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;
121 package Net::Z3950::FacetList;
122 package Net::Z3950::FacetField;
123 package Net::Z3950::FacetTerms;
124 package Net::Z3950::FacetTerm;
127 # Utility method for re-rendering Type-1 query back down to PQF
128 package Net::Z3950::RPN::Node;
132 my $class = ref $this;
134 if ($class eq "Net::Z3950::APDU::Query") {
136 my $set = $this->{attributeSet};
137 $res .= "\@attrset $set " if defined $set;
138 return $res . $this->{query}->toPQF();
139 } elsif ($class eq "Net::Z3950::RPN::Or") {
140 return '@or ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
141 } elsif ($class eq "Net::Z3950::RPN::And") {
142 return '@and ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
143 } elsif ($class eq "Net::Z3950::RPN::AndNot") {
144 return '@not ' . $this->[0]->toPQF() . ' ' . $this->[1]->toPQF();
145 } elsif ($class eq "Net::Z3950::RPN::RSID") {
146 return '@set ' . $this->{id};
147 } elsif ($class ne "Net::Z3950::RPN::Term") {
148 die "unknown PQF node-type '$class'";
152 foreach my $attr (@{ $this->{attributes} }) {
154 my $set = $attr->{attributeSet};
155 $res .= "$set " if defined $set;
156 $res .= $attr->{attributeType} . "=" . $attr->{attributeValue} . " ";
159 return $res . $this->{term};
163 # Must revert to original package for Autoloader's benefit
164 package Net::Z3950::SimpleServer;
167 # Autoload methods go after =cut, and are processed by the autosplit program.
171 # Below is the stub of documentation for your module. You better edit it!
175 Net::Z3950::SimpleServer - Simple Perl API for building Z39.50 servers.
179 use Net::Z3950::SimpleServer;
181 sub my_search_handler {
184 my $set_id = $args->{SETNAME};
185 my @database_list = @{ $args->{DATABASES} };
186 my $query = $args->{QUERY};
188 ## Perform the query on the specified set of databases
189 ## and return the number of hits:
191 $args->{HITS} = $hits;
194 sub my_fetch_handler { # Get a record for the user
197 my $set_id = $args->{SETNAME};
199 my $record = fetch_a_record($args->{OFFSET});
201 $args->{RECORD} = $record;
202 if (number_of_hits() == $args->{OFFSET}) { ## Last record in set?
209 ## Register custom event handlers:
210 my $z = new Net::Z3950::SimpleServer(GHANDLE = $someObject,
211 INIT => \&my_init_handler,
212 CLOSE => \&my_close_handler,
213 SEARCH => \&my_search_handler,
214 FETCH => \&my_fetch_handler);
217 $z->launch_server("ztest.pl", @ARGV);
221 The SimpleServer module is a tool for constructing Z39.50 "Information
222 Retrieval" servers in Perl. The module is easy to use, but it
223 does help to have an understanding of the Z39.50 query
224 structure and the construction of structured retrieval records.
226 Z39.50 is a network protocol for searching remote databases and
227 retrieving the results in the form of structured "records". It is widely
228 used in libraries around the world, as well as in the US Federal Government.
229 In addition, it is generally useful whenever you wish to integrate a number
230 of different database systems around a shared, abstract data model.
232 The model of the module is simple: It implements a "generic" Z39.50
233 server, which invokes callback functions supplied by you to search
234 for content in your database. You can use any tools available in
235 Perl to supply the content, including modules like DBI and
238 The server will take care of managing the network connections for
239 you, and it will spawn a new process (or thread, in some
240 environments) whenever a new connection is received.
242 The programmer can specify subroutines to take care of the following type
248 - Fetching of records
249 - Scan request (browsing)
250 - Closing down connection
252 Note that only the Search and Fetch handler functions are required.
253 The module can supply default responses to the other on its own.
255 After the launching of the server, all control is given away from
256 the Perl script to the server. The server calls the registered
257 subroutines to field incoming requests from Z39.50 clients.
259 A reference to an anonymous hash is passed to each handler. Some of
260 the entries of these hashes are to be considered input and others
263 The Perl programmer specifies the event handlers for the server by
264 means of the SimpleServer object constructor
266 my $z = new Net::Z3950::SimpleServer(
267 INIT => \&my_init_handler,
268 CLOSE => \&my_close_handler,
269 SEARCH => \&my_search_handler,
270 PRESENT => \&my_present_handler,
271 SCAN => \&my_scan_handler,
272 FETCH => \&my_fetch_handler,
273 EXPLAIN => \&my_explain_handler,
274 DELETE => \&my_delete_handler,
275 SORT => \&my_sort_handler);
277 In addition, the arguments to the constructor may include GHANDLE, a
278 global handle which is made available to each invocation of every
279 callback function. This is typically a reference to either a hash or
282 If you want your SimpleServer to start a thread (threaded mode) to
283 handle each incoming Z39.50 request instead of forking a process
284 (forking mode), you need to register the handlers by symbol rather
285 than by code reference. Thus, in threaded mode, you will need to
286 register your handlers this way:
288 my $z = new Net::Z3950::SimpleServer(
289 INIT => "my_package::my_init_handler",
290 CLOSE => "my_package::my_close_handler",
294 where my_package is the Perl package in which your handler is
297 After the custom event handlers are declared, the server is launched
298 by means of the method
300 $z->launch_server("MyServer.pl", @ARGV);
302 Notice, the first argument should be the name of your server
303 script (for logging purposes), while the rest of the arguments
304 are documented in the YAZ toolkit manual: The section on
305 application invocation: <http://indexdata.com/yaz/doc/server.invocation.tkl>
307 In particular, you need to use the -T switch to start your SimpleServer
312 The init handler is called whenever a Z39.50 client is attempting
313 to logon to the server. The exchange of parameters between the
314 server and the handler is carried out via an anonymous hash reached
319 The argument hash passed to the init handler has the form
322 ## Response parameters:
324 PEER_NAME => "", ## Name or IP address of connecting client
325 IMP_ID => "", ## Z39.50 Implementation ID
326 IMP_NAME => "", ## Z39.50 Implementation name
327 IMP_VER => "", ## Z39.50 Implementation version
328 ERR_CODE => 0, ## Error code, cnf. Z39.50 manual
329 ERR_STR => "", ## Error string (additional info.)
330 USER => "xxx" ## If Z39.50 authentication is used,
331 ## this member contains user name
332 PASS => "yyy" ## Under same conditions, this member
333 ## contains the password in clear text
334 GHANDLE => $obj ## Global handler specified at creation
335 HANDLE => undef ## Handler of Perl data structure
338 The HANDLE member can be used to store any scalar value which will then
339 be provided as input to all subsequent calls (ie. for searching, record
340 retrieval, etc.). A common use of the handle is to store a reference to
341 a hash which may then be used to store session-specific parameters.
342 If you have any session-specific information (such as a list of
343 result sets or a handle to a back-end search engine of some sort),
344 it is always best to store them in a private session structure -
345 rather than leaving them in global variables in your script.
347 The Implementation ID, name and version are only really used by Z39.50
348 client developers to see what kind of server they're dealing with.
349 Filling these in is optional.
351 The ERR_CODE should be left at 0 (the default value) if you wish to
352 accept the connection. Any other value is interpreted as a failure
353 and the client will be shown the door, with the code and the
354 associated additional information, ERR_STR returned.
356 =head2 Search handler
358 Similarly, the search handler is called with a reference to an anony-
359 mous hash. The structure is the following:
362 ## Request parameters:
364 GHANDLE => $obj ## Global handler specified at creation
365 HANDLE => ref, ## Your session reference.
366 SETNAME => "id", ## ID of the result set
367 REPL_SET => 0, ## Replace set if already existing?
368 DATABASES => ["xxx"], ## Reference to a list of data-
370 QUERY => "query", ## The query expression
371 RPN => $obj, ## Reference to a Net::Z3950::APDU::Query
373 ## Response parameters:
375 ERR_CODE => 0, ## Error code (0=Successful search)
376 ERR_STR => "", ## Error string
377 HITS => 0 ## Number of matches
380 Note that a search which finds 0 hits is considered successful in
381 Z39.50 terms - you should only set the ERR_CODE to a non-zero value
382 if there was a problem processing the request. The Z39.50 standard
383 provides a comprehensive list of standard diagnostic codes, and you
384 should use these whenever possible.
386 The QUERY is a tree-structure of terms combined by operators, the
387 terms being qualified by lists of attributes. The query is presented
388 to the search function in the Prefix Query Format (PQF) which is
389 used in many applications based on the YAZ toolkit. The full grammar
390 is described in the YAZ manual.
392 The following are all examples of valid queries in the PQF.
398 @or "dylan" "zimmerman"
402 @or @and bob dylan @set Result-1
404 @and @attr 1=1 "bob dylan" @attr 1=4 "slow train coming"
406 @attrset @attr 4=1 @attr 1=4 "self portrait"
408 You will need to write a recursive function or something similar to
409 parse incoming query expressions, and this is usually where a lot of
410 the work in writing a database-backend happens. Fortunately, you don't
411 need to support anymore functionality than you want to. For instance,
412 it is perfectly legal to not accept boolean operators, but you SHOULD
413 try to return good error codes if you run into something you can't or
416 A more convenient alternative to the QUERY member may be the RPN
417 member, which is a reference to a Net::Z3950::APDU::Query object
418 representing the RPN query tree. The structure of that object is
419 supposed to be self-documenting, but here's a brief summary of what
426 C<Net::Z3950::APDU::Query> is a hash with two fields:
432 =item C<attributeSet>
434 Optional. If present, it is a reference to a
435 C<Net::Z3950::APDU::OID>. This is a string of dot-separated integers
436 representing the OID of the query's top-level attribute set.
440 Mandatory: a reference to the RPN tree itself.
446 Each node of the tree is an object of one of the following types:
452 =item C<Net::Z3950::RPN::And>
454 =item C<Net::Z3950::RPN::Or>
456 =item C<Net::Z3950::RPN::AndNot>
458 These three classes are all arrays of two elements, each of which is a
459 node of one of the above types.
461 =item C<Net::Z3950::RPN::Term>
463 See below for details.
465 =item C<Net::Z3950::RPN::RSID>
467 A reference to a result-set ID indicating a previous search. The ID
468 of the result-set is in the C<id> element.
478 C<Net::Z3950::RPN::Term> is a hash with two fields:
486 A string containing the search term itself.
490 A reference to a C<Net::Z3950::RPN::Attributes> object.
496 C<Net::Z3950::RPN::Attributes> is an array of references to
497 C<Net::Z3950::RPN::Attribute> objects. (Note the plural/singular
502 C<Net::Z3950::RPN::Attribute> is a hash with three elements:
508 =item C<attributeSet>
510 Optional. If present, it is dot-separated OID string, as above.
512 =item C<attributeType>
514 An integer indicating the type of the attribute - for example, under
515 the BIB-1 attribute set, type 1 indicates a ``use'' attribute, type 2
516 a ``relation'' attribute, etc.
518 =item C<attributeValue>
520 An integer or string indicating the value of the attribute - for example, under
521 BIB-1, if the attribute type is 1, then value 4 indicates a title
522 search and 7 indicates an ISBN search; but if the attribute type is
523 2, then value 4 indicates a ``greater than or equal'' search, and 102
524 indicates a relevance match.
530 All of these classes except C<Attributes> and C<Attribute> are
531 subclasses of the abstract class C<Net::Z3950::RPN::Node>. That class
532 has a single method, C<toPQF()>, which may be used to turn an RPN
533 tree, or part of one, back into a textual prefix query.
535 Note that, apart to C<toPQF()>, none of these classes have any methods at
536 all: the blessing into classes is largely just a documentation thing
537 so that, for example, if you do
539 { use Data::Dumper; print Dumper($args->{RPN}) }
541 you get something fairly human-readable. But of course, the type
542 distinction between the three different kinds of boolean node is
545 By adding your own methods to these classes (building what I call
546 ``augmented classes''), you can easily build code that walks the tree
547 of the incoming RPN. Take a look at C<samples/render-search.pl> for a
548 sample implementation of such an augmented classes technique.
551 =head2 Present handler
553 The presence of a present handler in a SimpleServer front-end is optional.
554 Each time a client wishes to retrieve records, the present service is
555 called. The present service allows the origin to request a certain number
556 of records retrieved from a given result set.
557 When the present handler is called, the front-end server should prepare a
558 result set for fetching. In practice, this means to get access to the
559 data from the backend database and store the data in a temporary fashion
560 for fast and efficient fetching. The present handler does *not* fetch
561 anything. This task is taken care of by the fetch handler, which will be
562 called the correct number of times by the YAZ library. More about this
564 If no present handler is implemented in the front-end, the YAZ toolkit
565 will take care of a minimum of preparations itself. This default present
566 handler is sufficient in many situations, where only a small amount of
567 records are expected to be retrieved. If on the other hand, large result
568 sets are likely to occur, the implementation of a reasonable present
569 handler can gain performance significantly.
571 The information exchanged between client and present handle is:
574 ## Client/server request:
576 GHANDLE => $obj ## Global handler specified at creation
577 HANDLE => ref, ## Reference to datastructure
578 SETNAME => "id", ## Result set ID
579 START => xxx, ## Start position
580 COMP => "", ## Desired record composition
581 NUMBER => yyy, ## Number of requested records
584 ## Response parameters:
586 HITS => zzz, ## Number of returned records
587 ERR_CODE => 0, ## Error code
588 ERR_STR => "" ## Error message
594 The fetch handler is asked to retrieve a SINGLE record from a given
595 result set (the front-end server will automatically call the fetch
596 handler as many times as required).
598 The parameters exchanged between the server and the fetch handler are
601 ## Client/server request:
603 GHANDLE => $obj ## Global handler specified at creation
604 HANDLE => ref ## Reference to data structure
605 SETNAME => "id" ## ID of the requested result set
606 OFFSET => nnn ## Record offset number
607 REQ_FORM => "n.m.k.l"## Client requested format OID
608 COMP => "xyz" ## Formatting instructions
609 SCHEMA => "abc" ## Requested schema, if any
613 RECORD => "" ## Record string
614 BASENAME => "" ## Origin of returned record
615 LAST => 0 ## Last record in set?
616 ERR_CODE => 0 ## Error code
617 ERR_STR => "" ## Error string
618 SUR_FLAG => 0 ## Surrogate diagnostic flag
619 REP_FORM => "n.m.k.l"## Provided format OID
620 SCHEMA => "abc" ## Provided schema, if any
623 The REP_FORM value has by default the REQ_FORM value but can be set to
624 something different if the handler desires. The BASENAME value should
625 contain the name of the database from where the returned record originates.
626 The ERR_CODE and ERR_STR works the same way they do in the search
627 handler. If there is an error condition, the SUR_FLAG is used to
628 indicate whether the error condition pertains to the record currently
629 being retrieved, or whether it pertains to the operation as a whole
630 (eg. the client has specified a result set which does not exist.)
632 If you need to return USMARC records, you might want to have a look at
633 the MARC module on CPAN, if you don't already have a way of generating
636 NOTE: The record offset is 1-indexed - 1 is the offset of the first
641 A full featured Z39.50 server should support scan (or in some literature
642 browse). The client specifies a starting term of the scan, and the server
643 should return an ordered list of specified length consisting of terms
644 actually occurring in the data base. Each of these terms should be close
645 to or equal to the term originally specified. The quality of scan compared
646 to simple search is a guarantee of hits. It is simply like browsing through
647 an index of a book, you always find something! The parameters exchanged are
652 GHANDLE => $obj, ## Global handler specified at creation
653 HANDLE => $ref, ## Reference to data structure
654 DATABASES => ["xxx"], ## Reference to a list of data-
656 TERM => 'start', ## The start term
657 RPN => $obj, ## Reference to a Net::Z3950::RPN::Term
659 NUMBER => xx, ## Number of requested terms
660 POS => yy, ## Position of starting point
661 ## within returned list
662 STEP => 0, ## Step size
666 ERR_CODE => 0, ## Error code
667 ERR_STR => '', ## Diagnostic message
668 NUMBER => zz, ## Number of returned terms
669 STATUS => $status, ## ScanSuccess/ScanFailure
670 ENTRIES => $entries ## Referenced list of terms
673 where the term list is returned by reference in the scalar $entries, which
674 should point at a data structure of this kind,
680 { TERM => 'energy density',
683 { TERM => 'energy flow',
691 The $status flag is only meaningful after a successful scan, and
692 should be assigned one of two values:
694 Net::Z3950::SimpleServer::ScanSuccess Full success (default)
695 Net::Z3950::SimpleServer::ScanPartial Fewer terms returned than requested
697 The STEP member contains the requested number of entries in the term-list
698 between two adjacent entries in the response.
700 A better alternative to the TERM member is the the RPN
701 member, which is a reference to a Net::Z3950::RPN::Term object
702 representing the scan clause. The structure of that object is the
703 same as for Term objects included as part of the RPN tree passed to
704 search handlers. This is more useful than the simple TERM because it
705 includes attributes (e.g. access points associated with the term),
706 which are discarded by the TERM element.
710 The argument hash received by the close handler has two elements only:
715 GHANDLE => $obj ## Global handler specified at creation
716 HANDLE => ref ## Reference to data structure
719 What ever data structure the HANDLE value points at goes out of scope
720 after this call. If you need to close down a connection to your server
721 or something similar, this is the place to do it.
723 =head2 Delete handler
725 The argument hash received by the delete handler has the following elements:
729 GHANDLE => $obj, ## Global handler specified at creation
730 HANDLE => ref, ## Reference to data structure
731 SETNAME => "id", ## Result set ID
734 STATUS => 0 ## Deletion status
737 The SETNAME element of the argument hash may or may not be defined.
738 If it is, then SETNAME is the name of a result set to be deleted; if
739 not, then all result-sets associated with the current session should
740 be deleted. In either case, the callback function should report on
741 success or failure by setting the STATUS element either to zero, on
742 success, or to an integer from 1 to 10, to indicate one of the ten
743 possible failure codes described in section 3.2.4.1.4 of the Z39.50
745 http://www.loc.gov/z3950/agency/markup/05.html#Delete-list-statuses1
749 The argument hash received by the sort handler has the following elements:
753 GHANDLE => $obj, ## Global handler specified at creation
754 HANDLE => ref, ## Reference to data structure
755 INPUT => [ a, b ... ], ## Names of result-sets to sort
756 OUTPUT => "name", ## Name of result-set to sort into
757 SEQUENCE ## Sort specification: see below
760 STATUS => 0, ## Success, Partial or Failure
761 ERR_CODE => 0, ## Error code
762 ERR_STR => '', ## Diagnostic message
766 The SEQUENCE element is a reference to an array, each element of which
767 is a hash representing a sort key. Each hash contains the following
774 0 for an ascending sort, 1 for descending, 3 for ascending by
775 frequency, or 4 for descending by frequency.
779 0 for a case-sensitive sort, 1 for case-insensitive
783 How to respond if one or more records in the set to be sorted are
784 missing the fields indicated in the sort specification. 1 to abort
785 the sort, 2 to use a "null value", 3 if a value is provided to use in
786 place of the missing data (although in the latter case, the actual
787 value to use is currently not made available, so this is useless).
791 And one or other of the following:
797 A string indicating the field to be sorted, which the server may
798 interpret as it sees fit (presumably by an out-of-band agreement with
801 =item ELEMENTSPEC_TYPE and ELEMENTSPEC_VALUE
803 I have no idea what this is.
805 =item ATTRSET and SORT_ATTR
807 ATTRSET is the attribute set from which the attributes are taken, and
808 SORT_ATTR is a reference to an array containing the attributes
809 themselves. Each attribute is represented by (are you following this
810 carefully?) yet another hash, this one containing the elements
811 ATTR_TYPE and ATTR_VALUE: for example, type=1 and value=4 in the BIB-1
812 attribute set would indicate access-point 4 which is title, so that a
813 sort of title is requested.
817 Precisely why all of the above is so is not clear, but goes some way
818 to explain why, in the Z39.50 world, the developers of the standard
819 are not so much worshiped as blamed.
821 The backend function should set STATUS to 0 on success, 1 for "partial
822 success" (don't ask) or 2 on failure, in which case ERR_CODE and
823 ERR_STR should be set.
825 =head2 Support for SRU and SRW
827 Since release 1.0, SimpleServer includes support for serving the SRU
828 and SRW protocols as well as Z39.50. These ``web-friendly'' protocols
829 enable similar functionality to that of Z39.50, but by means of rich
830 URLs in the case of SRU, and a SOAP-based web-service in the case of
831 SRW. These protocols are described at
832 http://www.loc.gov/sru
834 In order to serve these protocols from a SimpleServer-based
835 application, it is necessary to launch the application with a YAZ
836 Generic Frontend Server (GFS) configuration file, which can be
837 specified using the command-line argument C<-f> I<filename>. A
838 minimal configuration file looks like this:
842 <cql2rpn>pqf.properties</cql2rpn>
846 This file specifies only that C<pqf.properties> should be used to
847 translate the CQL queries of SRU and SRW into corresponding Z39.50
848 Type-1 queries. For more information about YAZ GFS configuration,
849 including how to specify an Explain record, see the I<Virtual Hosts>
850 section of the YAZ manual at
851 http://indexdata.com/yaz/doc/server.vhosts.tkl
853 The mapping of CQL queries into Z39.50 Type-1 queries is specified by
854 a file that indicates which BIB-1 attributes should be generated for
855 each CQL index, relation, modifiers, etc. A typical section of this
856 file looks like this:
859 index.dc.subject = 1=21
860 index.dc.creator = 1=1003
864 This file specifies the BIB-1 access points (type=1) for the Dublin
865 Core indexes C<title>, C<subject> and C<creator>, and the BIB-1
866 relations (type=2) corresponding to the CQL relations C<E<lt>> and
867 C<E<lt>=>. For more information about the format of this file, see
868 the I<CQL> section of the YAZ manual at
869 http://indexdata.com/yaz/doc/tools.tkl#tools.cql
871 The YAZ distribution include a sample CQL-to-PQF mapping configuration
872 file called C<pqf.properties>; this is sufficient for many
873 applications, and a good base to work from for most others.
875 If a SimpleServer-based application is run without this SRU-specific
876 configuration, it can still serve SRU; however, CQL queries will not
877 be translated, but passed straight through to the search-handler
878 function, as the C<CQL> member of the parameters hash. It is then the
879 responsibility of the back-end application to parse and handle the CQL
880 query, which is most easily done using Ed Summers' fine C<CQL::Parser>
881 module, available from CPAN at
882 http://search.cpan.org/~esummers/CQL-Parser/
886 Anders Sønderberg (sondberg@indexdata.dk),
887 Sebastian Hammer (quinn@indexdata.dk),
888 Mike Taylor (indexdata.com).
890 =head1 COPYRIGHT AND LICENCE
892 Copyright (C) 2000-2011 by Index Data.
894 This library is free software; you can redistribute it and/or modify
895 it under the same terms as Perl itself, either Perl version 5.8.4 or,
896 at your option, any later version of Perl 5 you may have available.
900 Any Perl module which is useful for accessing the data source of your