-## $Id: Makefile.am,v 1.83 2007-07-10 09:42:46 adam Exp $
+## $Id: Makefile.am,v 1.84 2007-11-12 11:13:05 adam Exp $
SUBDIRS = common
MANFILES=yaz-client.1 yaz-ztest.8 \
yaz-config.8 yaz.7 zoomsh.1 yaz-asncomp.1 \
- yaz-marcdump.1 yaz-iconv.1 yaz-log.7 yaz-illclient.1
+ yaz-marcdump.1 yaz-iconv.1 yaz-log.7 \
+ yaz-illclient.1 yaz-icu.1
REFFILES=yaz-client-man.xml yaz-ztest-man.xml yaz-config-man.xml \
yaz-man.xml zoomsh-man.xml yaz-asncomp-man.xml \
yaz-marcdump-man.xml yaz-iconv-man.xml yaz-log-man.xml \
- yaz-illclient-man.xml
+ yaz-illclient-man.xml yaz-icu-man.xml
SUPPORTFILES=entities.ent apilayer.obj local.ent.in
yaz-log.7: yaz-log-man.xml
$(MAN_COMPILE) $(srcdir)/yaz-log-man.xml
+yaz-icu.1: yaz-icu-man.xml
+ $(MAN_COMPILE) $(srcdir)/yaz-icu-man.xml
+
$(HTMLFILES): $(XMLFILES)
rm -f *.html
$(HTML_COMPILE) $(srcdir)/yaz.xml
--- /dev/null
+<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN"
+ "http://www.oasis-open.org/docbook/xml/4.1/docbookx.dtd"
+[
+ <!ENTITY % local SYSTEM "local.ent">
+ %local;
+ <!ENTITY % entities SYSTEM "entities.ent">
+ %entities;
+ <!ENTITY % idcommon SYSTEM "common/common.ent">
+ %idcommon;
+]>
+<!-- $Id: yaz-icu-man.xml,v 1.1 2007-11-12 11:13:05 adam Exp $ -->
+<refentry id="zoomsh">
+ <refentryinfo>
+ <productname>YAZ</productname>
+ <productnumber>&version;</productnumber>
+ </refentryinfo>
+
+ <refmeta>
+ <refentrytitle>yaz-icu</refentrytitle>
+ <manvolnum>1</manvolnum>
+ </refmeta>
+
+ <refnamediv>
+ <refname>yaz-icu</refname>
+ <refpurpose>YAZ ICU utility</refpurpose>
+ </refnamediv>
+
+ <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>-x</arg>
+ </cmdsynopsis>
+ </refsynopsisdiv>
+
+ <refsect1><title>DESCRIPTION</title>
+ <para>
+ <command>yaz-icu</command> is utility which demonstrates
+ the ICU chain module of yaz. (<filename>yaz/icu.h</filename>).
+ </para>
+ </refsect1>
+
+ <refsect1><title>OPTIONS</title>
+ <variablelist>
+ <varlistentry>
+ <term>-c <replaceable>config</replaceable></term>
+ <listitem><para>
+ Specifies the file containing ICU chain configuration
+ which is XML based.
+ </para></listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>-p <replaceable>type</replaceable></term>
+ <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 locates are printed.
+ If <replaceable>type</replaceable> is <literal>t</literal>
+ available transliterators are printed.
+ </para></listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>-x <replaceable>config</replaceable></term>
+ <listitem><para>
+ Specifies that output should be XML based rather than
+ "text" based.
+ </para></listitem>
+ </varlistentry>
+
+ </variablelist>
+ </refsect1>
+ <refsect1><title>ICU chain configuration</title>
+ <para>
+ The ICU chain configuration speicifies one or more rules to convert
+ text data into tokens. The configuration format is XML based.
+ </para>
+ <para>
+ The toplevel element must be named <literal>icu_chain</literal>.
+ The <literal>icu_chain</literal> element has one required attribute
+ <literal>locale</literal> which specifies the ICU locale to be used
+ in the conversion steps.
+ </para>
+ <para>
+ The <literal>icu_chain</literal> element must include elements where
+ each element specifies a conversion step. The conversion is performed
+ in the order in which the conversion steps are specified.
+ Each conversion element takes one attribute: <literal>rule</literal>
+ which serves as argument to the conversion step.
+ </para>
+ <para>
+ The following conversion elements are available:
+
+ <variablelist>
+ <varlistentry>
+ <term>casemap</term>
+ <listitem><para>
+ Converts case and rule specifies how:
+
+ <variablelist>
+ <varlistentry>
+ <term>l</term>
+ <listitem>
+ <para>Lowercase using ICU function u_strToLower. </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>u</term>
+ <listitem>
+ <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>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>f</term>
+ <listitem>
+ <para>Fold case using ICU function u_strFoldCase.</para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
+ </para></listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>display</term>
+ <listitem><para>
+ This is a meta step which specifies that a term/token is to
+ be displayed. This term is retrieved in an application
+ using function icu_chain_token_display (<filename>yaz/icu.h</filename>).
+ </para></listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>transform</term>
+ <listitem><para>
+ Specifies an ICU transform rule. The rule attribute is the
+ custom transformation rule to be used. This is a text based format
+ which is offered by the ICU transform system. See
+ <ulink url="&url.icu.transform;">ICU Transforms</ulink> for
+ more information.
+ </para></listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>tokenize</term>
+ <listitem><para>
+ Breaks / tokenizes a string into components using
+ ICU functions ubrk_open, ubrk_setText, .. . The rule is
+ one of:
+ <variablelist>
+ <varlistentry>
+ <term>l</term>
+ <listitem>
+ <para>Line. ICU: UBRK_LINE.</para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>s</term>
+ <listitem>
+ <para>Sentence. ICU: UBRK_SENTENCE.</para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>w</term>
+ <listitem>
+ <para>Word. ICU: UBRK_WORD.</para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>c</term>
+ <listitem>
+ <para>Character. ICU: UBRK_CHARACTER.</para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>t</term>
+ <listitem>
+ <para>Title. ICU: UBRK_TITLE.</para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
+ </para></listitem>
+ </varlistentry>
+
+ </variablelist>
+
+ </para>
+ </refsect1>
+ <refsect1><title>EXAMPLES</title>
+ <para>
+ The following command analyzes text in file <filename>text</filename>
+ using ICU chain configuration <filename>chain.xml</filename>:
+ <screen>
+ cat text | yaz-icu -c chain.xml
+ </screen>
+ The chain.xml might look as follows:
+ <screen><![CDATA[
+<icu_chain locale="en">
+ <transform rule="[:Control:] Any-Remove"/>
+ <tokenize rule="w"/>
+ <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
+ <display/>
+ <casemap rule="l"/>
+</icu_chain>
+]]>
+ </screen>
+ </para>
+ </refsect1>
+ <refsect1><title>SEE ALSO</title>
+ <para>
+ <citerefentry>
+ <refentrytitle>yaz</refentrytitle>
+ <manvolnum>7</manvolnum>
+ </citerefentry>
+ </para>
+ <para>
+ <ulink url="&url.icu;">ICU Home</ulink>
+ </para>
+ <para>
+ <ulink url="&url.icu.transform;">ICU Transforms</ulink>
+ </para>
+ </refsect1>
+</refentry>
+
+<!-- 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
+End:
+-->
projects / yaz-moved-to-github.git / commitdiff