X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/374ca955a76ecab1204ca8bfa63ff9238d998416..b25be06635768807f8f693286fa73bb2297bb06c:/icuSources/data/translit/Hebrew_Latin.txt diff --git a/icuSources/data/translit/Hebrew_Latin.txt b/icuSources/data/translit/Hebrew_Latin.txt index 4e0635cc..bef7bc5a 100644 --- a/icuSources/data/translit/Hebrew_Latin.txt +++ b/icuSources/data/translit/Hebrew_Latin.txt @@ -1,109 +1,73 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Transliteration table for Hebrew -# Based on the UNGEGN table at: -# http://www.eki.ee/wgrs/rom1_he.pdf +# *************************************************************************** +# * +# * Copyright (C) 2004-2010, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Hebrew_Latin.txt +# Generated from CLDR # -# 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:] [:^ccc=0:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF] - [\u05BD]] ; +:: [[:Hebrew:] [:^ccc=0:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2ℵ-ℸ\u0304\u05BF] - [\u05BD]] ; :: 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 +ח ↔ h\u0331 ; +צ ↔ z\u0331 } $letterAfter; +ץ ↔ z\u0331 ; +ש ↔ s\u0327 ; +ת ↔ t\u0327 ; +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 +\u05BC ↔ \u0307 ; # dagesh just goes to overdot for now +\u05C1 ↔ \u030C ; # shin dot -→ sh +\u05C2 ↔ \u0302 ; # sin dot -→ s $above = [^[:ccc=0:][:ccc=230:]]*; - -‎ֲ‎ > à ; -‎ֲ‎ $1< a ($above) ̀; - -‎ָ‎ > á ; -‎ָ‎ $1 < a ($above) ́; - -‎ֱ‎ > è ; -‎ֱ‎ $1 < e ($above) ̀; - -‎ֵ‎ > é ; -‎ֵ‎ $1 < e ($above) ́; - -‎ְ‎ > e ̆ ; -‎ְ‎ $1 < e ($above) ̆; - -‎ֹ‎ > ò ; -‎ֹ‎ $1 < o ($above) ̀; - -ִ <> i ; -ֻ <> u ; -ַ <> a ; -ֶ <> e ; -ֳ <> o ; - -\u05BF <> ̄ ; - -# fallbacks -ק < c ; -פ < f } $letterAfter; -ף < f ; -ז < j ; -ו < v ; -כס < x ; - +‎\u05B2‎ → à ; +‎\u05B2‎ $1← a ($above) \u0300; +‎\u05B8‎ → á ; +‎\u05B8‎ $1 ← a ($above) \u0301; +‎\u05B1‎ → è ; +‎\u05B1‎ $1 ← e ($above) \u0300; +‎\u05B5‎ → é ; +‎\u05B5‎ $1 ← e ($above) \u0301; +‎\u05B0‎ → e \u0306 ; +‎\u05B0‎ $1 ← e ($above) \u0306; +‎\u05B9‎ → ò ; +‎\u05B9‎ $1 ← o ($above) \u0300; +\u05B4 ↔ i ; +\u05BB ↔ u ; +\u05B7 ↔ a ; +\u05B6 ↔ e ; +\u05B3 ↔ o ; +\u05BF ↔ \u0304 ; +ק ← c ; +פ ← f } $letterAfter; +ף ← f ; +ז ← j ; +ו ← v ; +כס ← x ; :: (lower); :: nfc (nfd) ; -:: ([[:Latin:] [:^ccc=0:] [\u02BB-\u02BC\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 ̄ ]]); \ No newline at end of file +:: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 \u0304 ]]);