Tweak rank/relevance algorithm

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

diff --git a/doc/pazpar2_conf.xml b/doc/pazpar2_conf.xml
index f66068e..454cc02 100644 (file)
--- a/doc/pazpar2_conf.xml
+++ b/doc/pazpar2_conf.xml
@@ -262,17 +262,33 @@
             Specifies that this element is to be used to
             help rank 
             records against the user's query (when ranking is
             Specifies that this element is to be used to
             help rank 
             records against the user's query (when ranking is

-            requested). The value is an integer, used as a
+            requested). 
+            The valus is of the form 
+            <literallayout>
+             M [F N]
+            </literallayout>
+            where M is an integer, used as a

             multiplier against the basic TF*IDF score. A value of
             multiplier against the basic TF*IDF score. A value of

-            1 is the base, higher values give additional
-            weight to 
+            1 is the base, higher values give additional weight to

             elements of this type. The default is '0', which
             excludes this element from the rank calculation.
            </para>
            <para>
             elements of this type. The default is '0', which
             excludes this element from the rank calculation.
            </para>
            <para>

+            F is a CCL field and N is the multipler for terms
+            that matches those part of the CCL field in search.
+            The F+N combo allows the system to use a different
+            multipler for a certain field. For example, a rank value of
+            "<literal>1 au 3</literal>" gives a multipler of 3 for
+            all terms part of the au(thor) terms and 1 for everything else.
+           </para>
+           <para>

             For Pazpar2 1.6.13 and later, the rank may also defined
             "per-document", by the normalization stylesheet. 
            </para>
             For Pazpar2 1.6.13 and later, the rank may also defined
             "per-document", by the normalization stylesheet. 
            </para>

+           <para>
+            The per field rank was introduced in Pazpar2 1.6.15. Earlier
+            releases only allowed a rank value M (simple integer).
+           </para>

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

@@ -343,6 +359,28 @@
          </varlistentry>
          
          <varlistentry>
          </varlistentry>
          
          <varlistentry>

+          <term id="metadata_limitmap">limitmap</term>
+          <listitem>
+           <para>
+            Specifies a default limitmap for this field. This is to avoid mass 
+            configuring of targets. However it is important to review/do this on a per
+            target since it is usually target-specific. See limitmap for format. 
+           </para>
+          </listitem>
+         </varlistentry>
+         
+         <varlistentry>
+          <term id="metadata_facetmap">facetmap</term>
+          <listitem>
+           <para>
+            Specifies a default facetmap for this field. This is to avoid mass 
+            configuring of targets. However it is important to review/do this on a per
+            target since it is usually target-specific. See facetmap for format. 
+           </para>
+          </listitem>
+         </varlistentry>
+         
+         <varlistentry>

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

@@ -525,7 +563,53 @@
         </para>
        </listitem>
        </varlistentry>
         </para>
        </listitem>
        </varlistentry>

-       
+
+       <varlistentry>
+       <term>ccldirective</term>
+       <listitem>
+        <para>
+         Customizes the CCL parsing (interpretation of query parameter
+         in search).
+         The name and value of the CCL directive is gigen by attributes
+         'name' and 'value' respectively. Refer to possible list of names
+         in the
+         <ulink 
+             url="http://www.indexdata.com/yaz/doc/tools.html#ccl.directives.table">
+          YAZ manual
+          </ulink>.
+        </para>
+       </listitem>
+       </varlistentry>
+
+       <varlistentry>
+       <term>rank</term>
+       <listitem>
+        <para>
+         Customizes the ranking (relevance) algorithm.
+         Attribute 'cluster' is a boolean
+         that controls whether Pazpar2 should boost ranking for merged
+         records. Is 'yes' by default. A value of 'no' will make
+         Pazpar2 avergage ranking of each record in a cluster.
+        </para>
+        <para>
+         This configuration was added in pazpar2 1.6.18.
+        </para>
+       </listitem>
+       </varlistentry>
+
+<!--       
+       <varlistentry>
+       <term>set</term>
+       <listitem>
+        <para>
+         Specifies a variable that will be inherited by all targets defined in settings
+         <screen>
+          &lt;set name="test" value="en"..&lt;set>
+         </screen>
+        </para>
+       </listitem>
+       </varlistentry>
+-->   

        <varlistentry>
        <term>settings</term>
        <listitem>
        <varlistentry>
        <term>settings</term>
        <listitem>

@@ -587,7 +671,7 @@
              type="year" merge="range" termlist="yes"/>
    <metadata name="author" brief="yes" termlist="yes"
              merge="longest" rank="2"/>
              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="subject" merge="unique" termlist="yes" rank="3" limitmap="local:"/>

    <metadata name="url" merge="unique"/>
    <icu_chain id="relevance" locale="el">
     <transform rule="[:Control:] Any-Remove"/>
    <metadata name="url" merge="unique"/>
    <icu_chain id="relevance" locale="el">
     <transform rule="[:Control:] Any-Remove"/>

@@ -1082,6 +1166,15 @@
      </listitem>
     </varlistentry>
     <varlistentry>
      </listitem>
     </varlistentry>
     <varlistentry>

+     <term>pz:presentchunk</term>
+     <listitem>
+      <para>
+       Controls the chunk size in present requests. Pazpar2 will 
+       make (maxrecs / chunk) request(s). The default is 20.
+      </para>
+     </listitem>
+    </varlistentry>
+    <varlistentry>

      <term>pz:id</term>
      <listitem>
       <para>
      <term>pz:id</term>
      <listitem>
       <para>

@@ -1118,7 +1211,7 @@
      <listitem>
       <para>
        This setting enables
      <listitem>
       <para>
        This setting enables

-       <ulink url="&url.sru;">SRU</ulink>/<ulink url="&url.solr;">SOLR</ulink>
+       <ulink url="&url.sru;">SRU</ulink>/<ulink url="&url.solr;">Solr</ulink>

        support.
        It has four possible settings.
        'get', enables SRU access through GET requests. 'post' enables SRU/POST
        support.
        It has four possible settings.
        'get', enables SRU access through GET requests. 'post' enables SRU/POST

@@ -1127,7 +1220,7 @@
        the protocol.
       </para>
       <para>
        the protocol.
       </para>
       <para>

-       A value of 'solr' anables SOLR client support. This is supported
+       A value of 'solr' enables Solr client support. This is supported

        for Pazpar version 1.5.0 and later.
       </para>
      </listitem>
        for Pazpar version 1.5.0 and later.
       </para>
      </listitem>

@@ -1139,7 +1232,7 @@
       <para>
        This allows SRU version to be specified. If unset Pazpar2
        will the default of YAZ (currently 1.2). Should be set
       <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. For SOLR, the current supported/tested version is 1.4
+       to 1.1 or 1.2. For Solr, the current supported/tested version is 1.4 and 3.x.

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

@@ -1224,7 +1317,6 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

-

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

@@ -1234,6 +1326,29 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

+    <varlistentry>
+     <term>pz:termlist_term_count</term>
+     <listitem>
+      <para>
+       Specifies number of facet terms to be requested from the target. 
+       The default is unspecified e.g. server-decided. Also see pz:facetmap.
+      </para>
+     </listitem>
+    </varlistentry>
+    <varlistentry>
+     <term>pz:termlist_term_factor</term>
+     <listitem>
+      <para>
+       Specifies whether to use a factor for pazpar2 generated facets (1) or not (0). 
+       When mixing locallly generated (by the downloaded (pz:maxrecs) samples) 
+       facet with native (target-generated) facets, the later will dominated the dominate the facet list
+       since they are generated based on the complete result set. 
+       By scaling up the facet count using the ratio between total hit count and the sample size, 
+       the total facet count can be approximated and thus better compared with native facets. 
+       This is not enabled by default.
+      </para>
+     </listitem>
+    </varlistentry>

 
     <varlistentry>
      <term>pz:facetmap:<replaceable>name</replaceable></term>
 
     <varlistentry>
      <term>pz:facetmap:<replaceable>name</replaceable></term>

@@ -1245,7 +1360,7 @@
       </para>
       <note>
        <para>
       </para>
       <note>
        <para>

-       At this point only SOLR targets have been tested with this
+       At this point only Solr targets have been tested with this

        facility.
        </para>
       </note>
        facility.
        </para>
       </note>