Nirendra Awasthi - Nirendra

common.h

Sun, 23 Jul 2006 03:25:51 -0700

#define NTRIALS 100000

#define BUFF_LEN 100

#define FILE_NAME "/home/nirendra/test.html"

#define measure_time(code) \

	for(i=0; i < NTRIALS; i++) { \

		rdtscl(ini); \

		code; \

		rdtscl(end); \

		now = end - ini; \

		if(now < best) best = now; \

	}
static void parse_html(char *html, char *text)

{

	int hcount = 0, tcount = 0;

	int tag=0;

	/*Parse buffer to remove html tags*/

	for(hcount = 0; html[hcount] != '\0' && html[hcount]; hcount++)

	{

		if(html[hcount] == '<') /*HTML tag begins*/

			tag = 1;

		if(!tag)

			text[tcount++] = html[hcount];

		if(html[hcount] == '>') /*HTML tag ends*/

			tag = 0;

	}

	text[tcount] = '\0';

}

uhtmlparser.c

Sun, 23 Jul 2006 03:26:46 -0700

#include <stdio.h>

#include <stdlib.h>

#include <fcntl.h>

#include <sys/types.h>

#include <sys/stat.h>

#include <asm/msr.h>
#include "common.h"
int main()

{

	unsigned long ini, end, now, best, tsc;

	int i;

	int fd;

	int nhtml = 0, ntext = 0;

	char *html, *text;

	html = malloc(BUFF_LEN);

	text = malloc(BUFF_LEN);

	memset(html, 0, BUFF_LEN);

	memset(text, 0, BUFF_LEN);
	/*time rdsc, i.e. no code*/

	best =~ 0;

	measure_time(0);

	tsc = best;

	printf("Time taken for no code: %ld\n", tsc);
	/*Measure time for reading a file*/

	fd = open(FILE_NAME, O_RDONLY, 0600);

	if(!fd){

		printf("Error opening file\n");

		exit(1);

	}

	best = ~0;

	measure_time(read(fd, html, 1000));

	printf("Time taken by read: %li\n", best - tsc);

	parse_html(html, text);

	printf("Parsed text: %s\n", text);

}

khtmlparser.c

Sun, 23 Jul 2006 03:27:26 -0700

#include <linux/init.h>

#include <linux/module.h>

#include <linux/init.h>

#include <linux/syscalls.h>

#include <linux/fcntl.h>

#include <linux/fs.h>

#include <linux/file.h>

#include <linux/unistd.h>

#include <asm/uaccess.h>

MODULE_LICENSE("Dual BSD/GPL");
#include "common.h"
static int khtmlparser_init(void)

{

	mm_segment_t fs;

	unsigned long ini, end, now, best, tsc;

	int i;

	struct file *fd;

	char *html;

	char *text;

	html = kzalloc(BUFF_LEN, GFP_KERNEL);

	text = kzalloc(BUFF_LEN, GFP_KERNEL);

	best = ~0;

	measure_time(0);

	tsc = best;

	printk(KERN_INFO "Time taken for no code: %ld\n", tsc);
	/*Measure time of reading a file*/

	/*Prepare to invoke system call*/

	fs = get_fs();	/*Save previous value*/

     	set_fs(get_ds());	/*use kernel limit*/

	/*Call system call*/

	fd = filp_open(FILE_NAME, O_RDONLY, 0600);

	if(IS_ERR(fd)){

			printk(KERN_INFO "flip_open returned an error\n");

			return(-EINVAL);

	}

	if(fd->f_op && fd->f_op->read){

		best = ~0;

		measure_time(fd->f_op->read(fd, html, 1000, &fd->f_pos));

		printk(KERN_INFO "Time taken by read: %ld\n", best-tsc);

		parse_html(html, text); /*Parse html to text*/

		printk(KERN_INFO "Parsed text: %s", text);

	}

	if(fd) filp_close(fd, NULL);

	set_fs(fs);	/*restore before returning to userspace*/

	return -EINVAL;

}
/*Never used*/

static void khtmlparser_exit(void)

{

}
module_init(khtmlparser_init);

module_exit(khtmlparser_exit);