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
|
#!@@perlbinary@@ -w
use strict;
# This is set to where Swish-e's "make install" installed the helper modules.
use lib qw( @@perlmoduledir@@ );
use SWISH::Filter;
=pod
This is an example of how to use the SWISH::Filter module to filter
documents using Swish-e's C<FileFilter> feature. This will filter any
number of document types, depending on what filter modules are installed.
This program should typically only be used for the -S fs indexing method.
For -S http the F<swishspider> program calls SWISH::Filter directly. And -S
prog programs written in Perl can also make use of SWISH::Filter directly.
In general, you will not want to filter with this program if you have a lot
of files to filter. Running a perl program for many documents will be slow
(due to the compiliation of the perl program). If you have many documents
to convert with the -S fs method of indexing then consider using -S prog
with F<prog-bin/DirTree.pl> and use the SWISH::Filter module (see
F<filters/README>).
Swish-e configuration:
FileFilter .pdf /path/to/swish_filter.pl
FileFilter .doc /path/to/swish_filter.pl
FileFilter .mp3 /path/to/swish_filter.pl
IndexContents HTML2 .pdf .mp3
IndexContents TXT2 .doc
Then when indexing those type of documents this program will attempt to filter (convert)
them into a text format.
See SWISH-CONFIG documentation on Filtering for more information.
=cut
my ( $work_path, $real_path ) = @ARGV;
my $filter = SWISH::Filter->new;
my $filtered = $filter->filter(
document => $work_path,
name => $real_path,
content_type => \$real_path, # use the real path to lookup the content type
);
print STDERR $filtered ? " - Filtered: $real_path\n" : " - Not filtered: $real_path ($work_path)\n";
print $filtered
? ${$filter->fetch_doc}
: $real_path;
|
