larvitgeodata/cldrData/common/segments/ja.xml

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

<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.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
-->
<ldml>
	<identity>
		<version number="$Revision: 11914 $"/>
		<language type="ja"/>
	</identity>
	<segmentations>
		<segmentation type="LineBreak">
			<variables>
				<variable id="$ID">[[\p{Line_Break=Ideographic}] [$CJ]]</variable>
				<variable id="$NS">\p{Line_Break=Nonstarter}</variable>
			</variables>
		</segmentation>
		<segmentation type="WordBreak">
			<variables>
				<variable id="$Hiragana">\p{Hiragana}</variable>
				<variable id="$Hiragana">($Hiragana $X)</variable>
				<variable id="$Ideographic">[[\p{Ideographic}] [\u3005 \u3007 \u303B]]</variable>
				<variable id="$Ideographic">($Ideographic $X)</variable>
			</variables>
			<segmentRules>
				<rule id="13.05"> $Hiragana × $Hiragana </rule>
				<rule id="13.06"> $Ideographic × $Ideographic </rule>
			</segmentRules>
		</segmentation>
	</segmentations>
</ldml>