X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=doc%2Fyaz-icu-man.xml;h=d0fd43c414425ad3986131fa60faf071f3f6b085;hb=02b4f0ab937b62d892d3e0918439da770fe720c2;hp=7c2bda54bb65d1af5603a44fb4854cfbb1086eb2;hpb=5b5d2ba5455538ccc356e208476dc7aeb3703421;p=yaz-moved-to-github.git

diff --git a/doc/yaz-icu-man.xml b/doc/yaz-icu-man.xml
index 7c2bda5..d0fd43c 100644
--- a/doc/yaz-icu-man.xml
+++ b/doc/yaz-icu-man.xml
@@ -1,5 +1,5 @@
-<!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 V4.4//EN"
+ "http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"
 [
      <!ENTITY % local SYSTEM "local.ent">
      %local;
@@ -12,13 +12,15 @@
  <refentryinfo>
   <productname>YAZ</productname>
   <productnumber>&version;</productnumber>
+  <info><orgname>Index Data</orgname></info>
  </refentryinfo>
- 
+
  <refmeta>
   <refentrytitle>yaz-icu</refentrytitle>
   <manvolnum>1</manvolnum>
+  <refmiscinfo class="manual">Commands</refmiscinfo>
  </refmeta>
- 
+
  <refnamediv>
   <refname>yaz-icu</refname>
   <refpurpose>YAZ ICU utility</refpurpose>
@@ -27,19 +29,30 @@
  <refsynopsisdiv>
   <cmdsynopsis>
    <command>yaz-icu</command>
-   <arg choice="opt" rep="repeat">commands</arg>
    <arg>-c <replaceable>config</replaceable></arg>
    <arg>-p <replaceable>opt</replaceable></arg>
    <arg>-s</arg>
    <arg>-x</arg>
+   <arg choice="opt">infile</arg>
   </cmdsynopsis>
  </refsynopsisdiv>
- 
+
  <refsect1><title>DESCRIPTION</title>
   <para>
-   <command>yaz-icu</command> is utility which demonstrates 
+   <command>yaz-icu</command> is a utility which demonstrates
    the ICU chain module of yaz. (<filename>yaz/icu.h</filename>).
   </para>
+  <para>
+    The utility can be used in two ways. It may read some text
+    using an XML configuration for configuring ICU and show text analysis.
+    This mode is triggered by option <literal>-c</literal> which specifies
+    the configuration to be used. The input file is read from standard
+    input or from a file if <literal>infile</literal> is specified.
+  </para>
+  <para>
+    The utility may also show ICU information. This is triggered by
+    option <literal>-p</literal>.
+  </para>
  </refsect1>
 
  <refsect1><title>OPTIONS</title>
@@ -57,11 +70,11 @@
     <listitem><para>
       Specifies extra information to be printed about the ICU system.
       If <replaceable>type</replaceable> is <literal>c</literal>
-      then ICU converters are printed. 
-      If <replaceable>type</replaceable> is <literal>l</literal>
-      available locales are printed.
-      If <replaceable>type</replaceable> is <literal>t</literal>
-      available transliterators are printed.
+      then ICU converters are printed.
+      If <replaceable>type</replaceable> is <literal>l</literal>,
+      then available locales are printed.
+      If <replaceable>type</replaceable> is <literal>t</literal>,
+      then available transliterators are printed.
      </para></listitem>
    </varlistentry>
 
@@ -85,7 +98,7 @@
  </refsect1>
  <refsect1><title>ICU chain configuration</title>
   <para>
-   The ICU chain configuration speicifies one or more rules to convert
+   The ICU chain configuration specifies one or more rules to convert
    text data into tokens. The configuration format is XML based.
   </para>
   <para>
@@ -103,18 +116,18 @@
   </para>
   <para>
    The following conversion elements are available:
-   
+
    <variablelist>
     <varlistentry>
      <term>casemap</term>
      <listitem><para>
-       Converts case and rule specifies how:
+       Converts case (and rule specifies how):
 
        <variablelist>
 	<varlistentry>
 	 <term>l</term>
 	 <listitem>
-	  <para>Lowercase using ICU function u_strToLower. </para>
+	  <para>Lower case using ICU function u_strToLower. </para>
 	 </listitem>
 	</varlistentry>
 
@@ -124,11 +137,11 @@
 	  <para>Upper case using ICU function u_strToUpper.</para>
 	 </listitem>
 	</varlistentry>
-	
+
 	<varlistentry>
 	 <term>t</term>
 	 <listitem>
-	  <para>To title using UCU function u_strToTitle.</para>
+	  <para>To title using ICU function u_strToTitle.</para>
 	 </listitem>
 	</varlistentry>
 
@@ -138,7 +151,7 @@
 	  <para>Fold case using ICU function u_strFoldCase.</para>
 	 </listitem>
 	</varlistentry>
-	
+
        </variablelist>
       </para></listitem>
     </varlistentry>
@@ -151,7 +164,7 @@
        using function icu_chain_token_display (<filename>yaz/icu.h</filename>).
       </para></listitem>
     </varlistentry>
-    
+
     <varlistentry>
      <term>transform</term>
      <listitem><para>
@@ -162,7 +175,7 @@
        more information.
       </para></listitem>
     </varlistentry>
-    
+
     <varlistentry>
      <term>transliterate</term>
      <listitem><para>
@@ -172,7 +185,7 @@
        more information.
       </para></listitem>
     </varlistentry>
-    
+
     <varlistentry>
      <term>tokenize</term>
      <listitem><para>
@@ -193,7 +206,7 @@
 	  <para>Sentence. ICU: UBRK_SENTENCE.</para>
 	 </listitem>
 	</varlistentry>
-	
+
 	<varlistentry>
 	 <term>w</term>
 	 <listitem>
@@ -218,9 +231,19 @@
        </variablelist>
       </para></listitem>
     </varlistentry>
-    
+
+    <varlistentry>
+     <term>join</term>
+     <listitem>
+      <para>
+       Joins tokens into one string. The rule attribute is the joining
+       string, which may be empty. The join conversion element was added
+       in YAZ 4.2.49.
+      </para>
+     </listitem>
+    </varlistentry>
    </variablelist>
-   
+
   </para>
  </refsect1>
  <refsect1><title>EXAMPLES</title>
@@ -236,7 +259,7 @@
   <transform rule="[:Control:] Any-Remove"/>
   <tokenize rule="w"/>
   <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
-  <transliterate rule="xy -> z"/>
+  <transliterate rule="xy > z;"/>
   <display/>
   <casemap rule="l"/>
 </icu_chain>
@@ -262,15 +285,7 @@
 
 <!-- Keep this comment at the end of the file
 Local variables:
-mode: sgml
-sgml-omittag:t
-sgml-shorttag:t
-sgml-minimize-attributes:nil
-sgml-always-quote-attributes:t
-sgml-indent-step:1
-sgml-indent-data:t
-sgml-parent-document:nil
-sgml-local-catalogs: nil
-sgml-namecase-general:t
+mode: nxml
+nxml-child-indent: 1
 End:
 -->