1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
|
#!/usr/bin/perl
# xapian-omega search engine plugin
package IkiWiki::Plugin::search;
use warnings;
use strict;
use IkiWiki 2.00;
sub import { #{{{
hook(type => "checkconfig", id => "search", call => \&checkconfig);
hook(type => "pagetemplate", id => "search", call => \&pagetemplate);
hook(type => "sanitize", id => "search", call => \&index);
hook(type => "delete", id => "search", call => \&delete);
hook(type => "cgi", id => "search", call => \&cgi);
} # }}}
sub checkconfig () { #{{{
foreach my $required (qw(url cgiurl)) {
if (! length $config{$required}) {
error(sprintf(gettext("Must specify %s when using the search plugin"), $required));
}
}
if (! exists $config{omega_cgi}) {
$config{omega_cgi}="/usr/lib/cgi-bin/omega/omega";
}
} #}}}
my $form;
sub pagetemplate (@) { #{{{
my %params=@_;
my $page=$params{page};
my $template=$params{template};
# Add search box to page header.
if ($template->query(name => "searchform")) {
if (! defined $form) {
my $searchform = template("searchform.tmpl", blind_cache => 1);
$searchform->param(searchaction => $config{cgiurl});
$form=$searchform->output;
}
$template->param(searchform => $form);
}
} #}}}
my $scrubber;
my $stemmer;
sub index (@) { #{{{
my %params=@_;
return $params{content} if $IkiWiki::preprocessing{$params{destpage}};
setupfiles();
# A unique pageterm is used to identify the document for a page.
my $pageterm=pageterm($params{page});
return $params{content} unless defined $pageterm;
my $db=xapiandb();
my $doc=Search::Xapian::Document->new();
my $caption=IkiWiki::pagetitle($params{page});
my $title;
if (exists $pagestate{$params{page}}{meta} &&
exists $pagestate{$params{page}}{meta}{title}) {
$title=$pagestate{$params{page}}{meta}{title};
}
else {
$title=$caption;
}
# Remove html from text to be indexed.
if (! defined $scrubber) {
eval q{use HTML::Scrubber};
if (! $@) {
$scrubber=HTML::Scrubber->new(allow => []);
}
}
my $toindex = defined $scrubber ? $scrubber->scrub($params{content}) : $params{content};
# Take 512 characters for a sample, then extend it out
# if it stopped in the middle of a word.
my $size=512;
my ($sample)=substr($toindex, 0, $size);
if (length($sample) == $size) {
my $max=length($toindex);
my $next;
while ($size < $max &&
($next=substr($toindex, $size++, 1)) !~ /\s/) {
$sample.=$next;
}
}
$sample=~s/\n/ /g;
# data used by omega
# Decode html entities in it, since omega re-encodes them.
eval q{use HTML::Entities};
$doc->set_data(
"url=".urlto($params{page}, "")."\n".
"sample=".decode_entities($sample)."\n".
"caption=".decode_entities($caption)."\n".
"modtime=$IkiWiki::pagemtime{$params{page}}\n".
"size=".length($params{content})."\n"
);
# Index document and add terms for other metadata.
my $tg = Search::Xapian::TermGenerator->new();
if (! $stemmer) {
my $langcode=$ENV{LANG} || "en";
$langcode=~s/_.*//;
eval { $stemmer=Search::Xapian::Stem->new($langcode) };
if ($@) {
$stemmer=Search::Xapian::Stem->new("english");
}
}
$tg->set_stemmer($stemmer);
$tg->set_document($doc);
$tg->index_text($params{page}, 2);
$tg->index_text($caption, 2);
$tg->index_text($title, 2) if $title ne $caption;
$tg->index_text($toindex);
$tg->index_text(lc($title), 1, "ZS"); # for title:foo
foreach my $link (@{$links{$params{page}}}) {
$tg->index_text(lc($link), 1, "ZLINK"); # for link:bar
}
$doc->add_term($pageterm);
$db->replace_document_by_term($pageterm, $doc);
return $params{content};
} #}}}
sub delete (@) { #{{{
my $db=xapiandb();
foreach my $page (@_) {
my $pageterm=pageterm(pagename($page));
$db->delete_document_by_term($pageterm) if defined $pageterm;
}
} #}}}
sub cgi ($) { #{{{
my $cgi=shift;
if (defined $cgi->param('P')) {
# only works for GET requests
chdir("$config{wikistatedir}/xapian") || error("chdir: $!");
$ENV{OMEGA_CONFIG_FILE}="./omega.conf";
$ENV{CGIURL}=$config{cgiurl},
IkiWiki::loadindex();
$ENV{HELPLINK}=htmllink("", "", "ikiwiki/searching",
noimageinline => 1, linktext => "Help");
exec($config{omega_cgi}) || error("$config{omega_cgi} failed: $!");
}
} #}}}
sub pageterm ($) { #{{{
my $page=shift;
# 240 is the number used by omindex to decide when to hash an
# overlong term. This does not use a compatible hash method though.
if (length $page > 240) {
eval q{use Digest::SHA1};
if ($@) {
debug("search: ".sprintf(gettext("need Digest::SHA1 to index %s"), $page)) if $@;
return undef;
}
# Note no colon, therefore it's guaranteed to not overlap
# with a page with the same name as the hash..
return "U".lc(Digest::SHA1::sha1_hex($page));
}
else {
return "U:".$page;
}
} #}}}
my $db;
sub xapiandb () { #{{{
if (! defined $db) {
eval q{
use Search::Xapian;
use Search::Xapian::WritableDatabase;
};
error($@) if $@;
$db=Search::Xapian::WritableDatabase->new($config{wikistatedir}."/xapian/default",
Search::Xapian::DB_CREATE_OR_OPEN());
}
return $db;
} #}}}
sub setupfiles () { #{{{
if (! -e $config{wikistatedir}."/xapian" || $config{rebuild}) {
writefile("omega.conf", $config{wikistatedir}."/xapian",
"database_dir .\n".
"template_dir ./templates\n");
writefile("query", $config{wikistatedir}."/xapian/templates",
IkiWiki::misctemplate(gettext("search"),
readfile(IkiWiki::template_file("searchquery.tmpl"))));
}
} #}}}
1
|