common/transforms/Han-Spacedhan.xml

<?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="$Revision$"/>
	<transforms>
		<transform source="Han" target="Spacedhan" direction="both" visibility="internal">
			<tRule>
# Only intended for internal use
# Make sure Han are normalized, including characters that contain them.
# The first set in the filter is computed with http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:tonfkd:/XXX/:]-[:ideographic:]-[:sc=han:]
# Where XXX is the resolved [:ideographic:][:sc=han:]. It needs updating with each Unicode release!
:: [[、。々《-』〜・㆒-㆟㈠-㉇㊀-㊰㋀-㋋ ㍘-㍰㍻-㍿㏠-㏾🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc;
:: fullwidth-halfwidth;
｡ → '.';
。→ '.';
、→ ',';
､→ ',';
《→ '«';
》→ '»';
〈 → '‹';
 〉→ '›';
「→ '‘';
」→ '’';
｢→ '‘';
｣→ '’';
『→ '“';
』→ '”';

・→ '‧';
･ → '‧';
々→ '⓶';
〜→ '~';

$terminalPunct = [\.\,\:\;\?\!．，：？！｡、；[:Pe:][:Pf:]];
$initialPunct = [:Ps:][:Pi:];
# add space between any Han or terminal punctuation and letters, and
# between letters and Han or initial punct
[[:Ideographic:] $terminalPunct] {} [:Letter:] → ' ' ;
[:Letter:] [:Mark:]* {} [[:Ideographic:] $initialPunct] → ' ' ;
# remove spacing between ideographs and other letters
← [:Ideographic:] { ' ' } [:Letter:] ;
← [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ;
			</tRule>
		</transform>
	</transforms>
</supplementalData>