Attachment #8150 for bug #7698

View | Details | Raw Unified | Return to bug 7698
Collapse All | Expand All




  'AUTH_INDEX_MODE'   => 'dom',
  'ZEBRA_MARC_FORMAT' => 'marc21',
  'ZEBRA_LANGUAGE'    => 'en',
  'ZEBRA_TOKENIZER'   => 'chr',
  'ZEBRA_USER'        => 'kohauser',
  'ZEBRA_PASS'        => 'zebrastripes',
  'ZEBRA_SRU_HOST'    => 'localhost',

  'AUTH_INDEX_MODE' => { 'grs1' => 1, 'dom' => 1 },
  'ZEBRA_MARC_FORMAT' => { 'marc21' => 1, 'normarc' => 1, 'unimarc' => 1 }, # FIXME should generate from contents of distributation
  'ZEBRA_LANGUAGE'    => { 'en' => 1, 'fr' => 1, 'nb' => 1 }, # FIXME should generate from contents of distribution
  'ZEBRA_TOKENIZER' => { chr => 1, icu => 1 },
  'RUN_DATABASE_TESTS' => { 'yes' => 1, 'no' => 1 },
  'USE_MEMCACHED'      => { 'yes' => 1, 'no' => 1 },
);

      'rewrite-config.PL' => [
         'blib/KOHA_CONF_DIR/koha-conf.xml',
         'blib/KOHA_CONF_DIR/koha-httpd.conf',
         'blib/ZEBRA_CONF_DIR/etc/default.idx',
         'blib/MISC_DIR/koha-install-log'
         ],
	  'fix-perl-path.PL' => [	# this script ensures the correct shebang line for the platform installed on...
		 'blib'
		 ],
};

if ($config{'INSTALL_ZEBRA'} eq "yes") {

    );
}

$config{ZEBRA_TOKENIZER_STMT} = $config{ZEBRA_TOKENIZER} eq 'icu'
    ? 'icuchain words-icu.xml'
    : 'charmap word-phrase-utf.chr';

my %test_suite_override_dirs = (
    KOHA_CONF_DIR  => ['etc'],
    ZEBRA_CONF_DIR => ['etc', 'zebradb'],

you must specify the primary MARC format of the
records to be indexed by Zebra.

Koha provides Zebra configuration files for MARC21,
NORMARC and UNIMARC.

MARC format for Zebra indexing);
        $msg .= _add_valid_values_disp('ZEBRA_MARC_FORMAT', $valid_values);

        $config{'AUTH_INDEX_MODE'} = _get_value('AUTH_INDEX_MODE', $msg, $defaults->{'AUTH_INDEX_MODE'}, $valid_values, $install_log_values);

        $msg = q(
Zebra has two methods to perform records tokenization
and characters normalization: CHR and ICU. ICU is
recommended for catalogs containing non-Latin
characters.);

        $msg .= _add_valid_values_disp('ZEBRA_TOKENIZER', $valid_values);
        $config{'ZEBRA_TOKENIZER'} = _get_value('ZEBRA_TOKENIZER', $msg, $defaults->{'ZEBRA_TOKENIZER'}, $valid_values, $install_log_values);

        $msg = q(
Please specify Zebra database user);
        $config{'ZEBRA_USER'} = _get_value('ZEBRA_USER', $msg, $defaults->{'ZEBRA_USER'}, $valid_values, $install_log_values);





position 1
alwaysmatches 1
firstinfield 1
__ZEBRA_TOKENIZER_STMT__
#firstinfield 1

# Phrase index
# Used if completeness is 'complete {sub}field' (@attr 6=2, @attr 6=1)
# and structure is word/phrase/word-list/free-form-text/document-text
index p
completeness 1
charmap word-phrase-utf.chr
firstinfield 1
__ZEBRA_TOKENIZER_STMT__

# URX (URL) index
# Used if structure=urx (@attr 4=104)




<icu_chain locale="">
  <transliterate rule="\'>\ "/>
  <transliterate rule="[:Number:] { '-' > '' "/>
  <transform rule="[:Control:] Any-Remove"/>
  <tokenize rule="l"/>
  <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
  <transform rule="NFD"/>
  <transform rule="[:Nonspacing Mark:] Remove"/>
  <transform rule="NFC"/>
  <display/>
  <casemap rule="l"/>
</icu_chain>

Lines 120-125 $prefix = $ENV{'INSTALL_BASE'} \|\| "/usr"; Link Here

(-)a/rewrite-config.PL (-1 / +1 lines)
120	'__ZEBRA_RUN_DIR__' => "$prefix/var/run/zebradb",	120	'__ZEBRA_RUN_DIR__' => "$prefix/var/run/zebradb",
121	'__ZEBRA_MARC_FORMAT__' => 'marc21',	121	'__ZEBRA_MARC_FORMAT__' => 'marc21',
122	'__ZEBRA_LANGUAGE__' => 'en',	122	'__ZEBRA_LANGUAGE__' => 'en',
		123	'__ZEBRA_TOKENIZER_STMT__' => 'charmap word-phrase-utf.chr',
123	'__ZEBRA_AUTH_CFG__' => 'zebra-authorities.cfg',	124	'__ZEBRA_AUTH_CFG__' => 'zebra-authorities.cfg',
124	'__AUTH_RETRIEVAL_CFG__' => 'retrieval-info-auth-grs1.xml',	125	'__AUTH_RETRIEVAL_CFG__' => 'retrieval-info-auth-grs1.xml',
125	"__MERGE_SERVER_HOST__" => $myhost,	126	"__MERGE_SERVER_HOST__" => $myhost,
126	-

Return to bug 7698

Lines 410-415 my %config_defaults = ( Link Here

(-)a/Makefile.PL (-3 / +19 lines)
410	'AUTH_INDEX_MODE' => 'dom',	410	'AUTH_INDEX_MODE' => 'dom',
411	'ZEBRA_MARC_FORMAT' => 'marc21',	411	'ZEBRA_MARC_FORMAT' => 'marc21',
412	'ZEBRA_LANGUAGE' => 'en',	412	'ZEBRA_LANGUAGE' => 'en',
		413	'ZEBRA_TOKENIZER' => 'chr',
413	'ZEBRA_USER' => 'kohauser',	414	'ZEBRA_USER' => 'kohauser',
414	'ZEBRA_PASS' => 'zebrastripes',	415	'ZEBRA_PASS' => 'zebrastripes',
415	'ZEBRA_SRU_HOST' => 'localhost',	416	'ZEBRA_SRU_HOST' => 'localhost',
Lines 461-466 my %valid_config_values = ( Link Here
461	'AUTH_INDEX_MODE' => { 'grs1' => 1, 'dom' => 1 },	462	'AUTH_INDEX_MODE' => { 'grs1' => 1, 'dom' => 1 },
462	'ZEBRA_MARC_FORMAT' => { 'marc21' => 1, 'normarc' => 1, 'unimarc' => 1 }, # FIXME should generate from contents of distributation	463	'ZEBRA_MARC_FORMAT' => { 'marc21' => 1, 'normarc' => 1, 'unimarc' => 1 }, # FIXME should generate from contents of distributation
463	'ZEBRA_LANGUAGE' => { 'en' => 1, 'fr' => 1, 'nb' => 1 }, # FIXME should generate from contents of distribution	464	'ZEBRA_LANGUAGE' => { 'en' => 1, 'fr' => 1, 'nb' => 1 }, # FIXME should generate from contents of distribution
		465	'ZEBRA_TOKENIZER' => { chr => 1, icu => 1 },
464	'RUN_DATABASE_TESTS' => { 'yes' => 1, 'no' => 1 },	466	'RUN_DATABASE_TESTS' => { 'yes' => 1, 'no' => 1 },
465	'USE_MEMCACHED' => { 'yes' => 1, 'no' => 1 },	467	'USE_MEMCACHED' => { 'yes' => 1, 'no' => 1 },
466	);	468	);
Lines 487-497 my $pl_files = { Link Here
487	'rewrite-config.PL' => [	489	'rewrite-config.PL' => [
488	'blib/KOHA_CONF_DIR/koha-conf.xml',	490	'blib/KOHA_CONF_DIR/koha-conf.xml',
489	'blib/KOHA_CONF_DIR/koha-httpd.conf',	491	'blib/KOHA_CONF_DIR/koha-httpd.conf',
		492	'blib/ZEBRA_CONF_DIR/etc/default.idx',
490	'blib/MISC_DIR/koha-install-log'	493	'blib/MISC_DIR/koha-install-log'
491	],	494	],
492	'fix-perl-path.PL' => [ # this script ensures the correct shebang line for the platform installed on...	495	'fix-perl-path.PL' => [ # this script ensures the correct shebang line for the platform installed on...
493	'blib'	496	'blib'
494	]	497	],
495	};	498	};
496		499
497	if ($config{'INSTALL_ZEBRA'} eq "yes") {	500	if ($config{'INSTALL_ZEBRA'} eq "yes") {
Lines 528-533 if ($config{'INSTALL_MODE'} ne "dev") { Link Here
528	);	531	);
529	}	532	}
530		533
		534	$config{ZEBRA_TOKENIZER_STMT} = $config{ZEBRA_TOKENIZER} eq 'icu'
		535	? 'icuchain words-icu.xml'
		536	: 'charmap word-phrase-utf.chr';
		537
531	my %test_suite_override_dirs = (	538	my %test_suite_override_dirs = (
532	KOHA_CONF_DIR => ['etc'],	539	KOHA_CONF_DIR => ['etc'],
533	ZEBRA_CONF_DIR => ['etc', 'zebradb'],	540	ZEBRA_CONF_DIR => ['etc', 'zebradb'],
Lines 918-925 Since you've chosen to use Zebra with Koha, Link Here
918	you must specify the primary MARC format of the	925	you must specify the primary MARC format of the
919	records to be indexed by Zebra.	926	records to be indexed by Zebra.
920		927
921	Koha provides Zebra configuration files for MARC 21	928	Koha provides Zebra configuration files for MARC21,
922	and UNIMARC.	929	NORMARC and UNIMARC.
923		930
924	MARC format for Zebra indexing);	931	MARC format for Zebra indexing);
925	$msg .= _add_valid_values_disp('ZEBRA_MARC_FORMAT', $valid_values);	932	$msg .= _add_valid_values_disp('ZEBRA_MARC_FORMAT', $valid_values);
Lines 947-952 Authorities indexing mode); Link Here
947	$config{'AUTH_INDEX_MODE'} = _get_value('AUTH_INDEX_MODE', $msg, $defaults->{'AUTH_INDEX_MODE'}, $valid_values, $install_log_values);	954	$config{'AUTH_INDEX_MODE'} = _get_value('AUTH_INDEX_MODE', $msg, $defaults->{'AUTH_INDEX_MODE'}, $valid_values, $install_log_values);
948		955
949	$msg = q(	956	$msg = q(
		957	Zebra has two methods to perform records tokenization
		958	and characters normalization: CHR and ICU. ICU is
		959	recommended for catalogs containing non-Latin
		960	characters.);
		961
		962	$msg .= _add_valid_values_disp('ZEBRA_TOKENIZER', $valid_values);
		963	$config{'ZEBRA_TOKENIZER'} = _get_value('ZEBRA_TOKENIZER', $msg, $defaults->{'ZEBRA_TOKENIZER'}, $valid_values, $install_log_values);
		964
		965	$msg = q(
950	Please specify Zebra database user);	966	Please specify Zebra database user);
951	$config{'ZEBRA_USER'} = _get_value('ZEBRA_USER', $msg, $defaults->{'ZEBRA_USER'}, $valid_values, $install_log_values);	967	$config{'ZEBRA_USER'} = _get_value('ZEBRA_USER', $msg, $defaults->{'ZEBRA_USER'}, $valid_values, $install_log_values);
952		968

Lines 10-25 completeness 0 Link Here

(-)a/etc/zebradb/etc/default.idx (-3 / +2 lines)
10	position 1	10	position 1
11	alwaysmatches 1	11	alwaysmatches 1
12	firstinfield 1	12	firstinfield 1
13	charmap word-phrase-utf.chr	13	__ZEBRA_TOKENIZER_STMT__
14	#firstinfield 1
15		14
16	# Phrase index	15	# Phrase index
17	# Used if completeness is 'complete {sub}field' (@attr 6=2, @attr 6=1)	16	# Used if completeness is 'complete {sub}field' (@attr 6=2, @attr 6=1)
18	# and structure is word/phrase/word-list/free-form-text/document-text	17	# and structure is word/phrase/word-list/free-form-text/document-text
19	index p	18	index p
20	completeness 1	19	completeness 1
21	charmap word-phrase-utf.chr
22	firstinfield 1	20	firstinfield 1
		21	__ZEBRA_TOKENIZER_STMT__
23		22
24	# URX (URL) index	23	# URX (URL) index
25	# Used if structure=urx (@attr 4=104)	24	# Used if structure=urx (@attr 4=104)

Line 0 Link Here

(-)a/etc/zebradb/etc/words-icu.xml (+12 lines)
	1	<icu_chain locale="">
	2	<transliterate rule="\'>\ "/>
	3	<transliterate rule="[:Number:] { '-' > '' "/>
	4	<transform rule="[:Control:] Any-Remove"/>
	5	<tokenize rule="l"/>
	6	<transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
	7	<transform rule="NFD"/>
	8	<transform rule="[:Nonspacing Mark:] Remove"/>
	9	<transform rule="NFC"/>
	10	<display/>
	11	<casemap rule="l"/>
	12	</icu_chain>