X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=doc%2Ffield-structure.xml;h=a10712ae6c719becf7fa6cfb015435c2305184ef;hb=300581b6fb502ae0ac1fb3802458526a6d40e2be;hp=3a0a5f2535027830e1d86c71c7b7cfe00c834376;hpb=a92270aafb3ba7b336bc2334ed7c44c631c1cb29;p=idzebra-moved-to-github.git

diff --git a/doc/field-structure.xml b/doc/field-structure.xml
index 3a0a5f2..a10712a 100644
--- a/doc/field-structure.xml
+++ b/doc/field-structure.xml
@@ -1,5 +1,5 @@
  <chapter id="fields-and-charsets">
-  <!-- $Id: field-structure.xml,v 1.8 2006-11-28 13:05:57 marc Exp $ -->
+  <!-- $Id: field-structure.xml,v 1.10 2006-11-28 14:37:45 marc Exp $ -->
   <title>Field Structure and Character Sets
   </title>
   
@@ -108,6 +108,40 @@
       </listitem></varlistentry>
     </variablelist>
    </para>
+   <para>
+    Following are three excerpts of the standard
+    <filename>tab/default.idx</filename> configuration file. Notice
+    that the <literal>index</literal> and <literal>sort</literal>
+    are grouping directives, which bind all other following directives
+    to them:
+    <screen>
+     # Traditional word index
+     # Used if completenss is 'incomplete field' (@attr 6=1) and
+     # structure is word/phrase/word-list/free-form-text/document-text
+     index w
+     completeness 0
+     position 1
+     alwaysmatches 1
+     firstinfield 1
+     charmap string.chr
+
+     ...
+
+     # Null map index (no mapping at all)
+     # Used if structure=key (@attr 4=3)
+     index 0
+     completeness 0
+     position 1
+     charmap @
+
+     ...
+
+     # Sort register
+     sort s
+     completeness 1
+     charmap string.chr
+    </screen>
+   </para>
   </section>
 
   <section id="character-map-files">
@@ -175,6 +209,29 @@
    <para>
     The contents of the character map files are structured as follows:
     <variablelist>
+     <varlistentry>
+      <term>encoding <replaceable>encoding-name</replaceable></term>
+      <listitem>
+       <para>
+	This directive must be at the very beginning of the file, and it
+        specifies the character encoding used in the entire file. If
+        omitted, the encoding <literal>ISO-8859-1</literal> is assumed.
+       </para>
+       <para>
+        For example, one of the test files found at  
+          <literal>test/rusmarc/tab/string.chr</literal> contains the following
+        encoding directive:
+        <screen>
+         encoding koi8-r
+        </screen>
+          and the test file
+          <literal>test/charmap/string.utf8.chr</literal> is encoded
+          in UTF-8:
+        <screen>
+         encoding utf-8
+        </screen>
+       </para>
+      </listitem></varlistentry>
 
      <varlistentry>
       <term>lowercase <replaceable>value-set</replaceable></term>