From 272bdc15f634d3c05a3a1ed9efbf302259eeaaf9 Mon Sep 17 00:00:00 2001 From: Dobrica Pavlinusic Date: Mon, 5 Dec 2005 17:47:04 +0000 Subject: [PATCH] r11519@llin: dpavlin | 2005-12-05 00:20:06 +0100 partial changes to support multiple databases git-svn-id: svn+ssh://mjesec/home/dpavlin/svn/webpac2/trunk@210 07558da8-63fa-0310-ba24-9fe276d99e06 --- Makefile.PL | 5 +- conf/log.conf | 2 +- lib/WebPAC/Output/Estraier.pm | 81 +++++++++++++++++-- run.pl | 148 +++++++++++++++++++--------------- 4 files changed, 158 insertions(+), 78 deletions(-) diff --git a/Makefile.PL b/Makefile.PL index b61a01c..398467a 100644 --- a/Makefile.PL +++ b/Makefile.PL @@ -24,6 +24,7 @@ WriteMakefile( 'File::Temp' => 0, 'List::Util' => 0, 'URI::Escape' => 0, + 'LWP::Simple' => 0, }, dist => { COMPRESS => 'gzip -9f', SUFFIX => 'gz', }, clean => { FILES => 'WebPAC-* pod2html Makefile tags' }, @@ -52,8 +53,8 @@ sf: run: rm -f log test ! -e conf/config.yml && ln -s /data/Webpacus/config.yml conf/ || true - estcall raw -auth admin admin 'http://localhost:1978/master?action=nodedel&name=webpac2' || true - estcall raw -auth admin admin 'http://localhost:1978/master?action=nodeadd&name=webpac2&label=WebPAC%20test' || true + #estcall raw -auth admin admin 'http://localhost:1978/master?action=nodedel&name=webpac2' || true + #estcall raw -auth admin admin 'http://localhost:1978/master?action=nodeadd&name=webpac2&label=WebPAC%20test' || true ./run.pl MAKE_MORE diff --git a/conf/log.conf b/conf/log.conf index 24aac8f..e7dc254 100644 --- a/conf/log.conf +++ b/conf/log.conf @@ -28,7 +28,7 @@ log4perl.logger.main=INFO #log4perl.logger.WebPAC.Normalize.parse_to_arr=DEBUG #log4perl.logger.WebPAC.Output.TT=DEBUG -#log4perl.logger.WebPAC.Output.Estraier=DEBUG +log4perl.logger.WebPAC.Output.Estraier=DEBUG #log4perl.logger.WebPAC.Search.Estraier=DEBUG #log4perl.logger.WebPAC.Common=DEBUG diff --git a/lib/WebPAC/Output/Estraier.pm b/lib/WebPAC/Output/Estraier.pm index 871237f..83eae34 100644 --- a/lib/WebPAC/Output/Estraier.pm +++ b/lib/WebPAC/Output/Estraier.pm @@ -8,6 +8,8 @@ use base qw/WebPAC::Common/; use HyperEstraier; use Text::Iconv; use Data::Dumper; +use LWP::Simple; +use URI::Escape; =head1 NAME @@ -15,11 +17,11 @@ WebPAC::Output::Estraier - Create Hyper Estraier full text index =head1 VERSION -Version 0.01 +Version 0.02 =cut -our $VERSION = '0.01'; +our $VERSION = '0.02'; =head1 SYNOPSIS @@ -33,7 +35,7 @@ type C. Connect to Hyper Estraier index using HTTP my $est = new WebPAC::Output::Estraier( - url => 'http://localhost:1978/node/webpac2', + masterurl => 'http://localhost:1978/', user => 'admin', passwd => 'admin', database => 'demo', @@ -44,7 +46,7 @@ Options are: =over 4 -=item url +=item masterurl URI to C node @@ -79,14 +81,31 @@ sub new { my $log = $self->_get_logger; - foreach my $p (qw/url user passwd/) { + $log->debug("self: ", sub { Dumper($self) }); + + foreach my $p (qw/masterurl user passwd database/) { $log->logdie("need $p") unless ($self->{$p}); } - $log->info("opening Hyper Estraier index $self->{'url'}"); + my $url = $self->{masterurl} . '/node/' . $self->{database}; + $url =~ s#//#/#g; + $self->{url} = $url; + + $log->info("opening Hyper Estraier index $self->{url}"); - $self->{'db'} = HyperEstraier::Node->new($self->{'url'}); - $self->{'db'}->set_auth($self->{'user'}, $self->{'passwd'}); + my @nodes = $self->est_master( action => 'nodelist' ); + + if (! grep(/$self->{database}/, @nodes)) { + $log->info("creating index $url"); + $self->est_master( + action => 'nodeadd', + name => $self->{database}, + label => "WebPAC $self->{database}", + ) || $log->logdie("can't create Hyper Estraier node $self->{database}"); + } + + $self->{'db'} = HyperEstraier::Node->new($self->{url}); + $self->{'db'}->set_auth($self->{'user'}, $self->{passwd}); my $encoding = $self->{'encoding'} || 'ISO-8859-2'; $log->info("using encoding $encoding"); @@ -179,6 +198,52 @@ sub add { return 1; } +=head2 est_master + +Issue administrative commands to C process and receive response +as array of lines + + my $nodelist = $self->est_master( action => nodelist ); + +=cut + +my $estmaster_actions = { + userdel => [ qw/name/ ], + nodelist => [], + nodeadd => [ qw/name label/ ], + nodedel => [ qw/name/ ], +}; + +sub est_master { + my $self = shift; + my $args = {@_}; + my $log = $self->_get_logger; + + $log->debug(Dumper($args)); + + my $action = $args->{action} || $log->logconfess("no action specified"); + + $log->logdie("action '$action' isn't supported") unless ($estmaster_actions->{$action}); + + my $url = $self->{masterurl} . '/master?action=' . $action; + + foreach my $arg (@{ $estmaster_actions->{$action} }) { + $log->logdie("missing parametar $arg for action $action") unless ($args->{$arg}); + $url .= '&' . $arg . '=' . uri_escape( $args->{$arg} ); + } + + $log->debug("calling $url"); + + my $tsv = get($url); + + if (! $tsv) { + $log->warn("unable to call $url"); + return; + } + + return split(/\n/, $tsv); +} + =head1 AUTHOR Dobrica Pavlinusic, C<< >> diff --git a/run.pl b/run.pl index 6e47b6a..5a09b6b 100755 --- a/run.pl +++ b/run.pl @@ -12,8 +12,9 @@ use WebPAC::Input::ISIS; use WebPAC::Store 0.03; use WebPAC::Normalize::XML; use WebPAC::Output::TT; -use WebPAC::Output::Estraier; +use WebPAC::Output::Estraier 0.02; use YAML qw/LoadFile/; +use LWP::Simple; my $limit = shift @ARGV; @@ -21,94 +22,107 @@ my $config = LoadFile('conf/config.yml'); print "config = ",Dumper($config); -my $type = lc($config->{input}->{type}); +die "no databases in config file!\n" unless ($config->{databases}); -die "I know only how to handle input type isis, not '$type'!\n" unless ($type eq 'isis'); +while (my ($database, $db_config) = each %{ $config->{databases} }) { -my $abs_path = abs_path($0); -$abs_path =~ s#/[^/]*$#/#; + my $type = lc($db_config->{input}->{type}); -my $lookup = new WebPAC::Lookup( - lookup_file => $config->{input}->{lookup}, -); + die "I know only how to handle input type isis, not '$type'!\n" unless ($type eq 'isis'); + my $abs_path = abs_path($0); + $abs_path =~ s#/[^/]*$#/#; + my $lookup = new WebPAC::Lookup( + lookup_file => $db_config->{input}->{lookup}, + ); + + my $db_path = $config->{webpac}->{db_path} . '/' . $database; + + + my $log = $lookup->_get_logger; + $log->info("working on $database in $db_path"); + + my $isis = new WebPAC::Input::ISIS( + code_page => $config->{webpac}->{webpac_encoding}, + limit_mfn => $db_config->{input}->{limit}, + ); + + my $maxmfn = $isis->open( + filename => $db_config->{input}->{path}, + code_page => $db_config->{input}->{encoding}, # database encoding + ); -my $isis = new WebPAC::Input::ISIS( - code_page => $config->{webpac}->{webpac_encoding}, - limit_mfn => $config->{input}->{limit}, -); + my $path = './db/'; -my $maxmfn = $isis->open( - filename => $config->{input}->{path}, - code_page => $config->{input}->{encoding}, # database encoding -); + my $db = new WebPAC::Store( + path => $db_path, + ); -my $path = './db/'; + my $n = new WebPAC::Normalize::XML( + # filter => { 'foo' => sub { shift } }, + db => $db, + lookup_regex => $lookup->regex, + lookup => $lookup, + ); -my $db = new WebPAC::Store( - path => $config->{webpac}->{db_path}, -); + $n->open( + tag => $db_config->{normalize}->{tag}, + xml_file => $db_config->{normalize}->{path}, + ); -my $n = new WebPAC::Normalize::XML( -# filter => { 'foo' => sub { shift } }, - db => $db, - lookup_regex => $lookup->regex, - lookup => $lookup, -); + my $out = new WebPAC::Output::TT( + include_path => $config->{webpac}->{template_path}, + filters => { foo => sub { shift } }, + ); -$n->open( - tag => $config->{normalize}->{tag}, - xml_file => $config->{normalize}->{path}, -); + my $est_config = $config->{hyperestraier} || $log->logdie("can't find 'hyperestraier' part in confguration"); + $est_config->{database} = $database; -my $out = new WebPAC::Output::TT( - include_path => $config->{webpac}->{template_path}, - filters => { foo => sub { shift } }, -); + $log->info("using HyperEstraier URL $est_config->{url}"); -my $est = new WebPAC::Output::Estraier( - %{ $config->{hyperestraier} } -); + my $est = new WebPAC::Output::Estraier( + %{ $est_config }, + ); -my $total_rows = 0; + my $total_rows = 0; -for ( 0 ... $isis->size ) { + for ( 0 ... $isis->size ) { - my $row = $isis->fetch || next; + my $row = $isis->fetch || next; - my $mfn = $row->{'000'}->[0] || die "can't find MFN"; + my $mfn = $row->{'000'}->[0] || die "can't find MFN"; - my $ds = $n->data_structure($row); + my $ds = $n->data_structure($row); -# print STDERR Dumper($row, $ds); + # print STDERR Dumper($row, $ds); -# my $html = $out->apply( -# template => 'html_ffzg.tt', -# data => $ds, -# ); -# -# # create test output -# -# my $file = sprintf('out/%02d.html', $mfn ); -# open(my $fh, '>', $file) or die "can't open $file: $!"; -# print $fh $html; -# close($fh); -# -# $html =~ s#\s*[\n\r]+\s*##gs; -# -# print STDERR $html; + # my $html = $out->apply( + # template => 'html_ffzg.tt', + # data => $ds, + # ); + # + # # create test output + # + # my $file = sprintf('out/%02d.html', $mfn ); + # open(my $fh, '>', $file) or die "can't open $file: $!"; + # print $fh $html; + # close($fh); + # + # $html =~ s#\s*[\n\r]+\s*##gs; + # + # print STDERR $html; - $est->add( - id => $mfn, - ds => $ds, - type => $config->{hyperestraier}->{type}, - ); + $est->add( + id => $mfn, + ds => $ds, + type => $config->{hyperestraier}->{type}, + ); - $total_rows++; + $total_rows++; -}; + }; -my $log = $lookup->_get_logger; + $log->info("$total_rows records indexed"); +} -$log->info("$total_rows records indexed"); -- 2.20.1