/[Grep]/lib/Grep/Import/ScrapBook.pm
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Contents of /lib/Grep/Import/ScrapBook.pm

Parent Directory Parent Directory | Revision Log Revision Log


Revision 155 - (show annotations)
Sun Jun 10 19:20:59 2007 UTC (16 years, 8 months ago) by dpavlin
File size: 2859 byte(s)
hush debugging, Import plugin now returns stats for better reporting
1 #!/usr/bin/perl
2
3 use warnings;
4 use strict;
5
6 package Grep::Import::ScrapBook;
7
8 =head1 NAME
9
10 Grep::Import::ScrapBook - importer for local ScrapBook pages
11
12 =head1 CONFIGURATION
13
14 You can symlink your ScrapBook directory
15
16 ~/Grep/share/web/static$ ln -sf /home/dpavlin/private/ScrapBook scrapbook
17
18 or modify L<ScrapBookDir> path (relative to Grep installation static root).
19
20 =cut
21
22 use XML::Simple;
23 use File::Slurp;
24 use Data::Dump qw/dump/;
25
26 sub import {
27 my $self = shift;
28 my $search = shift or die "need search";
29 die "search is ", ref($search), " and not Grep::Search" unless ($search->isa('Grep::Search'));
30
31 my $dir =
32 Jifty::Util->app_root . '/' .
33 Jifty->config->framework('Web')->{'StaticRoot'} . '/' .
34 Jifty->config->app('ScrapBookDir');
35
36 my $path = $dir . '/scrapbook.rdf';
37 $path =~ s!//+!/!g;
38
39 if ( ! -e $dir || ! -e $path ) {
40 Jifty->log->warn("Skipping ScrapBook import $path: $!");
41 return 1;
42 }
43
44 my $rdf = XMLin(
45 $path,
46 # KeyAttr => [ qw/RDF:about/ ],
47 ) || die "can't open $path: $!";
48
49 # warn "## original rdf -> ", dump( $rdf );
50
51 my $feed = Grep::Model::Feed->new();
52 $feed->load_or_create(
53 uri => 'file://' . $path,
54 title => 'ScrapBook',
55 #source => 'Grep::Source',
56 );
57
58 my $stats;
59
60 foreach my $item ( @{ $rdf->{'RDF:Description'} } ) {
61
62 $stats->{total}++;
63
64 #warn "## item = ",dump( $item );
65
66 my $hash;
67 foreach my $k ( keys %$item ) {
68 next if $k =~ m/^RDF:/;
69 next if ( $item->{$k} eq '' );
70 my $n = $k;
71 $n =~ s/^\w+://; # strip namespace
72 $hash->{$n} = $item->{$k};
73 }
74
75 #warn "## hash = ", dump( $hash );
76
77
78 # fetch full-text content and import it
79
80 my $content_path = $dir . '/data/' . $hash->{id} . '/index.html';
81 if ( ! -r $content_path ) {
82 Jifty->log->warn("can't import $content_path: $!");
83 $stats->{failure}++;
84 next;
85 }
86 my $content = read_file( $content_path ) or
87 die "can't read $content_path: $!";
88
89
90 # create date from id
91
92 my $dt;
93 if ( $hash->{id} =~ m/^(\d{4})(\d\d)(\d\d)(\d\d)(\d\d)(\d\d)$/ ) {
94 $dt = DateTime->new(
95 year => $1,
96 month => $2,
97 day => $3,
98 hour => $4,
99 minute => $5,
100 second => $6,
101 #time_zone => 'UTC',
102 );
103 } else {
104 warn "can't parse date from ", $hash->{id};
105 }
106
107 my $i = Grep::Model::Item->new();
108 my ($ok,$msg) = $i->load_or_create(
109 in_feed => $feed,
110 title => $hash->{title},
111 link => $hash->{source},
112 content => $content,
113 issued => $hash->{id},
114 );
115
116 if ( ! $ok ) {
117 Jifty->log->error( $msg );
118 $stats->{failure}++;
119 next;
120 }
121
122 if ( $msg && $msg =~ m/^Found/ ) {
123 $stats->{old}++;
124 } else {
125 $stats->{new}++;
126 Jifty->log->info("imported ", $i->id ," ", $i->link, " ", length( $content ), " bytes");
127 $search->add( $i, $i->in_feed->owner->id );
128 }
129
130 }
131
132 return $stats;
133 }
134
135 =head1 SEE ALSO
136
137 L<http://amb.vis.ne.jp/mozilla/scrapbook/> - ScrapBook FireFox extension
138
139 =cut
140
141 1;

  ViewVC Help
Powered by ViewVC 1.1.26