[8520] | 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 |
|
---|
[12373] | 35 | use strict;
|
---|
[8520] | 36 | use util;
|
---|
| 37 |
|
---|
[12373] | 38 | my $PROGNAME = $0;
|
---|
| 39 | $PROGNAME =~ s/^.*\/(.*)$/$1/;
|
---|
[8520] | 40 |
|
---|
| 41 |
|
---|
[12848] | 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 |
|
---|
[8520] | 55 | sub open_java_lucene
|
---|
| 56 | {
|
---|
[12275] | 57 | my $full_indexdir = shift(@_);
|
---|
[12770] | 58 | my $fuzziness = shift(@_);
|
---|
[12408] | 59 | my $filter_string = shift(@_);
|
---|
[12373] | 60 | my $sort_field = shift(@_);
|
---|
[27069] | 61 | my $reverse_sort = shift(@_);
|
---|
[12373] | 62 | my $dco = shift(@_);
|
---|
[12656] | 63 | my $start_results = shift(@_);
|
---|
| 64 | my $end_results = shift(@_);
|
---|
[12373] | 65 | my $out_file = shift(@_);
|
---|
[12364] | 66 |
|
---|
[12848] | 67 | my $java = &get_java_path();
|
---|
[29144] | 68 | my $classpath = &util::filename_cat($ENV{'GSDLHOME'}, "bin", "java", "LuceneWrapper4.jar");
|
---|
| 69 | my $java_lucene = "\"$java\" -classpath \"$classpath\" org.greenstone.LuceneWrapper4.GS2LuceneQuery";
|
---|
[8520] | 70 |
|
---|
[12373] | 71 | my $cmd = "| " . $java_lucene . " \"" . $full_indexdir . "\"";
|
---|
[12770] | 72 | if (defined($fuzziness)) {
|
---|
| 73 | $cmd .= " -fuzziness " . $fuzziness;
|
---|
[9219] | 74 | }
|
---|
[12408] | 75 | if (defined($filter_string)) {
|
---|
| 76 | $cmd .= " -filter \"" . $filter_string . "\"";
|
---|
| 77 | }
|
---|
[12373] | 78 | if (defined($sort_field)) {
|
---|
[12364] | 79 | $cmd .= " -sort " . $sort_field;
|
---|
[12373] | 80 | }
|
---|
[27069] | 81 | if ($reverse_sort) {
|
---|
| 82 | $cmd .= " -reverse_sort";
|
---|
| 83 | }
|
---|
[12373] | 84 | if (defined($dco)) {
|
---|
[12364] | 85 | $cmd .= " -dco " . $dco;
|
---|
[12373] | 86 | }
|
---|
[12656] | 87 | if (defined($start_results)) {
|
---|
| 88 | $cmd .= " -startresults " . $start_results;
|
---|
| 89 | }
|
---|
| 90 | if (defined($end_results)) {
|
---|
| 91 | $cmd .= " -endresults " . $end_results;
|
---|
| 92 | }
|
---|
[12373] | 93 | if (defined($out_file)) {
|
---|
| 94 | $cmd .= " > \"" . $out_file . "\"";
|
---|
| 95 | }
|
---|
[27069] | 96 | print STDERR $cmd . "\n";
|
---|
[12364] | 97 |
|
---|
| 98 | if (!open (PIPEOUT, $cmd)) {
|
---|
[12373] | 99 | die "$PROGNAME - couldn't run $cmd\n";
|
---|
[8520] | 100 | }
|
---|
| 101 | }
|
---|
| 102 |
|
---|
| 103 | sub close_java_lucene
|
---|
| 104 | {
|
---|
| 105 | close(PIPEOUT);
|
---|
| 106 | }
|
---|
| 107 |
|
---|
| 108 | sub main
|
---|
| 109 | {
|
---|
| 110 | my (@argv) = @_;
|
---|
| 111 | my $argc = scalar(@argv);
|
---|
[12373] | 112 | if ($argc == 0) {
|
---|
[27069] | 113 | print STDERR "Usage: $PROGNAME full-index-dir [query] [-fuzziness value] [-filter filter_string] [-sort sort_field] [-reverse_sort] [-dco AND|OR] [-startresults number -endresults number] [-out out_file]\n";
|
---|
[12373] | 114 | exit 1;
|
---|
| 115 | }
|
---|
[8520] | 116 |
|
---|
[12373] | 117 | my $full_indexdir = shift(@argv);
|
---|
[8520] | 118 | my $query = undef;
|
---|
[12770] | 119 | my $fuzziness = undef;
|
---|
[12408] | 120 | my $filter_string = undef;
|
---|
[12275] | 121 | my $sort_field = undef;
|
---|
[27069] | 122 | my $reverse_sort = 0;
|
---|
[12373] | 123 | my $dco = undef;
|
---|
[12656] | 124 | my $start_results = undef;
|
---|
| 125 | my $end_results = undef;
|
---|
[9219] | 126 | my $out_file = undef;
|
---|
[12373] | 127 | for (my $i = 0; $i < scalar(@argv); $i++)
|
---|
| 128 | {
|
---|
[12770] | 129 | if ($argv[$i] eq "-fuzziness") {
|
---|
| 130 | $i++;
|
---|
| 131 | $fuzziness = $argv[$i];
|
---|
[12373] | 132 | }
|
---|
[12408] | 133 | elsif ($argv[$i] eq "-filter") {
|
---|
| 134 | $i++;
|
---|
| 135 | $filter_string = $argv[$i];
|
---|
| 136 | }
|
---|
[12373] | 137 | elsif ($argv[$i] eq "-sort") {
|
---|
| 138 | $i++;
|
---|
| 139 | $sort_field = $argv[$i];
|
---|
| 140 | }
|
---|
[27069] | 141 | elsif ($argv[$i] eq "-reverse_sort") {
|
---|
| 142 | $reverse_sort = 1;
|
---|
| 143 | }
|
---|
[12373] | 144 | elsif ($argv[$i] eq "-dco") {
|
---|
| 145 | $i++;
|
---|
| 146 | $dco = $argv[$i];
|
---|
| 147 | }
|
---|
[12656] | 148 | elsif ($argv[$i] eq "-startresults") {
|
---|
| 149 | $i++;
|
---|
| 150 | $start_results = $argv[$i];
|
---|
| 151 | }
|
---|
| 152 | elsif ($argv[$i] eq "-endresults") {
|
---|
| 153 | $i++;
|
---|
| 154 | $end_results = $argv[$i];
|
---|
| 155 | }
|
---|
[12373] | 156 | elsif ($argv[$i] eq "-out") {
|
---|
| 157 | $i++;
|
---|
| 158 | $out_file = $argv[$i];
|
---|
| 159 | }
|
---|
| 160 | else {
|
---|
| 161 | $query = $argv[$i];
|
---|
| 162 | }
|
---|
[8520] | 163 | }
|
---|
| 164 |
|
---|
[27069] | 165 | open_java_lucene($full_indexdir, $fuzziness, $filter_string, $sort_field, $reverse_sort, $dco, $start_results, $end_results, $out_file);
|
---|
[12373] | 166 |
|
---|
[8520] | 167 | if (defined $query) {
|
---|
| 168 | print PIPEOUT "$query\n";
|
---|
| 169 | }
|
---|
| 170 | else {
|
---|
| 171 | while (defined (my $line = <STDIN>)) {
|
---|
| 172 | print PIPEOUT $line;
|
---|
| 173 | }
|
---|
| 174 | }
|
---|
| 175 |
|
---|
| 176 | close_java_lucene();
|
---|
| 177 | }
|
---|
| 178 |
|
---|
| 179 | &main(@ARGV);
|
---|