You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
<!--
Copyright © 1991 - 2018 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= "$Revision$" />
<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 $FE*)</variable>
<variable id= "$Ideographic" > [[\p{Ideographic}] [\u3005 \u3007 \u303B]]</variable>
<variable id= "$Ideographic" > ($Ideographic $FE*)</variable>
</variables>
<segmentRules >
<rule id= "13.3" > $Hiragana × </rule>
<rule id= "13.4" > $Ideographic × </rule>
</segmentRules>
</segmentation>
</segmentations>
</ldml>
