can't open file :%s/n", argv[1]);
exit(1);
}
if ((fpt = fopen("out.txt", "w+")) == NULL){
printf("Can't open file :out.txt /n");
exit(1);
}
while (((tp = GetToken()) != ENDFILE)){
fprintf(fpt,"Token %d= %d/n",i++,tp);
}
fclose(fps);
return 0;
}
2.编译
code block 8.02编译
3.输入文件
//filename app.c

//ANSI C exit() prototype
int main(int argc, char *argv[])
{
int ch; // place to store each character as read
FILE *fp; // "file pointer"
long count = 0;
if (argc != 2)
{
printf("Usage: %s filename/n", argv[0]);
exit(1);
}
if ((fp = fopen(argv[1], "r")) == NULL)
{
printf("Can't open %s/n", argv[1]);
exit(1);
}
while ((ch = getc(fp)) != EOF)
{
putchar(ch,stdout); /*same as putchar(ch);
count++;
}
fclose(fp);*/
printf("File %s has %ld characters/n", argv[1], count);
return 0;
}

4.运行
temp app.c
8.结果

Get Keywords -->int
Token 0= 0
Get ID -->main
Token 1= 0
Token 2= 28
Get Keywords -->int
Token 3= 0
Get ID -->argc
Token 4= 0
Get Keywords -->char
Token 5= 0
Token 6= 24
Get ID -->argv
Token 7= 0
Token 8= 30
Token 9= 31
Token 10= 29
Token 11= 32
Get Keywords -->int
Token 12= 0
Get ID -->ch
Token 13= 0
Token 14= 37
Get ID -->FILE
Token 15= 0
Token 16= 24
Get ID -->fp
Token 17= 0
Token 18= 37
Get Keywords -->long
Token 19= 0
Get ID -->count
Token 20= 0
Get NUM -->0
Token 21= 1
Token 22= 37
Get Keywords -->if
Token 23= 0
Token 24= 28
Get ID -->argc
Token 25= 0
Token 26= 36
Get NUM -->2
Token 27= 1
Token 28= 29
Token 29= 32
Get ID -->printf
Token 30= 0
Token 31= 28
Get ID -->Usage
Token 32= 0
Get ID -->s
Token 33= 0
Get ID -->filename
Token 34= 0
Get ID -->n
Token 35= 0
Get ID -->argv
Token 36= 0
Token 37= 30
Get NUM -->0
Token 38= 1
Token 39= 31
Token 40= 29
Token 41= 37
Get ID -->exit
Token 42= 0
Token 43= 28
Get NUM -->1
Token 44= 1
Token 45= 29
Token 46= 37
Token 47= 33
Get Keywords -->if
Token 48= 0
Token 49= 28
Token 50= 28
Get ID -->fp
Token 51= 0
Get ID -->fopen
Token 52= 0
Token 53= 28
Get ID -->argv
Token 54= 0
Token 55= 30
Get NUM -->1
Token 56= 1
Token 57= 31
Get ID -->r
Token 58= 0
Token 59= 29
Token 60= 29
Get ID -->NULL
Token 61= 0
Token 62= 29
Token 63= 32
Get ID -->printf
Token 64= 0
Token 65= 28
Get ID -->Can
Token 66= 0
Get ID -->t
Token 67= 0
Get ID -->open
Token 68= 0
Get ID -->s
Token 69= 0
Get ID -->n
Token 70= 0
Get ID -->argv
Token 71= 0
Token 72= 30
Get NUM -->1
Token 73= 1
Token 74= 31
Token 75= 29
Token 76= 37
Get ID -->exit
Token 77= 0
Token 78= 28
Get NUM -->1
Token 79= 1
Token 80= 29
Token 81= 37
Token 82= 33
Get Keywords -->while
Token 83= 0
Token 84= 28
Token 85= 28
Get ID -->ch
Token 86= 0
Get ID -->getc
Token 87= 0
Token 88= 28
Get ID -->fp
Token 89= 0
Token 90= 29
Token 91= 29
Token 92= 36
Get ID -->EOF
Token 93= 0
Token 94= 29
Token 95= 32
Get ID -->putchar
Token 96= 0
Token 97= 28
Get ID -->ch
Token 98= 0
Get ID -->stdout
Token 99= 0
Token 100= 29
Token 101= 37
Get ID -->printf
Token 102= 0
Token 103= 28
Get ID -->File
Token 104= 0
Get ID -->s
Token 105= 0
Get ID -->has
Token 106= 0
Get ID -->ld
Token 107= 0
Get ID -->characters
Token 108= 0
Get ID -->n
Token 109= 0
Get ID -->argv
Token 110= 0
Token 111= 30
Get NUM -->1
Token 112= 1
Token 113= 31
Get ID -->count
Token 114= 0
Token 115= 29
Token 116= 37
Get ID -->return
Token 117= 0
Get NUM -->0
Token 118= 1
Token 119= 37
Token 120= 33