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
|
#!/usr/bin/perl -w
# Copyright (C) 2007 Reini Urban
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as
# published by the Free Software Foundation; either version 2 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
=pod
=head1 NAME
wiki2omega [-u URL] WIKIDB
=over 4
=item B<WIKIDB>
The first argument may be a phpwiki url, a directory or a single file.
If it is an url the -url option is optional, otherwise mandatory.
=item B<-url>
The url prefix for the xapian database to be able to link to the result page.
=item B<-man>
Prints the manual page and exits.
=back
=head1 DESCRIPTION
Convert a phpwiki database to a format recognizable for xapian scriptindex,
to prepare a fulltext index.
=head1 SYNOPSIS
# serial dump (see config.ini for DEFAULT_DUMP_DIR)
DEFAULT_DUMP_DIR = /var/www/wikidb/pgsrc
lwp-request -d http://localhost/phpwiki/?action=dumpserial
wiki2omega -u wiki $DEFAULT_DUMP_DIR | \
scriptindex /var/lib/omega/data/wiki /usr/share/omega/wiki2omega.script
# zip dump
wiki2omega http://localhost/phpwiki/ | \
scriptindex /var/lib/omega/data/wiki /usr/share/omega/wiki2omega.script
# single file
wiki2omega -u wiki /tmp/wikidump/HomePage | \
scriptindex /var/lib/omega/data/wiki /usr/share/omega/wiki2omega.script
# real life usage
DEFAULT_DUMP_DIR = /var/www/wikidb/pgsrc
nice /usr/bin/lwp-request -P -d -m GET "http://localhost/wiki/?action=dumpserial"
nice wiki2omega -u /wiki $DEFAULT_DUMP_DIR | \
scriptindex /var/lib/omega/data/wiki /var/lib/omega/scripts/wiki2index.script \
> /var/log/omega/updateindex-wiki.log
=cut
use strict;
use Getopt::Long;
use Pod::Usage;
use Digest::MD5 qw(md5_hex);
use constant AZ_OK => 0;
my $man = 0;
my $help = 0;
my $db;
my $wikiurl;
GetOptions('help|?' => \$help,
'man' => \$man,
'url|u=s' => \$wikiurl,
) or pod2usage(2);
pod2usage(1) if $help;
pod2usage(-exitstatus => 0, -verbose => 2) if $man;
sub urldecode ($) {
my $s = shift;
$s =~ s/%([A-F0-9][A-F0-9])/chr(hex($1))/eg;
return $s;
}
sub p ($) {
# my $title = shift;
my $content = shift;
my $hdr = 1;
my $headers = '';
my %hdr;
return unless $content;
$hdr{md5} = md5_hex($content);
$hdr{size} = length($content);
$hdr{language} = 'english';
@_ = split(/\n/, $content);
LINE: while ($_ = shift @_) {
s/\r$//;
if ($hdr) {
if (/^$/) {
# headers finished, dump them
my $title = $hdr{title};
print "url=$wikiurl/$title\n";
for my $h (keys %hdr) {
print "$h=$hdr{$h}\n";
}
print "content";
$hdr = 0;
next LINE;
}
# ignore continuation lines
my $line = $_;
#while ($_ = shift @_) {
# s/\r$//;
# last unless /^[ \t]/;
# $line .= $_;
#}
if ($line =~ s/^Date:\s*(.*?)\s*$/$1/i) {
$hdr{date} = $line if length $line;
#print "date=$line\n" if length $line;
} elsif ($line =~ s/ pagename=(.*?);$/$1/) {
$hdr{title} = urldecode($line) if length $line;
} elsif ($line =~ s/ author=(.*?);$/$1/) {
$hdr{author} = urldecode($line) if length $line;
} elsif ($line =~ s/ lastmodified=(.*?);$/$1/) {
$hdr{lastmod} = $line if length $line;
$hdr{date} = $line if length $line;
}
} else {
# the rest is the content:
# gather headers
if (/^\s*\!+(.+)$/) {
$headers .= "$1 ";
}
print "=",$_,"\n";
}
}
print "headers=$headers" if $headers;
}
unless ($wikiurl) {
$wikiurl = $db = shift or die "Syntax: $0 WIKIURL\n";
} else {
$db = shift or die "Syntax: $0 -u WIKIURL DATABASE\n";
}
if ($db =~ /^http/) {
`wget -nv -O/tmp/wikidb.zip "$db?action=zip"`;
$db = "/tmp/wikidb.zip";
}
if ($db =~ /\.zip$/i) {
eval "require Archive::Zip;";
my $zip = Archive::Zip->new();
die 'wikidb.zip read error' unless $zip->read( $db ) == AZ_OK;
foreach my $member ($zip->members()) {
unless ($member->isDirectory()) {
my $page = $zip->contents($member);
p ($page);
print "\n";
}
}
} elsif (-d $db) {
local $/;
@_ = glob "$db/*";
while (my $filename = shift @_) {
open IN, "< $filename";
my $content = <IN>;
p ($content);
print "\n";
close IN;
}
} elsif (-f $db) {
local $/;
open IN, "< $db";
my $content = <IN>;
p ($content);
close IN;
print "\n";
} else {
die "invalid argument";
}
|
