| 1 |
################################# |
| 2 |
# |
| 3 |
# $Id: libp.pm,v 1.3 2002/07/19 18:13:50 cvsjoko Exp $ |
| 4 |
# |
| 5 |
# $Log: libp.pm,v $ |
| 6 |
# Revision 1.3 2002/07/19 18:13:50 cvsjoko |
| 7 |
# no message |
| 8 |
# |
| 9 |
# Revision 1.2 2002/06/27 02:14:22 cvsjoko |
| 10 |
# + stripHtml stripSpaces stripNewLines toReal |
| 11 |
# |
| 12 |
# Revision 1.1 2002/06/24 14:49:59 cvsjoko |
| 13 |
# + new |
| 14 |
# |
| 15 |
# |
| 16 |
################################# |
| 17 |
|
| 18 |
package libp; |
| 19 |
|
| 20 |
require Exporter; |
| 21 |
@ISA = qw( Exporter ); |
| 22 |
@EXPORT = qw( |
| 23 |
Dumper |
| 24 |
md5 md5_hex md5_base64 |
| 25 |
ParseDate UnixDate |
| 26 |
strftime |
| 27 |
stripHtml stripSpaces stripNewLines toReal trim |
| 28 |
croak |
| 29 |
array_getDifference |
| 30 |
getDirList |
| 31 |
); |
| 32 |
|
| 33 |
use strict; |
| 34 |
use warnings; |
| 35 |
|
| 36 |
use Data::Dumper; |
| 37 |
use Digest::MD5 qw(md5 md5_hex md5_base64); |
| 38 |
|
| 39 |
$main::TZ = 'GMT'; |
| 40 |
use Date::Manip; |
| 41 |
|
| 42 |
require LWP::UserAgent; |
| 43 |
use HTML::PullParser; |
| 44 |
|
| 45 |
# $now_string = strftime "%a %b %e %H:%M:%S %Y", localtime; |
| 46 |
# see "perldoc -f localtime" |
| 47 |
use POSIX qw(strftime); |
| 48 |
|
| 49 |
use Carp; |
| 50 |
|
| 51 |
use DirHandle; |
| 52 |
|
| 53 |
|
| 54 |
######################################## |
| 55 |
|
| 56 |
sub stripSpaces { |
| 57 |
my $text = shift; |
| 58 |
#print "text: $text", "\n"; |
| 59 |
#print "ord: ", ord(substr($text, 0, 1)), "\n"; |
| 60 |
$text =~ s/^\s*//g; |
| 61 |
$text =~ s/\s*$//g; |
| 62 |
return $text; |
| 63 |
} |
| 64 |
|
| 65 |
sub trim { |
| 66 |
my $string = shift; |
| 67 |
return stripSpaces($string); |
| 68 |
} |
| 69 |
|
| 70 |
sub stripNewLines { |
| 71 |
my $text = shift; |
| 72 |
#print "text: $text", "\n"; |
| 73 |
#print "ord: ", ord(substr($text, 0, 1)), "\n"; |
| 74 |
$text =~ s/\n//g; |
| 75 |
#$text =~ s/\s*$//g; |
| 76 |
return $text; |
| 77 |
} |
| 78 |
|
| 79 |
sub toReal { |
| 80 |
my $string = shift; |
| 81 |
$string =~ m/(\d+\.*\d+)/; |
| 82 |
my $real = $1; |
| 83 |
return $real; |
| 84 |
} |
| 85 |
|
| 86 |
sub stripHtml { |
| 87 |
my $html = shift; |
| 88 |
my $result = ''; |
| 89 |
#$html =~ s/<br>(.*)/ - ($1)/i; |
| 90 |
my $p = HTML::PullParser->new( |
| 91 |
doc => \$html, |
| 92 |
text => 'text', |
| 93 |
unbroken_text => 1, |
| 94 |
); |
| 95 |
while (my $token = $p->get_token()) { |
| 96 |
my $text = join('', @{$token}); |
| 97 |
$result .= $text; |
| 98 |
} |
| 99 |
#$result =~ s/ //g; |
| 100 |
return $result; |
| 101 |
} |
| 102 |
|
| 103 |
sub array_getRelations { |
| 104 |
my $a_ref = shift; |
| 105 |
my $b_ref = shift; |
| 106 |
my @a = @{$a_ref}; |
| 107 |
my @b = @{$b_ref}; |
| 108 |
|
| 109 |
my @isect = my @diff = my @union = (); |
| 110 |
my $e; |
| 111 |
my %count; |
| 112 |
|
| 113 |
foreach $e (@a, @b) { $count{$e}++ } |
| 114 |
|
| 115 |
foreach $e (keys %count) { |
| 116 |
push(@union, $e); |
| 117 |
push @{ $count{$e} == 2 ? \@isect : \@diff }, $e; |
| 118 |
} |
| 119 |
|
| 120 |
my $result = { |
| 121 |
union => \@union, |
| 122 |
isect => \@isect, |
| 123 |
diff => \@diff, |
| 124 |
}; |
| 125 |
|
| 126 |
} |
| 127 |
|
| 128 |
sub array_getDifference { |
| 129 |
my $res = array_getRelations(shift, shift); |
| 130 |
return $res->{diff}; |
| 131 |
} |
| 132 |
|
| 133 |
|
| 134 |
# ============================================= |
| 135 |
# "global" vars used in directory-recursive-parsing |
| 136 |
my $dirlist_buf; |
| 137 |
my @dirlist_path; |
| 138 |
my $dirlist_base; |
| 139 |
|
| 140 |
sub entry_callback { |
| 141 |
|
| 142 |
my $entry = shift; |
| 143 |
|
| 144 |
# CHECKS |
| 145 |
# dont't use this: |
| 146 |
if ($entry eq '.' || $entry eq '..') { return; } |
| 147 |
|
| 148 |
# PREPARE |
| 149 |
# prepare path to current entry |
| 150 |
my $cur_entry = join('/', @dirlist_path, $entry); |
| 151 |
# prepare path to current entry (absolute) |
| 152 |
my $cur_entry_abs = join('/', $dirlist_base, @dirlist_path, $entry); |
| 153 |
|
| 154 |
# ENTRY |
| 155 |
# add current entry to buffer |
| 156 |
$dirlist_buf .= $cur_entry . "\n"; |
| 157 |
|
| 158 |
# (SUB-)DIRECTORY |
| 159 |
# check if current entry is a (sub-)directory ... |
| 160 |
if (-d $cur_entry_abs) { |
| 161 |
push @dirlist_path, $cur_entry; |
| 162 |
# ... and parse this (recursion here!!!) |
| 163 |
iterate_path($cur_entry_abs); |
| 164 |
pop @dirlist_path; |
| 165 |
} |
| 166 |
} |
| 167 |
|
| 168 |
sub iterate_path { |
| 169 |
|
| 170 |
my $path = shift; |
| 171 |
|
| 172 |
# create new "DirHandle"-object |
| 173 |
my $d = new DirHandle $path; |
| 174 |
if (defined $d) { |
| 175 |
|
| 176 |
# iterate through all entries in $path ($d->read) and call out entry-handler on each entry |
| 177 |
while (defined(my $line = $d->read)) { |
| 178 |
entry_callback($line); |
| 179 |
} |
| 180 |
|
| 181 |
undef $d; |
| 182 |
} |
| 183 |
} |
| 184 |
|
| 185 |
sub getDirList { |
| 186 |
|
| 187 |
$dirlist_base = shift; |
| 188 |
|
| 189 |
# reset vars |
| 190 |
$dirlist_buf = ''; |
| 191 |
@dirlist_path = (); |
| 192 |
|
| 193 |
# start parsing file-structure |
| 194 |
iterate_path($dirlist_base); |
| 195 |
|
| 196 |
# return complete list of directory-content including files and subdirs |
| 197 |
# entries are newline (\n) - seperated |
| 198 |
return $dirlist_buf; |
| 199 |
|
| 200 |
} |
| 201 |
# ============================================= |
| 202 |
|
| 203 |
|
| 204 |
1; |
Parent Directory
| 
Revision Log
