| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Plucene::SearchEngine::Index::URL; |
|
2
|
1
|
|
|
1
|
|
1026
|
use base "Plucene::SearchEngine::Index::Base"; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
68
|
|
|
3
|
|
|
|
|
|
|
|
|
4
|
1
|
|
|
1
|
|
5
|
use strict; |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
30
|
|
|
5
|
1
|
|
|
1
|
|
4
|
use Carp; |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
56
|
|
|
6
|
1
|
|
|
1
|
|
4
|
use Time::Piece; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
8
|
|
|
7
|
1
|
|
|
1
|
|
76
|
use File::Temp; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
100
|
|
|
8
|
1
|
|
|
1
|
|
3415
|
use URI; |
|
|
1
|
|
|
|
|
12529
|
|
|
|
1
|
|
|
|
|
21
|
|
|
9
|
1
|
|
|
1
|
|
11339
|
use Date::Parse; |
|
|
1
|
|
|
|
|
9787
|
|
|
|
1
|
|
|
|
|
171
|
|
|
10
|
1
|
|
|
1
|
|
1345
|
use HTTP::Request; |
|
|
1
|
|
|
|
|
28026
|
|
|
|
1
|
|
|
|
|
15
|
|
|
11
|
1
|
|
|
1
|
|
3917
|
use LWP::UserAgent; |
|
|
1
|
|
|
|
|
26549
|
|
|
|
1
|
|
|
|
|
15
|
|
|
12
|
1
|
|
|
1
|
|
43
|
use File::Basename; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
100
|
|
|
13
|
1
|
|
|
1
|
|
6
|
use File::Temp qw(tempfile); |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
450
|
|
|
14
|
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
=head1 NAME |
|
16
|
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
Plucene::SearchEngine::Index::URL - File reader for web URLs |
|
18
|
|
|
|
|
|
|
|
|
19
|
|
|
|
|
|
|
=head1 DESCRIPTION |
|
20
|
|
|
|
|
|
|
|
|
21
|
|
|
|
|
|
|
This frontend module takes a URL, downloads its content, extracts its metadata |
|
22
|
|
|
|
|
|
|
and passes the file onto a backend. The frontend registers the following |
|
23
|
|
|
|
|
|
|
Plucene fields: |
|
24
|
|
|
|
|
|
|
|
|
25
|
|
|
|
|
|
|
=over 3 |
|
26
|
|
|
|
|
|
|
|
|
27
|
|
|
|
|
|
|
=item mimetype |
|
28
|
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
The MIME type of the data. |
|
30
|
|
|
|
|
|
|
|
|
31
|
|
|
|
|
|
|
=item filename |
|
32
|
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
The basename of the URL's filename. |
|
34
|
|
|
|
|
|
|
|
|
35
|
|
|
|
|
|
|
=item id |
|
36
|
|
|
|
|
|
|
|
|
37
|
|
|
|
|
|
|
The URL given. |
|
38
|
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
=item modified |
|
40
|
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
A Plucene date field representing the last modified date of the file |
|
42
|
|
|
|
|
|
|
|
|
43
|
|
|
|
|
|
|
=item language |
|
44
|
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
The ISO language identifier of the content |
|
46
|
|
|
|
|
|
|
|
|
47
|
|
|
|
|
|
|
=item encoding |
|
48
|
|
|
|
|
|
|
|
|
49
|
|
|
|
|
|
|
The original character set. (before conversion to UTF-8) |
|
50
|
|
|
|
|
|
|
|
|
51
|
|
|
|
|
|
|
=back |
|
52
|
|
|
|
|
|
|
|
|
53
|
|
|
|
|
|
|
=head2 METHODS |
|
54
|
|
|
|
|
|
|
|
|
55
|
|
|
|
|
|
|
Plucene::SearchEngine::Index::URL->examine($url); |
|
56
|
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
This downloads and examines a file on the filesystem for the above metadata, |
|
58
|
|
|
|
|
|
|
before handling it to a backend. |
|
59
|
|
|
|
|
|
|
|
|
60
|
|
|
|
|
|
|
=cut |
|
61
|
|
|
|
|
|
|
|
|
62
|
|
|
|
|
|
|
sub examine { |
|
63
|
0
|
|
|
0
|
0
|
|
my ($class, $url) = @_; |
|
64
|
0
|
|
|
|
|
|
my $ua = LWP::UserAgent->new; |
|
65
|
0
|
|
|
|
|
|
my $response = $ua->get($url); |
|
66
|
0
|
0
|
|
|
|
|
return unless $response->is_success; |
|
67
|
|
|
|
|
|
|
|
|
68
|
0
|
|
|
|
|
|
my $encoding = ""; |
|
69
|
0
|
|
|
|
|
|
my $filename = basename($url); # Hack, hack |
|
70
|
0
|
|
|
|
|
|
my $mime = $response->header("Content-Type"); |
|
71
|
0
|
|
|
|
|
|
$mime =~ s/;\s+(.*)//; |
|
72
|
0
|
|
|
|
|
|
my $rest = $1; |
|
73
|
0
|
|
|
|
|
|
my $self = $class->handler_for($filename, $mime)->new(); |
|
74
|
0
|
|
|
|
|
|
my $lm = $response->header("Last-Modified"); |
|
75
|
0
|
0
|
|
|
|
|
if ($rest =~ /charset=([\w\-]+)/) { $encoding = $1; } |
|
|
0
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
|
|
77
|
0
|
0
|
|
|
|
|
if (my $language =$response->header("Content-Language")) { |
|
78
|
0
|
|
|
|
|
|
$self->add_data("language", "Keyword", $language); |
|
79
|
|
|
|
|
|
|
} |
|
80
|
|
|
|
|
|
|
|
|
81
|
0
|
|
|
|
|
|
$self->add_data("mimetype", "Keyword", $mime); |
|
82
|
0
|
|
|
|
|
|
$self->add_data("id", "Keyword", $url); |
|
83
|
0
|
|
|
|
|
|
$self->add_data("filename", "Keyword", $filename); |
|
84
|
0
|
|
|
|
|
|
$self->add_data("modified", "Date", Time::Piece->new(str2time($lm))); |
|
85
|
|
|
|
|
|
|
|
|
86
|
0
|
|
|
|
|
|
my ($fh, $tmpfile) = tempfile(); |
|
87
|
0
|
0
|
|
|
|
|
if ($encoding) { |
|
88
|
0
|
|
|
|
|
|
require Encode; |
|
89
|
0
|
|
|
|
|
|
binmode $fh, ":utf8"; |
|
90
|
0
|
|
|
|
|
|
print $fh Encode::decode($encoding, $response->content); |
|
91
|
|
|
|
|
|
|
} else { |
|
92
|
0
|
|
|
|
|
|
print $fh $response->content; |
|
93
|
|
|
|
|
|
|
} |
|
94
|
0
|
|
|
|
|
|
close $fh; |
|
95
|
0
|
|
|
|
|
|
my @docs = $self->gather_data_from_file($tmpfile); |
|
96
|
0
|
0
|
|
|
|
|
if (@docs <2) { @docs = ($self) } |
|
|
0
|
|
|
|
|
|
|
|
97
|
0
|
0
|
|
|
|
|
if ($encoding) { |
|
98
|
0
|
|
|
|
|
|
$_->add_data("encoding", "Text", $encoding) for @docs; |
|
99
|
|
|
|
|
|
|
} |
|
100
|
0
|
|
|
|
|
|
unlink $tmpfile; |
|
101
|
0
|
0
|
|
|
|
|
if (wantarray) { return @docs } |
|
|
0
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
else { |
|
103
|
0
|
|
|
|
|
|
carp "Using ->examine in scalar context is deprecated"; |
|
104
|
0
|
|
|
|
|
|
return $docs[0]; |
|
105
|
|
|
|
|
|
|
} |
|
106
|
|
|
|
|
|
|
} |
|
107
|
|
|
|
|
|
|
|
|
108
|
|
|
|
|
|
|
1; |