1 |
cvsjoko |
1.1 |
################################# |
2 |
|
|
# |
3 |
cvsjoko |
1.3 |
# $Id: libp.pm,v 1.2 2002/06/27 02:14:22 cvsjoko Exp $ |
4 |
cvsjoko |
1.2 |
# |
5 |
|
|
# $Log: libp.pm,v $ |
6 |
cvsjoko |
1.3 |
# Revision 1.2 2002/06/27 02:14:22 cvsjoko |
7 |
|
|
# + stripHtml stripSpaces stripNewLines toReal |
8 |
|
|
# |
9 |
cvsjoko |
1.2 |
# Revision 1.1 2002/06/24 14:49:59 cvsjoko |
10 |
|
|
# + new |
11 |
cvsjoko |
1.1 |
# |
12 |
|
|
# |
13 |
|
|
################################# |
14 |
|
|
|
15 |
|
|
package libp; |
16 |
|
|
|
17 |
|
|
require Exporter; |
18 |
|
|
@ISA = qw( Exporter ); |
19 |
|
|
@EXPORT = qw( |
20 |
cvsjoko |
1.3 |
Dumper |
21 |
|
|
md5 md5_hex md5_base64 |
22 |
|
|
ParseDate UnixDate |
23 |
|
|
strftime |
24 |
|
|
stripHtml stripSpaces stripNewLines toReal trim |
25 |
|
|
croak |
26 |
|
|
array_getDifference |
27 |
cvsjoko |
1.1 |
); |
28 |
|
|
|
29 |
|
|
use strict; |
30 |
|
|
use warnings; |
31 |
|
|
|
32 |
|
|
use Data::Dumper; |
33 |
|
|
use Digest::MD5 qw(md5 md5_hex md5_base64); |
34 |
|
|
|
35 |
|
|
$main::TZ = 'GMT'; |
36 |
|
|
use Date::Manip; |
37 |
cvsjoko |
1.2 |
|
38 |
|
|
require LWP::UserAgent; |
39 |
|
|
use HTML::PullParser; |
40 |
|
|
|
41 |
cvsjoko |
1.3 |
# $now_string = strftime "%a %b %e %H:%M:%S %Y", localtime; |
42 |
|
|
# see "perldoc -f localtime" |
43 |
|
|
use POSIX qw(strftime); |
44 |
|
|
|
45 |
|
|
use Carp; |
46 |
|
|
|
47 |
cvsjoko |
1.2 |
|
48 |
|
|
######################################## |
49 |
|
|
|
50 |
|
|
sub stripSpaces { |
51 |
|
|
my $text = shift; |
52 |
|
|
#print "text: $text", "\n"; |
53 |
|
|
#print "ord: ", ord(substr($text, 0, 1)), "\n"; |
54 |
|
|
$text =~ s/^\s*//g; |
55 |
|
|
$text =~ s/\s*$//g; |
56 |
|
|
return $text; |
57 |
|
|
} |
58 |
|
|
|
59 |
cvsjoko |
1.3 |
sub trim { |
60 |
|
|
my $string = shift; |
61 |
|
|
return stripSpaces($string); |
62 |
|
|
} |
63 |
|
|
|
64 |
cvsjoko |
1.2 |
sub stripNewLines { |
65 |
|
|
my $text = shift; |
66 |
|
|
#print "text: $text", "\n"; |
67 |
|
|
#print "ord: ", ord(substr($text, 0, 1)), "\n"; |
68 |
|
|
$text =~ s/\n//g; |
69 |
|
|
#$text =~ s/\s*$//g; |
70 |
|
|
return $text; |
71 |
|
|
} |
72 |
|
|
|
73 |
|
|
sub toReal { |
74 |
|
|
my $string = shift; |
75 |
|
|
$string =~ m/(\d+\.*\d+)/; |
76 |
|
|
my $real = $1; |
77 |
|
|
return $real; |
78 |
|
|
} |
79 |
|
|
|
80 |
|
|
sub stripHtml { |
81 |
|
|
my $html = shift; |
82 |
|
|
my $result = ''; |
83 |
|
|
#$html =~ s/<br>(.*)/ - ($1)/i; |
84 |
|
|
my $p = HTML::PullParser->new( |
85 |
|
|
doc => \$html, |
86 |
|
|
text => 'text', |
87 |
|
|
unbroken_text => 1, |
88 |
|
|
); |
89 |
|
|
while (my $token = $p->get_token()) { |
90 |
|
|
my $text = join('', @{$token}); |
91 |
|
|
$result .= $text; |
92 |
|
|
} |
93 |
|
|
#$result =~ s/ //g; |
94 |
|
|
return $result; |
95 |
cvsjoko |
1.3 |
} |
96 |
|
|
|
97 |
|
|
sub array_getRelations { |
98 |
|
|
my $a_ref = shift; |
99 |
|
|
my $b_ref = shift; |
100 |
|
|
my @a = @{$a_ref}; |
101 |
|
|
my @b = @{$b_ref}; |
102 |
|
|
|
103 |
|
|
my @isect = my @diff = my @union = (); |
104 |
|
|
my $e; |
105 |
|
|
my %count; |
106 |
|
|
|
107 |
|
|
foreach $e (@a, @b) { $count{$e}++ } |
108 |
|
|
|
109 |
|
|
foreach $e (keys %count) { |
110 |
|
|
push(@union, $e); |
111 |
|
|
push @{ $count{$e} == 2 ? \@isect : \@diff }, $e; |
112 |
|
|
} |
113 |
|
|
|
114 |
|
|
my $result = { |
115 |
|
|
union => \@union, |
116 |
|
|
isect => \@isect, |
117 |
|
|
diff => \@diff, |
118 |
|
|
}; |
119 |
|
|
|
120 |
|
|
} |
121 |
|
|
|
122 |
|
|
sub array_getDifference { |
123 |
|
|
my $res = array_getRelations(shift, shift); |
124 |
|
|
return $res->{diff}; |
125 |
cvsjoko |
1.2 |
} |
126 |
cvsjoko |
1.1 |
|
127 |
|
|
1; |