larvitgeodata/cldrData/common/transforms/Han-Spacedhan.xml

Geo data, primarily ISO territories, languages etc. Data fetched mostly from CLDR.

<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
<!--
Copyright © 1991-2013 Unicode, Inc.
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
For terms of use, see http://www.unicode.org/copyright.html
-->
<supplementalData>
  <version number="$Revision: 11914 $"/>
	<transforms>
		<transform source="Han" target="Spacedhan" direction="both" visibility="internal">
            <comment># Only intended for internal use</comment>
            <comment># Make sure Han are normalized, including characters that contain them. </comment>
            <comment># The first set in the filter is computed with http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:tonfkd:/XXX/:]-[:ideographic:]-[:sc=han:]</comment>
            <comment># Where XXX is the resolved [:ideographic:][:sc=han:]. It needs updating with each Unicode release!</comment>
			<tRule>:: [[㆒-㆟㈠-㉇㊀-㊰㋀-㋋㍘-㍰㍻-㍿㏠-㏾ 🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc; </tRule>			
            <tRule>:: fullwidth-halfwidth;</tRule>
			<tRule>｡ → '.';</tRule>
			<tRule>$terminalPunct = [\.\,\:\;\?\!．，：？！｡、；[:Pe:][:Pf:]];</tRule>
			<tRule>$initialPunct = [:Ps:][:Pi:];</tRule>
			<comment># add space between any Han or terminal punctuation and letters, and</comment>
			<comment># between letters and Han or initial punct</comment>
			<tRule>[[:Ideographic:] $terminalPunct] {} [:Letter:] → ' ' ;</tRule>
			<tRule>[:Letter:] [:Mark:]* {} [[:Ideographic:] $initialPunct] → ' ' ;</tRule>
			<comment># remove spacing between ideographs and other letters</comment>
			<tRule>← [:Ideographic:] { ' ' } [:Letter:] ;</tRule>
			<tRule>← [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ;</tRule>
		</transform>
	</transforms>
</supplementalData>