From 0ebf5bdf043a27fd3dfb7f92e0cb63d88954c44d Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Fri, 19 Apr 2024 03:47:29 +0200 Subject: Adding upstream version 115.8.0esr. Signed-off-by: Daniel Baumann --- intl/icu/source/data/translit/Hebr_Latn.txt | 98 +++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) create mode 100644 intl/icu/source/data/translit/Hebr_Latn.txt (limited to 'intl/icu/source/data/translit/Hebr_Latn.txt') diff --git a/intl/icu/source/data/translit/Hebr_Latn.txt b/intl/icu/source/data/translit/Hebr_Latn.txt new file mode 100644 index 0000000000..b2c2286bd3 --- /dev/null +++ b/intl/icu/source/data/translit/Hebr_Latn.txt @@ -0,0 +1,98 @@ +# © 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html +# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml +# +# File: Hebr_Latn.txt +# Generated from CLDR +# + +# 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://www.ibm.com/software/globalization/icu/demo/transform +# 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://icu.sourceforge.net/userguide/Transform.html +:: [[־׳״][: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 ↔ 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 } $letterAfter; +ף ↔ p ; +ק ↔ q ; +ר ↔ r ; +װ → | וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV +ױ → | וי; # HEBREW LIGATURE YIDDISH VAV YOD +ײ → | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD +\u05BC ↔ \u0307 ; # dagesh just goes to overdot for now +\u05C1 ↔ \u030C ; # shin dot -→ sh +\u05C2 ↔ \u0302 ; # sin dot -→ s +# points +$above = [^[:ccc=0:][:ccc=230:]]*; +‎\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 ; +# fallbacks +ק ← c ; +פ ← f } $letterAfter; +ף ← f ; +ז ← j ; +ו ← v ; +כס ← x ; +:: (lower); +:: nfc (nfd) ; +:: ([[-′″][:Latin:] [:^ccc=0:] [ʻ-ʼ\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 \u0304 ]]); + -- cgit v1.2.3