ICU-1426 move el rules to locale resource
X-SVN-Rev: 6588
This commit is contained in:
Alan Liu
parent
87387a13d1
commit
eda7ce7b44
240
icu4j/src/com/ibm/icu/impl/data/LocaleElements_el.java
Executable file
240
icu4j/src/com/ibm/icu/impl/data/LocaleElements_el.java
Executable file
@ -0,0 +1,240 @@
|
||||
/**************************************************************************
|
||||
* Copyright (C) 1996-2001, International Business Machines Corporation and
|
||||
* others. All Rights Reserved.
|
||||
**************************************************************************
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/impl/data/Attic/LocaleElements_el.java,v $
|
||||
* $Date: 2001/11/02 19:59:11 $
|
||||
* $Revision: 1.1 $
|
||||
**************************************************************************
|
||||
*/
|
||||
|
||||
package com.ibm.text.resources;
|
||||
|
||||
import java.util.ListResourceBundle;
|
||||
|
||||
public class LocaleElements_el extends ListResourceBundle {
|
||||
/**
|
||||
* Overrides ListResourceBundle
|
||||
*/
|
||||
public Object[][] getContents() {
|
||||
return new Object[][] {
|
||||
{ "Transliterate_Latin",
|
||||
new String[] { "UNGEGN",
|
||||
|
||||
"# Rules are predicated on running NFD first, and NFC afterwards\n"+
|
||||
"::NFD (NFC) ; "+
|
||||
|
||||
"# For modern Greek.\n"+
|
||||
|
||||
"# Useful variables\n"+
|
||||
|
||||
"$lower = [:Ll:] ; "+
|
||||
"$upper = [:Lu:] ; "+
|
||||
"$accent = [:M:] ; "+
|
||||
|
||||
"$macron = \u0304 ;"+
|
||||
"$ddot = \u0308 ;"+
|
||||
|
||||
"$lcgvowel = [\u03b1\u03b5\u03b7\u03b9\u03bf\u03c5\u03c9] ; "+
|
||||
"$ucgvowel = [\u0391\u0395\u0397\u0399\u039f\u03a5\u03a9] ; "+
|
||||
"$gvowel = [$lcgvowel $ucgvowel] ; "+
|
||||
"$lcgvowelC = [$lcgvowel $accent] ; "+
|
||||
|
||||
"$evowel = [aeiouyAEIOUY];"+
|
||||
"$vowel = [ $evowel $gvowel] ; "+
|
||||
|
||||
"$beforeLower = $accent * $lower ; "+
|
||||
|
||||
"$gammaLike = [\u0393\u039a\u039e\u03a7\u03b3\u03ba\u03be\u03c7\u03f0] ; "+
|
||||
"$egammaLike = [GKXCgkxc] ; "+
|
||||
"$smooth = \u0313 ; "+
|
||||
"$rough = \u0314 ; "+
|
||||
"$iotasub = \u0345 ; "+
|
||||
|
||||
"$softener = [\u03b2\u0392\u03b3\u0393\u03b4\u0394\u03b6\u0396\u03bb\u039b\u03bc\u039c\u03bd\u039d\u03c1\u03a1$gvowel] ;"+
|
||||
|
||||
"$under = \u0331;"+
|
||||
|
||||
"$caron = \u030C;"+
|
||||
|
||||
"$afterLetter = [:^L:] [\\'[:M:]]* ;"+
|
||||
"$beforeLetter = [\\'[:M:]]* [:^L:] ;"+
|
||||
|
||||
|
||||
"# Fix punctuation\n"+
|
||||
|
||||
"\\; <> \\? ;"+
|
||||
"\u00b7 <> \\: ;"+
|
||||
|
||||
"# Fix any ancient characters that creep in\n"+
|
||||
|
||||
"\u0342 > \u0301 ;"+
|
||||
"\u0302 > \u0301 ;"+
|
||||
"\u0300 > \u0301 ;"+
|
||||
"$smooth > ;"+
|
||||
"$rough > ;"+
|
||||
"$iotasub > ;"+
|
||||
"\u037A > ;"+
|
||||
|
||||
"# need to have these up here so the rules don't mask\n"+
|
||||
|
||||
"\u03b7 <> i $under ;"+
|
||||
"\u0397 <> I $under ;"+
|
||||
|
||||
"\u03a8 } $beforeLower <> Ps ; "+
|
||||
"\u03a8 <> PS ; "+
|
||||
"\u03c8 <> ps ; "+
|
||||
|
||||
"\u03c9 <> o $under ;"+
|
||||
"\u03a9 <> O $under;"+
|
||||
|
||||
"# at begining or end of word, convert mp to b\n"+
|
||||
|
||||
"[^[:L:][:M:]] } \u03bc\u03c0 > b ; "+
|
||||
"\u03bc\u03c0 } [^[:L:][:M:]] > b ; "+
|
||||
"[^[:L:][:M:]] } [\u039c\u03bc][\u03a0\u03c0] > B ; "+
|
||||
"[\u039c\u03bc][\u03a0\u03c0] } [^[:L:][:M:]] > B ;"+
|
||||
|
||||
"\u03bc\u03c0 < b ; "+
|
||||
"\u039c\u03c0 < B { $beforeLower ; "+
|
||||
"\u039c\u03a0 < B ; "+
|
||||
|
||||
"# handle diphthongs ending with upsilon\n"+
|
||||
|
||||
"$vowel { \u03c5 } $softener <> v $under ; "+
|
||||
"$vowel { \u03c5 } <> f $under; "+
|
||||
"\u03c5 <> y ; "+
|
||||
"$vowel { \u03a5 } $softener <> V $under ; "+
|
||||
"$vowel { \u03a5 <> U $under ; "+
|
||||
"\u03a5 <> Y ; "+
|
||||
|
||||
"# NORMAL\n"+
|
||||
|
||||
"\u03b1 <> a ; "+
|
||||
"\u0391 <> A ; "+
|
||||
|
||||
"\u03b2 <> v ; "+
|
||||
"\u0392 <> V ; "+
|
||||
|
||||
"\u03b3 } $gammaLike <> n } $egammaLike ; "+
|
||||
"\u03b3 <> g ; "+
|
||||
"\u0393 } $gammaLike <> N } $egammaLike ; "+
|
||||
"\u0393 <> G ; "+
|
||||
|
||||
"\u03b4 <> d ; "+
|
||||
"\u0394 <> D ; "+
|
||||
|
||||
"\u03b5 <> e ; "+
|
||||
"\u0395 <> E ; "+
|
||||
|
||||
"\u03b6 <> z ; "+
|
||||
"\u0396 <> Z ; "+
|
||||
|
||||
"\u03b8 <> th ; "+
|
||||
"\u0398 } $beforeLower <> Th ; "+
|
||||
"\u0398 <> TH ; "+
|
||||
|
||||
"\u03b9 <> i ; "+
|
||||
"\u0399 <> I ; "+
|
||||
|
||||
"\u03ba <> k ;"+
|
||||
"\u039a <> K ; "+
|
||||
|
||||
"\u03bb <> l ; "+
|
||||
"\u039b <> L ; "+
|
||||
|
||||
"\u03bc <> m ; "+
|
||||
"\u039c <> M ; "+
|
||||
|
||||
"\u03bd } $gammaLike > n\\' ; "+
|
||||
"\u03bd <> n ; "+
|
||||
"\u039d } $gammaLike <> N\\' ; "+
|
||||
"\u039d <> N ; "+
|
||||
|
||||
"\u03be <> x ; "+
|
||||
"\u039e <> X ; "+
|
||||
|
||||
"\u03bf <> o ; "+
|
||||
"\u039f <> O ; "+
|
||||
|
||||
"\u03c0 <> p ; "+
|
||||
"\u03a0 <> P ; "+
|
||||
|
||||
"\u03c1 <> r ; "+
|
||||
"\u03a1 <> R ; "+
|
||||
|
||||
"[Pp] { } \u03c2 > \\' ; "+
|
||||
"[Pp] { } \u03c3 > \\' ;"+
|
||||
|
||||
"# Caron means exception\n"+
|
||||
|
||||
"# before a letter, initial\n"+
|
||||
"\u03c2 } $beforeLetter <> s $caron } $beforeLetter;"+
|
||||
"\u03c3 } $beforeLetter <> s } $beforeLetter;"+
|
||||
|
||||
"# otherwise, after a letter = final\n"+
|
||||
"$afterLetter { \u03c3 <> $afterLetter { s $caron;"+
|
||||
"$afterLetter { \u03c2 <> $afterLetter { s ;"+
|
||||
|
||||
"# otherwise (isolated) = initial\n"+
|
||||
"\u03c2 <> s $caron;"+
|
||||
"\u03c3 <> s ;"+
|
||||
|
||||
"[Pp] { \u03a3 <> \\'S ; "+
|
||||
"\u03a3 <> S ; "+
|
||||
|
||||
"\u03c4 <> t ; "+
|
||||
"\u03a4 <> T ; "+
|
||||
|
||||
"\u03c6 <> f ; "+
|
||||
"\u03a6 <> F ;"+
|
||||
|
||||
"\u03c7 <> ch ; "+
|
||||
"\u03a7 } $beforeLower <> Ch ; "+
|
||||
"\u03a7 <> CH ; "+
|
||||
|
||||
"# Completeness for ASCII\n"+
|
||||
|
||||
"$ignore = [[:Mark:]''] * ;"+
|
||||
|
||||
"| ch < h ;"+
|
||||
"| k < c ;"+
|
||||
"| i < j ;"+
|
||||
"| k < q ;"+
|
||||
"| y < u ;"+
|
||||
"| y < w ;"+
|
||||
|
||||
"| Ch < H ;"+
|
||||
"| K < C ;"+
|
||||
"| I < J ;"+
|
||||
"| K < Q ;"+
|
||||
"| Y < W ;"+
|
||||
"| Y < U ;"+
|
||||
|
||||
"# Completeness for Greek\n"+
|
||||
|
||||
"\u03d0 > | \u03b2 ;"+
|
||||
"\u03d1 > | \u03b8 ;"+
|
||||
"\u03d2 > | \u03a5 ;"+
|
||||
"\u03d5 > | \u03c6 ;"+
|
||||
"\u03d6 > | \u03c0 ;"+
|
||||
|
||||
"\u03f0 > | \u03ba ;"+
|
||||
"\u03f1 > | \u03c1 ;"+
|
||||
"\u03f2 > | \u03c3 ;"+
|
||||
"\u03f3 > j ;"+
|
||||
"\u03f4 > | \u0398 ;"+
|
||||
"\u03f5 > | \u03b5 ;"+
|
||||
|
||||
"# delete any trailing ' marks used for roundtripping\n"+
|
||||
|
||||
" < [\u03a0\u03c0] { \\' } [Ss] ;"+
|
||||
" < [\u039d\u03bd] { \\' } $egammaLike ;"+
|
||||
|
||||
"::NFC (NFD) ; "
|
||||
|
||||
}
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
@ -48,8 +48,8 @@ Cyrillic-Latin:file:Transliterator_Cyrillic_Latin.txt:UTF8:FORWARD
|
||||
Latin-Greek:file:Transliterator_Greek_Latin.txt:UTF8:REVERSE
|
||||
Greek-Latin:file:Transliterator_Greek_Latin.txt:UTF8:FORWARD
|
||||
|
||||
Latin-el:file:Transliterator_el_Latin.txt:UTF8:REVERSE
|
||||
el-Latin:file:Transliterator_el_Latin.txt:UTF8:FORWARD
|
||||
Latin-Greek/UNGEGN:alias:Latin-el/UNGEGN
|
||||
Greek-Latin/UNGEGN:alias:el-Latin/UNGEGN
|
||||
|
||||
LowerLatin-Jamo:internal:Transliterator_Latin_Jamo.txt:UTF8:FORWARD
|
||||
Latin-Jamo:alias:[:Latin:]Any-Lower;LowerLatin-Jamo
|
||||
|
||||
240
icu4j/src/com/ibm/text/resources/LocaleElements_el.java
Executable file
240
icu4j/src/com/ibm/text/resources/LocaleElements_el.java
Executable file
@ -0,0 +1,240 @@
|
||||
/**************************************************************************
|
||||
* Copyright (C) 1996-2001, International Business Machines Corporation and
|
||||
* others. All Rights Reserved.
|
||||
**************************************************************************
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/LocaleElements_el.java,v $
|
||||
* $Date: 2001/11/02 19:59:11 $
|
||||
* $Revision: 1.1 $
|
||||
**************************************************************************
|
||||
*/
|
||||
|
||||
package com.ibm.text.resources;
|
||||
|
||||
import java.util.ListResourceBundle;
|
||||
|
||||
public class LocaleElements_el extends ListResourceBundle {
|
||||
/**
|
||||
* Overrides ListResourceBundle
|
||||
*/
|
||||
public Object[][] getContents() {
|
||||
return new Object[][] {
|
||||
{ "Transliterate_Latin",
|
||||
new String[] { "UNGEGN",
|
||||
|
||||
"# Rules are predicated on running NFD first, and NFC afterwards\n"+
|
||||
"::NFD (NFC) ; "+
|
||||
|
||||
"# For modern Greek.\n"+
|
||||
|
||||
"# Useful variables\n"+
|
||||
|
||||
"$lower = [:Ll:] ; "+
|
||||
"$upper = [:Lu:] ; "+
|
||||
"$accent = [:M:] ; "+
|
||||
|
||||
"$macron = \u0304 ;"+
|
||||
"$ddot = \u0308 ;"+
|
||||
|
||||
"$lcgvowel = [\u03b1\u03b5\u03b7\u03b9\u03bf\u03c5\u03c9] ; "+
|
||||
"$ucgvowel = [\u0391\u0395\u0397\u0399\u039f\u03a5\u03a9] ; "+
|
||||
"$gvowel = [$lcgvowel $ucgvowel] ; "+
|
||||
"$lcgvowelC = [$lcgvowel $accent] ; "+
|
||||
|
||||
"$evowel = [aeiouyAEIOUY];"+
|
||||
"$vowel = [ $evowel $gvowel] ; "+
|
||||
|
||||
"$beforeLower = $accent * $lower ; "+
|
||||
|
||||
"$gammaLike = [\u0393\u039a\u039e\u03a7\u03b3\u03ba\u03be\u03c7\u03f0] ; "+
|
||||
"$egammaLike = [GKXCgkxc] ; "+
|
||||
"$smooth = \u0313 ; "+
|
||||
"$rough = \u0314 ; "+
|
||||
"$iotasub = \u0345 ; "+
|
||||
|
||||
"$softener = [\u03b2\u0392\u03b3\u0393\u03b4\u0394\u03b6\u0396\u03bb\u039b\u03bc\u039c\u03bd\u039d\u03c1\u03a1$gvowel] ;"+
|
||||
|
||||
"$under = \u0331;"+
|
||||
|
||||
"$caron = \u030C;"+
|
||||
|
||||
"$afterLetter = [:^L:] [\\'[:M:]]* ;"+
|
||||
"$beforeLetter = [\\'[:M:]]* [:^L:] ;"+
|
||||
|
||||
|
||||
"# Fix punctuation\n"+
|
||||
|
||||
"\\; <> \\? ;"+
|
||||
"\u00b7 <> \\: ;"+
|
||||
|
||||
"# Fix any ancient characters that creep in\n"+
|
||||
|
||||
"\u0342 > \u0301 ;"+
|
||||
"\u0302 > \u0301 ;"+
|
||||
"\u0300 > \u0301 ;"+
|
||||
"$smooth > ;"+
|
||||
"$rough > ;"+
|
||||
"$iotasub > ;"+
|
||||
"\u037A > ;"+
|
||||
|
||||
"# need to have these up here so the rules don't mask\n"+
|
||||
|
||||
"\u03b7 <> i $under ;"+
|
||||
"\u0397 <> I $under ;"+
|
||||
|
||||
"\u03a8 } $beforeLower <> Ps ; "+
|
||||
"\u03a8 <> PS ; "+
|
||||
"\u03c8 <> ps ; "+
|
||||
|
||||
"\u03c9 <> o $under ;"+
|
||||
"\u03a9 <> O $under;"+
|
||||
|
||||
"# at begining or end of word, convert mp to b\n"+
|
||||
|
||||
"[^[:L:][:M:]] } \u03bc\u03c0 > b ; "+
|
||||
"\u03bc\u03c0 } [^[:L:][:M:]] > b ; "+
|
||||
"[^[:L:][:M:]] } [\u039c\u03bc][\u03a0\u03c0] > B ; "+
|
||||
"[\u039c\u03bc][\u03a0\u03c0] } [^[:L:][:M:]] > B ;"+
|
||||
|
||||
"\u03bc\u03c0 < b ; "+
|
||||
"\u039c\u03c0 < B { $beforeLower ; "+
|
||||
"\u039c\u03a0 < B ; "+
|
||||
|
||||
"# handle diphthongs ending with upsilon\n"+
|
||||
|
||||
"$vowel { \u03c5 } $softener <> v $under ; "+
|
||||
"$vowel { \u03c5 } <> f $under; "+
|
||||
"\u03c5 <> y ; "+
|
||||
"$vowel { \u03a5 } $softener <> V $under ; "+
|
||||
"$vowel { \u03a5 <> U $under ; "+
|
||||
"\u03a5 <> Y ; "+
|
||||
|
||||
"# NORMAL\n"+
|
||||
|
||||
"\u03b1 <> a ; "+
|
||||
"\u0391 <> A ; "+
|
||||
|
||||
"\u03b2 <> v ; "+
|
||||
"\u0392 <> V ; "+
|
||||
|
||||
"\u03b3 } $gammaLike <> n } $egammaLike ; "+
|
||||
"\u03b3 <> g ; "+
|
||||
"\u0393 } $gammaLike <> N } $egammaLike ; "+
|
||||
"\u0393 <> G ; "+
|
||||
|
||||
"\u03b4 <> d ; "+
|
||||
"\u0394 <> D ; "+
|
||||
|
||||
"\u03b5 <> e ; "+
|
||||
"\u0395 <> E ; "+
|
||||
|
||||
"\u03b6 <> z ; "+
|
||||
"\u0396 <> Z ; "+
|
||||
|
||||
"\u03b8 <> th ; "+
|
||||
"\u0398 } $beforeLower <> Th ; "+
|
||||
"\u0398 <> TH ; "+
|
||||
|
||||
"\u03b9 <> i ; "+
|
||||
"\u0399 <> I ; "+
|
||||
|
||||
"\u03ba <> k ;"+
|
||||
"\u039a <> K ; "+
|
||||
|
||||
"\u03bb <> l ; "+
|
||||
"\u039b <> L ; "+
|
||||
|
||||
"\u03bc <> m ; "+
|
||||
"\u039c <> M ; "+
|
||||
|
||||
"\u03bd } $gammaLike > n\\' ; "+
|
||||
"\u03bd <> n ; "+
|
||||
"\u039d } $gammaLike <> N\\' ; "+
|
||||
"\u039d <> N ; "+
|
||||
|
||||
"\u03be <> x ; "+
|
||||
"\u039e <> X ; "+
|
||||
|
||||
"\u03bf <> o ; "+
|
||||
"\u039f <> O ; "+
|
||||
|
||||
"\u03c0 <> p ; "+
|
||||
"\u03a0 <> P ; "+
|
||||
|
||||
"\u03c1 <> r ; "+
|
||||
"\u03a1 <> R ; "+
|
||||
|
||||
"[Pp] { } \u03c2 > \\' ; "+
|
||||
"[Pp] { } \u03c3 > \\' ;"+
|
||||
|
||||
"# Caron means exception\n"+
|
||||
|
||||
"# before a letter, initial\n"+
|
||||
"\u03c2 } $beforeLetter <> s $caron } $beforeLetter;"+
|
||||
"\u03c3 } $beforeLetter <> s } $beforeLetter;"+
|
||||
|
||||
"# otherwise, after a letter = final\n"+
|
||||
"$afterLetter { \u03c3 <> $afterLetter { s $caron;"+
|
||||
"$afterLetter { \u03c2 <> $afterLetter { s ;"+
|
||||
|
||||
"# otherwise (isolated) = initial\n"+
|
||||
"\u03c2 <> s $caron;"+
|
||||
"\u03c3 <> s ;"+
|
||||
|
||||
"[Pp] { \u03a3 <> \\'S ; "+
|
||||
"\u03a3 <> S ; "+
|
||||
|
||||
"\u03c4 <> t ; "+
|
||||
"\u03a4 <> T ; "+
|
||||
|
||||
"\u03c6 <> f ; "+
|
||||
"\u03a6 <> F ;"+
|
||||
|
||||
"\u03c7 <> ch ; "+
|
||||
"\u03a7 } $beforeLower <> Ch ; "+
|
||||
"\u03a7 <> CH ; "+
|
||||
|
||||
"# Completeness for ASCII\n"+
|
||||
|
||||
"$ignore = [[:Mark:]''] * ;"+
|
||||
|
||||
"| ch < h ;"+
|
||||
"| k < c ;"+
|
||||
"| i < j ;"+
|
||||
"| k < q ;"+
|
||||
"| y < u ;"+
|
||||
"| y < w ;"+
|
||||
|
||||
"| Ch < H ;"+
|
||||
"| K < C ;"+
|
||||
"| I < J ;"+
|
||||
"| K < Q ;"+
|
||||
"| Y < W ;"+
|
||||
"| Y < U ;"+
|
||||
|
||||
"# Completeness for Greek\n"+
|
||||
|
||||
"\u03d0 > | \u03b2 ;"+
|
||||
"\u03d1 > | \u03b8 ;"+
|
||||
"\u03d2 > | \u03a5 ;"+
|
||||
"\u03d5 > | \u03c6 ;"+
|
||||
"\u03d6 > | \u03c0 ;"+
|
||||
|
||||
"\u03f0 > | \u03ba ;"+
|
||||
"\u03f1 > | \u03c1 ;"+
|
||||
"\u03f2 > | \u03c3 ;"+
|
||||
"\u03f3 > j ;"+
|
||||
"\u03f4 > | \u0398 ;"+
|
||||
"\u03f5 > | \u03b5 ;"+
|
||||
|
||||
"# delete any trailing ' marks used for roundtripping\n"+
|
||||
|
||||
" < [\u03a0\u03c0] { \\' } [Ss] ;"+
|
||||
" < [\u039d\u03bd] { \\' } $egammaLike ;"+
|
||||
|
||||
"::NFC (NFD) ; "
|
||||
|
||||
}
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
@ -1,220 +0,0 @@
|
||||
#--------------------------------------------------------------------
|
||||
# Copyright (c) 1999-2001, International Business Machines
|
||||
# Corporation and others. All Rights Reserved.
|
||||
#--------------------------------------------------------------------
|
||||
# $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/Transliterator_el_Latin.txt,v $
|
||||
# $Date: 2001/11/02 19:07:06 $
|
||||
# $Revision: 1.2 $
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
# Rules are predicated on running NFD first, and NFC afterwards
|
||||
::NFD (NFC) ;
|
||||
|
||||
# For modern Greek.
|
||||
|
||||
# Useful variables
|
||||
|
||||
$lower = [:Ll:] ;
|
||||
$upper = [:Lu:] ;
|
||||
$accent = [:M:] ;
|
||||
|
||||
$macron = \u0304 ;
|
||||
$ddot = \u0308 ;
|
||||
|
||||
$lcgvowel = [αεηιουω] ;
|
||||
$ucgvowel = [ΑΕΗΙΟΥΩ] ;
|
||||
$gvowel = [$lcgvowel $ucgvowel] ;
|
||||
$lcgvowelC = [$lcgvowel $accent] ;
|
||||
|
||||
$evowel = [aeiouyAEIOUY];
|
||||
$vowel = [ $evowel $gvowel] ;
|
||||
|
||||
$beforeLower = $accent * $lower ;
|
||||
|
||||
$gammaLike = [ΓΚΞΧγκξχϰ] ;
|
||||
$egammaLike = [GKXCgkxc] ;
|
||||
$smooth = ̓ ;
|
||||
$rough = ̔ ;
|
||||
$iotasub = ͅ ;
|
||||
|
||||
$softener = [βΒγΓδΔζΖλΛμΜνΝρΡ$gvowel] ;
|
||||
|
||||
$under = \u0331;
|
||||
|
||||
$caron = \u030C;
|
||||
|
||||
$afterLetter = [:^L:] [\'[:M:]]* ;
|
||||
$beforeLetter = [\'[:M:]]* [:^L:] ;
|
||||
|
||||
|
||||
# Fix punctuation
|
||||
|
||||
\; <> \? ;
|
||||
· <> \: ;
|
||||
|
||||
# Fix any ancient characters that creep in
|
||||
|
||||
\u0342 > \u0301 ;
|
||||
\u0302 > \u0301 ;
|
||||
\u0300 > \u0301 ;
|
||||
$smooth > ;
|
||||
$rough > ;
|
||||
$iotasub > ;
|
||||
\u037A > ;
|
||||
|
||||
# need to have these up here so the rules don't mask
|
||||
|
||||
η <> i $under ;
|
||||
Η <> I $under ;
|
||||
|
||||
Ψ } $beforeLower <> Ps ;
|
||||
Ψ <> PS ;
|
||||
ψ <> ps ;
|
||||
|
||||
ω <> o $under ;
|
||||
Ω <> O $under;
|
||||
|
||||
# at begining or end of word, convert mp to b
|
||||
|
||||
[^[:L:][:M:]] } μπ > b ;
|
||||
μπ } [^[:L:][:M:]] > b ;
|
||||
[^[:L:][:M:]] } [Μμ][Ππ] > B ;
|
||||
[Μμ][Ππ] } [^[:L:][:M:]] > B ;
|
||||
|
||||
μπ < b ;
|
||||
Μπ < B { $beforeLower ;
|
||||
ΜΠ < B ;
|
||||
|
||||
# handle diphthongs ending with upsilon
|
||||
|
||||
$vowel { υ } $softener <> v $under ;
|
||||
$vowel { υ } <> f $under;
|
||||
υ <> y ;
|
||||
$vowel { Υ } $softener <> V $under ;
|
||||
$vowel { Υ <> U $under ;
|
||||
Υ <> Y ;
|
||||
|
||||
# NORMAL
|
||||
|
||||
α <> a ;
|
||||
Α <> A ;
|
||||
|
||||
β <> v ;
|
||||
Β <> V ;
|
||||
|
||||
γ } $gammaLike <> n } $egammaLike ;
|
||||
γ <> g ;
|
||||
Γ } $gammaLike <> N } $egammaLike ;
|
||||
Γ <> G ;
|
||||
|
||||
δ <> d ;
|
||||
Δ <> D ;
|
||||
|
||||
ε <> e ;
|
||||
Ε <> E ;
|
||||
|
||||
ζ <> z ;
|
||||
Ζ <> Z ;
|
||||
|
||||
θ <> th ;
|
||||
Θ } $beforeLower <> Th ;
|
||||
Θ <> TH ;
|
||||
|
||||
ι <> i ;
|
||||
Ι <> I ;
|
||||
|
||||
κ <> k ;
|
||||
Κ <> K ;
|
||||
|
||||
λ <> l ;
|
||||
Λ <> L ;
|
||||
|
||||
μ <> m ;
|
||||
Μ <> M ;
|
||||
|
||||
ν } $gammaLike > n\' ;
|
||||
ν <> n ;
|
||||
Ν } $gammaLike <> N\' ;
|
||||
Ν <> N ;
|
||||
|
||||
ξ <> x ;
|
||||
Ξ <> X ;
|
||||
|
||||
ο <> o ;
|
||||
Ο <> O ;
|
||||
|
||||
π <> p ;
|
||||
Π <> P ;
|
||||
|
||||
ρ <> r ;
|
||||
Ρ <> R ;
|
||||
|
||||
[Pp] { } ς > \' ;
|
||||
[Pp] { } σ > \' ;
|
||||
|
||||
# Caron means exception
|
||||
|
||||
# before a letter, initial
|
||||
ς } $beforeLetter <> s $caron } $beforeLetter;
|
||||
σ } $beforeLetter <> s } $beforeLetter;
|
||||
|
||||
# otherwise, after a letter = final
|
||||
$afterLetter { σ <> $afterLetter { s $caron;
|
||||
$afterLetter { ς <> $afterLetter { s ;
|
||||
|
||||
# otherwise (isolated) = initial
|
||||
ς <> s $caron;
|
||||
σ <> s ;
|
||||
|
||||
[Pp] { Σ <> \'S ;
|
||||
Σ <> S ;
|
||||
|
||||
τ <> t ;
|
||||
Τ <> T ;
|
||||
|
||||
φ <> f ;
|
||||
Φ <> F ;
|
||||
|
||||
χ <> ch ;
|
||||
Χ } $beforeLower <> Ch ;
|
||||
Χ <> CH ;
|
||||
|
||||
# Completeness for ASCII
|
||||
|
||||
$ignore = [[:Mark:]''] * ;
|
||||
|
||||
| ch < h ;
|
||||
| k < c ;
|
||||
| i < j ;
|
||||
| k < q ;
|
||||
| y < u ;
|
||||
| y < w ;
|
||||
|
||||
| Ch < H ;
|
||||
| K < C ;
|
||||
| I < J ;
|
||||
| K < Q ;
|
||||
| Y < W ;
|
||||
| Y < U ;
|
||||
|
||||
# Completeness for Greek
|
||||
|
||||
ϐ > | β ;
|
||||
ϑ > | θ ;
|
||||
ϒ > | Υ ;
|
||||
ϕ > | φ ;
|
||||
ϖ > | π ;
|
||||
|
||||
ϰ > | κ ;
|
||||
ϱ > | ρ ;
|
||||
ϲ > | σ ;
|
||||
ϳ > j ;
|
||||
ϴ > | Θ ;
|
||||
ϵ > | ε ;
|
||||
|
||||
# delete any trailing ' marks used for roundtripping
|
||||
|
||||
< [Ππ] { \' } [Ss] ;
|
||||
< [Νν] { \' } $egammaLike ;
|
||||
|
||||
::NFC (NFD) ;
|
||||
@ -48,8 +48,8 @@ Cyrillic-Latin:file:Transliterator_Cyrillic_Latin.txt:UTF8:FORWARD
|
||||
Latin-Greek:file:Transliterator_Greek_Latin.txt:UTF8:REVERSE
|
||||
Greek-Latin:file:Transliterator_Greek_Latin.txt:UTF8:FORWARD
|
||||
|
||||
Latin-el:file:Transliterator_el_Latin.txt:UTF8:REVERSE
|
||||
el-Latin:file:Transliterator_el_Latin.txt:UTF8:FORWARD
|
||||
Latin-Greek/UNGEGN:alias:Latin-el/UNGEGN
|
||||
Greek-Latin/UNGEGN:alias:el-Latin/UNGEGN
|
||||
|
||||
LowerLatin-Jamo:internal:Transliterator_Latin_Jamo.txt:UTF8:FORWARD
|
||||
Latin-Jamo:alias:[:Latin:]Any-Lower;LowerLatin-Jamo
|
||||
|
||||
Loading…
Reference in New Issue
Block a user