Update WRT settings, relevance etc.

diff --git a/doc/pazpar2_conf.xml b/doc/pazpar2_conf.xml
index 9f0272d..c2d2227 100644 (file)
--- a/doc/pazpar2_conf.xml
+++ b/doc/pazpar2_conf.xml
@@ -101,80 +101,30 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </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>
-     </listitem>
-    </varlistentry>

 
     <varlistentry>
 
     <varlistentry>

-     <term>sort</term>
+     <term>relevance / sort / mergekey</term>

      <listitem>
       <para>
      <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>.
+       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>
       </para>
      </listitem>
     </varlistentry>
     
     <varlistentry>

-     <term>mergekey</term>
+     <term>settings</term>

      <listitem>
       <para>
      <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>.
+       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>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

@@ -322,7 +272,6 @@
           </listitem>
          </varlistentry>
 
           </listitem>
          </varlistentry>
 

-

          <varlistentry><term>setting</term>
           <listitem>
            <para>
          <varlistentry><term>setting</term>
           <listitem>
            <para>

@@ -337,22 +286,117 @@
              the value to decide how to deal with other data values.
            </para>
            <para>
              the value to decide how to deal with other data values.
            </para>
            <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.
              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>
           </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>
+

       </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>
 

@@ -360,38 +404,35 @@
  
  <refsect1><title>EXAMPLE</title>
   <para>Below is a working example configuration:
  
  <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"/>
+        <service>
+     </server>
+   </pazpar2>
+    ]]></screen>

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