scan.h

使用re2c分析html頁面的url scan.h url.re Makefile

#ifndef  SCAN_H_
#define  SCAN_H_
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>


typedef unsigned char uchar;
typedef unsigned int  uint ;


#define	BSIZE	8192
/*
 *  @tok  : first match of result 
 *  @bot  : the buffer pointer   : must free 
 *  @cur  : YYCURSOR  
 *  @pos  : 
 *  @lim  : YYLIMIT         
 *  @ptr  : YYMARKER       
 *  @top 
 *  @eof
 *
 */

typedef struct Scanner {
    int			fd;
    uchar		*bot, *tok, *ptr, *cur, *pos, *lim, *top, *eof;
    uint		line;
} Scanner;


uchar *fill(Scanner *s, uchar *cursor){
    if(!s->eof) {
	uint cnt = s->tok - s->bot;
	if(cnt){
	    memcpy(s->bot, s->tok, s->lim - s->tok);
	    s->tok = s->bot;
	    s->ptr -= cnt;
	    cursor -= cnt;
	    s->pos -= cnt;
	    s->lim -= cnt;
	}
	if((s->top - s->lim) < BSIZE){
	    uchar *buf = (uchar*) malloc(((s->lim - s->bot) + BSIZE)*sizeof(uchar));
	    memcpy(buf, s->tok, s->lim - s->tok);
	    s->tok = buf;
	    s->ptr = &buf[s->ptr - s->bot];
	    cursor = &buf[cursor - s->bot];
	    s->pos = &buf[s->pos - s->bot];
	    s->lim = &buf[s->lim - s->bot];
	    s->top = &s->lim[BSIZE];
	    free(s->bot);
	    s->bot = buf;
	}
	if((cnt = read(s->fd, (char*) s->lim, BSIZE)) != BSIZE){
	    s->eof = &s->lim[cnt]; 
	    *(s->eof)++ = '\n';
	}
	s->lim += cnt;
    }
    return cursor;
}



#endif