Initial revision

diff --git a/Changes b/Changes
new file mode 100644 (file)
index 0000000..cfd79e2
--- /dev/null
+++ b/Changes
@@ -0,0 +1,10 @@
+$Id: Changes,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+Revision history for Perl extension Net::Z3950::IRSpy.
+
+0.02  [IN PROGRESS]
+
+0.01  Wed Apr  5 15:53:47 2006
+       - original version; created by h2xs 1.23 with options
+               -X --name=Net::Z3950::IRSpy --compat-version=5.8.0 --omit-constant --skip-exporter --skip-ppport
+

diff --git a/MANIFEST b/MANIFEST
new file mode 100644 (file)
index 0000000..bffba75
--- /dev/null
+++ b/MANIFEST
@@ -0,0 +1,8 @@
+Changes
+Makefile.PL
+MANIFEST
+README
+t/Net-Z3950-IRSpy.t
+lib/Net/Z3950/IRSpy.pm
+META.yml                                 Module meta-data (added by MakeMaker)
+MANIFEST.SKIP

diff --git a/MANIFEST.SKIP b/MANIFEST.SKIP
new file mode 100644 (file)
index 0000000..f1d43c6
--- /dev/null
+++ b/MANIFEST.SKIP
@@ -0,0 +1 @@
+archive

diff --git a/META.yml b/META.yml
new file mode 100644 (file)
index 0000000..a0938e6
--- /dev/null
+++ b/META.yml
@@ -0,0 +1,12 @@
+# $Id: META.yml,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+# http://module-build.sourceforge.net/META-spec.html
+#XXXXXXX This is a prototype!!!  It will change in the future!!! XXXXX#
+name:         Net-Z3950-IRSpy
+version:      0.01
+version_from: lib/Net/Z3950/IRSpy.pm
+installdirs:  site
+requires:
+
+distribution_type: module
+generated_by: ExtUtils::MakeMaker version 6.17

diff --git a/Makefile.PL b/Makefile.PL
new file mode 100644 (file)
index 0000000..dd79c1e
--- /dev/null
+++ b/Makefile.PL
@@ -0,0 +1,16 @@
+# $Id: Makefile.PL,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+use 5.008;
+use ExtUtils::MakeMaker;
+# See lib/ExtUtils/MakeMaker.pm for details of how to influence
+# the contents of the Makefile that is written.
+WriteMakefile(
+    NAME              => 'Net::Z3950::IRSpy',
+    VERSION_FROM      => 'lib/Net/Z3950/IRSpy.pm', # finds $VERSION
+    PREREQ_PM         => {
+       Net::Z3950::ZOOM => 1.04,
+    },
+    ($] >= 5.005 ?     ## Add these new keywords supported since 5.005
+      (ABSTRACT_FROM  => 'lib/Net/Z3950/IRSpy.pm', # retrieve abstract from module
+       AUTHOR         => 'Mike Taylor <mike@indexdata.com>') : ()),
+);

diff --git a/README b/README
new file mode 100644 (file)
index 0000000..6bb120b
--- /dev/null
+++ b/README
@@ -0,0 +1,34 @@
+$Id: README,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+Net-Z3950-IRSpy
+===============
+
+This module exists to implement the IRspy program, which discovers,
+analyses and monitors IR servers implementing the Z39.50 and SRU/W
+protocols.  It is a successor to the ZSpy program.
+
+INSTALLATION
+
+To install this module type the following:
+
+   perl Makefile.PL
+   make
+   make test
+   make install
+
+DEPENDENCIES
+
+This module requires these other modules and libraries, in addition to
+those specified in Makefile.PL:
+
+  Zebra, release 1.4.0 or later: see http://indexdata.com/zebra/
+
+COPYRIGHT AND LICENCE
+
+Copyright (C) 2006 by Index Data ApS.
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself, either Perl version 5.8.7 or,
+at your option, any later version of Perl 5 you may have available.
+
+

diff --git a/archive/2006 - 04 - 05 Target Monitor Software.doc b/archive/2006 - 04 - 05 Target Monitor Software.doc
new file mode 100644 (file)
index 0000000..5329eb0
Binary files /dev/null and b/archive/2006 - 04 - 05 Target Monitor Software.doc differ

diff --git a/archive/Net-Z3950-IRSpy-0.01.tar.gz b/archive/Net-Z3950-IRSpy-0.01.tar.gz
new file mode 100644 (file)
index 0000000..ea927aa
Binary files /dev/null and b/archive/Net-Z3950-IRSpy-0.01.tar.gz differ

diff --git a/archive/press-release b/archive/press-release
new file mode 100644 (file)
index 0000000..c2f6b45
--- /dev/null
+++ b/archive/press-release
@@ -0,0 +1,187 @@
+From mike  Thu Apr  6 07:29:26 2006
+X-VM-v5-Data: ([nil nil nil nil t nil nil nil nil]
+       ["36361" "Wednesday" "5" "April" "2006" "16:03:54" "-0400" "David Dorman" "dorman@indexdata.com" "<7.0.1.0.2.20060405160339.03da1e80@indexdata.com>" "530" "[Staff] Support for NISO Metasearch Initiative" "^X-Spam-Status:" nil nil "4" nil nil nil nil nil nil nil nil nil]
+       nil)
+Return-path: <staff-bounces@lists.indexdata.dk>
+X-Spam-Checker-Version: SpamAssassin 3.1.0 (2005-09-13) on bagel.indexdata.dk
+X-Spam-Level: 
+Envelope-to: mike@indexdata.com
+Delivery-date: Thu, 06 Apr 2006 08:09:00 +0200
+Received: from localhost.localdomain [127.0.0.1]
+       by localhost with POP3 (fetchmail-6.2.5)
+       for mike@localhost (single-drop); Thu, 06 Apr 2006 07:29:26 +0100 (BST)
+Received: from kebab.indexdata.dk ([83.133.64.60])
+       by bagel.indexdata.dk with esmtp (Exim 3.35 #1 (Debian))
+       id 1FRNfv-0006yp-00; Thu, 06 Apr 2006 08:08:59 +0200
+Received: from localhost ([127.0.0.1] helo=kebab.indexdata.dk)
+       by kebab.indexdata.dk with esmtp (Exim 4.50)
+       id 1FRNcT-0002Nn-5P; Thu, 06 Apr 2006 08:05:25 +0200
+Received: from user.indexdata.dk ([213.150.43.10] helo=bagel.indexdata.dk)
+       by kebab.indexdata.dk with esmtp (Exim 4.50) id 1FREGw-0007if-6b
+       for staff@lists.indexdata.dk; Wed, 05 Apr 2006 22:06:40 +0200
+Received: from mailman by bagel.indexdata.dk with local (Exim 3.35 #1 (Debian))
+       id 1FREKM-0007Hj-00
+       for <staff-filtered@indexdata.dk>; Wed, 05 Apr 2006 22:10:06 +0200
+Received: from post1.wesleyan.edu ([129.133.6.131])
+       by bagel.indexdata.dk with esmtp (Exim 3.35 #1 (Debian))
+       id 1FREKL-0007HA-00
+       for <staff@indexdata.com>; Wed, 05 Apr 2006 22:10:05 +0200
+Received: from DAVID.indexdata.com (69.177.235.51.adsl.snet.net
+       [69.177.235.51] (may be forged)) (authenticated bits=0)
+       by post1.wesleyan.edu (8.12.11/8.12.11) with ESMTP id k35K3wSC030632;
+       Wed, 5 Apr 2006 16:04:56 -0400
+Message-Id: <7.0.1.0.2.20060405160339.03da1e80@indexdata.com>
+Message-Id: <7.0.1.0.2.20060405150259.03dbfe48@indexdata.com>
+X-Mailer: QUALCOMM Windows Eudora Version 7.0.1.0
+Mime-Version: 1.0
+X-Wesleyan-MailScanner-Information: Please contact the ISP for more information
+X-Wesleyan-MailScanner: Found to be clean
+X-MailScanner-From: dorman@indexdata.com
+X-Mailman-Approved-At: Thu, 06 Apr 2006 08:05:23 +0200
+X-BeenThere: staff@lists.indexdata.dk
+X-Mailman-Version: 2.1.5
+Precedence: list
+List-Id: Index Data's PRIVATE staff discussion list <staff.lists.indexdata.dk>
+List-Unsubscribe: <http://lists.indexdata.dk/cgi-bin/mailman/listinfo/staff>, 
+       <mailto:staff-request@lists.indexdata.dk?subject=unsubscribe>
+List-Archive: <http://lists.indexdata.dk/cgi-bin/mailman/private/staff>
+List-Post: <mailto:staff@lists.indexdata.dk>
+List-Help: <mailto:staff-request@lists.indexdata.dk?subject=help>
+List-Subscribe: <http://lists.indexdata.dk/cgi-bin/mailman/listinfo/staff>,
+       <mailto:staff-request@lists.indexdata.dk?subject=subscribe>
+Errors-To: staff-bounces@lists.indexdata.dk
+X-SA-Exim-Connect-IP: 127.0.0.1
+X-SA-Exim-Mail-From: staff-bounces@lists.indexdata.dk
+X-SA-Exim-Scanned: No (on kebab.indexdata.dk); SAEximRunCond expanded to false
+X-Spam-Status: No, score=-2.4 required=5.0 tests=AWL,BAYES_00,
+       FORGED_RCVD_HELO autolearn=unavailable version=3.1.0
+From: David Dorman <dorman@indexdata.com>
+Sender: staff-bounces@lists.indexdata.dk
+To: "Index Data News List 3":;
+Subject: [Staff] Support for NISO Metasearch Initiative
+Date: Wed, 05 Apr 2006 16:03:54 -0400
+X-StripMime: Non-text section removed by stripmime
+Content-Type: text/plain; charset="us-ascii"; format=flowed
+
+Hello to everyone on my Index Data news distribution list.  I hope 
+this note finds you all engaged and feeling well.  I am pleased to be 
+able to report, with the following announcement, that Index Data is 
+advancing the standardization of metasearching in a way that we are 
+confident will result in significant cost savings for the library community.
+
+David Dorman
+
+INDEX DATA DEVELOPMENT CONTRACT SUPPORTS NISO METASEARCH INITIATIVE
+
+April 5, 2006 - West Hartford, CT - Index Data, the premier developer 
+of Open Source information retrieval software for libraries and their 
+vendors, has just signed a contract with Helsinki University Library, 
+The National Library of Finland, to develop an information retrieval 
+target monitoring and analysis tool. This software, which is being 
+released under the name Keystone Target Manager, will be designed to 
+meet the specifications of the NISO draft standard Z39.92: 
+Information Retrieval Service Description, which is based on an 
+earlier community standard called ZeeRex.
+
+The Keystone Target Manager will perform the following services:
+    * Automatically monitor a collection of Z39.50/SRW/SRU targets, 
+maintaining statistics for availability over time.
+    * Provide configurable alerting services when targets become unavailable.
+    * Automatically gather information about the search capabilities 
+of targets that use standard search protocols, such as 
+Z39.50/SRW/SRU, for use in configuring IR clients of different types.
+    * Make the gathered information available in a software-readable 
+form, as a database of ZeeRex (ANSI/NISO Z39.92) records. (This will 
+enable sharing of this information via the Internet.)
+Juha Hakala, Director of Information Technology at Helsinki 
+University Library and Chair of the NISO Committee which developed 
+the NISO Z39.92 draft standard, points out that "up to now 
+information about Z39.50 or SRU/SRW targets has usually been 
+discovered and documented manually, which is a laborious and time 
+consuming process. Also, there has been no efficient means of 
+exchanging this data among metasearch applications such as portals. 
+While NISO Z39.92, solves the latter problem, the Keystone Target 
+Manager will simplify the process of creating accurate target 
+descriptions and keeping them up-to-date."
+
+"Given the expertise Index Data has in implementing Z39.50 and 
+SRU/SRW applications," Hakala continued, "I am confident that the 
+service descriptions generated by the Target Manager will be useful. 
+It will be interesting to see how quickly the IR portal vendors and 
+maintenance agencies such as libraries will adopt this target 
+management tool, and start sharing on a global scale the target 
+descriptions harvested with it."
+
+Pat Stevens, the Interim Executive Director of NISO, was delighted to 
+learn about this agreement: "NISO thanks Helsinki University and 
+Index Data for their collaborative work on this project," she stated. 
+"It comes at just the right time as organizations are now looking for 
+an effective way to implement Z39.92."
+
+The Keystone Target Manager will be a major step forward in 
+standardizing and reducing the costs of maintaining target gateways 
+for metasearch services. Content providers that support standardized 
+search interfaces, and federated search services that take advantage 
+of this soon-to-be-released Open Source/Open Access target management 
+service, will together be able to reduce the cost of providing 
+federated search services to libraries. If these lower costs are 
+passed on to libraries in the form of reduced gateway maintenance 
+fees, libraries will be able to shift costs from access mechanisms to 
+licensing content.
+
+About Index Data
+
+Index Data has been developing standards-based information retrieval 
+technology since 1994. Library software vendors as varied as Ex 
+Libris, Fretwell-Downing, Geac, ISACSOFT, Koha and Polaris use Index 
+Data's technology in the software they provide to libraries. And 
+libraries around the world, including the Library of Congress and 
+many other national libraries, use the company's technology and 
+services to meet demanding and sophisticated information retrieval 
+challenges. The company's metasearch service, Keystone Retriever, is 
+among the most advanced in the industry and is distributed under an 
+Open Source license.
+
+--------------------------------------------------
+LIST MANAGEMENT INFO
+
+All recipients of this newsletter have been individually and manually 
+added to the Index Data News Distribution List.  If you would like to 
+be deleted from this list, simply reply to this email with a remove 
+request and I will remove your name. If this email was forwarded to 
+you and you would like to receive these occasional mailings in the 
+future, let me know and I will add you to the list.
+--------------------------------------------------
+
+Yours for a More Open World,
+
+David
+
+
+David Dorman
+US Marketing Manager, Index Data
+52 Whitman Ave.
+West Hartford, Connecticut  06107
+dorman@indexdata.com
+860-389-1568 or toll free 866-489-1568
+fax: 860-561-5613
+
+INDEX DATA Means Business
+for Open Source and Open Standards
+- - - - - - - - - - - - - - -
+www.indexdata.com
+
+_______________________________________________
+Staff mailing list
+Staff@lists.indexdata.dk
+http://lists.indexdata.dk/cgi-bin/mailman/listinfo/staff
+
+
+--- StripMime Report -- processed MIME parts ---
+multipart/mixed
+  text/plain (text body -- kept)
+  application/msword
+  text/plain (text body -- kept)
+---
+
+

diff --git a/t/Net-Z3950-IRSpy.t b/t/Net-Z3950-IRSpy.t
new file mode 100644 (file)
index 0000000..dba53ae
--- /dev/null
+++ b/t/Net-Z3950-IRSpy.t
@@ -0,0 +1,11 @@
+# $Id: Net-Z3950-IRSpy.t,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+# change 'tests => 1' to 'tests => last_test_to_print';
+use Test::More tests => 1;
+BEGIN { use_ok('Net::Z3950::IRSpy') };
+
+#########################
+
+# Insert your test code below, the Test::More module is use()ed here so read
+# its man page ( perldoc Test::More ) for help writing this test script.
+

diff --git a/zebra/README b/zebra/README
new file mode 100644 (file)
index 0000000..411f04a
--- /dev/null
+++ b/zebra/README
@@ -0,0 +1,59 @@
+$Id: README,v 1.1 2006-04-13 14:53:18 mike Exp $
+
+What's what in this directory:
+
+README -- This file
+
+yazserver.xml -- The primary configuration file that controls how
+       Zebra runs (as a YAZ GFS application) in order to serve the
+       ZeeRex database.  This specifies where to find this database's
+       own ZeeRex record (zeerex.xml), the configuration for
+       translating CQL queries into Z39.50 Type-1 (pqf.properties),
+       and the Zebra-specific configuration (zebra.cfg).
+
+zeerex.xml -- The static ZeeRex record for this database of ZeeRex
+       records.  It describes what a ZeeRex database looks like, and
+       how it behaves.  (Life would be better if Zebra could at least
+       partially work this out for itself, but for now we have to go
+       the long way round.)
+
+zeerex-2.0.xsd -- The XML Schema describing ZeeRex records, as
+       downloaded from the official ZeeRex site at:
+               http://explain.z3950.org/dtd/zeerex-2.0.xsd
+       This can be used to validate both our own static ZeeRex record
+       and the records created by IRSpy.       
+
+pqf.properties -- The specification for how CQL queries are translated
+       into 39.50 Type-1 queries.  This file is identical to the one
+       supplied in the YAZ distribution: we'd just use that if there
+       was a reliable way to discover where it is.
+
+zebra.cfg -- Zebra-specific configuration, including the location of
+       the register files, the location of the XSLT filter
+       configuration (filterconf.xml), etc.
+
+filterconf.xml -- Configuration of Zebra's XSLT filter, which uses
+       XSLT stylesheets to identify the indexable data in incoming
+       files and to transform records for presentation.
+
+zeerex2index.xsl -- The indexing stylesheet for ZeeRex records.
+
+zeerex2zeerex.xsl -- The "no-op" stylesheet for presenting ZeeRex
+       records.
+
+db -- A subdirectory containing the actual database: register files,
+       dictionaries and suchlike.
+
+--
+
+To create the database and start the server:
+
+xmllint --noout --schema zeerex-2.0.xsd zeerex.xml # Verify
+xsltproc zeerex2index.xsl zeerex.xml # Check what indexer will see
+zebraidx -c zebra.cfg init # Remove any existing database records
+zebraidx -c zebra.cfg update zeerex.xml # Our only record!
+zebraidx -c zebra.cfg commit
+zebrasrv -f yazserver.xml
+
+Then interrogate the database with SRU URLs such as:
+       http://localhost:1313/IR-Explain--1?version=1.1&operation=searchRetrieve&x-pquery=@attr%201=net:host%20localhost
\ No newline at end of file

diff --git a/zebra/filterconf.xml b/zebra/filterconf.xml
new file mode 100644 (file)
index 0000000..ec24652
--- /dev/null
+++ b/zebra/filterconf.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- $Id: filterconf.xml,v 1.1 2006-04-13 14:53:18 mike Exp $ -->
+<schemaInfo>
+ <schema name="index" stylesheet="zeerex2index.xsl"
+        identifier="http://indexdata.dk/zebra/xslt/1"/>
+ <schema name="zeerex" stylesheet="zeerex2zeerex.xsl"/>
+</schemaInfo>

diff --git a/zebra/pqf.properties b/zebra/pqf.properties
new file mode 100644 (file)
index 0000000..1f5b7d4
--- /dev/null
+++ b/zebra/pqf.properties
@@ -0,0 +1,150 @@
+# $Id: pqf.properties,v 1.1 2006-04-13 14:53:18 mike Exp $
+#
+# Propeties file to drive org.z3950.zing.cql.CQLNode's toPQF()
+# back-end and the YAZ CQL-to-PQF converter.  This specifies the
+# interpretation of various CQL indexes, relations, etc. in terms
+# of Type-1 query attributes.
+#
+# This configuration file generates queries using BIB-1 attributes.
+# See http://www.loc.gov/z3950/agency/zing/cql/dc-indexes.html
+# for the Maintenance Agency's work-in-progress mapping of Dublin Core
+# indexes to Attribute Architecture (util, XD and BIB-2)
+# attributes.
+
+# Identifiers for prefixes used in this file. (index.*)
+set.cql                = info:srw/cql-context-set/1/cql-v1.1
+set.rec                = info:srw/cql-context-set/2/rec-1.0
+set.dc         = info:srw/cql-context-set/1/dc-v1.1
+set.bath       = http://zing.z3950.org/cql/bath/2.0/
+
+# default set (in query)
+set            = info:srw/cql-context-set/1/dc-v1.1
+
+# The default access point and result-set references
+index.cql.serverChoice                 = 1=1016
+       # srw.serverChoice is deprecated in favour of cql.serverChoice
+       # BIB-1 "any"
+
+index.rec.id                           = 1=12
+
+index.dc.title                         = 1=4
+index.dc.subject                       = 1=21
+index.dc.creator                       = 1=1003
+index.dc.author                                = 1=1003
+       ### Unofficial synonym for "creator"
+index.dc.editor                                = 1=1020
+index.dc.publisher                     = 1=1018
+index.dc.description                   = 1=62
+       # "abstract"
+index.dc.date                          = 1=30
+index.dc.resourceType                  = 1=1031
+       # guesswork: "Material-type"
+index.dc.format                                = 1=1034
+       # guesswork: "Content-type"
+index.dc.resourceIdentifier            = 1=12
+       # "Local number"
+index.dc.source                                = 1=1019
+       # "Record-source"
+index.dc.language                      = 1=54
+       # "Code--language"
+index.dc.relation                      = 1=?
+       ### No idea how to represent this
+index.dc.coverage                      = 1=?
+       ### No idea how to represent this
+index.dc.rights                                = 1=?
+       ### No idea how to represent this
+
+# Relation attributes are selected according to the CQL relation by
+# looking up the "relation.<relation>" property:
+#
+relation.<                             = 2=1
+relation.le                            = 2=2
+relation.eq                            = 2=3
+relation.exact                         = 2=3
+relation.ge                            = 2=4
+relation.>                             = 2=5
+relation.<>                            = 2=6
+
+### These two are not really right:
+relation.all                           = 2=3
+relation.any                           = 2=3
+
+# BIB-1 doesn't have a server choice relation, so we just make the
+# choice here, and use equality (which is clearly correct).
+relation.scr                           = 2=3
+
+# Relation modifiers.
+#
+relationModifier.relevant              = 2=102
+relationModifier.fuzzy                 = 5=102
+       ### truncation=regExpr-2 (5=102) in Zebra is "fuzzy matching"
+relationModifier.stem                  = 2=101
+relationModifier.phonetic              = 2=100
+
+# Position attributes may be specified for anchored terms (those
+# beginning with "^", which is stripped) and unanchored (those not
+# beginning with "^").  This may change when we get a BIB-1 truncation
+# attribute that says "do what CQL does".
+#
+position.first                         = 3=1 6=1
+       # "first in field"
+position.any                           = 3=3 6=1
+       # "any position in field"
+position.last                          = 3=4 6=1
+       # not a standard BIB-1 attribute
+position.firstAndLast                  = 3=3 6=3
+       # search term is anchored to be complete field
+
+# Structure attributes may be specified for individual relations; a
+# default structure attribute my be specified by the pseudo-relation
+# "*", to be used whenever a relation not listed here occurs.
+#
+structure.exact                                = 4=108
+       # string
+structure.all                          = 4=2
+structure.any                          = 4=2
+structure.*                            = 4=1
+       # phrase
+
+# Truncation attributes used to implement CQL wildcard patterns.  The
+# simpler forms, left, right- and both-truncation will be used for the
+# simplest patterns, so that we produce PQF queries that conform more
+# closely to the Bath Profile.  However, when a more complex pattern
+# such as "foo*bar" is used, we fall back on Z39.58-style masking.
+#
+truncation.right                       = 5=1
+truncation.left                                = 5=2
+truncation.both                                = 5=3
+truncation.none                                = 5=100
+truncation.z3958                       = 5=104
+
+# Finally, any additional attributes that should always be included
+# with each term can be specified in the "always" property.
+#
+always                                 = 6=1
+# 6=1: completeness = incomplete subfield
+
+
+# Bath Profile support, added Thu Dec 18 13:06:20 GMT 2003
+# See the Bath Profile for SRW at
+#      http://zing.z3950.org/cql/bath.html
+# including the Bath Context Set defined within that document.
+#
+# In this file, we only map index-names to BIB-1 use attributes, doing
+# so in accordance with the specifications of the Z39.50 Bath Profile,
+# and leaving the relations, wildcards, etc. to fend for themselves.
+
+index.bath.keyTitle                    = 1=33
+index.bath.possessingInstitution       = 1=1044
+index.bath.name                                = 1=1002
+index.bath.personalName                        = 1=1
+index.bath.corporateName               = 1=2
+index.bath.conferenceName              = 1=3
+index.bath.uniformTitle                        = 1=6
+index.bath.isbn                                = 1=7
+index.bath.issn                                = 1=8
+index.bath.geographicName              = 1=58
+index.bath.notes                       = 1=63
+index.bath.topicalSubject              = 1=1079
+index.bath.genreForm                   = 1=1075
+

diff --git a/zebra/yazserver.xml b/zebra/yazserver.xml
new file mode 100644 (file)
index 0000000..274ca26
--- /dev/null
+++ b/zebra/yazserver.xml
@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- $Id: yazserver.xml,v 1.1 2006-04-13 14:53:17 mike Exp $ -->
+<yazgfs>
+ <listen id="tcp1313">tcp:@:1313</listen>
+ <server id="alvis" listenref="tcp1313">
+  <directory>./</directory>
+  <config>zebra.cfg</config>
+  <cql2rpn>pqf.properties</cql2rpn>
+  <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="explain.xml">
+   <xi:fallback>
+    <explain xmlns="http://explain.z3950.org/dtd/2.0/">
+     <serverInfo>
+      <host>localhost</host>
+      <port>1313</port>
+      <database>IR-Explain---1</database>
+     </serverInfo>
+    </explain>
+   </xi:fallback>
+  </xi:include>
+ </server>
+</yazgfs>

diff --git a/zebra/zebra.cfg b/zebra/zebra.cfg
new file mode 100644 (file)
index 0000000..17da22a
--- /dev/null
+++ b/zebra/zebra.cfg
@@ -0,0 +1,23 @@
+# $Id: zebra.cfg,v 1.1 2006-04-13 14:53:17 mike Exp $
+
+# Where to look for config files
+#profilePath: /usr/local/share/idzebra/tab:/usr/share/idzebra/tab
+
+# Where to look for loadable zebra modules
+#modulePath: zebra/lib/
+
+# store records and record keys internally
+storeData: 1
+storeKeys: 1
+
+# Use the "xslt" filter with config file filter_alvis_conf.xml
+recordtype: xslt.filterconf.xml
+
+database: IR-Explain---1
+
+# where to put registers, and other var content, and how large they may be
+register: db/register:100G
+shadow: db/shadow:100G
+lockdir: db/lock
+tmpdir: db/tmp
+keytmpdir: db/tmp

diff --git a/zebra/zeerex-2.0.xsd b/zebra/zeerex-2.0.xsd
new file mode 100644 (file)
index 0000000..0ae5fb1
--- /dev/null
+++ b/zebra/zeerex-2.0.xsd
@@ -0,0 +1,484 @@
+<schema
+  xmlns='http://www.w3.org/2001/XMLSchema'
+  targetNamespace='http://explain.z3950.org/dtd/2.0/'
+  xmlns:explain='http://explain.z3950.org/dtd/2.0/'>
+
+ <element name='explain'>
+  <complexType>
+   <sequence>
+    <element ref='explain:serverInfo'/>
+    <element ref='explain:databaseInfo' minOccurs='0' maxOccurs='1'/>
+    <element ref='explain:metaInfo' minOccurs='0' maxOccurs='1'/>
+    <element ref='explain:indexInfo' minOccurs='0' maxOccurs='1'/>
+    <choice minOccurs='0' maxOccurs='1'>
+     <element ref='explain:recordInfo'/>
+     <element ref='explain:schemaInfo'/>
+    </choice>
+    <element ref='explain:configInfo' minOccurs='0' maxOccurs='1'/>
+   </sequence>
+   <attribute name='authoritative' use='optional' default='false'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='id' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='serverInfo'>
+  <complexType>
+   <sequence>
+    <element ref='explain:host'/>
+    <element ref='explain:port'/>
+    <element ref='explain:database'/>
+    <element ref='explain:authentication' minOccurs='0' maxOccurs='1'/>
+   </sequence>
+   <attribute name='protocol' type='string' use='optional' default='Z39.50'/>
+   <attribute name='version' type='string' use='optional' default='3'/>
+   <attribute name='transport' type='string' use='optional' default='http'/>
+   <!-- ### The next line is not in the official schema.  I need 2.1 -->
+   <attribute name='method' type='string' use='optional' default='get'/>
+   <attribute name='wsdl' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='host'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='port'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='database'>
+  <complexType mixed='true'>
+   <attribute name='numRecs' type='string' use='optional'/>
+   <attribute name='lastUpdate' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='authentication'>
+  <complexType>
+   <choice>
+    <element ref='explain:open'/>
+    <sequence>
+     <element ref='explain:user' minOccurs='0' maxOccurs='1'/>
+     <element ref='explain:group' minOccurs='0' maxOccurs='1'/>
+     <element ref='explain:password' minOccurs='0' maxOccurs='1'/>
+    </sequence>
+   </choice>
+   <attribute name='required' use='optional' default='true'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+  </complexType>
+ </element>
+
+ <element name='open'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='user'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='group'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='password'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='databaseInfo'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+    <element ref='explain:description' minOccurs='0' maxOccurs='unbounded'/>
+    <choice minOccurs='0' maxOccurs='unbounded'>
+     <element ref='explain:author'/>
+     <element ref='explain:contact'/>
+     <element ref='explain:extent'/>
+     <element ref='explain:history'/>
+     <element ref='explain:langUsage'/>
+     <element ref='explain:restrictions'/>
+     <element ref='explain:subjects'/>
+     <element ref='explain:links'/>
+     <element ref='explain:implementation'/>
+    </choice>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='title'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='description'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='author'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='contact'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='extent'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='history'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='langUsage'>
+  <complexType mixed='true'>
+   <attribute name='codes' type='string' use='optional'/>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='restrictions'>
+  <complexType mixed='true'>
+   <attribute name='primary' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='lang' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='subjects'>
+  <complexType>
+   <sequence>
+    <element ref='explain:subject' maxOccurs='unbounded'/>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='subject'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='links'>
+  <complexType>
+   <sequence>
+    <element ref='explain:link' maxOccurs='unbounded'/>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='link'>
+  <complexType mixed='true'>
+   <attribute name='type' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='implementation'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+   </sequence>
+   <attribute name='identifier' type='string' use='optional'/>
+   <attribute name='version' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='metaInfo'>
+  <complexType>
+   <sequence>
+    <element ref='explain:dateModified'/>
+    <sequence minOccurs='0' maxOccurs='1'>
+     <element ref='explain:aggregatedFrom'/>
+     <element ref='explain:dateAggregated'/>
+    </sequence>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='dateModified'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='aggregatedFrom'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='dateAggregated'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='indexInfo'>
+  <complexType>
+   <choice maxOccurs='unbounded'>
+    <element ref='explain:set'/>
+    <element ref='explain:index'/>
+    <element ref='explain:sortKeyword'/>
+   </choice>
+  </complexType>
+ </element>
+
+ <element name='set'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+   </sequence>
+   <attribute name='name' type='string' use='required'/>
+   <attribute name='identifier' type='string' use='required'/>
+  </complexType>
+ </element>
+
+ <element name='index'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+    <element ref='explain:map' maxOccurs='unbounded'/>
+    <element ref='explain:configInfo' minOccurs='0' maxOccurs='1'/>
+   </sequence>
+   <attribute name='id' type='string' use='optional'/>
+   <attribute name='search' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='scan' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='sort' use='optional'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+  </complexType>
+ </element>
+
+ <element name='sortKeyword'>
+  <complexType mixed='true'>
+  </complexType>
+ </element>
+
+ <element name='map'>
+  <complexType>
+   <choice>
+    <sequence>
+     <element ref='explain:attr' maxOccurs='unbounded'/>
+    </sequence>
+    <element ref='explain:name'/>
+   </choice>
+   <attribute name='primary' use='optional' default='false'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+  </complexType>
+ </element>
+
+ <element name='name'>
+  <complexType mixed='true'>
+   <attribute name='set' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='attr'>
+  <complexType mixed='true'>
+   <attribute name='type' type='string' use='required'/>
+   <attribute name='set' type='string' use='optional' default='1.2.840.10003.3.1'/>
+  </complexType>
+ </element>
+
+ <element name='recordInfo'>
+  <complexType>
+   <sequence>
+    <element ref='explain:recordSyntax' maxOccurs='unbounded'/>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='recordSyntax'>
+  <complexType>
+   <sequence>
+    <element ref='explain:elementSet' maxOccurs='unbounded'/>
+   </sequence>
+   <attribute name='name' type='string' use='optional'/>
+   <attribute name='identifier' type='string' use='optional'/>
+  </complexType>
+ </element>
+
+ <element name='elementSet'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+   </sequence>
+   <attribute name='name' type='string' use='required'/>
+  </complexType>
+ </element>
+
+ <element name='schemaInfo'>
+  <complexType>
+   <sequence>
+    <element ref='explain:schema' maxOccurs='unbounded'/>
+   </sequence>
+  </complexType>
+ </element>
+
+ <element name='schema'>
+  <complexType>
+   <sequence>
+    <element ref='explain:title' minOccurs='0' maxOccurs='unbounded'/>
+   </sequence>
+   <attribute name='identifier' type='string' use='required'/>
+   <attribute name='name' type='string' use='required'/>
+   <attribute name='location' type='string' use='optional'/>
+   <attribute name='sort' use='optional' default='false'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+   <attribute name='retrieve' use='optional' default='true'>
+    <simpleType>
+     <restriction base='string'>
+      <enumeration value='true'/>
+      <enumeration value='false'/>
+     </restriction>
+    </simpleType>
+   </attribute>
+  </complexType>
+ </element>
+
+ <element name='configInfo'>
+  <complexType>
+   <choice minOccurs='0' maxOccurs='unbounded'>
+    <element ref='explain:default'/>
+    <element ref='explain:setting'/>
+    <element ref='explain:supports'/>
+   </choice>
+  </complexType>
+ </element>
+
+ <element name='default'>
+  <complexType mixed='true'>
+   <attribute name='type' type='string' use='required'/>
+  </complexType>
+ </element>
+
+ <element name='setting'>
+  <complexType mixed='true'>
+   <attribute name='type' type='string' use='required'/>
+  </complexType>
+ </element>
+
+ <element name='supports'>
+  <complexType mixed='true'>
+   <attribute name='type' type='string' use='required'/>
+  </complexType>
+ </element>
+</schema>

diff --git a/zebra/zeerex.xml b/zebra/zeerex.xml
new file mode 100644 (file)
index 0000000..f16f0f9
--- /dev/null
+++ b/zebra/zeerex.xml
@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- $Id: zeerex.xml,v 1.1 2006-04-13 14:53:17 mike Exp $ -->
+<explain xmlns="http://explain.z3950.org/dtd/2.0/">
+ <serverInfo protocol="SRW/SRU/Z39.50" version="1.1" method="GET/POST">
+  <host>localhost</host>
+  <port>1313</port>
+  <database>Default</database>
+ </serverInfo>
+ <databaseInfo>
+  <title lang="en" primary="true">IRSpy database of ZeeRex records</title>
+  <author>Mike Taylor, Index Data Aps, http://www.indexdata.com</author>
+  <contact>mike@indexdata.com</contact>
+ </databaseInfo>
+ <!-- ### Much, much more to be added -->
+</explain>

diff --git a/zebra/zeerex2index.xsl b/zebra/zeerex2index.xsl
new file mode 100644 (file)
index 0000000..8eab014
--- /dev/null
+++ b/zebra/zeerex2index.xsl
@@ -0,0 +1,50 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- $Id: zeerex2index.xsl,v 1.1 2006-04-13 14:53:18 mike Exp $ -->
+<!-- See the ZeeRex profile at http://srw.cheshire3.org/profiles/ZeeRex/ -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                xmlns:z="http://indexdata.dk/zebra/xslt/1"
+                xmlns:e="http://explain.z3950.org/dtd/2.0/"
+                version="1.0">
+ <xsl:output indent="yes" method="xml" version="1.0" encoding="UTF-8"/>
+ <!-- disable all default text node output -->
+ <xsl:template match="text()"/>
+ <!-- match on alvis xml record -->
+ <xsl:template match="//e:explain">
+  <z:record id="{concat(
+               e:serverInfo/e:host, ':',
+               e:serverInfo/e:port, '/',
+               e:serverInfo/e:database)}"
+           type="update">
+   <z:index name="rec:id" type="0">
+    <xsl:value-of select="concat(
+                         e:serverInfo/e:host, ':',
+                         e:serverInfo/e:port, '/',
+                         e:serverInfo/e:database)"/>
+   </z:index>
+   <z:index name="net:protocol" type="w">
+    <xsl:value-of select="e:serverInfo/@protocol"/>
+   </z:index>
+   <z:index name="net:version" type="0">
+    <xsl:value-of select="e:serverInfo/@version"/>
+   </z:index>
+   <z:index name="net:method" type="w">
+    <xsl:value-of select="e:serverInfo/@method"/>
+   </z:index>
+   <z:index name="net:host" type="0">
+    <xsl:value-of select="e:serverInfo/e:host"/>
+   </z:index>
+   <z:index name="net:port" type="0">
+    <xsl:value-of select="e:serverInfo/e:port"/>
+   </z:index>
+   <z:index name="net:path" type="0">
+    <xsl:value-of select="e:serverInfo/e:database"/>
+   </z:index>
+   <z:index name="dc:title" type="w">
+    <xsl:value-of select="e:databaseInfo/e:title"/>
+   </z:index>
+   <z:index name="dc:creator" type="w">
+    <xsl:value-of select="e:databaseInfo/e:author"/>
+   </z:index>
+  </z:record>
+ </xsl:template>
+</xsl:stylesheet>

diff --git a/zebra/zeerex2zeerex.xsl b/zebra/zeerex2zeerex.xsl
new file mode 100644 (file)
index 0000000..cfbdde2
--- /dev/null
+++ b/zebra/zeerex2zeerex.xsl
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- $Id: zeerex2zeerex.xsl,v 1.1 2006-04-13 14:53:18 mike Exp $ -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
+ <xsl:output indent="yes" method="xml" version="1.0" encoding="UTF-8"/>
+ <xsl:template match="/">
+  <xsl:copy-of select="/"/>
+ </xsl:template>
+</xsl:stylesheet>