t/db_dependent/www/search_utf8.t

   1 #!/usr/bin/perl
   2
   3 # This file is part of Koha.
   4 #
   5 # Koha is free software; you can redistribute it and/or modify it
   6 # under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 3 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # Koha is distributed in the hope that it will be useful, but
  11 # WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License
  16 # along with Koha; if not, see <http://www.gnu.org/licenses>.
  17
  18 use Modern::Perl;
  19
  20 use utf8;
  21 use Test::More; #See plan tests => \d+ below
  22 use Test::WWW::Mechanize;
  23 use Data::Dumper;
  24 use XML::Simple;
  25 use JSON;
  26 use File::Basename;
  27 use File::Path;
  28 use File::Spec;
  29 use File::Temp qw/ tempdir /;
  30 use POSIX;
  31 use Encode;
  32 use URI::Escape;
  33
  34 use C4::Context;
  35
  36 my $testdir = File::Spec->rel2abs( dirname(__FILE__) );
  37 # global variables that will be used when forking
  38 our $zebra_pid;
  39 our $indexer_pid;
  40 our $datadir = tempdir();;
  41
  42 my $koha_conf = $ENV{KOHA_CONF};
  43 my $xml       = XMLin($koha_conf);
  44
  45 my $marcflavour = C4::Context->preference('marcflavour') || 'MARC21';
  46
  47 # For the purpose of this test, we can reasonably take MARC21 and NORMARC to be the same
  48 my $file1 =
  49   $marcflavour eq 'UNIMARC'
  50   ? "$testdir/data/unimarcutf8record.mrc"
  51   : "$testdir/data/marc21utf8record.mrc";
  52
  53 my $file2 =
  54   $marcflavour eq 'UNIMARC'
  55   ? "$testdir/data/unimarclatin1utf8rec.mrc"
  56   : "$testdir/data/marc21latin1utf8rec.mrc";
  57
  58 my $file3 =
  59   $marcflavour eq 'UNIMARC'
  60   ? "$testdir/data/unimarcutf8supprec.mrc"
  61   : "$testdir/data/marc21utf8supprec.mrc";
  62
  63 my $user     = $ENV{KOHA_USER} || $xml->{config}->{user};
  64 my $password = $ENV{KOHA_PASS} || $xml->{config}->{pass};
  65 my $intranet = $ENV{KOHA_INTRANET_URL};
  66 my $opac     = $ENV{KOHA_OPAC_URL};
  67
  68
  69 # test KOHA_INTRANET_URL is set
  70 if ( not defined $intranet ) {
  71    plan skip_all => "Tests skip. You must set env. variable KOHA_INTRANET_URL to do tests\n";
  72 }
  73 # test KOHA_OPAC_URL is set
  74 elsif ( not defined $opac ) {
  75    plan skip_all => "Tests skip. You must set env. variable KOHA_OPAC_URL to do tests\n";
  76 }
  77 else {
  78     plan tests => 99;
  79 }
  80
  81 $intranet =~ s#/$##;
  82 $opac     =~ s#/$##;
  83
  84 #-------------------------------- Test with greek and corean chars;
  85 # launch the zebra saerch process
  86 launch_zebra( $datadir, $koha_conf );
  87 if ( not defined $zebra_pid ) {
  88     plan skip_all => "Tests skip. Error starting Zebra Server to do those tests\n";
  89 }
  90 # launch the zebra index process
  91 launch_indexer( );
  92 if ( not defined $indexer_pid ) {
  93     plan skip_all => "Tests skip. Error starting the indexer daemon to do those tests\n";
  94 }
  95
  96 my $utf8_reg1 = qr/学協会. μμ/;
  97 test_search($file1,'Αθήνα', 'deuteros', $utf8_reg1);
  98
  99
 100 #--------------------------------- Test with only utf-8 chars in the latin-1 range;
 101 launch_zebra( $datadir, $koha_conf );
 102 if ( not defined $zebra_pid ) {
 103     plan skip_all => "Tests skip. Error starting Zebra Server to do those tests\n";
 104 }
 105 launch_indexer( );
 106 if ( not defined $indexer_pid ) {
 107     plan skip_all => "Tests skip. Error starting the indexer daemon to do those tests\n";
 108 }
 109 my $utf8_reg2 = qr/Tòmas/;
 110 test_search($file2,'Ramòn', 'Tòmas',$utf8_reg2);
 111
 112 #--------------------------------- Test with supplementary utf-8 chars;
 113 launch_zebra( $datadir, $koha_conf );
 114 if ( not defined $zebra_pid ) {
 115     plan skip_all => "Tests skip. Error starting Zebra Server to do those tests\n";
 116 }
 117 launch_indexer( );
 118 if ( not defined $indexer_pid ) {
 119     plan skip_all => "Tests skip. Error starting the indexer daemon to do those tests\n";
 120 }
 121 my $utf8_reg3 = qr/😀/;
 122 test_search($file3, "𠻺tomasito𠻺", 'A tiny record', $utf8_reg3);
 123
 124 sub test_search{
 125     #Params
 126     my $file = $_[0];
 127     my $publisher = $_[1];
 128     my $search_key = $_[2];
 129     my $utf8_reg = $_[3];
 130
 131     my $agent = Test::WWW::Mechanize->new( autocheck => 1 );
 132     my $jsonresponse;
 133
 134     # -------------------------------------------------- LOAD RECORD
 135
 136     $agent->get_ok( "$intranet/cgi-bin/koha/mainpage.pl", 'connect to intranet' );
 137     $agent->form_name('loginform');
 138     $agent->field( 'password', $password );
 139     $agent->field( 'userid',   $user );
 140     $agent->field( 'branch',   '' );
 141     $agent->click_ok( '', 'login to staff client' );
 142
 143     $agent->get_ok( "$intranet/cgi-bin/koha/mainpage.pl", 'load main page' );
 144
 145     $agent->follow_link_ok( { url_regex => qr/tools-home/i }, 'open tools module' );
 146     $agent->follow_link_ok( { text => 'Stage MARC records for import' },
 147         'go to stage MARC' );
 148
 149     $agent->post(
 150         "$intranet/cgi-bin/koha/tools/upload-file.pl?temp=1",
 151         [ 'fileToUpload' => [$file], ],
 152         'Content_Type' => 'form-data',
 153     );
 154     ok( $agent->success, 'uploaded file' );
 155
 156     $jsonresponse = decode_json $agent->content();
 157     is( $jsonresponse->{'status'}, 'done', 'upload succeeded' );
 158     my $fileid = $jsonresponse->{'fileid'};
 159
 160     $agent->get_ok( "$intranet/cgi-bin/koha/tools/stage-marc-import.pl",
 161         'reopen stage MARC page' );
 162     $agent->submit_form_ok(
 163         {
 164             form_number => 5,
 165             fields      => {
 166                 'uploadedfileid'  => $fileid,
 167                 'nomatch_action'  => 'create_new',
 168                 'overlay_action'  => 'replace',
 169                 'item_action'     => 'always_add',
 170                 'matcher'         => '',
 171                 'comments'        => '',
 172                 'encoding'        => 'utf8',
 173                 'parse_items'     => '1',
 174                 'runinbackground' => '1',
 175                 'record_type'     => 'biblio'
 176             }
 177         },
 178         'stage MARC'
 179     );
 180
 181     $jsonresponse = decode_json $agent->content();
 182     my $jobID = $jsonresponse->{'jobID'};
 183     ok( $jobID, 'have job ID' );
 184
 185     my $completed = 0;
 186
 187     # if we haven't completed the batch in two minutes, it's not happening
 188     for my $counter ( 1 .. 24 ) {
 189         $agent->get(
 190             "$intranet/cgi-bin/koha/tools/background-job-progress.pl?jobID=$jobID"
 191         ); # get job progress
 192         $jsonresponse = decode_json $agent->content();
 193         if ( $jsonresponse->{'job_status'} eq 'completed' ) {
 194             $completed = 1;
 195             last;
 196         }
 197         warn(
 198             (
 199                 $jsonresponse->{'job_size'}
 200                 ? floor(
 201                     100 * $jsonresponse->{'progress'} / $jsonresponse->{'job_size'}
 202                   )
 203                 : '100'
 204             )
 205             . "% completed"
 206         );
 207         sleep 5;
 208     }
 209     is( $jsonresponse->{'job_status'}, 'completed', 'job was completed' );
 210
 211     $agent->get_ok(
 212         "$intranet/cgi-bin/koha/tools/stage-marc-import.pl",
 213         'reopen stage MARC page at end of upload'
 214     );
 215     $agent->submit_form_ok(
 216         {
 217             form_number => 5,
 218             fields      => {
 219                 'uploadedfileid'  => $fileid,
 220                 'nomatch_action'  => 'create_new',
 221                 'overlay_action'  => 'replace',
 222                 'item_action'     => 'always_add',
 223                 'matcher'         => '1',
 224                 'comments'        => '',
 225                 'encoding'        => 'utf8',
 226                 'parse_items'     => '1',
 227                 'runinbackground' => '1',
 228                 'completedJobID'  => $jobID,
 229                 'record_type'     => 'biblio'
 230             }
 231         },
 232         'stage MARC'
 233     );
 234
 235     $agent->follow_link_ok( { text => 'Manage staged records' }, 'view batch' );
 236
 237
 238     $agent->form_number(6);
 239     $agent->field( 'framework', '' );
 240     $agent->click_ok( 'mainformsubmit', "imported records into catalog" );
 241     my $webpage = $agent->{content};
 242
 243     $webpage =~ /(.*<title>.*?)(\d{1,})(.*<\/title>)/sx;
 244     my $id_batch = $2;
 245     my $id_bib_number = GetBiblionumberFromImport($id_batch);
 246
 247     # wait enough time for the indexer
 248     sleep 10;
 249
 250     # --------------------------------- TEST INTRANET SEARCH
 251
 252
 253     $agent->get_ok( "$intranet/cgi-bin/koha/catalogue/search.pl" , "got search on intranet");
 254     $agent->form_number(5);
 255     $agent->field('idx', 'kw');
 256     $agent->field('q', $search_key);
 257     $agent->click();
 258     my $intra_text = $agent->text() ;
 259     like( $intra_text, qr|Publisher: $publisher|, );
 260
 261     $agent->get_ok( "$intranet/cgi-bin/koha/catalogue/search.pl" , "got search on intranet");
 262     $agent->form_number(5);
 263     $agent->field('idx', 'kw');
 264     $agent->field('q', $publisher);
 265     $agent->click();
 266     $intra_text = $agent->text();
 267
 268     like( $intra_text, qr|Publisher: $publisher|, );
 269     my $expected_base = q|search.pl\?advsearch=1&idx=kw&q=| . uri_escape_utf8( $publisher );
 270     $agent->base_like(qr|$expected_base|, );
 271
 272     ok ( ( length(Encode::encode('UTF-8', $intra_text)) != length($intra_text) ) , 'UTF-8 are multi-byte. Good') ;
 273     ok ($intra_text =~  $utf8_reg, 'UTF-8 chars are correctly present. Good');
 274     # -------------------------------------------------- TEST ON OPAC
 275
 276     $agent->get_ok( "$opac" , "got opac");
 277     $agent->form_name('searchform');
 278     $agent->field( 'q',   $search_key );
 279     $agent->field( 'idx',   '' );
 280     $agent->click( );
 281     my $opac_text = $agent->text() ;
 282     like( $opac_text, qr|Publisher: $publisher|, );
 283
 284     $agent->get_ok( "$opac" , "got opac");
 285     $agent->form_name('searchform');
 286     $agent->field('q', $publisher);
 287     $agent->field( 'idx',   '' );
 288     $agent->click();
 289     $opac_text = $agent->text();
 290
 291     like( $opac_text, qr|Publisher: $publisher|, );
 292     $expected_base = q|opac-search.pl\?(idx=&)?q=| . uri_escape_utf8( $publisher );
 293     $agent->base_like(qr|$expected_base|, );
 294     # Test added on BZ 14909 in addition to making the empty idx= optional
 295     # in the previous regex
 296     $agent->base_unlike( qr|idx=\w+|, 'Base does not contain an idx' );
 297
 298
 299     ok ( ( length(Encode::encode('UTF-8', $opac_text)) != length($opac_text) ) , 'UTF-8 are multi-byte. Good') ;
 300     ok ($opac_text =~  $utf8_reg, 'UTF-8 chars are correctly present. Good');
 301
 302     #-------------------------------------------------- REVERT
 303
 304     $agent->get_ok( "$intranet/cgi-bin/koha/tools/manage-marc-import.pl", 'view and clean batch' );
 305     $agent->form_name('clean_batch_'.$id_batch);
 306     $agent->click();
 307     $agent->get_ok( "$intranet/cgi-bin/koha/catalogue/detail.pl?biblionumber=$id_bib_number", 'biblio on intranet' );
 308     $agent->get_ok( "$intranet/cgi-bin/koha/cataloguing/addbiblio.pl?op=delete&biblionumber=$id_bib_number", 'biblio deleted' );
 309
 310     # clean
 311     cleanup();
 312 }
 313
 314
 315 # function that launches the zebra daemon
 316 sub launch_zebra {
 317
 318     my ( $datadir, $koha_conf ) = @_;
 319
 320     $zebra_pid = fork();
 321     if ( $zebra_pid == 0 ) {
 322         exec("zebrasrv -f $koha_conf -v none,request -l $datadir/zebra.log");
 323         exit;
 324     }
 325     sleep( 1 );
 326 }
 327
 328 sub launch_indexer {
 329
 330     my $rootdir       = dirname(__FILE__) . '/../../../';
 331     my $rebuild_zebra = "$rootdir/misc/migration_tools/rebuild_zebra.pl";
 332
 333     $indexer_pid = fork();
 334
 335     if ( $indexer_pid == 0 ) {
 336         exec("$rebuild_zebra -daemon -sleep 5");
 337         exit;
 338     }
 339     sleep( 1 );
 340 }
 341
 342 sub cleanup {
 343
 344     kill 9, $zebra_pid   if defined $zebra_pid;
 345     kill 9, $indexer_pid if defined $indexer_pid;
 346     # Clean up the Zebra files since the child process was just shot
 347     rmtree $datadir;
 348
 349 }
 350
 351 sub GetBiblionumberFromImport{
 352     my ( $batch_id) = @_;
 353     use C4::ImportBatch;
 354     my $data = C4::ImportBatch::GetImportRecordsRange($batch_id, '', '', undef,
 355                     { order_by => 'import_record_id', order_by_direction => 'DESC' });
 356     my $biblionumber = $data->[0]->{'matched_biblionumber'};
 357
 358     return $biblionumber;
 359 }
 360
 361 END {
 362     cleanup();
 363 };
 364