Refactor rpn2perl() to clarify structure.

[simpleserver-moved-to-github.git] / SimpleServer.pm

diff --git a/SimpleServer.pm b/SimpleServer.pm
index e77f78a..f6a4c39 100644 (file)
--- a/SimpleServer.pm
+++ b/SimpleServer.pm
@@ -1,5 +1,5 @@
 ##
 ##

-##  Copyright (c) 2000-2004, Index Data.
+##  Copyright (c) 2000-2006, Index Data.

 ##
 ##  Permission to use, copy, modify, distribute, and sell this software and
 ##  its documentation, in whole or in part, for any purpose, is hereby granted,
 ##
 ##  Permission to use, copy, modify, distribute, and sell this software and
 ##  its documentation, in whole or in part, for any purpose, is hereby granted,

@@ -25,56 +25,7 @@
 ##
 ##
 
 ##
 ##
 

-## $Log: SimpleServer.pm,v $
-## Revision 1.19  2004-05-13 19:04:32  adam
-## Bump year
-##
-## Revision 1.18  2003/09/09 20:12:38  mike
-## Return diagnostics on Init failure
-##
-## Revision 1.17  2003/09/09 11:40:10  mike
-## (Finally!) support implementation-ID
-##
-## Revision 1.16  2003/01/03 09:01:51  sondberg
-## Version 0.07.
-##
-## Revision 1.15  2002/09/16 14:00:16  sondberg
-## Updated Changes and added a few lines of documentation.
-##
-## Revision 1.14  2002/03/06 11:30:02  mike
-## Add RPN structure documentation to SimpleServer.pm's POD.
-## Add README to MANIFEST.
-##
-## Revision 1.13  2002/03/06 11:02:04  mike
-## Added simple README file, derived from POD comments in SimpleServer.pm
-## Fixed my (Mike Taylor's) email address
-##
-## Revision 1.12  2002/03/05 20:52:22  sondberg
-## Version 0.05 so that we can release the thing at CPAN.
-##
-## Revision 1.11  2002/03/05 20:49:56  sondberg
-## Added a couple of lines of documentation.
-##
-## Revision 1.10  2002/02/28 11:21:57  mike
-## Add RPN structure to search-handler argument hash.
-##
-## Revision 1.9  2001/08/29 11:48:36  sondberg
-## Added routines
-##
-##     Net::Z3950::SimpleServer::ScanSuccess
-##     Net::Z3950::SimpleServer::ScanPartial
-##
-## and a bit of documentation.
-##
-## Revision 1.8  2001/08/29 10:29:51  sondberg
-## Added some documentation of scan.
-##
-## Revision 1.7  2001/08/24 14:00:20  sondberg
-## Added support for scan.
-##
-## Revision 1.6  2001/03/13 14:17:15  sondberg
-## Added support for GRS-1.
-##
+## $Id: SimpleServer.pm,v 1.35 2007-08-15 13:21:22 mike Exp $

 
 package Net::Z3950::SimpleServer;
 
 
 package Net::Z3950::SimpleServer;
 

@@ -87,13 +38,8 @@ require DynaLoader;
 require AutoLoader;
 
 @ISA = qw(Exporter AutoLoader DynaLoader);
 require AutoLoader;
 
 @ISA = qw(Exporter AutoLoader DynaLoader);

-# Items to export into callers namespace by default. Note: do not export
-# names by default without a very good reason. Use EXPORT_OK instead.
-# Do not simply export all your public functions/methods/constants.
-@EXPORT = qw(
-       
-);
-$VERSION = '0.08';
+@EXPORT = qw( );
+$VERSION = '1.06';

 
 bootstrap Net::Z3950::SimpleServer $VERSION;
 
 
 bootstrap Net::Z3950::SimpleServer $VERSION;
 

@@ -123,6 +69,13 @@ sub launch_server {
        my $self = shift;
        my @args = @_;
 
        my $self = shift;
        my @args = @_;
 

+       ### This modal internal interface, in which we set a bunch of
+       #   globals and then call start_server(), is asking for
+       #   trouble.  Instead, we should just pass the $self object
+       #   as a parameter into start_server().
+       if (defined($self->{GHANDLE})) {
+               set_ghandle($self->{GHANDLE});
+       }

        if (defined($self->{INIT})) {
                set_init_handler($self->{INIT});
        }
        if (defined($self->{INIT})) {
                set_init_handler($self->{INIT});
        }

@@ -137,6 +90,12 @@ sub launch_server {
        if (defined($self->{SCAN})) {
                set_scan_handler($self->{SCAN});
        }
        if (defined($self->{SCAN})) {
                set_scan_handler($self->{SCAN});
        }

+       if (defined($self->{SORT})) {
+               set_sort_handler($self->{SORT});
+       }
+       if (defined($self->{EXPLAIN})) {
+               set_explain_handler($self->{EXPLAIN});
+       }

 
        start_server(@args);
 }
 
        start_server(@args);
 }

@@ -149,6 +108,7 @@ package Net::Z3950::RPN::And;
 package Net::Z3950::RPN::Or;
 package Net::Z3950::RPN::AndNot;
 package Net::Z3950::RPN::Term;
 package Net::Z3950::RPN::Or;
 package Net::Z3950::RPN::AndNot;
 package Net::Z3950::RPN::Term;

+package Net::Z3950::RPN::RSID;

 package Net::Z3950::RPN::Attributes;
 package Net::Z3950::RPN::Attribute;
 
 package Net::Z3950::RPN::Attributes;
 package Net::Z3950::RPN::Attribute;
 

@@ -198,15 +158,14 @@ Net::Z3950::SimpleServer - Simple Perl API for building Z39.50 servers.
        }
   }
 
        }
   }
 

-

   ## Register custom event handlers:
   ## Register custom event handlers:

+  my $z = new Net::Z3950::SimpleServer(GHANDLE = $someObject,
+                                      INIT   =>  \&my_init_handler,
+                                      CLOSE  =>  \&my_close_handler,
+                                      SEARCH =>  \&my_search_handler,
+                                      FETCH  =>  \&my_fetch_handler);

 
 

-  my $z = new Net::Z3950::SimpleServer(                INIT   =>  \&my_init_handler,
-                                               CLOSE  =>  \&my_close_handler,
-                                               SEARCH =>  \&my_search_handler,
-                                               FETCH  =>  \&my_fetch_handler);

   ## Launch server:
   ## Launch server:

-

   $z->launch_server("ztest.pl", @ARGV);
 
 =head1 DESCRIPTION
   $z->launch_server("ztest.pl", @ARGV);
 
 =head1 DESCRIPTION

@@ -249,12 +208,12 @@ After the launching of the server, all control is given away from
 the Perl script to the server. The server calls the registered
 subroutines to field incoming requests from Z39.50 clients.
 
 the Perl script to the server. The server calls the registered
 subroutines to field incoming requests from Z39.50 clients.
 

-A reference to an anonymous hash is passed to each handle. Some of
+A reference to an anonymous hash is passed to each handler. Some of

 the entries of these hashes are to be considered input and others
 output parameters.
 
 the entries of these hashes are to be considered input and others
 output parameters.
 

-The Perl programmer specifies the event handles for the server by
-means of the the SimpleServer object constructor
+The Perl programmer specifies the event handlers for the server by
+means of the SimpleServer object constructor

 
   my $z = new Net::Z3950::SimpleServer(
                        INIT    =>      \&my_init_handler,
 
   my $z = new Net::Z3950::SimpleServer(
                        INIT    =>      \&my_init_handler,

@@ -262,9 +221,30 @@ means of the the SimpleServer object constructor
                        SEARCH  =>      \&my_search_handler,
                        PRESENT =>      \&my_present_handler,
                        SCAN    =>      \&my_scan_handler,
                        SEARCH  =>      \&my_search_handler,
                        PRESENT =>      \&my_present_handler,
                        SCAN    =>      \&my_scan_handler,

-                       FETCH   =>      \&my_fetch_handler);
+                       FETCH   =>      \&my_fetch_handler,
+                       EXPLAIN =>      \&my_explain_handler);
+
+In addition, the arguments to the constructor may include GHANDLE, a
+global handle which is made available to each invocation of every
+callback function.  This is typically a reference to either a hash or
+an object.

 
 

-After the custom event handles are declared, the server is launched
+If you want your SimpleServer to start a thread (threaded mode) to
+handle each incoming Z39.50 request instead of forking a process
+(forking mode), you need to register the handlers by symbol rather
+than by code reference. Thus, in threaded mode, you will need to
+register your handlers this way:
+
+  my $z = new Net::Z3950::SimpleServer(
+                       INIT    =>      "my_package::my_init_handler",
+                       CLOSE   =>      "my_package::my_close_handler",
+                       ....
+                       ....          );
+
+where my_package is the Perl package in which your handler is
+located.
+
+After the custom event handlers are declared, the server is launched

 by means of the method
 
   $z->launch_server("MyServer.pl", @ARGV);
 by means of the method
 
   $z->launch_server("MyServer.pl", @ARGV);

@@ -274,6 +254,9 @@ script (for logging purposes), while the rest of the arguments
 are documented in the YAZ toolkit manual: The section on
 application invocation: <http://www.indexdata.dk/yaz/yaz-7.php>
 
 are documented in the YAZ toolkit manual: The section on
 application invocation: <http://www.indexdata.dk/yaz/yaz-7.php>
 

+In particular, you need to use the -T switch to start your SimpleServer
+in threaded mode.
+

 =head2 Init handler
 
 The init handler is called whenever a Z39.50 client is attempting
 =head2 Init handler
 
 The init handler is called whenever a Z39.50 client is attempting

@@ -297,6 +280,7 @@ The argument hash passed to the init handler has the form
                                    ## this member contains user name
             PASS      =>  "yyy"    ## Under same conditions, this member
                                    ## contains the password in clear text
                                    ## this member contains user name
             PASS      =>  "yyy"    ## Under same conditions, this member
                                    ## contains the password in clear text

+            GHANDLE   =>  $obj     ## Global handler specified at creation

             HANDLE    =>  undef    ## Handler of Perl data structure
          };
 
             HANDLE    =>  undef    ## Handler of Perl data structure
          };
 

@@ -326,6 +310,7 @@ mous hash. The structure is the following:
   $args = {
                                    ## Request parameters:
 
   $args = {
                                    ## Request parameters:
 

+            GHANDLE   =>  $obj     ## Global handler specified at creation

             HANDLE    =>  ref,     ## Your session reference.
             SETNAME   =>  "id",    ## ID of the result set
             REPL_SET  =>  0,       ## Replace set if already existing?
             HANDLE    =>  ref,     ## Your session reference.
             SETNAME   =>  "id",    ## ID of the result set
             REPL_SET  =>  0,       ## Replace set if already existing?

@@ -426,10 +411,15 @@ node of one of the above types.
 
 See below for details.
 
 
 See below for details.
 

+=item C<Net::Z3950::RPN::RSID>
+
+A reference to a result-set ID indicating a previous search.  The ID
+of the result-set is in the C<id> element.
+

 =back
 
 (I guess I should make a superclass C<Net::Z3950::RPN::Node> and make
 =back
 
 (I guess I should make a superclass C<Net::Z3950::RPN::Node> and make

-all of these subclasses of it.  Not done that yet, but will do soon.)
+all of these subclasses of it.  Not done that yet, but will do one day.)

 
 =back
 
 
 =back
 

@@ -530,6 +520,7 @@ The informations exchanged between client and present handle are:
   $args = {
                                    ## Client/server request:
 
   $args = {
                                    ## Client/server request:
 

+            GHANDLE   =>  $obj     ## Global handler specified at creation

             HANDLE    =>  ref,     ## Reference to datastructure
             SETNAME   =>  "id",    ## Result set ID
             START     =>  xxx,     ## Start position
             HANDLE    =>  ref,     ## Reference to datastructure
             SETNAME   =>  "id",    ## Result set ID
             START     =>  xxx,     ## Start position

@@ -556,11 +547,13 @@ The parameters exchanged between the server and the fetch handler are
   $args = {
                                    ## Client/server request:
 
   $args = {
                                    ## Client/server request:
 

+            GHANDLE   =>  $obj     ## Global handler specified at creation

             HANDLE    =>  ref      ## Reference to data structure
             SETNAME   =>  "id"     ## ID of the requested result set
             OFFSET    =>  nnn      ## Record offset number
             REQ_FORM  =>  "n.m.k.l"## Client requested format OID
             COMP      =>  "xyz"    ## Formatting instructions
             HANDLE    =>  ref      ## Reference to data structure
             SETNAME   =>  "id"     ## ID of the requested result set
             OFFSET    =>  nnn      ## Record offset number
             REQ_FORM  =>  "n.m.k.l"## Client requested format OID
             COMP      =>  "xyz"    ## Formatting instructions

+            SCHEMA    =>  "abc"    ## Requested schema, if any

 
                                    ## Handler response:
 
 
                                    ## Handler response:
 

@@ -571,6 +564,7 @@ The parameters exchanged between the server and the fetch handler are
             ERR_STR   =>  ""       ## Error string
             SUR_FLAG  =>  0        ## Surrogate diagnostic flag
             REP_FORM  =>  "n.m.k.l"## Provided format OID
             ERR_STR   =>  ""       ## Error string
             SUR_FLAG  =>  0        ## Surrogate diagnostic flag
             REP_FORM  =>  "n.m.k.l"## Provided format OID

+            SCHEMA    =>  "abc"    ## Provided schema, if any

          };
 
 The REP_FORM value has by default the REQ_FORM value but can be set to
          };
 
 The REP_FORM value has by default the REQ_FORM value but can be set to

@@ -602,7 +596,10 @@ an index of a book, you always find something! The parameters exchanged are
   $args = {
                                                ## Client request
 
   $args = {
                                                ## Client request
 

-               HANDLE          => $ref         ## Reference to data structure
+               GHANDLE         => $obj,        ## Global handler specified at creation
+               HANDLE          => $ref,        ## Reference to data structure
+               DATABASES       => ["xxx"],     ## Reference to a list of data-
+                                               ## bases to search

                TERM            => 'start',     ## The start term
                NUMBER          => xx,          ## Number of requested terms
                POS             => yy,          ## Position of starting point
                TERM            => 'start',     ## The start term
                NUMBER          => xx,          ## Number of requested terms
                POS             => yy,          ## Position of starting point

@@ -636,20 +633,23 @@ should point at a data structure of this kind,
                                ...
        ];
 
                                ...
        ];
 

-The $status flag should be assigned one of two values:
+The $status flag is only meaningful after a successful scan, and
+should be assigned one of two values:

 
 

-  Net::Z3950::SimpleServer::ScanSuccess  On success (default)
-  Net::Z3950::SimpleServer::ScanPartial  Less terms returned than requested
+  Net::Z3950::SimpleServer::ScanSuccess  Full success (default)
+  Net::Z3950::SimpleServer::ScanPartial  Fewer terms returned than requested

 
 The STEP member contains the requested number of entries in the term-list
 between two adjacent entries in the response.
 
 =head2 Close handler
 
 
 The STEP member contains the requested number of entries in the term-list
 between two adjacent entries in the response.
 
 =head2 Close handler
 

-The argument hash recieved by the close handler has one element only:
+The argument hash recieved by the close handler has two elements only:

 
   $args = {
                                    ## Server provides:
 
   $args = {
                                    ## Server provides:

+
+            GHANDLE   =>  $obj     ## Global handler specified at creation

             HANDLE    =>  ref      ## Reference to data structure
          };
 
             HANDLE    =>  ref      ## Reference to data structure
          };
 

@@ -657,11 +657,70 @@ What ever data structure the HANDLE value points at goes out of scope
 after this call. If you need to close down a connection to your server
 or something similar, this is the place to do it.
 
 after this call. If you need to close down a connection to your server
 or something similar, this is the place to do it.
 

+=head2 Support for SRU and SRW
+
+Since release 1.0, SimpleServer includes support for serving the SRU
+and SRW protocols as well as Z39.50.  These ``web-friendly'' protocols
+enable similar functionality to that of Z39.50, but by means of rich
+URLs in the case of SRU, and a SOAP-based web-service in the case of
+SRW.  These protocols are described at
+http://www.loc.gov/sru
+
+In order to serve these protocols from a SimpleServer-based
+application, it is necessary to launch the application with a YAZ
+Generic Frontend Server (GFS) configuration file, which can be
+specified using the command-line argument C<-f> I<filename>.  A
+minimal configuration file looks like this:
+
+  <yazgfs>
+    <server>
+      <cql2rpn>pqf.properties</cql2rpn>
+    </server>
+  </yazgfs>
+
+This file specifies only that C<pqf.properties> should be used to
+translate the CQL queries of SRU and SRW into corresponding Z39.50
+Type-1 queries.  For more information about YAZ GFS configuration,
+including how to specify an Explain record, see the I<Virtual Hosts>
+section of the YAZ manual at
+http://indexdata.com/yaz/doc/server.vhosts.tkl
+
+The mapping of CQL queries into Z39.50 Type-1 queries is specified by
+a file that indicates which BIB-1 attributes should be generated for
+each CQL index, relation, modifiers, etc.  A typical section of this
+file looks like this:
+
+  index.dc.title                        = 1=4
+  index.dc.subject                      = 1=21
+  index.dc.creator                      = 1=1003
+  relation.<                            = 2=1
+  relation.le                           = 2=2
+
+This file specifies the BIB-1 access points (type=1) for the Dublin
+Core indexes C<title>, C<subject> and C<creator>, and the BIB-1
+relations (type=2) corresponding to the CQL relations C<E<lt>> and
+C<E<lt>=>.  For more information about the format of this file, see
+the I<CQL> section of the YAZ manual at
+http://indexdata.com/yaz/doc/tools.tkl#tools.cql
+
+The YAZ distribution include a sample CQL-to-PQF mapping configuration
+file called C<pqf.properties>; this is sufficient for many
+applications, and a good base to work from for most others.
+
+If a SimpleServer-based application is run without this SRU-specific
+configuration, it can still serve SRU; however, CQL queries will not
+be translated, but passed straight through to the search-handler
+function, as the C<CQL> member of the parameters hash.  It is then the
+responsibility of the back-end application to parse and handle the CQL
+query, which is most easily done using Ed Summers' fine C<CQL::Parser>
+module, available from CPAN at
+http://search.cpan.org/~esummers/CQL-Parser/
+

 =head1 AUTHORS
 
 =head1 AUTHORS
 

-Anders Sønderberg (sondberg@indexdata.dk) and Sebastian Hammer
-(quinn@indexdata.dk). Substantial contributions made by Mike Taylor
-(mike@miketaylor.org.uk).
+Anders Sønderberg (sondberg@indexdata.dk),
+Sebastian Hammer (quinn@indexdata.dk),
+Mike Taylor (indexdata.com).

 
 =head1 SEE ALSO
 
 
 =head1 SEE ALSO