--- trunk/PlusPlus.pm 2004/12/05 12:48:00 10
+++ trunk/PlusPlus.pm 2004/12/05 15:35:53 14
@@ -4,7 +4,7 @@
use strict;
use warnings;
-our $VERSION = '0.04';
+our $VERSION = '0.06';
use Carp;
use File::Temp qw/ tempdir /;
@@ -90,15 +90,27 @@
croak "need $_" unless $self->{$_};
}
- if (! -e $self->{'index_dir'}) {
- mkdir $self->{'index_dir'} || confess "can't create index ",$self->{'index'},": $!";
+ my $index_dir = $self->{'index_dir'};
+
+ my $cwd;
+ chomp($cwd = `pwd`);
+ $self->{'cwd'} = $cwd || carp "can't get cwd!";
+
+ if ($index_dir !~ m#^/#) {
+ $index_dir = "$cwd/$index_dir";
+ print STDERR "## full path to index_dir: $index_dir\n" if ($self->{'debug'});
+ $self->{'index_dir'} = $index_dir;
+ }
+
+ if (! -e $index_dir) {
+ mkdir $index_dir || confess "can't create index ",$self->{'index'},": $!";
}
# default executables
$self->{'index'} ||= 'index';
$self->{'search'} ||= 'search';
- print STDERR "## new index_dir: ",$self->{'index_dir'}," index: ",$self->{'index'}, " search: ",$self->{'search'},"\n" if ($self->{'debug'});
+ print STDERR "## new index_dir: ",$index_dir," index: ",$self->{'index'}, " search: ",$self->{'search'},"\n" if ($self->{'debug'});
$self ? return $self : return undef;
}
@@ -134,6 +146,7 @@
confess $self->{'search'}," binary is not SWISH++" unless ($s =~ m/^SWISH\+\+/);
if ($i eq $s) {
+ $i =~ s/^SWISH\+\+\s+// || confess "can't strip SWISH++ from version";
$self->{'version'} = $i;
return 1;
} else {
@@ -208,7 +221,7 @@
my $query = shift || return;
- $self->_close_index;
+ $self->finish_update;
my @results;
@@ -239,6 +252,29 @@
return @results;
}
+=head2 finish_update
+
+This method will close index.
+
+ $i->finish_update;
+
+It will be called on DESTROY when $i goes out of scope.
+
+=cut
+
+sub finish_update {
+ my $self = shift;
+
+ print STDERR "## finish_update\n" if ($self->{'debug'});
+
+ $self->_close_index;
+}
+
+sub DESTROY {
+ my $self = shift;
+ $self->finish_update;
+}
+
=head1 PRIVATE METHODS
Private methods implement internals for creating temporary file needed for
@@ -259,11 +295,16 @@
sub _init_indexer {
my $self = shift;
- $self->{'tmp_dir'} = tempdir( CLEANUP => 1 ) || confess "can't create temporary directory: $!";
+ return if ($self->{'_index_fh'});
- chdir $self->{'tmp_dir'} || confess "can't chdir to ".$self->{'tmp_dir'}.": $!";
+ my $tmp_dir = tempdir( CLEANUP => 1 ) || confess "can't create temporary directory: $!";
+ $self->{'tmp_dir'} = $tmp_dir;
- my $opt = "-v 4";
+ chdir $tmp_dir || confess "can't chdir to ".$tmp_dir.": $!";
+
+ print STDERR "## tmp_dir: $tmp_dir" if ($self->{'debug'});
+
+ my $opt = "-v " . ($self->{'debug'} || '0');
unless ($self->{'use_stopwrods'}) {
open(STOP, '>', "_stopwords_") || carp "can't create empty stopword file, skipping\n";
@@ -274,11 +315,13 @@
my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$self->{'index_dir'}.'/index -';
+ print STDERR "## init_indexer: $open_cmd\n" if ($self->{'debug'});
- open($self->{'index_fh'}, $open_cmd) || confess "can't start index with $open_cmd: $!";
+ open($self->{'_index_fh'}, $open_cmd) || confess "can't start index with $open_cmd: $!";
+ chdir $self->{'cwd'} || confess "can't chdir to ".$self->{'cwd'}.": $!";
- return $self->{'index_fh'};
+ return $self->{'_index_fh'};
}
=head2 _create_doc
@@ -305,18 +348,25 @@
my $arg = {@_};
# open indexer if needed
- $self->{'index_fh'} ||= $self->_init_indexer;
+ $self->_init_indexer;
my $path = $self->{'tmp_dir'} || confess "no tmp_dir?";
+ $path .= '/' . $arg->{'path'};
+
+ print STDERR "## _create_doc: $path\n" if ($self->{'debug'});
- open(TMP, '>', $arg->{'path'}) || die "can't create temp file ".$arg->{'path'}.": $!";
+ open(TMP, '>', $path) || die "can't create temp file $path: $!";
print TMP '';
$arg->{'body'} ||= '';
if ($arg->{'meta'}) {
- confess "not yet implemented";
+ foreach my $name (keys %{$arg->{'meta'}}) {
+ my $content = $arg->{'meta'}->{$name};
+ print TMP qq{};
+ $arg->{'body'} .= " $content" if ($self->{'meta_in_body'});
+ }
}
if (defined($arg->{'title'})) {
@@ -328,7 +378,7 @@
close(TMP) || confess "can't close tmp file ".$arg->{'path'}.": $!";
- print { $self->{'index_fh'} } $arg->{'path'}."\n";
+ print { $self->{'_index_fh'} } $arg->{'path'}."\n";
}
=head2 _close_index
@@ -344,12 +394,12 @@
sub _close_index {
my $self = shift;
- return unless ($self->{'index_fh'});
+ return unless ($self->{'_index_fh'});
print STDERR "## close index\n" if ($self->{'debug'});
- close($self->{'index_fh'});
- undef $self->{'index_fh'};
+ close($self->{'_index_fh'});
+ undef $self->{'_index_fh'};
}
1;
@@ -390,6 +440,14 @@
pages. To see my very relaxed sample configuration take a look at C
directory included in distribution.
+=head2 SWISH++ config
+
+C located in C directory of this distribution is relaxed
+SWISH++ configuration that will index all words passed to it. This
+configuration is needed for B because default configuration
+doesn't recognize 2004-12-05 as date. Have in mind that your index size
+might explode.
+
=head1 SEE ALSO
C web site L