Timeout per-service, obsoletes -T

[pazpar2-moved-to-github.git] / doc / pazpar2_conf.xml

diff --git a/doc/pazpar2_conf.xml b/doc/pazpar2_conf.xml
index dab43f6..9d08cbc 100644 (file)
--- a/doc/pazpar2_conf.xml
+++ b/doc/pazpar2_conf.xml
@@ -1,3 +1,4 @@
+<?xml version="1.0" standalone="no"?>

 <!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN"
  "http://www.oasis-open.org/docbook/xml/4.1/docbookx.dtd"
 [
 <!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN"
  "http://www.oasis-open.org/docbook/xml/4.1/docbookx.dtd"
 [

@@ -8,7 +9,6 @@
      <!ENTITY % idcommon SYSTEM "common/common.ent">
      %idcommon;
 ]>
      <!ENTITY % idcommon SYSTEM "common/common.ent">
      %idcommon;
 ]>

-<!-- $Id: pazpar2_conf.xml,v 1.27 2007-06-22 13:18:23 adam Exp $ -->

 <refentry id="pazpar2_conf">
  <refentryinfo>
   <productname>Pazpar2</productname>
 <refentry id="pazpar2_conf">
  <refentryinfo>
   <productname>Pazpar2</productname>

@@ -59,8 +59,9 @@
   
   <refsect2 id="config-server"><title>server</title>
    <para>
   
   <refsect2 id="config-server"><title>server</title>
    <para>

-    This section governs overall behavior of the client. The data
-    elements are described below.
+    This section governs overall behavior of the server. The data
+    elements are described below. From Pazpar2 version 1.2 this is
+    a repeatable element.

    </para>
    <variablelist> <!-- level 1 -->
     <varlistentry>
    </para>
    <variablelist> <!-- level 1 -->
     <varlistentry>

@@ -100,70 +101,31 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

+
+    <varlistentry>
+     <term>relevance / sort / mergekey</term>
+     <listitem>
+      <para>
+       Specifies character set normalization for relevancy / sorting 
+       and the mergekey - for the server. These definitions serves as
+       default for services that don't have these given. For the meaning
+       of these settings refer to the "relevance" element inside service.
+      </para>
+     </listitem>
+    </varlistentry>

     
     <varlistentry>
     
     <varlistentry>

-     <term>icu_chain</term>
+     <term>settings</term>

      <listitem>
       <para>
      <listitem>
       <para>

-       Definition of ICU tokenization and normalization rules
-       are used if ICU support is compiled in.  The 'id'
-       attribute is currently not used, and the 'locale'
-       attribute must be set to one of the locale strings
-       defined in ICU. The child elements listed below can be
-       in any order, except the 'index' element which logically
-       belongs to the end of the list. The stated tokenization,
-       normalization and charmapping instructions are performed
-       in order from top to bottom. 
+       Specifies target settings for the server.. These settings serves
+       as default for all services which don't have these given.
+       The settings element requires one attribute 'src' which specifies
+       a settings file or a directory . If a directory is given all
+       files with suffix <filename>.xml</filename> is read from this
+       directory. Refer to 
+       <xref linkend="target_settings"/> for more information.

       </para>
       </para>

-      <variablelist> <!-- Level 2 -->
-       <varlistentry><term>casemap</term>
-       <listitem>
-        <para>
-         The attribute 'rule' defines the direction of the
-         per-character casemapping, allowed values are "l"
-         (lower), "u" (upper), "t" (title).  
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>normalize</term>
-       <listitem>
-        <para>
-         Normalization and transformation of tokens follows
-         the rules defined in the 'rule' attribute. For
-         possible values we refer to the extensive ICU
-         documentation found at the 
-         <ulink url="&url.icu.transform;">ICU
-          transformation</ulink> home page. Set filtering
-         principles are explained at the 
-         <ulink url="&url.icu.unicode.set;">ICU set and
-          filtering</ulink> page.
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>tokenize</term>
-       <listitem>
-        <para>
-         Tokenization is the only rule in the ICU chain
-         which splits one token into multiple tokens. The
-         'rule' attribute may have the following values:
-         "s" (sentence), "l" (line-break), "w" (word), and
-         "c" (character), the later probably not being
-         very useful in a pruning Pazpar2 installation. 
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>index</term>
-       <listitem>
-        <para>
-         Finally the 'index' element instruction - without
-         any 'rule' attribute - is used to store the tokens
-         after chain processing in the relevance ranking
-         unit of Pazpar2. It will always be the last
-         instruction in the chain.
-        </para>
-       </listitem>
-       </varlistentry>
-      </variablelist>

      </listitem>
     </varlistentry>
     
      </listitem>
     </varlistentry>
     

@@ -178,7 +140,16 @@
        extraction of data from the internal representation, primarily
        through the 'metadata' sub-element.
       </para>
        extraction of data from the internal representation, primarily
        through the 'metadata' sub-element.
       </para>

-      
+      <para>
+       Pazpar2 version 1.2 and later allows multiple service elements.
+       Multiple services must be given a unique ID by specifying
+       attribute <literal>id</literal>.
+       A single service may be unnamed (service ID omitted). The
+       service ID is referred to in the
+       <link linkend="command-init"><literal>init</literal></link> webservice
+       command's <literal>service</literal> parameter.
+      </para>
+

       <variablelist> <!-- Level 2 -->
        <varlistentry><term>metadata</term>
        <listitem>
       <variablelist> <!-- Level 2 -->
        <varlistentry><term>metadata</term>
        <listitem>

@@ -290,55 +261,212 @@
            </para>
           </listitem>
          </varlistentry>
            </para>
           </listitem>
          </varlistentry>

+
+         <varlistentry><term>mergekey</term>
+          <listitem>
+           <para>
+            If set to <literal>yes</literal>, the value of this
+            metadata element is appended to the resulting mergekey.
+            By default metadata is not part of a mergekey.
+           </para>
+          </listitem>
+         </varlistentry>
+
+         <varlistentry><term>setting</term>
+          <listitem>
+           <para>
+             This attribute allows you to make use of static database
+             settings in the processing of records. Three possible values
+             are allowed. 'no' is the default and doesn't do anything.
+             'postproc' copies the value of a setting with the same name
+             into the output of the normalization stylesheet(s). 'parameter'
+             makes the value of a setting with the same name available 
+             as a parameter to the normalization stylesheet, so you
+             can further process the value inside of the stylesheet, or use
+             the value to decide how to deal with other data values.
+           </para>
+           <para>
+             The purpose of using settings in this way can either be to
+             control the behavior of normalization stylesheet in a database-
+             dependent way, or to easily make database-dependent values
+             available to display-logic in your user interface, without having
+             to implement complicated interactions between the user interface
+             and your configuration system.
+           </para>
+          </listitem>
+         </varlistentry>
+         

         </variablelist> <!-- attributes to metadata -->
         
        </listitem>
        </varlistentry>
         </variablelist> <!-- attributes to metadata -->
         
        </listitem>
        </varlistentry>

+       
+       <varlistentry>
+       <term>relevance</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's relevance ranking.
+         The 'id' attribute is currently not used, and the 'locale'
+         attribute must be set to one of the locale strings
+         defined in ICU. The child elements listed below can be
+         in any order, except the 'index' element which logically
+         belongs to the end of the list. The stated tokenization,
+         transformation and charmapping instructions are performed
+         in order from top to bottom. 
+        </para>
+        <variablelist> <!-- Level 2 -->
+         <varlistentry><term>casemap</term>
+          <listitem>
+           <para>
+            The attribute 'rule' defines the direction of the
+            per-character casemapping, allowed values are "l"
+            (lower), "u" (upper), "t" (title).  
+           </para>
+          </listitem>
+         </varlistentry>
+         <varlistentry><term>transform</term>
+          <listitem>
+           <para>
+            Normalization and transformation of tokens follows
+            the rules defined in the 'rule' attribute. For
+            possible values we refer to the extensive ICU
+            documentation found at the 
+            <ulink url="&url.icu.transform;">ICU
+             transformation</ulink> home page. Set filtering
+            principles are explained at the 
+            <ulink url="&url.icu.unicode.set;">ICU set and
+             filtering</ulink> page.
+           </para>
+          </listitem>
+         </varlistentry>
+         <varlistentry><term>tokenize</term>
+          <listitem>
+           <para>
+            Tokenization is the only rule in the ICU chain
+            which splits one token into multiple tokens. The
+            'rule' attribute may have the following values:
+            "s" (sentence), "l" (line-break), "w" (word), and
+            "c" (character), the later probably not being
+            very useful in a pruning Pazpar2 installation. 
+           </para>
+          </listitem>
+         </varlistentry>
+        </variablelist>
+        <para>
+         From Pazpar2 version 1.1 the ICU wrapper from YAZ is used.
+         Refer to the <ulink url="&url.yaz.yaz-icu;">yaz-icu</ulink>
+         utility for more information.
+        </para>
+       </listitem>
+       </varlistentry>
+       
+       <varlistentry>
+       <term>sort</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's sorting. The contents
+         is similar to that of <literal>relevance</literal>.
+        </para>
+       </listitem>
+       </varlistentry>
+       
+       <varlistentry>
+       <term>mergekey</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's mergekey. The contents
+         is similar to that of <literal>relevance</literal>.
+        </para>
+       </listitem>
+       </varlistentry>
+
+       <varlistentry>
+       <term>settings</term>
+       <listitem>
+        <para>
+         Specifies target settings for this service. Refer to
+         <xref linkend="target_settings"/>.
+        </para>
+       </listitem>
+       </varlistentry>
+
+       <varlistentry>
+       <term>timeout</term>
+       <listitem>
+        <para>
+         Specifies timeout parameters for this service.
+         The <literal>timeout</literal>
+         element supports the following attributes: 
+         <literal>session</literal>, <literal>z3950_connect</literal>,
+         <literal>z3950_session</literal> which specifies
+         'session timeout', 'Z39.50 connect timeout', 'Z39.50 session timeout'
+         respectively.
+        </para>
+       </listitem>
+       </varlistentry>
+

       </variablelist>     <!-- Data elements in service directive -->
      </listitem>
     </varlistentry>
       </variablelist>     <!-- Data elements in service directive -->
      </listitem>
     </varlistentry>

+    

    </variablelist>           <!-- Data elements in server directive -->
   </refsect2>
    </variablelist>           <!-- Data elements in server directive -->
   </refsect2>

-  
+

  </refsect1>
  
  <refsect1><title>EXAMPLE</title>
   <para>Below is a working example configuration:
  </refsect1>
  
  <refsect1><title>EXAMPLE</title>
   <para>Below is a working example configuration:

-  <screen><![CDATA[
-<?xml version="1.0" encoding="UTF-8"?>
-<pazpar2 xmlns="http://www.indexdata.com/pazpar2/1.0">
-
-<server>
-  <listen port="9004"/>
-  <proxy host="us1.indexdata.com" myurl="us1.indexdata.com"/>
-
-  <!-- optional ICU ranking configuration example -->
-  <!--
-  <icu_chain id="el:word" locale="el">
-    <normalize rule="[:Control:] Any-Remove"/>
-    <tokenize rule="l"/>
-    <normalize rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
-    <casemap rule="l"/>
-    <index/>
-  </icu_chain>
-  -->
-
-  <service>
-    <metadata name="title" brief="yes" sortkey="skiparticle" merge="longest" rank="6"/>
-    <metadata name="isbn" merge="unique"/>
-    <metadata name="date" brief="yes" sortkey="numeric" type="year" merge="range"
-           termlist="yes"/>
-    <metadata name="author" brief="yes" termlist="yes" merge="longest" rank="2"/>
-    <metadata name="subject" merge="unique" termlist="yes" rank="3"/>
-    <metadata name="url" merge="unique"/>
-  </service>
-</server>
-
-</pazpar2>
-]]></screen>
+   <screen><![CDATA[
+    <?xml version="1.0" encoding="UTF-8"?>
+    <pazpar2 xmlns="http://www.indexdata.com/pazpar2/1.0">
+    
+      <server>
+        <listen port="9004"/>
+        <service>
+          <metadata name="title" brief="yes" sortkey="skiparticle"
+             merge="longest" rank="6"/>
+          <metadata name="isbn" merge="unique"/>
+          <metadata name="date" brief="yes" sortkey="numeric"
+             type="year" merge="range" termlist="yes"/>
+          <metadata name="author" brief="yes" termlist="yes"
+             merge="longest" rank="2"/>
+          <metadata name="subject" merge="unique" termlist="yes" rank="3"/>
+          <metadata name="url" merge="unique"/>
+          <relevance>
+            <icu_chain id="relevance" locale="el">
+              <transform rule="[:Control:] Any-Remove"/>
+              <tokenize rule="l"/>
+              <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
+              <casemap rule="l"/>
+             </icu_chain>
+           </relevance>
+           <settings src="mysettings"/>
+           <timeout session="60"/>
+        <service>
+     </server>
+   </pazpar2>
+    ]]></screen>

   </para>
  </refsect1> 
   </para>
  </refsect1> 

- 
+
+ <refsect1 id="config-include"><title>INCLUDE FACILITY</title>
+  <para>
+   The XML configuration may be partitioned into multiple files by using
+   the <literal>include</literal> element which takes a single attribute,
+   <literal>src</literal>. The of the <literal>src</literal> attribute is
+   regular Shell like glob-pattern. For example,
+   <screen><![CDATA[
+    <include src="/etc/pazpar2/conf.d/*.xml"/>
+    ]]></screen>
+  </para>
+  <para>
+   The include facility requires Pazpar2 version 1.2.
+  </para>
+ </refsect1>
+

  <refsect1 id="target_settings"><title>TARGET SETTINGS</title>
   <para>
    Pazpar2 features a cunning scheme by which you can associate various
  <refsect1 id="target_settings"><title>TARGET SETTINGS</title>
   <para>
    Pazpar2 features a cunning scheme by which you can associate various

@@ -351,7 +479,9 @@
    pairs with groups of targets -- for instance, if you would like to
    place all commercial full-text bases in one group for selection
    purposes, or you would like to control what targets are accessible
    pairs with groups of targets -- for instance, if you would like to
    place all commercial full-text bases in one group for selection
    purposes, or you would like to control what targets are accessible

-   to users by default.
+   to users by default. Per-database settings values can even be used
+   to drive sorting, facet/termlist generation, or end-user interface display
+   logic.

   </para>
   
   <para>
   </para>
   
   <para>

@@ -372,7 +502,9 @@
    environment, where different end-users may need to be represented to
    some search targets in different ways. This, again, can be managed
    using an external database or other lookup mechanism. Setting overrides
    environment, where different end-users may need to be represented to
    some search targets in different ways. This, again, can be managed
    using an external database or other lookup mechanism. Setting overrides

-   can be performed either using the 'init' or the 'settings' webservice
+   can be performed either using the
+   <link linkend="command-init">init</link> or the 
+   <link linkend="command-settings">settings</link> webservice

    command.
   </para>
   
    command.
   </para>
   

@@ -385,8 +517,10 @@
   
   <para>
    Finally, as an extreme case of this, the webservice client can
   
   <para>
    Finally, as an extreme case of this, the webservice client can

-   introduce entirely new targets, on the fly, as part of the init or
-   settings command. This is useful if you desire to manage information
+   introduce entirely new targets, on the fly, as part of the
+   <link linkend="command-init">init</link> or
+   <link linkend="command-settings">settings</link> command.
+   This is useful if you desire to manage information

    about your search targets in a separate application such as a database.
    You do not need any static settings file whatsoever to run Pazpar2 -- as
    long as the webservice client is prepared to supply the necessary
    about your search targets in a separate application such as a database.
    You do not need any static settings file whatsoever to run Pazpar2 -- as
    long as the webservice client is prepared to supply the necessary

@@ -541,7 +675,6 @@
 <settings target="*">
 
   <!-- This file introduces default settings for pazpar2 -->
 <settings target="*">
 
   <!-- This file introduces default settings for pazpar2 -->

-  <!-- $Id: pazpar2_conf.xml,v 1.27 2007-06-22 13:18:23 adam Exp $ -->

 
   <!-- mapping for unqualified search -->
   <set name="pz:cclmap:term" value="u=1016 t=l,r s=al"/>
 
   <!-- mapping for unqualified search -->
   <set name="pz:cclmap:term" value="u=1016 t=l,r s=al"/>

@@ -556,7 +689,10 @@
   <!-- Retrieval settings -->
 
   <set name="pz:requestsyntax" value="marc21"/>
   <!-- Retrieval settings -->
 
   <set name="pz:requestsyntax" value="marc21"/>

-  <!-- <set name="pz:elements" value="F"/> NOT YET IMPLEMENTED -->
+  <set name="pz:elements" value="F"/>
+
+  <!-- Query encoding -->
+  <set name="pz:queryencoding" value="iso-8859-1"/>

 
   <!-- Result normalization settings -->
 
 
   <!-- Result normalization settings -->
 

@@ -636,7 +772,7 @@
      <listitem>
       <para>
        The element set name to be used when retrieving records from a
      <listitem>
       <para>
        The element set name to be used when retrieving records from a

-       server (not yet implemented).
+       server.

       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

@@ -664,8 +800,24 @@
        For iso2709, can also specify a native character set, e.g. "iso2709;latin-1".
        If no character set is provided, MARC-8 is assumed.
       </para>
        For iso2709, can also specify a native character set, e.g. "iso2709;latin-1".
        If no character set is provided, MARC-8 is assumed.
       </para>

+      <para>
+        If pz:nativesyntax is not specified, pazpar2 will attempt to determine
+       the value based on the response from the server.
+      </para>
+     </listitem>
+    </varlistentry>
+
+    <varlistentry>
+     <term>pz:queryencoding</term>
+     <listitem>
+      <para>
+        The encoding of the search terms that a target accepts. Most
+        targets do not honor UTF-8 in which case this needs to be specified.
+        Each term in a query will be converted if this setting is given.
+      </para>

      </listitem>
     </varlistentry>
      </listitem>
     </varlistentry>

+

     <varlistentry>
      <term>pz:xslt</term>
      <listitem>
     <varlistentry>
      <term>pz:xslt</term>
      <listitem>

@@ -700,7 +852,7 @@
      <listitem>
       <para>
        Controls the maximum number of records to be retrieved from a
      <listitem>
       <para>
        Controls the maximum number of records to be retrieved from a

-       server. The default is 100 (not yet implemented).
+       server. The default is 100.

       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

@@ -725,10 +877,82 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

+
+    <varlistentry>
+     <term>pz:apdulog</term>
+     <listitem>
+      <para>
+       If the 'pz:apdulog' setting is defined and has other value than 0,
+       then Z39.50 APDUs are written to the log.
+      </para>
+     </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>pz:sru</term>
+      <listitem>
+        <para>
+         This setting enables SRU/SRW support. It has three possible settings.
+         'get', enables SRU access through GET requests. 'post' enables SRU/POST
+         support, less commonly supported, but useful if very large requests are
+         to be submitted. 'srw' enables the SRW variation of the protocol.
+       </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>pz:sru_version</term>
+      <listitem>
+        <para>
+         This allows SRU version to be specified. If unset Pazpar2
+         will the default of YAZ (currently 1.2). Should be set
+         to 1.1 or 1.2.
+       </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>pz:pqf_prefix</term>
+      <listitem>
+        <para>
+         Allows you to specify an arbitrary PQF query language substring. The provided
+         string is prefixed the user's query after it has been normalized to PQF
+         internally in pazpar2. This allows you to attach complex 'filters' to
+         queries for a gien target, sometimes necessary to select sub-catalogs
+         in union catalog systems, etc.
+       </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>pz:sort</term>
+      <listitem>
+        <para>
+         Specifies sort criteria to be applied to the result set. Only works for targets
+         which support the sort service.
+       </para>
+      </listitem>
+    </varlistentry>

    </variablelist>
   </refsect2>
 
  </refsect1>
    </variablelist>
   </refsect2>
 
  </refsect1>

+ <refsect1><title>SEE ALSO</title>
+  <para>
+   <citerefentry>
+    <refentrytitle>pazpar2</refentrytitle>
+    <manvolnum>8</manvolnum>
+   </citerefentry>
+   <citerefentry>
+    <refentrytitle>yaz-icu</refentrytitle>
+    <manvolnum>1</manvolnum>
+   </citerefentry>
+   <citerefentry>
+    <refentrytitle>pazpar2_protocol</refentrytitle>
+    <manvolnum>7</manvolnum>
+   </citerefentry>
+  </para>
+ </refsect1>

 </refentry>
 <!-- Keep this comment at the end of the file
 Local variables:
 </refentry>
 <!-- Keep this comment at the end of the file
 Local variables: