scuffed-code/icu4c/source/data/translit/t_Hebr_Latn.txt
2002-07-27 18:10:15 +00:00

113 lines
2.7 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2002, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpicurules.bat
// Source: ../../../impl/data/Transliterator_Hebrew_Latin.txt
// Date: Sat Jul 27 10:31:07 2002
//--------------------------------------------------------------------
// Hebrew_Latin
t_Hebr_Latn {
Rule {
//--------------------------------------------------------------------
//--------------------------------------------------------------------
//--------------------------------------------------------------------
// Transliteration table for Hebrew
// Based on the UNGEGN table at:
// http://www.eki.ee/wgrs/rom1_he.pdf
//
// Exceptions:
// - Accents are added to disambiguate letters
// - Combinations of dagesh, shin/sin dot that produce different
// letters are not yet encoded.
//
// To test, open:
// http://oss.software.ibm.com/cgi-bin/icu/tr
// Click Edit, paste in this file, Save As hebrew-latin/XXX
// (where XXX is a username)
// Now go back to the main window, and try it out.
// Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2
// Paste in hebrew text in Input, and hit Transliterate.
//
// For more information, see"
// http://oss.software.ibm.com/icu/userguide/Transliteration.html
":: [[:Hebrew:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF]] ;"
":: nfkd (nfc) ;"
"$letterAfter = [:M:]* [:L:] ;"
// move longer items here to avoid masking
"ח <> ẖ ;"
"צ <> ẕ } $letterAfter;"
"ץ <> ẕ ;"
"ש <> ş ;"
"ת <> ţ ;"
"א <> ʼ ;"
"ב <> b ;"
"ג <> g ;"
"ד <> d ;"
"ה <> h ;"
"ו <> w ;"
"ז <> z ;"
"ט <> t ;"
"י <> y ;"
"כ <> k } $letterAfter;"
"ך <> k ;"
"ל <> l ;"
"מ <> m } $letterAfter;"
"ם <> m ;"
"נ <> n } $letterAfter;"
"ן <> n ;"
"ס <> s ;"
"ע <> ʻ ;"
"פ <> p } $letterAfter;"
"ף <> p ;"
"ק <> q ;"
"ר <> r ;"
"װ > | וו;" // HEBREW LIGATURE YIDDISH DOUBLE VAV
"ױ > | וי;" // HEBREW LIGATURE YIDDISH VAV YOD
"ײ > | יי ;" // HEBREW LIGATURE YIDDISH DOUBLE YOD
"ּ <> ̇ ;" // dagesh just goes to overdot for now
"ׁ <> ̌ ;" // shin dot -> sh
"ׂ <> ̂ ;" // sin dot -> s
// points
"ֲ <> à ;"
"ָ <> á ;"
"ֱ <> è ;"
"ֵ <> é ;"
"ְ <> ê ;"
"ִ <> i ;"
"ֹ <> ò ;"
"ֻ <> u ;"
"ַ <> a ;"
"ֶ <> e ;"
"ֳ <> o ;"
"\u05BF <> ̄ ;"
// fallbacks
"ק < c ;"
"פ < f } $letterAfter;"
"ף < f ;"
"ז < j ;"
"ו < v ;"
"כס < x ;"
":: (lower);"
":: nfc (nfd) ;"
":: ([[:Latin:] [\u02BB-\u02BC\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 ̄ ]]);"
}
}