1 # $Id: Session.pm,v 1.15 2003-03-13 04:25:18 pop Exp $
3 # Zebra perl API header
4 # =============================================================================
5 package IDZebra::Session;
13 use IDZebra::Logger qw(:flags :calls);
14 use IDZebra::Resultset;
15 use IDZebra::ScanList;
16 use IDZebra::RetrievalRecord;
18 our $VERSION = do { my @r = (q$Revision: 1.15 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
19 our @ISA = qw(IDZebra::Logger Exporter);
20 our @EXPORT = qw (TRANS_RW TRANS_RO);
23 use constant TRANS_RW => 1;
24 use constant TRANS_RO => 0;
27 # -----------------------------------------------------------------------------
28 # Class constructors, destructor
29 # -----------------------------------------------------------------------------
31 my ($proto, %args) = @_;
32 my $class = ref($proto) || $proto;
34 $self->{args} = \%args;
36 bless ($self, $class);
37 $self->{cql_ct} = undef;
38 $self->{cql_mapfile} = "";
41 $self->{databases} = {};
45 my ($self, %args) = @_;
48 unless (defined($self->{zs})) {
49 if (defined($args{'configFile'})) {
50 $self->{zs} = IDZebra::start($args{'configFile'});
52 $self->{zs} = IDZebra::start("zebra.cfg");
59 if (defined($self->{zs})) {
60 IDZebra::stop($self->{zs}) if ($self->{zs});
67 my ($proto,%args) = @_;
70 if (ref($proto)) { $self = $proto; } else {
71 $self = $proto->new(%args);
75 %args = %{$self->{args}};
78 $self->start_service(%args);
80 unless (defined($self->{zs})) {
81 croak ("Falied to open zebra service");
84 unless (defined($self->{zh})) {
85 $self->{zh}=IDZebra::open($self->{zs});
88 # Reset result set counter
91 # This is needed in order to somehow initialize the service
92 $self->databases("Default");
94 # Load the default configuration
99 my $shadow = defined($args{shadow}) ? $args{shadow} : 0;
100 $self->shadow($shadow);
102 $self->{odr_input} = IDZebra::odr_createmem($IDZebra::ODR_DECODE);
103 $self->{odr_output} = IDZebra::odr_createmem($IDZebra::ODR_ENCODE);
110 unless (defined($self->{zh})) {
111 croak ("Zebra session is not opened");
121 # Delete all resulsets
122 my $r = IDZebra::deleteResultSet($self->{zh},
123 1, #Z_DeleteRequest_all,
127 while (IDZebra::trans_no($self->{zh}) > 0) {
128 logf (LOG_WARN,"Explicitly closing transaction with session");
132 IDZebra::close($self->{zh});
136 if ($self->{odr_input}) {
137 IDZebra::odr_reset($self->{odr_input});
138 IDZebra::odr_destroy($self->{odr_input});
139 $self->{odr_input} = undef;
142 if ($self->{odr_output}) {
143 IDZebra::odr_reset($self->{odr_output});
144 IDZebra::odr_destroy($self->{odr_output});
145 $self->{odr_output} = undef;
153 logf (LOG_LOG,"DESTROY $self");
156 if (defined ($self->{cql_ct})) {
157 IDZebra::cql_transform_close($self->{cql_ct});
161 # -----------------------------------------------------------------------------
162 # Record group selection This is a bit nasty... but used at many places
163 # -----------------------------------------------------------------------------
165 my ($self,%args) = @_;
168 $self->{rg} = $self->_makeRecordGroup(%args);
169 $self->_selectRecordGroup($self->{rg});
174 sub selectRecordGroup {
175 my ($self, $groupName) = @_;
177 $self->{rg} = $self->_getRecordGroup($groupName);
178 $self->_selectRecordGroup($self->{rg});
181 sub _displayRecordGroup {
182 my ($self, $rg) = @_;
183 print STDERR "-----\n";
184 foreach my $key qw (groupName
195 print STDERR "$key:",$rg->{$key},"\n";
199 sub _cloneRecordGroup {
200 my ($self, $orig) = @_;
201 my $rg = IDZebra::recordGroup->new();
202 my $r = IDZebra::init_recordGroup($rg);
203 foreach my $key qw (groupName
215 $rg->{$key} = $orig->{$key} if ($orig->{$key});
220 sub _getRecordGroup {
221 my ($self, $groupName, $ext) = @_;
222 my $rg = IDZebra::recordGroup->new();
223 my $r = IDZebra::init_recordGroup($rg);
224 $rg->{groupName} = $groupName if ($groupName ne "");
225 $ext = "" unless ($ext);
226 $r = IDZebra::res_get_recordGroup($self->{zh}, $rg, $ext);
230 sub _makeRecordGroup {
231 my ($self, %args) = @_;
234 my @keys = keys(%args);
235 unless ($#keys >= 0) {
236 return ($self->{rg});
239 if ($args{groupName}) {
240 $rg = $self->_getRecordGroup($args{groupName});
242 $rg = $self->_cloneRecordGroup($self->{rg});
244 $self->_setRecordGroupOptions($rg, %args);
248 sub _setRecordGroupOptions {
249 my ($self, $rg, %args) = @_;
251 foreach my $key qw (databaseName
262 if (defined ($args{$key})) {
263 $rg->{$key} = $args{$key};
267 sub _selectRecordGroup {
268 my ($self, $rg) = @_;
270 my $r = IDZebra::set_group($self->{zh}, $rg);
272 unless ($dbName = $rg->{databaseName}) {
275 unless ($self->databases($dbName)) {
276 croak("Fatal error selecting database $dbName");
279 # -----------------------------------------------------------------------------
280 # Selecting databases for search (and also for updating - internally)
281 # -----------------------------------------------------------------------------
283 my ($self, @databases) = @_;
288 return (keys(%{$self->{databases}}));
293 foreach my $db (@databases) {
295 next if ($self->{databases}{$db});
299 foreach my $db (keys (%{$self->{databases}})) {
300 $changed++ unless ($tmp{$db});
305 delete ($self->{databases});
306 foreach my $db (@databases) {
307 $self->{databases}{$db}++;
310 if (IDZebra::select_databases($self->{zh},
314 "Could not select database(s) %s errCode=%d",
315 join(",",@databases),
319 logf(LOG_LOG,"Database(s) selected: %s",join(",",@databases));
322 return (keys(%{$self->{databases}}));
325 # -----------------------------------------------------------------------------
327 # -----------------------------------------------------------------------------
330 return(IDZebra::errCode($self->{zh}));
335 return(IDZebra::errString($self->{zh}));
340 return(IDZebra::errAdd($self->{zh}));
343 # -----------------------------------------------------------------------------
345 # -----------------------------------------------------------------------------
348 $m = TRANS_RW unless (defined ($m));
349 if (my $err = IDZebra::begin_trans($self->{zh},$m)) {
350 if ($self->errCode == 2) {
351 croak ("TRANS_RW not allowed within TRANS_RO");
353 croak("Error starting transaction; code:".
354 $self->errCode . " message: " . $self->errString);
362 my $stat = IDZebra::ZebraTransactionStatus->new();
363 IDZebra::end_trans($self->{zh}, $stat);
368 my ($self, $value) = @_;
371 $value = 0 unless (defined($value));
372 my $r =IDZebra::set_shadow_enable($self->{zh},$value);
374 return (IDZebra::get_shadow_enable($self->{zh}));
381 return(IDZebra::commit($self->{zh}));
385 # -----------------------------------------------------------------------------
386 # We don't really need that...
387 # -----------------------------------------------------------------------------
389 my ($self, $name) = @_;
390 if ($name !~/^(input|output)$/) {
391 croak("Undefined ODR '$name'");
393 IDZebra::odr_reset($self->{"odr_$name"});
396 # -----------------------------------------------------------------------------
398 # -----------------------------------------------------------------------------
402 return(IDZebra::init($self->{zh}));
408 return(IDZebra::compact($self->{zh}));
412 my ($self, %args) = @_;
414 my $rg = $self->_update_args(%args);
415 $self->_selectRecordGroup($rg);
417 IDZebra::repository_update($self->{zh});
418 $self->_selectRecordGroup($self->{rg});
423 my ($self, %args) = @_;
425 my $rg = $self->_update_args(%args);
426 $self->_selectRecordGroup($rg);
428 IDZebra::repository_delete($self->{zh});
429 $self->_selectRecordGroup($self->{rg});
434 my ($self, %args) = @_;
436 my $rg = $self->_update_args(%args);
437 $self->_selectRecordGroup($rg);
439 IDZebra::repository_show($self->{zh});
440 $self->_selectRecordGroup($self->{rg});
445 my ($self, %args) = @_;
446 my $rg = $self->_makeRecordGroup(%args);
447 $self->_selectRecordGroup($rg);
451 # -----------------------------------------------------------------------------
453 # -----------------------------------------------------------------------------
455 my ($self, %args) = @_;
457 return(IDZebra::insert_record($self->{zh},
458 $self->_record_update_args(%args)));
462 my ($self, %args) = @_;
464 return(IDZebra::update_record($self->{zh},
465 $self->_record_update_args(%args)));
469 my ($self, %args) = @_;
471 return(IDZebra::delete_record($self->{zh},
472 $self->_record_update_args(%args)));
475 sub _record_update_args {
476 my ($self, %args) = @_;
478 my $sysno = $args{sysno} ? $args{sysno} : 0;
479 my $match = $args{match} ? $args{match} : "";
480 my $rectype = $args{recordType} ? $args{recordType} : "";
481 my $fname = $args{file} ? $args{file} : "<no file>";
482 my $force = $args{force} ? $args{force} : 0;
489 elsif ($args{file}) {
490 CORE::open (F, $args{file}) || warn ("Cannot open $args{file}");
491 $buff = join('',(<F>));
494 my $len = length($buff);
496 delete ($args{sysno});
497 delete ($args{match});
498 delete ($args{recordType});
499 delete ($args{file});
500 delete ($args{data});
501 delete ($args{force});
503 my $rg = $self->_makeRecordGroup(%args);
505 # If no record type is given, then try to find it out from the
508 if (my ($ext) = $fname =~ /\.(\w+)$/) {
509 my $rg2 = $self->_getRecordGroup($rg->{groupName},$ext);
510 $rectype = $rg2->{recordType};
514 $rg->{databaseName} = "Default" unless ($rg->{databaseName});
519 return ($rg, $rectype, $sysno, $match, $fname, $buff, $len, $force);
522 # -----------------------------------------------------------------------------
525 my ($self,$mapfile) = @_;
527 if ($self->{cql_mapfile} ne $mapfile) {
528 unless (-f $mapfile) {
529 croak("Cannot find $mapfile");
531 if (defined ($self->{cql_ct})) {
532 IDZebra::cql_transform_close($self->{cql_ct});
534 $self->{cql_ct} = IDZebra::cql_transform_open_fname($mapfile);
535 $self->{cql_mapfile} = $mapfile;
538 return ($self->{cql_mapfile});
542 my ($self, $cqlquery) = @_;
543 unless (defined($self->{cql_ct})) {
544 croak("CQL map file is not specified yet.");
546 my $res = "\0" x 2048;
547 my $r = IDZebra::cql2pqf($self->{cql_ct}, $cqlquery, $res, 2048);
549 # carp ("Error transforming CQL query: '$cqlquery', status:$r");
556 # -----------------------------------------------------------------------------
558 # -----------------------------------------------------------------------------
560 my ($self, %args) = @_;
564 if ($args{cqlmap}) { $self->cqlmap($args{cqlmap}); }
572 ($query, $cqlstat) = $self->cql2pqf($args{cql});
574 croak ("Failed to transform query: '$args{cql}', ".
575 "status: ($cqlstat)");
579 croak ("No query given to search");
584 if ($args{databases}) {
585 @origdbs = $self->databases;
586 $self->databases(@{$args{databases}});
589 my $rsname = $args{rsname} ? $args{rsname} : $self->_new_setname;
591 my $rs = $self->_search_pqf($query, $rsname);
593 if ($args{databases}) {
594 $self->databases(@origdbs);
599 carp("Sort skipped due to search error: ".
602 $rs->sort($args{sort});
611 return ("set_".$self->{rscount}++);
615 my ($self, $query, $setname) = @_;
617 my $hits = IDZebra::search_PQF($self->{zh},
623 my $rs = IDZebra::Resultset->new($self,
625 recordCount => $hits,
626 errCode => $self->errCode,
627 errString => $self->errString);
631 # -----------------------------------------------------------------------------
634 # Sorting of multiple result sets is not supported by zebra...
635 # -----------------------------------------------------------------------------
638 my ($self, $sortspec, $setname, @sets) = @_;
643 croak ("Sorting/merging of multiple resultsets is not supported now");
648 foreach my $rs (@sets) {
649 push (@setnames, $rs->{name});
650 $count += $rs->{recordCount}; # is this really sure ??? It doesn't
654 my $status = IDZebra::sort($self->{zh},
660 my $errCode = $self->errCode;
661 my $errString = $self->errString;
663 logf (LOG_LOG, "Sort status $setname: %d, errCode: %d, errString: %s",
664 $status, $errCode, $errString);
666 if ($status || $errCode) {$count = 0;}
668 my $rs = IDZebra::Resultset->new($self,
670 recordCount => $count,
672 errString => $errString);
676 # -----------------------------------------------------------------------------
678 # -----------------------------------------------------------------------------
680 my ($self, %args) = @_;
684 unless ($args{expression}) {
685 croak ("No scan expression given");
688 my $sl = IDZebra::ScanList->new($self,%args);
693 # ============================================================================
699 IDZebra::Session - A Zebra database server session for update and retrieval
703 $sess = IDZebra::Session->new(configFile => 'demo/zebra.cfg');
706 $sess = IDZebra::Session->open(configFile => 'demo/zebra.cfg',
707 groupName => 'demo1');
709 $sess->group(groupName => 'demo2');
715 $sess->update(path => 'lib');
717 my $s1=$sess->update_record(data => $rec1,
718 recordType => 'grs.perl.pod',
719 groupName => "demo1",
722 my $stat = $sess->end_trans;
724 $sess->databases('demo1','demo2');
726 my $rs1 = $sess->search(cqlmap => 'demo/cql.map',
727 cql => 'dc.title=IDZebra',
728 databases => [qw(demo1 demo2)]);
733 Zebra is a high-performance, general-purpose structured text indexing and retrieval engine. It reads structured records in a variety of input formats (eg. email, XML, MARC) and allows access to them through exact boolean search expressions and relevance-ranked free-text queries.
735 Zebra supports large databases (more than ten gigabytes of data, tens of millions of records). It supports incremental, safe database updates on live systems. You can access data stored in Zebra using a variety of Index Data tools (eg. YAZ and PHP/YAZ) as well as commercial and freeware Z39.50 clients and toolkits.
737 =head1 OPENING AND CLOSING A ZEBRA SESSIONS
739 For the time beeing only local database services are supported, the same way as calling zebraidx or zebrasrv from the command shell. In order to open a local Zebra database, with a specific configuration file, use
741 $sess = IDZebra::Session->new(configFile => 'demo/zebra.cfg');
746 $sess = IDZebra::Session->open(configFile => 'demo/zebra.cfg');
748 where $sess is going to be the object representing a Zebra Session. Whenever this variable gets out of scope, the session is closed, together with all active transactions, etc... Anyway, if you'd like to close the session, just say:
753 - close all transactions
754 - destroy all result sets and scan lists
757 Note, that if I<shadow registers> are enabled, the changes will not be committed automatically.
759 In the future different database access methods are going to be available,
762 $sess = IDZebra::Session->open(server => 'ostrich.technomat.hu:9999');
764 You can also use the B<record group> arguments described below directly when calling the constructor, or the open method:
766 $sess = IDZebra::Session->open(configFile => 'demo/zebra.cfg',
767 groupName => 'demo');
772 If you manage different sets of records that share common characteristics, you can organize the configuration settings for each type into "groups". See the Zebra manual on the configuration file (zebra.cfg).
774 For each open session a default record group is assigned. You can configure it in the constructor, or by the B<group> method:
776 $sess->group(groupName => ..., ...)
778 The following options are available:
784 This will select the named record group, and load the corresponding settings from the configuration file. All subsequent values will overwrite those...
786 =item B<databaseName>
788 The name of the (logical) database the updated records will belong to.
792 This path is used for directory updates (B<update>, B<delete> methods);
796 This option determines how to identify your records. See I<Zebra manual: Locating Records>
800 The record type used for indexing.
802 =item B<flagStoreData>
804 Specifies whether the records should be stored internally in the Zebra system files. If you want to maintain the raw records yourself, this option should be false (0). If you want Zebra to take care of the records for you, it should be true(1).
806 =item B<flagStoreKeys>
808 Specifies whether key information should be saved for a given group of records. If you plan to update/delete this type of records later this should be specified as 1; otherwise it should be 0 (default), to save register space.
814 =item B<fileVerboseLimit>
816 Skip log messages, when doing a directory update, and the specified number of files are processed...
818 =item B<databaseNamePath>
822 =item B<explainDatabase>
824 The name of the explain database to be used
828 Follow links when doing directory update.
832 You can use the same parameters calling all update methods.
834 =head1 TRANSACTIONS (READ / WRITE LOCKS)
836 A transaction is a block of record update (insert / modify / delete) or retrieval procedures. So, all call to such function will implicitly start a transaction, unless one is already started by
842 $sess->begin_trans(TRANS_RW)
844 (these two are equivalents). The effect of this call is a kind of lock: if you call is a write lock is put on the registers, so other processes trying to update the database will be blocked. If there is already an RW (Read-Write) transaction opened by another process, the I<begin_trans> call will be blocked.
848 $sess->begin_trans(TRANS_RO),
850 if you would like to put on a "read lock". This one is B<deprecated>, as while you have explicitly opened a transaction for read, you can't open another one for update. For example:
852 $sess->begin_trans(TRANS_RO);
853 $sess->begin_tran(TRANS_RW); # invalid, die here
859 $sess->begin_tran(TRANS_RW);
860 $sess->begin_trans(TRANS_RO);
864 is valid, but probably useless. Note again, that for each retrieval call, an RO transaction is opened. I<TRANS_RW> and I<TRANS_RO> are exported by default by IDZebra::Session.pm.
866 For multiple per-record I<updates> it's efficient to start transactions explicitly: otherwise registers (system files, vocabularies, etc..) are updated one by one. After finishing all requested updates, use
868 $stat = $sess->end_trans;
870 The return value is a ZebraTransactionStatus object, containing the following members as a hash reference:
872 $stat->{processed} # Number of records processed
873 $stat->{updated} # Number of records processed
874 $stat->{deleted} # Number of records processed
875 $stat->{inserted} # Number of records processed
876 $stat->{stime} # System time used
877 $stat->{utime} # User time used
879 Normally, if the perl code dies due to some runtime error, or the session is closed, then the API attempts to close all pending transactions.
881 =head1 THE SHADOW REGISTERS
883 The Zebra server supports updating of the index structures. That is, you can add, modify, or remove records from databases managed by Zebra without rebuilding the entire index. Since this process involves modifying structured files with various references between blocks of data in the files, the update process is inherently sensitive to system crashes, or to process interruptions: Anything but a successfully completed update process will leave the register files in an unknown state, and you will essentially have no recourse but to re-index everything, or to restore the register files from a backup medium. Further, while the update process is active, users cannot be allowed to access the system, as the contents of the register files may change unpredictably.
885 You can solve these problems by enabling the shadow register system in Zebra. During the updating procedure, zebraidx will temporarily write changes to the involved files in a set of "shadow files", without modifying the files that are accessed by the active server processes. If the update procedure is interrupted by a system crash or a signal, you simply repeat the procedure - the register files have not been changed or damaged, and the partially written shadow files are automatically deleted before the new updating procedure commences.
887 At the end of the updating procedure (or in a separate operation, if you so desire), the system enters a "commit mode". First, any active server processes are forced to access those blocks that have been changed from the shadow files rather than from the main register files; the unmodified blocks are still accessed at their normal location (the shadow files are not a complete copy of the register files - they only contain those parts that have actually been modified). If the commit process is interrupted at any point during the commit process, the server processes will continue to access the shadow files until you can repeat the commit procedure and complete the writing of data to the main register files. You can perform multiple update operations to the registers before you commit the changes to the system files, or you can execute the commit operation at the end of each update operation. When the commit phase has completed successfully, any running server processes are instructed to switch their operations to the new, operational register, and the temporary shadow files are deleted.
889 By default, (in the API !) the use of shadow registers is disabled. If zebra is configured that way (there is a "shadow" entry in zebra.cfg), then the shadow system can be enabled by calling:
897 If shadow system is enabled, then you have to commit changes you did, by calling:
901 Note, that you can also determine shadow usage in the session constructor:
903 $sess = IDZebra::Session->open(configFile => 'demo/zebra.cfg',
906 Changes to I<shadow> will not have effect, within a I<transaction> (ie.: a transaction is started either with shadow enabled or disabled). For more details, read Zebra documentation: I<Safe Updating - Using Shadow Registers>.
910 There are two ways to update data in a Zebra database using the perl API. You can update an entire directory structure just the way it's done by zebraidx:
912 $sess->update(path => 'lib');
914 This will update the database with the files in directory "lib", according to the current record group settings.
918 This will update the database with the files, specified by the default record group setting. I<path> has to be specified there...
920 $sess->update(groupName => 'demo1',
923 Update the database with files in "lib" according to the settings of group "demo1"
925 $sess->delete(groupName => 'demo1',
928 Delete the records derived from the files in directory "lib", according to the "demo1" group settings. Sounds complex? Read zebra documentation about identifying records.
930 You can also update records one by one, even directly from the memory:
932 $sysno = $sess->update_record(data => $rec1,
933 recordType => 'grs.perl.pod',
934 groupName => "demo1");
936 This will update the database with the given record buffer. Note, that in this case recordType is explicitly specified, as there is no filename given, and for the demo1 group, no default record type is specified. The return value is the system assigned id of the record.
938 You can also index a single file:
940 $sysno = $sess->update_record(file => "lib/IDZebra/Data1.pm");
942 Or, provide a buffer, and a filename (where filename will only be used to identify the record, if configured that way, and possibly to find out it's record type):
944 $sysno = $sess->update_record(data => $rec1,
945 file => "lib/IDZebra/Data1.pm");
947 And some crazy stuff:
949 $sysno = $sess->delete_record(sysno => $sysno);
951 where sysno in itself is sufficient to identify the record
953 $sysno = $sess->delete_record(data => $rec1,
954 recordType => 'grs.perl.pod',
955 groupName => "demo1");
957 This case the record is extracted, and if already exists, located in the database, then deleted...
959 $sysno = $sess->update_record(data => $rec1,
961 recordType => 'grs.perl.pod',
962 groupName => "demo1");
964 Don't try this at home! This case, the record identifier string (which is normally generated according to the rules set in I<recordId> member of the record group, or in the I<recordId> parameter) is provided directly.... Looks much better this way:
966 $sysno = $sess->update_record(data => $rec1,
967 databaseName => 'books',
968 recordId => '(bib1,ISBN)',
969 recordType => 'grs.perl.pod',
973 You can notice, that it's not necessary to define a record group in zebra.cfg: you can do it "on the fly" in your code.
975 B<Important:> Note, that one record can be updated only once within a transaction - all subsequent updates are skipped. If you'd like to override this feature, use the I<force=E<gt>1> flag:
977 $sysno = $sess->update_record(data => $rec1,
978 recordType => 'grs.perl.pod',
979 groupName => "demo1",
982 If you don't like to update the record, if it alerady exists, use the I<insert_record> method:
984 $sysno = $sess->insert_record(data => $rec1,
985 recordType => 'grs.perl.pod',
986 groupName => "demo1");
988 In this case, sysno will be -1, if the record could not be added, because there was already one in the database, with the same record identifier (generated according to the I<recordId> setting).
990 =head1 DATABASE SELECTION
992 Within a zebra repository you can define logical databases. You can either do this by record groups, or by providing the databaseName argument for update methods. For each record the database name it belongs to is stored.
994 For searching, you can select databases by calling:
996 $sess->databases('db1','db2');
998 This will not do anything if the given and only the given databases are already selected. You can get the list of the actually selected databases, by calling:
1000 @dblist = $sess->databases();
1004 It's nice to be able to store data in your repository... But it's useful to reach it as well. So this is how to do searching:
1006 $rs = $sess->search(databases => [qw(demo1,demo2)], # optional
1007 pqf => '@attr 1=4 computer');
1009 This is going to execute a search in databases demo1 and demo2, for title 'com,puter'. This is a PQF (Prefix Query Format) search, see YAZ documentation for details. The database selection is optional: if it's provided, the given list of databases is selected for this particular search, then the original selection is restored.
1011 =head2 CCL searching
1013 Not all users enjoy typing in prefix query structures and numerical attribute values, even in a minimalistic test client. In the library world, the more intuitive Common Command Language (or ISO 8777) has enjoyed some popularity - especially before the widespread availability of graphical interfaces. It is still useful in applications where you for some reason or other need to provide a symbolic language for expressing boolean query structures.
1015 The CCL searching is not currently supported by this API.
1017 =head2 CQL searching
1019 CQL - Common Query Language - was defined for the SRW protocol. In many ways CQL has a similar syntax to CCL. The objective of CQL is different. Where CCL aims to be an end-user language, CQL is the protocol query language for SRW.
1021 In order to map CQL queries to Zebra internal search structures, you have to define a mapping, the way it is described in YAZ documentation: I<Specification of CQL to RPN mapping>. The mapping is interpreted by the method:
1023 $sess->cqlmap($mapfile);
1025 Or, you can directly provide the I<mapfile> parameter for the search:
1027 $rs = $sess->search(cqlmap => 'demo/cql.map',
1028 cql => 'dc.title=IDZebra');
1030 As you see, CQL searching is so simple: just give the query in the I<cql> parameter.
1034 If you'd like the search results to be sorted, use the I<sort> parameter:
1036 $rs = $sess->search(cql => 'IDZebra',
1039 Note, that B<currently> this is (almost) equivalent to
1041 $rs = $sess->search(cql => 'IDZebra');
1042 $rs->sort('1=4 ia');
1044 but in the further versions of Zebra and this API a single phase search and sort will take place, optimizing performance. For more details on sorting, see I<IDZebra::ResultSet> manpage.
1048 As you have seen, the result of the search request is a I<Resultset> object.
1049 It contains number of hits, and search status, and can be used to sort and retrieve the resulting records.
1051 $count = $rs->count;
1053 printf ("RS Status is %d (%s)\n", $rs->errCode, $rs->errString);
1055 I<$rs-E<gt>errCode> is 0, if there were no errors during search. Read the I<IDZebra::Resultset> manpage for more details.
1059 Zebra supports scanning index values. The result of the
1061 $sl = $sess->scan(expression => "a");
1063 call is an I<IDZebra::ScanList> object, what you can use to list the values. The scan expression has to be provided in a PQF like format. Examples:
1065 B< a> (scan trough words of "default", "Any" indexes)
1068 B< @attr 1=1016 a> (same effect)
1071 B< @attr 1=4 @attr 6=2 a> (scan trough titles as phrases)
1073 An illegal scan expression will cause your code to die. If you'd like to select databases just for the scan call, you can optionally use the I<databases> parameter:
1075 $sl = $sess->scan(expression => "a",
1076 databases => [qw(demo1 demo2)]);
1078 You can use the I<IDZebra::ScanList> object returned by the i<scan> method, to reach the result. Check I<IDZebra::ScanList> manpage for more details.
1080 =head1 SESSION STATUS AND ERRORS
1082 Most of the API calls causes die, if an error occures. You avoid this, by using eval {} blocks. The following methods are available to get the status of Zebra service:
1088 The Zebra provided error code... (for the result of the last call);
1092 Error string corresponding to the message
1096 Additional information for the status
1100 This functionality may change, see TODO.
1102 =head1 LOGGING AND MISC. FUNCTIONS
1104 Zebra provides logging facility for the internal events, and also for application developers trough the API. See manpage I<IDZebra::Logger> for details.
1108 =item B<IDZebra::LogFile($filename)>
1110 Will set the output file for logging. By default it's STDERR;
1112 =item B<IDZebra::LogLevel(15)>
1114 Set log level. 0 for no logs. See IDZebra::Logger for usable flags.
1118 Some other functions
1122 =item B<$sess-E<gt>init>
1124 Initialize, and clean registers. This will remove all data!
1126 =item B<$sess-E<gt>compact>
1128 Compact the registers (? does this work)
1130 =item B<$sess-E<gt>show>
1132 Doesn't have too much meaning. Don't try :)
1140 =item B<Clean up error handling>
1142 By default all zebra errors should cause die. (such situations could be avoided by using eval {}), and then check for errCode, errString... An optional flag or package variable should be introduced to override this, and skip zebra errors, to let the user decide what to do.
1144 =item B<Make the package self-distributable>
1146 Build and link with installed header and library files
1150 Test shadow system, unicode...
1154 Cleanup, arrange, remove redundancy
1164 Peter Popovics, pop@technomat.hu
1168 Zebra documentation, Zebra::ResultSet, Zebra::ScanList, Zebra::Logger manpages