1 ## This file is part of simpleserver
2 ## Copyright (C) 2000-2011 Index Data.
3 ## All rights reserved.
4 ## Redistribution and use in source and binary forms, with or without
5 ## modification, are permitted provided that the following conditions are met:
7 ## * Redistributions of source code must retain the above copyright
8 ## notice, this list of conditions and the following disclaimer.
9 ## * Redistributions in binary form must reproduce the above copyright
10 ## notice, this list of conditions and the following disclaimer in the
11 ## documentation and/or other materials provided with the distribution.
12 ## * Neither the name of Index Data nor the names of its contributors
13 ## may be used to endorse or promote products derived from this
14 ## software without specific prior written permission.
16 ## THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND ANY
17 ## EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 ## WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 ## DISCLAIMED. IN NO EVENT SHALL THE REGENTS AND CONTRIBUTORS BE LIABLE FOR ANY
20 ## DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 ## (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 ## LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 ## ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 ## (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
25 ## THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27 package Net::Z3950::SimpleServer;
30 use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
37 @ISA = qw(Exporter AutoLoader DynaLoader);
41 bootstrap Net::Z3950::SimpleServer $VERSION;
43 # Preloaded methods go here.
53 carp "SimpleServer.pm: WARNING: Multithreaded server unsupported";
57 croak "SimpleServer.pm: ERROR: Unspecified search handler" unless defined($self->{SEARCH});
58 croak "SimpleServer.pm: ERROR: Unspecified fetch handler" unless defined($self->{FETCH});
69 ### This modal internal interface, in which we set a bunch of
70 # globals and then call start_server(), is asking for
71 # trouble. Instead, we should just pass the $self object
72 # as a parameter into start_server().
73 if (defined($self->{GHANDLE})) {
74 set_ghandle($self->{GHANDLE});
76 if (defined($self->{INIT})) {
77 set_init_handler($self->{INIT});
79 set_search_handler($self->{SEARCH});
80 set_fetch_handler($self->{FETCH});
81 if (defined($self->{CLOSE})) {
82 set_close_handler($self->{CLOSE});
84 if (defined($self->{PRESENT})) {
85 set_present_handler($self->{PRESENT});
87 if (defined($self->{SCAN})) {
88 set_scan_handler($self->{SCAN});
90 if (defined($self->{SORT})) {
91 set_sort_handler($self->{SORT});
93 if (defined($self->{EXPLAIN})) {
94 set_explain_handler($self->{EXPLAIN});
96 if (defined($self->{DELETE})) {
97 set_delete_handler($self->{DELETE});
104 # Register packages that we will use in translated RPNs
105 package Net::Z3950::RPN::Node;
106 package Net::Z3950::APDU::Query;
107 our @ISA = qw(Net::Z3950::RPN::Node);
108 package Net::Z3950::APDU::OID;
109 package Net::Z3950::RPN::And;
110 our @ISA = qw(Net::Z3950::RPN::Node);
111 package Net::Z3950::RPN::Or;
112 our @ISA = qw(Net::Z3950::RPN::Node);
113 package Net::Z3950::RPN::AndNot;
114 our @ISA = qw(Net::Z3950::RPN::Node);
115 package Net::Z3950::RPN::Term;
116 our @ISA = qw(Net::Z3950::RPN::Node);
117 package Net::Z3950::RPN::RSID;
118 our @ISA = qw(Net::Z3950::RPN::Node);
119 package Net::Z3950::RPN::Attributes;
120 package Net::Z3950::RPN::Attribute;
123 # Utility method for re-rendering Type-1 query back down to PQF
124 package Net::Z3950::RPN::Node;
128 my $class = ref $this;
130 if ($class eq "Net::Z3950::APDU::Query") {
132 my $set = $this->{attributeSet};
133 $res .= "\@attrset $set " if defined $set;
134 return $res . $this->{query}->toPQF();
135 } elsif ($class eq "Net::Z3950::RPN::Or") {
136 return '@or ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
137 } elsif ($class eq "Net::Z3950::RPN::And") {
138 return '@and ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
139 } elsif ($class eq "Net::Z3950::RPN::AndNot") {
140 return '@not ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
141 } elsif ($class eq "Net::Z3950::RPN::RSID") {
142 return '@set ' . $this->{id};
143 } elsif ($class ne "Net::Z3950::RPN::Term") {
144 die "unknown PQF node-type '$class'";
148 foreach my $attr (@{ $this->{attributes} }) {
150 my $set = $attr->{attributeSet};
151 $res .= "$set " if defined $set;
152 $res .= $attr->{attributeType} . "=" . $attr->{attributeValue} . " ";
155 return $res . $this->{term};
159 # Must revert to original package for Autoloader's benefit
160 package Net::Z3950::SimpleServer;
163 # Autoload methods go after =cut, and are processed by the autosplit program.
167 # Below is the stub of documentation for your module. You better edit it!
171 Net::Z3950::SimpleServer - Simple Perl API for building Z39.50 servers.
175 use Net::Z3950::SimpleServer;
177 sub my_search_handler {
180 my $set_id = $args->{SETNAME};
181 my @database_list = @{ $args->{DATABASES} };
182 my $query = $args->{QUERY};
184 ## Perform the query on the specified set of databases
185 ## and return the number of hits:
187 $args->{HITS} = $hits;
190 sub my_fetch_handler { # Get a record for the user
193 my $set_id = $args->{SETNAME};
195 my $record = fetch_a_record($args->{OFFSET});
197 $args->{RECORD} = $record;
198 if (number_of_hits() == $args->{OFFSET}) { ## Last record in set?
205 ## Register custom event handlers:
206 my $z = new Net::Z3950::SimpleServer(GHANDLE = $someObject,
207 INIT => \&my_init_handler,
208 CLOSE => \&my_close_handler,
209 SEARCH => \&my_search_handler,
210 FETCH => \&my_fetch_handler);
213 $z->launch_server("ztest.pl", @ARGV);
217 The SimpleServer module is a tool for constructing Z39.50 "Information
218 Retrieval" servers in Perl. The module is easy to use, but it
219 does help to have an understanding of the Z39.50 query
220 structure and the construction of structured retrieval records.
222 Z39.50 is a network protocol for searching remote databases and
223 retrieving the results in the form of structured "records". It is widely
224 used in libraries around the world, as well as in the US Federal Government.
225 In addition, it is generally useful whenever you wish to integrate a number
226 of different database systems around a shared, abstract data model.
228 The model of the module is simple: It implements a "generic" Z39.50
229 server, which invokes callback functions supplied by you to search
230 for content in your database. You can use any tools available in
231 Perl to supply the content, including modules like DBI and
234 The server will take care of managing the network connections for
235 you, and it will spawn a new process (or thread, in some
236 environments) whenever a new connection is received.
238 The programmer can specify subroutines to take care of the following type
244 - Fetching of records
245 - Scan request (browsing)
246 - Closing down connection
248 Note that only the Search and Fetch handler functions are required.
249 The module can supply default responses to the other on its own.
251 After the launching of the server, all control is given away from
252 the Perl script to the server. The server calls the registered
253 subroutines to field incoming requests from Z39.50 clients.
255 A reference to an anonymous hash is passed to each handler. Some of
256 the entries of these hashes are to be considered input and others
259 The Perl programmer specifies the event handlers for the server by
260 means of the SimpleServer object constructor
262 my $z = new Net::Z3950::SimpleServer(
263 INIT => \&my_init_handler,
264 CLOSE => \&my_close_handler,
265 SEARCH => \&my_search_handler,
266 PRESENT => \&my_present_handler,
267 SCAN => \&my_scan_handler,
268 FETCH => \&my_fetch_handler,
269 EXPLAIN => \&my_explain_handler,
270 DELETE => \&my_delete_handler,
271 SORT => \&my_sort_handler);
273 In addition, the arguments to the constructor may include GHANDLE, a
274 global handle which is made available to each invocation of every
275 callback function. This is typically a reference to either a hash or
278 If you want your SimpleServer to start a thread (threaded mode) to
279 handle each incoming Z39.50 request instead of forking a process
280 (forking mode), you need to register the handlers by symbol rather
281 than by code reference. Thus, in threaded mode, you will need to
282 register your handlers this way:
284 my $z = new Net::Z3950::SimpleServer(
285 INIT => "my_package::my_init_handler",
286 CLOSE => "my_package::my_close_handler",
290 where my_package is the Perl package in which your handler is
293 After the custom event handlers are declared, the server is launched
294 by means of the method
296 $z->launch_server("MyServer.pl", @ARGV);
298 Notice, the first argument should be the name of your server
299 script (for logging purposes), while the rest of the arguments
300 are documented in the YAZ toolkit manual: The section on
301 application invocation: <http://indexdata.com/yaz/doc/server.invocation.tkl>
303 In particular, you need to use the -T switch to start your SimpleServer
308 The init handler is called whenever a Z39.50 client is attempting
309 to logon to the server. The exchange of parameters between the
310 server and the handler is carried out via an anonymous hash reached
315 The argument hash passed to the init handler has the form
318 ## Response parameters:
320 PEER_NAME => "", ## Name or IP address of connecting client
321 IMP_ID => "", ## Z39.50 Implementation ID
322 IMP_NAME => "", ## Z39.50 Implementation name
323 IMP_VER => "", ## Z39.50 Implementation version
324 ERR_CODE => 0, ## Error code, cnf. Z39.50 manual
325 ERR_STR => "", ## Error string (additional info.)
326 USER => "xxx" ## If Z39.50 authentication is used,
327 ## this member contains user name
328 PASS => "yyy" ## Under same conditions, this member
329 ## contains the password in clear text
330 GHANDLE => $obj ## Global handler specified at creation
331 HANDLE => undef ## Handler of Perl data structure
334 The HANDLE member can be used to store any scalar value which will then
335 be provided as input to all subsequent calls (ie. for searching, record
336 retrieval, etc.). A common use of the handle is to store a reference to
337 a hash which may then be used to store session-specific parameters.
338 If you have any session-specific information (such as a list of
339 result sets or a handle to a back-end search engine of some sort),
340 it is always best to store them in a private session structure -
341 rather than leaving them in global variables in your script.
343 The Implementation ID, name and version are only really used by Z39.50
344 client developers to see what kind of server they're dealing with.
345 Filling these in is optional.
347 The ERR_CODE should be left at 0 (the default value) if you wish to
348 accept the connection. Any other value is interpreted as a failure
349 and the client will be shown the door, with the code and the
350 associated additional information, ERR_STR returned.
352 =head2 Search handler
354 Similarly, the search handler is called with a reference to an anony-
355 mous hash. The structure is the following:
358 ## Request parameters:
360 GHANDLE => $obj ## Global handler specified at creation
361 HANDLE => ref, ## Your session reference.
362 SETNAME => "id", ## ID of the result set
363 REPL_SET => 0, ## Replace set if already existing?
364 DATABASES => ["xxx"], ## Reference to a list of data-
366 QUERY => "query", ## The query expression
367 RPN => $obj, ## Reference to a Net::Z3950::APDU::Query
369 ## Response parameters:
371 ERR_CODE => 0, ## Error code (0=Successful search)
372 ERR_STR => "", ## Error string
373 HITS => 0 ## Number of matches
376 Note that a search which finds 0 hits is considered successful in
377 Z39.50 terms - you should only set the ERR_CODE to a non-zero value
378 if there was a problem processing the request. The Z39.50 standard
379 provides a comprehensive list of standard diagnostic codes, and you
380 should use these whenever possible.
382 The QUERY is a tree-structure of terms combined by operators, the
383 terms being qualified by lists of attributes. The query is presented
384 to the search function in the Prefix Query Format (PQF) which is
385 used in many applications based on the YAZ toolkit. The full grammar
386 is described in the YAZ manual.
388 The following are all examples of valid queries in the PQF.
394 @or "dylan" "zimmerman"
398 @or @and bob dylan @set Result-1
400 @and @attr 1=1 "bob dylan" @attr 1=4 "slow train coming"
402 @attrset @attr 4=1 @attr 1=4 "self portrait"
404 You will need to write a recursive function or something similar to
405 parse incoming query expressions, and this is usually where a lot of
406 the work in writing a database-backend happens. Fortunately, you don't
407 need to support anymore functionality than you want to. For instance,
408 it is perfectly legal to not accept boolean operators, but you SHOULD
409 try to return good error codes if you run into something you can't or
412 A more convenient alternative to the QUERY member may be the RPN
413 member, which is a reference to a Net::Z3950::APDU::Query object
414 representing the RPN query tree. The structure of that object is
415 supposed to be self-documenting, but here's a brief summary of what
422 C<Net::Z3950::APDU::Query> is a hash with two fields:
428 =item C<attributeSet>
430 Optional. If present, it is a reference to a
431 C<Net::Z3950::APDU::OID>. This is a string of dot-separated integers
432 representing the OID of the query's top-level attribute set.
436 Mandatory: a reference to the RPN tree itself.
442 Each node of the tree is an object of one of the following types:
448 =item C<Net::Z3950::RPN::And>
450 =item C<Net::Z3950::RPN::Or>
452 =item C<Net::Z3950::RPN::AndNot>
454 These three classes are all arrays of two elements, each of which is a
455 node of one of the above types.
457 =item C<Net::Z3950::RPN::Term>
459 See below for details.
461 =item C<Net::Z3950::RPN::RSID>
463 A reference to a result-set ID indicating a previous search. The ID
464 of the result-set is in the C<id> element.
474 C<Net::Z3950::RPN::Term> is a hash with two fields:
482 A string containing the search term itself.
486 A reference to a C<Net::Z3950::RPN::Attributes> object.
492 C<Net::Z3950::RPN::Attributes> is an array of references to
493 C<Net::Z3950::RPN::Attribute> objects. (Note the plural/singular
498 C<Net::Z3950::RPN::Attribute> is a hash with three elements:
504 =item C<attributeSet>
506 Optional. If present, it is dot-separated OID string, as above.
508 =item C<attributeType>
510 An integer indicating the type of the attribute - for example, under
511 the BIB-1 attribute set, type 1 indicates a ``use'' attribute, type 2
512 a ``relation'' attribute, etc.
514 =item C<attributeValue>
516 An integer or string indicating the value of the attribute - for example, under
517 BIB-1, if the attribute type is 1, then value 4 indicates a title
518 search and 7 indicates an ISBN search; but if the attribute type is
519 2, then value 4 indicates a ``greater than or equal'' search, and 102
520 indicates a relevance match.
526 All of these classes except C<Attributes> and C<Attribute> are
527 subclasses of the abstract class C<Net::Z3950::RPN::Node>. That class
528 has a single method, C<toPQF()>, which may be used to turn an RPN
529 tree, or part of one, back into a textual prefix query.
531 Note that, apart to C<toPQF()>, none of these classes have any methods at
532 all: the blessing into classes is largely just a documentation thing
533 so that, for example, if you do
535 { use Data::Dumper; print Dumper($args->{RPN}) }
537 you get something fairly human-readable. But of course, the type
538 distinction between the three different kinds of boolean node is
541 By adding your own methods to these classes (building what I call
542 ``augmented classes''), you can easily build code that walks the tree
543 of the incoming RPN. Take a look at C<samples/render-search.pl> for a
544 sample implementation of such an augmented classes technique.
547 =head2 Present handler
549 The presence of a present handler in a SimpleServer front-end is optional.
550 Each time a client wishes to retrieve records, the present service is
551 called. The present service allows the origin to request a certain number
552 of records retrieved from a given result set.
553 When the present handler is called, the front-end server should prepare a
554 result set for fetching. In practice, this means to get access to the
555 data from the backend database and store the data in a temporary fashion
556 for fast and efficient fetching. The present handler does *not* fetch
557 anything. This task is taken care of by the fetch handler, which will be
558 called the correct number of times by the YAZ library. More about this
560 If no present handler is implemented in the front-end, the YAZ toolkit
561 will take care of a minimum of preparations itself. This default present
562 handler is sufficient in many situations, where only a small amount of
563 records are expected to be retrieved. If on the other hand, large result
564 sets are likely to occur, the implementation of a reasonable present
565 handler can gain performance significantly.
567 The information exchanged between client and present handle is:
570 ## Client/server request:
572 GHANDLE => $obj ## Global handler specified at creation
573 HANDLE => ref, ## Reference to datastructure
574 SETNAME => "id", ## Result set ID
575 START => xxx, ## Start position
576 COMP => "", ## Desired record composition
577 NUMBER => yyy, ## Number of requested records
580 ## Response parameters:
582 HITS => zzz, ## Number of returned records
583 ERR_CODE => 0, ## Error code
584 ERR_STR => "" ## Error message
590 The fetch handler is asked to retrieve a SINGLE record from a given
591 result set (the front-end server will automatically call the fetch
592 handler as many times as required).
594 The parameters exchanged between the server and the fetch handler are
597 ## Client/server request:
599 GHANDLE => $obj ## Global handler specified at creation
600 HANDLE => ref ## Reference to data structure
601 SETNAME => "id" ## ID of the requested result set
602 OFFSET => nnn ## Record offset number
603 REQ_FORM => "n.m.k.l"## Client requested format OID
604 COMP => "xyz" ## Formatting instructions
605 SCHEMA => "abc" ## Requested schema, if any
609 RECORD => "" ## Record string
610 BASENAME => "" ## Origin of returned record
611 LAST => 0 ## Last record in set?
612 ERR_CODE => 0 ## Error code
613 ERR_STR => "" ## Error string
614 SUR_FLAG => 0 ## Surrogate diagnostic flag
615 REP_FORM => "n.m.k.l"## Provided format OID
616 SCHEMA => "abc" ## Provided schema, if any
619 The REP_FORM value has by default the REQ_FORM value but can be set to
620 something different if the handler desires. The BASENAME value should
621 contain the name of the database from where the returned record originates.
622 The ERR_CODE and ERR_STR works the same way they do in the search
623 handler. If there is an error condition, the SUR_FLAG is used to
624 indicate whether the error condition pertains to the record currently
625 being retrieved, or whether it pertains to the operation as a whole
626 (eg. the client has specified a result set which does not exist.)
628 If you need to return USMARC records, you might want to have a look at
629 the MARC module on CPAN, if you don't already have a way of generating
632 NOTE: The record offset is 1-indexed - 1 is the offset of the first
637 A full featured Z39.50 server should support scan (or in some literature
638 browse). The client specifies a starting term of the scan, and the server
639 should return an ordered list of specified length consisting of terms
640 actually occurring in the data base. Each of these terms should be close
641 to or equal to the term originally specified. The quality of scan compared
642 to simple search is a guarantee of hits. It is simply like browsing through
643 an index of a book, you always find something! The parameters exchanged are
648 GHANDLE => $obj, ## Global handler specified at creation
649 HANDLE => $ref, ## Reference to data structure
650 DATABASES => ["xxx"], ## Reference to a list of data-
652 TERM => 'start', ## The start term
653 RPN => $obj, ## Reference to a Net::Z3950::RPN::Term
655 NUMBER => xx, ## Number of requested terms
656 POS => yy, ## Position of starting point
657 ## within returned list
658 STEP => 0, ## Step size
662 ERR_CODE => 0, ## Error code
663 ERR_STR => '', ## Diagnostic message
664 NUMBER => zz, ## Number of returned terms
665 STATUS => $status, ## ScanSuccess/ScanFailure
666 ENTRIES => $entries ## Referenced list of terms
669 where the term list is returned by reference in the scalar $entries, which
670 should point at a data structure of this kind,
676 { TERM => 'energy density',
679 { TERM => 'energy flow',
687 The $status flag is only meaningful after a successful scan, and
688 should be assigned one of two values:
690 Net::Z3950::SimpleServer::ScanSuccess Full success (default)
691 Net::Z3950::SimpleServer::ScanPartial Fewer terms returned than requested
693 The STEP member contains the requested number of entries in the term-list
694 between two adjacent entries in the response.
696 A better alternative to the TERM member is the the RPN
697 member, which is a reference to a Net::Z3950::RPN::Term object
698 representing the scan clause. The structure of that object is the
699 same as for Term objects included as part of the RPN tree passed to
700 search handlers. This is more useful than the simple TERM because it
701 includes attributes (e.g. access points associated with the term),
702 which are discarded by the TERM element.
706 The argument hash received by the close handler has two elements only:
711 GHANDLE => $obj ## Global handler specified at creation
712 HANDLE => ref ## Reference to data structure
715 What ever data structure the HANDLE value points at goes out of scope
716 after this call. If you need to close down a connection to your server
717 or something similar, this is the place to do it.
719 =head2 Delete handler
721 The argument hash received by the delete handler has the following elements:
725 GHANDLE => $obj, ## Global handler specified at creation
726 HANDLE => ref, ## Reference to data structure
727 SETNAME => "id", ## Result set ID
730 STATUS => 0 ## Deletion status
733 The SETNAME element of the argument hash may or may not be defined.
734 If it is, then SETNAME is the name of a result set to be deleted; if
735 not, then all result-sets associated with the current session should
736 be deleted. In either case, the callback function should report on
737 success or failure by setting the STATUS element either to zero, on
738 success, or to an integer from 1 to 10, to indicate one of the ten
739 possible failure codes described in section 3.2.4.1.4 of the Z39.50
741 http://www.loc.gov/z3950/agency/markup/05.html#Delete-list-statuses1
745 The argument hash received by the sort handler has the following elements:
749 GHANDLE => $obj, ## Global handler specified at creation
750 HANDLE => ref, ## Reference to data structure
751 INPUT => [ a, b ... ], ## Names of result-sets to sort
752 OUTPUT => "name", ## Name of result-set to sort into
753 SEQUENCE ## Sort specification: see below
756 STATUS => 0, ## Success, Partial or Failure
757 ERR_CODE => 0, ## Error code
758 ERR_STR => '', ## Diagnostic message
762 The SEQUENCE element is a reference to an array, each element of which
763 is a hash representing a sort key. Each hash contains the following
770 0 for an ascending sort, 1 for descending, 3 for ascending by
771 frequency, or 4 for descending by frequency.
775 0 for a case-sensitive sort, 1 for case-insensitive
779 How to respond if one or more records in the set to be sorted are
780 missing the fields indicated in the sort specification. 1 to abort
781 the sort, 2 to use a "null value", 3 if a value is provided to use in
782 place of the missing data (although in the latter case, the actual
783 value to use is currently not made available, so this is useless).
787 And one or other of the following:
793 A string indicating the field to be sorted, which the server may
794 interpret as it sees fit (presumably by an out-of-band agreement with
797 =item ELEMENTSPEC_TYPE and ELEMENTSPEC_VALUE
799 I have no idea what this is.
801 =item ATTRSET and SORT_ATTR
803 ATTRSET is the attribute set from which the attributes are taken, and
804 SORT_ATTR is a reference to an array containing the attributes
805 themselves. Each attribute is represented by (are you following this
806 carefully?) yet another hash, this one containing the elements
807 ATTR_TYPE and ATTR_VALUE: for example, type=1 and value=4 in the BIB-1
808 attribute set would indicate access-point 4 which is title, so that a
809 sort of title is requested.
813 Precisely why all of the above is so is not clear, but goes some way
814 to explain why, in the Z39.50 world, the developers of the standard
815 are not so much worshiped as blamed.
817 The backend function should set STATUS to 0 on success, 1 for "partial
818 success" (don't ask) or 2 on failure, in which case ERR_CODE and
819 ERR_STR should be set.
821 =head2 Support for SRU and SRW
823 Since release 1.0, SimpleServer includes support for serving the SRU
824 and SRW protocols as well as Z39.50. These ``web-friendly'' protocols
825 enable similar functionality to that of Z39.50, but by means of rich
826 URLs in the case of SRU, and a SOAP-based web-service in the case of
827 SRW. These protocols are described at
828 http://www.loc.gov/sru
830 In order to serve these protocols from a SimpleServer-based
831 application, it is necessary to launch the application with a YAZ
832 Generic Frontend Server (GFS) configuration file, which can be
833 specified using the command-line argument C<-f> I<filename>. A
834 minimal configuration file looks like this:
838 <cql2rpn>pqf.properties</cql2rpn>
842 This file specifies only that C<pqf.properties> should be used to
843 translate the CQL queries of SRU and SRW into corresponding Z39.50
844 Type-1 queries. For more information about YAZ GFS configuration,
845 including how to specify an Explain record, see the I<Virtual Hosts>
846 section of the YAZ manual at
847 http://indexdata.com/yaz/doc/server.vhosts.tkl
849 The mapping of CQL queries into Z39.50 Type-1 queries is specified by
850 a file that indicates which BIB-1 attributes should be generated for
851 each CQL index, relation, modifiers, etc. A typical section of this
852 file looks like this:
855 index.dc.subject = 1=21
856 index.dc.creator = 1=1003
860 This file specifies the BIB-1 access points (type=1) for the Dublin
861 Core indexes C<title>, C<subject> and C<creator>, and the BIB-1
862 relations (type=2) corresponding to the CQL relations C<E<lt>> and
863 C<E<lt>=>. For more information about the format of this file, see
864 the I<CQL> section of the YAZ manual at
865 http://indexdata.com/yaz/doc/tools.tkl#tools.cql
867 The YAZ distribution include a sample CQL-to-PQF mapping configuration
868 file called C<pqf.properties>; this is sufficient for many
869 applications, and a good base to work from for most others.
871 If a SimpleServer-based application is run without this SRU-specific
872 configuration, it can still serve SRU; however, CQL queries will not
873 be translated, but passed straight through to the search-handler
874 function, as the C<CQL> member of the parameters hash. It is then the
875 responsibility of the back-end application to parse and handle the CQL
876 query, which is most easily done using Ed Summers' fine C<CQL::Parser>
877 module, available from CPAN at
878 http://search.cpan.org/~esummers/CQL-Parser/
882 Anders Sønderberg (sondberg@indexdata.dk),
883 Sebastian Hammer (quinn@indexdata.dk),
884 Mike Taylor (indexdata.com).
886 =head1 COPYRIGHT AND LICENCE
888 Copyright (C) 2000-2011 by Index Data.
890 This library is free software; you can redistribute it and/or modify
891 it under the same terms as Perl itself, either Perl version 5.8.4 or,
892 at your option, any later version of Perl 5 you may have available.
896 Any Perl module which is useful for accessing the data source of your