1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # lucene_query.pl -- perl wrapper to initiate query using Lucene
|
---|
6 | # A component of the Greenstone digital library software
|
---|
7 | # from the New Zealand Digital Library Project at the
|
---|
8 | # University of Waikato, New Zealand.
|
---|
9 | #
|
---|
10 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful,
|
---|
18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | # GNU General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 |
|
---|
29 | BEGIN {
|
---|
30 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
31 | die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
|
---|
32 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
33 | }
|
---|
34 |
|
---|
35 | use strict;
|
---|
36 | use util;
|
---|
37 |
|
---|
38 | my $PROGNAME = $0;
|
---|
39 | $PROGNAME =~ s/^.*\/(.*)$/$1/;
|
---|
40 |
|
---|
41 |
|
---|
42 | sub get_java_path()
|
---|
43 | {
|
---|
44 | # Check the JAVA_HOME environment variable first
|
---|
45 | if (defined $ENV{'JAVA_HOME'}) {
|
---|
46 | my $java_home = $ENV{'JAVA_HOME'};
|
---|
47 | $java_home =~ s/\/$//; # Remove trailing slash if present (Unix specific)
|
---|
48 | return &util::filename_cat($java_home, "bin", "java");
|
---|
49 | }
|
---|
50 |
|
---|
51 | # Hope that Java is on the PATH
|
---|
52 | return "java";
|
---|
53 | }
|
---|
54 |
|
---|
55 | sub open_java_lucene
|
---|
56 | {
|
---|
57 | my $full_indexdir = shift(@_);
|
---|
58 | my $fuzziness = shift(@_);
|
---|
59 | my $filter_string = shift(@_);
|
---|
60 | my $sort_field = shift(@_);
|
---|
61 | my $dco = shift(@_);
|
---|
62 | my $start_results = shift(@_);
|
---|
63 | my $end_results = shift(@_);
|
---|
64 | my $out_file = shift(@_);
|
---|
65 |
|
---|
66 | my $java = &get_java_path();
|
---|
67 | my $classpath = &util::filename_cat($ENV{'GSDLHOME'}, "bin", "java", "LuceneWrapper.jar");
|
---|
68 | my $java_lucene = "\"$java\" -classpath \"$classpath\" org.greenstone.LuceneWrapper.GS2LuceneQuery";
|
---|
69 |
|
---|
70 | my $cmd = "| " . $java_lucene . " \"" . $full_indexdir . "\"";
|
---|
71 | if (defined($fuzziness)) {
|
---|
72 | $cmd .= " -fuzziness " . $fuzziness;
|
---|
73 | }
|
---|
74 | if (defined($filter_string)) {
|
---|
75 | $cmd .= " -filter \"" . $filter_string . "\"";
|
---|
76 | }
|
---|
77 | if (defined($sort_field)) {
|
---|
78 | $cmd .= " -sort " . $sort_field;
|
---|
79 | }
|
---|
80 | if (defined($dco)) {
|
---|
81 | $cmd .= " -dco " . $dco;
|
---|
82 | }
|
---|
83 | if (defined($start_results)) {
|
---|
84 | $cmd .= " -startresults " . $start_results;
|
---|
85 | }
|
---|
86 | if (defined($end_results)) {
|
---|
87 | $cmd .= " -endresults " . $end_results;
|
---|
88 | }
|
---|
89 | if (defined($out_file)) {
|
---|
90 | $cmd .= " > \"" . $out_file . "\"";
|
---|
91 | }
|
---|
92 | # print STDERR $cmd . "\n";
|
---|
93 |
|
---|
94 | if (!open (PIPEOUT, $cmd)) {
|
---|
95 | die "$PROGNAME - couldn't run $cmd\n";
|
---|
96 | }
|
---|
97 | }
|
---|
98 |
|
---|
99 | sub close_java_lucene
|
---|
100 | {
|
---|
101 | close(PIPEOUT);
|
---|
102 | }
|
---|
103 |
|
---|
104 | sub main
|
---|
105 | {
|
---|
106 | my (@argv) = @_;
|
---|
107 | my $argc = scalar(@argv);
|
---|
108 | if ($argc == 0) {
|
---|
109 | print STDERR "Usage: $PROGNAME full-index-dir [query] [-fuzziness value] [-filter filter_string] [-sort sort_field] [-dco AND|OR] [-startresults number -endresults number] [-out out_file]\n";
|
---|
110 | exit 1;
|
---|
111 | }
|
---|
112 |
|
---|
113 | my $full_indexdir = shift(@argv);
|
---|
114 | my $query = undef;
|
---|
115 | my $fuzziness = undef;
|
---|
116 | my $filter_string = undef;
|
---|
117 | my $sort_field = undef;
|
---|
118 | my $dco = undef;
|
---|
119 | my $start_results = undef;
|
---|
120 | my $end_results = undef;
|
---|
121 | my $out_file = undef;
|
---|
122 | for (my $i = 0; $i < scalar(@argv); $i++)
|
---|
123 | {
|
---|
124 | if ($argv[$i] eq "-fuzziness") {
|
---|
125 | $i++;
|
---|
126 | $fuzziness = $argv[$i];
|
---|
127 | }
|
---|
128 | elsif ($argv[$i] eq "-filter") {
|
---|
129 | $i++;
|
---|
130 | $filter_string = $argv[$i];
|
---|
131 | }
|
---|
132 | elsif ($argv[$i] eq "-sort") {
|
---|
133 | $i++;
|
---|
134 | $sort_field = $argv[$i];
|
---|
135 | }
|
---|
136 | elsif ($argv[$i] eq "-dco") {
|
---|
137 | $i++;
|
---|
138 | $dco = $argv[$i];
|
---|
139 | }
|
---|
140 | elsif ($argv[$i] eq "-startresults") {
|
---|
141 | $i++;
|
---|
142 | $start_results = $argv[$i];
|
---|
143 | }
|
---|
144 | elsif ($argv[$i] eq "-endresults") {
|
---|
145 | $i++;
|
---|
146 | $end_results = $argv[$i];
|
---|
147 | }
|
---|
148 | elsif ($argv[$i] eq "-out") {
|
---|
149 | $i++;
|
---|
150 | $out_file = $argv[$i];
|
---|
151 | }
|
---|
152 | else {
|
---|
153 | $query = $argv[$i];
|
---|
154 | }
|
---|
155 | }
|
---|
156 |
|
---|
157 | open_java_lucene($full_indexdir, $fuzziness, $filter_string, $sort_field, $dco, $start_results, $end_results, $out_file);
|
---|
158 |
|
---|
159 | if (defined $query) {
|
---|
160 | print PIPEOUT "$query\n";
|
---|
161 | }
|
---|
162 | else {
|
---|
163 | while (defined (my $line = <STDIN>)) {
|
---|
164 | print PIPEOUT $line;
|
---|
165 | }
|
---|
166 | }
|
---|
167 |
|
---|
168 | close_java_lucene();
|
---|
169 | }
|
---|
170 |
|
---|
171 | &main(@ARGV);
|
---|