diff --git a/.gitattributes b/.gitattributes index 6ef88ba3d61..226facd6720 100644 --- a/.gitattributes +++ b/.gitattributes @@ -105,16 +105,10 @@ icu4j/src/com/ibm/text/resources/Transliterator_Kanji_English.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Kanji_OnRomaji.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Kannada_InterIndic.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_KeyboardEscape_Latin1.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_Latin_Arabic.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_Latin_Cyrillic.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Latin_Devanagari.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_Latin_Greek.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_Latin_Hebrew.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Latin_Jamo.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_Latin_Kana.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Malayalam_InterIndic.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Oriya_InterIndic.utf8.txt -text -icu4j/src/com/ibm/text/resources/Transliterator_StraightQuotes_CurlyQuotes.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Tamil_InterIndic.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_Telugu_InterIndic.utf8.txt -text icu4j/src/com/ibm/text/resources/Transliterator_UnicodeName_UnicodeChar.utf8.txt -text diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Arabic.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Arabic.utf8.txt deleted file mode 100755 index edbc72cc01a..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Arabic.utf8.txt +++ /dev/null @@ -1,189 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 2001 -#-------------------------------------------------------------------- - -# To Do: finish adding shadda, add sokoon -# [Is this done? Can someone finish this?] - -### $alefmadda=آ; -### $alefuhamza=أ; -### $wauuhamza=ؤ; -### $alefhamza=إ; -### $yehuhamza=ئ; -### $alef=ا; -### $beh=ب; -### $tehmarbuta=ة; -### $teh=ت; -### $theh=ث; -### $geem=ج; -### $hah=ح; -### $kha=خ; -### $dal=د; -### $dhal=ذ; -### $reh=ر; -### $zain=ز; -### $seen=س; -### $sheen=ش; -### $sad=ص; -### $dad=ض; -### $tah=ط; -### $zah=ظ; -### $ein=ع; -### $ghein=غ; -### $feh=ف; -### $qaaf=ق; -### $kaf=ك; -### $lam=ل; -### $meem=م; -### $noon=ن; -### $heh=ه; -### $wau=و; -### $yehmaqsura=ى; -### $yeh=ي; -### $peh=ڤ; - -### $hamza=ء; -### $fathatein=ً; -### $dammatein=ٌ; -### $kasratein=ٍ; -### $fatha=َ; -### $damma=ُ; -### $kasra=ِ; -### $shadda=ّ; -### $sokoon=ْ; - -# Doubles - liu -t'' < {ت} [تثةط]; -h'' < {ه} [هح]; -s'' < {س} ش; - -# A few pathological special cases to make round -# trip work. - liu -d'~'d <> د د; -dh'~'dh <> ذ ذ; -dd'~'dd <> ض ض; - -# Shadda: Map x ّ to x x, where x is dh, dd, or -# d (that is, ذ, ض, or د). If x is d, d'd is -# output. Net effect is to map s.th. like ض ّ -# to dd'dd. - liu -ذ {dh} <> dh {ّ}; -ض {dd} <> dd {ّ}; -د {''d} [^dh] <> d {ّ}; # Avoid d'dd or d'dh - -# [This should be removed, but it's good for demos] -Arabic> \ -تتمتع' ' \ -اللغة' ' \ -العرببية' ' \ -ببنظم' ' \ -كتاببية' ' \ -جميلة; - -# Main rules -''aiآ; -''aeأ; -''aoإ; -''aaا; -''anً; -''aَ; -b<>ب; -''dhذ; -''ddض; -''dد; -''eع; -f<>ف; -gh<>غ; -''hhح; -''hه; -''iiٍ; -''iِ; -j<>ج; -kh<>خ; -k<>ك; -l<>ل; -''mم; -n<>ن; -''oء; -p<>ڤ; -q<>ق; -r<>ر; -sh<>ش; -''ssص; -''sس; -th<>ث; -tm<>ة; -''ttط; -''tت; -''uuٌ; -''uُ; -we<>ؤ; -w<>و; -ye<>ئ; -ym<>ى; -''yي; -''zzظ; -''zز; - -# One-way Latin-Arabic compatability rules -c>ك; -g>ج; -x>كّس; -v>ب; - -# Digits -0<>٠; # Arabic digit 0 -1<>١; # Arabic digit 1 -2<>٢; # Arabic digit 2 -3<>٣; # Arabic digit 3 -4<>٤; # Arabic digit 4 -5<>٥; # Arabic digit 5 -6<>٦; # Arabic digit 6 -7<>٧; # Arabic digit 7 -8<>٨; # Arabic digit 8 -9<>٩; # Arabic digit 9 -'%'<>٪; # Arabic % -'.'<>٫; # Arabic decimal separator -','<>٬; # Arabic thousands separator -'*'<>٭; # Arabic five-pointed star - -''>; - -# eof diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Cyrillic.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Cyrillic.utf8.txt deleted file mode 100755 index 8899d95dd6b..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Cyrillic.utf8.txt +++ /dev/null @@ -1,305 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 12:42:05 2001 -#-------------------------------------------------------------------- - -# Latin-Cyrillic - - -# These rules provide general Latin-Cyrillic -# transliteration. The standard Russian transliterations -# are generally used for the letters from Russian, -# with additional Cyrillic characters given consistent -# mappings. - -### $S_hacek=Š; -### $s_hacek=š; - -### $YO=Ё; -### $J=Ј; -### $A=А; -### $B=Б; -### $V=В; -### $G=Г; -### $D=Д; -### $YE=Е; -### $ZH=Ж; -### $Z=З; -### $YI=И; -### $Y=Й; -### $K=К; -### $L=Л; -### $M=М; -### $N=Н; -### $O=О; -### $P=П; -### $R=Р; -### $S=С; -### $T=Т; -### $U=У; -### $F=Ф; -### $KH=Х; -### $TS=Ц; -### $CH=Ч; -### $SH=Ш; -### $SHCH=Щ; -### $HARD=Ъ; -### $I=Ы; -### $SOFT=Ь; -### $E=Э; -### $YU=Ю; -### $YA=Я; - -# Lowercase - -### $a=а; -### $b=б; -### $v=в; -### $g=г; -### $d=д; -### $ye=е; -### $zh=ж; -### $z=з; -### $yi=и; -### $y=й; -### $k=к; -### $l=л; -### $m=м; -### $n=н; -### $o=о; -### $p=п; -### $r=р; -### $s=с; -### $t=т; -### $u=у; -### $f=ф; -### $kh=х; -### $ts=ц; -### $ch=ч; -### $sh=ш; -### $shch=щ; -### $hard=ъ; -### $i=ы; -### $soft=ь; -### $e=э; -### $yu=ю; -### $ya=я; - -### $yo=ё; -### $j=ј; - -# variables -# some are duplicated so lowercasing works - -$csoft=[eiyEIY]; -$CSOFT=[eiyEIY]; - -$BECOMES_H=[Ъъ]; -$becomes_h=[Ъъ]; - -$BECOMES_S=[Сс]; -$becomes_s=[Сс]; - -$BECOMES_C=[Чч]; -$becomes_c=[Чч]; - -$BECOMES_VOWEL=[АЭЫОУаэыоу]; -$becomes_vowel=[АЭЫОУаэыоу]; - -$letter=[[:Lu:][:Ll:]]; -$lower=[[:Ll:]]; - -# Modified to combine display transliterator and typing transliterator. -# The display mapping uses accents for the "soft" vowels. -# It does not, although it could, use characters like š instead of digraphs -# like sh. - -# ############################################# -# Special titlecase forms, not duplicated -# ############################################# - -Sh''ch<>Шч; # LIU Distinguish Шч from Щ - -Ch <> {Ч} $lower; -Kh <> {Х} $lower; -Shch <> {Щ}$lower; -Sh <> {Ш} $lower; -Ts <> {Ц} $lower; -Zh <> {Ж} $lower; -Yi>И; -Ye>Е; -Yo>Ё; -Yu>Ю; -Ya>Я; - -# ############################################# -# Rules to Duplicate -# To get the lowercase versions, copy these and lowercase -# ############################################# - -# variant spellings in English - -SHTCH>Щ; -TCH>Ч; -TH>З; -Q>К; -WH>В; -W>В; -X>КС; #+ "X<КС;" - -# Separate letters that would otherwise join - -SH''<Ш}$BECOMES_C; -T''<Т}$BECOMES_S; -T''<Т}[ЧЩщ]; # LIU add special cases - -K''<К}$BECOMES_H; -S''<С}$BECOMES_H; -T''<Т}$BECOMES_H; -Z''<З}$BECOMES_H; - -Y''<Й}$BECOMES_VOWEL; - -# Main letters - -A<>А; -B<>Б; -CH<>Ч; -D<>Д; -E<>Э; -F<>Ф; -G<>Г; -Ì<>И; -I<>Ы; -KH<>Х; -K<>К; -L<>Л; -M<>М; -N<>Н; -O<>О; -P<>П; -R<>Р; -SHCH<>Щ; -SH>Ш; #+ "SH<Ш;" -Š<>Ш; -S<>С; -TS<>Ц; -T<>Т; -U<>У; -V<>В; -#ÌÀÈÒÙ -YE>Е; #+ "YE<Е;" -È<>Е; -YO>Ё; #+ "YO<Ё;" -Ò<>Ё; -YU>Ю; #+ "YU<Ю;" -Ù<>Ю; -YA>Я; #+ "YA<Я;" -À<>Я; -Y<>Й; -ZH<>Ж; -Z<>З; - -H<>Ъ; -Ÿ<>Ь; - -# Non-russian - -J<>Ј; - -# variant spellings in English - -C}$csoft>С; -C>К; - -# ############################################# -# Duplicated Rules -# Copy and lowercase the above rules -# ############################################# - -# variant spellings in english - -shtch>щ; -tch>ч; -th>з; -q>к; -wh>в; -w>в; -x>кс; #+ "x<кс;" - -# separate letters that would otherwise join - -sh''<ш}$becomes_c; -t''<т}$becomes_s; -t''<т}[чщ]; # LIU add special cases - -k''<к}$becomes_h; -s''<с}$becomes_h; -t''<т}$becomes_h; -z''<з}$becomes_h; - -y''<й}$becomes_vowel; - -# main letters - -a<>а; -b<>б; -ch<>ч; -d<>д; -e<>э; -f<>ф; -g<>г; -ì<>и; -i<>ы; -kh<>х; -k<>к; -l<>л; -m<>м; -n<>н; -o<>о; -p<>п; -r<>р; -shch<>щ; -sh>ш; #+ "sh<ш;" -š<>ш; -s<>с; -ts<>ц; -t<>т; -u<>у; -v<>в; -#ìàèòù -ye>е; #+ "ye<е;" -è<>е; -yo>ё; #+ "yo<ё;" -ò<>ё; -yu>ю; #+ "yu<ю;" -ù<>ю; -ya>я; #+ "ya<я;" -à<>я; -y<>й; -zh<>ж; -z<>з; - -h<>ъ; -ÿ<>ь; - -# non-russian - -j<>ј; - -# variant spellings in english - -c}$csoft>с; -c>к; - - -# ############################################# -# End of Duplicated Rules -# ############################################# - -#generally the last rule -''>; - -# eof diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Greek.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Greek.utf8.txt deleted file mode 100755 index 31a6a01db2f..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Greek.utf8.txt +++ /dev/null @@ -1,375 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 12:18:45 2001 -#-------------------------------------------------------------------- - -# Latin-Greek - -# ============================================== -# Modern Greek Transliteration Rules -# -# This transliterates modern Greek characters, but using rules -# that are traditional for Ancient Greek, and -# thus more resemble Greek words that have become part -# of English. It differs from the official Greek -# transliteration, which is more phonetic (since -# most modern Greek vowels, for example, have -# degenerated simply to sound like "ee"). -# -# There are only a few tricky parts. -# 1. eta and omega don't map directly to Latin vowels, -# so we use a macron on e and o, and some -# other combinations if they are accented. -# 2. The accented, diaeresis i and y are substituted too. -# 3. Some letters use digraphs, like "ph". While typical, -# they need some special handling. -# 4. A gamma before a gamma or a few other letters is -# transliterated as an "n", as in "Anglo" -# 5. An ypsilon after a vowel is a "u", as in -# "Mouseio". Otherwise it is a "y" as in "Physikon" -# 6. The construction of the rules is made simpler by making sure -# that most rules for lowercase letters exactly correspond to the -# rules for uppercase letters, *except* for the case of the letters -# in the rule itself. That way, after modifying the uppercase rules, -# you can just copy, paste, and "set to lowercase" to get -# the rules for lowercase letters! -# ============================================== - -# ============================================== -# Variables, used to make the rules more comprehensible -# and for conditionals. -# ============================================== - -### $quote='\"'; - -# Latin Letters - -### $E_MACRON=Ē; -### $e_macron=ē; -### $O_MACRON=Ō; -### $o_macron=ō; -### $Y_UMLAUT=Ÿ; -### $y_umlaut=ÿ; - -#! // with real accents. -#! + "$E_MACRON_ACUTE=Ḗ;" -#! + "$e_macron_acute=ḗ;" -#! + "$O_MACRON_ACUTE=Ṓ;" -#! + "$o_macron_acute=ṓ;" -#! + "$y_umlaut_acute=ÿ́;" -#! + "$u00ef_acute=ḯ;" -#! + "$u00fc_acute=ǘ;" -#! // - -# single letter equivalents - -### $E_MACRON_ACUTE=Ê; -### $e_macron_acute=ê; -### $O_MACRON_ACUTE=Ô; -### $o_macron_acute=ô; -### $y_umlaut_acute=ŷ; -### $u00ef_acute=î; -### $u00fc_acute=û; - -# Greek Letters - -### $ALPHA=Α; -### $BETA=Β; -### $GAMMA=Γ; -### $DELTA=Δ; -### $EPSILON=Ε; -### $ZETA=Ζ; -### $ETA=Η; -### $THETA=Θ; -### $IOTA=Ι; -### $KAPPA=Κ; -### $LAMBDA=Λ; -### $MU=Μ; -### $NU=Ν; -### $XI=Ξ; -### $OMICRON=Ο; -### $PI=Π; -### $RHO=Ρ; -### $SIGMA=Σ; -### $TAU=Τ; -### $YPSILON=Υ; -### $PHI=Φ; -### $CHI=Χ; -### $PSI=Ψ; -### $OMEGA=Ω; - -### $ALPHA2=Ά; -### $EPSILON2=Έ; -### $ETA2=Ή; -### $IOTA2=Ί; -### $OMICRON2=Ό; -### $YPSILON2=Ύ; -### $OMEGA2=Ώ; -### $IOTA_DIAERESIS=Ϊ; -### $YPSILON_DIAERESIS=Ϋ; - -### $alpha=α; -### $beta=β; -### $gamma=γ; -### $delta=δ; -### $epsilon=ε; -### $zeta=ζ; -### $eta=η; -### $theta=θ; -### $iota=ι; -### $kappa=κ; -### $lambda=λ; -### $mu=μ; -### $nu=ν; -### $xi=ξ; -### $omicron=ο; -### $pi=π; -### $rho=ρ; -### $sigma=σ; -### $tau=τ; -### $ypsilon=υ; -### $phi=φ; -### $chi=χ; -### $psi=ψ; -### $omega=ω; - -#forms - -### $alpha2=ά; -### $epsilon2=έ; -### $eta2=ή; -### $iota2=ί; -### $omicron2=ό; -### $ypsilon2=ύ; -### $omega2=ώ; -### $iota_diaeresis=ϊ; -### $ypsilon_diaeresis=ϋ; -### $iota_diaeresis2=ΐ; -### $ypsilon_diaeresis2=ΰ; -### $sigma2=ς; - -# Variables for conditional mappings - -# Use lowercase for all variable names, to allow cut/paste below. - -$letter=[~[:Lu:][:Ll:]]; -$lower=[[:Ll:]]; -$softener=[eiyEIY]; -$vowel=[aeiouAEIOU \ - ΑΕΗΙΟΥΩ \ - ΆΈΉΊΌΎΏ \ - ΪΫ \ - αεηιουω \ - άέήίόύώ \ - ϊϋ \ - ΐΰ \ - ]; -$n_gamma=[GKXCgkxc]; -$gamma_n=[ΓΚΧΞγκχξ]; -$pp=[Pp]; - -# ============================================== -# Rules -# ============================================== -# The following are special titlecases, and should -# not be copied when duplicating the lowercase -# ============================================== - -Th <> Θ}$lower; -Ph <> Φ}$lower; -Ch <> Χ}$lower; -#masked: + "Ps<Φ}$lower;" - -# Because there is no uppercase forms for final sigma, -# we had to move all the sigma rules up here. - -# Remember to insert ' to preserve round trip, for double letters -# don't need to do this for the digraphs with h, -# since it is not created when mapping back from greek - -# use special form for s - -''S <> $pp{Σ; # handle PS -S <> Σ; - -# The following are a bit tricky. 's' takes two forms in greek -# final or non final. -# We use ~s to represent the abnormal form: final before letter -# or non-final before non-letter. -# We use 's to separate p and s (otherwise ps is one letter) -# so, we break out the following forms: - -''s < $pp{σ}$letter; -s < σ}$letter; -'~'s < σ; - -'~'s < ς}$letter; -''s < $pp{ς; -s < ς; - -'~'s }$letter>ς; -'~'s > σ; -''s }$letter>σ; -''s > ς; -s }$letter>σ; -s > ς; - -# because there are no uppercase forms, had to move these up too. - -i'\"''`'>ΐ; -y'\"''`'>ΰ; - -î<>ΐ; -û<>$vowel{ΰ; -ŷ<>ΰ; - -# ============================================== -# Uppercase Forms. -# To make lowercase forms, just copy and lowercase below -# ============================================== - -# Typing variants, in case the keyboard doesn't have accents - -'A`'>Ά; -'E`'>Έ; -'EE`'>Ή; -EE>Η; -'I`'>Ί; -'O`'>Ό; -'OO`'>Ώ; -OO>Ω; -I'\"'>Ϊ; -Y'\"'>Ϋ; - -# Basic Letters - -A<>Α; -Á<>Ά; -B<>Β; -N }$n_gamma<>Γ}$gamma_n; -G<>Γ; -D<>Δ; -''E <> [Ee]{Ε; # handle EE -E<>Ε; -É<>Έ; -Z<>Ζ; -Ê<>Ή; -Ē<>Η; -TH<>Θ; -I<>Ι; -Í<>Ί; -Ï<>Ϊ; -K<>Κ; -L<>Λ; -M<>Μ; -N'' <> Ν}$gamma_n; -N<>Ν; -X<>Ξ; -''O <> [Oo]{ Ο; # handle OO -O<>Ο; -Ó<>Ό; -PH<>Φ; # needs ordering before P -PS<>Ψ; # needs ordering before P -P<>Π; -R<>Ρ; -T<>Τ; -U <> $vowel{Υ; -Ú <> $vowel{Ύ; -Ü <> $vowel{Ϋ; -Y<>Υ; -Ý<>Ύ; -Ÿ<>Ϋ; -CH<>Χ; -Ô<>Ώ; -Ō<>Ω; - -# Extra English Letters. Mapped for completeness - -C}$softener>|S; -C>|K; -F>|PH; -H>|CH; -J>|I; -Q>|K; -V>|U; -W>|U; - -# ============================================== -# Lowercase Forms. Just copy above and lowercase -# ============================================== - -# typing variants, in case the keyboard doesn't have accents - -'a`'>ά; -'e`'>έ; -'ee`'>ή; -ee>η; -'i`'>ί; -'o`'>ό; -'oo`'>ώ; -oo>ω; -i'\"'>ϊ; -y'\"'>ϋ; - -# basic letters - -a<>α; -á<>ά; -b<>β; -n }$n_gamma<>γ}$gamma_n; -g<>γ; -d<>δ; -''e <> [Ee]{ε; # handle EE -e<>ε; -é<>έ; -z<>ζ; -ê<>ή; -ē<>η; -th<>θ; -i<>ι; -í<>ί; -ï<>ϊ; -k<>κ; -l<>λ; -m<>μ; -n'' <> ν}$gamma_n; -n<>ν; -x<>ξ; -''o <> [Oo]{ ο; # handle OO -o<>ο; -ó<>ό; -ph<>φ; # needs ordering before p -ps<>ψ; # needs ordering before p -p<>π; -r<>ρ; -t<>τ; -u <> $vowel{υ; -ú <> $vowel{ύ; -ü <> $vowel{ϋ; -y<>υ; -ý<>ύ; -ÿ<>ϋ; -ch<>χ; -ô<>ώ; -ō<>ω; - -# extra english letters. mapped for completeness - -c}$softener>|s; -c>|k; -f>|ph; -h>|ch; -j>|i; -q>|k; -v>|u; -w>|u; - -# ==================================== -# Normal final rule: remove ' -# ==================================== - -#+ "''>;" - -# eof diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Hebrew.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Hebrew.utf8.txt deleted file mode 100755 index 5fc7c89b18c..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Hebrew.utf8.txt +++ /dev/null @@ -1,216 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 12:42:06 2001 -#-------------------------------------------------------------------- - -# Latin-Hebrew - - -# Variable names, derived from the Unicode names. -### $POINT_SHEVA=ְ; -### $POINT_HATAF_SEGOL=ֱ; -### $POINT_HATAF_PATAH=ֲ; -### $POINT_HATAF_QAMATS=ֳ; -### $POINT_HIRIQ=ִ; -### $POINT_TSERE=ֵ; -### $POINT_SEGOL=ֶ; -### $POINT_PATAH=ַ; -### $POINT_QAMATS=ָ; -### $POINT_HOLAM=ֹ; -### $POINT_QUBUTS=ֻ; -### $POINT_DAGESH_OR_MAPIQ=ּ; -### $POINT_METEG=ֽ; -### $PUNCTUATION_MAQAF=־; -### $POINT_RAFE=ֿ; -### $PUNCTUATION_PASEQ=׀; -### $POINT_SHIN_DOT=ׁ; -### $POINT_SIN_DOT=ׂ; -### $PUNCTUATION_SOF_PASUQ=׃; -### $ALEF=א; -### $BET=ב; -### $GIMEL=ג; -### $DALET=ד; -### $HE=ה; -### $VAV=ו; -### $ZAYIN=ז; -### $HET=ח; -### $TET=ט; -### $YOD=י; -### $FINAL_KAF=ך; -### $KAF=כ; -### $LAMED=ל; -### $FINAL_MEM=ם; -### $MEM=מ; -### $FINAL_NUN=ן; -### $NUN=נ; -### $SAMEKH=ס; -### $AYIN=ע; -### $FINAL_PE=ף; -### $PE=פ; -### $FINAL_TSADI=ץ; -### $TSADI=צ; -### $QOF=ק; -### $RESH=ר; -### $SHIN=ש; -### $TAV=ת; -### $YIDDISH_DOUBLE_VAV=װ; -### $YIDDISH_VAV_YOD=ױ; -### $YIDDISH_DOUBLE_YOD=ײ; -### $PUNCTUATION_GERESH=׳; -### $PUNCTUATION_GERSHAYIM=״; - -$letter=[a-zA-Z]; -$softvowel=[eiyEIY]; -$vowellike=[אעיו]; -$hebrew=[֐-׿]; # the whole block -liu - -# [Why is this a special case? -liu] -k''h <> כ ה ; - -# Mark non-final forms in final position as x~ -liu -k < כ } $hebrew ; -m < מ } $hebrew ; -n < נ } $hebrew ; -p < פ } $hebrew ; -ts < צ } $hebrew ; -k'~' <> כ ; -m'~' <> מ ; -n'~' <> נ ; -p'~' <> פ ; -ts'~'<> צ ; - -# Mark final forms in non-final position as x^ -liu -k'^' <> ך } $hebrew ; -m'^' <> ם } $hebrew ; -n'^' <> ן } $hebrew ; -p'^' <> ף } $hebrew ; -ts'^'<> ץ } $hebrew ; -k < ך; -m < ם; -n < ן; -p < ף; -ts < ץ; - -# Main rules -a<>א; -A>א; - -b<>ב; -B>ב; - -c}$softvowel>ס; -C}$softvowel>ס; -c}$letter>כ; -C}$letter>כ; -c>ך; -C>ך; - -d<>ד; -D>ד; - -e<>ע; -E>ע; - -f}$letter>פ; -f>ף; -F}$letter>פ; -F>ף; - -g<>ג; -G>ג; - -h<>ה; -H>ה; - -i>י; -I>י; - -j>דש; -J>דש; - -kh<>ח; -kH>ח; -Kh>ח; -KH>ח; -k}$letter>כ; -K}$letter>כ; -k>ך; -K>ך; - -l<>ל; -L>ל; - -m}$letter>מ; -m>ם; -M}$letter>מ; -M>ם; - -n}$letter>נ; -n>ן; -N}$letter>נ; -N>ן; - -o>ו; -O>ו; - -p}$letter>פ; -p>ף; -P}$letter>פ; -P>ף; - -q<>ק; -Q>ק; - -r<>ר; -R>ר; - -sh<>ש; -sH>ש; -Sh>ש; -SH>ש; -s''<ס}ה; -s<>ס; -S>ס; - -th<>ת; -tH>ת; -Th>ת; -TH>ת; -tS}$letter>צ; -ts}$letter>צ; -Ts}$letter>צ; -TS}$letter>צ; -tS>ץ; -ts>ץ; -Ts>ץ; -TS>ץ; -t''<ט}[ה ס ש]; -t<>ט; -T>ט; - -v<ו}$vowellike; -u<>ו; -U>ו; - -v>ו; -V>ו; - -w>ו; -W>ו; - -x>כס; -X>כס; - -y<>י; -Y>י; - -z<>ז; -Z>ז; - -# Delete stray apostrophes -''>; -<''; - -# eof diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Kana.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Kana.utf8.txt deleted file mode 100755 index 33f245c0997..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_Latin_Kana.utf8.txt +++ /dev/null @@ -1,969 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 12:18:46 2001 -#-------------------------------------------------------------------- - -# Latin-Kana - - -# Japanese hiragana and katakana to and from latin -# (romaji). Lower case latin corresponds to hiragana; -# upper case latin to katakana. The handling of -# Hiragana and Katakana is largely the same. The bulk -# of the transliterator consists of two identical sets -# of rules, differing only in case. - -# Because of minor differences between the two blocks -# (e.g., the existence of small katakana ka and ke, but -# no corresponding hiragana), some rules exist for only -# one script. - -# Uses modified Hepburn. Small changes to make -# unambiguous. - -#| Kunrei-shiki: Hepburn/MHepburn -#| ------------------------------ -#| si: shi -#| si ~ya: sha -#| si ~yu: shu -#| si ~yo: sho -#| zi: ji -#| zi ~ya: ja -#| zi ~yu: ju -#| zi ~yo: jo -#| ti: chi -#| ti ~ya: cha -#| ti ~yu: chu -#| ti ~yu: cho -#| tu: tsu -#| di: ji/dji -#| du: zu/dzu -#| hu: fu - -#| For foreign words: -#| ----------------- -#| se ~i si -#| si ~e she -#| -#| ze ~i zi -#| zi ~e je -#| -#| te ~i ti -#| ti ~e che -#| te ~u tu -#| -#| de ~i di -#| de ~u du -#| de ~i di -#| -#| he ~u: hu -#| hu ~a fa -#| hu ~i fi -#| hu ~e he -#| hu ~o ho - -# Most small forms are generated, but if necessary -# explicit small forms are given with ~a, ~ya, etc. - -#------------------------------------------------------ -# Variables - -$vowel=[aeiou]; -### $QUOTE=''; - -# Hiragana block - -### $a2=ぁ; -### $a=あ; -### $i2=ぃ; -### $i=い; -### $u2=ぅ; -### $u=う; -### $e2=ぇ; -### $e=え; -### $o2=ぉ; -### $o=お; - -### $ka=か; -### $ga=が; -### $ki=き; -### $gi=ぎ; -### $ku=く; -### $gu=ぐ; -### $ke=け; -### $ge=げ; -### $ko=こ; -### $go=ご; - -### $sa=さ; -### $za=ざ; -### $si=し; -### $zi=じ; -### $su=す; -### $zu=ず; -### $se=せ; -### $ze=ぜ; -### $so=そ; -### $zo=ぞ; - -### $ta=た; -### $da=だ; -### $ti=ち; -### $di=ぢ; -### $tu2=っ; -### $tu=つ; -### $du=づ; -### $te=て; -### $de=で; -### $to=と; -### $do=ど; - -### $na=な; -### $ni=に; -### $nu=ぬ; -### $ne=ね; -### $no=の; - -### $ha=は; -### $ba=ば; -### $pa=ぱ; -### $hi=ひ; -### $bi=び; -### $pi=ぴ; -### $hu=ふ; -### $bu=ぶ; -### $pu=ぷ; -### $he=へ; -### $be=べ; -### $pe=ぺ; -### $ho=ほ; -### $bo=ぼ; -### $po=ぽ; - -### $ma=ま; -### $mi=み; -### $mu=む; -### $me=め; -### $mo=も; - -### $ya2=ゃ; -### $ya=や; -### $yu2=ゅ; -### $yu=ゆ; -### $yo2=ょ; -### $yo=よ; - -### $ra=ら; -### $ri=り; -### $ru=る; -### $re=れ; -### $ro=ろ; - -### $wa2=ゎ; -### $wa=わ; -### $wi=ゐ; -### $we=ゑ; -### $wo=を; - -### $n=ん; -### $vu=ゔ; - -# Alternates, just to make the rules easier -### $yi2=ぃ; -### $yi=い; -### $ye2=ぇ; -### $ye=え; -### $wu=$u; -# End alternates - -# Katakana block - -### $A2=ァ; -### $A=ア; -### $I2=ィ; -### $I=イ; -### $U2=ゥ; -### $U=ウ; -### $E2=ェ; -### $E=エ; -### $O2=ォ; -### $O=オ; - -### $KA=カ; -### $GA=ガ; -### $KI=キ; -### $GI=ギ; -### $KU=ク; -### $GU=グ; -### $KE=ケ; -### $GE=ゲ; -### $KO=コ; -### $GO=ゴ; - -### $KA2=ヵ; # Small Katakana KA; no Hiragana equiv. -### $KE2=ヶ; # Small Katakana KE; no Hiragana equiv. - -### $SA=サ; -### $ZA=ザ; -### $SI=シ; -### $ZI=ジ; -### $SU=ス; -### $ZU=ズ; -### $SE=セ; -### $ZE=ゼ; -### $SO=ソ; -### $ZO=ゾ; - -### $TA=タ; -### $DA=ダ; -### $TI=チ; -### $DI=ヂ; -### $TU2=ッ; -### $TU=ツ; -### $DU=ヅ; -### $TE=テ; -### $DE=デ; -### $TO=ト; -### $DO=ド; - -### $NA=ナ; -### $NI=ニ; -### $NU=ヌ; -### $NE=ネ; -### $NO=ノ; - -### $HA=ハ; -### $BA=バ; -### $PA=パ; -### $HI=ヒ; -### $BI=ビ; -### $PI=ピ; -### $HU=フ; -### $BU=ブ; -### $PU=プ; -### $HE=ヘ; -### $BE=ベ; -### $PE=ペ; -### $HO=ホ; -### $BO=ボ; -### $PO=ポ; - -### $MA=マ; -### $MI=ミ; -### $MU=ム; -### $ME=メ; -### $MO=モ; - -### $YA2=ャ; -### $YA=ヤ; -### $YU2=ュ; -### $YU=ユ; -### $YO2=ョ; -### $YO=ヨ; -### $WA2=ヮ; - -# Alternates, just to make the rules easier -### $YI2=ィ; -### $YI=イ; -### $YE2=ェ; -### $YE=エ; -### $WU=$U; -# End alternates - -### $RA=ラ; -### $RI=リ; -### $RU=ル; -### $RE=レ; -### $RO=ロ; - -### $VA=ヷ; -### $VI=ヸ; -### $VU=ヴ; -### $VE=ヹ; -### $VO=ヺ; - -### $WA=ワ; -### $WI=ヰ; -### $WE=ヱ; -### $WO=ヲ; - -### $N=ン; -### $LONG=ー; - -# Variables used for doubled-consonants with tsu - -$K_START=[カキクケコかきくけこ]; -$G_START=[ガギグゲゴがぎぐげご]; - -$S_START=[サシスセソさしすせそ]; -$Z_START=[ザズゼゾざずぜぞ]; -$J_START=[ジじ]; - -$T_START=[タチツテトたちつてと]; -$D_START=[ダヂヅデドだぢづでど]; - -$N_START=[ナニヌネノなにぬねの]; - -$H_START=[ハヒヘホはひへほ]; -$F_START=[フふ]; -$B_START=[バビブベボばびぶべぼ]; -$P_START=[パピプペポぱぴぷぺぽ]; - -$M_START=[マミムメモまみむめも]; - -$Y_START=[ヤユヨやゆよ]; - -$R_START=[ラリルレロらりるれろ]; - -$W_START=[ワヰヱヲわゐゑを]; - -$V_START=[ヷヸヴヹヺゔ]; - -# If ン is followed by $N_QUOTER, then it needs an -# apostrophe after its romaji form to disambiguate it. -# E.g., ン ア != ナ, so represent as "n'a", not "na". - -$N_QUOTER = [ア イ ウ エ オ ナ ニ ヌ ネ ノ \ - ヤ ユ ヨ ン]; - -$n_quoter = [あ い う え お な に ぬ ね の \ - や ゆ よ ん]; - -# Lowercase copies for convenience in making hiragana -# rule set copy - -### $long = $LONG; -### $quote = $QUOTE; -### $k_start=$K_START; -### $g_start=$G_START; -### $s_start=$S_START; -### $z_start=$Z_START; -### $j_start=$J_START; -### $t_start=$T_START; -### $d_start=$D_START; -### $n_start=$N_START; -### $h_start=$H_START; -### $f_start=$F_START; -### $b_start=$B_START; -### $p_start=$P_START; -### $m_start=$M_START; -### $y_start=$Y_START; -### $r_start=$R_START; -### $w_start=$W_START; -### $v_start=$V_START; - -#------------------------------------------------------ -# Katakana rules - -# The rules immediately following are not shared. That -# is, they exist only for katakana, not for hiragana. - -VA<>ヷ; -VI<>ヸ; -VE<>ヹ; -VO<>ヺ; -'~KA'<>ヵ; -'~KE'<>ヶ; - -# ~~~ BEGIN shared rules ~~~ - -# The shared rules are copied from katakana to hiragana -# and then mechanically lowercased. - -A<>ア; - -BA<>バ; -BYA<ビャ; -BYI<ビィ; -BYU<ビュ; -BYE<ビェ; -BYO<ビョ; -BI<>ビ; -BU<>ブ; -BE<>ベ; -BO<>ボ; -BY>ビ|'~Y'; - -CHA<チャ; -CHI'~I'<チィ; # Liu -CHU<チュ; -CHE<チェ; -CHO<チョ; -CHI<>チ; -CH>チ|'~Y'; - -C}I>|S; -C}E>|S; - -DA<>ダ; -DI<>ディ; -DU<>デゥ; -DE<>デ; -DO<>ド; -DZU<>ヅ; -DJA<ヂャ; -DJI'~I'<ヂィ; # Liu -DJU<ヂュ; -DJE<ヂェ; -DJO<ヂョ; -DJI<>ヂ; -DJ>ヂ|'~Y'; - -E<>エ; - -FA<ファ; -FI<フィ; -FE<フェ; -FO<フォ; -FU<>フ; - -GA<>ガ; -GYA<ギャ; -GYI<ギィ; -GYU<ギュ; -GYE<ギェ; -GYO<ギョ; -GI<>ギ; -GU<>グ; -GE<>ゲ; -GO<>ゴ; -GY>ギ|'~Y'; - -HA<>ハ; -HI<>ヒ; -HU<>ヘゥ; -HE<>ヘ; -HO<>ホ; - -I<>イ; - -JA<ジャ; -JI'~I'<ジィ; # Liu -JU<ジュ; -JE<ジェ; -JO<ジョ; -JI<>ジ; - -KA<>カ; -KYA<キャ; -KYI<キィ; -KYU<キュ; -KYE<キェ; -KYO<キョ; -KI<>キ; -KU<>ク; -KE<>ケ; -KO<>コ; -KY>キ|'~Y'; - -MA<>マ; -MYA<ミャ; -MYI<ミィ; -MYU<ミュ; -MYE<ミェ; -MYO<ミョ; -MI<>ミ; -MU<>ム; -ME<>メ; -MO<>モ; -MY>ミ|'~Y'; - -M}P>ン; -M}B>ン; -M}F>ン; -M}V>ン; - -NA<>ナ; -NYA<ニャ; -NYI<ニィ; -NYU<ニュ; -NYE<ニェ; -NYO<ニョ; -NI<>ニ; -NU<>ヌ; -NE<>ネ; -NO<>ノ; -NY>ニ|'~Y'; - -O<>オ; - -PA<>パ; -PYA<ピャ; -PYI<ピィ; -PYU<ピュ; -PYE<ピェ; -PYO<ピョ; -PI<>ピ; -PU<>プ; -PE<>ペ; -PO<>ポ; -PY>ピ|'~Y'; - -RA<>ラ; -RYA<リャ; -RYI<リィ; -RYU<リュ; -RYE<リェ; -RYO<リョ; -RI<>リ; -RU<>ル; -RE<>レ; -RO<>ロ; -RY>リ|'~Y'; - -SA<>サ; -SI<>セィ; -SU<>ス; -SE<>セ; -SO<>ソ; - -SHA<シャ; -SHI'~I'<シィ; # Liu -SHU<シュ; -SHE<シェ; -SHO<ショ; -SHI<>シ; -SH>シ|'~Y'; - -TA<>タ; -TI<>ティ; -TU<>テゥ; -TE<>テ; -TO<>ト; - -# Double consonants - -B}B<>ッ}$B_START; -C}K>ッ; -C}C>ッ; -C}Q>ッ; -D}D<>ッ}$D_START; -F}F<>ッ}$F_START; -G}G<>ッ}$G_START; -H}H<>ッ}$H_START; -J}J<>ッ}$J_START; -K}K<>ッ}$K_START; -L}L>ッ; -M}M<>ッ}$M_START; -N}N<>ッ}$N_START; -P}P<>ッ}$P_START; -Q}Q>ッ; -R}R<>ッ}$R_START; -S}SH>ッ; -S}S<>ッ}$S_START; -T}CH>ッ; -T}T<>ッ}$T_START; -V}V<>ッ}$V_START; -W}W<>ッ}$W_START; -X}X>ッ; -Y}Y<>ッ}$Y_START; -Z}Z<>ッ}$Z_START; - -TSU<>ツ; - -U<>ウ; - -'V~A'<ヴァ; # Liu -'V~I'<ヴィ; # Liu -'V~E'<ヴェ; # Liu -'V~O'<ヴォ; # Liu -VU<>ヴ; - -WA<>ワ; -WI<>ヰ; -WU>ウ; -WE<>ヱ; -WO<>ヲ; - -YA<>ヤ; -YI>イ; -YU<>ユ; -YE>エ; -YO<>ヨ; - -ZA<>ザ; -ZI<>ゼィ; -ZU<>ズ; -ZE<>ゼ; -ZO<>ゾ; - -# Prolonged vowel mark. This indicates a doubling of -# the preceding vowel sound in both katakana and -# hiragana. - -Aァ; -'~I'<>ィ; -'~U'<>ゥ; -'~E'<>ェ; -'~O'<>ォ; -'~TSU'<>ッ; -'~WA'<>ヮ; -'~YA'<>ャ; -'~YI'>ィ; -'~YU'<>ュ; -'~YE'>ェ; -'~YO'<>ョ; - -# One-way latin->kana rules. These do not occur in -# well-formed romaji representing actual Japanese text. -# Their purpose is to make all romaji map to kana of -# some sort. - -# The following are not really necessary, but produce -# slightly more natural results. - -CY>セィ; -DY>ディ; -HY>ヒ; -SY>セィ; -TY>ティ; -ZY>ゼィ; - -# Simple substitutions using backup - -C>|K; -F>フ|'~'; -J>ジ|'~Y'; -L>|R; -Q>|K; -V>ヴ|'~'; -W>ウ|'~'; -X>|KS; - -# Isolated consonants listed here so as not to mask -# longer rules above. - -B>ブ; -D>デ; -G>グ; -H>ヘ; -K>ク; -M>ン; -N''<ン}$N_QUOTER; -N<>ン; -P>プ; -R>ル; -S>ス; -T>テ; -Y>イ; -Z>ズ; - -# ~~~ END shared rules ~~~ - -#------------------------------------------------------ -# Hiragana rules - -# Currently, there are no hiragana rules other than the -# shared rules. - -# ~~~ BEGIN shared rules ~~~ - -# The shared rules are copied from katakana to hiragana -# and then mechanically lowercased. - -a<>あ; - -ba<>ば; -bya<びゃ; -byi<びぃ; -byu<びゅ; -bye<びぇ; -byo<びょ; -bi<>び; -bu<>ぶ; -be<>べ; -bo<>ぼ; -by>び|'~y'; - -cha<ちゃ; -chi'~i'<ちぃ; # liu -chu<ちゅ; -che<ちぇ; -cho<ちょ; -chi<>ち; -ch>ち|'~y'; - -c}i>|s; -c}e>|s; - -da<>だ; -di<>でぃ; -du<>でぅ; -de<>で; -do<>ど; -dzu<>づ; -dja<ぢゃ; -dji'~i'<ぢぃ; # liu -dju<ぢゅ; -dje<ぢぇ; -djo<ぢょ; -dji<>ぢ; -dj>ぢ|'~y'; - -e<>え; - -fa<ふぁ; -fi<ふぃ; -fe<ふぇ; -fo<ふぉ; -fu<>ふ; - -ga<>が; -gya<ぎゃ; -gyi<ぎぃ; -gyu<ぎゅ; -gye<ぎぇ; -gyo<ぎょ; -gi<>ぎ; -gu<>ぐ; -ge<>げ; -go<>ご; -gy>ぎ|'~y'; - -ha<>は; -hi<>ひ; -hu<>へぅ; -he<>へ; -ho<>ほ; - -i<>い; - -ja<じゃ; -ji'~i'<じぃ; # liu -ju<じゅ; -je<じぇ; -jo<じょ; -ji<>じ; - -ka<>か; -kya<きゃ; -kyi<きぃ; -kyu<きゅ; -kye<きぇ; -kyo<きょ; -ki<>き; -ku<>く; -ke<>け; -ko<>こ; -ky>き|'~y'; - -ma<>ま; -mya<みゃ; -myi<みぃ; -myu<みゅ; -mye<みぇ; -myo<みょ; -mi<>み; -mu<>む; -me<>め; -mo<>も; -my>み|'~y'; - -m}p>ん; -m}b>ん; -m}f>ん; -m}v>ん; - -na<>な; -nya<にゃ; -nyi<にぃ; -nyu<にゅ; -nye<にぇ; -nyo<にょ; -ni<>に; -nu<>ぬ; -ne<>ね; -no<>の; -ny>に|'~y'; - -o<>お; - -pa<>ぱ; -pya<ぴゃ; -pyi<ぴぃ; -pyu<ぴゅ; -pye<ぴぇ; -pyo<ぴょ; -pi<>ぴ; -pu<>ぷ; -pe<>ぺ; -po<>ぽ; -py>ぴ|'~y'; - -ra<>ら; -rya<りゃ; -ryi<りぃ; -ryu<りゅ; -rye<りぇ; -ryo<りょ; -ri<>り; -ru<>る; -re<>れ; -ro<>ろ; -ry>り|'~y'; - -sa<>さ; -si<>せぃ; -su<>す; -se<>せ; -so<>そ; - -sha<しゃ; -shi'~i'<しぃ; # liu -shu<しゅ; -she<しぇ; -sho<しょ; -shi<>し; -sh>し|'~y'; - -ta<>た; -ti<>てぃ; -tu<>てぅ; -te<>て; -to<>と; - -# double consonants - -b}b<>っ}$B_START; -c}k>っ; -c}c>っ; -c}q>っ; -d}d<>っ}$D_START; -f}f<>っ}$F_START; -g}g<>っ}$G_START; -h}h<>っ}$H_START; -j}j<>っ}$J_START; -k}k<>っ}$K_START; -l}l>っ; -m}m<>っ}$M_START; -n}n<>っ}$N_START; -p}p<>っ}$P_START; -q}q>っ; -r}r<>っ}$R_START; -s}sh>っ; -s}s<>っ}$S_START; -t}ch>っ; -t}t<>っ}$T_START; -v}v<>っ}$V_START; -w}w<>っ}$W_START; -x}x>っ; -y}y<>っ}$Y_START; -z}z<>っ}$Z_START; - -tsu<>つ; - -u<>う; - -'v~a'<ゔぁ; # liu -'v~i'<ゔぃ; # liu -'v~e'<ゔぇ; # liu -'v~o'<ゔぉ; # liu -vu<>ゔ; - -wa<>わ; -wi<>ゐ; -wu>う; -we<>ゑ; -wo<>を; - -ya<>や; -yi>い; -yu<>ゆ; -ye>え; -yo<>よ; - -za<>ざ; -zi<>ぜぃ; -zu<>ず; -ze<>ぜ; -zo<>ぞ; - -# prolonged vowel mark. this indicates a doubling of -# the preceding vowel sound in both katakana and -# hiragana. - -aぁ; -'~i'<>ぃ; -'~u'<>ぅ; -'~e'<>ぇ; -'~o'<>ぉ; -'~tsu'<>っ; -'~wa'<>ゎ; -'~ya'<>ゃ; -'~yi'>ぃ; -'~yu'<>ゅ; -'~ye'>ぇ; -'~yo'<>ょ; - -# one-way latin->kana rules. these do not occur in -# well-formed romaji representing actual japanese text. -# their purpose is to make all romaji map to kana of -# some sort. - -# the following are not really necessary, but produce -# slightly more natural results. - -cy>せぃ; -dy>でぃ; -hy>ひ; -sy>せぃ; -ty>てぃ; -zy>ぜぃ; - -# simple substitutions using backup - -c>|k; -f>ふ|'~'; -j>じ|'~y'; -l>|r; -q>|k; -v>ゔ|'~'; -w>う|'~'; -x>|ks; - -# isolated consonants listed here so as not to mask -# longer rules above. - -b>ぶ; -d>で; -g>ぐ; -h>へ; -k>く; -m>ん; -n''<ん}$n_quoter; -n<>ん; -p>ぷ; -r>る; -s>す; -t>て; -y>い; -z>ず; - -# ~~~ END shared rules ~~~ - -#------------------------------------------------------ -# Final cleanup - -'~'>; # delete stray tildes -''>; # delete stray quotes -'-'>ー; - -# eof diff --git a/icu4j/src/com/ibm/text/resources/Transliterator_StraightQuotes_CurlyQuotes.utf8.txt b/icu4j/src/com/ibm/text/resources/Transliterator_StraightQuotes_CurlyQuotes.utf8.txt deleted file mode 100755 index df4ef91d7d4..00000000000 --- a/icu4j/src/com/ibm/text/resources/Transliterator_StraightQuotes_CurlyQuotes.utf8.txt +++ /dev/null @@ -1,77 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2001, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# Date: Tue Jan 23 12:42:07 2001 -#-------------------------------------------------------------------- - -# StraightQuotes-CurlyQuotes - -# Rewritten using character codes [LIU] -$white=[[:Zs:][:Zl:][:Zp:]]; -$black=[^$white]; -$open=[:Ps:]; -### $dquote='\"'; - -### $lAng=〈; -### $ldAng=《; -### $lBrk='['; -### $lBrc='{'; - -### $lquote=‘; -### $rquote=’; -### $ldquote=“; -### $rdquote=”; - -### $ldguill=«; -### $rdguill=»; -### $lguill=‹; -### $rguill=›; - -### $mdash=—; - -######################################## -# Conversions from input -######################################## - -# join single quotes -‘''>“; -‘‘>“; -’''>”; -’’>”; - -#smart single quotes -$white{''>‘; -$open{''>‘; -$black{''>’; -''>‘; - -#smart doubles -$white{'\"'>“; -$open{'\"'>“; -$black{'\"'>”; -'\"'>“; - -# join single guillemets -››>»; -'>>'>»; -‹‹>«; -'<<'>«; - -# prevent double spaces -\\ {\\ >; - -# join hyphens into dash ### BIDIRECTIONAL ### -'--'<>—; - -######################################## -# Conversions back to input -######################################## - -#smart quotes -''<‘; -''<’; -'\"'<“; -'\"'<”; - -# eof