#!/usr/bin/perl -W
#
# File: find.pl
# Author: 路小佳
# License: GPL-2
use strict; use warnings; use File::Find;
my ($size, $dircnt, $filecnt) = (0, 0, 0);
sub process { my $file = $File::Find::name; #print $file, "\n";
if (-d $file) { $dircnt++; } else { $filecnt++; $size += -s $file; } }
find(\&process, '.'); print "$filecnt files, $dircnt directory. $size bytes.\n";
|
2. lsr递归遍历
#!/usr/bin/perl -W
#
# File: lsr.pl
# Author: 路小佳
# License: GPL-2
use strict; use warnings;
sub lsr($) { sub lsr; my $cwd = shift;
local *DH; if (!opendir(DH, $cwd)) { warn "Cannot opendir $cwd: $! $^E"; return undef; } foreach (readdir(DH)) { if ($_ eq '.' || $_ eq '..') { next; } my $file = $cwd.'/'.$_; if (!-l $file && -d _) { $file .= '/'; lsr($file); } process($file, $cwd); } closedir(DH); }
my ($size, $dircnt, $filecnt) = (0, 0, 0);
sub process($$) { my $file = shift; #print $file, "\n";
if (substr($file, length($file)-1, 1) eq '/') { $dircnt++; } else { $filecnt++; $size += -s $file; } }
lsr('.'); print "$filecnt files, $dircnt directory. $size bytes.\n";
|
3. lsr_s栈遍历
#!/usr/bin/perl -W
#
# File: lsr_s.pl
# Author: 路小佳
# License: GPL-2
use strict; use warnings;
sub lsr_s($) { my $cwd = shift; my @dirs = ($cwd.'/');
my ($dir, $file); while ($dir = pop(@dirs)) { local *DH; if (!opendir(DH, $dir)) { warn "Cannot opendir $dir: $! $^E"; next; } foreach (readdir(DH)) { if ($_ eq '.' || $_ eq '..') { next; } $file = $dir.$_; if (!-l $file && -d _) { $file .= '/'; push(@dirs, $file); } process($file, $dir); } closedir(DH); } }
my ($size, $dircnt, $filecnt) = (0, 0, 0);
sub process($$) { my $file = shift; print $file, "\n"; if (substr($file, length($file)-1, 1) eq '/') { $dircnt++; } else { $filecnt++; $size += -s $file; } }
lsr_s('.'); print "$filecnt files, $dircnt directory. $size bytes.\n";
|
对我的硬盘/dev/hda6的测试结果。
1: File::Find
26881 files, 1603 directory. 9052479946 bytes.
real 0m9.140s
user 0m3.124s
sys 0m5.811s
2: lsr
26881 files, 1603 directory. 9052479946 bytes.
real 0m8.266s
user 0m2.686s
sys 0m5.405s
3: lsr_s
26881 files, 1603 directory. 9052479946 bytes.
real 0m6.532s
user 0m2.124s
sys 0m3.952s
测试时考虑到cache所以要多测几次取平均, 也不要同时打印文件名, 因为控制台是慢设备, 会形成瓶颈。
lsr_s之所以用栈而不是队列来遍历,是因为Perl的push shift pop操作是基于数组的, push pop这样成对操作可能有优化。内存和cpu占用大小顺序也是1>2>3.
CPU load memory
use File::Find 97% 4540K
lsr 95% 3760K
lsr_s 95% 3590K
结论: 强烈推荐使用lsr_s来遍历文件夹。
=============再罗嗦几句======================
从执行效率上来看,find.pl比lsr.pl的差距主要在user上, 原因是File::Find模块选项较多,条件判断费时较多,而 lsr_s.pl比lsr.pl在作系统调用用时较少, 是因为递归时程序还在保存原有的文件句柄和函数恢复现场的信息,所以sys费时较多。 所以 lsr_s在sys与user上同时胜出是不无道理的。
#!/usr/bin/perl -w
#读取目录下的目录,并且去除..和.目录以及隐藏的目录
opendir (DIR,"/root") or die "could not open /root";
@dots=grep {/^[^\.]/ && -d "/root/$_" } readdir(DIR);
foreach (@dots) {
print "$_\n";
}
closedir DIR;
#!/usr/bin/perl
# A small program to read the contents
# of a directory and print them to screen
@dir_contents;
$dir_to_open="/home/sant/dcs/Teaching/Internet_Systems/Lectures";
# open file with handle DIR
opendir(DIR,$dir_to_open) || die("Cannot open directory !\n");
# Get contents of directory
@dir_contents= readdir(DIR);
# Close the directory
closedir(DIR);
# Now loop through array and print file names
foreach $file (@dir_contents)
{
if(!(($file eq ".") || ($file eq "..")))
{
print "$file \n";
}
}
阅读(466) | 评论(0) | 转发(0) |