larvitgeodata
Version:
Geo data, primarily ISO territories, languages etc. Data fetched mostly from CLDR.
102 lines (100 loc) • 4.25 kB
text/xml
<!--
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 $"/>
<transforms>
<transform source="Hebrew" target="Latin" direction="both">
<comment># Transliteration table for Hebrew</comment>
<comment># Based on the UNGEGN table at:</comment>
<comment># http://www.eki.ee/wgrs/rom1_he.pdf</comment>
<comment>#</comment>
<comment># Exceptions:</comment>
<comment># - Accents are added to disambiguate letters</comment>
<comment># - Combinations of dagesh, shin/sin dot that produce different</comment>
<comment># letters are not yet encoded.</comment>
<comment>#</comment>
<comment># To test, open:</comment>
<comment># http://www.ibm.com/software/globalization/icu/demo/transform</comment>
<comment># Click Edit, paste in this file, Save As hebrew-latin/XXX</comment>
<comment># (where XXX is a username)</comment>
<comment># Now go back to the main window, and try it out.</comment>
<comment># Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2</comment>
<comment># Paste in hebrew text in Input, and hit Transliterate.</comment>
<comment>#</comment>
<comment># For more information, see"</comment>
<comment># http://icu.sourceforge.net/userguide/Transform.html</comment>
<tRule>:: [[:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;</tRule>
<tRule>:: nfkd (nfc) ;</tRule>
<tRule>$letterAfter = [:M:]* [:L:] ;</tRule>
<comment># move longer items here to avoid masking</comment>
<tRule>ח ↔ ẖ ;</tRule>
<tRule>צ ↔ ẕ } $letterAfter;</tRule>
<tRule>ץ ↔ ẕ ;</tRule>
<tRule>ש ↔ ş ;</tRule>
<tRule>ת ↔ ţ ;</tRule>
<tRule>א ↔ ʼ ;</tRule>
<tRule>ב ↔ b ;</tRule>
<tRule>ג ↔ g ;</tRule>
<tRule>ד ↔ d ;</tRule>
<tRule>ה ↔ h ;</tRule>
<tRule>ו ↔ w ;</tRule>
<tRule>ז ↔ z ;</tRule>
<tRule>ט ↔ t ;</tRule>
<tRule>י ↔ y ;</tRule>
<tRule>כ ↔ k } $letterAfter;</tRule>
<tRule>ך ↔ k ;</tRule>
<tRule>ל ↔ l ;</tRule>
<tRule>מ ↔ m } $letterAfter;</tRule>
<tRule>ם ↔ m ;</tRule>
<tRule>נ ↔ n } $letterAfter;</tRule>
<tRule>ן ↔ n ;</tRule>
<tRule>ס ↔ s ;</tRule>
<tRule>ע ↔ ʻ ;</tRule>
<tRule>פ ↔ p } $letterAfter;</tRule>
<tRule>ף ↔ p ;</tRule>
<tRule>ק ↔ q ;</tRule>
<tRule>ר ↔ r ;</tRule>
<tRule>װ → | וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV</tRule>
<tRule>ױ → | וי; # HEBREW LIGATURE YIDDISH VAV YOD</tRule>
<tRule>ײ → | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD</tRule>
<tRule>ּ ↔ ̇ ; # dagesh just goes to overdot for now</tRule>
<tRule>ׁ ↔ ̌ ; # shin dot -→ sh</tRule>
<tRule>ׂ ↔ ̂ ; # sin dot -→ s</tRule>
<comment># points</comment>
<tRule>$above = [^[:ccc=0:][:ccc=230:]]*;</tRule>
<tRule>ֲ → à ;</tRule>
<tRule>ֲ $1← a ($above) ̀;</tRule>
<tRule>ָ → á ;</tRule>
<tRule>ָ $1 ← a ($above) ́;</tRule>
<tRule>ֱ → è ;</tRule>
<tRule>ֱ $1 ← e ($above) ̀;</tRule>
<tRule>ֵ → é ;</tRule>
<tRule>ֵ $1 ← e ($above) ́;</tRule>
<tRule>ְ → e ̆ ;</tRule>
<tRule>ְ $1 ← e ($above) ̆;</tRule>
<tRule>ֹ → ò ;</tRule>
<tRule>ֹ $1 ← o ($above) ̀;</tRule>
<tRule>ִ ↔ i ;</tRule>
<tRule>ֻ ↔ u ;</tRule>
<tRule>ַ ↔ a ;</tRule>
<tRule>ֶ ↔ e ;</tRule>
<tRule>ֳ ↔ o ;</tRule>
<tRule>ֿ ↔ ̄ ;</tRule>
<comment># fallbacks</comment>
<tRule>ק ← c ;</tRule>
<tRule>פ ← f } $letterAfter;</tRule>
<tRule>ף ← f ;</tRule>
<tRule>ז ← j ;</tRule>
<tRule>ו ← v ;</tRule>
<tRule>כס ← x ;</tRule>
<tRule>:: (lower);</tRule>
<tRule>:: nfc (nfd) ;</tRule>
<tRule>:: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́ ̄ ]]);</tRule>
</transform>
</transforms>
</supplementalData>